Add release v1.1.0

Only update DockerHub `latest` images on mainline release

Fixes #1383.

.gitignore

@@ -6,6 +6,7 @@
 # Folders
 _obj
 _test
+.vagrant
 
 # Architecture specific extensions/prefixes
 *.[568vq]
@@ -22,12 +23,40 @@ _testmain.go
 *.exe
 *.test
 *.prof
+profile.cov
+coverage.html
 
 # Emacs backup files
 *~
 
+# Vim backup files
+*.swp
+
 # Project specific
-weaver/weaver
-weavedns/weavedns
+prog/weaver/weaver
+prog/weavedns/weavedns
+prog/weavehosts/weavehosts
+prog/weaveproxy/weaveproxy
+prog/sigproxy/sigproxy
+prog/weavewait/weavewait
+prog/netcheck/netcheck
+testing/cover/cover
+testing/runner/runner
 tools/bin
+tools/build
 releases
+.weaver.uptodate
+.weavedns.uptodate
+.weaveexec.uptodate
+weave.tar
+prog/weaveexec/weave
+prog/weaveexec/weavehosts
+prog/weaveexec/weaveproxy
+prog/weaveexec/weavewait
+prog/weaveexec/sigproxy
+prog/weaveexec/netcheck
+prog/weaveexec/docker*.tgz
+Vagrantfile.local
+test/tls/*.pem
+test/coverage
+test/coverage.*

.travis.yml

@@ -0,0 +1,29 @@
+language: go
+sudo: false
+go:
+  - 1.4
+
+env:
+  - PATH="${PATH}:${HOME}/.local/bin"
+
+addons:
+  apt:
+    packages:
+    - libpcap-dev
+
+install:
+  - go clean -i net
+  - go install -tags netgo std
+  - go get github.com/golang/lint/golint
+  - pip install --user --upgrade gsutil
+  - bin/setup-ci-secrets $encrypted_5ba036e89377_key $encrypted_5ba036e89377_iv
+  - make travis
+  - go get ./...
+
+script:
+  - bin/lint .
+  - make tests
+
+after_success:
+  - go get github.com/mattn/goveralls
+  - test "${TRAVIS_PULL_REQUEST}" = "false" && site/build-and-publish.sh

CHANGELOG.md

@@ -1,3 +1,192 @@
+## Release v1.1.0
+
+**Highlights**:
+
+- `weave launch` now launches all weave components, simplifying
+  startup.
+- `weave status` has been completely revamped, with a much improved
+  presentation of the information, and the option to select and output
+  data in JSON.
+- weaveDNS has been rewritten and embedded in the router. The new
+  implementation simplifies configuration, improves performance, and
+  provides fault resilience for services.
+- the weave Docker API proxy now provides an even more seamless user
+  experience, and enables easier integration of weave with other
+  systems such as kubernetes.
+- many usability improvements
+- a few minor bug fixes, including a couple of security
+  vulnerabilities
+
+More details in the
+[change log](https://github.com/weaveworks/weave/issues?q=milestone%3A1.1.0).
+
+## Release 1.0.3
+
+This release contains a weaveDNS feature enhancement as well as minor fixes for
+improved stability and robustness.
+
+More details in the
+[change log](https://github.com/weaveworks/weave/issues?q=milestone%3A1.0.3).
+
+The release is fully compatible with other 1.0.x versions, so existing
+clusters can be upgraded incrementally.
+
+## Release 1.0.2
+
+This release fixes a number of bugs, including some security
+vulnerabilities in the Weave Docker API proxy, hangs and failures in
+address allocation, and sporadic failures in name resolution.
+
+More details in the
+[change log](https://github.com/weaveworks/weave/issues?q=milestone%3A1.0.2).
+
+The release is fully compatible with other 1.0.x versions, so existing
+clusters can be upgraded incrementally.
+
+## Release 1.0.1
+
+This is a bug fix release, addressing the following issue:
+
+- executing `docker run` from a Docker 1.7 client against the weave
+  proxy would report a `no such image` error when the requested image
+  wasn't present on the Docker host, instead of downloading it.
+
+## Release 1.0.0
+
+**Highlights**:
+
+- It is now easier than ever to start containers and for them to
+  communicate, across multiple hosts. Automatic IP address allocation,
+  and name resolution via weaveDNS are now enabled by default, and the
+  proxy has become more fully-featured. In short, once weave has been
+  launched the following is possible:
+
+      ````
+      host1$ docker run --name=pingme -dti ubuntu
+      host2$ docker run -ti ubuntu
+      root@d11e9287f65b:/# ping pingme
+      ````
+- Containers can now be
+  [load-balanced](http://docs.weave.works/weave/latest_release/weavedns.html#load-balancing)
+  easily.
+- IP address allocation is now available across [multiple
+  subnets](http://docs.weave.works/weave/latest_release/ipam.html#range),
+  and hence can be employed when running multiple, isolated
+  applications.
+- The proxy now supports [TLS
+  connections](http://docs.weave.works/weave/latest_release/proxy.html#tls),
+  enabling its deployment when the communication between docker
+  clients and the server must be secured.
+
+There are many other new features, plus the usual assortment of bug
+fixes and improvements under the hood. More detail below and in the
+[change log](https://github.com/weaveworks/weave/issues?q=milestone%3A1.0.0).
+
+*NB: This release changes the weave protocol version. Therefore, when
+ upgrading an existing installation, all hosts need to be upgraded in
+ order to for them to be able to communicate and form a network.*
+
+## Release 0.11.2
+
+This is a bug fix release, addressing the following issues:
+
+- `weave run` did not respect DOCKER_CLIENT_ARGS. #855
+- Negative result cache did not expire if requeried within TTL. #845
+
+More details in the [change
+log](https://github.com/weaveworks/weave/issues?q=milestone%3A0.11.2).
+
+*NB: This release does not change the weave protocol version.
+Therefore, when upgrading an existing 0.11 installation incrementally,
+connectivity between peers will be retained.*
+
+## Release 0.11.1
+
+This is a bug fix release, addressing the following issues:
+
+- The IP Allocator could crash in some relatively rare
+  circumstances. #782/#783.
+- When the proxy failed to attach a container to the weave network,
+  there was no failure indication and descriptive error anywhere, and
+  the application process would still start. Now an error is reported
+  to the client (i.e. typically the Docker CLI), recorded in the proxy
+  logs, and the container is terminated. #788/#799.
+- `weave launch-proxy --with-ipam` failed to configure the entrypoint
+  and DNS unless a (possibly blank) `WEAVE_CIDR` was
+  specified. Affected containers could start the application process
+  w/o the weave network interface being available, and without
+  functioning name resolution for the weaveDNS domain.
+  #744/#747/#751/#752
+- The `weave status` output for the IP Allocator was misleadingly
+  conveying a sense of brokenness when no IP allocation requests had
+  been made yet. #787/#801
+- When invoking `weave launch-proxy` twice, the second invocation
+  would output a blank line and terminate with a success exit
+  status. Now it reports that the proxy is already running and exits
+  with a non-zero status. #767/#780
+- `weave launch-proxy` was not respecting WEAVEPROXY_DOCKER_ARGS, so
+  any user-supplied custom configuration for the weaveproxy container
+  was ignored. #755/#780
+- The proxy was not intercepting API calls to the unversioned (1.0)
+  Docker Remote API. Hence none of the weave functionality was
+  available when Docker clients were using that version of the
+  API. #770/#774/#777,#809
+- The proxy would crash when certain elements of the
+  `/containers/create` JSON were missing. We are not aware of any
+  Docker clients doing this, but it's been fixed regardless. #778/#777
+
+More details in the [change
+log](https://github.com/weaveworks/weave/issues?q=milestone%3A0.11.1).
+
+*NB: This release does not change the weave protocol version.
+Therefore, when upgrading an existing 0.11 installation incrementally,
+connectivity between peers will be retained.*
+
+## Release 0.11.0
+
+**Highlights**:
+
+- **automatic IP Address Management (IPAM)**, which allows application
+  containers to be started and attached to the weave network without
+  needing to supply an IP address.
+- **proxy** for automatically attaching containers started with
+  ordinary `docker run`, or the Docker remote API, to the weave
+  network.
+- ability to **add/remove extra DNS records**.
+- performance and scalability improvements
+- fixes for a small number of bugs discovered during testing
+
+More detail in the [change log](https://github.com/weaveworks/weave/issues?q=milestone%3A0.11.0)
+
+*NB: This release changes the weave protocol version. Therefore, when
+upgrading an existing installation, all hosts need to be upgraded in
+order to for them to be able to communicate and form a network.*
+
+## Release 0.10.0
+
+**Highlights**:
+
+- **bug fixes**, in particular eradicating several deadlocks that could
+  cause peer connection failures and hangs.
+- **performance and scalability improvements** to the weave control plane,
+  as a result of which it is now possible to construct much larger
+  weave networks than previously.
+- **improved installation and administration**, particularly the
+  introduction of remote execution of the weave script in a container,
+  permitting fully containerised deployment of weave.
+- **improved diagnostics**, such as the reporting of connection failures
+  in `weave status`.
+- **new weaveDNS features**, most notably the caching of DNS records
+  for application containers, which makes finding container IP
+  addresses via weaveDNS much faster.
+
+More detail in the [change log](https://github.com/weaveworks/weave/issues?q=milestone%3A0.10.0)
+
+*NB: This release changes the Weave Docker image names. To upgrade
+from an older version, 1) stop all application containers, 2) run
+`weave reset` from the old version to remove all traces of weave, and
+only then 3) install the new version.*
+
 ## Release 0.9.0
 
 - Improve WeaveDNS to the point where it can act as the name server
@@ -8,11 +197,11 @@
 - Adapt to changes in topology - adding & removing of weave peers,
   disruption of connectivity - more rapidly.
 
-- Cope with delays delays in downloading/running docker
-  images/containers required for weave operation.
+- Cope with delays in downloading/running docker images/containers
+  required for weave operation.
 
 See the
-[complete change log](https://github.com/zettio/weave/issues?q=milestone%3A0.9.0)
+[complete change log](https://github.com/weaveworks/weave/issues?q=milestone%3A0.9.0)
 for more details.
 
 ## Release 0.8.0
@@ -39,9 +228,9 @@ This is the first release assigned a version number.
 
 When downloading weave you now have the following choices...
 
-1. a specific version, e.g. https://github.com/zettio/weave/releases/download/v0.7.0/weave
-2. latest released version: https://github.com/zettio/weave/releases/download/latest_release/weave
-3. most recent 'master' commit: https://raw.githubusercontent.com/zettio/weave/master/weave
+1. a specific version, e.g. https://github.com/weaveworks/weave/releases/download/v0.7.0/weave
+2. latest released version: https://github.com/weaveworks/weave/releases/download/latest_release/weave
+3. most recent 'master' commit: https://raw.githubusercontent.com/weaveworks/weave/master/weave
 
 Previously the only documented download location was (3). We recommend
 that any automated scripts using that be changed to either (1) or (2).

LICENSE

@@ -176,7 +176,7 @@
 
    END OF TERMS AND CONDITIONS
 
-   Copyright 2014 Zettio Ltd.
+   Copyright 2014-2015 Weaveworks Ltd.
 
    Licensed under the Apache License, Version 2.0 (the "License");
    you may not use this file except in compliance with the License.

Makefile

@@ -1,71 +1,132 @@
-PUBLISH=publish_weave publish_weavedns publish_weavetools
+PUBLISH=publish_weave publish_weaveexec
 
 .DEFAULT: all
-.PHONY: all update tests publish $(PUBLISH) clean
+.PHONY: all update tests publish $(PUBLISH) clean prerequisites build travis run-smoketests
 
 # If you can use docker without being root, you can do "make SUDO="
 SUDO=sudo
 
-DOCKERHUB_USER=zettio
+DOCKERHUB_USER=weaveworks
 WEAVE_VERSION=git-$(shell git rev-parse --short=12 HEAD)
-WEAVER_EXE=weaver/weaver
-WEAVEDNS_EXE=weavedns/weavedns
-WEAVETOOLS_EXES=tools/bin
-WEAVER_IMAGE=$(DOCKERHUB_USER)/weave
-WEAVEDNS_IMAGE=$(DOCKERHUB_USER)/weavedns
-WEAVETOOLS_IMAGE=$(DOCKERHUB_USER)/weavetools
-WEAVER_EXPORT=/var/tmp/weave.tar
-WEAVEDNS_EXPORT=/var/tmp/weavedns.tar
-WEAVETOOLS_EXPORT=/var/tmp/weavetools.tar
 
-all: $(WEAVER_EXPORT) $(WEAVEDNS_EXPORT) $(WEAVETOOLS_EXPORT)
+WEAVER_EXE=prog/weaver/weaver
+WEAVEPROXY_EXE=prog/weaveproxy/weaveproxy
+SIGPROXY_EXE=prog/sigproxy/sigproxy
+WEAVEWAIT_EXE=prog/weavewait/weavewait
+WEAVEHOSTS_EXE=prog/weavehosts/weavehosts
+NETCHECK_EXE=prog/netcheck/netcheck
+COVER_EXE=testing/cover/cover
+RUNNER_EXE=testing/runner/runner
+
+EXES=$(WEAVER_EXE) $(SIGPROXY_EXE) $(WEAVEPROXY_EXE) $(WEAVEWAIT_EXE) $(WEAVEHOSTS_EXE) $(NETCHECK_EXE) $(COVER_EXE) $(RUNNER_EXE)
+
+WEAVER_UPTODATE=.weaver.uptodate
+WEAVEEXEC_UPTODATE=.weaveexec.uptodate
+
+IMAGES_UPTODATE=$(WEAVER_UPTODATE) $(WEAVEEXEC_UPTODATE)
+
+WEAVER_IMAGE=$(DOCKERHUB_USER)/weave
+WEAVEEXEC_IMAGE=$(DOCKERHUB_USER)/weaveexec
+
+IMAGES=$(WEAVER_IMAGE) $(WEAVEEXEC_IMAGE)
+
+WEAVE_EXPORT=weave.tar
+
+WEAVEEXEC_DOCKER_VERSION=1.3.1
+DOCKER_DISTRIB=prog/weaveexec/docker-$(WEAVEEXEC_DOCKER_VERSION).tgz
+DOCKER_DISTRIB_URL=https://get.docker.com/builds/Linux/x86_64/docker-$(WEAVEEXEC_DOCKER_VERSION).tgz
+NETGO_CHECK=@strings $@ | grep cgo_stub\\\.go >/dev/null || { \
+	rm $@; \
+	echo "\nYour go standard library was built without the 'netgo' build tag."; \
+	echo "To fix that, run"; \
+	echo "    sudo go clean -i net"; \
+	echo "    sudo go install -tags netgo std"; \
+	false; \
+}
+BUILD_FLAGS=-ldflags "-extldflags \"-static\" -X main.version $(WEAVE_VERSION)" -tags netgo
+
+all: $(WEAVE_EXPORT) $(COVER_EXE) $(RUNNER_EXE)
+
+travis: $(EXES)
 
 update:
-	go get -u -f -v -tags -netgo ./$(dir $(WEAVER_EXE)) ./$(dir $(WEAVEDNS_EXE))
+	go get -u -f -v -tags -netgo $(addprefix ./,$(dir $(EXES)))
 
-$(WEAVER_EXE) $(WEAVEDNS_EXE): common/*.go
+$(WEAVER_EXE) $(WEAVEPROXY_EXE): common/*.go common/*/*.go net/*.go
+ifeq ($(COVERAGE),true)
+	$(eval COVERAGE_MODULES := $(shell (go list ./$(@D); go list -f '{{join .Deps "\n"}}' ./$(@D) | grep "weaveworks") | paste -s -d,))
+	go get -t -tags netgo ./$(@D)
+	go test -c -o ./$@ $(BUILD_FLAGS) -v -covermode=atomic -coverpkg $(COVERAGE_MODULES) ./$(@D)/
+else
 	go get -tags netgo ./$(@D)
-	go build -ldflags "-extldflags \"-static\" -X main.version $(WEAVE_VERSION)" -tags netgo -o $@ ./$(shell dirname $@)
-	@strings $@ | grep cgo_stub\\\.go >/dev/null || { \
-		rm $@; \
-		echo "\nYour go standard library was built without the 'netgo' build tag."; \
-		echo "To fix that, run"; \
-		echo "    sudo go clean -i net"; \
-		echo "    sudo go install -tags netgo std"; \
-		false; \
-	}
+	go build $(BUILD_FLAGS) -o $@ ./$(@D)
+endif
+	$(NETGO_CHECK)
 
-$(WEAVER_EXE): router/*.go weaver/main.go
-$(WEAVEDNS_EXE): nameserver/*.go weavedns/main.go
+$(NETCHECK_EXE): common/*.go common/*/*.go net/*.go
+	go get -tags netgo ./$(@D)
+	go build $(BUILD_FLAGS) -o $@ ./$(@D)
+	$(NETGO_CHECK)
 
-$(WEAVETOOLS_EXES): tools/build.sh
-	$(SUDO) docker run --rm -v $(realpath $(<D)):/home/weave ubuntu sh /home/weave/build.sh
+$(WEAVER_EXE): router/*.go ipam/*.go ipam/*/*.go nameserver/*.go prog/weaver/*.go
+$(WEAVEPROXY_EXE): proxy/*.go prog/weaveproxy/main.go
+$(NETCHECK_EXE): prog/netcheck/netcheck.go
 
-$(WEAVER_EXPORT): weaver/Dockerfile $(WEAVER_EXE)
-	$(SUDO) docker build -t $(WEAVER_IMAGE) weaver
-	$(SUDO) docker save $(WEAVER_IMAGE):latest > $@
+# Sigproxy and weavewait need separate rules as they fail the netgo check in
+# the main build stanza due to not importing net package
+$(SIGPROXY_EXE): prog/sigproxy/main.go
+$(WEAVEWAIT_EXE): prog/weavewait/main.go net/*.go
+$(WEAVEHOSTS_EXE): prog/weavehosts/weavehosts.go
+$(COVER_EXE): testing/cover/cover.go
+$(RUNNER_EXE): testing/runner/runner.go
 
-$(WEAVEDNS_EXPORT): weavedns/Dockerfile $(WEAVEDNS_EXE)
-	$(SUDO) docker build -t $(WEAVEDNS_IMAGE) weavedns
-	$(SUDO) docker save $(WEAVEDNS_IMAGE):latest > $@
+$(WEAVEWAIT_EXE) $(SIGPROXY_EXE) $(WEAVEHOSTS_EXE) $(COVER_EXE) $(RUNNER_EXE):
+	go get ./$(@D)
+	go build -o $@ ./$(@D)
 
-$(WEAVETOOLS_EXPORT): tools/Dockerfile $(WEAVETOOLS_EXES)
-	$(SUDO) docker build -t $(WEAVETOOLS_IMAGE) tools
-	$(SUDO) docker save $(WEAVETOOLS_IMAGE):latest > $@
+$(WEAVER_UPTODATE): prog/weaver/Dockerfile $(WEAVER_EXE)
+	$(SUDO) docker build -t $(WEAVER_IMAGE) prog/weaver
+	touch $@
 
-# Add more directories in here as more tests are created
-tests:
-	cd router; go test -tags netgo
-	cd nameserver; go test -tags netgo
+$(WEAVEEXEC_UPTODATE): prog/weaveexec/Dockerfile $(DOCKER_DISTRIB) weave $(SIGPROXY_EXE) $(WEAVEPROXY_EXE) $(WEAVEWAIT_EXE) $(WEAVEHOSTS_EXE) $(NETCHECK_EXE)
+	cp weave prog/weaveexec/weave
+	cp $(SIGPROXY_EXE) prog/weaveexec/sigproxy
+	cp $(WEAVEPROXY_EXE) prog/weaveexec/weaveproxy
+	cp $(WEAVEWAIT_EXE) prog/weaveexec/weavewait
+	cp $(WEAVEHOSTS_EXE) prog/weaveexec/weavehosts
+	cp $(NETCHECK_EXE) prog/weaveexec/netcheck
+	cp $(DOCKER_DISTRIB) prog/weaveexec/docker.tgz
+	$(SUDO) docker build -t $(WEAVEEXEC_IMAGE) prog/weaveexec
+	touch $@
 
-$(PUBLISH): publish_%:
-	$(SUDO) docker tag  $(DOCKERHUB_USER)/$* $(DOCKERHUB_USER)/$*:$(WEAVE_VERSION)
-	$(SUDO) docker push $(DOCKERHUB_USER)/$*:$(WEAVE_VERSION)
-	$(SUDO) docker push $(DOCKERHUB_USER)/$*:latest
+$(WEAVE_EXPORT): $(IMAGES_UPTODATE)
+	$(SUDO) docker save $(addsuffix :latest,$(IMAGES)) > $@
+
+$(DOCKER_DISTRIB):
+	curl -o $(DOCKER_DISTRIB) $(DOCKER_DISTRIB_URL)
+
+tests: $(COVER_EXE)
+	@test/units.sh
+
+$(PUBLISH): publish_%: $(IMAGES_UPTODATE)
+	$(SUDO) docker tag -f $(DOCKERHUB_USER)/$* $(DOCKERHUB_USER)/$*:$(WEAVE_VERSION)
+	$(SUDO) docker push   $(DOCKERHUB_USER)/$*:$(WEAVE_VERSION)
+ifneq ($(UPDATE_LATEST),false)
+	$(SUDO) docker push   $(DOCKERHUB_USER)/$*:latest
+endif
 
 publish: $(PUBLISH)
 
 clean:
-	-$(SUDO) docker rmi $(WEAVER_IMAGE) $(WEAVEDNS_IMAGE) $(WEAVETOOLS_IMAGE)
-	rm -f $(WEAVER_EXE) $(WEAVEDNS_EXE) $(WEAVER_EXPORT) $(WEAVEDNS_EXPORT) $(WEAVETOOLS_EXPORT)
-	$(SUDO) rm -rf $(WEAVETOOLS_EXES)
+	-$(SUDO) docker rmi $(IMAGES)
+	go clean -r ./...
+	rm -f $(EXES) $(IMAGES_UPTODATE) $(WEAVE_EXPORT)
+	rm -rf test/tls/*.pem test/coverage.* test/coverage
+
+build:
+	$(SUDO) go clean -i net
+	$(SUDO) go install -tags netgo std
+	$(MAKE)
+
+run-smoketests: all
+	cd test && ./setup.sh && ./run_all.sh

NOTICE

@@ -1,3 +1,3 @@
 Weave
-Copyright 2012-2014 Zettio Ltd.
-This product includes software developed at Zettio Ltd.
+Copyright 2014-2015 Weaveworks Ltd.
+This product includes software developed at Weaveworks Ltd.

README.md

@@ -1,7 +1,22 @@
-# Weave - the Docker network
+# Weave - weaving containers into applications
+
+[![Build Status](https://travis-ci.org/weaveworks/weave.svg?branch=master)](https://travis-ci.org/weaveworks/weave) [![Integration Tests](https://circleci.com/gh/weaveworks/weave/tree/master.svg?style=shield&circle-token=4933c7dabb3d0383e62117565cb9d16df7b1a811)](https://circleci.com/gh/weaveworks/weave) [![Coverage Status](https://coveralls.io/repos/weaveworks/weave/badge.svg)](https://coveralls.io/r/weaveworks/weave)
+
+# About Weaveworks
+
+[Weaveworks](http://weave.works) is the company that develops Weave -
+the most productive way for developers to connect, observe and control
+Docker containers. To learn about our products, including getting
+started tutorials, visit our [website](http://weave.works), read about
+the
+[1.0 release of Weave](http://blog.weave.works/2015/06/18/weave-1-0-is-out-and-it-is-good/),
+visit our [documentation](http://docs.weave.works) or continue to read
+about some of the more technical aspects of Weave in this readme.
+
+# Weave
 
 Weave creates a virtual network that connects Docker containers
-deployed across multiple hosts.
+deployed across multiple hosts and enables their automatic discovery.
 
 ![Weave Virtual Network](/docs/virtual-network.png?raw=true "Weave Virtual Network")
 
@@ -27,16 +42,20 @@ capabilities, so these can continue to be used by containers.
 
 ## Installation
 
-Ensure you are running Linux (kernel 3.5 or later) and have Docker
-(version 0.9.1 or later) installed. Then install weave with
+Ensure you are running Linux (kernel 3.8 or later) and have Docker
+(version 1.3.1 or later) installed. Then install weave with
 
-    sudo wget -O /usr/local/bin/weave \
-      https://github.com/zettio/weave/releases/download/latest_release/weave
+    sudo curl -L git.io/weave -o /usr/local/bin/weave
     sudo chmod a+x /usr/local/bin/weave
 
+CoreOS users see [here](https://github.com/fintanr/weave-gs/blob/master/coreos-simple/user-data) for an example of installing weave using cloud-config.
+
+Weave respects the environment variable `DOCKER_HOST`, so you can run
+it locally to control a weave network on a remote host.
+
 ## Quick Start Screencast
 
-<a href="http://youtu.be/k6r7yuSr0hE" alt="Click to watch the screencast" target="_blank">
+<a href="https://youtu.be/BF9YJSPQUcY" alt="Click to watch the screencast" target="_blank">
   <img src="/docs/hello-screencast.png" />
 </a>
 
@@ -46,94 +65,91 @@ Say you have docker running on two hosts, accessible to each other as
 `$HOST1` and `$HOST2`, and want to deploy an application consisting of
 two containers, one on each host.
 
-On `$HOST1` run (as root)
+On $HOST1 we run:
 
-    host1# weave launch
-    host1# C=$(weave run 10.0.1.1/24 -t -i ubuntu)
+    host1$ weave launch
+    host1$ eval $(weave env)
+    host1$ docker run --name a1 -ti ubuntu
 
-The first line starts the weave router, in a container. This needs to
-be done once on each host. The required docker image for the weave
-router container is downloaded automatically. There is also a `weave
-setup` command for downloading this and other images required for
-weave operation; this is a strictly optional step which is especially
-useful for automated installation of weave and ensures that any
-subsequent weave commands do not encounter delays due to image
-downloading.
+> NB: If the first command results in an error like
+> `http:///var/run/docker.sock/v1.19/containers/create: dial unix
+> /var/run/docker.sock: permission denied. Are you trying to connect
+> to a TLS-enabled daemon without TLS?` then you likely need to be
+> 'root' in order to connect to the Docker daemon. If so, run the
+> above and all subsequent commands in a *single* root shell (e.g. one
+> created with `sudo -s`). Do *not* prefix individual commands with
+> `sudo`, since some commands modify environment entries and hence
+> they all need to be executed from the same shell.
 
-The second line runs our application container. We give it an IP
-address and network, in
-[CIDR notation](http://en.wikipedia.org/wiki/Classless_Inter-Domain_Routing#CIDR_notation).
-`weave run` invokes `docker run -d` with all the parameters following
-the IP address and network. So we could be launching any container
-this way; here we just take a stock ubuntu container and launch a
-shell in it. There's also a `weave start` command, which invokes
-`docker start` for starting existing containers.
+The first line runs weave. The second line configures our environment
+so that containers launched via the docker command line are
+automatically attached to the weave network. Finally, we run our
+application container.
 
-If our application consists of more than one container on this host we
-simply launch them with a variation on that second line.
+That's it! If our application consists of more than one container on
+this host we simply launch them with `docker run` as appropriate.
 
-The IP addresses and netmasks can be anything you like, but make sure
-they don't conflict with any IP ranges in use on the hosts or IP
-addresses of external services the hosts or containers need to connect
-to. The same IP range must be used everywhere, and the individual IP
-addresses must, of course, be unique.
+Next we repeat similar steps on `$HOST2`...
 
-We repeat similar steps on `$HOST2`...
+    host2$ weave launch $HOST1
+    host2$ eval $(weave env)
+    host2$ docker run --name a2 -ti ubuntu
 
-    host2# weave launch $HOST1
-    host2# C=$(weave run 10.0.1.2/24 -t -i ubuntu)
-
-The only difference, apart from the choice of IP address for the
-application container, is that we tell our weave that it should peer
-with the weave on `$HOST1` (specified as the IP address or hostname, and
-optional `:port`, by which `$HOST2` can reach it). NB: if there is a
-firewall between `$HOST1` and `$HOST2`, you must open port 6783 for TCP
-and UDP.
+The only difference, apart from the name of the application container,
+is that we tell our weave that it should peer with the weave on
+`$HOST1` (specified as the IP address or hostname, and optional
+`:port`, by which `$HOST2` can reach it). NB: if there is a firewall
+between `$HOST1` and `$HOST2`, you must open the weave port (6783 by
+default; this can be overriden by setting `WEAVE_PORT`) for TCP and
+UDP.
 
 Note that we could instead have told the weave on `$HOST1` to connect to
 `$HOST2`, or told both about each other. Order does not matter here;
 weave automatically (re)connects to peers when they become
 available. Also, we can tell weave to connect to multiple peers by
 supplying multiple addresses, separated by spaces. And we can
-[add peers dynamically](http://zettio.github.io/weave/features.html#dynamic-topologies).
+[add peers dynamically](http://docs.weave.works/weave/latest_release/features.html#dynamic-topologies).
+
+Weave must be started once per host. The relevant container images are
+pulled down on demand, but if you wish you can preload them by running
+`weave setup` - this is particularly useful for automated deployments,
+and ensures that there are no delays during later operations.
 
 Now that we've got everything set up, let's see whether our containers
 can talk to each other...
 
-On `$HOST1`...
+In the container started on `$HOST1`...
 
-    host1# docker attach $C
-    root@28841bd02eff:/# ping -c 1 -q 10.0.1.2
-    PING 10.0.1.2 (10.0.1.2): 48 data bytes
-    --- 10.0.1.2 ping statistics ---
-    1 packets transmitted, 1 packets received, 0% packet loss
-    round-trip min/avg/max/stddev = 1.048/1.048/1.048/0.000 ms
+    root@a1:/# ping -c 1 -q a2
+    PING a2.weave.local (10.40.0.2) 56(84) bytes of data.
+    --- a2.weave.local ping statistics ---
+    1 packets transmitted, 1 received, 0% packet loss, time 0ms
+    rtt min/avg/max/mdev = 0.341/0.341/0.341/0.000 ms
 
-Similarly, on `$HOST2`...
+Similarly, in the container started on `$HOST2`...
 
-    host2# docker attach $C
-    root@f76829496120:/# ping -c 1 -q 10.0.1.1
-    PING 10.0.1.1 (10.0.1.1): 48 data bytes
-    --- 10.0.1.1 ping statistics ---
-    1 packets transmitted, 1 packets received, 0% packet loss
-    round-trip min/avg/max/stddev = 1.034/1.034/1.034/0.000 ms
+    root@a2:/# ping -c 1 -q a1
+    PING a1.weave.local (10.32.0.2) 56(84) bytes of data.
+    --- a1.weave.local ping statistics ---
+    1 packets transmitted, 1 received, 0% packet loss, time 0ms
+    rtt min/avg/max/mdev = 0.366/0.366/0.366/0.000 ms
 
 So there we have it, two containers on separate hosts happily talking
 to each other.
 
 ## Find out more
 
- * [Documentation homepage](http://zettio.github.io/weave/)
- * [Features](http://zettio.github.io/weave/features.html)
- * [Troubleshooting](http://zettio.github.io/weave/troubleshooting.html)
- * [Building](http://zettio.github.io/weave/building.html)
- * [How it works](http://zettio.github.io/weave/how-it-works.html)
- * [WeaveDNS README](https://github.com/zettio/weave/tree/master/weavedns#readme)
+ * [Documentation homepage](http://docs.weave.works/weave/latest_release/)
+ * [Getting Started Guides](http://weave.works/guides/)
+ * [Features](http://docs.weave.works/weave/latest_release/features.html)
+ * [Troubleshooting](http://docs.weave.works/weave/latest_release/troubleshooting.html)
+ * [Building](http://docs.weave.works/weave/latest_release/building.html)
+ * [How it works](http://docs.weave.works/weave/latest_release/how-it-works.html)
 
 ## Contact Us
 
 Found a bug, want to suggest a feature, or have a question?
-[File an issue](https://github.com/zettio/weave/issues), or email
+[File an issue](https://github.com/weaveworks/weave/issues), or email
 help@weave.works. When reporting a bug, please include which version of
 weave you are running, as shown by `weave version`.
 

Vagrantfile

@@ -1,32 +1,40 @@
 VAGRANTFILE_API_VERSION = "2"
 
+require './vagrant-common.rb'
+
 vm_ip = "172.16.0.3" # arbitrary private IP
-pkgs = "lxc-docker build-essential ethtool libpcap-dev git mercurial"
+
+pkgs = %w(
+  lxc-docker
+  aufs-tools
+  build-essential
+  ethtool
+  iputils-arping
+  libpcap-dev
+  git
+  mercurial
+  bc
+)
 
 Vagrant.configure(VAGRANTFILE_API_VERSION) do |config|
-  config.vm.box = "phusion/ubuntu-14.04-amd64"
-  config.vm.box_url = "https://oss-binaries.phusionpassenger.com/vagrant/boxes/latest/ubuntu-14.04-amd64-vbox.box"
+
+  config.vm.box = "ubuntu/ubuntu-15.04-amd64"
+  config.vm.box_url = "https://cloud-images.ubuntu.com/vagrant/vivid/current/vivid-server-cloudimg-amd64-vagrant-disk1.box"
 
   config.vm.network "private_network", ip: vm_ip
+  config.vm.provider :virtualbox do |vb|
+    vb.customize ["modifyvm", :id, "--natdnshostresolver1", "off"]
+    vb.customize ["modifyvm", :id, "--natdnsproxy1", "off"]
+  end
 
-  config.vm.synced_folder "./", "/home/vagrant/src/github.com/zettio/weave"
+  config.vm.synced_folder ".", "/vagrant", disabled: true
+  config.vm.synced_folder ".", "/home/vagrant/src/github.com/weaveworks/weave"
 
-  config.vm.provision :shell, :inline => "sudo apt-key adv --keyserver hkp://keyserver.ubuntu.com:80 --recv-keys 36A1D7869245C8950F966E92D8576A8BA88D21E9"
-  config.vm.provision :shell, :inline => "echo deb https://get.docker.io/ubuntu docker main > /etc/apt/sources.list.d/docker.list"
-
-  pkg_cmd = "export DEBIAN_FRONTEND=noninteractive; " \
-    "apt-get update -qq; " \
-    "apt-get install -qq --no-install-recommends #{pkgs}"
-
-  install_go_toolchain = "curl -s https://storage.googleapis.com/golang/go1.4.linux-amd64.tar.gz | tar xz -C /usr/local"
-
-  config.vm.provision :shell, :inline => pkg_cmd
-  config.vm.provision :shell, :inline => install_go_toolchain
-  config.vm.provision :shell, :inline => "usermod -a -G docker vagrant; "
-  config.vm.provision :shell, :inline => "echo export GOPATH=/home/vagrant >> /home/vagrant/.bashrc"
-  config.vm.provision :shell, :inline => "echo export PATH=/usr/local/go/bin:${PATH} >> /home/vagrant/.bashrc"
-  config.vm.provision :shell, :inline => "chown -R vagrant:vagrant /home/vagrant/src"
-  config.vm.provision :shell, :inline => "/usr/local/go/bin/go clean -i net; /usr/local/go/bin/go install -tags netgo std"
+  install_build_deps config.vm, pkgs
+  install_go_toochain config.vm
+  tweak_user_env config.vm
+  tweak_docker_daemon config.vm
+  cleanup config.vm
 
 end
 

bin/lint

@@ -0,0 +1,86 @@
+#!/bin/bash
+# This scipt lints go files for common errors.
+#
+# Its runs gofmt and go vet, and optionally golint and
+# gocyclo, if they are installed.
+#
+# With no arguments, it lints the current files staged
+# for git commit.  Or you can pass it explicit filenames
+# (or directories) and it will lint them.
+#
+# To use this script automatically, run:
+#   ln -s ../../bin/lint .git/hooks/pre-commit
+
+set -eu
+
+function lint_go {
+	filename="$1"
+	result=0
+
+	if [ -n "$(gofmt -l "${filename}")" ]; then
+		result=1
+		echo "${filename}: run gofmt -w ${filename}!"
+	fi
+
+	go tool vet "${filename}" || result=$?
+
+	# golint is completely optional.  If you don't like it
+	# don't have it installed.
+	if type golint >/dev/null 2>&1; then
+		# golint doesn't set an exit code it seems
+		lintoutput=$(golint "${filename}" | grep -vE 'comment|dot imports')
+		if [ "$lintoutput" != "" ]; then
+			result=1
+			echo "$lintoutput"
+		fi
+	fi
+
+	# gocyclo is completely optional.  If you don't like it
+	# don't have it installed.  Also never blocks a commit,
+	# it just warns.
+	if type gocyclo >/dev/null 2>&1; then
+		gocyclo -over 25 "${filename}" | while read line; do
+			echo "${filename}": higher than 25 cyclomatic complexity - "${line}"
+		done
+	fi
+
+	return $result
+}
+
+function lint {
+	filename="$1"
+	ext="${filename##*\.}"
+
+	# Don't lint this script
+	if [ "${filename}" = "bin/lint" ]; then
+		return
+	fi
+
+	# Don't lint files that don't exist
+	if ! [ -a "${filename}" ]; then
+		return
+	fi
+
+	case "$ext" in
+		go) lint_go "${filename}"
+		;;
+	esac
+}
+
+function lint_files {
+	lint_result=0
+	while read filename; do
+		lint "${filename}" || lint_result=1
+	done
+	exit $lint_result
+}
+
+function list_files {
+	if [ $# -gt 0 ]; then
+		find "$@" -type f
+	else
+		git diff --cached --name-only
+	fi
+}
+
+list_files "$@" | lint_files

bin/merge-into-gh-pages

@@ -1,20 +0,0 @@
-#! /bin/bash
-set -e
-
-# For info on why/how to use this script, see
-# https://github.com/zettio/weave/wiki/WorkingOnWeave#working-on-docs
-
-MERGE_ARGS="-X subtree=site"
-
-merge_dir=$(mktemp -d -t weave-merge.XXXXXX)/weave
-git clone -b gh-pages . $merge_dir
-
-pushd $merge_dir
-git pull --ff-only git@github.com:zettio/weave gh-pages
-git fetch origin master
-git merge $MERGE_ARGS -e -m "Merge master into gh-pages" origin/master
-
-popd
-git fetch $merge_dir gh-pages:gh-pages
-
-# rm -rf $merge_dir

bin/multiweave

@@ -0,0 +1,54 @@
+#!/bin/bash
+set -e
+
+# You may need to adjust
+#    echo 4096 >/proc/sys/net/ipv4/neigh/default/gc_thresh3
+# where the number is greater than NUM_WEAVES*(NUM_WEAVES-1) plus some
+# fudge.
+#
+# Without that, some connections between the weaves may fail to get
+# established, and networking on the host in general becomes
+# broken. There will also be some "net_ratelimit: nnn callbacks
+# suppressed" messages in the syslog.
+
+START=${FIRST_WEAVE:-1}
+COUNT=${NUM_WEAVES:-28}
+FINISH=$((START+COUNT-1))
+PORT=6783
+
+weavedir=$(dirname $0)/..
+
+# Generate a random MAC value - copied from 'weave' script
+random_mac() {
+    # In the first byte of the MAC, the 'multicast' bit should be
+    # clear and 'locally administered' bit should be set.  All other
+    # bits should be random.
+    od -txC -An -N6 /dev/urandom | ( read a b c d e f && printf "%02x:$b:$c:$d:$e:$f" $((0x$a & ~1 | 2)) )
+}
+
+case "$1" in
+    launch)
+        shift 1
+        for i in $(seq $START $FINISH); do
+            WEAVE_CONTAINER_NAME=weave$i WEAVE_PORT=$((5000+i)) $weavedir/weave launch-router --iface '' --name $(random_mac) --nickname weave$i --port $PORT --no-dns "$@"
+        done
+        if [ $START -ne 1 ] ; then
+            status=$(docker inspect --format='{{.State.Running}} {{.NetworkSettings.IPAddress}}' weave$((START-1)))
+            PREV="${status#true }"
+        fi
+        for i in $(seq $START $FINISH); do
+            if [ -n "$PREV" ] ; then
+                echo connecting weave$i to $PREV
+                WEAVE_CONTAINER_NAME=weave$i $weavedir/weave connect $PREV
+            fi
+            status=$(docker inspect --format='{{.State.Running}} {{.NetworkSettings.IPAddress}}' weave$i)
+            PREV="${status#true }"
+        done
+        ;;
+    stop)
+        for i in $(seq $START $FINISH); do
+            echo Stopping weave$i
+            WEAVE_CONTAINER_NAME=weave$i $weavedir/weave stop-router
+        done
+        ;;
+esac

bin/publish-gh-pages

@@ -1,3 +0,0 @@
-#! /bin/sh
-set -e
-git push git@github.com:zettio/weave gh-pages:gh-pages

bin/release

@@ -3,22 +3,56 @@
 set -e
 
 SUDO=${SUDO-sudo}
-GITHUB_USER=${GITHUB_USER:-zettio}
-DOCKERHUB_USER=${DOCKERHUB_USER:-zettio}
+GITHUB_USER=${GITHUB_USER:-weaveworks}
+DOCKERHUB_USER=${DOCKERHUB_USER:-weaveworks}
 RELEASE_NAME=${RELEASE_NAME:-"Weave"}
 RELEASE_DESCRIPTION=${RELEASE_DESCRIPTION:-"Weaving Containers into Applications"}
 
 PWD=`pwd`
 
-setup() {
-    ## Get the new version number from the most recent tag
-    if ! LATEST_TAG=$(git describe --abbrev=0 --match='v*' 2>/dev/null) ; then
-        echo "Could not find an annotated 'v*' version tag." >&2
-        exit 1
+infer_release_type() {
+    if echo $1 | grep -qE '^v[0-9]+\.[0-9]+\.0+$' ; then
+        echo MAINLINE
+    elif echo $1 | grep -qE '^v[0-9]+\.[0-9]+\.[0-9]+$' ; then
+        echo BRANCH
+    else
+        echo PRERELEASE
     fi
+}
+
+setup() {
+    # Ensure we have exactly one annotated tag pointing at HEAD
+    HEAD_TAGS=$(git tag --points-at HEAD)
+    case $(echo $HEAD_TAGS | wc -w) in
+        1)
+            if [ $HEAD_TAGS != "latest_release" ] ; then
+                LATEST_TAG=$HEAD_TAGS
+            else
+                echo "Cannot determine version - latest_release points at HEAD" >&2
+                exit 1
+            fi
+            ;;
+        0)
+            echo "Cannot determine version - no tags point at HEAD" >&2
+            exit 1
+            ;;
+        *)
+            echo "Cannot determine version - multiple tags point at HEAD:" >&2
+            for TAG in $HEAD_TAGS ; do
+                echo -e "\t$TAG" >&2
+            done
+            exit 1
+            ;;
+    esac
+
+    RELEASE_TYPE=$(infer_release_type $LATEST_TAG)
+    echo "== Inferred release type $RELEASE_TYPE from tag $LATEST_TAG"
+
     LATEST_TAG_SHA=$(git rev-parse $LATEST_TAG)
+    LATEST_TAG_COMMIT_SHA=$(git rev-list -1 $LATEST_TAG)
     LATEST_RELEASE_SHA=$(git rev-parse latest_release)
-    VERSION=${LATEST_TAG#v}
+    LATEST_RELEASE_COMMIT_SHA=$(git rev-list -1 latest_release)
+    VERSION=${LATEST_TAG}
     # NB does not check that this tag is on master
     RELEASE_DIR=./releases/$LATEST_TAG
 }
@@ -39,8 +73,8 @@ build() {
     cd $RELEASE_DIR
 
     ## Check that the top changelog entry is this version
-    if ! latest_changelog=$(grep -o "## Release [0-9].*" -m1 ./CHANGELOG.md) || \
-       ! [ `echo "$latest_changelog" | grep -o '[0-9][^ ]*'` == "$VERSION" ]; then
+    if ! latest_changelog=$(grep -oP '(?<=^## Release ).*' -m1 ./CHANGELOG.md) || \
+       ! [ `echo "$latest_changelog" = "$VERSION"` ]; then
         echo -e "\u2757 Latest changelog entry \"$latest_changelog\" does not match the release version $VERSION" >&2
         exit 1
     fi
@@ -61,7 +95,7 @@ build() {
     fi
 
     ## Run tests with the distributables, including version check
-    v=$(./weaver/weaver --version | grep -o '[0-9].*')
+    v=$(./prog/weaver/weaver --version | grep -oP '(?<=^weave router ).*')
     if ! [ "$v" == "$VERSION" ]; then
         echo "Version of distributable "$v" does not match release version $VERSION" >&2
         exit 1
@@ -71,24 +105,13 @@ build() {
     echo '** Release artefacts in' $RELEASE_DIR
 }
 
-publish() {
+draft() {
     setup
+
     cd $PWD/$RELEASE_DIR
 
     echo "== Sanity checks"
 
-    if ! which github-release >/dev/null; then
-        echo "Please install git-release:" >&2
-        echo -e "\tgo get github.com/aktau/github-release" >&2
-        echo "and create a git token per https://github.com/aktau/github-release" >&2
-        exit 1
-    fi
-
-    if ! [ $(git rev-list -1 $LATEST_TAG) == $(git rev-list -1 latest_release) ]; then
-        echo -e "\u2757 The tag latest_release does not point to the same commit as $LATEST_TAG"
-        exit 1
-    fi
-
     ## Check that the tag exists by looking at github
     if ! curl -sSf https://api.github.com/repos/$GITHUB_USER/weave/git/tags/$LATEST_TAG_SHA >/dev/null 2>&1; then
         echo -e "\u2757 Tag $LATEST_TAG is not on GitHub, or is not the same as the local tag" >&2
@@ -98,19 +121,9 @@ publish() {
         exit 1
     fi
 
-    ## Check that the 'latest_release' tag exists by looking at github
-    if ! curl -sSf https://api.github.com/repos/$GITHUB_USER/weave/git/tags/$LATEST_RELEASE_SHA >/dev/null 2>&1; then
-        echo -e "\u2757 Tag latest_release is not on GitHub, or is not the same as the local tag" >&2
-        echo -e "\thttps://github.com/$GITHUB_USER/weave/tags" >&2
-        echo "You may need to" >&2
-        echo -e "\tgit tag -af latest_release"
-        echo -e "\tgit push -f git@github.com:$GITHUB_USER/weave latest_release"
-        exit 1
-    fi
-
     echo -e "\u2713 Tag $LATEST_TAG exists in GitHub repo $GITHUB_USER/weave"
 
-    ## Check that the version doesn't already exist by looking at github
+    ## Check that the version does not already exist by looking at github
     ## releases
     if github-release info --user $GITHUB_USER --repo weave --tag $LATEST_TAG >/dev/null 2>&1; then
         echo -e "\u2757 Release $LATEST_TAG already exists on GitHub" >&2
@@ -120,13 +133,13 @@ publish() {
 
     echo '** Sanity checks OK for publishing tag' $LATEST_TAG as $DOCKERHUB_USER/weave:$VERSION
 
-    echo "== Tagging and publishing images on docker hub as user $DOCKERHUB_USER"
-    make SUDO=$SUDO WEAVE_VERSION=$VERSION DOCKERHUB_USER=$DOCKERHUB_USER publish
+    RELEASE_ARGS="--draft"
+    if [ "$RELEASE_TYPE" = 'PRERELEASE' ] ; then
+        RELEASE_ARGS="$RELEASE_ARGS --pre-release"
+    fi
 
-    echo "== Creating GitHub release $RELEASE_NAME $VERSION"
-    # This cannot be done as a draft because of a bug in
-    # github-release: https://github.com/aktau/github-release/issues/7
-    github-release release \
+    echo "== Creating GitHub release $RELEASE_ARGS $RELEASE_NAME $VERSION"
+    github-release release $RELEASE_ARGS \
         --user $GITHUB_USER \
         --repo weave \
         --tag $LATEST_TAG \
@@ -140,52 +153,126 @@ publish() {
         --name "weave" \
         --file "./weave"
 
-    echo "** Published release $RELEASE_NAME $VERSION"
+    echo "** Draft $TYPE $RELEASE_NAME $VERSION created at"
     echo -e "\thttps://github.com/$GITHUB_USER/weave/releases/$LATEST_TAG"
+}
 
-    if github-release info --user $GITHUB_USER --repo weave \
-        --tag latest_release >/dev/null 2>&1; then
-        github-release delete \
-            --user $GITHUB_USER \
-            --repo weave \
-            --tag latest_release
+publish() {
+    setup
+    cd $PWD/$RELEASE_DIR
+
+    UPDATE_LATEST=false
+    if [ "$RELEASE_TYPE" = 'MAINLINE' ] ; then
+        UPDATE_LATEST=true
     fi
 
-    github-release release \
-        --user $GITHUB_USER \
-        --repo weave \
-        --tag latest_release \
-        --name "$RELEASE_NAME latest ($VERSION)" \
-        --description "$RELEASE_DESCRIPTION"
+    if [ "$RELEASE_TYPE" = 'PRERELEASE' ] ; then
+        echo "== Tagging and pushing images on docker hub as user $DOCKERHUB_USER"
+        make UPDATE_LATEST=$UPDATE_LATEST SUDO=$SUDO WEAVE_VERSION=$VERSION DOCKERHUB_USER=$DOCKERHUB_USER publish
+        echo "** Docker images tagged and pushed"
 
-    github-release upload \
-        --user $GITHUB_USER \
-        --repo weave \
-        --tag latest_release \
-        --name "weave" \
-        --file "./weave"
+        echo "== Publishing pre-release on GitHub"
 
-    echo "** Published $RELEASE_NAME as latest_release at"
-    echo -e "\thttps://github.com/$GITHUB_USER/weave/releases/latest_release"
+        github-release publish \
+            --user $GITHUB_USER \
+            --repo weave \
+            --tag $LATEST_TAG
+
+        echo "** Pre-release $RELEASE_NAME $VERSION published at"
+        echo -e "\thttps://github.com/$GITHUB_USER/weave/releases/$LATEST_TAG"
+    else
+        echo "== Sanity checks"
+        if ! [ "$LATEST_TAG_COMMIT_SHA" == "$LATEST_RELEASE_COMMIT_SHA" ] ; then
+            echo -e "\u2757 The tag latest_release does not point to the same commit as $LATEST_TAG" >&2
+            echo "You may need to" >&2
+            echo -e "\tgit tag -af latest_release $LATEST_TAG" >&2
+            exit 1
+        fi
+
+        ## Check that the 'latest_release' tag exists by looking at github
+        if ! curl -sSf https://api.github.com/repos/$GITHUB_USER/weave/git/tags/$LATEST_RELEASE_SHA >/dev/null 2>&1; then
+            echo -e "\u2757 Tag latest_release is not on GitHub, or is not the same as the local tag" >&2
+            echo -e "\thttps://github.com/$GITHUB_USER/weave/tags" >&2
+            echo "You may need to" >&2
+            echo -e "\tgit push -f git@github.com:$GITHUB_USER/weave latest_release" >&2
+            exit 1
+        fi
+        echo '** Sanity checks OK for publishing tag' $LATEST_TAG as $DOCKERHUB_USER/weave:$VERSION
+
+        echo "== Tagging and pushing images on docker hub as user $DOCKERHUB_USER"
+        make UPDATE_LATEST=$UPDATE_LATEST SUDO=$SUDO WEAVE_VERSION=$VERSION DOCKERHUB_USER=$DOCKERHUB_USER publish
+        echo "** Docker images tagged and pushed"
+
+        echo "== Publishing release on GitHub"
+
+        github-release publish \
+            --user $GITHUB_USER \
+            --repo weave \
+            --tag $LATEST_TAG
+
+        if github-release info --user $GITHUB_USER --repo weave \
+            --tag latest_release >/dev/null 2>&1; then
+            github-release delete \
+                --user $GITHUB_USER \
+                --repo weave \
+                --tag latest_release
+        fi
+
+        github-release release \
+            --user $GITHUB_USER \
+            --repo weave \
+            --tag latest_release \
+            --name "$RELEASE_NAME latest ($VERSION)" \
+            --description "$RELEASE_DESCRIPTION"
+
+        github-release upload \
+            --user $GITHUB_USER \
+            --repo weave \
+            --tag latest_release \
+            --name "weave" \
+            --file "./weave"
+
+        echo "** Release $RELEASE_NAME $VERSION published at"
+        echo -e "\thttps://github.com/$GITHUB_USER/weave/releases/$LATEST_TAG"
+        echo -e "\thttps://github.com/$GITHUB_USER/weave/releases/latest_release"
+    fi
 }
 
 usage() {
     echo "Usage:"
     echo -e "\t./bin/release build"
     echo "-- Build artefacts for the latest version tag"
+    echo -e "\t./bin/release draft"
+    echo "-- Create draft release with artefacts in GitHub"
     echo -e "\t./bin/release publish"
-    echo "-- Publish the artefacts for the latest tag to GitHub and DockerHub"
+    echo "-- Publish the GitHub release and update DockerHub"
+    exit 1
 }
 
-case "$1" in
+# Ensure required tooling is installed
+if ! which github-release >/dev/null; then
+    echo "Please install git-release:" >&2
+    echo -e "\tgo get github.com/aktau/github-release" >&2
+    echo "and create a git token per https://github.com/aktau/github-release" >&2
+    exit 1
+fi
+
+[ $# -eq 0 ] && usage
+COMMAND=$1
+shift
+
+case "$COMMAND" in
     build)
-        build
+        build "$@"
+        ;;
+    draft)
+        draft "$@"
         ;;
     publish)
-        publish
+        publish "$@"
         ;;
     *)
-        echo "Unknown command \"$1\""
+        echo "Unknown command \"$COMMAND\""
         usage
         ;;
 esac

bin/setup-ci-secrets

@@ -0,0 +1,57 @@
+#!/bin/sh
+
+## This is the shape of unencrypted `do-setup-ci-secrets`
+## 
+## cat > /tmp/boto_gsutil_cert.pem << EOF
+## -----BEGIN PRIVATE KEY-----
+## <...>
+## -----END PRIVATE KEY-----
+## EOF
+## 
+## cat > ~/.boto << EOF
+## [Credentials]
+## gs_service_client_id = <...>
+## gs_service_key_file = /tmp/boto_gsutil_cert.pem
+## 
+## [Boto]
+## https_validate_certificates = True
+## 
+## [GSUtil]
+## content_language = en
+## default_api_version = 2
+## default_project_id = <...>
+## EOF
+
+openssl base64 -d << EOF \
+  | openssl aes-256-cbc -d -K $1 -iv $2 \
+    -out bin/do-setup-ci-secrets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+EOF
+
+exec sh bin/do-setup-ci-secrets

bin/setup-circleci-secrets

@@ -0,0 +1,115 @@
+#!/bin/bash
+
+set -eu
+
+# openssl enc -in do-setup-circleci-secrets.orig -out setup-circleci-secrets.orig -e -aes256 -pass stdin
+# openssl base64 < setup-circleci-secrets.orig
+
+openssl base64 -d << EOF \
+  | openssl enc \
+    -out bin/do-setup-circleci-secrets \
+		-d -aes256 -pass pass:$1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+EOF
+
+exec sh bin/do-setup-circleci-secrets

build/Dockerfile

@@ -0,0 +1,24 @@
+FROM ubuntu
+
+RUN apt-get -y update && apt-get -y install --no-install-recommends ca-certificates apt-transport-https
+RUN apt-key adv --keyserver hkp://keyserver.ubuntu.com:80 --recv-keys 36A1D7869245C8950F966E92D8576A8BA88D21E9
+RUN echo deb https://get.docker.io/ubuntu docker main > /etc/apt/sources.list.d/docker.list
+RUN apt-get -y update && apt-get -y install --no-install-recommends build-essential git lxc-docker-1.3.1 mercurial libpcap-dev curl make pkg-config gcc bison flex python-requests
+
+# When doing a build in a container, "apt-get update" happens twice,
+# which can be a very significant overhead for incremental builds.
+# And it's unnecessary, because if any of the prerequisites do change,
+# the right thing to do is to rebuild the container image.  Rather
+# than suppressing the "apt-get update" commands explicitly, we clear
+# out sources.list so that 'apt-get update' doesn't do anything.
+RUN echo >/etc/apt/sources.list
+
+ENV GO_VERSION 1.4.2
+RUN curl -sSL https://golang.org/dl/go${GO_VERSION}.linux-amd64.tar.gz | tar -C /usr/local -xz
+ENV PATH /usr/local/go/bin:$PATH
+
+# So that sudo does not trample on PATH
+RUN sed -ie '/secure_path/d' /etc/sudoers
+
+COPY build.sh /
+ENTRYPOINT ["sh", "/build.sh"]

build/build.sh

@@ -0,0 +1,49 @@
+#!/bin/sh
+set -e
+
+GOPATH=/home/go
+export GOPATH
+
+WEAVE_SRC=$GOPATH/src/github.com/weaveworks/weave
+
+if [ $# -eq 0 -o "$1" = "tests" ] ; then
+    # No arguments.  Expect that the weave repo will be bind-mounted
+    # into $GOPATH
+    if ! [ -e $WEAVE_SRC ] ; then
+        cat 2>&1 <<EOF
+No container arguments supplied, and nothing at ${WEAVE_SRC}.  Please
+either bind-mount the golang workspace containing weave with the
+docker run -v option, e.g.:
+
+    $ docker run -v <host gopath>:${GOPATH} \\
+          -v /var/run/docker.sock:/var/run/docker.sock weaveworks/weave-build
+
+Or supply git clone arguments to retrieve it, e.g.:
+
+    $ docker run -v /var/run/docker.sock:/var/run/docker.sock \\
+          weaveworks/weave-build https://github.com/weaveworks/weave.git
+EOF
+        exit 1
+    fi
+
+    # If we run make directly, any files created on the bind mount
+    # will have awkward ownership.  So we switch to a user with the
+    # same user and group IDs as source directory.  We have to set a
+    # few things up so that sudo works without complaining later on.
+    uid=$(stat --format="%u" $WEAVE_SRC)
+    gid=$(stat --format="%g" $WEAVE_SRC)
+    echo "weave:x:$uid:$gid::$WEAVE_SRC:/bin/sh" >>/etc/passwd
+    echo "weave:*:::::::" >>/etc/shadow
+    echo "weave	ALL=(ALL)	NOPASSWD: ALL" >>/etc/sudoers
+
+    if [ "$1" = "tests" ] ; then
+        su weave -c "PATH=$PATH make -C $WEAVE_SRC tests"
+    else
+        su weave -c "PATH=$PATH make -C $WEAVE_SRC build"
+    fi
+else
+    # There are arguments to pass to git-clone
+    mkdir -p ${WEAVE_SRC%/*}
+    git clone "$@" $WEAVE_SRC
+    make -C $WEAVE_SRC build
+fi

circle.yml

@@ -0,0 +1,61 @@
+general:
+  branches:
+    ignore:
+      - gh\-pages
+      - /pull\/.*/
+
+machine:
+  services:
+    - docker
+  environment:
+    GOPATH: /home/ubuntu:$GOPATH
+    SRCDIR: /home/ubuntu/src/github.com/weaveworks/weave
+    PATH: $PATH:$HOME/.local/bin:$HOME/google-cloud-sdk/bin/
+    CLOUDSDK_CORE_DISABLE_PROMPTS: 1
+    WEAVE_BUILD: $HOME/docker/weave-build.tar
+
+dependencies:
+  cache_directories:
+    - "~/docker"
+  override:
+    - if [[ -e "$WEAVE_BUILD" ]]; then
+        docker load -i $WEAVE_BUILD;
+      else
+        docker build -t weaveworks/weave-build build;
+        mkdir -p $(dirname "$WEAVE_BUILD");
+        docker save weaveworks/weave-build >$WEAVE_BUILD;
+      fi
+  post:
+    - sudo apt-get update
+    - sudo apt-get install bc jq
+    - pip install requests
+    - curl https://sdk.cloud.google.com | bash
+    - bin/setup-circleci-secrets "$SECRET_PASSWORD"
+    - mkdir -p $(dirname $SRCDIR)
+    - cp -r $(pwd)/ $SRCDIR
+
+test:
+  override:
+    - docker run -v /var/run/docker.sock:/run/docker.sock -v /home/ubuntu:/home/go -e COVERDIR=test/coverage -e SLOW=true -e CIRCLECI -e CIRCLE_BUILD_NUM -e CIRCLE_NODE_TOTAL -e CIRCLE_NODE_INDEX weaveworks/weave-build tests:
+        parallel: true
+    - docker run -v /var/run/docker.sock:/run/docker.sock -v /home/ubuntu:/home/go -e COVERAGE=true weaveworks/weave-build:
+        parallel: true
+    - cd $SRCDIR/test; ./gce.sh setup:
+        parallel: true
+    - cd $SRCDIR/test; eval $(./gce.sh hosts); ./setup.sh:
+        parallel: true
+    - cd $SRCDIR/test; eval $(./gce.sh hosts); export COVERAGE=true; ./run_all.sh:
+        parallel: true
+        timeout: 300
+  post:
+    - cd $SRCDIR/test; ./gce.sh destroy:
+        parallel: true
+
+teardown:
+  pre:
+    - test "$CIRCLE_NODE_INDEX" != "0" || (cd $SRCDIR/test; ./gen_coverage_reports.sh):
+        parallel: true
+    - test "$CIRCLE_NODE_INDEX" != "0" || (go get github.com/mattn/goveralls && goveralls -repotoken $COVERALLS_REPO_TOKEN -coverprofile=$SRCDIR/test/profile.cov -service=circleci || true):
+        parallel: true
+    - test "$CIRCLE_NODE_INDEX" != "0" || (cd $SRCDIR/test; cp coverage.* $CIRCLE_ARTIFACTS):
+        parallel: true

common/docker/client.go

@@ -0,0 +1,64 @@
+package docker
+
+import (
+	"github.com/fsouza/go-dockerclient"
+	. "github.com/weaveworks/weave/common"
+)
+
+// An observer for container events
+type ContainerObserver interface {
+	ContainerDied(ident string)
+}
+
+type Client struct {
+	*docker.Client
+}
+
+// NewClient creates a new Docker client and checks we can talk to Docker
+func NewClient(apiPath string) (*Client, error) {
+	dc, err := docker.NewClient(apiPath)
+	if err != nil {
+		return nil, err
+	}
+	client := &Client{dc}
+
+	env, err := client.Version()
+	if err != nil {
+		return nil, err
+	}
+	Log.Infof("[docker] Using Docker API on %s: %v", apiPath, env)
+	return client, nil
+}
+
+// AddObserver adds an observer for docker events
+func (c *Client) AddObserver(ob ContainerObserver) error {
+	events := make(chan *docker.APIEvents)
+	if err := c.AddEventListener(events); err != nil {
+		Log.Errorf("[docker] Unable to add listener to Docker API: %s", err)
+		return err
+	}
+
+	go func() {
+		for event := range events {
+			switch event.Status {
+			case "die":
+				id := event.ID
+				ob.ContainerDied(id)
+			}
+		}
+	}()
+	return nil
+}
+
+// IsContainerNotRunning returns true if we have checked with Docker that the ID is not running
+func (c *Client) IsContainerNotRunning(idStr string) bool {
+	container, err := c.InspectContainer(idStr)
+	if err == nil {
+		return !container.State.Running
+	}
+	if _, notThere := err.(*docker.NoSuchContainer); notThere {
+		return true
+	}
+	Log.Errorf("[docker] Could not check container status: %s", err)
+	return false
+}

common/init.go

@@ -1,10 +0,0 @@
-package common
-
-import (
-	"io/ioutil"
-	"os"
-)
-
-func init() {
-	InitLogging(ioutil.Discard, os.Stdout, os.Stdout, os.Stderr)
-}

common/logging.go

@@ -1,41 +1,54 @@
 package common
 
 import (
-	"io"
-	"io/ioutil"
-	"log"
-	"os"
+	"bytes"
+	"fmt"
+	"strings"
+
+	"github.com/Sirupsen/logrus"
 )
 
-const (
-	standardLogFlags = log.Ldate | log.Ltime | log.Lmicroseconds
-)
+type textFormatter struct {
+}
 
-// Largely taken from
-// http://www.goinggo.net/2013/11/using-log-package-in-go.html
+// Based off logrus.TextFormatter, which behaves completely
+// differently when you don't want colored output
+func (f *textFormatter) Format(entry *logrus.Entry) ([]byte, error) {
+	b := &bytes.Buffer{}
+
+	levelText := strings.ToUpper(entry.Level.String())[0:4]
+	timeStamp := entry.Time.Format("2006/01/02 15:04:05.000000")
+	if len(entry.Data) > 0 {
+		fmt.Fprintf(b, "%s: %s %-44s ", levelText, timeStamp, entry.Message)
+		for k, v := range entry.Data {
+			fmt.Fprintf(b, " %s=%v", k, v)
+		}
+	} else {
+		// No padding when there's no fields
+		fmt.Fprintf(b, "%s: %s %s", levelText, timeStamp, entry.Message)
+	}
+
+	b.WriteByte('\n')
+	return b.Bytes(), nil
+}
 
 var (
-	Debug   *log.Logger
-	Info    *log.Logger
-	Warning *log.Logger
-	Error   *log.Logger
+	standardTextFormatter = &textFormatter{}
 )
 
-func InitLogging(debugHandle io.Writer,
-	infoHandle io.Writer,
-	warningHandle io.Writer,
-	errorHandle io.Writer) {
+var (
+	Log *logrus.Logger
+)
 
-	Debug = log.New(debugHandle, "DEBUG: ", standardLogFlags)
-	Info = log.New(infoHandle, "INFO: ", standardLogFlags)
-	Warning = log.New(warningHandle, "WARNING: ", standardLogFlags)
-	Error = log.New(errorHandle, "ERROR: ", standardLogFlags)
+func init() {
+	Log = logrus.New()
+	Log.Formatter = standardTextFormatter
 }
 
-func InitDefaultLogging(debug bool) {
-	debugOut := ioutil.Discard
-	if debug {
-		debugOut = os.Stderr
+func SetLogLevel(levelname string) {
+	level, err := logrus.ParseLevel(levelname)
+	if err != nil {
+		Log.Fatal(err)
 	}
-	InitLogging(debugOut, os.Stdout, os.Stdout, os.Stderr)
+	Log.Level = level
 }

common/mflagext/listvar.go

@@ -0,0 +1,31 @@
+package mflagext
+
+import (
+	"fmt"
+
+	"github.com/docker/docker/pkg/mflag"
+)
+
+type listOpts struct {
+	value      *[]string
+	hasBeenSet bool
+}
+
+func ListVar(p *[]string, names []string, value []string, usage string) {
+	*p = value
+	mflag.Var(&listOpts{p, false}, names, usage)
+}
+
+func (opts *listOpts) Set(value string) error {
+	if opts.hasBeenSet {
+		(*opts.value) = append((*opts.value), value)
+	} else {
+		(*opts.value) = []string{value}
+		opts.hasBeenSet = true
+	}
+	return nil
+}
+
+func (opts *listOpts) String() string {
+	return fmt.Sprintf("%v", []string(*opts.value))
+}

common/signals.go

@@ -0,0 +1,32 @@
+package common
+
+import (
+	"os"
+	"os/signal"
+	"runtime"
+	"syscall"
+)
+
+// A subsystem/server/... that can be stopped or queried about the status with a signal
+type SignalReceiver interface {
+	Stop() error
+}
+
+func SignalHandlerLoop(ss ...SignalReceiver) {
+	sigs := make(chan os.Signal, 1)
+	signal.Notify(sigs, syscall.SIGINT, syscall.SIGQUIT, syscall.SIGUSR1, syscall.SIGTERM)
+	buf := make([]byte, 1<<20)
+	for {
+		switch <-sigs {
+		case syscall.SIGINT, syscall.SIGTERM:
+			Log.Infof("=== received SIGINT/SIGTERM ===\n*** exiting")
+			for _, subsystem := range ss {
+				subsystem.Stop()
+			}
+			return
+		case syscall.SIGQUIT:
+			stacklen := runtime.Stack(buf, true)
+			Log.Infof("=== received SIGQUIT ===\n*** goroutine dump...\n%s\n*** end", buf[:stacklen])
+		}
+	}
+}

common/utils.go

@@ -0,0 +1,20 @@
+package common
+
+import (
+	"strings"
+)
+
+// Assert test is true, panic otherwise
+func Assert(test bool) {
+	if !test {
+		panic("Assertion failure")
+	}
+}
+
+func ErrorMessages(errors []error) string {
+	var result []string
+	for _, err := range errors {
+		result = append(result, err.Error())
+	}
+	return strings.Join(result, "\n")
+}

docs/architecture.txt

@@ -34,7 +34,7 @@ Router:
   the known locations of peers as they're discovered and is informed
   when connections we have made die. It proactively tries to create
   connections to remote peers we're not connected to using a random
-  binary exponential backoff to regulate the period between connection
+  exponential backoff to regulate the period between connection
   attempts.
 
 - Local Peer
@@ -160,7 +160,7 @@ if a node receives a packet that is bigger than the next MTU, it is
 required to drop the packet and send back an ICMP 3,4 packet which
 informs the sending node of the next hop MTU (RFC 1191). In theory,
 these ICMP packets should have all the reverse NAT and so forth
-applied, to make it all the way back to the sender. In practise this
+applied, to make it all the way back to the sender. In practice, this
 does often work, but in some cases all ICMP are sometimes blocked,
 often by idiots who don't understand that ICMP is really the error
 channel of all network traffic.
@@ -187,16 +187,16 @@ If weave determines that fragmentation is reliable then when weave
 sniffs large packets (i.e. packets larger than the MTU and thus don't
 have DF set) then weave will encapsulate these packets as necessary
 and similarly send them out as-is, without DF set, trusting to the
-network to do all necessary fragementation and reassembly.
+network to do all necessary fragmentation and reassembly.
 
-However, if weave determines that fragementation is not reliable
+However, if weave determines that fragmentation is not reliable
 between any two peers then it will manually fragment larger packets
 correctly according to the IP spec, and will then send them between
 weave peers with the DF flag set (i.e. the fragmentation will ensure
-that the encapsulatated traffic will not be greater than the PMTU
+that the encapsulated traffic will not be greater than the PMTU
 between weave peers). Because the fragmentation is done according to
 the IP spec, we don't need to do reassembly ourselves - on the
-receiving weave, we jus inject all the fragments and rely on the
+receiving weave, we just inject all the fragments and rely on the
 stack to do reassembly.
 
 Sometimes PMTU discovery doesn't work as ICMP packets sometimes get

docs/dockerless.txt

@@ -125,8 +125,8 @@ VM2> nc 192.168.122.2 6783
 If all is well, you should now be able to launch weave on VM1
 then on VM2:
 
-VM1> weaver -iface veth6 -name vm1
-VM2> weaver -iface veth6 -name vm2 192.168.122.1
+VM1> weaver --iface veth6 --name vm1
+VM2> weaver --iface veth6 --name vm2 192.168.122.2
 
 Once the connection is up and running, you should be able to connect
 from VM1/ns2 to VM2/ns2 and vice versa:

docs/ipam.md

@@ -0,0 +1,220 @@
+See the [requirements](https://github.com/zettio/weave/wiki/IP-allocation-requirements).
+
+At its highest level, the idea is that we start with a certain IP
+address space, known to all peers, and divide it up between the
+peers. This allows peers to allocate and free individual IPs locally
+until they run out.
+
+We use a CRDT to represent shared knowledge about the space,
+transmitted over the Weave Gossip mechanism, together with
+point-to-point messages for one peer to request more space from
+another.
+
+The allocator running at each peer also has an http interface which
+the container infrastructure (e.g. the Weave script, or a Docker
+plugin) uses to request IP addresses.
+
+![Schematic of IP allocation in operation](https://docs.google.com/drawings/d/1-EUIRKYxwfKTpBJ7v_LMcdvSpodIMSz4lT3wgEfWKl4/pub?w=701&h=310)
+
+## Commands
+
+The commands supported by the allocator via the http interface are:
+
+- Allocate: request one IP address for a container in a subnet
+- Lookup: fetch the previously-allocated IP address for a container in a subnet
+- Free: return an IP address that is currently allocated
+- Claim: request a specific IP address for a container (e.g. because
+  it is already using that address)
+
+Each http request either specifies a subnet, or if no subnet is
+specified this is taken as a request to allocate in a pre-defined
+default subnet.
+
+The allocator also watches via the Docker event mechanism: if a
+container dies then all IP addresses allocated to that container are
+freed.
+
+## Definitions
+
+1. Allocations. We use the word 'allocation' to refer to a specific
+   IP address being assigned, e.g. so it can be given to a container.
+
+2. Range. Most of the time, instead of dealing with individual IP
+   addresses, we operate on them in contiguous groups, for which we
+   use the word "range".
+
+3. Ring. We consider the address space as a ring, so ranges wrap
+   around from the highest address to the lowest address.
+
+4. Peer. A Peer is a node on the Weave network. It can own zero or
+   more ranges.
+
+### The Allocation Process
+
+When a peer owns some range(s), it can allocate freely from within
+those ranges to containers on the same machine. If it runs out of
+space in a subnet (all owned ranges are full), it will ask another
+peer for space:
+  - it picks a peer to ask at random, weighted by the amount of space
+    owned by each peer in the subnet
+    - if the target peer decides to give up space, it unicasts a message
+      back to the asker with the newly-updated ring.
+    - if the target peer has no space, it unicasts a message back to the
+      asker with its current copy of the ring, on the basis that the
+      requestor must have acted on out-of-date information.
+  - it will continue to ask for space until it receives some, or its
+    copy of the ring tells it all peers are full in that subnet.
+
+### Claiming an address
+
+If a Weave process is restarted, in most cases it will hear from
+another peer which ranges it used to own, but it needs to know which
+individual IP addresses are assigned to containers in order to avoid
+giving the same address out in subsequent allocation requests. The
+weave script invokes the `claim` command in `populate_ipam` to do
+this.
+
+When the Allocator is told to claim an address, there are four
+possibilities:
+  - the address is outside of the space managed by this Allocator, in
+    which case we ignore the request.
+  - the address is owned by this peer, in which case we record the
+    address as being assigned to a particular container and return
+    success.
+  - the address is owned by a different peer, in which case we return
+    failure.
+  - we have not yet heard of any address ranges being owned by anyone,
+    in which case we wait until we do hear.
+
+This approach fails if the peer does not hear from another peer about
+the ranges it used to own, e.g. if all peers in a network partition
+are restarted at once.
+
+### The Ring CRDT
+
+We use a Convergent Replicated Data Type - a CRDT - so that peers can
+make changes concurrently and communicate them without central
+coordination. To achieve this, we arrange that peers only make changes
+to the data structure in ranges that they own (except under
+administrator command - see later).
+
+The data structure is a set of tokens, each containing the name of an
+owning peer. A peer can own many ranges. Each token is placed at the
+start address of a range, and the set is kept ordered so each range
+goes from one token to the next. Each range on the ring includes the
+start address but does not include the end address (which is the start
+of the next range).  Ranges wrap, so the 'next' token after the last
+one is the first token.
+
+![Tokens on the Ring](https://docs.google.com/drawings/d/1hp--q2vmxbBAnPjhza4Kqjr1ugrw2iS1M1GerhH-IKY/pub?w=960&h=288)
+
+In more detail:
+- Each token is a tuple {peer name, version}, placed
+  at an IP address.
+- Peer names are taken from Weave: they are unique and survive across restarts.
+- The contents of a token can only be updated by the owning peer, and
+  when this is done the version is incremented
+- The ring data structure is always gossiped in its entirety
+- The merge operation when a peer receives a ring via gossip is:
+  - Tokens with unique addresses are just copied into the combined ring
+  - For tokens at the same address, pick the one with the highest
+    version number
+- The data gossiped about the ring also includes the amount of free
+  space in each range: this is not essential but it improves the
+  selection of which peer to ask for space.
+- When a peer is asked for space, there are four scenarios:
+  1. It has an empty range; it can change the peer associated with
+     the token at the beginning of the range and increment the version.
+  2. It has a range which can be subdivided by a single token to form
+     a free range.  It inserts said token, owned by the peer requesting
+     space.
+  3. It has a 'hole' in the middle of a range; an empty range can be
+     created by inserting two tokens, one at the beginning of the hole
+     owned by the peer requesting the space, and one at the end of the
+     hole owned by the requestee.
+  4. It has no space.
+
+## Initialisation
+
+The previous sections describe how peers coordinate changes to the
+ring.  But how is the initial state of the ring established?  If a new
+peer joins a long-standing cluster, it can learn about the ring state
+from other peers.  But in a freshly started cluster, the initial ring
+state must be established from a clean slate.  And it must be
+consistent across all peers.  This is a distributed consensus problem,
+and we solve it using the Paxos algorithm.
+
+Although Paxos has a reputation for being hard to understand and to
+implement, the implementation used for ring initialization is
+relatively straightforward:
+
+- We only need to establish consensus for a single value, rather than
+  a succession of values (as in a replicated transaction log).  Thus
+  we implement basic Paxos, rather than multi-Paxos, and the
+  implementation closely follows the outline of basic Paxos described
+  [on
+  wikipedia](http://en.wikipedia.org/wiki/Paxos_%28computer_science%29#Basic_Paxos).
+
+- All peers play all the roles described in basic Paxos: Proposer,
+  acceptor and listener.
+
+- Paxos is usually described in terms of unicast messages from one
+  agent to another, although three of the four messages are fanned out
+  to all agents in a certain role ("prepare" and "accept request" from
+  a proposer to all acceptors; "accepted" from an acceptor to all
+  learners).  So most implementations involve a communications layer
+  to implement the required communication patterns.  But our
+  implementation is built on top of the weave gossip layer, which
+  gives us a broadcast medium.  Using broadcast for the one truly
+  unicast message ("promise") may seem wasteful, but as we only
+  establish consensus for a single value, it is not a major concern.
+
+The value the peers obtain consensus on is the set of peers that will
+be represented in the initial ring (with each peer getting an equal
+share of the address space).  When a proposing peer gets to choose the
+value, it includes all the peers it has heard from during the Paxos
+phase, which is at least a quorum.
+
+Once a consensus is reached, it is used to initialize the ring.  If a
+peer hears about an initialized ring via gossip, that implies that a
+consensus was reached, so it will stop participating in Paxos.
+
+Paxos requires that we know the quorum size for the cluster.  As weave
+clusters are a dynamic entity, there is no fixed quorum size.  But the
+Paxos phase used to initialize the ring should normally be
+short-lived, so we just need to know the initial cluster size.  A
+heuristic is used to derive this from the list of addresses passed to
+`weave launch`, but the user can set it explicitly.
+
+## Peer shutdown
+
+When a peer leaves (a `weave reset` command), it grants all its own
+tokens to another peer, then broadcasts the updated ring.
+
+After sending the message, the peer terminates - it does not wait for
+any response.
+
+Failures:
+- message lost
+  - the space will be unusable by other peers because it will still be
+    seen as owned.
+
+To cope with the situation where a peer has left or died without
+managing to tell its peers, an administrator may go to any other peer
+and command that it take over the dead peer's tokens (with `weave
+rmpeer`).  This information will then be gossipped out to the network.
+
+(This operation is not guaranteed to be safe - if the dead peer made
+some transfers which have are known to other peers but have not
+reached the peer that does the `rmpeer`, then we get an inconsistent
+ring.  We could make it safe, up to partitions, by inquiring of every
+live peer what its view of the dead peer is, and making sure we use
+the latest info.)
+
+## Limitations
+
+Nothing is persisted. If one peer restarts it should receive gossip
+from other peers showing what it used to own, and in that case it can
+recover quite well. If, however, there are no peers left alive, or
+this peer cannot establish network communication with those that are,
+then it cannot recover.

docs/release-process.md

@@ -0,0 +1,145 @@
+# Release Process
+## Prerequisites
+
+* Up-to-date versions of `git`, `go` etc
+* Install GitHub release tool `go get github.com/weaveworks/github-release`
+* Create a [github token for
+  github-release](https://help.github.com/articles/creating-an-access-token-for-command-line-use/);
+set and export `$GITHUB_TOKEN` with this value
+* Update all dependencies with `make update`
+
+## Release Types
+
+The release script behaves differently depending on the kind of
+release you are doing. There are three types:
+
+* **Mainline** - a release (typically from master) with version tag
+  `vX.Y.Z` where Z is zero (e.g. `v2.1.0`)
+* **Branch** - a bugfix release (typically from a branch) with version tag
+  `vX.Y.Z` where Z is non-zero (e.g `v2.1.1`)
+* **Prerelease** - a release from an arbitrary branch with an arbitrary
+  version tag (e.g. `feature-preview-20150904`)
+
+N.B. the release script _infers the release type from the format of the
+version tag_. Ensure your tag is in the correct format and the desired
+behaviours for that type of release will be obtained from the script.
+
+## Build Phase
+### Update CHANGELOG.md
+
+* Checkout the branch from which you wish to release
+* Choose a version tag (see above) henceforth referred to as `$TAG`.
+* Add a changelog entry for the new tag at the top of `CHANGELOG.md`.
+  The first line must be a markdown header of the form `## Release
+  $TAG`
+
+Commit the changelog update:
+
+    git commit -m "Add release $TAG" CHANGELOG.md
+
+### Create Version Tag
+
+Next you must tag the changelog commit with `$TAG`
+
+    git tag -a -m "Release $TAG" $TAG
+
+### Execute Build
+
+You are now ready to perform the build. If you have skipped the
+previous steps (e.g. because you're doing a rebuild), you must ensure
+that `HEAD` points to the tagged commit. You may then execute
+
+    bin/release build
+
+This has the following effects:
+
+* `git tag --points-at HEAD` is used to determine `$TAG` (hence the
+  `HEAD` requirement)
+* Your *local* repository is cloned into `releases/$TAG`
+* `CHANGELOG.md` is checked to ensure it has an entry for `$TAG`
+* Distributables injected with `$TAG` are built
+* Tests are executed
+
+## Draft Phase
+### Push Version Tag Upstream
+
+First you must push your version tag upstream, so that an associated
+GitHub release may be created:
+
+    git push git@github.com:weaveworks/weave $TAG
+
+N.B. if you're testing the release process, push to your fork
+instead!
+
+### Create Draft Release
+
+You're now ready to draft your release notes:
+
+    bin/release draft
+
+This has the following effects:
+
+* A [release](https://help.github.com/articles/about-releases) is
+  created in GitHub for `$TAG`. This release is in the draft state, so
+  it is only visible to contributors; for **Prerelease** builds the
+  pre-release attribute will also be set
+* The `weave` script is uploaded as an attachment to the release
+
+Navigate to https://github.com/weaveworks/weave/releases, 'Edit' the
+draft and input the release notes. When you are done make sure you
+'Save draft' (and not 'Publish release'!).
+
+Once the release notes have passed review, proceed to the publish
+phase.
+
+## Publish Phase
+### Move/Force Push `latest_release` Tag
+
+This step must only be performed for **Mainline** and **Branch**
+releases:
+
+    git tag -af -m "Release $TAG" latest_release $TAG
+    git push -f git@github.com:weaveworks/weave latest_release
+
+The `latest_release` tag *must* point at `$TAG`, *not* at `HEAD` -
+the build script will complain otherwise.
+
+N.B. if you're testing the release process, push to your fork
+instead!
+
+### Publish Release & Distributable Artefacts
+
+You can now publish the release and upload the remaining
+distributables to DockerHub:
+
+    bin/release publish
+
+The effects of this step depend on the inferred release type. The
+following occurs for all types:
+
+* Docker images are tagged `$TAG` and pushed to DockerHub
+* GitHub release moves from draft to published state
+
+Additionally, for **Mainline** and **Branch** types:
+
+* Release named `latest_release` is updated on GitHub
+
+Finally, for **Mainline** releases only:
+
+* Images tagged `latest` are updated on DockerHub
+
+
+## Troubleshooting
+
+There's a few things that can go wrong.
+
+ * If the build is wonky, e.g., the tests don't pass, you can delete
+   the directory in `./releases/`, fix whatever it is, move the
+   version tag (which should still be only local) and have another go.
+ * If the DockerHub pushes fail (which sadly seems to happen a lot),
+   you can just run `./bin/release publish` again.
+ * If you need to overwrite a release you can do so by manually
+   deleting the GitHub version release and re-running the process.
+   Please note that the DockerHub `latest` images, GitHub
+   `latest_release` and download links may be in an inconsistent state
+   until the overwrite is completed.

ipam/allocate.go

@@ -0,0 +1,67 @@
+package ipam
+
+import (
+	"fmt"
+
+	"github.com/weaveworks/weave/net/address"
+)
+
+type allocateResult struct {
+	addr address.Address
+	err  error
+}
+
+type allocate struct {
+	resultChan       chan<- allocateResult
+	ident            string
+	r                address.Range // Range we are trying to allocate within
+	hasBeenCancelled func() bool
+}
+
+// Try returns true if the request is completed, false if pending
+func (g *allocate) Try(alloc *Allocator) bool {
+	if g.hasBeenCancelled() {
+		g.Cancel()
+		return true
+	}
+
+	if addr, found := alloc.lookupOwned(g.ident, g.r); found {
+		g.resultChan <- allocateResult{addr, nil}
+		return true
+	}
+
+	if !alloc.universe.Overlaps(g.r) {
+		g.resultChan <- allocateResult{0, fmt.Errorf("range %s out of bounds: %s", g.r, alloc.universe)}
+		return true
+	}
+
+	alloc.establishRing()
+
+	if ok, addr := alloc.space.Allocate(g.r); ok {
+		alloc.debugln("Allocated", addr, "for", g.ident, "in", g.r)
+		alloc.addOwned(g.ident, addr)
+		g.resultChan <- allocateResult{addr, nil}
+		return true
+	}
+
+	// out of space
+	donors := alloc.ring.ChoosePeersToAskForSpace(g.r.Start, g.r.End)
+	for _, donor := range donors {
+		if err := alloc.sendSpaceRequest(donor, g.r); err != nil {
+			alloc.debugln("Problem asking peer", donor, "for space:", err)
+		} else {
+			alloc.debugln("Decided to ask peer", donor, "for space in range", g.r)
+			break
+		}
+	}
+
+	return false
+}
+
+func (g *allocate) Cancel() {
+	g.resultChan <- allocateResult{0, fmt.Errorf("Allocate request for %s cancelled", g.ident)}
+}
+
+func (g *allocate) ForContainer(ident string) bool {
+	return g.ident == ident
+}

ipam/allocator.go

@@ -0,0 +1,733 @@
+package ipam
+
+import (
+	"bytes"
+	"encoding/gob"
+	"fmt"
+	"sort"
+	"time"
+
+	"github.com/weaveworks/weave/common"
+	"github.com/weaveworks/weave/ipam/paxos"
+	"github.com/weaveworks/weave/ipam/ring"
+	"github.com/weaveworks/weave/ipam/space"
+	"github.com/weaveworks/weave/net/address"
+	"github.com/weaveworks/weave/router"
+)
+
+// Kinds of message we can unicast to other peers
+const (
+	msgSpaceRequest = iota
+	msgRingUpdate
+	msgSpaceRequestDenied
+
+	paxosInterval = time.Second * 5
+	MinSubnetSize = 4 // first and last addresses are excluded, so 2 would be too small
+)
+
+// operation represents something which Allocator wants to do, but
+// which may need to wait until some other message arrives.
+type operation interface {
+	// Try attempts this operations and returns false if needs to be tried again.
+	Try(alloc *Allocator) bool
+
+	Cancel()
+
+	// Does this operation pertain to the given container id?
+	// Used for tidying up pending operations when containers die.
+	ForContainer(ident string) bool
+}
+
+// Allocator brings together Ring and space.Set, and does the
+// necessary plumbing.  Runs as a single-threaded Actor, so no locks
+// are used around data structures.
+type Allocator struct {
+	actionChan       chan<- func()
+	ourName          router.PeerName
+	universe         address.Range                // superset of all ranges
+	ring             *ring.Ring                   // information on ranges owned by all peers
+	space            space.Space                  // more detail on ranges owned by us
+	owned            map[string][]address.Address // who owns what addresses, indexed by container-ID
+	nicknames        map[router.PeerName]string   // so we can map nicknames for rmpeer
+	pendingAllocates []operation                  // held until we get some free space
+	pendingClaims    []operation                  // held until we know who owns the space
+	gossip           router.Gossip                // our link to the outside world for sending messages
+	paxos            *paxos.Node
+	paxosTicker      *time.Ticker
+	shuttingDown     bool // to avoid doing any requests while trying to shut down
+	now              func() time.Time
+}
+
+// NewAllocator creates and initialises a new Allocator
+func NewAllocator(ourName router.PeerName, ourUID router.PeerUID, ourNickname string, universe address.Range, quorum uint) *Allocator {
+	return &Allocator{
+		ourName:   ourName,
+		universe:  universe,
+		ring:      ring.New(universe.Start, universe.End, ourName),
+		owned:     make(map[string][]address.Address),
+		paxos:     paxos.NewNode(ourName, ourUID, quorum),
+		nicknames: map[router.PeerName]string{ourName: ourNickname},
+		now:       time.Now,
+	}
+}
+
+// Start runs the allocator goroutine
+func (alloc *Allocator) Start() {
+	actionChan := make(chan func(), router.ChannelSize)
+	alloc.actionChan = actionChan
+	go alloc.actorLoop(actionChan)
+}
+
+// Stop makes the actor routine exit, for test purposes ONLY because any
+// calls after this is processed will hang. Async.
+func (alloc *Allocator) Stop() {
+	alloc.actionChan <- nil
+}
+
+// Operation life cycle
+
+// Given an operation, try it, and add it to the pending queue if it didn't succeed
+func (alloc *Allocator) doOperation(op operation, ops *[]operation) {
+	alloc.actionChan <- func() {
+		if alloc.shuttingDown {
+			op.Cancel()
+			return
+		}
+		if !op.Try(alloc) {
+			*ops = append(*ops, op)
+		}
+	}
+}
+
+// Given an operation, remove it from the pending queue
+//  Note the op may not be on the queue; it may have
+//  already succeeded.  If it is on the queue, we call
+//  cancel on it, allowing callers waiting for the resultChans
+//  to unblock.
+func (alloc *Allocator) cancelOp(op operation, ops *[]operation) {
+	for i, op := range *ops {
+		if op == op {
+			*ops = append((*ops)[:i], (*ops)[i+1:]...)
+			op.Cancel()
+			break
+		}
+	}
+}
+
+// Cancel all operations in a queue
+func (alloc *Allocator) cancelOps(ops *[]operation) {
+	for _, op := range *ops {
+		op.Cancel()
+	}
+	*ops = []operation{}
+}
+
+// Cancel all operations for a given container id, returns true
+// if we found any.
+func (alloc *Allocator) cancelOpsFor(ops *[]operation, ident string) bool {
+	var found bool
+	for i, op := range *ops {
+		if op.ForContainer(ident) {
+			found = true
+			op.Cancel()
+			*ops = append((*ops)[:i], (*ops)[i+1:]...)
+		}
+	}
+	return found
+}
+
+// Try all pending operations
+func (alloc *Allocator) tryPendingOps() {
+	// The slightly different semantics requires us to operate on 'claims' and
+	// 'allocates' separately:
+	// Claims must be tried before Allocates
+	for i := 0; i < len(alloc.pendingClaims); {
+		op := alloc.pendingClaims[i]
+		if !op.Try(alloc) {
+			i++
+			continue
+		}
+		alloc.pendingClaims = append(alloc.pendingClaims[:i], alloc.pendingClaims[i+1:]...)
+	}
+
+	// When the first Allocate fails, bail - no need to
+	// send too many begs for space.
+	for i := 0; i < len(alloc.pendingAllocates); {
+		op := alloc.pendingAllocates[i]
+		if !op.Try(alloc) {
+			break
+		}
+		alloc.pendingAllocates = append(alloc.pendingAllocates[:i], alloc.pendingAllocates[i+1:]...)
+	}
+}
+
+func (alloc *Allocator) spaceRequestDenied(sender router.PeerName, r address.Range) {
+	for i := 0; i < len(alloc.pendingClaims); {
+		claim := alloc.pendingClaims[i].(*claim)
+		if r.Contains(claim.addr) {
+			claim.deniedBy(alloc, sender)
+			alloc.pendingClaims = append(alloc.pendingClaims[:i], alloc.pendingClaims[i+1:]...)
+			continue
+		}
+		i++
+	}
+}
+
+func hasBeenCancelled(cancelChan <-chan bool) func() bool {
+	return func() bool {
+		select {
+		case <-cancelChan:
+			return true
+		default:
+			return false
+		}
+	}
+}
+
+// Actor client API
+
+// Allocate (Sync) - get new IP address for container with given name in range
+// if there isn't any space in that range we block indefinitely
+func (alloc *Allocator) Allocate(ident string, r address.Range, cancelChan <-chan bool) (address.Address, error) {
+	resultChan := make(chan allocateResult)
+	op := &allocate{resultChan: resultChan, ident: ident, r: r,
+		hasBeenCancelled: hasBeenCancelled(cancelChan)}
+	alloc.doOperation(op, &alloc.pendingAllocates)
+	result := <-resultChan
+	return result.addr, result.err
+}
+
+// Lookup (Sync) - get existing IP address for container with given name in range
+func (alloc *Allocator) Lookup(ident string, r address.Range) (address.Address, error) {
+	resultChan := make(chan allocateResult)
+	alloc.actionChan <- func() {
+		if addr, found := alloc.lookupOwned(ident, r); found {
+			resultChan <- allocateResult{addr: addr}
+			return
+		}
+		resultChan <- allocateResult{err: fmt.Errorf("lookup: no address found for %s in range %s", ident, r)}
+	}
+	result := <-resultChan
+	return result.addr, result.err
+}
+
+// Claim an address that we think we should own (Sync)
+func (alloc *Allocator) Claim(ident string, addr address.Address, noErrorOnUnknown bool) error {
+	resultChan := make(chan error)
+	op := &claim{resultChan: resultChan, ident: ident, addr: addr, noErrorOnUnknown: noErrorOnUnknown}
+	alloc.doOperation(op, &alloc.pendingClaims)
+	return <-resultChan
+}
+
+// ContainerDied is provided to satisfy the updater interface; does a 'Delete' underneath.  Sync.
+func (alloc *Allocator) ContainerDied(ident string) {
+	if err := alloc.Delete(ident); err == nil {
+		alloc.debugln("Container", ident, "died; released addresses")
+	}
+}
+
+// Delete (Sync) - release all IP addresses for container with given name
+func (alloc *Allocator) Delete(ident string) error {
+	errChan := make(chan error)
+	alloc.actionChan <- func() {
+		addrs, found := alloc.owned[ident]
+		for _, addr := range addrs {
+			alloc.space.Free(addr)
+		}
+		delete(alloc.owned, ident)
+
+		// Also remove any pending ops
+		found = alloc.cancelOpsFor(&alloc.pendingAllocates, ident) || found
+		found = alloc.cancelOpsFor(&alloc.pendingClaims, ident) || found
+
+		if !found {
+			errChan <- fmt.Errorf("Delete: no addresses for %s", ident)
+			return
+		}
+		errChan <- nil
+	}
+	return <-errChan
+}
+
+// Free (Sync) - release single IP address for container
+func (alloc *Allocator) Free(ident string, addrToFree address.Address) error {
+	errChan := make(chan error)
+	alloc.actionChan <- func() {
+		addrs := alloc.owned[ident]
+		for i, ownedAddr := range addrs {
+			if ownedAddr == addrToFree {
+				alloc.debugln("Freed", addrToFree, "for", ident)
+				if len(addrs) == 1 {
+					delete(alloc.owned, ident)
+				} else {
+					alloc.owned[ident] = append(addrs[:i], addrs[i+1:]...)
+				}
+				alloc.space.Free(addrToFree)
+				errChan <- nil
+				return
+			}
+		}
+
+		errChan <- fmt.Errorf("Free: address %s not found for %s", addrToFree, ident)
+	}
+	return <-errChan
+}
+
+// Shutdown (Sync)
+func (alloc *Allocator) Shutdown() {
+	alloc.infof("Shutdown")
+	doneChan := make(chan struct{})
+	alloc.actionChan <- func() {
+		alloc.shuttingDown = true
+		alloc.cancelOps(&alloc.pendingClaims)
+		alloc.cancelOps(&alloc.pendingAllocates)
+		if heir := alloc.ring.PickPeerForTransfer(); heir != router.UnknownPeerName {
+			alloc.ring.Transfer(alloc.ourName, heir)
+			alloc.space.Clear()
+			alloc.gossip.GossipBroadcast(alloc.Gossip())
+			time.Sleep(100 * time.Millisecond)
+		}
+		doneChan <- struct{}{}
+	}
+	<-doneChan
+}
+
+// AdminTakeoverRanges (Sync) - take over the ranges owned by a given peer.
+// Only done on adminstrator command.
+func (alloc *Allocator) AdminTakeoverRanges(peerNameOrNickname string) error {
+	resultChan := make(chan error)
+	alloc.actionChan <- func() {
+		peername, err := alloc.lookupPeername(peerNameOrNickname)
+		if err != nil {
+			resultChan <- fmt.Errorf("Cannot find peer '%s'", peerNameOrNickname)
+			return
+		}
+
+		alloc.debugln("AdminTakeoverRanges:", peername)
+		if peername == alloc.ourName {
+			resultChan <- fmt.Errorf("Cannot take over ranges from yourself!")
+			return
+		}
+
+		delete(alloc.nicknames, peername)
+		newRanges, err := alloc.ring.Transfer(peername, alloc.ourName)
+		alloc.space.AddRanges(newRanges)
+		resultChan <- err
+	}
+	return <-resultChan
+}
+
+// Lookup a PeerName by nickname or stringified PeerName.  We can't
+// call into the router for this because we are interested in peers
+// that have gone away but are still in the ring, which is why we
+// maintain our own nicknames map.
+func (alloc *Allocator) lookupPeername(name string) (router.PeerName, error) {
+	for peername, nickname := range alloc.nicknames {
+		if nickname == name {
+			return peername, nil
+		}
+	}
+
+	return router.PeerNameFromString(name)
+}
+
+// Restrict the peers in "nicknames" to those in the ring and our own
+func (alloc *Allocator) pruneNicknames() {
+	ringPeers := alloc.ring.PeerNames()
+	for name := range alloc.nicknames {
+		if _, ok := ringPeers[name]; !ok && name != alloc.ourName {
+			delete(alloc.nicknames, name)
+		}
+	}
+}
+
+func decodeRange(msg []byte) (r address.Range, err error) {
+	decoder := gob.NewDecoder(bytes.NewReader(msg))
+	return r, decoder.Decode(&r)
+}
+
+// OnGossipUnicast (Sync)
+func (alloc *Allocator) OnGossipUnicast(sender router.PeerName, msg []byte) error {
+	alloc.debugln("OnGossipUnicast from", sender, ": ", len(msg), "bytes")
+	resultChan := make(chan error)
+	alloc.actionChan <- func() {
+		switch msg[0] {
+		case msgSpaceRequest:
+			// some other peer asked us for space
+			r, err := decodeRange(msg[1:])
+			if err == nil {
+				alloc.donateSpace(r, sender)
+			}
+			resultChan <- err
+		case msgSpaceRequestDenied:
+			r, err := decodeRange(msg[1:])
+			if err == nil {
+				alloc.spaceRequestDenied(sender, r)
+			}
+			resultChan <- err
+		case msgRingUpdate:
+			resultChan <- alloc.update(sender, msg[1:])
+		}
+	}
+	return <-resultChan
+}
+
+// OnGossipBroadcast (Sync)
+func (alloc *Allocator) OnGossipBroadcast(sender router.PeerName, msg []byte) (router.GossipData, error) {
+	alloc.debugln("OnGossipBroadcast from", sender, ":", len(msg), "bytes")
+	resultChan := make(chan error)
+	alloc.actionChan <- func() {
+		resultChan <- alloc.update(sender, msg)
+	}
+	return alloc.Gossip(), <-resultChan
+}
+
+type gossipState struct {
+	// We send a timstamp along with the information to be
+	// gossipped in order to detect skewed clocks
+	Now       int64
+	Nicknames map[router.PeerName]string
+
+	Paxos paxos.GossipState
+	Ring  *ring.Ring
+}
+
+func (alloc *Allocator) encode() []byte {
+	data := gossipState{
+		Now:       alloc.now().Unix(),
+		Nicknames: alloc.nicknames,
+	}
+
+	// We're only interested in Paxos until we have a Ring.
+	if alloc.ring.Empty() {
+		data.Paxos = alloc.paxos.GossipState()
+	} else {
+		data.Ring = alloc.ring
+	}
+	buf := new(bytes.Buffer)
+	enc := gob.NewEncoder(buf)
+	if err := enc.Encode(data); err != nil {
+		panic(err)
+	}
+	return buf.Bytes()
+}
+
+// Encode (Sync)
+func (alloc *Allocator) Encode() []byte {
+	resultChan := make(chan []byte)
+	alloc.actionChan <- func() {
+		resultChan <- alloc.encode()
+	}
+	return <-resultChan
+}
+
+// OnGossip (Sync)
+func (alloc *Allocator) OnGossip(msg []byte) (router.GossipData, error) {
+	alloc.debugln("Allocator.OnGossip:", len(msg), "bytes")
+	resultChan := make(chan error)
+	alloc.actionChan <- func() {
+		resultChan <- alloc.update(router.UnknownPeerName, msg)
+	}
+	return nil, <-resultChan // for now, we never propagate updates. TBD
+}
+
+// GossipData implementation is trivial - we always gossip the latest
+// data we have at time of sending
+type ipamGossipData struct {
+	alloc *Allocator
+}
+
+func (d *ipamGossipData) Merge(other router.GossipData) {
+	// no-op
+}
+
+func (d *ipamGossipData) Encode() [][]byte {
+	return [][]byte{d.alloc.Encode()}
+}
+
+// Gossip returns a GossipData implementation, which in this case always
+// returns the latest ring state (and does nothing on merge)
+func (alloc *Allocator) Gossip() router.GossipData {
+	return &ipamGossipData{alloc}
+}
+
+// SetInterfaces gives the allocator two interfaces for talking to the outside world
+func (alloc *Allocator) SetInterfaces(gossip router.Gossip) {
+	alloc.gossip = gossip
+}
+
+// ACTOR server
+
+func (alloc *Allocator) actorLoop(actionChan <-chan func()) {
+	for {
+		var tickChan <-chan time.Time
+		if alloc.paxosTicker != nil {
+			tickChan = alloc.paxosTicker.C
+		}
+
+		select {
+		case action := <-actionChan:
+			if action == nil {
+				return
+			}
+			action()
+		case <-tickChan:
+			alloc.propose()
+		}
+
+		alloc.assertInvariants()
+		alloc.reportFreeSpace()
+	}
+}
+
+// Helper functions
+
+// Ensure we are making progress towards an established ring
+func (alloc *Allocator) establishRing() {
+	if !alloc.ring.Empty() || alloc.paxosTicker != nil {
+		return
+	}
+
+	alloc.propose()
+	if ok, cons := alloc.paxos.Consensus(); ok {
+		// If the quorum was 1, then proposing immediately
+		// leads to consensus
+		alloc.createRing(cons.Value)
+	} else {
+		// re-try until we get consensus
+		alloc.paxosTicker = time.NewTicker(paxosInterval)
+	}
+}
+
+func (alloc *Allocator) createRing(peers []router.PeerName) {
+	alloc.debugln("Paxos consensus:", peers)
+	alloc.ring.ClaimForPeers(normalizeConsensus(peers))
+	alloc.gossip.GossipBroadcast(alloc.Gossip())
+	alloc.ringUpdated()
+}
+
+func (alloc *Allocator) ringUpdated() {
+	// When we have a ring, we don't need paxos any more
+	if alloc.paxos != nil {
+		alloc.paxos = nil
+
+		if alloc.paxosTicker != nil {
+			alloc.paxosTicker.Stop()
+			alloc.paxosTicker = nil
+		}
+	}
+
+	alloc.space.UpdateRanges(alloc.ring.OwnedRanges())
+	alloc.tryPendingOps()
+}
+
+// For compatibility with sort.Interface
+type peerNames []router.PeerName
+
+func (a peerNames) Len() int           { return len(a) }
+func (a peerNames) Less(i, j int) bool { return a[i] < a[j] }
+func (a peerNames) Swap(i, j int)      { a[i], a[j] = a[j], a[i] }
+
+// When we get a consensus from Paxos, the peer names are not in a
+// defined order and may contain duplicates.  This function sorts them
+// and de-dupes.
+func normalizeConsensus(consensus []router.PeerName) []router.PeerName {
+	if len(consensus) == 0 {
+		return nil
+	}
+
+	peers := make(peerNames, len(consensus))
+	copy(peers, consensus)
+	sort.Sort(peers)
+
+	dst := 0
+	for src := 1; src < len(peers); src++ {
+		if peers[dst] != peers[src] {
+			dst++
+			peers[dst] = peers[src]
+		}
+	}
+
+	return peers[:dst+1]
+}
+
+func (alloc *Allocator) propose() {
+	alloc.debugf("Paxos proposing")
+	alloc.paxos.Propose()
+	alloc.gossip.GossipBroadcast(alloc.Gossip())
+}
+
+func encodeRange(r address.Range) []byte {
+	buf := new(bytes.Buffer)
+	enc := gob.NewEncoder(buf)
+	if err := enc.Encode(r); err != nil {
+		panic(err)
+	}
+	return buf.Bytes()
+}
+
+func (alloc *Allocator) sendSpaceRequest(dest router.PeerName, r address.Range) error {
+	msg := router.Concat([]byte{msgSpaceRequest}, encodeRange(r))
+	return alloc.gossip.GossipUnicast(dest, msg)
+}
+
+func (alloc *Allocator) sendSpaceRequestDenied(dest router.PeerName, r address.Range) error {
+	msg := router.Concat([]byte{msgSpaceRequestDenied}, encodeRange(r))
+	return alloc.gossip.GossipUnicast(dest, msg)
+}
+
+func (alloc *Allocator) sendRingUpdate(dest router.PeerName) {
+	msg := router.Concat([]byte{msgRingUpdate}, alloc.encode())
+	alloc.gossip.GossipUnicast(dest, msg)
+}
+
+func (alloc *Allocator) update(sender router.PeerName, msg []byte) error {
+	reader := bytes.NewReader(msg)
+	decoder := gob.NewDecoder(reader)
+	var data gossipState
+	var err error
+
+	if err := decoder.Decode(&data); err != nil {
+		return err
+	}
+
+	deltat := time.Unix(data.Now, 0).Sub(alloc.now())
+	if deltat > time.Hour || -deltat > time.Hour {
+		return fmt.Errorf("clock skew of %v detected, ignoring update", deltat)
+	}
+
+	// Merge nicknames
+	for peer, nickname := range data.Nicknames {
+		alloc.nicknames[peer] = nickname
+	}
+
+	// only one of Ring and Paxos should be present.  And we
+	// shouldn't get updates for a empty Ring. But tolerate
+	// them just in case.
+	if data.Ring != nil {
+		if data.Ring.Range() != alloc.universe {
+			return fmt.Errorf("Incompatible IP allocation range %s; ours is %s",
+				data.Ring.Range().AsCIDRString(), alloc.universe.AsCIDRString())
+		}
+		err = alloc.ring.Merge(*data.Ring)
+		if !alloc.ring.Empty() {
+			alloc.pruneNicknames()
+			alloc.ringUpdated()
+		}
+		return err
+	}
+
+	if data.Paxos != nil {
+		if alloc.ring.Empty() {
+			if alloc.paxos.Update(data.Paxos) {
+				if alloc.paxos.Think() {
+					// If something important changed, broadcast
+					alloc.gossip.GossipBroadcast(alloc.Gossip())
+				}
+
+				if ok, cons := alloc.paxos.Consensus(); ok {
+					alloc.createRing(cons.Value)
+				}
+			}
+		} else if sender != router.UnknownPeerName {
+			// Sender is trying to initialize a ring, but we have one
+			// already - send it straight back
+			alloc.sendRingUpdate(sender)
+		}
+	}
+
+	return nil
+}
+
+func (alloc *Allocator) donateSpace(r address.Range, to router.PeerName) {
+	// No matter what we do, we'll send a unicast gossip
+	// of our ring back to tha chap who asked for space.
+	// This serves to both tell him of any space we might
+	// have given him, or tell him where he might find some
+	// more.
+	defer alloc.sendRingUpdate(to)
+
+	alloc.debugln("Peer", to, "asked me for space")
+	chunk, ok := alloc.space.Donate(r)
+	if !ok {
+		free := alloc.space.NumFreeAddressesInRange(r)
+		common.Assert(free == 0)
+		alloc.debugln("No space to give to peer", to)
+		// separate message maintains backwards-compatibility:
+		// down-level peers will ignore this and still get the ring update.
+		alloc.sendSpaceRequestDenied(to, r)
+		return
+	}
+	alloc.debugln("Giving range", chunk, "to", to)
+	alloc.ring.GrantRangeToHost(chunk.Start, chunk.End, to)
+	alloc.sendRingUpdate(to)
+}
+
+func (alloc *Allocator) assertInvariants() {
+	// We need to ensure all ranges the ring thinks we own have
+	// a corresponding space in the space set, and vice versa
+	checkSpace := space.New()
+	checkSpace.AddRanges(alloc.ring.OwnedRanges())
+	ranges := checkSpace.OwnedRanges()
+	spaces := alloc.space.OwnedRanges()
+
+	common.Assert(len(ranges) == len(spaces))
+
+	for i := 0; i < len(ranges); i++ {
+		r := ranges[i]
+		s := spaces[i]
+		common.Assert(s.Start == r.Start && s.End == r.End)
+	}
+}
+
+func (alloc *Allocator) reportFreeSpace() {
+	ranges := alloc.ring.OwnedRanges()
+	if len(ranges) == 0 {
+		return
+	}
+
+	freespace := make(map[address.Address]address.Offset)
+	for _, r := range ranges {
+		freespace[r.Start] = alloc.space.NumFreeAddressesInRange(r)
+	}
+	alloc.ring.ReportFree(freespace)
+}
+
+// Owned addresses
+
+// NB: addr must not be owned by ident already
+func (alloc *Allocator) addOwned(ident string, addr address.Address) {
+	alloc.owned[ident] = append(alloc.owned[ident], addr)
+}
+
+func (alloc *Allocator) lookupOwned(ident string, r address.Range) (address.Address, bool) {
+	for _, addr := range alloc.owned[ident] {
+		if r.Contains(addr) {
+			return addr, true
+		}
+	}
+	return 0, false
+}
+
+func (alloc *Allocator) findOwner(addr address.Address) string {
+	for ident, addrs := range alloc.owned {
+		for _, candidate := range addrs {
+			if candidate == addr {
+				return ident
+			}
+		}
+	}
+	return ""
+}
+
+// Logging
+
+func (alloc *Allocator) infof(fmt string, args ...interface{}) {
+	common.Log.Infof("[allocator %s] "+fmt, append([]interface{}{alloc.ourName}, args...)...)
+}
+func (alloc *Allocator) debugln(args ...interface{}) {
+	common.Log.Debugln(append([]interface{}{fmt.Sprintf("[allocator %s]:", alloc.ourName)}, args...)...)
+}
+func (alloc *Allocator) debugf(fmt string, args ...interface{}) {
+	common.Log.Debugf("[allocator %s] "+fmt, append([]interface{}{alloc.ourName}, args...)...)
+}

ipam/allocator_test.go

@@ -0,0 +1,534 @@
+package ipam
+
+import (
+	"fmt"
+	"math/rand"
+	"sync"
+	"testing"
+	"time"
+
+	"github.com/stretchr/testify/require"
+
+	"github.com/weaveworks/weave/common"
+	"github.com/weaveworks/weave/net/address"
+	"github.com/weaveworks/weave/testing/gossip"
+)
+
+const (
+	testStart1 = "10.0.1.0"
+	testStart2 = "10.0.2.0"
+	testStart3 = "10.0.3.0"
+)
+
+func TestAllocFree(t *testing.T) {
+	const (
+		container1 = "abcdef"
+		container2 = "baddf00d"
+		container3 = "b01df00d"
+		universe   = "10.0.3.0/26"
+		subnet1    = "10.0.3.0/28"
+		subnet2    = "10.0.3.32/28"
+		testAddr1  = "10.0.3.1"
+		testAddr2  = "10.0.3.33"
+		spaceSize  = 62 // 64 IP addresses in /26, minus .0 and .63
+	)
+
+	alloc, subnet := makeAllocatorWithMockGossip(t, "01:00:00:01:00:00", universe, 1)
+	defer alloc.Stop()
+	_, cidr1, _ := address.ParseCIDR(subnet1)
+	_, cidr2, _ := address.ParseCIDR(subnet2)
+
+	alloc.claimRingForTesting()
+	addr1, err := alloc.Allocate(container1, cidr1.HostRange(), nil)
+	require.NoError(t, err)
+	require.Equal(t, testAddr1, addr1.String(), "address")
+
+	addr2, err := alloc.Allocate(container1, cidr2.HostRange(), nil)
+	require.NoError(t, err)
+	require.Equal(t, testAddr2, addr2.String(), "address")
+
+	// Ask for another address for a different container and check it's different
+	addr1b, _ := alloc.Allocate(container2, cidr1.HostRange(), nil)
+	if addr1b.String() == testAddr1 {
+		t.Fatalf("Expected different address but got %s", addr1b.String())
+	}
+
+	// Ask for the first container again and we should get the same addresses again
+	addr1a, _ := alloc.Allocate(container1, cidr1.HostRange(), nil)
+	require.Equal(t, testAddr1, addr1a.String(), "address")
+	addr2a, _ := alloc.Allocate(container1, cidr2.HostRange(), nil)
+	require.Equal(t, testAddr2, addr2a.String(), "address")
+
+	// Now delete the first container, and we should get its addresses back
+	require.NoError(t, alloc.Delete(container1))
+	addr3, _ := alloc.Allocate(container3, cidr1.HostRange(), nil)
+	require.Equal(t, testAddr1, addr3.String(), "address")
+	addr4, _ := alloc.Allocate(container3, cidr2.HostRange(), nil)
+	require.Equal(t, testAddr2, addr4.String(), "address")
+
+	alloc.ContainerDied(container2)
+	alloc.ContainerDied(container3)
+	require.Equal(t, address.Offset(spaceSize), alloc.NumFreeAddresses(subnet))
+}
+
+func TestBootstrap(t *testing.T) {
+	const (
+		donateSize     = 5
+		donateStart    = "10.0.1.7"
+		ourNameString  = "01:00:00:01:00:00"
+		peerNameString = "02:00:00:02:00:00"
+	)
+
+	alloc1, subnet := makeAllocatorWithMockGossip(t, ourNameString, testStart1+"/22", 2)
+	defer alloc1.Stop()
+
+	// Simulate another peer on the gossip network
+	alloc2, _ := makeAllocatorWithMockGossip(t, peerNameString, testStart1+"/22", 2)
+	defer alloc2.Stop()
+
+	alloc1.OnGossipBroadcast(alloc2.ourName, alloc2.Encode())
+
+	alloc1.actionChan <- func() { alloc1.tryPendingOps() }
+
+	ExpectBroadcastMessage(alloc1, nil) // alloc1 will try to form consensus
+	done := make(chan bool)
+	go func() {
+		alloc1.Allocate("somecontainer", subnet, nil)
+		done <- true
+	}()
+	time.Sleep(100 * time.Millisecond)
+	AssertNothingSent(t, done)
+
+	CheckAllExpectedMessagesSent(alloc1, alloc2)
+
+	alloc1.actionChan <- func() { alloc1.tryPendingOps() }
+	AssertNothingSent(t, done)
+
+	CheckAllExpectedMessagesSent(alloc1, alloc2)
+
+	// alloc2 receives paxos update and broadcasts its reply
+	ExpectBroadcastMessage(alloc2, nil)
+	alloc2.OnGossipBroadcast(alloc1.ourName, alloc1.Encode())
+
+	ExpectBroadcastMessage(alloc1, nil)
+	alloc1.OnGossipBroadcast(alloc2.ourName, alloc2.Encode())
+
+	// both nodes will get consensus now so initialize the ring
+	ExpectBroadcastMessage(alloc2, nil)
+	ExpectBroadcastMessage(alloc2, nil)
+	alloc2.OnGossipBroadcast(alloc1.ourName, alloc1.Encode())
+
+	CheckAllExpectedMessagesSent(alloc1, alloc2)
+
+	alloc1.OnGossipBroadcast(alloc2.ourName, alloc2.Encode())
+	// now alloc1 should have space
+
+	AssertSent(t, done)
+
+	CheckAllExpectedMessagesSent(alloc1, alloc2)
+}
+
+func TestAllocatorClaim(t *testing.T) {
+	const (
+		container1 = "abcdef"
+		container3 = "b01df00d"
+		universe   = "10.0.3.0/24"
+		testAddr1  = "10.0.3.2"
+		testAddr2  = "10.0.4.2"
+	)
+
+	allocs, _, subnet := makeNetworkOfAllocators(2, universe)
+	alloc := allocs[1]
+	defer alloc.Stop()
+	addr1, _ := address.ParseIP(testAddr1)
+
+	// First claim should trigger "dunno, I'm going to wait"
+	err := alloc.Claim(container3, addr1, true)
+	require.NoError(t, err)
+
+	// Do one allocate to ensure paxos is all done
+	alloc.Allocate("unused", subnet, nil)
+	// Do an allocate on the other peer, which we will try to claim later
+	addrx, err := allocs[0].Allocate(container1, subnet, nil)
+
+	// Now try the claim again
+	err = alloc.Claim(container3, addr1, true)
+	require.NoError(t, err)
+	// Check we get this address back if we try an allocate
+	addr3, _ := alloc.Allocate(container3, subnet, nil)
+	require.Equal(t, testAddr1, addr3.String(), "address")
+	// one more claim should still work
+	err = alloc.Claim(container3, addr1, true)
+	require.NoError(t, err)
+	// claim for a different container should fail
+	err = alloc.Claim(container1, addr1, true)
+	require.Error(t, err)
+	// claiming the address allocated on the other peer should fail
+	err = alloc.Claim(container1, addrx, true)
+	require.Error(t, err, "claiming address allocated on other peer should fail")
+	// Check an address outside of our universe
+	addr2, _ := address.ParseIP(testAddr2)
+	err = alloc.Claim(container1, addr2, true)
+	require.NoError(t, err)
+}
+
+func (alloc *Allocator) pause() func() {
+	paused := make(chan struct{})
+	alloc.actionChan <- func() {
+		paused <- struct{}{}
+		<-paused
+	}
+	<-paused
+	return func() {
+		close(paused)
+	}
+}
+
+func TestCancel(t *testing.T) {
+	const (
+		CIDR = "10.0.1.7/26"
+	)
+
+	router := gossip.NewTestRouter(0.0)
+
+	alloc1, subnet := makeAllocator("01:00:00:02:00:00", CIDR, 2)
+	alloc1.SetInterfaces(router.Connect(alloc1.ourName, alloc1))
+
+	alloc2, _ := makeAllocator("02:00:00:02:00:00", CIDR, 2)
+	alloc2.SetInterfaces(router.Connect(alloc2.ourName, alloc2))
+	alloc1.claimRingForTesting(alloc1, alloc2)
+	alloc2.claimRingForTesting(alloc1, alloc2)
+
+	alloc1.Start()
+	alloc2.Start()
+
+	// tell peers about each other
+	alloc1.OnGossipBroadcast(alloc2.ourName, alloc2.Encode())
+
+	// Get some IPs, so each allocator has some space
+	res1, _ := alloc1.Allocate("foo", subnet, nil)
+	common.Log.Debugf("res1 = %s", res1.String())
+	res2, _ := alloc2.Allocate("bar", subnet, nil)
+	common.Log.Debugf("res2 = %s", res2.String())
+	if res1 == res2 {
+		require.FailNow(t, "Error: got same ips!")
+	}
+
+	// Now we're going to pause alloc2 and ask alloc1
+	// for an allocation
+	unpause := alloc2.pause()
+
+	// Use up all the IPs that alloc1 owns, so the allocation after this will prompt a request to alloc2
+	for i := 0; alloc1.NumFreeAddresses(subnet) > 0; i++ {
+		alloc1.Allocate(fmt.Sprintf("tmp%d", i), subnet, nil)
+	}
+	cancelChan := make(chan bool, 1)
+	doneChan := make(chan bool)
+	go func() {
+		_, ok := alloc1.Allocate("baz", subnet, cancelChan)
+		doneChan <- ok == nil
+	}()
+
+	AssertNothingSent(t, doneChan)
+	time.Sleep(100 * time.Millisecond)
+	AssertNothingSent(t, doneChan)
+
+	cancelChan <- true
+	unpause()
+	if <-doneChan {
+		require.FailNow(t, "Error: got result from Allocate")
+	}
+}
+
+func TestGossipShutdown(t *testing.T) {
+	const (
+		container1 = "abcdef"
+		container2 = "baddf00d"
+		universe   = "10.0.3.0/30"
+	)
+
+	alloc, subnet := makeAllocatorWithMockGossip(t, "01:00:00:01:00:00", universe, 1)
+	defer alloc.Stop()
+
+	alloc.claimRingForTesting()
+	alloc.Allocate(container1, subnet, nil)
+
+	alloc.Shutdown()
+
+	_, err := alloc.Allocate(container2, subnet, nil) // trying to allocate after shutdown should fail
+	require.False(t, err == nil, "no address")
+
+	CheckAllExpectedMessagesSent(alloc)
+}
+
+func TestTransfer(t *testing.T) {
+	const (
+		cidr = "10.0.1.7/22"
+	)
+	allocs, router, subnet := makeNetworkOfAllocators(3, cidr)
+	alloc1 := allocs[0]
+	alloc2 := allocs[1]
+	alloc3 := allocs[2] // This will be 'master' and get the first range
+
+	_, err := alloc2.Allocate("foo", subnet, nil)
+	require.True(t, err == nil, "Failed to get address")
+
+	_, err = alloc3.Allocate("bar", subnet, nil)
+	require.True(t, err == nil, "Failed to get address")
+
+	alloc2.gossip.GossipBroadcast(alloc2.Gossip())
+	router.Flush()
+	alloc2.gossip.GossipBroadcast(alloc3.Gossip())
+	router.Flush()
+	router.RemovePeer(alloc2.ourName)
+	router.RemovePeer(alloc3.ourName)
+	alloc2.Stop()
+	alloc3.Stop()
+	router.Flush()
+	require.NoError(t, alloc1.AdminTakeoverRanges(alloc2.ourName.String()))
+	require.NoError(t, alloc1.AdminTakeoverRanges(alloc3.ourName.String()))
+	router.Flush()
+
+	require.Equal(t, address.Offset(1022), alloc1.NumFreeAddresses(subnet))
+
+	_, err = alloc1.Allocate("foo", subnet, nil)
+	require.True(t, err == nil, "Failed to get address")
+	alloc1.Stop()
+}
+
+func TestFakeRouterSimple(t *testing.T) {
+	const (
+		cidr = "10.0.1.7/22"
+	)
+	allocs, _, subnet := makeNetworkOfAllocators(2, cidr)
+	defer stopNetworkOfAllocators(allocs)
+
+	alloc1 := allocs[0]
+	//alloc2 := allocs[1]
+
+	_, err := alloc1.Allocate("foo", subnet, nil)
+	require.NoError(t, err, "Failed to get address")
+}
+
+func TestAllocatorFuzz(t *testing.T) {
+	const (
+		firstpass    = 1000
+		secondpass   = 10000
+		nodes        = 5
+		maxAddresses = 1000
+		concurrency  = 5
+		cidr         = "10.0.1.7/22"
+	)
+	allocs, _, subnet := makeNetworkOfAllocators(nodes, cidr)
+	defer stopNetworkOfAllocators(allocs)
+
+	// Test state
+	// For each IP issued we store the allocator
+	// that issued it and the name of the container
+	// it was issued to.
+	type result struct {
+		name  string
+		alloc int32
+		block bool
+	}
+	stateLock := sync.Mutex{}
+	state := make(map[string]result)
+	// Keep a list of addresses issued, so we
+	// Can pick random ones
+	var addrs []string
+	numPending := 0
+
+	rand.Seed(0)
+
+	// Remove item from list by swapping it with last
+	// and reducing slice length by 1
+	rm := func(xs []string, i int32) []string {
+		ls := len(xs) - 1
+		xs[i] = xs[ls]
+		return xs[:ls]
+	}
+
+	bumpPending := func() bool {
+		stateLock.Lock()
+		if len(addrs)+numPending >= maxAddresses {
+			stateLock.Unlock()
+			return false
+		}
+		numPending++
+		stateLock.Unlock()
+		return true
+	}
+
+	noteAllocation := func(allocIndex int32, name string, addr address.Address) {
+		//common.Log.Infof("Allocate: got address %s for name %s", addr, name)
+		addrStr := addr.String()
+
+		stateLock.Lock()
+		defer stateLock.Unlock()
+
+		if res, existing := state[addrStr]; existing {
+			panic(fmt.Sprintf("Dup found for address %s - %s and %s", addrStr,
+				name, res.name))
+		}
+
+		state[addrStr] = result{name, allocIndex, false}
+		addrs = append(addrs, addrStr)
+		numPending--
+	}
+
+	// Do a Allocate and check the address
+	// is unique.  Needs a unique container
+	// name.
+	allocate := func(name string) {
+		if !bumpPending() {
+			return
+		}
+
+		allocIndex := rand.Int31n(nodes)
+		alloc := allocs[allocIndex]
+		//common.Log.Infof("Allocate: asking allocator %d", allocIndex)
+		addr, err := alloc.Allocate(name, subnet, nil)
+
+		if err != nil {
+			panic(fmt.Sprintf("Could not allocate addr"))
+		}
+
+		noteAllocation(allocIndex, name, addr)
+	}
+
+	// Free a random address.
+	free := func() {
+		stateLock.Lock()
+		if len(addrs) == 0 {
+			stateLock.Unlock()
+			return
+		}
+		// Delete an existing allocation
+		// Pick random addr
+		addrIndex := rand.Int31n(int32(len(addrs)))
+		addr := addrs[addrIndex]
+		res := state[addr]
+		if res.block {
+			stateLock.Unlock()
+			return
+		}
+		addrs = rm(addrs, addrIndex)
+		delete(state, addr)
+		stateLock.Unlock()
+
+		alloc := allocs[res.alloc]
+		//common.Log.Infof("Freeing %s (%s) on allocator %d", res.name, addr, res.alloc)
+
+		oldAddr, err := address.ParseIP(addr)
+		if err != nil {
+			panic(err)
+		}
+		require.NoError(t, alloc.Free(res.name, oldAddr))
+	}
+
+	// Do a Allocate on an existing container & allocator
+	// and check we get the right answer.
+	allocateAgain := func() {
+		stateLock.Lock()
+		addrIndex := rand.Int31n(int32(len(addrs)))
+		addr := addrs[addrIndex]
+		res := state[addr]
+		if res.block {
+			stateLock.Unlock()
+			return
+		}
+		res.block = true
+		state[addr] = res
+		stateLock.Unlock()
+		alloc := allocs[res.alloc]
+
+		//common.Log.Infof("Asking for %s (%s) on allocator %d again", res.name, addr, res.alloc)
+
+		newAddr, _ := alloc.Allocate(res.name, subnet, nil)
+		oldAddr, _ := address.ParseIP(addr)
+		if newAddr != oldAddr {
+			panic(fmt.Sprintf("Got different address for repeat request for %s: %s != %s", res.name, newAddr, oldAddr))
+		}
+
+		stateLock.Lock()
+		res.block = false
+		state[addr] = res
+		stateLock.Unlock()
+	}
+
+	// Claim a random address for a unique container name - may not succeed
+	claim := func(name string) {
+		if !bumpPending() {
+			return
+		}
+		allocIndex := rand.Int31n(nodes)
+		addressIndex := rand.Int31n(int32(subnet.Size()))
+		alloc := allocs[allocIndex]
+		addr := address.Add(subnet.Start, address.Offset(addressIndex))
+		err := alloc.Claim(name, addr, true)
+		if err == nil {
+			noteAllocation(allocIndex, name, addr)
+		}
+	}
+
+	// Run function _f_ _iterations_ times, in _concurrency_
+	// number of goroutines
+	doConcurrentIterations := func(iterations int, f func(int)) {
+		iterationsPerThread := iterations / concurrency
+
+		wg := sync.WaitGroup{}
+		for i := 0; i < concurrency; i++ {
+			wg.Add(1)
+			go func(j int) {
+				defer wg.Done()
+				for k := 0; k < iterationsPerThread; k++ {
+					f((j * iterationsPerThread) + k)
+				}
+			}(i)
+		}
+		wg.Wait()
+	}
+
+	// First pass, just allocate a bunch of ips
+	doConcurrentIterations(firstpass, func(iteration int) {
+		name := fmt.Sprintf("first%d", iteration)
+		allocate(name)
+	})
+
+	// Second pass, random ask for more allocations,
+	// or remove existing ones, or ask for allocation
+	// again.
+	doConcurrentIterations(secondpass, func(iteration int) {
+		r := rand.Float32()
+		switch {
+		case 0.0 <= r && r < 0.4:
+			// Ask for a new allocation
+			name := fmt.Sprintf("second%d", iteration)
+			allocate(name)
+
+		case (0.4 <= r && r < 0.8):
+			// free a random addr
+			free()
+
+		case 0.8 <= r && r < 0.95:
+			// ask for an existing name again, check we get same ip
+			allocateAgain()
+
+		case 0.95 <= r && r < 1.0:
+			name := fmt.Sprintf("second%d", iteration)
+			claim(name)
+		}
+	})
+}
+
+func TestGossipSkew(t *testing.T) {
+	alloc1, _ := makeAllocatorWithMockGossip(t, "01:00:00:01:00:00", "10.0.1.0/22", 2)
+	defer alloc1.Stop()
+	alloc2, _ := makeAllocatorWithMockGossip(t, "02:00:00:02:00:00", "10.0.1.0/22", 2)
+	alloc2.now = func() time.Time { return time.Now().Add(time.Hour * 2) }
+	defer alloc2.Stop()
+
+	if _, err := alloc1.OnGossipBroadcast(alloc2.ourName, alloc2.Encode()); err == nil {
+		t.Fail()
+	}
+}

ipam/claim.go

@@ -0,0 +1,103 @@
+package ipam
+
+import (
+	"fmt"
+
+	"github.com/weaveworks/weave/common"
+	"github.com/weaveworks/weave/net/address"
+	"github.com/weaveworks/weave/router"
+)
+
+type claim struct {
+	resultChan       chan<- error
+	ident            string
+	addr             address.Address
+	noErrorOnUnknown bool
+}
+
+// Send an error (or nil for success) back to caller listening on resultChan
+func (c *claim) sendResult(result error) {
+	// Make sure we only send a result once, since listener stops listening after that
+	if c.resultChan != nil {
+		c.resultChan <- result
+		close(c.resultChan)
+		c.resultChan = nil
+		return
+	}
+	if result != nil {
+		common.Log.Errorln("[allocator] " + result.Error())
+	}
+}
+
+// Try returns true for success (or failure), false if we need to try again later
+func (c *claim) Try(alloc *Allocator) bool {
+	if !alloc.ring.Contains(c.addr) {
+		// Address not within our universe; assume user knows what they are doing
+		alloc.infof("Ignored address %s claimed by %s - not in our universe", c.addr, c.ident)
+		c.sendResult(nil)
+		return true
+	}
+
+	alloc.establishRing()
+
+	switch owner := alloc.ring.Owner(c.addr); owner {
+	case alloc.ourName:
+		// success
+	case router.UnknownPeerName:
+		// If our ring doesn't know, it must be empty.
+		if c.noErrorOnUnknown {
+			alloc.infof("Claim %s for %s: address allocator still initializing; will try later.", c.addr, c.ident)
+			c.sendResult(nil)
+		} else {
+			c.sendResult(fmt.Errorf("%s is in the range %s, but the allocator is not initialized yet", c.addr, alloc.universe.AsCIDRString()))
+		}
+		return false
+	default:
+		alloc.debugf("requesting address %s from other peer %s", c.addr, owner)
+		err := alloc.sendSpaceRequest(owner, address.NewRange(c.addr, 1))
+		if err != nil { // can't speak to owner right now
+			if c.noErrorOnUnknown {
+				alloc.infof("Claim %s for %s: %s; will try later.", c.addr, c.ident, err)
+				c.sendResult(nil)
+			} else { // just tell the user they can't do this.
+				c.deniedBy(alloc, owner)
+			}
+		}
+		return false
+	}
+
+	// We are the owner, check we haven't given it to another container
+	switch existingIdent := alloc.findOwner(c.addr); existingIdent {
+	case "":
+		if err := alloc.space.Claim(c.addr); err == nil {
+			alloc.debugln("Claimed", c.addr, "for", c.ident)
+			alloc.addOwned(c.ident, c.addr)
+			c.sendResult(nil)
+		} else {
+			c.sendResult(err)
+		}
+	case c.ident:
+		// same identifier is claiming same address; that's OK
+		c.sendResult(nil)
+	default:
+		// Addr already owned by container on this machine
+		c.sendResult(fmt.Errorf("address %s is already owned by %s", c.addr.String(), existingIdent))
+	}
+	return true
+}
+
+func (c *claim) deniedBy(alloc *Allocator, owner router.PeerName) {
+	name, found := alloc.nicknames[owner]
+	if found {
+		name = " (" + name + ")"
+	}
+	c.sendResult(fmt.Errorf("address %s is owned by other peer %s%s", c.addr.String(), owner, name))
+}
+
+func (c *claim) Cancel() {
+	c.sendResult(fmt.Errorf("Operation cancelled."))
+}
+
+func (c *claim) ForContainer(ident string) bool {
+	return c.ident == ident
+}

ipam/http.go

@@ -0,0 +1,146 @@
+package ipam
+
+import (
+	"fmt"
+	"net/http"
+
+	"github.com/gorilla/mux"
+
+	"github.com/weaveworks/weave/common"
+	"github.com/weaveworks/weave/common/docker"
+	"github.com/weaveworks/weave/net/address"
+)
+
+func badRequest(w http.ResponseWriter, err error) {
+	http.Error(w, err.Error(), http.StatusBadRequest)
+	common.Log.Warningln("[allocator]:", err.Error())
+}
+
+// HandleHTTP wires up ipams HTTP endpoints to the provided mux.
+func (alloc *Allocator) HandleHTTP(router *mux.Router, defaultSubnet address.CIDR, dockerCli *docker.Client) {
+	router.Methods("PUT").Path("/ip/{id}/{ip}").HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		vars := mux.Vars(r)
+		ident := vars["id"]
+		ipStr := vars["ip"]
+		noErrorOnUnknown := r.FormValue("noErrorOnUnknown") == "true"
+		if ip, err := address.ParseIP(ipStr); err != nil {
+			badRequest(w, err)
+			return
+		} else if err := alloc.Claim(ident, ip, noErrorOnUnknown); err != nil {
+			badRequest(w, fmt.Errorf("Unable to claim: %s", err))
+			return
+		}
+
+		w.WriteHeader(204)
+	})
+
+	router.Methods("GET").Path("/ip/{id}/{ip}/{prefixlen}").HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		vars := mux.Vars(r)
+		cidr := vars["ip"] + "/" + vars["prefixlen"]
+		_, subnet, err := address.ParseCIDR(cidr)
+		if err != nil {
+			badRequest(w, err)
+			return
+		}
+		addr, err := alloc.Lookup(vars["id"], subnet.HostRange())
+		if err != nil {
+			http.NotFound(w, r)
+			return
+		}
+		fmt.Fprintf(w, "%s/%d", addr, subnet.PrefixLen)
+	})
+
+	router.Methods("GET").Path("/ip/{id}").HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		addr, err := alloc.Lookup(mux.Vars(r)["id"], defaultSubnet.HostRange())
+		if err != nil {
+			http.NotFound(w, r)
+			return
+		}
+		fmt.Fprintf(w, "%s/%d", addr, defaultSubnet.PrefixLen)
+	})
+
+	router.Methods("POST").Path("/ip/{id}/{ip}/{prefixlen}").HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		closedChan := w.(http.CloseNotifier).CloseNotify()
+		vars := mux.Vars(r)
+		ident := vars["id"]
+		cidrStr := vars["ip"] + "/" + vars["prefixlen"]
+		subnetAddr, cidr, err := address.ParseCIDR(cidrStr)
+		if err != nil {
+			badRequest(w, err)
+			return
+		}
+		if cidr.Start != subnetAddr {
+			badRequest(w, fmt.Errorf("Invalid subnet %s - bits after network prefix are not all zero", cidrStr))
+			return
+		}
+		addr, err := alloc.Allocate(ident, cidr.HostRange(), closedChan)
+		if err != nil {
+			badRequest(w, fmt.Errorf("Unable to allocate: %s", err))
+			return
+		}
+		if r.FormValue("check-alive") == "true" && dockerCli != nil && dockerCli.IsContainerNotRunning(ident) {
+			common.Log.Infof("[allocator] '%s' is not running: freeing %s", ident, addr)
+			alloc.Free(ident, addr)
+			return
+		}
+
+		fmt.Fprintf(w, "%s/%d", addr, cidr.PrefixLen)
+	})
+
+	router.Methods("POST").Path("/ip/{id}").HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		closedChan := w.(http.CloseNotifier).CloseNotify()
+		ident := mux.Vars(r)["id"]
+		newAddr, err := alloc.Allocate(ident, defaultSubnet.HostRange(), closedChan)
+		if err != nil {
+			badRequest(w, err)
+			return
+		}
+		if r.FormValue("check-alive") == "true" && dockerCli != nil && dockerCli.IsContainerNotRunning(ident) {
+			common.Log.Infof("[allocator] '%s' is not running: freeing %s", ident, newAddr)
+			alloc.Free(ident, newAddr)
+			return
+		}
+
+		fmt.Fprintf(w, "%s/%d", newAddr, defaultSubnet.PrefixLen)
+	})
+
+	router.Methods("DELETE").Path("/ip/{id}/{ip}").HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		vars := mux.Vars(r)
+		ident := vars["id"]
+		ipStr := vars["ip"]
+		if ip, err := address.ParseIP(ipStr); err != nil {
+			badRequest(w, err)
+			return
+		} else if err := alloc.Free(ident, ip); err != nil {
+			badRequest(w, fmt.Errorf("Unable to free: %s", err))
+			return
+		}
+
+		w.WriteHeader(204)
+	})
+
+	router.Methods("DELETE").Path("/ip/{id}").HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		ident := mux.Vars(r)["id"]
+		if err := alloc.Delete(ident); err != nil {
+			badRequest(w, err)
+			return
+		}
+
+		w.WriteHeader(204)
+	})
+
+	router.Methods("DELETE").Path("/peer").HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		alloc.Shutdown()
+		w.WriteHeader(204)
+	})
+
+	router.Methods("DELETE").Path("/peer/{id}").HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		ident := mux.Vars(r)["id"]
+		if err := alloc.AdminTakeoverRanges(ident); err != nil {
+			badRequest(w, err)
+			return
+		}
+
+		w.WriteHeader(204)
+	})
+}

ipam/http_test.go

@@ -0,0 +1,184 @@
+package ipam
+
+import (
+	"fmt"
+	"io"
+	"io/ioutil"
+	"net"
+	"net/http"
+	"strings"
+	"testing"
+	"time"
+
+	"github.com/gorilla/mux"
+	"github.com/stretchr/testify/require"
+	"github.com/weaveworks/weave/common"
+	"github.com/weaveworks/weave/net/address"
+	wt "github.com/weaveworks/weave/testing"
+)
+
+func HTTPPost(t *testing.T, url string) string {
+	resp, err := http.Post(url, "", nil)
+	require.NoError(t, err)
+	require.Equal(t, http.StatusOK, resp.StatusCode, "http response")
+	defer resp.Body.Close()
+	body, _ := ioutil.ReadAll(resp.Body)
+	return string(body)
+}
+
+func HTTPGet(t *testing.T, url string) string {
+	resp, err := http.Get(url)
+	require.NoError(t, err)
+	defer resp.Body.Close()
+	body, _ := ioutil.ReadAll(resp.Body)
+	return string(body)
+}
+
+func doHTTP(method string, url string) (resp *http.Response, err error) {
+	req, _ := http.NewRequest(method, url, nil)
+	return http.DefaultClient.Do(req)
+}
+
+func listenHTTP(alloc *Allocator, subnet address.CIDR) int {
+	router := mux.NewRouter()
+	router.HandleFunc("/status", func(w http.ResponseWriter, r *http.Request) {
+		io.WriteString(w, fmt.Sprintln(alloc))
+	})
+	alloc.HandleHTTP(router, subnet, nil)
+
+	httpListener, err := net.Listen("tcp", ":0")
+	if err != nil {
+		common.Log.Fatal("Unable to create http listener: ", err)
+	}
+
+	go func() {
+		srv := &http.Server{Handler: router}
+		if err := srv.Serve(httpListener); err != nil {
+			common.Log.Fatal("Unable to serve http: ", err)
+		}
+	}()
+	return httpListener.Addr().(*net.TCPAddr).Port
+}
+
+func identURL(port int, containerID string) string {
+	return fmt.Sprintf("http://localhost:%d/ip/%s", port, containerID)
+}
+
+func allocURL(port int, cidr string, containerID string) string {
+	return fmt.Sprintf("http://localhost:%d/ip/%s/%s", port, containerID, cidr)
+}
+
+func TestHttp(t *testing.T) {
+	var (
+		containerID = "deadbeef"
+		container2  = "baddf00d"
+		container3  = "b01df00d"
+		universe    = "10.0.0.0/8"
+		testCIDR1   = "10.0.3.8/29"
+		testCIDR2   = "10.2.0.0/16"
+		testAddr1   = "10.0.3.9/29"
+		testAddr2   = "10.2.0.1/16"
+	)
+
+	alloc, _ := makeAllocatorWithMockGossip(t, "08:00:27:01:c3:9a", universe, 1)
+	_, cidr, _ := address.ParseCIDR(universe)
+	port := listenHTTP(alloc, cidr)
+	alloc.claimRingForTesting()
+
+	// Allocate an address in each subnet, and check we got what we expected
+	cidr1a := HTTPPost(t, allocURL(port, testCIDR1, containerID))
+	require.Equal(t, testAddr1, cidr1a, "address")
+	cidr2a := HTTPPost(t, allocURL(port, testCIDR2, containerID))
+	require.Equal(t, testAddr2, cidr2a, "address")
+	// Now, make the same requests again to check the operation is idempotent
+	check := HTTPGet(t, allocURL(port, testCIDR1, containerID))
+	require.Equal(t, cidr1a, check, "address")
+	check = HTTPGet(t, allocURL(port, testCIDR2, containerID))
+	require.Equal(t, cidr2a, check, "address")
+
+	// Ask the http server for a pair of addresses for another container and check they're different
+	cidr1b := HTTPPost(t, allocURL(port, testCIDR1, container2))
+	require.False(t, cidr1b == testAddr1, "address")
+	cidr2b := HTTPPost(t, allocURL(port, testCIDR2, container2))
+	require.False(t, cidr2b == testAddr2, "address")
+
+	// Now free the first container, and we should get its addresses back when we ask
+	doHTTP("DELETE", identURL(port, containerID))
+
+	cidr1c := HTTPPost(t, allocURL(port, testCIDR1, container3))
+	require.Equal(t, testAddr1, cidr1c, "address")
+	cidr2c := HTTPPost(t, allocURL(port, testCIDR2, container3))
+	require.Equal(t, testAddr2, cidr2c, "address")
+
+	// Would like to shut down the http server at the end of this test
+	// but it's complicated.
+	// See https://groups.google.com/forum/#!topic/golang-nuts/vLHWa5sHnCE
+}
+
+func TestBadHttp(t *testing.T) {
+	var (
+		containerID = "deadbeef"
+		testCIDR1   = "10.0.0.0/8"
+	)
+
+	alloc, _ := makeAllocatorWithMockGossip(t, "08:00:27:01:c3:9a", testCIDR1, 1)
+	defer alloc.Stop()
+	_, cidr, _ := address.ParseCIDR(testCIDR1)
+	port := listenHTTP(alloc, cidr)
+
+	alloc.claimRingForTesting()
+	cidr1 := HTTPPost(t, allocURL(port, testCIDR1, containerID))
+	parts := strings.Split(cidr1, "/")
+	testAddr1 := parts[0]
+	// Verb that's not handled
+	resp, err := doHTTP("HEAD", fmt.Sprintf("http://localhost:%d/ip/%s/%s", port, containerID, testAddr1))
+	require.NoError(t, err)
+	require.Equal(t, http.StatusNotFound, resp.StatusCode, "http response")
+	// Mis-spelled URL
+	resp, err = doHTTP("POST", fmt.Sprintf("http://localhost:%d/xip/%s/", port, containerID))
+	require.NoError(t, err)
+	require.Equal(t, http.StatusNotFound, resp.StatusCode, "http response")
+	// Malformed URL
+	resp, err = doHTTP("POST", fmt.Sprintf("http://localhost:%d/ip/%s/foo/bar/baz", port, containerID))
+	require.NoError(t, err)
+	require.Equal(t, http.StatusNotFound, resp.StatusCode, "http response")
+}
+
+func TestHTTPCancel(t *testing.T) {
+	wt.RunWithTimeout(t, 2*time.Second, func() {
+		impTestHTTPCancel(t)
+	})
+}
+
+func impTestHTTPCancel(t *testing.T) {
+	var (
+		containerID = "deadbeef"
+		testCIDR1   = "10.0.3.0/29"
+	)
+
+	alloc, _ := makeAllocatorWithMockGossip(t, "08:00:27:01:c3:9a", testCIDR1, 1)
+	defer alloc.Stop()
+	alloc.claimRingForTesting()
+	_, cidr, _ := address.ParseCIDR(testCIDR1)
+	port := listenHTTP(alloc, cidr)
+
+	// Stop the alloc so nothing actually works
+	unpause := alloc.pause()
+
+	// Ask the http server for a new address
+	done := make(chan *http.Response)
+	req, _ := http.NewRequest("POST", allocURL(port, testCIDR1, containerID), nil)
+	go func() {
+		res, _ := http.DefaultClient.Do(req)
+		done <- res
+	}()
+
+	time.Sleep(100 * time.Millisecond)
+	fmt.Println("Cancelling allocate")
+	http.DefaultTransport.(*http.Transport).CancelRequest(req)
+	unpause()
+	res := <-done
+	if res != nil {
+		require.FailNow(t, "Error: Allocate returned non-nil")
+	}
+}

ipam/paxos/paxos.go

@@ -0,0 +1,263 @@
+package paxos
+
+import (
+	"github.com/weaveworks/weave/router"
+)
+
+// The node identifier.  The use of the UID here is important: Paxos
+// acceptors must not forget their promises, so it's important that a
+// node does not restart and lose its Paxos state but claim to have
+// the same ID.
+type NodeID struct {
+	Name router.PeerName
+	UID  router.PeerUID
+}
+
+// note all fields exported in structs so we can Gob them
+type ProposalID struct {
+	// round numbers begin at 1.  round 0 indicates an
+	// uninitialized ProposalID, and precedes all other ProposalIDs
+	Round    uint
+	Proposer NodeID
+}
+
+func (a ProposalID) precedes(b ProposalID) bool {
+	switch {
+	case a.Round != b.Round:
+		return a.Round < b.Round
+	case a.Proposer.Name != b.Proposer.Name:
+		return a.Proposer.Name < b.Proposer.Name
+	case a.Proposer.UID != b.Proposer.UID:
+		return a.Proposer.UID < b.Proposer.UID
+	default:
+		return false
+	}
+}
+
+func (a ProposalID) valid() bool {
+	return a.Round > 0
+}
+
+// For seeding IPAM, the value we want consensus on is a set of peer names
+type Value []router.PeerName
+
+// An AcceptedValue is a Value plus the proposal which originated that
+// Value.  The origin is not essential, but makes comparing
+// AcceptedValues easy even if comparing Values is not.
+type AcceptedValue struct {
+	Value  Value
+	Origin ProposalID
+}
+
+type NodeClaims struct {
+	// The node promises not to accept a proposal with id less
+	// than this.
+	Promise ProposalID
+
+	// The accepted proposal, if valid
+	Accepted    ProposalID
+	AcceptedVal AcceptedValue
+}
+
+func (a NodeClaims) equals(b NodeClaims) bool {
+	return a.Promise == b.Promise && a.Accepted == b.Accepted &&
+		a.AcceptedVal.Origin == b.AcceptedVal.Origin
+}
+
+type GossipState map[NodeID]NodeClaims
+
+type Node struct {
+	id     NodeID
+	quorum uint
+	knows  GossipState
+}
+
+func NewNode(name router.PeerName, uid router.PeerUID, quorum uint) *Node {
+	return &Node{
+		id:     NodeID{name, uid},
+		quorum: quorum,
+		knows:  map[NodeID]NodeClaims{},
+	}
+}
+
+func (node *Node) GossipState() GossipState {
+	return node.knows
+}
+
+// Update this node's information about what other nodes know.
+// Returns true if we learned something new.
+func (node *Node) Update(from GossipState) bool {
+	changed := false
+
+	for i, fromClaims := range from {
+		claims, ok := node.knows[i]
+		if ok {
+			if claims.Promise.precedes(fromClaims.Promise) {
+				claims.Promise = fromClaims.Promise
+				changed = true
+			}
+
+			if claims.Accepted.precedes(fromClaims.Accepted) {
+				claims.Accepted = fromClaims.Accepted
+				claims.AcceptedVal = fromClaims.AcceptedVal
+				changed = true
+			}
+		} else {
+			claims = fromClaims
+			changed = true
+		}
+
+		node.knows[i] = claims
+	}
+
+	return changed
+}
+
+func max(a uint, b uint) uint {
+	if a > b {
+		return a
+	}
+	return b
+}
+
+// Initiate a new proposal, i.e. the Paxos "Prepare" step.  This is
+// simply a matter of gossipping a new proposal that supersedes all
+// others.
+func (node *Node) Propose() {
+	// Find the highest round number around
+	round := uint(0)
+
+	for _, claims := range node.knows {
+		round = max(round, claims.Promise.Round)
+		round = max(round, claims.Accepted.Round)
+	}
+
+	ourClaims := node.knows[node.id]
+	ourClaims.Promise = ProposalID{
+		Round:    round + 1,
+		Proposer: node.id,
+	}
+	node.knows[node.id] = ourClaims
+
+	// With a quorum of 1, we can immediately accept our proposal
+	if node.quorum == 1 {
+		node.Think()
+	}
+}
+
+// The heart of the consensus algorithm. Return true if we have
+// changed our claims.
+func (node *Node) Think() bool {
+	ourClaims := node.knows[node.id]
+
+	// The "Promise" step of Paxos: Copy the highest known
+	// promise.
+	for _, claims := range node.knows {
+		if ourClaims.Promise.precedes(claims.Promise) {
+			ourClaims.Promise = claims.Promise
+		}
+	}
+
+	// The "Accept Request" step of Paxos: Acting as a proposer,
+	// do we have a proposal that has been promised by a quorum?
+	//
+	// In Paxos, the "proposer" and "acceptor" roles are distinct,
+	// so in principle a node acting as a proposer could continue
+	// trying to get its proposal acccepted even after the same
+	// node as an acceptor has superseded that proposal.  But
+	// that's pointless in a gossip context: If our promise
+	// supersedes our own proposal, then anyone who hears about
+	// that promise will not accept that proposal.  So our
+	// proposal is only in the running if it is also our promise.
+	if ourClaims.Promise.Proposer == node.id {
+		// Determine whether a quorum has promised, and the
+		// best previously-accepted value if there is one.
+		count := uint(0)
+		var accepted ProposalID
+		var acceptedVal AcceptedValue
+
+		for _, claims := range node.knows {
+			if claims.Promise == ourClaims.Promise {
+				count++
+
+				if accepted.precedes(claims.Accepted) {
+					accepted = claims.Accepted
+					acceptedVal = claims.AcceptedVal
+				}
+			}
+		}
+
+		if count >= node.quorum {
+			if !accepted.valid() {
+				acceptedVal.Value = node.pickValue()
+				acceptedVal.Origin = ourClaims.Promise
+			}
+
+			// We automatically accept our own proposal,
+			// and that's how we communicate the "accept
+			// request" to other nodes.
+			ourClaims.Accepted = ourClaims.Promise
+			ourClaims.AcceptedVal = acceptedVal
+		}
+	}
+
+	// The "Accepted" step of Paxos: If the proposal we promised
+	// on got accepted by some other node, we accept it too.
+	for _, claims := range node.knows {
+		if claims.Accepted == ourClaims.Promise {
+			ourClaims.Accepted = claims.Accepted
+			ourClaims.AcceptedVal = claims.AcceptedVal
+			break
+		}
+	}
+
+	if ourClaims.equals(node.knows[node.id]) {
+		return false
+	}
+
+	node.knows[node.id] = ourClaims
+	return true
+}
+
+// When we get to pick a value, we use the set of peer names we know
+// about.  This is not necessarily all peer names, but it is at least
+// a quorum, and so good enough for seeding the ring.
+func (node *Node) pickValue() Value {
+	val := make([]router.PeerName, len(node.knows))
+	i := 0
+	for id := range node.knows {
+		val[i] = id.Name
+		i++
+	}
+	return val
+}
+
+// Has a consensus been reached, based on the known claims of other nodes?
+func (node *Node) Consensus() (bool, AcceptedValue) {
+	counts := map[ProposalID]uint{}
+
+	for _, claims := range node.knows {
+		if claims.Accepted.valid() {
+			origin := claims.AcceptedVal.Origin
+			count := counts[origin] + 1
+			counts[origin] = count
+			if count >= node.quorum {
+				return true, claims.AcceptedVal
+			}
+		}
+	}
+
+	return false, AcceptedValue{}
+}
+
+type Status struct {
+	KnownNodes int
+	Quorum     uint
+}
+
+func NewStatus(node *Node) *Status {
+	if node == nil {
+		return nil
+	}
+	return &Status{len(node.knows), node.quorum}
+}

ipam/paxos/paxos_test.go

@@ -0,0 +1,373 @@
+package paxos
+
+import (
+	"fmt"
+	"math/rand"
+	"testing"
+	"time"
+
+	"github.com/weaveworks/weave/router"
+)
+
+type TestNode struct {
+	*Node
+
+	// Topology
+	links    []*Link
+	isolated bool
+
+	// The first consensus the Node observed
+	firstConsensus AcceptedValue
+}
+
+type Link struct {
+	from     *TestNode
+	to       *TestNode
+	converse *Link
+
+	// A link is considered ready if it is worthwhile gossipping
+	// along it (i.e. unless we already gossipped along it and the
+	// "from" node didn't change since then).  If this is <0, then
+	// the link is not ready.  Otherwise, this gives the index in
+	// the Model's readyLinks slice.
+	ready int
+}
+
+type Model struct {
+	t          *testing.T
+	r          *rand.Rand
+	quorum     uint
+	nodes      []TestNode
+	readyLinks []*Link
+	nextID     uint
+}
+
+func (m *Model) addLink(a, b *TestNode) {
+	if a == b {
+		// Never link a node to itself
+		return
+	}
+
+	ab := Link{from: a, to: b, ready: len(m.readyLinks)}
+	ba := Link{from: b, to: a, converse: &ab, ready: len(m.readyLinks) + 1}
+	ab.converse = &ba
+	a.links = append(a.links, &ab)
+	b.links = append(b.links, &ba)
+	m.readyLinks = append(m.readyLinks, &ab, &ba)
+}
+
+func (m *Model) linkExists(a, b *TestNode) bool {
+	for _, l := range a.links {
+		if l.to == b {
+			return true
+		}
+	}
+
+	return false
+}
+
+type TestParams struct {
+	// Number of nodes
+	nodeCount uint
+
+	// Probability that two nodes are connected.
+	connectedProb float32
+
+	// Probability that some node will re-propose at each
+	// step. Setting this too high makes it likely that we'll fail
+	// to converge.
+	reproposeProb float32
+
+	// Probability that some node will be isolated at each step.
+	isolateProb float32
+
+	// Probability that some node willbe restarted at each step.
+	restartProb float32
+}
+
+// Make a network of nodes with random topology
+func makeRandomModel(params *TestParams, r *rand.Rand, t *testing.T) *Model {
+	m := Model{
+		t:          t,
+		r:          r,
+		quorum:     params.nodeCount/2 + 1,
+		nodes:      make([]TestNode, params.nodeCount),
+		readyLinks: []*Link{},
+		nextID:     params.nodeCount + 1,
+	}
+
+	for i := range m.nodes {
+		m.nodes[i].Node = NewNode(router.PeerName(i/2+1),
+			router.PeerUID(r.Int63()), m.quorum)
+		m.nodes[i].Propose()
+	}
+
+	for i := 1; i < len(m.nodes); i++ {
+		// was node i connected to the other nodes yet?
+		connected := false
+
+		for j := 0; j < i; j++ {
+			if r.Float32() < params.connectedProb {
+				connected = true
+				m.addLink(&m.nodes[i], &m.nodes[j])
+			}
+		}
+
+		if !connected {
+			// node i must be connected into the graph
+			// somewhere.  So if we didn't connect it
+			// already, this is a last resort.
+			m.addLink(&m.nodes[i], &m.nodes[r.Intn(i)])
+		}
+	}
+
+	return &m
+}
+
+// Mark a link as unready
+func (m *Model) unreadyLink(link *Link) {
+	i := link.ready
+	if i >= 0 {
+		m.readyLinks[i] = m.readyLinks[len(m.readyLinks)-1]
+		m.readyLinks[i].ready = i
+		m.readyLinks = m.readyLinks[:len(m.readyLinks)-1]
+		link.ready = -1
+	}
+}
+
+// Mark a link as ready
+func (m *Model) readyLink(link *Link) {
+	if link.ready < 0 {
+		link.ready = len(m.readyLinks)
+		m.readyLinks = append(m.readyLinks, link)
+	}
+}
+
+// Mark all the outgoing links from a node as ready
+func (m *Model) nodeChanged(node *TestNode) {
+	for _, l := range node.links {
+		m.readyLink(l)
+	}
+}
+
+// Isolate a node
+func (m *Model) isolateNode(node *TestNode) {
+	node.isolated = true
+	for _, l := range node.links {
+		if l.ready >= 0 {
+			m.unreadyLink(l)
+			m.unreadyLink(l.converse)
+		}
+	}
+
+	// Isolating a node could partition the network.  We don't
+	// want to test such a case (because it could prevent
+	// consensus).  Checking for partitions would be more code
+	// than its worth, so just add some links to prevent the
+	// possibility of partitions.
+	for i := 1; i < len(node.links); i++ {
+		m.addLink(node.links[i-1].to, node.links[i].to)
+	}
+}
+
+// Restart a node
+func (m *Model) restart(node *TestNode) {
+	node.Node = NewNode(router.PeerName(m.nextID),
+		router.PeerUID(m.r.Int63()), m.quorum)
+	m.nextID++
+	node.Propose()
+
+	// The node is now ignorant, so we need to mark the links into
+	// the node as ready.
+	for _, l := range node.links {
+		if !l.to.isolated {
+			m.readyLink(l.converse)
+		}
+	}
+
+	// If a consensus was just accepted due to this node accepting
+	// it, without other nodes hearing of it, and we then restart
+	// this node, then a different consensus can occur later on.
+	// If a tree falls with no one to hear it, does it make a
+	// sound?
+	node.firstConsensus = AcceptedValue{}
+}
+
+func (m *Model) pickNode() *TestNode {
+	for {
+		node := &m.nodes[m.r.Intn(len(m.nodes))]
+		if !node.isolated {
+			return node
+		}
+	}
+}
+
+func (m *Model) simulate(params *TestParams) bool {
+	nodesLeft := uint(len(m.nodes))
+	restarts := uint(0)
+
+	for step := 0; step < 1000000; step++ {
+		if len(m.readyLinks) == 0 {
+			// Everything has converged.  This can be
+			// because consensus was reached, or because
+			// consensus became impossible, e.g. everyone
+			// promised on a particular proposal, but then
+			// the proposer restarted or was isolated.  So
+			// we detect the latter cases and force a new
+			// proposal
+			for i := range m.nodes {
+				ok, _ := m.nodes[i].Consensus()
+				if ok {
+					return true
+				}
+			}
+
+			node := m.pickNode()
+			node.Propose()
+			m.nodeChanged(node)
+		}
+
+		// Pick a ready link at random
+		i := m.r.Intn(len(m.readyLinks))
+		link := m.readyLinks[i]
+		if link.ready != i {
+			m.t.Fatal("Link in readyLinks was not ready")
+		}
+
+		// gossip across link
+		node := link.to
+		if node.Update(link.from.GossipState()) {
+			node.Think()
+
+			if !node.firstConsensus.Origin.valid() {
+				ok, val := node.Consensus()
+				if ok {
+					node.firstConsensus = val
+				}
+			}
+
+			m.nodeChanged(node)
+		}
+
+		m.unreadyLink(link)
+
+		// Re-propose?
+		if m.r.Float32() < params.reproposeProb {
+			node := m.pickNode()
+			node.Propose()
+			m.nodeChanged(node)
+		}
+
+		// Isolate?
+		if nodesLeft > m.quorum && m.r.Float32() < params.isolateProb {
+			m.isolateNode(m.pickNode())
+			nodesLeft--
+
+			// We isolated a node, so get another node to
+			// re-propose.  In reality the lack of
+			// consensus would be detected via a timeout
+			node := m.pickNode()
+			node.Propose()
+			m.nodeChanged(node)
+		}
+
+		// Restart?
+		if restarts < m.quorum && m.r.Float32() < params.restartProb {
+			restarts++
+			node := m.pickNode()
+			m.restart(node)
+			m.nodeChanged(node)
+		}
+	}
+
+	return false
+}
+
+func (m *Model) dump() {
+	for i := range m.nodes {
+		node := &m.nodes[i]
+		fmt.Println(node.id)
+		for n, claims := range node.knows {
+			fmt.Printf("\t%d %v\n", n, claims)
+		}
+	}
+}
+
+// Validate the final model state
+func (m *Model) validate() {
+	var origin ProposalID
+
+	for i := range m.nodes {
+		ok, val := m.nodes[i].Consensus()
+		if !ok {
+			//m.dump()
+			m.t.Fatal("Node doesn't know about consensus")
+		}
+
+		firstConsensus := m.nodes[i].firstConsensus
+		if firstConsensus.Origin.valid() &&
+			firstConsensus.Origin != val.Origin {
+			//m.dump()
+			m.t.Fatal("Consensus mismatch")
+		}
+
+		if i == 0 {
+			origin = val.Origin
+		} else if val.Origin != origin {
+			m.t.Fatal("Node disagrees about consensus")
+		}
+	}
+}
+
+func TestSingleNode(t *testing.T) {
+	r := rand.New(rand.NewSource(time.Now().UnixNano()))
+
+	// Test the single node case
+	params := &TestParams{
+		nodeCount:     1,
+		connectedProb: 0,
+		reproposeProb: 0,
+		isolateProb:   0,
+		restartProb:   0,
+	}
+
+	m := makeRandomModel(params, r, t)
+
+	if !m.simulate(params) {
+		m.t.Fatal("Failed to converge")
+	}
+
+	m.validate()
+}
+
+func TestPaxos(t *testing.T) {
+	r := rand.New(rand.NewSource(time.Now().UnixNano()))
+
+	params := &TestParams{
+		nodeCount:     10,
+		connectedProb: 0.5,
+		reproposeProb: 0.01,
+		isolateProb:   0.01,
+
+		// Restarts cause failures due to the case where 1)
+		// the gossip ordering is such that there is an
+		// effective partition from the start, with a quorum
+		// on one side and one node less than a quorum on the
+		// other; 2) the quorum reaches a consensus; 3) a node
+		// is restarted, and at the same time jumps the
+		// partition, so the side that was now just less than
+		// a quorum becomes a quorum; 4) the new quorum
+		// reaches a contradictory consensus.
+		restartProb: 0,
+	}
+
+	for i := 0; i < 1000; i++ {
+		m := makeRandomModel(params, r, t)
+
+		if !m.simulate(params) {
+			m.t.Fatal("Failed to converge")
+		}
+
+		m.validate()
+	}
+}

ipam/ring/entry.go

@@ -0,0 +1,98 @@
+package ring
+
+import (
+	"sort"
+
+	"github.com/weaveworks/weave/common"
+	"github.com/weaveworks/weave/net/address"
+	"github.com/weaveworks/weave/router"
+)
+
+// Entry represents entries around the ring
+type entry struct {
+	Token   address.Address // The start of this range
+	Peer    router.PeerName // Who owns this range
+	Version uint32          // Version of this range
+	Free    address.Offset  // Number of free IPs in this range
+}
+
+func (e *entry) Equal(e2 *entry) bool {
+	return e.Token == e2.Token && e.Peer == e2.Peer &&
+		e.Version == e2.Version
+}
+
+func (e *entry) update(peername router.PeerName, free address.Offset) {
+	e.Peer = peername
+	e.Version++
+	e.Free = free
+}
+
+// For compatibility with sort.Interface
+type entries []*entry
+
+func (es entries) Len() int           { return len(es) }
+func (es entries) Less(i, j int) bool { return es[i].Token < es[j].Token }
+func (es entries) Swap(i, j int)      { panic("Should never be swapping entries!") }
+
+func (es entries) entry(i int) *entry {
+	i = i % len(es)
+	if i < 0 {
+		i += len(es)
+	}
+	return es[i]
+}
+
+func (es *entries) insert(e entry) {
+	i := sort.Search(len(*es), func(j int) bool {
+		return (*es)[j].Token >= e.Token
+	})
+
+	if i < len(*es) && (*es)[i].Token == e.Token {
+		panic("Trying to insert an existing token!")
+	}
+
+	*es = append(*es, &entry{})
+	copy((*es)[i+1:], (*es)[i:])
+	(*es)[i] = &e
+}
+
+func (es entries) get(token address.Address) (*entry, bool) {
+	i := sort.Search(len(es), func(j int) bool {
+		return es[j].Token >= token
+	})
+
+	if i < len(es) && es[i].Token == token {
+		return es[i], true
+	}
+
+	return nil, false
+}
+
+// Is token between entries at i and j?
+// NB i and j can overflow and will wrap
+// NBB this function does not work very well if there is only one
+//     token on the ring; luckily an accurate answer is not needed
+//     by the call sites in this case.
+func (es entries) between(token address.Address, i, j int) bool {
+	common.Assert(i < j)
+
+	first := es.entry(i)
+	second := es.entry(j)
+
+	switch {
+	case first.Token == second.Token:
+		// This implies there is only one token
+		// on the ring (i < j and i.token == j.token)
+		// In which case everything is between, expect
+		// this one token
+		return token != first.Token
+
+	case first.Token < second.Token:
+		return first.Token <= token && token < second.Token
+
+	case second.Token < first.Token:
+		return first.Token <= token || token < second.Token
+	}
+
+	panic("Should never get here - switch covers all possibilities.")
+}

ipam/ring/expvar.go

@@ -0,0 +1,31 @@
+package ring
+
+/* Exported variables for monitoring and management */
+
+import (
+	"expvar"
+	"strconv"
+)
+
+var (
+	expRingSize    = expvar.NewMap("ipam.ringSize")
+	expRingEntries = expvar.NewMap("ipam.ringEntries")
+)
+
+type _int int
+
+func (i _int) String() string {
+	return strconv.Itoa(int(i))
+}
+
+type _uint32 uint32
+
+func (i _uint32) String() string {
+	return strconv.FormatUint(uint64(i), 10)
+}
+
+func (r *Ring) updateExportedVariables() {
+	ringName := r.Start.String()
+	expRingSize.Set(ringName, _uint32(r.End-r.Start))
+	expRingEntries.Set(ringName, _int(len(r.Entries)))
+}

ipam/ring/ring.go

@@ -0,0 +1,527 @@
+/*
+Package ring implements a simple ring CRDT.
+*/
+package ring
+
+import (
+	"bytes"
+	"errors"
+	"fmt"
+	"io"
+	"math/rand"
+	"sort"
+	"time"
+
+	"github.com/weaveworks/weave/common"
+	"github.com/weaveworks/weave/net/address"
+	"github.com/weaveworks/weave/router"
+)
+
+// Ring represents the ring itself
+type Ring struct {
+	Start, End address.Address // [min, max) tokens in this ring.  Due to wrapping, min == max (effectively)
+	Peer       router.PeerName // name of peer owning this ring instance
+	Entries    entries         // list of entries sorted by token
+}
+
+func (r *Ring) assertInvariants() {
+	err := r.checkInvariants()
+	if err != nil {
+		panic(err.Error())
+	}
+}
+
+// Errors returned by Merge
+var (
+	ErrNotSorted       = errors.New("Ring not sorted")
+	ErrTokenRepeated   = errors.New("Token appears twice in ring")
+	ErrTokenOutOfRange = errors.New("Token is out of range")
+	ErrDifferentRange  = errors.New("Received range differs from ours!")
+	ErrNewerVersion    = errors.New("Received new version for entry I own!")
+	ErrInvalidEntry    = errors.New("Received invalid state update!")
+	ErrEntryInMyRange  = errors.New("Received new entry in my range!")
+	ErrNotFound        = errors.New("No entries for peer found")
+)
+
+func (r *Ring) checkInvariants() error {
+	if !sort.IsSorted(r.Entries) {
+		return ErrNotSorted
+	}
+
+	// Check no token appears twice
+	// We know it's sorted...
+	for i := 1; i < len(r.Entries); i++ {
+		if r.Entries[i-1].Token == r.Entries[i].Token {
+			return ErrTokenRepeated
+		}
+	}
+
+	if len(r.Entries) == 0 {
+		return nil
+	}
+
+	// Check tokens are in range
+	if r.Entries.entry(0).Token < r.Start {
+		return ErrTokenOutOfRange
+	}
+	if r.Entries.entry(-1).Token >= r.End {
+		return ErrTokenOutOfRange
+	}
+
+	// Check all the freespaces are in range
+	for i, entry := range r.Entries {
+		next := r.Entries.entry(i + 1)
+		distance := r.distance(entry.Token, next.Token)
+
+		if entry.Free > distance {
+			return fmt.Errorf("Entry %s-%s reporting too much free space: %d > %d", entry.Token, next.Token, entry.Free, distance)
+		}
+	}
+
+	return nil
+}
+
+// New creates an empty ring belonging to peer.
+func New(start, end address.Address, peer router.PeerName) *Ring {
+	common.Assert(start < end)
+
+	ring := &Ring{Start: start, End: end, Peer: peer, Entries: make([]*entry, 0)}
+	ring.updateExportedVariables()
+	return ring
+}
+
+func (r *Ring) Range() address.Range {
+	return address.Range{Start: r.Start, End: r.End}
+}
+
+// Returns the distance between two tokens on this ring, dealing
+// with ranges which cross the origin
+func (r *Ring) distance(start, end address.Address) address.Offset {
+	if end > start {
+		return address.Offset(end - start)
+	}
+
+	return address.Offset((r.End - start) + (end - r.Start))
+}
+
+// GrantRangeToHost modifies the ring such that range [start, end)
+// is assigned to peer.  This may insert up to two new tokens.
+// Preconditions:
+// - start < end
+// - [start, end) must be owned by the calling peer
+func (r *Ring) GrantRangeToHost(start, end address.Address, peer router.PeerName) {
+	//fmt.Printf("%s GrantRangeToHost [%v,%v) -> %s\n", r.Peer, start, end, peer)
+
+	r.assertInvariants()
+	defer r.assertInvariants()
+	defer r.updateExportedVariables()
+
+	// ----------------- Start of Checks -----------------
+
+	common.Assert(start < end)
+	common.Assert(r.Start <= start && start < r.End)
+	common.Assert(r.Start < end && end <= r.End)
+	common.Assert(len(r.Entries) > 0)
+
+	// Look for the left-most entry greater than start, then go one previous
+	// to get the right-most entry less than or equal to start
+	preceedingPos := sort.Search(len(r.Entries), func(j int) bool {
+		return r.Entries[j].Token > start
+	})
+	preceedingPos--
+
+	// Check all tokens up to end are owned by us
+	for pos := preceedingPos; pos < len(r.Entries) && r.Entries.entry(pos).Token < end; pos++ {
+		common.Assert(r.Entries.entry(pos).Peer == r.Peer)
+	}
+
+	// ----------------- End of Checks -----------------
+
+	// Free space at start is max(length of range, distance to next token)
+	startFree := r.distance(start, r.Entries.entry(preceedingPos+1).Token)
+	if length := r.distance(start, end); startFree > length {
+		startFree = length
+	}
+	// Is there already a token at start, update it
+	if previousEntry := r.Entries.entry(preceedingPos); previousEntry.Token == start {
+		previousEntry.update(peer, startFree)
+	} else {
+		// Otherwise, these isn't a token here, insert a new one.
+		r.Entries.insert(entry{Token: start, Peer: peer, Free: startFree})
+		preceedingPos++
+		// Reset free space on previous entry, which we own.
+		previousEntry.update(r.Peer, r.distance(previousEntry.Token, start))
+	}
+
+	// Give all intervening tokens to the other peer
+	pos := preceedingPos + 1
+	for ; pos < len(r.Entries) && r.Entries.entry(pos).Token < end; pos++ {
+		entry := r.Entries.entry(pos)
+		entry.update(peer, address.Min(entry.Free, r.distance(entry.Token, end)))
+	}
+
+	// There is never an entry with a token of r.End, as the end of
+	// the ring is exclusive.
+	if end == r.End {
+		end = r.Start
+	}
+
+	//  If there is a token equal to the end of the range, we don't need to do anything further
+	if _, found := r.Entries.get(end); found {
+		return
+	}
+
+	// If not, we need to insert a token such that we claim this bit on the end.
+	endFree := r.distance(end, r.Entries.entry(pos).Token)
+	r.Entries.insert(entry{Token: end, Peer: r.Peer, Free: endFree})
+}
+
+// Merge the given ring into this ring and return any new ranges added
+func (r *Ring) Merge(gossip Ring) error {
+	r.assertInvariants()
+	defer r.assertInvariants()
+	defer r.updateExportedVariables()
+
+	// Don't panic when checking the gossiped in ring.
+	// In this case just return any error found.
+	if err := gossip.checkInvariants(); err != nil {
+		return err
+	}
+
+	if r.Start != gossip.Start || r.End != gossip.End {
+		return ErrDifferentRange
+	}
+
+	// Now merge their ring with yours, in a temporary ring.
+	var result entries
+	addToResult := func(e entry) { result = append(result, &e) }
+
+	var mine, theirs *entry
+	var previousOwner *router.PeerName
+	// i is index into r.Entries; j is index into gossip.Entries
+	var i, j int
+	for i < len(r.Entries) && j < len(gossip.Entries) {
+		mine, theirs = r.Entries[i], gossip.Entries[j]
+		switch {
+		case mine.Token < theirs.Token:
+			addToResult(*mine)
+			previousOwner = &mine.Peer
+			i++
+		case mine.Token > theirs.Token:
+			// insert, checking that a range owned by us hasn't been split
+			if previousOwner != nil && *previousOwner == r.Peer && theirs.Peer != r.Peer {
+				return ErrEntryInMyRange
+			}
+			addToResult(*theirs)
+			previousOwner = nil
+			j++
+		case mine.Token == theirs.Token:
+			// merge
+			switch {
+			case mine.Version >= theirs.Version:
+				if mine.Version == theirs.Version && !mine.Equal(theirs) {
+					common.Log.Debugf("Error merging entries at %s - %v != %v", mine.Token, mine, theirs)
+					return ErrInvalidEntry
+				}
+				addToResult(*mine)
+				previousOwner = &mine.Peer
+			case mine.Version < theirs.Version:
+				if mine.Peer == r.Peer { // We shouldn't receive updates to our own tokens
+					return ErrNewerVersion
+				}
+				addToResult(*theirs)
+				previousOwner = nil
+			}
+			i++
+			j++
+		}
+	}
+
+	// At this point, either i is at the end of r or j is at the end
+	// of gossip, so copy over the remaining entries.
+
+	for ; i < len(r.Entries); i++ {
+		mine = r.Entries[i]
+		addToResult(*mine)
+	}
+
+	for ; j < len(gossip.Entries); j++ {
+		theirs = gossip.Entries[j]
+		if previousOwner != nil && *previousOwner == r.Peer && theirs.Peer != r.Peer {
+			return ErrEntryInMyRange
+		}
+		addToResult(*theirs)
+		previousOwner = nil
+	}
+
+	r.Entries = result
+	return nil
+}
+
+// Empty returns true if the ring has no entries
+func (r *Ring) Empty() bool {
+	return len(r.Entries) == 0
+}
+
+// Given a slice of ranges which are all in the right order except
+// possibly the last one spans zero, fix that up and return the slice
+func (r *Ring) splitRangesOverZero(ranges []address.Range) []address.Range {
+	if len(ranges) == 0 {
+		return ranges
+	}
+	lastRange := ranges[len(ranges)-1]
+	// if end token == start (ie last) entry on ring, we want to actually use r.End
+	if lastRange.End == r.Start {
+		ranges[len(ranges)-1].End = r.End
+	} else if lastRange.End <= lastRange.Start {
+		// We wrapped; want to split around 0
+		// First shuffle everything up as we want results to be sorted
+		ranges = append(ranges, address.Range{})
+		copy(ranges[1:], ranges[:len(ranges)-1])
+		ranges[0] = address.Range{Start: r.Start, End: lastRange.End}
+		ranges[len(ranges)-1].End = r.End
+	}
+	return ranges
+}
+
+// OwnedRanges returns slice of Ranges, ordered by IP, indicating which
+// ranges are owned by this peer.  Will split ranges which
+// span 0 in the ring.
+func (r *Ring) OwnedRanges() (result []address.Range) {
+	r.assertInvariants()
+
+	for i, entry := range r.Entries {
+		if entry.Peer == r.Peer {
+			nextEntry := r.Entries.entry(i + 1)
+			result = append(result, address.Range{Start: entry.Token, End: nextEntry.Token})
+		}
+	}
+
+	return r.splitRangesOverZero(result)
+}
+
+// ClaimForPeers claims the entire ring for the array of peers passed
+// in.  Only works for empty rings.
+func (r *Ring) ClaimForPeers(peers []router.PeerName) {
+	common.Assert(r.Empty())
+	defer r.assertInvariants()
+	defer r.updateExportedVariables()
+
+	totalSize := r.distance(r.Start, r.End)
+	share := totalSize/address.Offset(len(peers)) + 1
+	remainder := totalSize % address.Offset(len(peers))
+	pos := r.Start
+
+	for i, peer := range peers {
+		if address.Offset(i) == remainder {
+			share--
+			if share == 0 {
+				break
+			}
+		}
+
+		if e, found := r.Entries.get(pos); found {
+			e.update(peer, share)
+		} else {
+			r.Entries.insert(entry{Token: pos, Peer: peer, Free: share})
+		}
+
+		pos += address.Address(share)
+	}
+
+	common.Assert(pos == r.End)
+}
+
+func (r *Ring) FprintWithNicknames(w io.Writer, m map[router.PeerName]string) {
+	for _, entry := range r.Entries {
+		nickname, found := m[entry.Peer]
+		if found {
+			nickname = fmt.Sprintf(" (%s)", nickname)
+		}
+
+		fmt.Fprintf(w, "\n  %s -> %s%s (v%d)", entry.Token,
+			entry.Peer, nickname, entry.Version)
+	}
+}
+
+func (r *Ring) String() string {
+	var buffer bytes.Buffer
+	fmt.Fprintf(&buffer, "Ring [%s, %s)", r.Start, r.End)
+	r.FprintWithNicknames(&buffer, make(map[router.PeerName]string))
+	return buffer.String()
+}
+
+// ReportFree is used by the allocator to tell the ring how many free
+// ips are in a given range, so that ChoosePeersToAskForSpace can make
+// more intelligent decisions.
+func (r *Ring) ReportFree(freespace map[address.Address]address.Offset) {
+	r.assertInvariants()
+	defer r.assertInvariants()
+	defer r.updateExportedVariables()
+
+	common.Assert(!r.Empty())
+	entries := r.Entries
+
+	// As OwnedRanges splits around the origin, we need to
+	// detect that here and fix up freespace
+	if free, found := freespace[r.Start]; found && entries.entry(0).Token != r.Start {
+		lastToken := entries.entry(-1).Token
+		prevFree, found := freespace[lastToken]
+		common.Assert(found)
+		freespace[lastToken] = prevFree + free
+		delete(freespace, r.Start)
+	}
+
+	for start, free := range freespace {
+		// Look for entry
+		i := sort.Search(len(entries), func(j int) bool {
+			return entries[j].Token >= start
+		})
+
+		// Are you trying to report free on space I don't own?
+		common.Assert(i < len(entries) && entries[i].Token == start && entries[i].Peer == r.Peer)
+
+		// Check we're not reporting more space than the range
+		entry, next := entries.entry(i), entries.entry(i+1)
+		maxSize := r.distance(entry.Token, next.Token)
+		common.Assert(free <= maxSize)
+
+		if entries[i].Free == free {
+			return
+		}
+
+		entries[i].Free = free
+		entries[i].Version++
+	}
+}
+
+type weightedPeer struct {
+	weight   float64
+	peername router.PeerName
+}
+type weightedPeers []weightedPeer
+
+// Note Less is using > so that bigger weights sort earlier
+func (ws weightedPeers) Less(i, j int) bool { return ws[i].weight > ws[j].weight }
+func (ws weightedPeers) Len() int           { return len(ws) }
+func (ws weightedPeers) Swap(i, j int)      { ws[i], ws[j] = ws[j], ws[i] }
+
+// ChoosePeersToAskForSpace returns all peers we can ask for space in
+// the range [start, end), in weighted-random order.  Assumes start<end.
+func (r *Ring) ChoosePeersToAskForSpace(start, end address.Address) []router.PeerName {
+	var (
+		sum               address.Offset
+		totalSpacePerPeer = make(map[router.PeerName]address.Offset) // Compute total free space per peer
+	)
+
+	// iterate through tokens
+	for i, entry := range r.Entries {
+		// Ignore entries that don't span the range we want
+		if i+1 < len(r.Entries) && r.Entries.entry(i+1).Token-1 < start {
+			continue
+		}
+		if entry.Token >= end {
+			break
+		}
+		// Ignore ranges with no free space
+		if entry.Free <= 0 {
+			continue
+		}
+
+		// Don't talk to yourself
+		if entry.Peer == r.Peer {
+			continue
+		}
+
+		totalSpacePerPeer[entry.Peer] += entry.Free
+		sum += entry.Free
+	}
+
+	// Compute weighted random numbers, then sort.
+	// This isn't perfect, e.g. an item with weight 2 will get chosen more than
+	// twice as often as an item with weight 1, but it's good enough for our purposes.
+	ws := make(weightedPeers, 0, len(totalSpacePerPeer))
+	for peername, space := range totalSpacePerPeer {
+		ws = append(ws, weightedPeer{weight: float64(space) * rand.Float64(), peername: peername})
+	}
+	sort.Sort(ws)
+	result := make([]router.PeerName, len(ws))
+	for i, wp := range ws {
+		result[i] = wp.peername
+	}
+	return result
+}
+
+func (r *Ring) PickPeerForTransfer() router.PeerName {
+	for _, entry := range r.Entries {
+		if entry.Peer != r.Peer {
+			return entry.Peer
+		}
+	}
+	return router.UnknownPeerName
+}
+
+// Transfer will mark all entries associated with 'from' peer as owned by 'to' peer
+// and return ranges indicating the new space we picked up
+func (r *Ring) Transfer(from, to router.PeerName) ([]address.Range, error) {
+	r.assertInvariants()
+	defer r.assertInvariants()
+	defer r.updateExportedVariables()
+
+	var newRanges []address.Range
+	found := false
+
+	for i, entry := range r.Entries {
+		if entry.Peer == from {
+			found = true
+			entry.Peer = to
+			entry.Version++
+			newRanges = append(newRanges, address.Range{Start: entry.Token, End: r.Entries.entry(i + 1).Token})
+		}
+	}
+
+	if !found {
+		return nil, ErrNotFound
+	}
+
+	return r.splitRangesOverZero(newRanges), nil
+}
+
+// Contains returns true if addr is in this ring
+func (r *Ring) Contains(addr address.Address) bool {
+	return addr >= r.Start && addr < r.End
+}
+
+// Owner returns the peername which owns the range containing addr
+func (r *Ring) Owner(token address.Address) router.PeerName {
+	common.Assert(r.Start <= token && token < r.End)
+
+	r.assertInvariants()
+	// There can be no owners on an empty ring
+	if r.Empty() {
+		return router.UnknownPeerName
+	}
+
+	// Look for the right-most entry, less than or equal to token
+	preceedingEntry := sort.Search(len(r.Entries), func(j int) bool {
+		return r.Entries[j].Token > token
+	})
+	preceedingEntry--
+	entry := r.Entries.entry(preceedingEntry)
+	return entry.Peer
+}
+
+// Get the set of PeerNames mentioned in the ring
+func (r *Ring) PeerNames() map[router.PeerName]struct{} {
+	res := make(map[router.PeerName]struct{})
+
+	for _, entry := range r.Entries {
+		res[entry.Peer] = struct{}{}
+	}
+
+	return res
+}
+
+func init() {
+	rand.Seed(time.Now().UTC().UnixNano())
+}

ipam/ring/ring_test.go

@@ -0,0 +1,746 @@
+package ring
+
+import (
+	"bytes"
+	"fmt"
+	"math/rand"
+	"sort"
+	"testing"
+
+	"github.com/stretchr/testify/require"
+	"github.com/weaveworks/weave/common"
+	"github.com/weaveworks/weave/net/address"
+	"github.com/weaveworks/weave/router"
+)
+
+var (
+	peer1name, _ = router.PeerNameFromString("01:00:00:00:02:00")
+	peer2name, _ = router.PeerNameFromString("02:00:00:00:02:00")
+	peer3name, _ = router.PeerNameFromString("03:00:00:00:02:00")
+
+	start, end    = ParseIP("10.0.0.0"), ParseIP("10.0.0.255")
+	dot10, dot245 = ParseIP("10.0.0.10"), ParseIP("10.0.0.245")
+	dot250        = ParseIP("10.0.0.250")
+	middle        = ParseIP("10.0.0.128")
+)
+
+func ParseIP(s string) address.Address {
+	addr, _ := address.ParseIP(s)
+	return addr
+}
+
+func TestInvariants(t *testing.T) {
+	ring := New(start, end, peer1name)
+
+	// Check ring is sorted
+	ring.Entries = []*entry{{Token: dot245, Peer: peer1name}, {Token: dot10, Peer: peer2name}}
+	require.True(t, ring.checkInvariants() == ErrNotSorted, "Expected error")
+
+	// Check tokens don't appear twice
+	ring.Entries = []*entry{{Token: dot245, Peer: peer1name}, {Token: dot245, Peer: peer2name}}
+	require.True(t, ring.checkInvariants() == ErrTokenRepeated, "Expected error")
+
+	// Check tokens are in bounds
+	ring = New(dot10, dot245, peer1name)
+	ring.Entries = []*entry{{Token: start, Peer: peer1name}}
+	require.True(t, ring.checkInvariants() == ErrTokenOutOfRange, "Expected error")
+
+	ring.Entries = []*entry{{Token: end, Peer: peer1name}}
+	require.True(t, ring.checkInvariants() == ErrTokenOutOfRange, "Expected error")
+}
+
+func TestInsert(t *testing.T) {
+	ring := New(start, end, peer1name)
+	ring.Entries = []*entry{{Token: start, Peer: peer1name, Free: 255}}
+
+	require.Panics(t, func() {
+		ring.Entries.insert(entry{Token: start, Peer: peer1name})
+	})
+
+	ring.Entries.entry(0).Free = 0
+	ring.Entries.insert(entry{Token: dot245, Peer: peer1name})
+	ring2 := New(start, end, peer1name)
+	ring2.Entries = []*entry{{Token: start, Peer: peer1name, Free: 0}, {Token: dot245, Peer: peer1name}}
+	require.Equal(t, ring2, ring)
+
+	ring.Entries.insert(entry{Token: dot10, Peer: peer1name})
+	ring2.Entries = []*entry{{Token: start, Peer: peer1name, Free: 0}, {Token: dot10, Peer: peer1name}, {Token: dot245, Peer: peer1name}}
+	require.Equal(t, ring2, ring)
+}
+
+func TestBetween(t *testing.T) {
+	ring1 := New(start, end, peer1name)
+	ring1.Entries = []*entry{{Token: start, Peer: peer1name, Free: 255}}
+
+	// First off, in a ring where everything is owned by the peer
+	// between should return true for everything
+	for i := 1; i <= 255; i++ {
+		ip := ParseIP(fmt.Sprintf("10.0.0.%d", i))
+		require.True(t, ring1.Entries.between(ip, 0, 1), "between should be true!")
+	}
+
+	// Now, construct a ring with entries at +10 and -10
+	// And check the correct behaviour
+
+	ring1.Entries = []*entry{{Token: dot10, Peer: peer1name}, {Token: dot245, Peer: peer2name}}
+	ring1.assertInvariants()
+	for i := 10; i <= 244; i++ {
+		ipStr := fmt.Sprintf("10.0.0.%d", i)
+		ip := ParseIP(ipStr)
+		require.True(t, ring1.Entries.between(ip, 0, 1),
+			fmt.Sprintf("Between should be true for %s!", ipStr))
+		require.False(t, ring1.Entries.between(ip, 1, 2),
+			fmt.Sprintf("Between should be false for %s!", ipStr))
+	}
+	for i := 0; i <= 9; i++ {
+		ipStr := fmt.Sprintf("10.0.0.%d", i)
+		ip := ParseIP(ipStr)
+		require.False(t, ring1.Entries.between(ip, 0, 1),
+			fmt.Sprintf("Between should be false for %s!", ipStr))
+		require.True(t, ring1.Entries.between(ip, 1, 2),
+			fmt.Sprintf("Between should be true for %s!", ipStr))
+	}
+	for i := 245; i <= 255; i++ {
+		ipStr := fmt.Sprintf("10.0.0.%d", i)
+		ip := ParseIP(ipStr)
+		require.False(t, ring1.Entries.between(ip, 0, 1),
+			fmt.Sprintf("Between should be false for %s!", ipStr))
+		require.True(t, ring1.Entries.between(ip, 1, 2),
+			fmt.Sprintf("Between should be true for %s!", ipStr))
+	}
+}
+
+func TestGrantSimple(t *testing.T) {
+	ring1 := New(start, end, peer1name)
+	ring2 := New(start, end, peer2name)
+
+	// Claim everything for peer1
+	ring1.ClaimItAll()
+	require.Equal(t, entries{{Token: start, Peer: peer1name, Free: 255}}, ring1.Entries)
+
+	// Now grant everything to peer2
+	ring1.GrantRangeToHost(start, end, peer2name)
+	ring2.Entries = []*entry{{Token: start, Peer: peer2name, Free: 255, Version: 1}}
+	require.Equal(t, ring2.Entries, ring1.Entries)
+
+	// Now spint back to peer 1
+	ring2.GrantRangeToHost(dot10, end, peer1name)
+	ring1.Entries = []*entry{{Token: start, Peer: peer2name, Free: 10, Version: 2},
+		{Token: dot10, Peer: peer1name, Free: 245}}
+	require.Equal(t, ring2.Entries, ring1.Entries)
+
+	// And spint back to peer 2 again
+	ring1.GrantRangeToHost(dot245, end, peer2name)
+	require.Equal(t, entries{{Token: start, Peer: peer2name, Free: 10, Version: 2},
+		{Token: dot10, Peer: peer1name, Free: 235, Version: 1},
+		{Token: dot245, Peer: peer2name, Free: 10}}, ring1.Entries)
+
+	// Grant range spanning a live token
+	ring1.Entries = []*entry{{Token: start, Peer: peer1name, Free: 10, Version: 2},
+		{Token: dot10, Peer: peer1name, Free: 235}, {Token: dot245, Peer: peer1name, Free: 10}}
+	ring1.GrantRangeToHost(dot10, end, peer2name)
+	require.Equal(t, entries{{Token: start, Peer: peer1name, Free: 10, Version: 2},
+		{Token: dot10, Peer: peer2name, Free: 235, Version: 1},
+		{Token: dot245, Peer: peer2name, Free: 10, Version: 1}}, ring1.Entries)
+
+}
+
+func TestGrantSplit(t *testing.T) {
+	ring1 := New(start, end, peer1name)
+	ring2 := New(start, end, peer2name)
+
+	// Claim everything for peer1
+	ring1.Entries = []*entry{{Token: start, Peer: peer1name, Free: 255}}
+	ring2.Merge(*ring1)
+	require.Equal(t, ring2.Entries, ring1.Entries)
+
+	// Now grant a split range to peer2
+	ring1.GrantRangeToHost(dot10, dot245, peer2name)
+	require.Equal(t, entries{{Token: start, Peer: peer1name, Free: 10, Version: 1},
+		{Token: dot10, Peer: peer2name, Free: 235},
+		{Token: dot245, Peer: peer1name, Free: 10}}, ring1.Entries)
+
+	ring1.assertInvariants()
+
+	// Grant range spanning a live token, and inserting a new token
+	ring1.Entries = []*entry{{Token: start, Peer: peer1name, Free: 10, Version: 2},
+		{Token: dot10, Peer: peer1name, Free: 118}, {Token: middle, Peer: peer1name, Free: 127}}
+	ring1.GrantRangeToHost(dot10, dot245, peer2name)
+	require.Equal(t, entries{{Token: start, Peer: peer1name, Free: 10, Version: 2},
+		{Token: dot10, Peer: peer2name, Free: 118, Version: 1},
+		{Token: middle, Peer: peer2name, Free: 117, Version: 1},
+		{Token: dot245, Peer: peer1name, Free: 10, Version: 0}}, ring1.Entries)
+
+	ring1.assertInvariants()
+}
+
+func TestMergeSimple(t *testing.T) {
+	ring1 := New(start, end, peer1name)
+	ring2 := New(start, end, peer2name)
+
+	// Claim everything for peer1
+	ring1.ClaimItAll()
+	ring1.GrantRangeToHost(middle, end, peer2name)
+	require.NoError(t, ring2.Merge(*ring1))
+
+	require.Equal(t, entries{{Token: start, Peer: peer1name, Free: 128, Version: 1},
+		{Token: middle, Peer: peer2name, Free: 127}}, ring1.Entries)
+
+	require.Equal(t, ring2.Entries, ring1.Entries)
+
+	// Now to two different operations on either side,
+	// check we can Merge again
+	ring1.GrantRangeToHost(start, middle, peer2name)
+	ring2.GrantRangeToHost(middle, end, peer1name)
+
+	require.NoError(t, ring2.Merge(*ring1))
+	require.NoError(t, ring1.Merge(*ring2))
+
+	require.Equal(t, entries{{Token: start, Peer: peer2name, Free: 128, Version: 2},
+		{Token: middle, Peer: peer1name, Free: 127, Version: 1}}, ring1.Entries)
+
+	require.Equal(t, ring2.Entries, ring1.Entries)
+}
+
+func TestMergeErrors(t *testing.T) {
+	// Cannot Merge in an invalid ring
+	ring1 := New(start, end, peer1name)
+	ring2 := New(start, end, peer2name)
+	ring2.Entries = []*entry{{Token: middle, Peer: peer2name}, {Token: start, Peer: peer2name}}
+	require.True(t, ring1.Merge(*ring2) == ErrNotSorted, "Expected ErrNotSorted")
+
+	// Should Merge two rings for different ranges
+	ring2 = New(start, middle, peer2name)
+	ring2.Entries = []*entry{}
+	require.True(t, ring1.Merge(*ring2) == ErrDifferentRange, "Expected ErrDifferentRange")
+
+	// Cannot Merge newer version of entry I own
+	ring2 = New(start, end, peer2name)
+	ring1.Entries = []*entry{{Token: start, Peer: peer1name}}
+	ring2.Entries = []*entry{{Token: start, Peer: peer1name, Version: 1}}
+	require.True(t, ring1.Merge(*ring2) == ErrNewerVersion, "Expected ErrNewerVersion")
+
+	// Cannot Merge two entries with same version but different hosts
+	ring1.Entries = []*entry{{Token: start, Peer: peer1name}}
+	ring2.Entries = []*entry{{Token: start, Peer: peer2name}}
+	require.True(t, ring1.Merge(*ring2) == ErrInvalidEntry, "Expected ErrInvalidEntry")
+
+	// Cannot Merge an entry into a range I own
+	ring1.Entries = []*entry{{Token: start, Peer: peer1name}}
+	ring2.Entries = []*entry{{Token: middle, Peer: peer2name}}
+	require.True(t, ring1.Merge(*ring2) == ErrEntryInMyRange, "Expected ErrEntryInMyRange")
+}
+
+func TestMergeMore(t *testing.T) {
+	ring1 := New(start, end, peer1name)
+	ring2 := New(start, end, peer2name)
+
+	assertRing := func(ring *Ring, entries entries) {
+		require.Equal(t, entries, ring.Entries)
+	}
+
+	assertRing(ring1, []*entry{})
+	assertRing(ring2, []*entry{})
+
+	// Claim everything for peer1
+	ring1.ClaimItAll()
+	assertRing(ring1, []*entry{{Token: start, Peer: peer1name, Free: 255}})
+	assertRing(ring2, []*entry{})
+
+	// Check the Merge sends it to the other ring
+	require.NoError(t, ring2.Merge(*ring1))
+	assertRing(ring1, []*entry{{Token: start, Peer: peer1name, Free: 255}})
+	assertRing(ring2, []*entry{{Token: start, Peer: peer1name, Free: 255}})
+
+	// Give everything to peer2
+	ring1.GrantRangeToHost(start, end, peer2name)
+	assertRing(ring1, []*entry{{Token: start, Peer: peer2name, Free: 255, Version: 1}})
+	assertRing(ring2, []*entry{{Token: start, Peer: peer1name, Free: 255}})
+
+	require.NoError(t, ring2.Merge(*ring1))
+	assertRing(ring1, []*entry{{Token: start, Peer: peer2name, Free: 255, Version: 1}})
+	assertRing(ring2, []*entry{{Token: start, Peer: peer2name, Free: 255, Version: 1}})
+
+	// And carve off some space
+	ring2.GrantRangeToHost(middle, end, peer1name)
+	assertRing(ring2, []*entry{{Token: start, Peer: peer2name, Free: 128, Version: 2},
+		{Token: middle, Peer: peer1name, Free: 127}})
+	assertRing(ring1, []*entry{{Token: start, Peer: peer2name, Free: 255, Version: 1}})
+
+	// And Merge back
+	require.NoError(t, ring1.Merge(*ring2))
+	assertRing(ring1, []*entry{{Token: start, Peer: peer2name, Free: 128, Version: 2},
+		{Token: middle, Peer: peer1name, Free: 127}})
+	assertRing(ring2, []*entry{{Token: start, Peer: peer2name, Free: 128, Version: 2},
+		{Token: middle, Peer: peer1name, Free: 127}})
+
+	// This should be a no-op
+	require.NoError(t, ring2.Merge(*ring1))
+	assertRing(ring1, []*entry{{Token: start, Peer: peer2name, Free: 128, Version: 2},
+		{Token: middle, Peer: peer1name, Free: 127}})
+	assertRing(ring2, []*entry{{Token: start, Peer: peer2name, Free: 128, Version: 2},
+		{Token: middle, Peer: peer1name, Free: 127}})
+}
+
+func TestMergeSplit(t *testing.T) {
+	ring1 := New(start, end, peer1name)
+	ring2 := New(start, end, peer2name)
+
+	// Claim everything for peer2
+	ring1.Entries = []*entry{{Token: start, Peer: peer2name, Free: 255}}
+	require.NoError(t, ring2.Merge(*ring1))
+	require.Equal(t, ring2.Entries, ring1.Entries)
+
+	// Now grant a split range to peer1
+	ring2.GrantRangeToHost(dot10, dot245, peer1name)
+	require.Equal(t, entries{{Token: start, Peer: peer2name, Free: 10, Version: 1},
+		{Token: dot10, Peer: peer1name, Free: 235},
+		{Token: dot245, Peer: peer2name, Free: 10}}, ring2.Entries)
+
+	require.NoError(t, ring1.Merge(*ring2))
+	require.Equal(t, entries{{Token: start, Peer: peer2name, Free: 10, Version: 1},
+		{Token: dot10, Peer: peer1name, Free: 235},
+		{Token: dot245, Peer: peer2name, Free: 10}}, ring1.Entries)
+
+	require.Equal(t, ring2.Entries, ring1.Entries)
+}
+
+func TestMergeSplit2(t *testing.T) {
+	ring1 := New(start, end, peer1name)
+	ring2 := New(start, end, peer2name)
+
+	// Claim everything for peer2
+	ring1.Entries = []*entry{{Token: start, Peer: peer2name, Free: 250}, {Token: dot250, Peer: peer2name, Free: 5}}
+	require.NoError(t, ring2.Merge(*ring1))
+	require.Equal(t, ring2.Entries, ring1.Entries)
+
+	// Now grant a split range to peer1
+	ring2.GrantRangeToHost(dot10, dot245, peer1name)
+	require.Equal(t, entries{{Token: start, Peer: peer2name, Free: 10, Version: 1},
+		{Token: dot10, Peer: peer1name, Free: 235},
+		{Token: dot245, Peer: peer2name, Free: 5}, {Token: dot250, Peer: peer2name, Free: 5}}, ring2.Entries)
+
+	require.NoError(t, ring1.Merge(*ring2))
+	require.Equal(t, entries{{Token: start, Peer: peer2name, Free: 10, Version: 1},
+		{Token: dot10, Peer: peer1name, Free: 235},
+		{Token: dot245, Peer: peer2name, Free: 5}, {Token: dot250, Peer: peer2name, Free: 5}}, ring1.Entries)
+
+	require.Equal(t, ring2.Entries, ring1.Entries)
+}
+
+// A simple test, very similar to above, but using the marshalling to byte[]s
+func TestGossip(t *testing.T) {
+	ring1 := New(start, end, peer1name)
+	ring2 := New(start, end, peer2name)
+
+	assertRing := func(ring *Ring, entries entries) {
+		require.Equal(t, entries, ring.Entries)
+	}
+
+	assertRing(ring1, []*entry{})
+	assertRing(ring2, []*entry{})
+
+	// Claim everything for peer1
+	ring1.ClaimItAll()
+	assertRing(ring1, []*entry{{Token: start, Peer: peer1name, Free: 255}})
+	assertRing(ring2, []*entry{})
+
+	// Check the Merge sends it to the other ring
+	require.NoError(t, ring2.Merge(*ring1))
+	assertRing(ring1, []*entry{{Token: start, Peer: peer1name, Free: 255}})
+	assertRing(ring2, []*entry{{Token: start, Peer: peer1name, Free: 255}})
+}
+
+func assertPeersWithSpace(t *testing.T, ring *Ring, start, end address.Address, expected int) []router.PeerName {
+	peers := ring.ChoosePeersToAskForSpace(start, end)
+	require.Equal(t, expected, len(peers))
+	return peers
+}
+
+func TestFindFree(t *testing.T) {
+	ring1 := New(start, end, peer1name)
+
+	assertPeersWithSpace(t, ring1, start, end, 0)
+
+	ring1.Entries = []*entry{{Token: start, Peer: peer1name}}
+	assertPeersWithSpace(t, ring1, start, end, 0)
+
+	// We shouldn't return outselves
+	ring1.ReportFree(map[address.Address]address.Offset{start: 10})
+	assertPeersWithSpace(t, ring1, start, end, 0)
+
+	ring1.Entries = []*entry{{Token: start, Peer: peer1name, Free: 1},
+		{Token: middle, Peer: peer1name, Free: 1}}
+	assertPeersWithSpace(t, ring1, start, end, 0)
+	ring1.assertInvariants()
+
+	// We should return others
+	var peers []router.PeerName
+
+	ring1.Entries = []*entry{{Token: start, Peer: peer2name, Free: 1}}
+	peers = assertPeersWithSpace(t, ring1, start, end, 1)
+	require.Equal(t, peer2name, peers[0])
+
+	ring1.Entries = []*entry{{Token: start, Peer: peer2name, Free: 1},
+		{Token: middle, Peer: peer3name, Free: 1}}
+	peers = assertPeersWithSpace(t, ring1, start, middle, 1)
+	require.Equal(t, peer2name, peers[0])
+
+	peers = assertPeersWithSpace(t, ring1, middle, end, 1)
+	require.Equal(t, peer3name, peers[0])
+
+	assertPeersWithSpace(t, ring1, start, end, 2)
+	ring1.assertInvariants()
+}
+
+func TestReportFree(t *testing.T) {
+	ring1 := New(start, end, peer1name)
+	ring2 := New(start, end, peer2name)
+
+	ring1.ClaimItAll()
+	ring1.GrantRangeToHost(middle, end, peer2name)
+	require.NoError(t, ring2.Merge(*ring1))
+
+	freespace := make(map[address.Address]address.Offset)
+	for _, r := range ring2.OwnedRanges() {
+		freespace[r.Start] = 0
+	}
+	ring2.ReportFree(freespace)
+}
+
+func TestMisc(t *testing.T) {
+	ring := New(start, end, peer1name)
+
+	require.True(t, ring.Empty(), "empty")
+
+	ring.ClaimItAll()
+	println(ring.String())
+}
+
+func TestEmptyGossip(t *testing.T) {
+	ring1 := New(start, end, peer1name)
+	ring2 := New(start, end, peer2name)
+
+	ring1.ClaimItAll()
+	// This used to panic, and it shouldn't
+	require.NoError(t, ring1.Merge(*ring2))
+}
+
+func TestMergeOldMessage(t *testing.T) {
+	ring1 := New(start, end, peer1name)
+	ring2 := New(start, end, peer2name)
+
+	ring1.ClaimItAll()
+	require.NoError(t, ring2.Merge(*ring1))
+
+	ring1.GrantRangeToHost(middle, end, peer1name)
+	require.NoError(t, ring1.Merge(*ring2))
+}
+
+func TestSplitRangeAtBeginning(t *testing.T) {
+	ring1 := New(start, end, peer1name)
+	ring2 := New(start, end, peer2name)
+
+	ring1.ClaimItAll()
+	require.NoError(t, ring2.Merge(*ring1))
+
+	ring1.GrantRangeToHost(start, middle, peer2name)
+	require.NoError(t, ring2.Merge(*ring1))
+}
+
+func TestOwnedRange(t *testing.T) {
+	ring1 := New(start, end, peer1name)
+	ring1.ClaimItAll()
+
+	require.Equal(t, []address.Range{{Start: start, End: end}}, ring1.OwnedRanges())
+
+	ring1.GrantRangeToHost(middle, end, peer2name)
+	require.Equal(t, []address.Range{{Start: start, End: middle}}, ring1.OwnedRanges())
+
+	ring2 := New(start, end, peer2name)
+	ring2.Merge(*ring1)
+	require.Equal(t, []address.Range{{Start: middle, End: end}}, ring2.OwnedRanges())
+
+	ring2.Entries = []*entry{{Token: middle, Peer: peer2name}}
+	require.Equal(t, []address.Range{{Start: start, End: middle}, {Start: middle, End: end}}, ring2.OwnedRanges())
+
+	ring2.Entries = []*entry{{Token: dot10, Peer: peer2name}, {Token: middle, Peer: peer2name}}
+	require.Equal(t, []address.Range{{Start: start, End: dot10}, {Start: dot10, End: middle},
+		{Start: middle, End: end}}, ring2.OwnedRanges())
+
+}
+
+func TestTransfer(t *testing.T) {
+	// First test just checks if we can grant some range to a host, when we transfer it, we get it back
+	ring1 := New(start, end, peer1name)
+	ring1.ClaimItAll()
+	ring1.GrantRangeToHost(middle, end, peer2name)
+	ring1.Transfer(peer2name, peer1name)
+	require.Equal(t, []address.Range{{start, middle}, {middle, end}}, ring1.OwnedRanges())
+
+	// Second test is what happens when a token exists at the end of a range but is transferred
+	// - does it get resurrected correctly?
+	ring1 = New(start, end, peer1name)
+	ring1.ClaimItAll()
+	ring1.GrantRangeToHost(middle, end, peer2name)
+	ring1.Transfer(peer2name, peer1name)
+	ring1.GrantRangeToHost(dot10, middle, peer2name)
+	require.Equal(t, []address.Range{{start, dot10}, {middle, end}}, ring1.OwnedRanges())
+}
+
+func TestOwner(t *testing.T) {
+	ring1 := New(start, end, peer1name)
+	require.True(t, ring1.Contains(start), "start should be in ring")
+	require.False(t, ring1.Contains(end), "end should not be in ring")
+
+	require.Equal(t, router.UnknownPeerName, ring1.Owner(start))
+
+	ring1.ClaimItAll()
+	ring1.GrantRangeToHost(middle, end, peer2name)
+	require.Equal(t, peer1name, ring1.Owner(start))
+	require.Equal(t, peer2name, ring1.Owner(middle))
+	require.Panics(t, func() {
+		ring1.Owner(end)
+	})
+
+}
+
+type addressSlice []address.Address
+
+func (s addressSlice) Len() int           { return len(s) }
+func (s addressSlice) Less(i, j int) bool { return s[i] < s[j] }
+func (s addressSlice) Swap(i, j int)      { s[i], s[j] = s[j], s[i] }
+
+func TestFuzzRing(t *testing.T) {
+	var (
+		numPeers   = 25
+		iterations = 1000
+	)
+
+	peers := make([]router.PeerName, numPeers)
+	for i := 0; i < numPeers; i++ {
+		peer, _ := router.PeerNameFromString(fmt.Sprintf("%02d:00:00:00:02:00", i))
+		peers[i] = peer
+	}
+
+	// Make a valid, random ring
+	makeGoodRandomRing := func() *Ring {
+		addressSpace := end - start
+		numTokens := rand.Intn(int(addressSpace))
+
+		tokenMap := make(map[address.Address]bool)
+		for i := 0; i < numTokens; i++ {
+			tokenMap[address.Address(rand.Intn(int(addressSpace)))] = true
+		}
+		var tokens []address.Address
+		for token := range tokenMap {
+			tokens = append(tokens, token)
+		}
+		sort.Sort(addressSlice(tokens))
+
+		peer := peers[rand.Intn(len(peers))]
+		ring := New(start, end, peer)
+		for _, token := range tokens {
+			peer = peers[rand.Intn(len(peers))]
+			ring.Entries = append(ring.Entries, &entry{Token: start + token, Peer: peer})
+		}
+
+		ring.assertInvariants()
+		return ring
+	}
+
+	for i := 0; i < iterations; i++ {
+		// make 2 random rings
+		ring1 := makeGoodRandomRing()
+		ring2 := makeGoodRandomRing()
+
+		// Merge them - this might fail, we don't care
+		// We just want to make sure it doesn't panic
+		ring1.Merge(*ring2)
+
+		// Check whats left still passes assertions
+		ring1.assertInvariants()
+		ring2.assertInvariants()
+	}
+
+	// Make an invalid, random ring
+	makeBadRandomRing := func() *Ring {
+		addressSpace := end - start
+		numTokens := rand.Intn(int(addressSpace))
+		tokens := make([]address.Address, numTokens)
+		for i := 0; i < numTokens; i++ {
+			tokens[i] = address.Address(rand.Intn(int(addressSpace)))
+		}
+
+		peer := peers[rand.Intn(len(peers))]
+		ring := New(start, end, peer)
+		for _, token := range tokens {
+			peer = peers[rand.Intn(len(peers))]
+			ring.Entries = append(ring.Entries, &entry{Token: start + token, Peer: peer})
+		}
+
+		return ring
+	}
+
+	for i := 0; i < iterations; i++ {
+		// make 2 random rings
+		ring1 := makeGoodRandomRing()
+		ring2 := makeBadRandomRing()
+
+		// Merge them - this might fail, we don't care
+		// We just want to make sure it doesn't panic
+		ring1.Merge(*ring2)
+
+		// Check whats left still passes assertions
+		ring1.assertInvariants()
+	}
+}
+
+func TestFuzzRingHard(t *testing.T) {
+	//common.SetLogLevel("debug")
+	var (
+		numPeers   = 100
+		iterations = 3000
+		peers      []router.PeerName
+		rings      []*Ring
+		nextPeerID = 0
+	)
+
+	addPeer := func() {
+		peer, _ := router.PeerNameFromString(fmt.Sprintf("%02d:%02d:00:00:00:00", nextPeerID/10, nextPeerID%10))
+		common.Log.Debugf("%s: Adding peer", peer)
+		nextPeerID++
+		peers = append(peers, peer)
+		rings = append(rings, New(start, end, peer))
+	}
+
+	for i := 0; i < numPeers; i++ {
+		addPeer()
+	}
+
+	rings[0].ClaimItAll()
+
+	randomPeer := func(exclude int) (int, router.PeerName, *Ring) {
+		var peerIndex int
+		if exclude >= 0 {
+			peerIndex = rand.Intn(len(peers) - 1)
+			if peerIndex == exclude {
+				peerIndex++
+			}
+		} else {
+			peerIndex = rand.Intn(len(peers))
+		}
+		return peerIndex, peers[peerIndex], rings[peerIndex]
+	}
+
+	// Keep a map of index -> ranges, as these are a little expensive to
+	// calculate for every ring on every iteration.
+	var theRanges = make(map[int][]address.Range)
+	theRanges[0] = rings[0].OwnedRanges()
+
+	addOrRmPeer := func() {
+		if len(peers) < numPeers {
+			addPeer()
+			return
+		}
+
+		// Pick one peer to remove, and a different one to transfer to
+		peerIndex, peername, _ := randomPeer(-1)
+		_, otherPeername, otherRing := randomPeer(peerIndex)
+
+		// We need to be in a ~converged ring to rmpeer
+		for _, ring := range rings {
+			require.NoError(t, otherRing.Merge(*ring))
+		}
+
+		common.Log.Debugf("%s: transferring from peer %s", otherPeername, peername)
+		otherRing.Transfer(peername, otherPeername)
+
+		// Remove peer from our state
+		peers = append(peers[:peerIndex], peers[peerIndex+1:]...)
+		rings = append(rings[:peerIndex], rings[peerIndex+1:]...)
+		theRanges = make(map[int][]address.Range)
+
+		// And now tell everyone about the transfer - rmpeer is
+		// not partition safe
+		for i, ring := range rings {
+			require.NoError(t, ring.Merge(*otherRing))
+			theRanges[i] = ring.OwnedRanges()
+		}
+	}
+
+	doGrantOrGossip := func() {
+		var ringsWithRanges = make([]int, 0, len(rings))
+		for index, ranges := range theRanges {
+			if len(ranges) > 0 {
+				ringsWithRanges = append(ringsWithRanges, index)
+			}
+		}
+
+		if len(ringsWithRanges) > 0 {
+			// Produce a random split in a random owned range, given to a random peer
+			indexWithRanges := ringsWithRanges[rand.Intn(len(ringsWithRanges))]
+			ownedRanges := theRanges[indexWithRanges]
+			ring := rings[indexWithRanges]
+
+			rangeToSplit := ownedRanges[rand.Intn(len(ownedRanges))]
+			size := address.Subtract(rangeToSplit.End, rangeToSplit.Start)
+			ipInRange := address.Add(rangeToSplit.Start, address.Offset(rand.Intn(int(size))))
+			_, peerToGiveTo, _ := randomPeer(-1)
+			common.Log.Debugf("%s: Granting [%v, %v) to %s", ring.Peer, ipInRange, rangeToSplit.End, peerToGiveTo)
+			ring.GrantRangeToHost(ipInRange, rangeToSplit.End, peerToGiveTo)
+
+			// Now 'gossip' this to a random host (note, note could be same host as above)
+			otherIndex, _, otherRing := randomPeer(-1)
+			common.Log.Debugf("%s: 'Gossiping' to %s", ring.Peer, otherRing.Peer)
+			require.NoError(t, otherRing.Merge(*ring))
+
+			theRanges[indexWithRanges] = ring.OwnedRanges()
+			theRanges[otherIndex] = otherRing.OwnedRanges()
+			return
+		}
+
+		// No rings think they own anything (as gossip might be behind)
+		// We're going to pick a random host (which has entries) and gossip
+		// it to a random host (which may or may not have entries).
+		var ringsWithEntries = make([]*Ring, 0, len(rings))
+		for _, ring := range rings {
+			if len(ring.Entries) > 0 {
+				ringsWithEntries = append(ringsWithEntries, ring)
+			}
+		}
+		ring1 := ringsWithEntries[rand.Intn(len(ringsWithEntries))]
+		ring2index, _, ring2 := randomPeer(-1)
+		common.Log.Debugf("%s: 'Gossiping' to %s", ring1.Peer, ring2.Peer)
+		require.NoError(t, ring2.Merge(*ring1))
+		theRanges[ring2index] = ring2.OwnedRanges()
+	}
+
+	for i := 0; i < iterations; i++ {
+		// about 1 in 10 times, rmpeer or add host
+		n := rand.Intn(10)
+		switch {
+		case n < 1:
+			addOrRmPeer()
+		default:
+			doGrantOrGossip()
+		}
+	}
+}
+
+func (r *Ring) ClaimItAll() {
+	r.ClaimForPeers([]router.PeerName{r.Peer})
+}
+
+func (es entries) String() string {
+	var buffer bytes.Buffer
+	fmt.Fprintf(&buffer, "[")
+	for i, entry := range es {
+		fmt.Fprintf(&buffer, "%+v", *entry)
+		if i+1 < len(es) {
+			fmt.Fprintf(&buffer, " ")
+		}
+	}
+	fmt.Fprintf(&buffer, "]")
+	return buffer.String()
+}

ipam/space/space.go

@@ -0,0 +1,258 @@
+package space
+
+import (
+	"bytes"
+	"fmt"
+	"sort"
+
+	"github.com/weaveworks/weave/common"
+	"github.com/weaveworks/weave/net/address"
+)
+
+type Space struct {
+	// ours and free represent a set of addresses as a sorted
+	// sequences of ranges.  Even elements give the inclusive
+	// starting points of ranges, and odd elements give the
+	// exclusive ending points.  Ranges in an array do not
+	// overlap, and neighbouring ranges are always coalesced if
+	// possible, so the arrays consist of sorted Addrs without
+	// repetition.
+	ours []address.Address
+	free []address.Address
+}
+
+func New() *Space {
+	return &Space{}
+}
+
+func (s *Space) Add(start address.Address, size address.Offset) {
+	s.free = add(s.free, start, address.Add(start, size))
+}
+
+// Clear removes all spaces from this space set.  Used during node shutdown.
+func (s *Space) Clear() {
+	s.free = s.free[:0]
+	s.ours = s.ours[:0]
+}
+
+// Walk down the free list calling f() on the in-range portions, until
+// f() returns true or we run out of free space.  Return true iff f() returned true
+func (s *Space) walkFree(r address.Range, f func(address.Range) bool) bool {
+	if r.Start >= r.End { // degenerate case
+		return false
+	}
+	for i := 0; i < len(s.free); i += 2 {
+		chunk := address.Range{Start: s.free[i], End: s.free[i+1]}
+		if chunk.End <= r.Start { // this chunk comes before the range
+			continue
+		}
+		if chunk.Start >= r.End {
+			// all remaining free space is completely after range
+			break
+		}
+		// at this point we know chunk.End>chunk.Start &&
+		// chunk.End>r.Start && r.End>chunk.Start && r.End>r.Start
+		// therefore max(start, r.Start) < min(end, r.End)
+		// Restrict this block of free space to be in range
+		if chunk.Start < r.Start {
+			chunk.Start = r.Start
+		}
+		if chunk.End > r.End {
+			chunk.End = r.End
+		}
+		// at this point we know start<end
+		if f(chunk) {
+			return true
+		}
+	}
+	return false
+}
+
+func (s *Space) Allocate(r address.Range) (bool, address.Address) {
+	var result address.Address
+	return s.walkFree(r, func(chunk address.Range) bool {
+		result = chunk.Start
+		s.ours = add(s.ours, result, result+1)
+		s.free = subtract(s.free, result, result+1)
+		return true
+	}), result
+}
+
+func (s *Space) Claim(addr address.Address) error {
+	if !contains(s.free, addr) {
+		return fmt.Errorf("Address %v is not free to claim", addr)
+	}
+
+	s.ours = add(s.ours, addr, addr+1)
+	s.free = subtract(s.free, addr, addr+1)
+	return nil
+}
+
+func (s *Space) NumFreeAddressesInRange(r address.Range) address.Offset {
+	res := address.Offset(0)
+	s.walkFree(r, func(chunk address.Range) bool {
+		res += chunk.Size()
+		return false
+	})
+	return res
+}
+
+func (s *Space) Free(addr address.Address) error {
+	if !contains(s.ours, addr) {
+		return fmt.Errorf("Address %v is not ours", addr)
+	}
+	if contains(s.free, addr) {
+		return fmt.Errorf("Address %v is already free", addr)
+	}
+
+	s.ours = subtract(s.ours, addr, addr+1)
+	s.free = add(s.free, addr, addr+1)
+	return nil
+}
+
+func (s *Space) biggestFreeRange(r address.Range) (biggest address.Range) {
+	biggestSize := address.Offset(0)
+	s.walkFree(r, func(chunk address.Range) bool {
+		if size := chunk.Size(); size >= biggestSize {
+			biggest = chunk
+			biggestSize = size
+		}
+		return false
+	})
+	return
+}
+
+func (s *Space) Donate(r address.Range) (address.Range, bool) {
+	biggest := s.biggestFreeRange(r)
+
+	if biggest.Size() == 0 {
+		return address.Range{}, false
+	}
+
+	// Donate half of that biggest free range. Note size/2 rounds down, so
+	// the resulting donation size rounds up, and in particular can't be empty.
+	biggest.Start = address.Add(biggest.Start, biggest.Size()/2)
+
+	s.ours = subtract(s.ours, biggest.Start, biggest.End)
+	s.free = subtract(s.free, biggest.Start, biggest.End)
+	return biggest, true
+}
+
+func firstGreater(a []address.Address, x address.Address) int {
+	return sort.Search(len(a), func(i int) bool { return a[i] > x })
+}
+
+func firstGreaterOrEq(a []address.Address, x address.Address) int {
+	return sort.Search(len(a), func(i int) bool { return a[i] >= x })
+}
+
+// Do the ranges contain the given address?
+func contains(addrs []address.Address, addr address.Address) bool {
+	return firstGreater(addrs, addr)&1 != 0
+}
+
+// Take the union of the range [start, end) with the ranges in the array
+func add(addrs []address.Address, start address.Address, end address.Address) []address.Address {
+	return addSub(addrs, start, end, 0)
+}
+
+// Subtract the range [start, end) from the ranges in the array
+func subtract(addrs []address.Address, start address.Address, end address.Address) []address.Address {
+	return addSub(addrs, start, end, 1)
+}
+
+func addSub(addrs []address.Address, start address.Address, end address.Address, sense int) []address.Address {
+	startPos := firstGreaterOrEq(addrs, start)
+	endPos := firstGreater(addrs[startPos:], end) + startPos
+
+	// Boundaries up to startPos are unaffected
+	res := make([]address.Address, startPos, len(addrs)+2)
+	copy(res, addrs)
+
+	// Include start and end as new boundaries if they lie
+	// outside/inside existing ranges (according to sense).
+	if startPos&1 == sense {
+		res = append(res, start)
+	}
+
+	if endPos&1 == sense {
+		res = append(res, end)
+	}
+
+	// Boundaries after endPos are unaffected
+	return append(res, addrs[endPos:]...)
+}
+
+func (s *Space) String() string {
+	var buf bytes.Buffer
+	if len(s.ours) > 0 {
+		fmt.Fprint(&buf, "owned:")
+		for i := 0; i < len(s.ours); i += 2 {
+			fmt.Fprintf(&buf, " %s+%d ", s.ours[i], s.ours[i+1]-s.ours[i])
+		}
+	}
+	if len(s.free) > 0 {
+		fmt.Fprintf(&buf, "free:")
+		for i := 0; i < len(s.free); i += 2 {
+			fmt.Fprintf(&buf, " %s+%d ", s.free[i], s.free[i+1]-s.free[i])
+		}
+	}
+	if len(s.ours) == 0 && len(s.free) == 0 {
+		fmt.Fprintf(&buf, "No address ranges owned")
+	}
+	return buf.String()
+}
+
+type addressSlice []address.Address
+
+func (p addressSlice) Len() int           { return len(p) }
+func (p addressSlice) Less(i, j int) bool { return p[i] < p[j] }
+func (p addressSlice) Swap(i, j int)      { p[i], p[j] = p[j], p[i] }
+
+func (s *Space) assertInvariants() {
+	common.Assert(sort.IsSorted(addressSlice(s.ours)))
+	common.Assert(sort.IsSorted(addressSlice(s.free)))
+}
+
+// Return a slice representing everything we own, whether it is free or not
+func (s *Space) everything() []address.Address {
+	a := make([]address.Address, len(s.ours))
+	copy(a, s.ours)
+	for i := 0; i < len(s.free); i += 2 {
+		a = add(a, s.free[i], s.free[i+1])
+	}
+	return a
+}
+
+// OwnedRanges returns slice of Ranges, ordered by IP, gluing together
+// contiguous sequences of owned and free addresses
+func (s *Space) OwnedRanges() []address.Range {
+	everything := s.everything()
+	result := make([]address.Range, len(everything)/2)
+	for i := 0; i < len(everything); i += 2 {
+		result[i/2] = address.Range{Start: everything[i], End: everything[i+1]}
+	}
+	return result
+}
+
+// Create a Space that has free space in all the supplied Ranges.
+func (s *Space) AddRanges(ranges []address.Range) {
+	for _, r := range ranges {
+		s.free = add(s.free, r.Start, r.End)
+	}
+}
+
+// Taking ranges to be a set of all space we should own, add in any excess as free space
+func (s *Space) UpdateRanges(ranges []address.Range) {
+	new := []address.Address{}
+	for _, r := range ranges {
+		new = add(new, r.Start, r.End)
+	}
+	current := s.everything()
+	for i := 0; i < len(current); i += 2 {
+		new = subtract(new, current[i], current[i+1])
+	}
+	for i := 0; i < len(new); i += 2 {
+		s.free = add(s.free, new[i], new[i+1])
+	}
+}

ipam/space/space_test.go

@@ -0,0 +1,263 @@
+package space
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/require"
+	"github.com/weaveworks/weave/net/address"
+	wt "github.com/weaveworks/weave/testing"
+)
+
+func makeSpace(start address.Address, size address.Offset) *Space {
+	s := New()
+	s.Add(start, size)
+	return s
+}
+
+func ip(s string) address.Address {
+	addr, _ := address.ParseIP(s)
+	return addr
+}
+
+// Helper function to avoid 'NumFreeAddressesInRange(start, end)'
+// dozens of times in tests
+func (s *Space) NumFreeAddresses() address.Offset {
+	res := address.Offset(0)
+	for i := 0; i < len(s.free); i += 2 {
+		res += address.Subtract(s.free[i+1], s.free[i])
+	}
+	return res
+}
+
+func TestLowlevel(t *testing.T) {
+	a := []address.Address{}
+	a = add(a, 100, 200)
+	require.Equal(t, []address.Address{100, 200}, a)
+	require.True(t, !contains(a, 99), "")
+	require.True(t, contains(a, 100), "")
+	require.True(t, contains(a, 199), "")
+	require.True(t, !contains(a, 200), "")
+	a = add(a, 700, 800)
+	require.Equal(t, []address.Address{100, 200, 700, 800}, a)
+	a = add(a, 300, 400)
+	require.Equal(t, []address.Address{100, 200, 300, 400, 700, 800}, a)
+	a = add(a, 400, 500)
+	require.Equal(t, []address.Address{100, 200, 300, 500, 700, 800}, a)
+	a = add(a, 600, 700)
+	require.Equal(t, []address.Address{100, 200, 300, 500, 600, 800}, a)
+	a = add(a, 500, 600)
+	require.Equal(t, []address.Address{100, 200, 300, 800}, a)
+	a = subtract(a, 500, 600)
+	require.Equal(t, []address.Address{100, 200, 300, 500, 600, 800}, a)
+	a = subtract(a, 600, 700)
+	require.Equal(t, []address.Address{100, 200, 300, 500, 700, 800}, a)
+	a = subtract(a, 400, 500)
+	require.Equal(t, []address.Address{100, 200, 300, 400, 700, 800}, a)
+	a = subtract(a, 300, 400)
+	require.Equal(t, []address.Address{100, 200, 700, 800}, a)
+	a = subtract(a, 700, 800)
+	require.Equal(t, []address.Address{100, 200}, a)
+	a = subtract(a, 100, 200)
+	require.Equal(t, []address.Address{}, a)
+
+	s := New()
+	require.Equal(t, address.Offset(0), s.NumFreeAddresses())
+	ok, got := s.Allocate(address.NewRange(0, 1000))
+	require.False(t, ok, "allocate in empty space should fail")
+
+	s.Add(100, 100)
+	require.Equal(t, address.Offset(100), s.NumFreeAddresses())
+	ok, got = s.Allocate(address.NewRange(0, 1000))
+	require.True(t, ok && got == 100, "allocate")
+	require.Equal(t, address.Offset(99), s.NumFreeAddresses())
+	require.NoError(t, s.Claim(150))
+	require.Equal(t, address.Offset(98), s.NumFreeAddresses())
+	require.NoError(t, s.Free(100))
+	require.Equal(t, address.Offset(99), s.NumFreeAddresses())
+	wt.AssertErrorInterface(t, (*error)(nil), s.Free(0), "free not allocated")
+	wt.AssertErrorInterface(t, (*error)(nil), s.Free(100), "double free")
+
+	r, ok := s.Donate(address.NewRange(0, 1000))
+	require.True(t, ok && r.Start == 125 && r.Size() == 25, "donate")
+
+	// test Donate when addresses are scarce
+	s = New()
+	r, ok = s.Donate(address.NewRange(0, 1000))
+	require.True(t, !ok, "donate on empty space should fail")
+	s.Add(0, 3)
+	require.NoError(t, s.Claim(0))
+	require.NoError(t, s.Claim(2))
+	r, ok = s.Donate(address.NewRange(0, 1000))
+	require.True(t, ok && r.Start == 1 && r.End == 2, "donate")
+	r, ok = s.Donate(address.NewRange(0, 1000))
+	require.True(t, !ok, "donate should fail")
+}
+
+func TestSpaceAllocate(t *testing.T) {
+	const (
+		testAddr1   = "10.0.3.4"
+		testAddr2   = "10.0.3.5"
+		testAddrx   = "10.0.3.19"
+		testAddry   = "10.0.9.19"
+		containerID = "deadbeef"
+		size        = 20
+	)
+	var (
+		start = ip(testAddr1)
+	)
+
+	space1 := makeSpace(start, size)
+	require.Equal(t, address.Offset(20), space1.NumFreeAddresses())
+	space1.assertInvariants()
+
+	_, addr1 := space1.Allocate(address.NewRange(start, size))
+	require.Equal(t, testAddr1, addr1.String(), "address")
+	require.Equal(t, address.Offset(19), space1.NumFreeAddresses())
+	space1.assertInvariants()
+
+	_, addr2 := space1.Allocate(address.NewRange(start, size))
+	require.False(t, addr2.String() == testAddr1, "address")
+	require.Equal(t, address.Offset(18), space1.NumFreeAddresses())
+	require.Equal(t, address.Offset(13), space1.NumFreeAddressesInRange(address.Range{Start: ip(testAddr1), End: ip(testAddrx)}))
+	require.Equal(t, address.Offset(18), space1.NumFreeAddressesInRange(address.Range{Start: ip(testAddr1), End: ip(testAddry)}))
+	space1.assertInvariants()
+
+	space1.Free(addr2)
+	space1.assertInvariants()
+
+	wt.AssertErrorInterface(t, (*error)(nil), space1.Free(addr2), "double free")
+	wt.AssertErrorInterface(t, (*error)(nil), space1.Free(ip(testAddrx)), "address not allocated")
+	wt.AssertErrorInterface(t, (*error)(nil), space1.Free(ip(testAddry)), "wrong out of range")
+
+	space1.assertInvariants()
+}
+
+func TestSpaceFree(t *testing.T) {
+	const (
+		testAddr1   = "10.0.3.4"
+		testAddrx   = "10.0.3.19"
+		testAddry   = "10.0.9.19"
+		containerID = "deadbeef"
+	)
+
+	entireRange := address.NewRange(ip(testAddr1), 20)
+	space := makeSpace(ip(testAddr1), 20)
+
+	// Check we are prepared to give up the entire space
+	r := space.biggestFreeRange(entireRange)
+	require.True(t, r.Start == ip(testAddr1) && r.Size() == 20, "Wrong space")
+
+	for i := 0; i < 20; i++ {
+		ok, _ := space.Allocate(entireRange)
+		require.True(t, ok, "Failed to get address")
+	}
+
+	// Check we are full
+	ok, _ := space.Allocate(entireRange)
+	require.True(t, !ok, "Should have failed to get address")
+	r, ok = space.Donate(entireRange)
+	require.True(t, r.Size() == 0, "Wrong space")
+
+	// Free in the middle
+	require.NoError(t, space.Free(ip("10.0.3.13")))
+	r = space.biggestFreeRange(entireRange)
+	require.True(t, r.Start == ip("10.0.3.13") && r.Size() == 1, "Wrong space")
+
+	// Free one at the end
+	require.NoError(t, space.Free(ip("10.0.3.23")))
+	r = space.biggestFreeRange(entireRange)
+	require.True(t, r.Start == ip("10.0.3.23") && r.Size() == 1, "Wrong space")
+
+	// Now free a few at the end
+	require.NoError(t, space.Free(ip("10.0.3.22")))
+	require.NoError(t, space.Free(ip("10.0.3.21")))
+
+	require.Equal(t, address.Offset(4), space.NumFreeAddresses())
+
+	// Now get the biggest free space; should be 3.21
+	r = space.biggestFreeRange(entireRange)
+	require.True(t, r.Start == ip("10.0.3.21") && r.Size() == 3, "Wrong space")
+
+	// Now free a few in the middle
+	require.NoError(t, space.Free(ip("10.0.3.12")))
+	require.NoError(t, space.Free(ip("10.0.3.11")))
+	require.NoError(t, space.Free(ip("10.0.3.10")))
+
+	require.Equal(t, address.Offset(7), space.NumFreeAddresses())
+
+	// Now get the biggest free space; should be 3.21
+	r = space.biggestFreeRange(entireRange)
+	require.True(t, r.Start == ip("10.0.3.10") && r.Size() == 4, "Wrong space")
+
+	require.Equal(t, []address.Range{{Start: ip("10.0.3.4"), End: ip("10.0.3.24")}}, space.OwnedRanges())
+}
+
+func TestDonateSimple(t *testing.T) {
+	const (
+		testAddr1 = "10.0.1.0"
+		testAddr2 = "10.0.1.32"
+		size      = 48
+	)
+
+	var (
+		ipAddr1 = ip(testAddr1)
+	)
+
+	ps1 := makeSpace(ipAddr1, size)
+
+	// Empty space set should split in two and give me the second half
+	r, ok := ps1.Donate(address.NewRange(ip(testAddr1), size))
+	numGivenUp := r.Size()
+	require.True(t, ok, "Donate result")
+	require.Equal(t, "10.0.1.24", r.Start.String(), "Invalid start")
+	require.Equal(t, address.Offset(size/2), numGivenUp)
+	require.Equal(t, address.Offset(size/2), ps1.NumFreeAddresses())
+
+	// Now check we can give the rest up.
+	count := 0 // count to avoid infinite loop
+	for ; count < 1000; count++ {
+		r, ok := ps1.Donate(address.NewRange(ip(testAddr1), size))
+		if !ok {
+			break
+		}
+		numGivenUp += r.Size()
+	}
+	require.Equal(t, address.Offset(0), ps1.NumFreeAddresses())
+	require.Equal(t, address.Offset(size), numGivenUp)
+}
+
+func TestDonateHard(t *testing.T) {
+	//common.InitDefaultLogging(true)
+	var (
+		start                = ip("10.0.1.0")
+		size  address.Offset = 48
+	)
+
+	// Fill a fresh space
+	spaceset := makeSpace(start, size)
+	for i := address.Offset(0); i < size; i++ {
+		ok, _ := spaceset.Allocate(address.NewRange(start, size))
+		require.True(t, ok, "Failed to get IP!")
+	}
+
+	require.Equal(t, address.Offset(0), spaceset.NumFreeAddresses())
+
+	// Now free all but the last address
+	// this will force us to split the free list
+	for i := address.Offset(0); i < size-1; i++ {
+		require.NoError(t, spaceset.Free(address.Add(start, i)))
+	}
+
+	// Now split
+	newRange, ok := spaceset.Donate(address.NewRange(start, size))
+	require.True(t, ok, "GiveUpSpace result")
+	require.Equal(t, ip("10.0.1.23"), newRange.Start)
+	require.Equal(t, address.Offset(24), newRange.Size())
+	require.Equal(t, address.Offset(23), spaceset.NumFreeAddresses())
+
+	//Space set should now have 2 spaces
+	expected := New()
+	expected.Add(start, 23)
+	expected.ours = add(nil, ip("10.0.1.47"), ip("10.0.1.48"))
+	require.Equal(t, expected, spaceset)
+}

ipam/status.go

@@ -0,0 +1,82 @@
+package ipam
+
+import (
+	"github.com/weaveworks/weave/ipam/paxos"
+	"github.com/weaveworks/weave/net/address"
+)
+
+type Status struct {
+	Paxos            *paxos.Status
+	Range            string
+	DefaultSubnet    string
+	Entries          []EntryStatus
+	PendingClaims    []ClaimStatus
+	PendingAllocates []string
+}
+
+type EntryStatus struct {
+	Token   string
+	Peer    string
+	Version uint32
+}
+
+type ClaimStatus struct {
+	Ident   string
+	Address address.Address
+}
+
+func NewStatus(allocator *Allocator, defaultSubnet address.CIDR) *Status {
+	if allocator == nil {
+		return nil
+	}
+
+	var paxosStatus *paxos.Status
+	if allocator.paxosTicker != nil {
+		paxosStatus = paxos.NewStatus(allocator.paxos)
+	}
+
+	resultChan := make(chan *Status)
+	allocator.actionChan <- func() {
+		resultChan <- &Status{
+			paxosStatus,
+			allocator.universe.String(),
+			defaultSubnet.String(),
+			newEntryStatusSlice(allocator),
+			newClaimStatusSlice(allocator),
+			newAllocateIdentSlice(allocator)}
+	}
+
+	return <-resultChan
+}
+
+func newEntryStatusSlice(allocator *Allocator) []EntryStatus {
+	var slice []EntryStatus
+
+	if allocator.ring.Empty() {
+		return slice
+	}
+
+	for _, entry := range allocator.ring.Entries {
+		slice = append(slice, EntryStatus{entry.Token.String(), entry.Peer.String(), entry.Version})
+	}
+
+	return slice
+}
+
+func newClaimStatusSlice(allocator *Allocator) []ClaimStatus {
+	var slice []ClaimStatus
+	for _, op := range allocator.pendingClaims {
+		claim := op.(*claim)
+		slice = append(slice, ClaimStatus{claim.ident, claim.addr})
+	}
+	return slice
+}
+
+func newAllocateIdentSlice(allocator *Allocator) []string {
+	var slice []string
+	for _, op := range allocator.pendingAllocates {
+		allocate := op.(*allocate)
+		slice = append(slice, allocate.ident)
+	}
+	return slice
+}

ipam/testutils_test.go

@@ -0,0 +1,220 @@
+package ipam
+
+import (
+	"fmt"
+	"math/rand"
+	"sync"
+	"testing"
+	"time"
+
+	"github.com/stretchr/testify/require"
+	"github.com/weaveworks/weave/net/address"
+	"github.com/weaveworks/weave/router"
+	"github.com/weaveworks/weave/testing/gossip"
+)
+
+type mockMessage struct {
+	dst     router.PeerName
+	msgType byte
+	buf     []byte
+}
+
+func (m *mockMessage) String() string {
+	return fmt.Sprintf("-> %s [%x]", m.dst, m.buf)
+}
+
+func toStringArray(messages []mockMessage) []string {
+	out := make([]string, len(messages))
+	for i := range out {
+		out[i] = messages[i].String()
+	}
+	return out
+}
+
+type mockGossipComms struct {
+	sync.RWMutex
+	*testing.T
+	name     string
+	messages []mockMessage
+}
+
+func (m *mockGossipComms) String() string {
+	m.RLock()
+	defer m.RUnlock()
+	return fmt.Sprintf("[mockGossipComms %s]", m.name)
+}
+
+// Note: this style of verification, using equalByteBuffer, requires
+// that the contents of messages are never re-ordered.  Which, for instance,
+// requires they are not based off iterating through a map.
+
+func (m *mockGossipComms) GossipBroadcast(update router.GossipData) error {
+	m.Lock()
+	defer m.Unlock()
+	buf := []byte{}
+	if len(m.messages) == 0 {
+		require.FailNow(m, fmt.Sprintf("%s: Gossip broadcast message unexpected: \n%x", m.name, buf))
+	} else if msg := m.messages[0]; msg.dst != router.UnknownPeerName {
+		require.FailNow(m, fmt.Sprintf("%s: Expected Gossip message to %s but got broadcast", m.name, msg.dst))
+	} else if msg.buf != nil && !equalByteBuffer(msg.buf, buf) {
+		require.FailNow(m, fmt.Sprintf("%s: Gossip message not sent as expected: \nwant: %x\ngot : %x", m.name, msg.buf, buf))
+	} else {
+		// Swallow this message
+		m.messages = m.messages[1:]
+	}
+	return nil
+}
+
+func equalByteBuffer(a, b []byte) bool {
+	if len(a) != len(b) {
+		return false
+	}
+	for i := 0; i < len(a); i++ {
+		if a[i] != b[i] {
+			return false
+		}
+	}
+	return true
+}
+
+func (m *mockGossipComms) GossipUnicast(dstPeerName router.PeerName, buf []byte) error {
+	m.Lock()
+	defer m.Unlock()
+	if len(m.messages) == 0 {
+		require.FailNow(m, fmt.Sprintf("%s: Gossip message to %s unexpected: \n%s", m.name, dstPeerName, buf))
+	} else if msg := m.messages[0]; msg.dst == router.UnknownPeerName {
+		require.FailNow(m, fmt.Sprintf("%s: Expected Gossip broadcast message but got dest %s", m.name, dstPeerName))
+	} else if msg.dst != dstPeerName {
+		require.FailNow(m, fmt.Sprintf("%s: Expected Gossip message to %s but got dest %s", m.name, msg.dst, dstPeerName))
+	} else if buf[0] != msg.msgType {
+		require.FailNow(m, fmt.Sprintf("%s: Expected Gossip message of type %d but got type %d", m.name, msg.msgType, buf[0]))
+	} else if msg.buf != nil && !equalByteBuffer(msg.buf, buf[1:]) {
+		require.FailNow(m, fmt.Sprintf("%s: Gossip message not sent as expected: \nwant: %x\ngot : %x", m.name, msg.buf, buf[1:]))
+	} else {
+		// Swallow this message
+		m.messages = m.messages[1:]
+	}
+	return nil
+}
+
+func ExpectMessage(alloc *Allocator, dst string, msgType byte, buf []byte) {
+	m := alloc.gossip.(*mockGossipComms)
+	dstPeerName, _ := router.PeerNameFromString(dst)
+	m.Lock()
+	m.messages = append(m.messages, mockMessage{dstPeerName, msgType, buf})
+	m.Unlock()
+}
+
+func ExpectBroadcastMessage(alloc *Allocator, buf []byte) {
+	m := alloc.gossip.(*mockGossipComms)
+	m.Lock()
+	m.messages = append(m.messages, mockMessage{router.UnknownPeerName, 0, buf})
+	m.Unlock()
+}
+
+func CheckAllExpectedMessagesSent(allocs ...*Allocator) {
+	for _, alloc := range allocs {
+		m := alloc.gossip.(*mockGossipComms)
+		m.RLock()
+		if len(m.messages) > 0 {
+			require.FailNow(m, fmt.Sprintf("%s: Gossip message(s) not sent as expected: \n%x", m.name, m.messages))
+		}
+		m.RUnlock()
+	}
+}
+
+func makeAllocator(name string, cidrStr string, quorum uint) (*Allocator, address.Range) {
+	peername, err := router.PeerNameFromString(name)
+	if err != nil {
+		panic(err)
+	}
+
+	_, cidr, err := address.ParseCIDR(cidrStr)
+	if err != nil {
+		panic(err)
+	}
+
+	alloc := NewAllocator(peername, router.PeerUID(rand.Int63()),
+		"nick-"+name, cidr.Range(), quorum)
+
+	return alloc, cidr.HostRange()
+}
+
+func makeAllocatorWithMockGossip(t *testing.T, name string, universeCIDR string, quorum uint) (*Allocator, address.Range) {
+	alloc, subnet := makeAllocator(name, universeCIDR, quorum)
+	gossip := &mockGossipComms{T: t, name: name}
+	alloc.SetInterfaces(gossip)
+	alloc.Start()
+	return alloc, subnet
+}
+
+func (alloc *Allocator) claimRingForTesting(allocs ...*Allocator) {
+	peers := []router.PeerName{alloc.ourName}
+	for _, alloc2 := range allocs {
+		peers = append(peers, alloc2.ourName)
+	}
+	alloc.ring.ClaimForPeers(normalizeConsensus(peers))
+	alloc.space.AddRanges(alloc.ring.OwnedRanges())
+}
+
+func (alloc *Allocator) NumFreeAddresses(r address.Range) address.Offset {
+	resultChan := make(chan address.Offset)
+	alloc.actionChan <- func() {
+		resultChan <- alloc.space.NumFreeAddressesInRange(r)
+	}
+	return <-resultChan
+}
+
+// Check whether or not something was sent on a channel
+func AssertSent(t *testing.T, ch <-chan bool) {
+	timeout := time.After(10 * time.Second)
+	select {
+	case <-ch:
+		// This case is ok
+	case <-timeout:
+		require.FailNow(t, "Nothing sent on channel")
+	}
+}
+
+func AssertNothingSent(t *testing.T, ch <-chan bool) {
+	select {
+	case val := <-ch:
+		require.FailNow(t, fmt.Sprintf("Unexpected value on channel: %v", val))
+	default:
+		// no message received
+	}
+}
+
+func AssertNothingSentErr(t *testing.T, ch <-chan error) {
+	select {
+	case val := <-ch:
+		require.FailNow(t, fmt.Sprintf("Unexpected value on channel: %v", val))
+	default:
+		// no message received
+	}
+}
+
+func makeNetworkOfAllocators(size int, cidr string) ([]*Allocator, *gossip.TestRouter, address.Range) {
+	gossipRouter := gossip.NewTestRouter(0.0)
+	allocs := make([]*Allocator, size)
+	var subnet address.Range
+
+	for i := 0; i < size; i++ {
+		var alloc *Allocator
+		alloc, subnet = makeAllocator(fmt.Sprintf("%02d:00:00:02:00:00", i),
+			cidr, uint(size/2+1))
+		alloc.SetInterfaces(gossipRouter.Connect(alloc.ourName, alloc))
+		alloc.Start()
+		allocs[i] = alloc
+	}
+
+	allocs[size-1].gossip.GossipBroadcast(allocs[size-1].Gossip())
+	gossipRouter.Flush()
+	return allocs, gossipRouter, subnet
+}
+
+func stopNetworkOfAllocators(allocs []*Allocator) {
+	for _, alloc := range allocs {
+		alloc.Stop()
+	}
+}

nameserver/dns.go

@@ -1,55 +1,298 @@
 package nameserver
 
 import (
-	"github.com/miekg/dns"
+	"bytes"
+	"fmt"
+	"math/rand"
 	"net"
+	"sort"
+	"strings"
+	"time"
+
+	"github.com/miekg/dns"
+
+	"github.com/weaveworks/weave/net/address"
 )
 
 const (
-	localTTL uint32 = 300 // somewhat arbitrary; we don't expect anyone
-	// downstream to cache results
+	topDomain        = "."
+	reverseDNSdomain = "in-addr.arpa."
+	etcResolvConf    = "/etc/resolv.conf"
+	udpBuffSize      = uint16(4096)
+	minUDPSize       = 512
+
+	DefaultListenAddress = "0.0.0.0:53"
+	DefaultTTL           = 1
+	DefaultClientTimeout = 5 * time.Second
 )
 
-func makeHeader(r *dns.Msg, q *dns.Question) *dns.RR_Header {
-	return &dns.RR_Header{
-		Name: q.Name, Rrtype: q.Qtype,
-		Class: dns.ClassINET, Ttl: localTTL}
+type DNSServer struct {
+	ns      *Nameserver
+	domain  string
+	ttl     uint32
+	address string
+
+	servers   []*dns.Server
+	upstream  *dns.ClientConfig
+	tcpClient *dns.Client
+	udpClient *dns.Client
 }
 
-func makeReply(r *dns.Msg, as []dns.RR) *dns.Msg {
-	m := new(dns.Msg)
-	m.SetReply(r)
-	m.RecursionAvailable = true
-	m.Answer = as
+func filter(ss []string, s string) []string {
+	for i := 0; i < len(ss); {
+		if ss[i] == s {
+			ss = append(ss[:i], ss[i+1:]...)
+			continue
+		}
+		i++
+	}
+	return ss
+}
+
+func NewDNSServer(ns *Nameserver, domain, address, effectiveAddress string, ttl uint32, clientTimeout time.Duration) (*DNSServer, error) {
+	s := &DNSServer{
+		ns:        ns,
+		domain:    dns.Fqdn(domain),
+		ttl:       ttl,
+		address:   address,
+		tcpClient: &dns.Client{Net: "tcp", ReadTimeout: clientTimeout},
+		udpClient: &dns.Client{Net: "udp", ReadTimeout: clientTimeout, UDPSize: udpBuffSize},
+	}
+	var err error
+	if s.upstream, err = dns.ClientConfigFromFile(etcResolvConf); err != nil {
+		return nil, err
+	}
+	if s.upstream != nil {
+		s.upstream.Servers = filter(s.upstream.Servers, effectiveAddress)
+	}
+
+	err = s.listen(address)
+	return s, err
+}
+
+func (d *DNSServer) String() string {
+	var buf bytes.Buffer
+	fmt.Fprintf(&buf, "WeaveDNS (%s)\n", d.ns.ourName)
+	fmt.Fprintf(&buf, "  listening on %s, for domain %s\n", d.address, d.domain)
+	fmt.Fprintf(&buf, "  response ttl %d\n", d.ttl)
+	return buf.String()
+}
+
+func (d *DNSServer) listen(address string) error {
+	udpListener, err := net.ListenPacket("udp", address)
+	if err != nil {
+		return err
+	}
+	udpServer := &dns.Server{PacketConn: udpListener, Handler: d.createMux(d.udpClient, minUDPSize)}
+
+	tcpListener, err := net.Listen("tcp", address)
+	if err != nil {
+		udpServer.Shutdown()
+		return err
+	}
+	tcpServer := &dns.Server{Listener: tcpListener, Handler: d.createMux(d.tcpClient, -1)}
+
+	d.servers = []*dns.Server{udpServer, tcpServer}
+	return nil
+}
+
+func (d *DNSServer) ActivateAndServe() {
+	for _, server := range d.servers {
+		go func(server *dns.Server) {
+			server.ActivateAndServe()
+		}(server)
+	}
+}
+
+func (d *DNSServer) Stop() error {
+	for _, server := range d.servers {
+		if err := server.Shutdown(); err != nil {
+			return err
+		}
+	}
+	return nil
+}
+
+type handler struct {
+	*DNSServer
+	maxResponseSize int
+	client          *dns.Client
+}
+
+func (d *DNSServer) createMux(client *dns.Client, defaultMaxResponseSize int) *dns.ServeMux {
+	m := dns.NewServeMux()
+	h := &handler{
+		DNSServer:       d,
+		maxResponseSize: defaultMaxResponseSize,
+		client:          client,
+	}
+	m.HandleFunc(d.domain, h.handleLocal)
+	m.HandleFunc(reverseDNSdomain, h.handleReverse)
+	m.HandleFunc(topDomain, h.handleRecursive)
 	return m
 }
 
-func makeAddressReply(r *dns.Msg, q *dns.Question, addrs []net.IP) *dns.Msg {
-	answers := make([]dns.RR, len(addrs))
-	header := makeHeader(r, q)
-	count := 0
-	for _, addr := range addrs {
-		switch q.Qtype {
-		case dns.TypeA:
-			if ip4 := addr.To4(); ip4 != nil {
-				answers[count] = &dns.A{*header, addr}
-				count++
-			}
-		case dns.TypeAAAA:
-			if ip4 := addr.To4(); ip4 == nil {
-				answers[count] = &dns.AAAA{*header, addr}
-				count++
-			}
-		}
+func (h *handler) handleLocal(w dns.ResponseWriter, req *dns.Msg) {
+	h.ns.debugf("local request: %+v", *req)
+	if len(req.Question) != 1 || req.Question[0].Qtype != dns.TypeA {
+		h.nameError(w, req)
+		return
 	}
-	return makeReply(r, answers[:count])
+
+	hostname := dns.Fqdn(req.Question[0].Name)
+	if strings.Count(hostname, ".") == 1 {
+		hostname = hostname + h.domain
+	}
+
+	addrs := h.ns.Lookup(hostname)
+	if len(addrs) == 0 {
+		h.nameError(w, req)
+		return
+	}
+
+	header := dns.RR_Header{
+		Name:   req.Question[0].Name,
+		Rrtype: dns.TypeA,
+		Class:  dns.ClassINET,
+		Ttl:    h.ttl,
+	}
+	answers := make([]dns.RR, len(addrs))
+	for i, addr := range addrs {
+		ip := addr.IP4()
+		answers[i] = &dns.A{Hdr: header, A: ip}
+	}
+	shuffleAnswers(&answers)
+
+	h.respond(w, h.makeResponse(req, answers))
 }
 
-func makePTRReply(r *dns.Msg, q *dns.Question, names []string) *dns.Msg {
-	answers := make([]dns.RR, len(names))
-	header := makeHeader(r, q)
-	for i, name := range names {
-		answers[i] = &dns.PTR{*header, name}
+func (h *handler) handleReverse(w dns.ResponseWriter, req *dns.Msg) {
+	h.ns.debugf("reverse request: %+v", *req)
+	if len(req.Question) != 1 || req.Question[0].Qtype != dns.TypePTR {
+		h.nameError(w, req)
+		return
+	}
+
+	ipStr := strings.TrimSuffix(req.Question[0].Name, "."+reverseDNSdomain)
+	ip, err := address.ParseIP(ipStr)
+	if err != nil {
+		h.nameError(w, req)
+		return
+	}
+
+	hostname, err := h.ns.ReverseLookup(ip.Reverse())
+	if err != nil {
+		h.handleRecursive(w, req)
+		return
+	}
+
+	header := dns.RR_Header{
+		Name:   req.Question[0].Name,
+		Rrtype: dns.TypePTR,
+		Class:  dns.ClassINET,
+		Ttl:    h.ttl,
+	}
+	answers := []dns.RR{&dns.PTR{
+		Hdr: header,
+		Ptr: hostname,
+	}}
+
+	h.respond(w, h.makeResponse(req, answers))
+}
+
+func (h *handler) handleRecursive(w dns.ResponseWriter, req *dns.Msg) {
+	h.ns.debugf("recursive request: %+v", *req)
+
+	// Resolve unqualified names locally
+	if len(req.Question) == 1 && req.Question[0].Qtype == dns.TypeA {
+		hostname := dns.Fqdn(req.Question[0].Name)
+		if strings.Count(hostname, ".") == 1 {
+			h.handleLocal(w, req)
+			return
+		}
+	}
+
+	for _, server := range h.upstream.Servers {
+		reqCopy := req.Copy()
+		reqCopy.Id = dns.Id()
+		response, _, err := h.client.Exchange(reqCopy, fmt.Sprintf("%s:%s", server, h.upstream.Port))
+		if err != nil || response == nil {
+			h.ns.debugf("error trying %s: %v", server, err)
+			continue
+		}
+		response.Id = req.Id
+		if h.responseTooBig(req, response) {
+			response.Compress = true
+		}
+		h.respond(w, response)
+		return
+	}
+
+	h.respond(w, h.makeErrorResponse(req, dns.RcodeServerFailure))
+}
+
+func (h *handler) makeResponse(req *dns.Msg, answers []dns.RR) *dns.Msg {
+	response := &dns.Msg{}
+	response.SetReply(req)
+	response.RecursionAvailable = true
+	response.Authoritative = true
+	response.Answer = answers
+	if !h.responseTooBig(req, response) {
+		return response
+	}
+
+	// search for smallest i that is too big
+	maxSize := h.getMaxResponseSize(req)
+	i := sort.Search(len(answers), func(i int) bool {
+		// return true if too big
+		response.Answer = answers[:i+1]
+		return response.Len() > maxSize
+	})
+
+	response.Answer = answers[:i]
+	if i < len(answers) {
+		response.Truncated = true
+	}
+	return response
+}
+
+func (h *handler) makeErrorResponse(req *dns.Msg, code int) *dns.Msg {
+	response := &dns.Msg{}
+	response.SetReply(req)
+	response.RecursionAvailable = true
+	response.Rcode = code
+	return response
+}
+
+func (h *handler) responseTooBig(req, response *dns.Msg) bool {
+	return len(response.Answer) > 1 && h.maxResponseSize > 0 && response.Len() > h.getMaxResponseSize(req)
+}
+
+func (h *handler) respond(w dns.ResponseWriter, response *dns.Msg) {
+	h.ns.debugf("response: %+v", response)
+	if err := w.WriteMsg(response); err != nil {
+		h.ns.infof("error responding: %v", err)
+	}
+}
+
+func (h *handler) nameError(w dns.ResponseWriter, req *dns.Msg) {
+	h.respond(w, h.makeErrorResponse(req, dns.RcodeNameError))
+}
+
+func (h *handler) getMaxResponseSize(req *dns.Msg) int {
+	if opt := req.IsEdns0(); opt != nil {
+		return int(opt.UDPSize())
+	}
+	return h.maxResponseSize
+}
+
+func shuffleAnswers(answers *[]dns.RR) {
+	if len(*answers) <= 1 {
+		return
+	}
+
+	for i := range *answers {
+		j := rand.Intn(i + 1)
+		(*answers)[i], (*answers)[j] = (*answers)[j], (*answers)[i]
 	}
-	return makeReply(r, answers)
 }

nameserver/dns_test.go

@@ -0,0 +1,170 @@
+package nameserver
+
+import (
+	"fmt"
+	"math/rand"
+	"net"
+	"strconv"
+	"testing"
+	"time"
+
+	"github.com/miekg/dns"
+	"github.com/stretchr/testify/require"
+
+	"github.com/weaveworks/weave/net/address"
+	"github.com/weaveworks/weave/router"
+)
+
+func startServer(t *testing.T) (*DNSServer, *Nameserver, int, int) {
+	peername, err := router.PeerNameFromString("00:00:00:02:00:00")
+	require.Nil(t, err)
+	nameserver := New(peername, nil, nil, "")
+	dnsserver, err := NewDNSServer(nameserver, "weave.local.", "0.0.0.0:0", "", 30, 5*time.Second)
+	require.Nil(t, err)
+	udpPort := dnsserver.servers[0].PacketConn.LocalAddr().(*net.UDPAddr).Port
+	tcpPort := dnsserver.servers[1].Listener.Addr().(*net.TCPAddr).Port
+	go dnsserver.ActivateAndServe()
+	return dnsserver, nameserver, udpPort, tcpPort
+}
+
+func TestTruncation(t *testing.T) {
+	//common.SetLogLevel("debug")
+	dnsserver, nameserver, udpPort, tcpPort := startServer(t)
+	defer dnsserver.Stop()
+
+	// Add 100 mappings to nameserver
+	addrs := []address.Address{}
+	for i := address.Address(0); i < 100; i++ {
+		addrs = append(addrs, i)
+		nameserver.AddEntry("foo.weave.local.", "", router.UnknownPeerName, i)
+	}
+
+	doRequest := func(client *dns.Client, request *dns.Msg, port int) *dns.Msg {
+		request.SetQuestion("foo.weave.local.", dns.TypeA)
+		response, _, err := client.Exchange(request, fmt.Sprintf("127.0.0.1:%d", port))
+		require.Nil(t, err)
+		return response
+	}
+
+	// do a udp query, ensure we get a truncated response
+	{
+		udpClient := dns.Client{Net: "udp", UDPSize: minUDPSize}
+		response := doRequest(&udpClient, &dns.Msg{}, udpPort)
+		require.True(t, response.MsgHdr.Truncated)
+		require.True(t, len(response.Answer) < 100)
+	}
+
+	// do a udp query with big size, ensure we don't get a truncated response
+	{
+		udpClient := dns.Client{Net: "udp", UDPSize: 65535}
+		request := &dns.Msg{}
+		request.SetEdns0(65535, false)
+		response := doRequest(&udpClient, request, udpPort)
+		require.False(t, response.MsgHdr.Truncated)
+		require.Equal(t, len(response.Answer), 100)
+	}
+
+	// do a tcp query, ensure we don't get a truncated response
+	{
+		tcpClient := dns.Client{Net: "tcp"}
+		response := doRequest(&tcpClient, &dns.Msg{}, tcpPort)
+		require.False(t, response.MsgHdr.Truncated)
+		require.Equal(t, len(response.Answer), 100)
+	}
+}
+
+func TestTruncateResponse(t *testing.T) {
+
+	header := dns.RR_Header{
+		Name:   "host.domain.com",
+		Rrtype: dns.TypePTR,
+		Class:  dns.ClassINET,
+		Ttl:    30,
+	}
+
+	for i := 0; i < 10000; i++ {
+		// generate a random answer set
+		numAnswers := 40 + rand.Intn(200)
+		answers := make([]dns.RR, numAnswers)
+		for j := 0; j < numAnswers; j++ {
+			answers[j] = &dns.A{Hdr: header, A: address.Address(j).IP4()}
+		}
+
+		// pick a random max size, truncate response to that, check it
+		maxSize := 512 + rand.Intn(2*512)
+		h := handler{maxResponseSize: maxSize}
+		response := h.makeResponse(&dns.Msg{}, answers)
+		require.True(t, response.Len() <= maxSize)
+	}
+}
+
+func TestRecursiveCompress(t *testing.T) {
+	const (
+		hostname = "foo.example."
+		maxSize  = 512
+	)
+
+	// Construct a response that is >512 when uncompressed, <512 when compressed
+	response := dns.Msg{}
+	response.Authoritative = true
+	response.Answer = []dns.RR{}
+	header := dns.RR_Header{
+		Name:   hostname,
+		Rrtype: dns.TypeA,
+		Class:  dns.ClassINET,
+		Ttl:    10,
+	}
+	for response.Len() <= maxSize {
+		ip := address.Address(rand.Uint32()).IP4()
+		response.Answer = append(response.Answer, &dns.A{Hdr: header, A: ip})
+	}
+	response.Compress = true
+	require.True(t, response.Len() <= maxSize)
+
+	// A dns server that returns the above response
+	var gotRequest = false
+	handleRecursive := func(w dns.ResponseWriter, req *dns.Msg) {
+		gotRequest = true
+		require.Equal(t, req.Question[0].Name, hostname)
+		response.SetReply(req)
+		err := w.WriteMsg(&response)
+		require.Nil(t, err)
+	}
+	mux := dns.NewServeMux()
+	mux.HandleFunc(topDomain, handleRecursive)
+	udpListener, err := net.ListenPacket("udp", "0.0.0.0:0")
+	require.Nil(t, err)
+	udpServer := &dns.Server{PacketConn: udpListener, Handler: mux}
+	udpServerPort := udpListener.LocalAddr().(*net.UDPAddr).Port
+	go udpServer.ActivateAndServe()
+	defer udpServer.Shutdown()
+
+	// The weavedns server, pointed at the above server
+	dnsserver, _, udpPort, _ := startServer(t)
+	dnsserver.upstream = &dns.ClientConfig{
+		Servers:  []string{"127.0.0.1"},
+		Port:     strconv.Itoa(udpServerPort),
+		Ndots:    1,
+		Timeout:  5,
+		Attempts: 2,
+	}
+	defer dnsserver.Stop()
+
+	// Now do lookup, check its what we expected.
+	// NB this doesn't really test golang's resolver behaves correctly, as I can't see
+	// a way to point golangs resolver at a specific hosts.
+	req := new(dns.Msg)
+	req.Id = dns.Id()
+	req.RecursionDesired = true
+	req.Question = make([]dns.Question, 1)
+	req.Question[0] = dns.Question{
+		Name:   hostname,
+		Qtype:  dns.TypeA,
+		Qclass: dns.ClassINET,
+	}
+	c := new(dns.Client)
+	res, _, err := c.Exchange(req, fmt.Sprintf("127.0.0.1:%d", udpPort))
+	require.Nil(t, err)
+	require.True(t, gotRequest)
+	require.True(t, res.Len() > maxSize)
+}

nameserver/entry.go

@@ -0,0 +1,209 @@
+package nameserver
+
+import (
+	"bytes"
+	"encoding/gob"
+	"fmt"
+	"sort"
+	"time"
+
+	"github.com/weaveworks/weave/net/address"
+	"github.com/weaveworks/weave/router"
+)
+
+var now = func() int64 { return time.Now().Unix() }
+
+type Entry struct {
+	ContainerID string
+	Origin      router.PeerName
+	Addr        address.Address
+	Hostname    string
+	Version     int
+	Tombstone   int64 // timestamp of when it was deleted
+}
+
+type Entries []Entry
+
+func (e1 *Entry) equal(e2 *Entry) bool {
+	return e1.ContainerID == e2.ContainerID &&
+		e1.Origin == e2.Origin &&
+		e1.Addr == e2.Addr &&
+		e1.Hostname == e2.Hostname
+}
+
+func (e1 *Entry) less(e2 *Entry) bool {
+	// Entries are kept sorted by Hostname, Origin, ContainerID then address
+	switch {
+	case e1.Hostname != e2.Hostname:
+		return e1.Hostname < e2.Hostname
+
+	case e1.Origin != e2.Origin:
+		return e1.Origin < e2.Origin
+
+	case e1.ContainerID != e2.ContainerID:
+		return e1.ContainerID < e2.ContainerID
+
+	default:
+		return e1.Addr < e2.Addr
+	}
+}
+
+// returns true to indicate a change
+func (e1 *Entry) merge(e2 *Entry) bool {
+	// we know container id, origin, add and hostname are equal
+	if e2.Version > e1.Version {
+		e1.Version = e2.Version
+		e1.Tombstone = e2.Tombstone
+		return true
+	}
+	return false
+}
+
+func (e1 *Entry) String() string {
+	return fmt.Sprintf("%s -> %s", e1.Hostname, e1.Addr.String())
+}
+
+func (es Entries) Len() int           { return len(es) }
+func (es Entries) Swap(i, j int)      { panic("Swap") }
+func (es Entries) Less(i, j int) bool { return es[i].less(&es[j]) }
+
+func (es Entries) check() error {
+	if !sort.IsSorted(es) {
+		return fmt.Errorf("Not sorted!")
+	}
+	for i := 1; i < len(es); i++ {
+		if es[i].equal(&es[i-1]) {
+			return fmt.Errorf("Duplicate entry: %d:%v and %d:%v", i-1, es[i-1], i, es[i])
+		}
+	}
+	return nil
+}
+
+func (es *Entries) checkAndPanic() {
+	if err := es.check(); err != nil {
+		panic(err)
+	}
+}
+
+func (es *Entries) add(hostname, containerid string, origin router.PeerName, addr address.Address) Entry {
+	es.checkAndPanic()
+	defer es.checkAndPanic()
+
+	entry := Entry{Hostname: hostname, Origin: origin, ContainerID: containerid, Addr: addr}
+	i := sort.Search(len(*es), func(i int) bool {
+		return !(*es)[i].less(&entry)
+	})
+	if i < len(*es) && (*es)[i].equal(&entry) {
+		if (*es)[i].Tombstone > 0 {
+			(*es)[i].Tombstone = 0
+			(*es)[i].Version++
+		}
+	} else {
+		*es = append(*es, Entry{})
+		copy((*es)[i+1:], (*es)[i:])
+		(*es)[i] = entry
+	}
+	return (*es)[i]
+}
+
+func (es *Entries) merge(incoming Entries) Entries {
+	es.checkAndPanic()
+	defer es.checkAndPanic()
+	newEntries := Entries{}
+	i := 0
+
+	for _, entry := range incoming {
+		for i < len(*es) && (*es)[i].less(&entry) {
+			i++
+		}
+		if i < len(*es) && (*es)[i].equal(&entry) {
+			if (*es)[i].merge(&entry) {
+				newEntries = append(newEntries, entry)
+			}
+		} else {
+			*es = append(*es, Entry{})
+			copy((*es)[i+1:], (*es)[i:])
+			(*es)[i] = entry
+			newEntries = append(newEntries, entry)
+		}
+	}
+
+	return newEntries
+}
+
+// f returning true means keep the entry.
+func (es *Entries) tombstone(ourname router.PeerName, f func(*Entry) bool) Entries {
+	es.checkAndPanic()
+	defer es.checkAndPanic()
+	tombstoned := Entries{}
+	for i, e := range *es {
+		if f(&e) && e.Origin == ourname {
+			e.Version++
+			e.Tombstone = now()
+			(*es)[i] = e
+			tombstoned = append(tombstoned, e)
+		}
+	}
+	return tombstoned
+}
+
+func (es *Entries) filter(f func(*Entry) bool) {
+	es.checkAndPanic()
+	defer es.checkAndPanic()
+	i := 0
+	for _, e := range *es {
+		if !f(&e) {
+			continue
+		}
+		(*es)[i] = e
+		i++
+	}
+	*es = (*es)[:i]
+}
+
+func (es Entries) lookup(hostname string) Entries {
+	es.checkAndPanic()
+	i := sort.Search(len(es), func(i int) bool {
+		return es[i].Hostname >= hostname
+	})
+	if i >= len(es) || es[i].Hostname != hostname {
+		return Entries{}
+	}
+
+	j := sort.Search(len(es)-i, func(j int) bool {
+		return es[i+j].Hostname > hostname
+	})
+
+	return es[i : i+j]
+}
+
+func (es *Entries) first(f func(*Entry) bool) (*Entry, error) {
+	es.checkAndPanic()
+	for _, e := range *es {
+		if f(&e) {
+			return &e, nil
+		}
+	}
+	return nil, fmt.Errorf("Not found")
+}
+
+type GossipData struct {
+	Timestamp int64
+	Entries
+}
+
+func (g *GossipData) Merge(o router.GossipData) {
+	other := o.(*GossipData)
+	g.Entries.merge(other.Entries)
+	if g.Timestamp < other.Timestamp {
+		g.Timestamp = other.Timestamp
+	}
+}
+
+func (g *GossipData) Encode() [][]byte {
+	buf := &bytes.Buffer{}
+	if err := gob.NewEncoder(buf).Encode(g); err != nil {
+		panic(err)
+	}
+	return [][]byte{buf.Bytes()}
+}

nameserver/entry_test.go

@@ -0,0 +1,132 @@
+package nameserver
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/require"
+
+	"github.com/weaveworks/weave/net/address"
+	"github.com/weaveworks/weave/router"
+)
+
+func TestAdd(t *testing.T) {
+	oldNow := now
+	defer func() { now = oldNow }()
+	now = func() int64 { return 1234 }
+
+	entries := Entries{}
+	entries.add("A", "", router.UnknownPeerName, address.Address(0))
+	expected := Entries{
+		Entry{Hostname: "A", Origin: router.UnknownPeerName, Addr: address.Address(0)},
+	}
+	require.Equal(t, entries, expected)
+
+	entries.tombstone(router.UnknownPeerName, func(e *Entry) bool { return e.Hostname == "A" })
+	expected = Entries{
+		Entry{Hostname: "A", Origin: router.UnknownPeerName, Addr: address.Address(0), Version: 1, Tombstone: 1234},
+	}
+	require.Equal(t, entries, expected)
+
+	entries.add("A", "", router.UnknownPeerName, address.Address(0))
+	expected = Entries{
+		Entry{Hostname: "A", Origin: router.UnknownPeerName, Addr: address.Address(0), Version: 2},
+	}
+	require.Equal(t, entries, expected)
+}
+
+func TestMerge(t *testing.T) {
+	e1 := Entries{
+		Entry{Hostname: "A"},
+		Entry{Hostname: "C"},
+		Entry{Hostname: "D"},
+		Entry{Hostname: "F"},
+	}
+
+	e2 := Entries{
+		Entry{Hostname: "B"},
+		Entry{Hostname: "E"},
+		Entry{Hostname: "F"},
+	}
+
+	diff := e1.merge(e2)
+	expectedDiff := Entries{
+		Entry{Hostname: "B"},
+		Entry{Hostname: "E"},
+	}
+	require.Equal(t, expectedDiff, diff)
+
+	expected := Entries{
+		Entry{Hostname: "A"},
+		Entry{Hostname: "B"},
+		Entry{Hostname: "C"},
+		Entry{Hostname: "D"},
+		Entry{Hostname: "E"},
+		Entry{Hostname: "F"},
+	}
+	require.Equal(t, expected, e1)
+
+	diff = e1.merge(e1)
+	require.Equal(t, Entries{}, diff)
+}
+
+func TestOldMerge(t *testing.T) {
+	e1 := Entries{Entry{Hostname: "A", Version: 0}}
+	diff := e1.merge(Entries{Entry{Hostname: "A", Version: 1}})
+	require.Equal(t, Entries{Entry{Hostname: "A", Version: 1}}, diff)
+	require.Equal(t, Entries{Entry{Hostname: "A", Version: 1}}, e1)
+
+	diff = e1.merge(Entries{Entry{Hostname: "A", Version: 0}})
+	require.Equal(t, Entries{}, diff)
+	require.Equal(t, Entries{Entry{Hostname: "A", Version: 1}}, e1)
+}
+
+func TestTombstone(t *testing.T) {
+	oldNow := now
+	defer func() { now = oldNow }()
+	now = func() int64 { return 1234 }
+
+	es := Entries{
+		Entry{Hostname: "A"},
+		Entry{Hostname: "B"},
+	}
+
+	es.tombstone(router.UnknownPeerName, func(e *Entry) bool {
+		return e.Hostname == "B"
+	})
+	expected := Entries{
+		Entry{Hostname: "A"},
+		Entry{Hostname: "B", Version: 1, Tombstone: 1234},
+	}
+	require.Equal(t, expected, es)
+}
+
+func TestDelete(t *testing.T) {
+	es := Entries{
+		Entry{Hostname: "A"},
+		Entry{Hostname: "B"},
+	}
+
+	es.filter(func(e *Entry) bool {
+		return e.Hostname != "A"
+	})
+	expected := Entries{
+		Entry{Hostname: "B"},
+	}
+	require.Equal(t, expected, es)
+}
+
+func TestLookup(t *testing.T) {
+	es := Entries{
+		Entry{Hostname: "A"},
+		Entry{Hostname: "B", ContainerID: "bar"},
+		Entry{Hostname: "B", ContainerID: "foo"},
+		Entry{Hostname: "C"},
+	}
+
+	have := es.lookup("B")
+	want := Entries{
+		Entry{Hostname: "B", ContainerID: "bar"},
+		Entry{Hostname: "B", ContainerID: "foo"},
+	}
+	require.Equal(t, have, want)
+}

nameserver/http.go

@@ -1,108 +1,93 @@
 package nameserver
 
 import (
-	"errors"
+	"encoding/json"
 	"fmt"
-	"github.com/miekg/dns"
-	. "github.com/zettio/weave/common"
-	"io"
-	"log"
-	"net"
 	"net/http"
-	"strings"
+
+	"github.com/gorilla/mux"
+	"github.com/miekg/dns"
+
+	"github.com/weaveworks/weave/net/address"
 )
 
-// Parse a URL of the form PUT /name/<identifier>/<ip-address>
-func parseUrl(url string) (identifier string, ipaddr string, err error) {
-	parts := strings.Split(url, "/")
-	if len(parts) != 4 {
-		return "", "", errors.New("Unable to parse url: " + url)
-	}
-	return parts[2], parts[3], nil
+func (n *Nameserver) badRequest(w http.ResponseWriter, err error) {
+	http.Error(w, err.Error(), http.StatusBadRequest)
+	n.infof("%v", err)
 }
 
-func httpErrorAndLog(level *log.Logger, w http.ResponseWriter, msg string,
-	status int, logmsg string, logargs ...interface{}) {
-	http.Error(w, msg, status)
-	level.Printf("[http] "+logmsg, logargs...)
-}
-
-func ListenHttp(domain string, db Zone, port int) {
-
-	http.HandleFunc("/status", func(w http.ResponseWriter, r *http.Request) {
-		if r.Method != "GET" {
-			http.Error(w, "Method not allowed", http.StatusMethodNotAllowed)
-		} else {
-			io.WriteString(w, "ok")
-		}
+func (n *Nameserver) HandleHTTP(router *mux.Router) {
+	router.Methods("GET").Path("/domain").HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		fmt.Fprint(w, n.domain)
 	})
 
-	http.HandleFunc("/name/", func(w http.ResponseWriter, r *http.Request) {
-
-		reqError := func(msg string, logmsg string, logargs ...interface{}) {
-			httpErrorAndLog(Warning, w, msg, http.StatusBadRequest,
-				logmsg, logargs...)
-		}
-
-		switch r.Method {
-		case "PUT":
-			ident, ipStr, err := parseUrl(r.URL.Path)
-			name := r.FormValue("fqdn")
-			if ident == "" || ipStr == "" || name == "" {
-				reqError("Invalid request", "Invalid request: %s, %s", r.URL, r.Form)
-				return
-			}
-
-			ip := net.ParseIP(ipStr)
-			if ip == nil {
-				reqError("Invalid IP", "Invalid IP in request: %s", ipStr)
-				return
-			}
-
-			if dns.IsSubDomain(domain, name) {
-				Info.Printf("[http] Adding %s -> %s", name, ipStr)
-				if err = db.AddRecord(ident, name, ip); err != nil {
-					if _, ok := err.(DuplicateError); !ok {
-						httpErrorAndLog(
-							Error, w, "Internal error", http.StatusInternalServerError,
-							"Unexpected error from DB: %s", err)
-						return
-					} // oh, I already know this. whatever.
-				}
-			} else {
-				Info.Printf("[http] Ignoring name %s, not in %s", name, domain)
-			}
-
-		case "DELETE":
-			ident, ipStr, err := parseUrl(r.URL.Path)
-			if ident == "" || ipStr == "" {
-				reqError("Invalid Request", "Invalid request: %s, %s", r.URL, r.Form)
-				return
-			}
-
-			ip := net.ParseIP(ipStr)
-			if ip == nil {
-				reqError("Invalid IP in request", "Invalid IP in request: %s", ipStr)
-				return
-			}
-			Info.Printf("[http] Deleting %s (%s)", ident, ipStr)
-			if err = db.DeleteRecord(ident, ip); err != nil {
-				if _, ok := err.(LookupError); !ok {
-					httpErrorAndLog(
-						Error, w, "Internal error", http.StatusInternalServerError,
-						"Unexpected error from DB: %s", err)
-					return
-				}
-			}
-		default:
-			msg := "Unexpected http method: " + r.Method
-			reqError(msg, msg)
+	router.Methods("PUT").Path("/name/{container}/{ip}").HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		var (
+			vars      = mux.Vars(r)
+			container = vars["container"]
+			ipStr     = vars["ip"]
+			hostname  = dns.Fqdn(r.FormValue("fqdn"))
+			ip, err   = address.ParseIP(ipStr)
+		)
+		if err != nil {
+			n.badRequest(w, err)
 			return
 		}
+
+		if err := n.AddEntry(hostname, container, n.ourName, ip); err != nil {
+			n.badRequest(w, fmt.Errorf("Unable to add entry: %v", err))
+			return
+		}
+
+		if r.FormValue("check-alive") == "true" && n.docker.IsContainerNotRunning(container) {
+			n.infof("container '%s' is not running: removing", container)
+			if err := n.Delete(hostname, container, ipStr, ip); err != nil {
+				n.infof("failed to remove: %v", err)
+			}
+		}
+
+		w.WriteHeader(204)
 	})
 
-	address := fmt.Sprintf(":%d", port)
-	if err := http.ListenAndServe(address, nil); err != nil {
-		Error.Fatal("[http] Unable to create http listener: ", err)
+	deleteHandler := func(w http.ResponseWriter, r *http.Request) {
+		vars := mux.Vars(r)
+
+		hostname := r.FormValue("fqdn")
+		if hostname == "" {
+			hostname = "*"
+		} else {
+			hostname = dns.Fqdn(hostname)
+		}
+
+		container, ok := vars["container"]
+		if !ok {
+			container = "*"
+		}
+
+		ipStr, ok := vars["ip"]
+		ip, err := address.ParseIP(ipStr)
+		if ok && err != nil {
+			n.badRequest(w, err)
+			return
+		} else if !ok {
+			ipStr = "*"
+		}
+
+		if err := n.Delete(hostname, container, ipStr, ip); err != nil {
+			n.badRequest(w, fmt.Errorf("Unable to delete entries: %v", err))
+			return
+		}
+		w.WriteHeader(204)
 	}
+	router.Methods("DELETE").Path("/name/{container}/{ip}").HandlerFunc(deleteHandler)
+	router.Methods("DELETE").Path("/name/{container}").HandlerFunc(deleteHandler)
+	router.Methods("DELETE").Path("/name").HandlerFunc(deleteHandler)
+
+	router.Methods("GET").Path("/name").Headers("Accept", "application/json").HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		n.RLock()
+		defer n.RUnlock()
+		if err := json.NewEncoder(w).Encode(n.entries); err != nil {
+			n.badRequest(w, fmt.Errorf("Error marshalling response: %v", err))
+		}
+	})
 }

nameserver/http_test.go

@@ -1,88 +0,0 @@
-package nameserver
-
-import (
-	"fmt"
-	wt "github.com/zettio/weave/testing"
-	"math/rand"
-	"net"
-	"net/http"
-	"net/url"
-	"strings"
-	"testing"
-	"time"
-)
-
-func genForm(method string, url string, data url.Values) (resp *http.Response, err error) {
-	req, err := http.NewRequest(method, url, strings.NewReader(data.Encode()))
-	req.Header.Set("Content-Type", "application/x-www-form-urlencoded")
-	return http.DefaultClient.Do(req)
-}
-
-func TestHttp(t *testing.T) {
-	var (
-		containerID     = "deadbeef"
-		testDomain      = "weave.local."
-		successTestName = "test1." + testDomain
-		testAddr1       = "10.0.2.1/24"
-		dockerIP        = "9.8.7.6"
-	)
-
-	var zone = new(ZoneDb)
-	port := rand.Intn(10000) + 32768
-	fmt.Println("Http test on port", port)
-	go ListenHttp(testDomain, zone, port)
-
-	time.Sleep(100 * time.Millisecond) // Allow for http server to get going
-
-	// Ask the http server to add our test address into the database
-	addrParts := strings.Split(testAddr1, "/")
-	addrUrl := fmt.Sprintf("http://localhost:%d/name/%s/%s", port, containerID, addrParts[0])
-	resp, err := genForm("PUT", addrUrl,
-		url.Values{"fqdn": {successTestName}, "local_ip": {dockerIP}, "routing_prefix": {addrParts[1]}})
-	wt.AssertNoErr(t, err)
-	wt.AssertStatus(t, resp.StatusCode, http.StatusOK, "http response")
-
-	// Check that the address is now there.
-	foundIP, err := zone.LookupName(successTestName)
-	wt.AssertNoErr(t, err)
-	ip, _, _ := net.ParseCIDR(testAddr1)
-	if !foundIP.Equal(ip) {
-		t.Fatal("Unexpected result for", successTestName, foundIP)
-	}
-
-	// Adding exactly the same address should be OK
-	resp, err = genForm("PUT", addrUrl,
-		url.Values{"fqdn": {successTestName}, "local_ip": {dockerIP}, "routing_prefix": {addrParts[1]}})
-	wt.AssertNoErr(t, err)
-	wt.AssertStatus(t, resp.StatusCode, http.StatusOK, "http success response for duplicate add")
-
-	// Now try adding the same address again with a different ident --
-	// again should be fine
-	otherUrl := fmt.Sprintf("http://localhost:%d/name/%s/%s", port, "other", addrParts[0])
-	resp, err = genForm("PUT", otherUrl,
-		url.Values{"fqdn": {successTestName}, "local_ip": {dockerIP}, "routing_prefix": {addrParts[1]}})
-	wt.AssertNoErr(t, err)
-	wt.AssertStatus(t, resp.StatusCode, http.StatusOK, "http response")
-
-	// Delete the address
-	resp, err = genForm("DELETE", addrUrl, nil)
-	wt.AssertNoErr(t, err)
-	wt.AssertStatus(t, resp.StatusCode, http.StatusOK, "http response")
-
-	// Check that the address is still resolvable.
-	_, err = zone.LookupName(successTestName)
-	wt.AssertNoErr(t, err)
-
-	// Delete the address record mentioning the other container
-	resp, err = genForm("DELETE", otherUrl, nil)
-	wt.AssertNoErr(t, err)
-	wt.AssertStatus(t, resp.StatusCode, http.StatusOK, "http response")
-
-	// Check that the address is gone
-	_, err = zone.LookupName(successTestName)
-	wt.AssertErrorType(t, err, (*LookupError)(nil), "fully-removed address")
-
-	// Would like to shut down the http server at the end of this test
-	// but it's complicated.
-	// See https://groups.google.com/forum/#!topic/golang-nuts/vLHWa5sHnCE
-}

nameserver/mdns_client.go

@@ -1,263 +0,0 @@
-package nameserver
-
-import (
-	"github.com/miekg/dns"
-	"math"
-	"net"
-	"time"
-)
-
-// Portions of this code taken from github.com/armon/mdns
-
-const (
-	ipv4mdns = "224.0.0.251" // link-local multicast address
-	mdnsPort = 5353          // mDNS assigned port
-	// We wait this long to hear a response from other mDNS servers on
-	// the network.
-	mDNSTimeout = 500 * time.Millisecond
-	MaxDuration = time.Duration(math.MaxInt64)
-	MailboxSize = 16
-)
-
-var (
-	ipv4Addr = &net.UDPAddr{
-		IP:   net.ParseIP(ipv4mdns),
-		Port: mdnsPort,
-	}
-)
-
-type Response struct {
-	Name string
-	Addr net.IP
-	Err  error
-}
-
-type responseInfo struct {
-	timeout time.Time // if no answer by this time, give up
-	ch      chan<- *Response
-}
-
-// Represents one query that we have sent for one name.
-// If we, internally, get several requests for the same name while we have
-// a query in flight, then we don't want to send more queries out.
-// Invariant on responseInfos: they are in ascending order of timeout.
-type inflightQuery struct {
-	name          string
-	id            uint16 // the DNS message ID
-	responseInfos []*responseInfo
-}
-
-type MDNSClient struct {
-	// note unorthodox use of 'Server' class in client logic - using it to
-	// listen on a multicast socket and call callback whenever a message comes in.
-	listener  *dns.Server
-	conn      *net.UDPConn
-	addr      *net.UDPAddr
-	inflight  map[string]*inflightQuery
-	queryChan chan<- *MDNSInteraction
-}
-
-type mDNSQueryInfo struct {
-	name       string
-	querytype  uint16
-	responseCh chan<- *Response
-}
-
-func NewMDNSClient() (*MDNSClient, error) {
-	if conn, err := net.ListenUDP("udp4", &net.UDPAddr{IP: net.IPv4zero, Port: 0}); err != nil {
-		return nil, err
-	} else {
-		return &MDNSClient{
-			conn:     conn,
-			addr:     ipv4Addr,
-			inflight: make(map[string]*inflightQuery)}, nil
-	}
-}
-
-func (c *MDNSClient) Start(ifi *net.Interface) error {
-	multicast, err := LinkLocalMulticastListener(ifi)
-	if err != nil {
-		return err
-	}
-
-	handleMDNS := func(w dns.ResponseWriter, r *dns.Msg) {
-		// Don't want to handle queries here, so filter anything out that isn't a response
-		if len(r.Answer) > 0 {
-			c.ResponseCallback(r)
-		}
-	}
-
-	c.listener = &dns.Server{Unsafe: true, PacketConn: multicast, Handler: dns.HandlerFunc(handleMDNS)}
-	go c.listener.ActivateAndServe()
-
-	queryChan := make(chan *MDNSInteraction, MailboxSize)
-	c.queryChan = queryChan
-	go c.queryLoop(queryChan)
-
-	return nil
-}
-
-func LinkLocalMulticastListener(ifi *net.Interface) (net.PacketConn, error) {
-	return net.ListenMulticastUDP("udp", ifi, ipv4Addr)
-}
-
-// ACTOR client API
-
-const (
-	CSendQuery = iota
-	CShutdown
-	CMessageReceived
-)
-
-type MDNSInteraction struct {
-	code       int
-	resultChan chan<- interface{}
-	payload    interface{}
-}
-
-// Async
-func (c *MDNSClient) Shutdown() {
-	c.queryChan <- &MDNSInteraction{code: CShutdown}
-}
-
-// Async
-func (c *MDNSClient) SendQuery(name string, querytype uint16, responseCh chan<- *Response) {
-	c.queryChan <- &MDNSInteraction{
-		code:    CSendQuery,
-		payload: mDNSQueryInfo{name, querytype, responseCh},
-	}
-}
-
-// Async - called from dns library multiplexer
-func (c *MDNSClient) ResponseCallback(r *dns.Msg) {
-	c.queryChan <- &MDNSInteraction{code: CMessageReceived, payload: r}
-}
-
-// ACTOR server
-
-// Check all in-flight queries, close all that have already timed out,
-// and return the duration until the next timeout
-func (c *MDNSClient) checkInFlightQueries() time.Duration {
-	now := time.Now()
-	after := MaxDuration
-	for name, query := range c.inflight {
-		// Invariant on responseInfos: they are in ascending order of timeout.
-		numClosed := 0
-		for _, item := range query.responseInfos {
-			duration := item.timeout.Sub(now)
-			if duration <= 0 { // timed out
-				close(item.ch)
-				numClosed++
-			} else {
-				if duration < after {
-					after = duration
-				}
-				break // don't need to look at any more for this query
-			}
-		}
-		// Remove timed-out items from the slice
-		query.responseInfos = query.responseInfos[numClosed:]
-		if len(query.responseInfos) == 0 {
-			delete(c.inflight, name)
-		}
-	}
-	return after
-}
-
-func (c *MDNSClient) queryLoop(queryChan <-chan *MDNSInteraction) {
-	timer := time.NewTimer(MaxDuration)
-	run := func() {
-		timer.Reset(c.checkInFlightQueries())
-	}
-
-	terminate := false
-	for !terminate {
-		select {
-		case query, ok := <-queryChan:
-			if !ok {
-				break
-			}
-			switch query.code {
-			case CShutdown:
-				c.listener.Shutdown()
-				terminate = true
-			case CSendQuery:
-				c.handleSendQuery(query.payload.(mDNSQueryInfo))
-				run()
-			case CMessageReceived:
-				c.handleResponse(query.payload.(*dns.Msg))
-				run()
-			}
-		case <-timer.C:
-			run()
-		}
-	}
-
-	// Close all response channels at termination
-	for _, query := range c.inflight {
-		for _, item := range query.responseInfos {
-			close(item.ch)
-		}
-	}
-}
-
-func (c *MDNSClient) handleSendQuery(q mDNSQueryInfo) {
-	query, found := c.inflight[q.name]
-	if !found {
-		m := new(dns.Msg)
-		m.SetQuestion(q.name, q.querytype)
-		m.RecursionDesired = false
-		buf, err := m.Pack()
-		if err != nil {
-			q.responseCh <- &Response{Err: err}
-			close(q.responseCh)
-			return
-		}
-		query = &inflightQuery{
-			name: q.name,
-			id:   m.Id,
-		}
-		if _, err = c.conn.WriteTo(buf, c.addr); err != nil {
-			q.responseCh <- &Response{Err: err}
-			close(q.responseCh)
-			return
-		}
-		c.inflight[q.name] = query
-	}
-	info := &responseInfo{
-		ch:      q.responseCh,
-		timeout: time.Now().Add(mDNSTimeout),
-	}
-	// Invariant on responseInfos: they are in ascending order of timeout.
-	// Since we use a fixed interval from Now(), this must be after all existing timeouts.
-	query.responseInfos = append(query.responseInfos, info)
-}
-
-func (c *MDNSClient) handleResponse(r *dns.Msg) {
-	for _, answer := range r.Answer {
-		var name string
-		var res *Response
-
-		switch rr := answer.(type) {
-		case *dns.A:
-			name = rr.Hdr.Name
-			res = &Response{Addr: rr.A}
-		case *dns.PTR:
-			name = rr.Hdr.Name
-			res = &Response{Name: rr.Ptr}
-		default:
-			return
-		}
-
-		if query, found := c.inflight[name]; found {
-			for _, resp := range query.responseInfos {
-				resp.ch <- res
-				close(resp.ch)
-			}
-			delete(c.inflight, name)
-		} else {
-			// We've received a response that didn't match a query
-			// Do we want to cache it?
-		}
-	}
-}

nameserver/mdns_client_test.go

@@ -1,186 +0,0 @@
-package nameserver
-
-import (
-	"github.com/miekg/dns"
-	wt "github.com/zettio/weave/testing"
-	"log"
-	"net"
-	"testing"
-	"time"
-)
-
-var (
-	successTestName = "test1.weave."
-	failTestName    = "test2.weave."
-	testAddr        = net.ParseIP("9.8.7.6")
-	testInAddr      = "6.7.8.9.in-addr.arpa."
-)
-
-func minimalServer(w dns.ResponseWriter, req *dns.Msg) {
-
-	sendAnswer := func(m *dns.Msg) {
-		buf, err := m.Pack()
-		checkFatal(err)
-		if buf == nil {
-			log.Fatal("Nil buffer")
-		}
-		//log.Println("minimalServer sending:", buf)
-		// This is a bit of a kludge - per the RFC we should send responses from 5353, but that doesn't seem to work
-		sendconn, err := net.DialUDP("udp", nil, ipv4Addr)
-		checkFatal(err)
-
-		_, err = sendconn.Write(buf)
-		sendconn.Close()
-		checkFatal(err)
-	}
-
-	//log.Println("minimalServer received:", req)
-	if len(req.Answer) > 0 {
-		return // Only interested in questions.
-	}
-	if len(req.Question) != 1 {
-		return // We only handle single-question messages
-	}
-
-	if req.Question[0].Qtype == dns.TypeA && req.Question[0].Name == successTestName {
-		m := new(dns.Msg)
-		m.SetReply(req)
-		hdr := dns.RR_Header{Name: m.Question[0].Name, Rrtype: dns.TypeA,
-			Class: dns.ClassINET, Ttl: 3600}
-		a := &dns.A{hdr, testAddr}
-		m.Answer = append(m.Answer, a)
-		sendAnswer(m)
-	} else if req.Question[0].Qtype == dns.TypePTR && req.Question[0].Name == testInAddr {
-		m := new(dns.Msg)
-		m.SetReply(req)
-		hdr := dns.RR_Header{Name: m.Question[0].Name, Rrtype: dns.TypePTR,
-			Class: dns.ClassINET, Ttl: 3600}
-		a := &dns.PTR{hdr, successTestName}
-		m.Answer = append(m.Answer, a)
-		sendAnswer(m)
-	}
-}
-
-func RunLocalMulticastServer() (*dns.Server, error) {
-	multicast, err := net.ListenMulticastUDP("udp", nil, ipv4Addr)
-	if err != nil {
-		return nil, err
-	}
-	server := &dns.Server{Listener: nil, PacketConn: multicast, Handler: dns.HandlerFunc(minimalServer)}
-	go server.ActivateAndServe()
-	return server, nil
-}
-
-func setup(t *testing.T) (*MDNSClient, *dns.Server, error) {
-	mdnsClient, err := NewMDNSClient()
-	wt.AssertNoErr(t, err)
-	err = mdnsClient.Start(nil)
-	wt.AssertNoErr(t, err)
-
-	server, err := RunLocalMulticastServer()
-	if err != nil {
-		t.Fatalf("Unable to run test server: %s", err)
-	}
-	return mdnsClient, server, err
-}
-
-type testContext struct {
-	receivedAddr  net.IP
-	receivedCount int
-	channel       chan *Response
-}
-
-func newTestContext() *testContext {
-	return &testContext{channel: make(chan *Response, 4)}
-}
-
-func (c *testContext) checkResponse(t *testing.T, channelOk bool, resp *Response) {
-	if !channelOk {
-		c.channel = nil
-		return
-	}
-	wt.AssertNoErr(t, resp.Err)
-	log.Printf("Got address response %s addr %s", resp.Name, resp.Addr)
-	c.receivedAddr = resp.Addr
-	c.receivedCount++
-}
-
-func TestSimpleQuery(t *testing.T) {
-	log.Println("TestSimpleQuery starting")
-	mdnsClient, server, _ := setup(t)
-	defer mdnsClient.Shutdown()
-	defer server.Shutdown()
-
-	context := newTestContext()
-
-	// First, a test we expect to succeed
-	mdnsClient.SendQuery(successTestName, dns.TypeA, context.channel)
-	for resp := range context.channel {
-		context.checkResponse(t, true, resp)
-	}
-
-	if !context.receivedAddr.Equal(testAddr) || context.receivedCount != 1 {
-		t.Fatal("Unexpected result for", successTestName, context.receivedAddr, context.receivedCount)
-	}
-
-	// Now, a test we expect to time out with no responses
-	context = newTestContext()
-	mdnsClient.SendQuery("test2.weave.", dns.TypeA, context.channel)
-	for resp := range context.channel {
-		context.checkResponse(t, true, resp)
-	}
-
-	if context.receivedCount > 0 {
-		t.Fatal("Unexpected result for test2.weave", context.receivedAddr)
-	}
-}
-
-func TestParallelQuery(t *testing.T) {
-	log.Println("TestParallelQuery starting")
-	mdnsClient, server, _ := setup(t)
-	defer mdnsClient.Shutdown()
-	defer server.Shutdown()
-
-	context1 := newTestContext()
-	context2 := newTestContext()
-
-	go mdnsClient.SendQuery(successTestName, dns.TypeA, context1.channel)
-	go mdnsClient.SendQuery(successTestName, dns.TypeA, context2.channel)
-	timeout := time.After(2 * time.Second)
-outerloop:
-	for context1.channel != nil || context2.channel != nil {
-		select {
-		case resp, ok := <-context1.channel:
-			context1.checkResponse(t, ok, resp)
-		case resp, ok := <-context2.channel:
-			context2.checkResponse(t, ok, resp)
-		case <-timeout:
-			break outerloop
-		}
-	}
-
-	if !context1.receivedAddr.Equal(testAddr) || !context2.receivedAddr.Equal(testAddr) || context1.receivedCount != 1 || context2.receivedCount != 1 {
-		t.Fatal("Unexpected result for", successTestName, context1.receivedAddr, context2.receivedAddr, context1.receivedCount, context2.receivedCount)
-	}
-}
-
-func TestAsLookup(t *testing.T) {
-	mdnsClient, server, _ := setup(t)
-	defer mdnsClient.Shutdown()
-	defer server.Shutdown()
-
-	ip, err := mdnsClient.LookupName(successTestName)
-	wt.AssertNoErr(t, err)
-	if !testAddr.Equal(ip) {
-		t.Fatalf("Returned address incorrect %s", ip)
-	}
-
-	ip, err = mdnsClient.LookupName("foo.example.com.")
-	wt.AssertErrorType(t, err, (*LookupError)(nil), "unknown hostname")
-
-	name, err := mdnsClient.LookupInaddr(testInAddr)
-	wt.AssertNoErr(t, err)
-	if !(successTestName == name) {
-		t.Fatalf("Expected name %s, got %s", successTestName, name)
-	}
-}

nameserver/mdns_lookup.go

@@ -1,40 +0,0 @@
-package nameserver
-
-import (
-	"github.com/miekg/dns"
-	. "github.com/zettio/weave/common"
-	"net"
-)
-
-func mdnsLookup(client *MDNSClient, name string, qtype uint16) (*Response, error) {
-	channel := make(chan *Response)
-	client.SendQuery(name, qtype, channel)
-	for resp := range channel {
-		if err := resp.Err; err != nil {
-			Debug.Printf("[mdns] Error for query type %s name %s: %s",
-				dns.TypeToString[qtype], name, err)
-			return nil, err
-		} else {
-			Debug.Printf("[mdns] Got response name for query type %s name %s: name %s, addr %s",
-				dns.TypeToString[qtype], name, resp.Name, resp.Addr)
-			return resp, nil
-		}
-	}
-	return nil, LookupError(name)
-}
-
-func (client *MDNSClient) LookupName(name string) (net.IP, error) {
-	if r, e := mdnsLookup(client, name, dns.TypeA); r != nil {
-		return r.Addr, nil
-	} else {
-		return nil, e
-	}
-}
-
-func (client *MDNSClient) LookupInaddr(inaddr string) (string, error) {
-	if r, e := mdnsLookup(client, inaddr, dns.TypePTR); r != nil {
-		return r.Name, nil
-	} else {
-		return "", e
-	}
-}

nameserver/mdns_server.go

@@ -1,116 +0,0 @@
-package nameserver
-
-import (
-	"github.com/miekg/dns"
-	. "github.com/zettio/weave/common"
-	"net"
-)
-
-type MDNSServer struct {
-	localAddrs []net.Addr
-	sendconn   *net.UDPConn
-	zone       Zone
-}
-
-func NewMDNSServer(zone Zone) (*MDNSServer, error) {
-	// This is a bit of a kludge - per the RFC we should send responses from 5353, but that doesn't seem to work
-	sendconn, err := net.ListenUDP("udp4", &net.UDPAddr{IP: net.IPv4zero, Port: 0})
-	if err != nil {
-		return nil, err
-	}
-	return &MDNSServer{sendconn: sendconn, zone: zone}, nil
-}
-
-// Return true if testaddr is a UDP address with IP matching my local i/f
-func (s *MDNSServer) addrIsLocal(testaddr net.Addr) bool {
-	if udpaddr, ok := testaddr.(*net.UDPAddr); ok {
-		for _, localaddr := range s.localAddrs {
-			if ipnetlocal, ok := localaddr.(*net.IPNet); ok {
-				if ipnetlocal.IP.Equal(udpaddr.IP) {
-					return true
-				}
-			}
-		}
-	}
-	return false
-}
-
-func (s *MDNSServer) Start(ifi *net.Interface) error {
-	conn, err := LinkLocalMulticastListener(ifi)
-	if err != nil {
-		return err
-	}
-
-	if ifi == nil {
-		s.localAddrs, err = net.InterfaceAddrs()
-	} else {
-		s.localAddrs, err = ifi.Addrs()
-	}
-	if err != nil {
-		return err
-	}
-
-	handleLocal := s.makeHandler(dns.TypeA,
-		func(zone Lookup, r *dns.Msg, q *dns.Question) *dns.Msg {
-			if ip, err := zone.LookupName(q.Name); err == nil {
-				return makeAddressReply(r, q, []net.IP{ip})
-			} else {
-				return nil
-			}
-		})
-
-	handleReverse := s.makeHandler(dns.TypePTR,
-		func(zone Lookup, r *dns.Msg, q *dns.Question) *dns.Msg {
-			if name, err := zone.LookupInaddr(q.Name); err == nil {
-				return makePTRReply(r, q, []string{name})
-			} else {
-				return nil
-			}
-		})
-
-	mux := dns.NewServeMux()
-	mux.HandleFunc(LOCAL_DOMAIN, handleLocal)
-	mux.HandleFunc(RDNS_DOMAIN, handleReverse)
-
-	go dns.ActivateAndServe(nil, conn, mux)
-	return err
-}
-
-type LookupFunc func(Lookup, *dns.Msg, *dns.Question) *dns.Msg
-
-func (s *MDNSServer) makeHandler(qtype uint16, lookup LookupFunc) dns.HandlerFunc {
-	return func(_ dns.ResponseWriter, r *dns.Msg) {
-		// Handle only questions, ignore answers. We might also ignore
-		// questions that arise locally (i.e., that come from an IP we
-		// think is local), but in the interest of avoiding
-		// complication, and easier testing, this is elided on the
-		// assumption that the client wouldn't ask if it already knew
-		// the answer, and if it does ask, it'll be happy to get an
-		// answer.
-		if len(r.Answer) == 0 && len(r.Question) > 0 {
-			q := &r.Question[0]
-			if q.Qtype == qtype {
-				if m := lookup(s.zone, r, q); m != nil {
-					Debug.Printf("[mdns msgid %d] Found local answer to mDNS query %s",
-						r.MsgHdr.Id, q.Name)
-					if err := s.sendResponse(m); err != nil {
-						Warning.Printf("[mdns msgid %d] Error writing to %s",
-							r.MsgHdr.Id, s.sendconn)
-					}
-				} else {
-					Debug.Printf("[mdns msgid %d] No local answer for mDNS query %s",
-						r.MsgHdr.Id, q.Name)
-				}
-			}
-		}
-	}
-}
-
-func (s *MDNSServer) sendResponse(m *dns.Msg) error {
-	buf, err := m.Pack()
-	if err != nil {
-		return err
-	}
-	_, err = s.sendconn.WriteTo(buf, ipv4Addr)
-	return err
-}

nameserver/mdns_server_test.go

@@ -1,126 +0,0 @@
-package nameserver
-
-import (
-	"github.com/miekg/dns"
-	"github.com/zettio/weave/common"
-	wt "github.com/zettio/weave/testing"
-	"log"
-	"net"
-	"testing"
-	"time"
-)
-
-var (
-	containerID = "deadbeef"
-	testName    = "test.weave.local."
-	testAddr1   = "10.0.2.1/24"
-	testInAddr1 = "1.2.0.10.in-addr.arpa."
-)
-
-func sendQuery(name string, querytype uint16) error {
-	m := new(dns.Msg)
-	m.SetQuestion(name, querytype)
-	m.RecursionDesired = false
-	buf, err := m.Pack()
-	if err != nil {
-		return err
-	}
-	conn, err := net.ListenUDP("udp4", &net.UDPAddr{IP: net.IPv4zero, Port: 0})
-	if err != nil {
-		return err
-	}
-	_, err = conn.WriteTo(buf, ipv4Addr)
-	return err
-}
-
-func TestServerSimpleQuery(t *testing.T) {
-	// The ff can be handy for debugging (obvs)
-	common.InitDefaultLogging(true)
-
-	log.Println("TestServerSimpleQuery starting")
-	var zone = new(ZoneDb)
-	ip, _, _ := net.ParseCIDR(testAddr1)
-	zone.AddRecord(containerID, testName, ip)
-
-	mdnsServer, err := NewMDNSServer(zone)
-	wt.AssertNoErr(t, err)
-	err = mdnsServer.Start(nil)
-	wt.AssertNoErr(t, err)
-
-	var receivedAddr net.IP
-	var receivedName string
-	var recvChan chan interface{}
-	receivedCount := 0
-
-	reset := func() {
-		receivedAddr = nil
-		receivedName = ""
-		receivedCount = 0
-		recvChan = make(chan interface{})
-	}
-
-	wait := func() {
-		select {
-		case <-recvChan:
-			return
-		case <-time.After(100 * time.Millisecond):
-			return
-		}
-	}
-
-	// Implement a minimal listener for responses
-	multicast, err := LinkLocalMulticastListener(nil)
-	wt.AssertNoErr(t, err)
-
-	handleMDNS := func(w dns.ResponseWriter, r *dns.Msg) {
-		// Only handle responses here
-		if len(r.Answer) > 0 {
-			for _, answer := range r.Answer {
-				switch rr := answer.(type) {
-				case *dns.A:
-					receivedAddr = rr.A
-					receivedCount++
-				case *dns.PTR:
-					receivedName = rr.Ptr
-					receivedCount++
-				}
-			}
-			recvChan <- "ok"
-		}
-	}
-
-	listener := &dns.Server{Unsafe: true, PacketConn: multicast, Handler: dns.HandlerFunc(handleMDNS)}
-	go listener.ActivateAndServe()
-	defer listener.Shutdown()
-
-	time.Sleep(100 * time.Millisecond) // Allow for server to get going
-
-	reset()
-	sendQuery(testName, dns.TypeA)
-	wait()
-
-	if receivedCount != 1 {
-		t.Fatalf("Unexpected result count %d for %s", receivedCount, testName)
-	}
-	if !receivedAddr.Equal(ip) {
-		t.Fatalf("Unexpected result %s for %s", receivedAddr, testName)
-	}
-
-	reset()
-	sendQuery("testfail.weave.", dns.TypeA)
-	wait()
-
-	if receivedCount != 0 {
-		t.Fatalf("Unexpected result count %d for testfail.weave", receivedCount)
-	}
-
-	reset()
-	sendQuery(testInAddr1, dns.TypePTR)
-	wait()
-
-	if receivedCount != 1 {
-		t.Fatalf("Expected an answer to %s, got %d answers", testInAddr1, receivedCount)
-	} else if !(testName == receivedName) {
-		t.Fatalf("Expected answer %s to query for %s, got %s", testName, testInAddr1, receivedName)
-	}
-}

nameserver/nameserver.go

@@ -0,0 +1,258 @@
+package nameserver
+
+import (
+	"bytes"
+	"encoding/gob"
+	"fmt"
+	"sync"
+	"time"
+
+	"github.com/miekg/dns"
+
+	. "github.com/weaveworks/weave/common"
+	"github.com/weaveworks/weave/common/docker"
+	"github.com/weaveworks/weave/net/address"
+	"github.com/weaveworks/weave/router"
+)
+
+const (
+	// Tombstones do not need to survive long periods of peer disconnection, as
+	// we delete entries for disconnected peers.  Therefore they just need to hang
+	// around to account for propagation delay through gossip.  We do need them
+	// to hang around longer than the allowed clock skew (defined next).  30mins
+	// tombstone timeout allows for 15mins max clock skew.
+	tombstoneTimeout = time.Minute * 30
+
+	// Maximum age of acceptable gossip messages (to account for clock skew)
+	gossipWindow = int64(tombstoneTimeout/time.Second) / 2
+
+	// Used by prog/weaver/main.go and proxy/create_container_interceptor.go
+	DefaultDomain = "weave.local."
+)
+
+// Nameserver: gossip-based, in memory nameserver.
+// - Holds a sorted list of (hostname, peer, container id, ip) tuples for the whole cluster.
+// - This list is gossiped & merged around the cluser.
+// - Lookup-by-hostname are O(nlogn), and return a (copy of a) slice of the entries
+// - Update is O(n) for now
+type Nameserver struct {
+	sync.RWMutex
+	ourName router.PeerName
+	domain  string
+	gossip  router.Gossip
+	docker  *docker.Client
+	entries Entries
+	peers   *router.Peers
+	quit    chan struct{}
+}
+
+func New(ourName router.PeerName, peers *router.Peers, docker *docker.Client, domain string) *Nameserver {
+	ns := &Nameserver{
+		ourName: ourName,
+		domain:  dns.Fqdn(domain),
+		peers:   peers,
+		docker:  docker,
+		quit:    make(chan struct{}),
+	}
+	if peers != nil {
+		peers.OnGC(ns.PeerGone)
+	}
+	return ns
+}
+
+func (n *Nameserver) SetGossip(gossip router.Gossip) {
+	n.gossip = gossip
+}
+
+func (n *Nameserver) Start() {
+	go func() {
+		ticker := time.Tick(tombstoneTimeout)
+		for {
+			select {
+			case <-n.quit:
+				return
+			case <-ticker:
+				n.deleteTombstones()
+			}
+		}
+	}()
+}
+
+func (n *Nameserver) Stop() {
+	n.quit <- struct{}{}
+}
+
+func (n *Nameserver) broadcastEntries(es ...Entry) error {
+	if n.gossip != nil {
+		return n.gossip.GossipBroadcast(&GossipData{
+			Entries:   Entries(es),
+			Timestamp: now(),
+		})
+	}
+	return nil
+}
+
+func (n *Nameserver) AddEntry(hostname, containerid string, origin router.PeerName, addr address.Address) error {
+	n.infof("adding entry %s -> %s", hostname, addr.String())
+	n.Lock()
+	entry := n.entries.add(hostname, containerid, origin, addr)
+	n.Unlock()
+	return n.broadcastEntries(entry)
+}
+
+func (n *Nameserver) Lookup(hostname string) []address.Address {
+	n.RLock()
+	defer n.RUnlock()
+
+	entries := n.entries.lookup(hostname)
+	result := []address.Address{}
+	for _, e := range entries {
+		if e.Tombstone > 0 {
+			continue
+		}
+		result = append(result, e.Addr)
+	}
+	n.debugf("lookup %s -> %s", hostname, &result)
+	return result
+}
+
+func (n *Nameserver) ReverseLookup(ip address.Address) (string, error) {
+	n.RLock()
+	defer n.RUnlock()
+
+	match, err := n.entries.first(func(e *Entry) bool {
+		return e.Tombstone == 0 && e.Addr == ip
+	})
+	if err != nil {
+		return "", err
+	}
+	n.debugf("reverse lookup %s -> %s", ip, match.Hostname)
+	return match.Hostname, nil
+}
+
+func (n *Nameserver) ContainerDied(ident string) {
+	n.Lock()
+	entries := n.entries.tombstone(n.ourName, func(e *Entry) bool {
+		if e.ContainerID == ident {
+			n.infof("container %s died; tombstoning entry %s", ident, e.String())
+			return true
+		}
+		return false
+	})
+	n.Unlock()
+	if len(entries) > 0 {
+		if err := n.broadcastEntries(entries...); err != nil {
+			n.errorf("failed to broadcast container %s death: %v", ident, err)
+		}
+	}
+}
+
+func (n *Nameserver) PeerGone(peer *router.Peer) {
+	n.infof("peer %s gone", peer.String())
+	n.Lock()
+	defer n.Unlock()
+	n.entries.filter(func(e *Entry) bool {
+		return e.Origin != peer.Name
+	})
+}
+
+func (n *Nameserver) Delete(hostname, containerid, ipStr string, ip address.Address) error {
+	n.Lock()
+	n.infof("tombstoning hostname=%s, container=%s, ip=%s", hostname, containerid, ipStr)
+	entries := n.entries.tombstone(n.ourName, func(e *Entry) bool {
+		if hostname != "*" && e.Hostname != hostname {
+			return false
+		}
+
+		if containerid != "*" && e.ContainerID != containerid {
+			return false
+		}
+
+		if ipStr != "*" && e.Addr != ip {
+			return false
+		}
+
+		n.infof("tombstoning entry %v", e)
+		return true
+	})
+	n.Unlock()
+	return n.broadcastEntries(entries...)
+}
+
+func (n *Nameserver) deleteTombstones() {
+	n.Lock()
+	defer n.Unlock()
+	now := time.Now().Unix()
+	n.entries.filter(func(e *Entry) bool {
+		return e.Tombstone == 0 || now-e.Tombstone <= int64(tombstoneTimeout/time.Second)
+	})
+}
+
+func (n *Nameserver) Gossip() router.GossipData {
+	n.RLock()
+	defer n.RUnlock()
+	gossip := &GossipData{
+		Entries:   make(Entries, len(n.entries)),
+		Timestamp: now(),
+	}
+	copy(gossip.Entries, n.entries)
+	return gossip
+}
+
+func (n *Nameserver) OnGossipUnicast(sender router.PeerName, msg []byte) error {
+	return nil
+}
+
+func (n *Nameserver) receiveGossip(msg []byte) (router.GossipData, router.GossipData, error) {
+	var gossip GossipData
+	if err := gob.NewDecoder(bytes.NewReader(msg)).Decode(&gossip); err != nil {
+		return nil, nil, err
+	}
+
+	if delta := gossip.Timestamp - now(); delta > gossipWindow || delta < -gossipWindow {
+		return nil, nil, fmt.Errorf("clock skew of %d detected", delta)
+	}
+
+	if err := gossip.Entries.check(); err != nil {
+		return nil, nil, err
+	}
+
+	n.Lock()
+	defer n.Unlock()
+
+	if n.peers != nil {
+		gossip.Entries.filter(func(e *Entry) bool {
+			return n.peers.Fetch(e.Origin) != nil
+		})
+	}
+
+	newEntries := n.entries.merge(gossip.Entries)
+	if len(newEntries) > 0 {
+		return &GossipData{Entries: newEntries, Timestamp: now()}, &gossip, nil
+	}
+	return nil, &gossip, nil
+}
+
+// merge received data into state and return "everything new I've
+// just learnt", or nil if nothing in the received data was new
+func (n *Nameserver) OnGossip(msg []byte) (router.GossipData, error) {
+	newEntries, _, err := n.receiveGossip(msg)
+	return newEntries, err
+}
+
+// merge received data into state and return a representation of
+// the received data, for further propagation
+func (n *Nameserver) OnGossipBroadcast(_ router.PeerName, msg []byte) (router.GossipData, error) {
+	_, entries, err := n.receiveGossip(msg)
+	return entries, err
+}
+
+func (n *Nameserver) infof(fmt string, args ...interface{}) {
+	Log.Infof("[nameserver %s] "+fmt, append([]interface{}{n.ourName}, args...)...)
+}
+func (n *Nameserver) debugf(fmt string, args ...interface{}) {
+	Log.Debugf("[nameserver %s] "+fmt, append([]interface{}{n.ourName}, args...)...)
+}
+func (n *Nameserver) errorf(fmt string, args ...interface{}) {
+	Log.Errorf("[nameserver %s] "+fmt, append([]interface{}{n.ourName}, args...)...)
+}

nameserver/nameserver_test.go

@@ -0,0 +1,256 @@
+package nameserver
+
+import (
+	"fmt"
+	"math/rand"
+	"reflect"
+	"sort"
+	"strings"
+	"testing"
+	"time"
+
+	"github.com/stretchr/testify/require"
+
+	"github.com/weaveworks/weave/net/address"
+	"github.com/weaveworks/weave/router"
+	wt "github.com/weaveworks/weave/testing"
+	"github.com/weaveworks/weave/testing/gossip"
+)
+
+func makeNetwork(size int) ([]*Nameserver, *gossip.TestRouter) {
+	gossipRouter := gossip.NewTestRouter(0.0)
+	nameservers := make([]*Nameserver, size)
+
+	for i := 0; i < size; i++ {
+		name, _ := router.PeerNameFromString(fmt.Sprintf("%02d:00:00:02:00:00", i))
+		nameserver := New(name, nil, nil, "")
+		nameserver.SetGossip(gossipRouter.Connect(nameserver.ourName, nameserver))
+		nameserver.Start()
+		nameservers[i] = nameserver
+	}
+
+	return nameservers, gossipRouter
+}
+
+func stopNetwork(nameservers []*Nameserver, grouter *gossip.TestRouter) {
+	for _, nameserver := range nameservers {
+		nameserver.Stop()
+	}
+	grouter.Stop()
+}
+
+type pair struct {
+	origin router.PeerName
+	addr   address.Address
+}
+
+type mapping struct {
+	hostname string
+	addrs    []pair
+}
+
+type addrs []address.Address
+
+func (a addrs) Len() int           { return len(a) }
+func (a addrs) Swap(i, j int)      { a[i], a[j] = a[j], a[i] }
+func (a addrs) Less(i, j int) bool { return a[i] < a[j] }
+func (a addrs) String() string {
+	ss := []string{}
+	for _, addr := range a {
+		ss = append(ss, addr.String())
+	}
+	return strings.Join(ss, " ")
+}
+
+func (m mapping) Addrs() []address.Address {
+	want := addrs{}
+	for _, p := range m.addrs {
+		want = append(want, p.addr)
+	}
+	sort.Sort(want)
+	return want
+}
+
+func TestNameservers(t *testing.T) {
+	wt.RunWithTimeout(t, time.Minute, func() {
+		testNameservers(t)
+	})
+}
+
+func testNameservers(t *testing.T) {
+	//common.SetLogLevel("debug")
+
+	lookupTimeout := 10 // ms
+	nameservers, grouter := makeNetwork(50)
+	defer stopNetwork(nameservers, grouter)
+	nameserversByName := map[router.PeerName]*Nameserver{}
+	for _, n := range nameservers {
+		nameserversByName[n.ourName] = n
+	}
+	mappings := []mapping{}
+
+	check := func(nameserver *Nameserver, expected mapping) {
+		have := []address.Address{}
+		for i := 0; i < lookupTimeout; i++ {
+			have = nameserver.Lookup(expected.hostname)
+			sort.Sort(addrs(have))
+			if reflect.DeepEqual(have, expected.Addrs()) {
+				return
+			}
+			time.Sleep(1 * time.Millisecond)
+		}
+		want := expected.Addrs()
+		require.Equal(t, addrs(want).String(), addrs(have).String())
+	}
+
+	addMapping := func() {
+		nameserver := nameservers[rand.Intn(len(nameservers))]
+		addr := address.Address(rand.Int31())
+		hostname := fmt.Sprintf("hostname%d", rand.Int63())
+		mapping := mapping{hostname, []pair{{nameserver.ourName, addr}}}
+		mappings = append(mappings, mapping)
+
+		require.Nil(t, nameserver.AddEntry(hostname, "", nameserver.ourName, addr))
+		check(nameserver, mapping)
+	}
+
+	addExtraMapping := func() {
+		if len(mappings) <= 0 {
+			return
+		}
+		nameserver := nameservers[rand.Intn(len(nameservers))]
+		i := rand.Intn(len(mappings))
+		mapping := mappings[i]
+		addr := address.Address(rand.Int31())
+		mapping.addrs = append(mapping.addrs, pair{nameserver.ourName, addr})
+		mappings[i] = mapping
+
+		require.Nil(t, nameserver.AddEntry(mapping.hostname, "", nameserver.ourName, addr))
+		check(nameserver, mapping)
+	}
+
+	deleteMapping := func() {
+		if len(mappings) <= 0 {
+			return
+		}
+		i := rand.Intn(len(mappings))
+		mapping := mappings[i]
+		if len(mapping.addrs) <= 0 {
+			return
+		}
+		j := rand.Intn(len(mapping.addrs))
+		pair := mapping.addrs[j]
+		mapping.addrs = append(mapping.addrs[:j], mapping.addrs[j+1:]...)
+		mappings[i] = mapping
+		nameserver := nameserversByName[pair.origin]
+
+		require.Nil(t, nameserver.Delete(mapping.hostname, "*", pair.addr.String(), pair.addr))
+		check(nameserver, mapping)
+	}
+
+	doLookup := func() {
+		if len(mappings) <= 0 {
+			return
+		}
+		mapping := mappings[rand.Intn(len(mappings))]
+		nameserver := nameservers[rand.Intn(len(nameservers))]
+		check(nameserver, mapping)
+	}
+
+	doReverseLookup := func() {
+		if len(mappings) <= 0 {
+			return
+		}
+		mapping := mappings[rand.Intn(len(mappings))]
+		if len(mapping.addrs) <= 0 {
+			return
+		}
+		nameserver := nameservers[rand.Intn(len(nameservers))]
+		hostname := ""
+		var err error
+		for i := 0; i < lookupTimeout; i++ {
+			hostname, err = nameserver.ReverseLookup(mapping.addrs[0].addr)
+			if err != nil && mapping.hostname == hostname {
+				return
+			}
+			time.Sleep(1 * time.Millisecond)
+		}
+		require.Nil(t, err)
+		require.Equal(t, mapping.hostname, hostname)
+	}
+
+	for i := 0; i < 1000; i++ {
+		r := rand.Float32()
+		switch {
+		case r < 0.1:
+			addMapping()
+
+		case 0.1 <= r && r < 0.2:
+			addExtraMapping()
+
+		case 0.2 <= r && r < 0.3:
+			deleteMapping()
+
+		case 0.3 <= r && r < 0.9:
+			doLookup()
+
+		case 0.9 <= r:
+			doReverseLookup()
+		}
+
+		grouter.Flush()
+	}
+}
+
+func TestContainerAndPeerDeath(t *testing.T) {
+	peername, err := router.PeerNameFromString("00:00:00:02:00:00")
+	require.Nil(t, err)
+	nameserver := New(peername, nil, nil, "")
+
+	err = nameserver.AddEntry("hostname", "containerid", peername, address.Address(0))
+	require.Nil(t, err)
+	require.Equal(t, []address.Address{0}, nameserver.Lookup("hostname"))
+
+	nameserver.ContainerDied("containerid")
+	require.Equal(t, []address.Address{}, nameserver.Lookup("hostname"))
+
+	err = nameserver.AddEntry("hostname", "containerid", peername, address.Address(0))
+	require.Nil(t, err)
+	require.Equal(t, []address.Address{0}, nameserver.Lookup("hostname"))
+
+	nameserver.PeerGone(&router.Peer{Name: peername})
+	require.Equal(t, []address.Address{}, nameserver.Lookup("hostname"))
+}
+
+func TestTombstoneDeletion(t *testing.T) {
+	oldNow := now
+	defer func() { now = oldNow }()
+	now = func() int64 { return 1234 }
+
+	peername, err := router.PeerNameFromString("00:00:00:02:00:00")
+	require.Nil(t, err)
+	nameserver := New(peername, nil, nil, "")
+
+	err = nameserver.AddEntry("hostname", "containerid", peername, address.Address(0))
+	require.Nil(t, err)
+	require.Equal(t, []address.Address{0}, nameserver.Lookup("hostname"))
+
+	nameserver.deleteTombstones()
+	require.Equal(t, []address.Address{0}, nameserver.Lookup("hostname"))
+
+	err = nameserver.Delete("hostname", "containerid", "", address.Address(0))
+	require.Nil(t, err)
+	require.Equal(t, []address.Address{}, nameserver.Lookup("hostname"))
+	require.Equal(t, Entries{{
+		ContainerID: "containerid",
+		Origin:      peername,
+		Addr:        address.Address(0),
+		Hostname:    "hostname",
+		Version:     1,
+		Tombstone:   1234,
+	}}, nameserver.entries)
+
+	now = func() int64 { return 1234 + int64(tombstoneTimeout/time.Second) + 1 }
+	nameserver.deleteTombstones()
+	require.Equal(t, Entries{}, nameserver.entries)
+}

nameserver/server.go

@@ -1,136 +0,0 @@
-package nameserver
-
-import (
-	"fmt"
-	"github.com/miekg/dns"
-	. "github.com/zettio/weave/common"
-	"net"
-)
-
-const (
-	LOCAL_DOMAIN = "weave.local."
-)
-
-func checkFatal(e error) {
-	if e != nil {
-		Error.Fatal(e)
-	}
-}
-
-func checkWarn(e error) {
-	if e != nil {
-		Warning.Println(e)
-	}
-}
-
-func makeDNSFailResponse(r *dns.Msg) *dns.Msg {
-	m := new(dns.Msg)
-	m.SetReply(r)
-	m.RecursionAvailable = true
-	m.Rcode = dns.RcodeNameError
-	return m
-}
-
-func queryHandler(lookups []Lookup) dns.HandlerFunc {
-	return func(w dns.ResponseWriter, r *dns.Msg) {
-		q := r.Question[0]
-		Debug.Printf("Query: %+v", q)
-		if q.Qtype == dns.TypeA {
-			for _, lookup := range lookups {
-				if ip, err := lookup.LookupName(q.Name); err == nil {
-					m := makeAddressReply(r, &q, []net.IP{ip})
-					w.WriteMsg(m)
-					return
-				}
-			}
-		}
-		Info.Printf("[dns msgid %d] No results for type %s query %s",
-			r.MsgHdr.Id, dns.TypeToString[q.Qtype], q.Name)
-		w.WriteMsg(makeDNSFailResponse(r))
-	}
-}
-
-func rdnsHandler(lookups []Lookup) dns.HandlerFunc {
-	fallback := notUsHandler()
-	return func(w dns.ResponseWriter, r *dns.Msg) {
-		q := r.Question[0]
-		Debug.Printf("Reverse query: %+v", q)
-		if q.Qtype == dns.TypePTR {
-			for _, lookup := range lookups {
-				if name, err := lookup.LookupInaddr(q.Name); err == nil {
-					m := makePTRReply(r, &q, []string{name})
-					w.WriteMsg(m)
-					return
-				}
-			}
-			fallback(w, r)
-			return
-		} else {
-			Warning.Printf("[dns msgid %d] Unexpected reverse query type %s: %+v",
-				r.MsgHdr.Id, dns.TypeToString[q.Qtype], q)
-		}
-	}
-}
-
-/* When we receive a request for a name outside of our '.weave.local.'
-   domain, ask the configured DNS server as a fallback.
-*/
-func notUsHandler() dns.HandlerFunc {
-	config, err := dns.ClientConfigFromFile("/etc/resolv.conf")
-	checkFatal(err)
-	return func(w dns.ResponseWriter, r *dns.Msg) {
-		q := r.Question[0]
-		Debug.Printf("[dns msgid %d] Fallback query: %+v", r.MsgHdr.Id, q)
-		for _, server := range config.Servers {
-			reply, err := dns.Exchange(r, fmt.Sprintf("%s:%s", server, config.Port))
-			if err != nil {
-				Debug.Printf("[dns msgid %d] Network error trying %s (%s)",
-					r.MsgHdr.Id, server, err)
-				continue
-			}
-			if reply != nil && reply.Rcode != dns.RcodeSuccess {
-				Debug.Printf("[dns msgid %d] Failure reported by %s for query %s",
-					r.MsgHdr.Id, server, q.Name)
-				continue
-			}
-			Debug.Printf("[dns msgid %d] Given answer by %s for query %s",
-				r.MsgHdr.Id, server, q.Name)
-			w.WriteMsg(reply)
-			return
-		}
-		Warning.Printf("[dns msgid %d] Failed lookup for external name %s",
-			r.MsgHdr.Id, q.Name)
-		w.WriteMsg(makeDNSFailResponse(r))
-	}
-}
-
-func StartServer(zone Zone, iface *net.Interface, dnsPort int, wait int) error {
-	mdnsClient, err := NewMDNSClient()
-	checkFatal(err)
-
-	ifaceName := "default interface"
-	if iface != nil {
-		ifaceName = iface.Name
-	}
-	Info.Printf("Using mDNS on %s", ifaceName)
-	err = mdnsClient.Start(iface)
-	checkFatal(err)
-
-	LocalServeMux := dns.NewServeMux()
-	LocalServeMux.HandleFunc(LOCAL_DOMAIN, queryHandler([]Lookup{zone, mdnsClient}))
-	LocalServeMux.HandleFunc(RDNS_DOMAIN, rdnsHandler([]Lookup{zone, mdnsClient}))
-	LocalServeMux.HandleFunc(".", notUsHandler())
-
-	mdnsServer, err := NewMDNSServer(zone)
-	checkFatal(err)
-
-	err = mdnsServer.Start(iface)
-	checkFatal(err)
-
-	address := fmt.Sprintf(":%d", dnsPort)
-	Info.Printf("Listening for DNS on %s", address)
-	err = dns.ListenAndServe(address, "udp", LocalServeMux)
-	checkFatal(err)
-
-	return nil
-}

nameserver/server_test.go

@@ -1,91 +0,0 @@
-package nameserver
-
-import (
-	"fmt"
-	"github.com/miekg/dns"
-	"github.com/zettio/weave/common"
-	wt "github.com/zettio/weave/testing"
-	"net"
-	"testing"
-	"time"
-)
-
-func TestDNSServer(t *testing.T) {
-	const (
-		port            = 17625
-		successTestName = "test1.weave.local."
-		failTestName    = "test2.weave.local."
-		nonLocalName    = "weave.works."
-		testAddr1       = "10.0.2.1"
-		testRDNSsuccess = "1.2.0.10.in-addr.arpa."
-		testRDNSfail    = "4.3.2.1.in-addr.arpa."
-	)
-	dnsAddr := fmt.Sprintf("localhost:%d", port)
-	testCIDR1 := testAddr1 + "/24"
-
-	common.InitDefaultLogging(true)
-	var zone = new(ZoneDb)
-	ip, _, _ := net.ParseCIDR(testCIDR1)
-	zone.AddRecord(containerID, successTestName, ip)
-
-	go StartServer(zone, nil, port, 0)
-	time.Sleep(100 * time.Millisecond) // Allow sever goroutine to start
-
-	c := new(dns.Client)
-	m := new(dns.Msg)
-	m.SetQuestion(successTestName, dns.TypeA)
-	m.RecursionDesired = true
-	r, _, err := c.Exchange(m, dnsAddr)
-	wt.AssertNoErr(t, err)
-	wt.AssertStatus(t, r.Rcode, dns.RcodeSuccess, "DNS response code")
-	wt.AssertEqualInt(t, len(r.Answer), 1, "Number of answers")
-	wt.AssertType(t, r.Answer[0], (*dns.A)(nil), "DNS record")
-	wt.AssertEqualString(t, r.Answer[0].(*dns.A).A.String(), testAddr1, "IP address")
-
-	m.SetQuestion(failTestName, dns.TypeA)
-	r, _, err = c.Exchange(m, dnsAddr)
-	wt.AssertNoErr(t, err)
-	wt.AssertStatus(t, r.Rcode, dns.RcodeNameError, "DNS response code")
-	wt.AssertEqualInt(t, len(r.Answer), 0, "Number of answers")
-
-	m.SetQuestion(testRDNSsuccess, dns.TypePTR)
-	r, _, err = c.Exchange(m, dnsAddr)
-	wt.AssertNoErr(t, err)
-	wt.AssertStatus(t, r.Rcode, dns.RcodeSuccess, "DNS response code")
-	wt.AssertEqualInt(t, len(r.Answer), 1, "Number of answers")
-	wt.AssertType(t, r.Answer[0], (*dns.PTR)(nil), "DNS record")
-	wt.AssertEqualString(t, r.Answer[0].(*dns.PTR).Ptr, successTestName, "IP address")
-	m.SetQuestion(testRDNSfail, dns.TypePTR)
-	r, _, err = c.Exchange(m, dnsAddr)
-	wt.AssertNoErr(t, err)
-	wt.AssertStatus(t, r.Rcode, dns.RcodeNameError, "DNS response code")
-	wt.AssertEqualInt(t, len(r.Answer), 0, "Number of answers")
-
-	// This should fail because we don't handle MX records
-	m.SetQuestion(successTestName, dns.TypeMX)
-	r, _, err = c.Exchange(m, dnsAddr)
-	wt.AssertNoErr(t, err)
-	wt.AssertStatus(t, r.Rcode, dns.RcodeNameError, "DNS response code")
-	wt.AssertEqualInt(t, len(r.Answer), 0, "Number of answers")
-
-	// This non-local query for an MX record should succeed by being
-	// passed on to the configured (/etc/resolv.conf) DNS server.
-	m.SetQuestion(nonLocalName, dns.TypeMX)
-	r, _, err = c.Exchange(m, dnsAddr)
-	wt.AssertNoErr(t, err)
-	wt.AssertStatus(t, r.Rcode, dns.RcodeSuccess, "DNS response code")
-	if !(len(r.Answer) > 0) {
-		t.Fatal("Number of answers > 0")
-	}
-
-	m.SetQuestion("8.8.8.8.in-addr.arpa.", dns.TypePTR)
-	r, _, err = c.Exchange(m, dnsAddr)
-	wt.AssertNoErr(t, err)
-	wt.AssertStatus(t, r.Rcode, dns.RcodeSuccess, "DNS success response code")
-	if !(len(r.Answer) > 0) {
-		t.Fatal("Number of answers > 0")
-	}
-
-	// Not testing MDNS functionality of server here (yet), since it
-	// needs two servers, each listening on its own address
-}

nameserver/status.go

@@ -0,0 +1,43 @@
+package nameserver
+
+type Status struct {
+	Domain  string
+	Address string
+	TTL     uint32
+	Entries []EntryStatus
+}
+
+type EntryStatus struct {
+	Hostname    string
+	Origin      string
+	ContainerID string
+	Address     string
+	Version     int
+	Tombstone   int64
+}
+
+func NewStatus(ns *Nameserver, dnsServer *DNSServer) *Status {
+	if dnsServer == nil {
+		return nil
+	}
+
+	ns.RLock()
+	defer ns.RUnlock()
+
+	var entryStatusSlice []EntryStatus
+	for _, entry := range ns.entries {
+		entryStatusSlice = append(entryStatusSlice, EntryStatus{
+			entry.Hostname,
+			entry.Origin.String(),
+			entry.ContainerID,
+			entry.Addr.String(),
+			entry.Version,
+			entry.Tombstone})
+	}
+
+	return &Status{
+		dnsServer.domain,
+		dnsServer.address,
+		dnsServer.ttl,
+		entryStatusSlice}
+}

nameserver/updater.go

@@ -1,44 +0,0 @@
-package nameserver
-
-import (
-	"github.com/fsouza/go-dockerclient"
-	. "github.com/zettio/weave/common"
-)
-
-func checkError(err error, apiPath string) {
-	if err != nil {
-		Error.Fatalf("[updater] Unable to connect to Docker API on %s: %s",
-			apiPath, err)
-	}
-}
-
-func StartUpdater(apiPath string, zone Zone) error {
-	client, err := docker.NewClient(apiPath)
-	checkError(err, apiPath)
-
-	env, err := client.Version()
-	checkError(err, apiPath)
-
-	events := make(chan *docker.APIEvents)
-	err = client.AddEventListener(events)
-	checkError(err, apiPath)
-
-	Info.Printf("[updater] Using Docker API on %s: %v", apiPath, env)
-
-	go func() {
-		for event := range events {
-			handleEvent(zone, event, client)
-		}
-	}()
-	return nil
-}
-
-func handleEvent(zone Zone, event *docker.APIEvents, client *docker.Client) error {
-	switch event.Status {
-	case "die":
-		id := event.ID
-		Info.Printf("[updater] Container %s down. Removing records", id)
-		zone.DeleteRecordsFor(id)
-	}
-	return nil
-}

nameserver/zone.go

@@ -1,135 +0,0 @@
-package nameserver
-
-import (
-	"github.com/miekg/dns"
-	. "github.com/zettio/weave/common"
-	"net"
-	"sync"
-)
-
-const (
-	RDNS_DOMAIN = "in-addr.arpa."
-)
-
-// +1 to also exclude a dot
-var rdnsDomainLen = len(RDNS_DOMAIN) + 1
-
-type Lookup interface {
-	LookupName(name string) (net.IP, error)
-	LookupInaddr(inaddr string) (string, error)
-}
-
-type Zone interface {
-	AddRecord(ident string, name string, ip net.IP) error
-	DeleteRecord(ident string, ip net.IP) error
-	DeleteRecordsFor(ident string) error
-	Lookup
-}
-
-type Record struct {
-	Ident string
-	Name  string
-	IP    net.IP
-}
-
-// Very simple data structure for now, with linear searching.
-// TODO: make more sophisticated to improve performance.
-type ZoneDb struct {
-	mx   sync.RWMutex
-	recs []Record
-}
-
-type LookupError string
-
-func (ops LookupError) Error() string {
-	return "Unable to find " + string(ops)
-}
-
-type DuplicateError struct {
-}
-
-func (dup DuplicateError) Error() string {
-	return "Tried to add a duplicate entry"
-}
-
-func (zone *ZoneDb) indexOf(match func(Record) bool) int {
-	for i, r := range zone.recs {
-		if match(r) {
-			return i
-		}
-	}
-	return -1
-}
-
-func (zone *ZoneDb) LookupName(name string) (net.IP, error) {
-	zone.mx.RLock()
-	defer zone.mx.RUnlock()
-	for _, r := range zone.recs {
-		if r.Name == name {
-			return r.IP, nil
-		}
-	}
-	return nil, LookupError(name)
-}
-
-func (zone *ZoneDb) LookupInaddr(inaddr string) (string, error) {
-	if revIP := net.ParseIP(inaddr[:len(inaddr)-rdnsDomainLen]); revIP != nil {
-		revIP4 := revIP.To4()
-		ip := []byte{revIP4[3], revIP4[2], revIP4[1], revIP4[0]}
-		Debug.Printf("[zonedb] Looking for address: %+v", ip)
-		zone.mx.RLock()
-		defer zone.mx.RUnlock()
-		for _, r := range zone.recs {
-			if r.IP.Equal(ip) {
-				return r.Name, nil
-			}
-		}
-		return "", LookupError(inaddr)
-	} else {
-		Warning.Printf("[zonedb] Asked to reverse lookup %s", inaddr)
-		return "", LookupError(inaddr)
-	}
-}
-
-func (zone *ZoneDb) AddRecord(ident string, name string, ip net.IP) error {
-	zone.mx.Lock()
-	defer zone.mx.Unlock()
-	fqdn := dns.Fqdn(name)
-	if index := zone.indexOf(
-		func(r Record) bool {
-			return r.Name == fqdn && r.IP.Equal(ip) && r.Ident == ident
-		}); index != -1 {
-		return DuplicateError{}
-	}
-	zone.recs = append(zone.recs, Record{ident, fqdn, ip})
-	return nil
-}
-
-func (zone *ZoneDb) DeleteRecord(ident string, ip net.IP) error {
-	zone.mx.Lock()
-	defer zone.mx.Unlock()
-	if index := zone.indexOf(
-		func(r Record) bool {
-			return r.Ident == ident && r.IP.Equal(ip)
-		}); index == -1 {
-		return LookupError(ident)
-	} else {
-		zone.recs = append(zone.recs[:index], zone.recs[index+1:]...)
-	}
-	return nil
-}
-
-func (zone *ZoneDb) DeleteRecordsFor(ident string) error {
-	zone.mx.Lock()
-	defer zone.mx.Unlock()
-	w := 0 // write index
-
-	for _, r := range zone.recs {
-		if r.Ident != ident {
-			zone.recs[w] = r
-			w++
-		}
-	}
-	zone.recs = zone.recs[:w]
-	return nil
-}

nameserver/zone_test.go

@@ -1,88 +0,0 @@
-package nameserver
-
-import (
-	wt "github.com/zettio/weave/testing"
-	"net"
-	"testing"
-)
-
-func TestZone(t *testing.T) {
-	var (
-		containerID      = "deadbeef"
-		otherContainerID = "cowjuice"
-		successTestName  = "test1.weave."
-		testAddr1        = "10.0.2.1/24"
-	)
-
-	var zone = new(ZoneDb)
-
-	ip, _, _ := net.ParseCIDR(testAddr1)
-	err := zone.AddRecord(containerID, successTestName, ip)
-	wt.AssertNoErr(t, err)
-
-	// Add a few more records to make the job harder
-	err = zone.AddRecord("abcdef0123", "adummy.weave.", net.ParseIP("10.0.0.1"))
-	wt.AssertNoErr(t, err)
-	err = zone.AddRecord("0123abcdef", "zdummy.weave.", net.ParseIP("10.0.0.2"))
-	wt.AssertNoErr(t, err)
-
-	// Check that the address is now there.
-	foundIP, err := zone.LookupName(successTestName)
-	wt.AssertNoErr(t, err)
-
-	if !foundIP.Equal(ip) {
-		t.Fatal("Unexpected result for", successTestName, foundIP)
-	}
-
-	// See if we can find the address by IP.
-	foundName, err := zone.LookupInaddr("1.2.0.10.in-addr.arpa.")
-	wt.AssertNoErr(t, err)
-
-	if foundName != successTestName {
-		t.Fatal("Unexpected result for", ip, foundName)
-	}
-
-	err = zone.AddRecord(containerID, successTestName, ip)
-	wt.AssertErrorType(t, err, (*DuplicateError)(nil), "duplicate add")
-
-	err = zone.AddRecord(otherContainerID, successTestName, ip)
-	// Delete the record for the original container
-	err = zone.DeleteRecord(containerID, ip)
-	wt.AssertNoErr(t, err)
-
-	_, err = zone.LookupName(successTestName)
-	wt.AssertNoErr(t, err)
-
-	err = zone.DeleteRecord(otherContainerID, ip)
-	wt.AssertNoErr(t, err)
-
-	// Check that the address is not there now.
-	_, err = zone.LookupName(successTestName)
-	wt.AssertErrorType(t, err, (*LookupError)(nil), "after deleting record")
-
-	// Delete a record that isn't there
-	err = zone.DeleteRecord(containerID, net.ParseIP("0.0.0.0"))
-	wt.AssertErrorType(t, err, (*LookupError)(nil), "when deleting record that doesn't exist")
-}
-
-func TestDeleteFor(t *testing.T) {
-	var (
-		id    = "foobar"
-		name  = "foo.weave."
-		addr1 = "10.1.2.3/24"
-		addr2 = "10.2.7.8/24"
-	)
-	zone := new(ZoneDb)
-	for _, addr := range []string{addr1, addr2} {
-		ip, _, _ := net.ParseCIDR(addr)
-		err := zone.AddRecord(id, name, ip)
-		wt.AssertNoErr(t, err)
-	}
-
-	_, err := zone.LookupName(name)
-	wt.AssertNoErr(t, err)
-
-	err = zone.DeleteRecordsFor(id)
-	_, err = zone.LookupName(name)
-	wt.AssertErrorType(t, err, (*LookupError)(nil), "after deleting records for ident")
-}

net/address/address.go

@@ -0,0 +1,122 @@
+package address
+
+import (
+	"fmt"
+	"net"
+
+	"github.com/weaveworks/weave/common"
+)
+
+// Using 32-bit integer to represent IPv4 address
+type Address uint32
+type Offset uint32
+
+type Range struct {
+	Start, End Address // [Start, End); Start <= End
+}
+
+func NewRange(start Address, size Offset) Range {
+	return Range{Start: start, End: Add(start, size)}
+}
+func (r Range) Size() Offset               { return Subtract(r.End, r.Start) }
+func (r Range) String() string             { return fmt.Sprintf("[%s-%s)", r.Start, r.End) }
+func (r Range) Overlaps(or Range) bool     { return !(r.Start >= or.End || r.End <= or.Start) }
+func (r Range) Contains(addr Address) bool { return addr >= r.Start && addr < r.End }
+
+func (r Range) AsCIDRString() string {
+	prefixLen := 32
+	for size := r.Size(); size > 1; size = size / 2 {
+		if size%2 != 0 { // Size not a power of two; cannot be expressed as a CIDR.
+			return r.String()
+		}
+		prefixLen--
+	}
+	return CIDR{Start: r.Start, PrefixLen: prefixLen}.String()
+}
+
+type CIDR struct {
+	Start     Address
+	PrefixLen int
+}
+
+func ParseIP(s string) (Address, error) {
+	if ip := net.ParseIP(s); ip != nil {
+		return FromIP4(ip), nil
+	}
+	return 0, &net.ParseError{Type: "IP Address", Text: s}
+}
+
+func ParseCIDR(s string) (Address, CIDR, error) {
+	if ip, ipnet, err := net.ParseCIDR(s); err != nil {
+		return 0, CIDR{}, err
+	} else if ipnet.IP.To4() == nil {
+		return 0, CIDR{}, &net.ParseError{Type: "Non-IPv4 address not supported", Text: s}
+	} else {
+		prefixLen, _ := ipnet.Mask.Size()
+		return FromIP4(ip), CIDR{Start: FromIP4(ipnet.IP), PrefixLen: prefixLen}, nil
+	}
+}
+
+func (cidr CIDR) Size() Offset { return 1 << uint(32-cidr.PrefixLen) }
+
+func (cidr CIDR) Range() Range {
+	return NewRange(cidr.Start, cidr.Size())
+}
+func (cidr CIDR) HostRange() Range {
+	// Respect RFC1122 exclusions of first and last addresses
+	return NewRange(cidr.Start+1, cidr.Size()-2)
+}
+
+func (cidr CIDR) String() string {
+	return fmt.Sprintf("%s/%d", cidr.Start.String(), cidr.PrefixLen)
+}
+
+// FromIP4 converts an ipv4 address to our integer address type
+func FromIP4(ip4 net.IP) (r Address) {
+	for _, b := range ip4.To4() {
+		r <<= 8
+		r |= Address(b)
+	}
+	return
+}
+
+// IP4 converts our integer address type to an ipv4 address
+func (addr Address) IP4() (r net.IP) {
+	r = make([]byte, net.IPv4len)
+	for i := 3; i >= 0; i-- {
+		r[i] = byte(addr)
+		addr >>= 8
+	}
+	return
+}
+
+func (addr Address) MarshalJSON() ([]byte, error) {
+	return []byte(fmt.Sprintf("%q", addr.String())), nil
+}
+
+func (addr Address) String() string {
+	return addr.IP4().String()
+}
+
+func Add(addr Address, i Offset) Address {
+	return addr + Address(i)
+}
+
+func Subtract(a, b Address) Offset {
+	common.Assert(a >= b)
+	return Offset(a - b)
+}
+
+func Min(a, b Offset) Offset {
+	if a > b {
+		return b
+	}
+	return a
+}
+
+func (addr Address) Reverse() Address {
+	return ((addr >> 24) & 0xff) | // move byte 3 to byte 0
+		((addr << 8) & 0xff0000) | // move byte 1 to byte 2
+		((addr >> 8) & 0xff00) | // move byte 2 to byte 1
+		((addr << 24) & 0xff000000) // byte 0 to byte 3
+}

net/if.go

@@ -3,18 +3,53 @@ package net
 import (
 	"fmt"
 	"net"
-	"time"
+	"syscall"
+
+	"github.com/vishvananda/netlink/nl"
 )
 
-func EnsureInterface(ifaceName string, wait int) (iface *net.Interface, err error) {
-	if iface, err = findInterface(ifaceName); err == nil || wait == 0 {
-		return
+// Wait for an interface to come up.
+func EnsureInterface(ifaceName string) (*net.Interface, error) {
+	s, err := nl.Subscribe(syscall.NETLINK_ROUTE, syscall.RTNLGRP_LINK)
+	if err != nil {
+		return nil, err
 	}
-	for ; err != nil && wait > 0; wait -= 1 {
-		time.Sleep(1 * time.Second)
-		iface, err = findInterface(ifaceName)
+	defer s.Close()
+	iface, err := ensureInterface(s, ifaceName)
+	if err != nil {
+		return nil, err
 	}
-	return
+	return iface, err
+}
+
+func ensureInterface(s *nl.NetlinkSocket, ifaceName string) (*net.Interface, error) {
+	if iface, err := findInterface(ifaceName); err == nil {
+		return iface, nil
+	}
+	netlinkReceiveUntil(s, matchIfName(ifaceName))
+	iface, err := findInterface(ifaceName)
+	return iface, err
+}
+
+// Wait for an interface to come up and have a route added to the multicast subnet.
+// This matches the behaviour in 'weave attach', which is the only context in which
+// we expect this to be called.  If you change one, change the other to match.
+func EnsureInterfaceAndMcastRoute(ifaceName string) (*net.Interface, error) {
+	s, err := nl.Subscribe(syscall.NETLINK_ROUTE, syscall.RTNLGRP_LINK, syscall.RTNLGRP_IPV4_ROUTE)
+	if err != nil {
+		return nil, err
+	}
+	defer s.Close()
+	iface, err := ensureInterface(s, ifaceName)
+	if err != nil {
+		return nil, err
+	}
+	dest := net.IPv4(224, 0, 0, 0)
+	if CheckRouteExists(ifaceName, dest) {
+		return iface, err
+	}
+	netlinkReceiveUntil(s, matchRoute(ifaceName, dest))
+	return iface, err
 }
 
 func findInterface(ifaceName string) (iface *net.Interface, err error) {
@@ -26,3 +61,40 @@ func findInterface(ifaceName string) (iface *net.Interface, err error) {
 	}
 	return
 }
+
+func netlinkReceiveUntil(s *nl.NetlinkSocket, f func(syscall.NetlinkMessage) (bool, error)) error {
+	for {
+		msgs, err := s.Receive()
+		if err != nil {
+			return err
+		}
+		for _, m := range msgs {
+			if done, err := f(m); done {
+				return err
+			}
+		}
+	}
+}
+
+func matchIfName(ifaceName string) func(m syscall.NetlinkMessage) (bool, error) {
+	return func(m syscall.NetlinkMessage) (bool, error) {
+		switch m.Header.Type {
+		case syscall.RTM_NEWLINK: // receive this type for link 'up'
+			ifmsg := nl.DeserializeIfInfomsg(m.Data)
+			attrs, err := syscall.ParseNetlinkRouteAttr(&m)
+			if err != nil {
+				return true, err
+			}
+			name := ""
+			for _, attr := range attrs {
+				if attr.Attr.Type == syscall.IFA_LABEL {
+					name = string(attr.Value[:len(attr.Value)-1])
+				}
+			}
+			if ifaceName == name && ifmsg.Flags&syscall.IFF_UP != 0 {
+				return true, nil
+			}
+		}
+		return false, nil
+	}
+}

net/route.go

@@ -0,0 +1,115 @@
+package net
+
+import (
+	"fmt"
+	"net"
+	"syscall"
+
+	"github.com/vishvananda/netlink"
+	"github.com/vishvananda/netlink/nl"
+)
+
+// A network is considered free if it does not overlap any existing
+// routes on this host. This is the same approach taken by Docker.
+func CheckNetworkFree(subnet *net.IPNet, ignoreIfaceNames map[string]struct{}) error {
+	return forEachRoute(ignoreIfaceNames, func(name string, route netlink.Route) error {
+		if route.Dst != nil && overlaps(route.Dst, subnet) {
+			return fmt.Errorf("Network %s overlaps with existing route %s on host.", subnet, route.Dst)
+		}
+		return nil
+	})
+}
+
+// Two networks overlap if the start-point of one is inside the other.
+func overlaps(n1, n2 *net.IPNet) bool {
+	return n1.Contains(n2.IP) || n2.Contains(n1.IP)
+}
+
+// For a specific address, we only care if it is actually *inside* an
+// existing route, because weave-local traffic never hits IP routing.
+func CheckAddressOverlap(addr net.IP, ignoreIfaceNames map[string]struct{}) error {
+	return forEachRoute(ignoreIfaceNames, func(name string, route netlink.Route) error {
+		if route.Dst != nil && route.Dst.Contains(addr) {
+			return fmt.Errorf("Address %s overlaps with existing route %s on host.", addr, route.Dst)
+		}
+		return nil
+	})
+}
+
+func forEachRoute(ignoreIfaceNames map[string]struct{}, check func(name string, r netlink.Route) error) error {
+	routes, err := netlink.RouteList(nil, netlink.FAMILY_V4)
+	if err != nil {
+		return err
+	}
+	for _, route := range routes {
+		link, err := netlink.LinkByIndex(route.LinkIndex)
+		if err == nil {
+			if _, found := ignoreIfaceNames[link.Attrs().Name]; found {
+				continue
+			}
+		}
+		if err := check(link.Attrs().Name, route); err != nil {
+			return err
+		}
+	}
+	return nil
+}
+
+func CheckRouteExists(ifaceName string, dest net.IP) bool {
+	found := false
+	forEachRoute(map[string]struct{}{}, func(name string, route netlink.Route) error {
+		if name == ifaceName && route.Dst.IP.Equal(dest) {
+			found = true
+		}
+		return nil
+	})
+	return found
+}
+
+func matchRoute(ifaceName string, dest net.IP) func(m syscall.NetlinkMessage) (bool, error) {
+	return func(m syscall.NetlinkMessage) (bool, error) {
+		switch m.Header.Type {
+		case syscall.RTM_NEWROUTE:
+			route, err := deserializeRoute(m.Data)
+			if err != nil {
+				return true, err
+			}
+			link, _ := netlink.LinkByIndex(route.LinkIndex)
+			if link.Attrs().Name == ifaceName && route.Dst.IP.Equal(dest) {
+				return true, nil
+			}
+		}
+		return false, nil
+	}
+}
+
+// This code proposed for addition to the vishvananda/netlink library
+// deserializeRoute decodes a binary netlink message into a Route struct
+func deserializeRoute(m []byte) (netlink.Route, error) {
+	route := netlink.Route{}
+	msg := nl.DeserializeRtMsg(m)
+	attrs, err := nl.ParseRouteAttr(m[msg.Len():])
+	if err != nil {
+		return route, err
+	}
+	route.Scope = netlink.Scope(msg.Scope)
+
+	native := nl.NativeEndian()
+	for _, attr := range attrs {
+		switch attr.Attr.Type {
+		case syscall.RTA_GATEWAY:
+			route.Gw = net.IP(attr.Value)
+		case syscall.RTA_PREFSRC:
+			route.Src = net.IP(attr.Value)
+		case syscall.RTA_DST:
+			route.Dst = &net.IPNet{
+				IP:   attr.Value,
+				Mask: net.CIDRMask(int(msg.Dst_len), 8*len(attr.Value)),
+			}
+		case syscall.RTA_OIF:
+			routeIndex := int(native.Uint32(attr.Value[0:4]))
+			route.LinkIndex = routeIndex
+		}
+	}
+	return route, nil
+}

net/route_test.go

@@ -0,0 +1,25 @@
+package net
+
+import (
+	"net"
+	"testing"
+
+	"github.com/stretchr/testify/require"
+)
+
+func TestOverlap(t *testing.T) {
+	_, subnet1, _ := net.ParseCIDR("10.0.3.0/24")
+	_, subnet2, _ := net.ParseCIDR("10.0.4.0/24")
+	_, subnet3, _ := net.ParseCIDR("10.0.3.128/25")
+	_, subnet4, _ := net.ParseCIDR("10.0.3.192/25")
+	_, universe, _ := net.ParseCIDR("10.0.0.0/8")
+	require.False(t, overlaps(subnet1, subnet2))
+	require.False(t, overlaps(subnet2, subnet1))
+	require.True(t, overlaps(subnet1, subnet1))
+	require.True(t, overlaps(subnet1, subnet3))
+	require.True(t, overlaps(subnet1, subnet4))
+	require.False(t, overlaps(subnet2, subnet4))
+	require.False(t, overlaps(subnet4, subnet2))
+	require.True(t, overlaps(universe, subnet1))
+	require.True(t, overlaps(subnet1, universe))
+}

prog/netcheck/netcheck.go

@@ -0,0 +1,54 @@
+/* netcheck: check whether a given network or address overlaps with any existing routes */
+package main
+
+import (
+	"fmt"
+	"net"
+	"os"
+
+	"github.com/docker/docker/pkg/mflag"
+	weavenet "github.com/weaveworks/weave/net"
+)
+
+func fatal(err error) {
+	fmt.Fprintln(os.Stderr, err)
+	os.Exit(1)
+}
+
+type stringList map[string]struct{}
+
+func (ss *stringList) Set(value string) error {
+	(*ss)[value] = struct{}{}
+	return nil
+}
+
+func (ss *stringList) String() string {
+	return fmt.Sprintf("%v", *ss)
+}
+
+func main() {
+	ignoreIfaceNames := make(stringList)
+
+	mflag.Var(&ignoreIfaceNames, []string{"-ignore-iface"}, "name of interface to ignore)")
+	mflag.Parse()
+
+	if len(mflag.Args()) < 1 {
+		fmt.Fprintln(os.Stderr, "usage: netcheck [--ignore-iface <iface-name>] network-cidr")
+		os.Exit(1)
+	}
+
+	cidrStr := mflag.Args()[0]
+	addr, ipnet, err := net.ParseCIDR(cidrStr)
+	if err != nil {
+		fatal(err)
+	}
+	if ipnet.IP.Equal(addr) {
+		err = weavenet.CheckNetworkFree(ipnet, ignoreIfaceNames)
+	} else {
+		err = weavenet.CheckAddressOverlap(addr, ignoreIfaceNames)
+	}
+	if err != nil {
+		fatal(err)
+	}
+	os.Exit(0)
+}

prog/sigproxy/main.go

@@ -0,0 +1,50 @@
+package main
+
+import (
+	"log"
+	"os"
+	"os/exec"
+	"os/signal"
+	"syscall"
+)
+
+func main() {
+	if len(os.Args) == 1 {
+		log.Fatal("USAGE: sigproxy <command> [arguments ...]")
+	}
+
+	// Install signal handler as soon as possible - channel is buffered so
+	// we'll catch signals that arrive whilst child process is starting
+	sc := make(chan os.Signal, 1)
+	signal.Notify(sc, syscall.SIGINT, syscall.SIGTERM)
+
+	cmd := exec.Command(os.Args[1], os.Args[2:]...)
+
+	// These default to /dev/null, so set them explicitly to ours
+	cmd.Stdin = os.Stdin
+	cmd.Stdout = os.Stdout
+	cmd.Stderr = os.Stderr
+
+	if err := cmd.Start(); err != nil {
+		log.Fatal(err)
+	}
+
+	// Only begin delivering signals after the child has started
+	go func() {
+		for {
+			// Signalling PID 0 delivers to our process group
+			syscall.Kill(0, (<-sc).(syscall.Signal))
+		}
+	}()
+
+	if err := cmd.Wait(); err != nil {
+		// Exit status is platform specific so not directly accessible - casts
+		// required to access system-dependent exit information
+		if exitErr, ok := err.(*exec.ExitError); ok {
+			waitStatus := exitErr.Sys().(syscall.WaitStatus)
+			os.Exit(waitStatus.ExitStatus())
+		}
+		os.Exit(1)
+	}
+	os.Exit(0)
+}

prog/weaveexec/Dockerfile

@@ -0,0 +1,23 @@
+FROM gliderlabs/alpine
+
+MAINTAINER Weaveworks Inc <help@weave.works>
+LABEL works.weave.role=system
+
+WORKDIR /home/weave
+VOLUME /w
+ENTRYPOINT ["/home/weave/sigproxy", "/home/weave/weave"]
+
+RUN apk add --update \
+    curl \
+    ethtool \
+    iptables \
+    iproute2 \
+    util-linux \
+    conntrack-tools \
+    bind-tools \
+  && rm -rf /var/cache/apk/*
+
+ADD ./weave ./sigproxy ./weaveproxy /home/weave/
+ADD ./netcheck ./weavehosts /usr/bin/
+ADD ./weavewait /w/w
+ADD ./docker.tgz /

prog/weavehosts/weavehosts.go

@@ -0,0 +1,120 @@
+/* weavehosts: rewrite /etc/hosts as necessary to put the weave address(es) at the top */
+package main
+
+import (
+	"bufio"
+	"bytes"
+	"fmt"
+	"io/ioutil"
+	"net"
+	"os"
+	"sort"
+	"strings"
+)
+
+func main() {
+	args := os.Args
+	if len(args) < 4 {
+		fmt.Fprintln(os.Stderr, "usage: weavehosts hostpath hostname cidr [cidr ...]")
+		os.Exit(1)
+	}
+
+	checkErr(updateHosts(args[1], args[2], args[3:]))
+
+	os.Exit(0)
+}
+
+func checkErr(err error) {
+	if err != nil {
+		fmt.Fprintln(os.Stderr, err)
+		os.Exit(1)
+	}
+}
+
+func updateHosts(path, hostname string, cidrs []string) error {
+	hosts, err := parseHosts(path)
+	if err != nil {
+		return err
+	}
+
+	// Remove existing ips pointing to our hostname
+	toRemove := []string{}
+	for ip, addrs := range hosts {
+		for _, addr := range addrs {
+			if addr == hostname {
+				toRemove = append(toRemove, ip)
+				break
+			}
+		}
+	}
+	for _, ip := range toRemove {
+		delete(hosts, ip)
+	}
+
+	// Add the weave ip(s)
+	for _, cidr := range cidrs {
+		ip, _, err := net.ParseCIDR(cidr)
+		checkErr(err)
+		ipStr := ip.String()
+		hosts[ipStr] = append(hosts[ipStr], hostname)
+	}
+
+	return writeHosts(path, hosts)
+}
+
+func parseHosts(path string) (map[string][]string, error) {
+	f, err := os.Open(path)
+	if err != nil {
+		return nil, err
+	}
+	defer f.Close()
+	ips := map[string][]string{}
+	scanner := bufio.NewScanner(f)
+	for scanner.Scan() {
+		line := scanner.Text()
+
+		// Remove any comments
+		if i := strings.IndexByte(line, '#'); i != -1 {
+			line = line[:i]
+		}
+
+		fields := strings.Fields(line)
+		if len(fields) > 0 {
+			ips[fields[0]] = append(ips[fields[0]], fields[1:]...)
+		}
+	}
+	if scanner.Err() != nil {
+		return nil, scanner.Err()
+	}
+	return ips, nil
+}
+
+func writeHosts(path string, contents map[string][]string) error {
+	ips := []string{}
+	for ip := range contents {
+		ips = append(ips, ip)
+	}
+	sort.Strings(ips)
+
+	buf := &bytes.Buffer{}
+	fmt.Fprintln(buf, "# modified by weave")
+	for _, ip := range ips {
+		if addrs := contents[ip]; len(addrs) > 0 {
+			fmt.Fprintf(buf, "%s\t%s\n", ip, strings.Join(uniqueStrs(addrs), " "))
+		}
+	}
+	return ioutil.WriteFile(path, buf.Bytes(), 644)
+}
+
+func uniqueStrs(s []string) []string {
+	m := map[string]struct{}{}
+	result := []string{}
+	for _, str := range s {
+		if _, ok := m[str]; !ok {
+			m[str] = struct{}{}
+			result = append(result, str)
+		}
+	}
+	sort.Strings(result)
+	return result
+}

prog/weaveproxy/main.go

@@ -0,0 +1,66 @@
+package main
+
+import (
+	"fmt"
+	"os"
+	"strings"
+
+	"github.com/docker/docker/pkg/mflag"
+	. "github.com/weaveworks/weave/common"
+	"github.com/weaveworks/weave/common/mflagext"
+	"github.com/weaveworks/weave/proxy"
+)
+
+var (
+	version = "(unreleased version)"
+)
+
+func main() {
+	var (
+		justVersion bool
+		logLevel    = "info"
+		c           = proxy.Config{ListenAddrs: []string{}}
+	)
+
+	c.Version = version
+
+	mflag.BoolVar(&justVersion, []string{"#version", "-version"}, false, "print version and exit")
+	mflag.StringVar(&logLevel, []string{"-log-level"}, "info", "logging level (debug, info, warning, error)")
+	mflagext.ListVar(&c.ListenAddrs, []string{"H"}, nil, "addresses on which to listen")
+	mflag.StringVar(&c.HostnameFromLabel, []string{"-hostname-from-label"}, "", "Key of container label from which to obtain the container's hostname")
+	mflag.StringVar(&c.HostnameMatch, []string{"-hostname-match"}, "(.*)", "Regexp pattern to apply on container names (e.g. '^aws-[0-9]+-(.*)$')")
+	mflag.StringVar(&c.HostnameReplacement, []string{"-hostname-replacement"}, "$1", "Expression to generate hostnames based on matches from --hostname-match (e.g. 'my-app-$1')")
+	mflag.BoolVar(&c.RewriteInspect, []string{"-rewrite-inspect"}, false, "Rewrite 'inspect' calls to return the weave network settings (if attached)")
+	mflag.BoolVar(&c.NoDefaultIPAM, []string{"#-no-default-ipam", "-no-default-ipalloc"}, false, "do not automatically allocate addresses for containers without a WEAVE_CIDR")
+	mflag.BoolVar(&c.NoRewriteHosts, []string{"-no-rewrite-hosts"}, false, "do not automatically rewrite /etc/hosts. Use if you need the docker IP to remain in /etc/hosts")
+	mflag.StringVar(&c.TLSConfig.CACert, []string{"#tlscacert", "-tlscacert"}, "", "Trust certs signed only by this CA")
+	mflag.StringVar(&c.TLSConfig.Cert, []string{"#tlscert", "-tlscert"}, "", "Path to TLS certificate file")
+	mflag.BoolVar(&c.TLSConfig.Enabled, []string{"#tls", "-tls"}, false, "Use TLS; implied by --tls-verify")
+	mflag.StringVar(&c.TLSConfig.Key, []string{"#tlskey", "-tlskey"}, "", "Path to TLS key file")
+	mflag.BoolVar(&c.TLSConfig.Verify, []string{"#tlsverify", "-tlsverify"}, false, "Use TLS and verify the remote")
+	mflag.BoolVar(&c.WithDNS, []string{"-with-dns", "w"}, false, "instruct created containers to always use weaveDNS as their nameserver")
+	mflag.BoolVar(&c.WithoutDNS, []string{"-without-dns"}, false, "instruct created containers to never use weaveDNS as their nameserver")
+	mflag.Parse()
+
+	if justVersion {
+		fmt.Printf("weave proxy %s\n", version)
+		os.Exit(0)
+	}
+
+	if c.WithDNS && c.WithoutDNS {
+		Log.Fatalf("Cannot use both '--with-dns' and '--without-dns' flags")
+	}
+
+	SetLogLevel(logLevel)
+
+	Log.Infoln("weave proxy", version)
+	Log.Infoln("Command line arguments:", strings.Join(os.Args[1:], " "))
+
+	p, err := proxy.NewProxy(c)
+	if err != nil {
+		Log.Fatalf("Could not start proxy: %s", err)
+	}
+
+	go p.ListenAndServe()
+	SignalHandlerLoop()
+}

prog/weaveproxy/main_test.go

@@ -0,0 +1,12 @@
+package main
+
+import (
+	"testing"
+
+	weavetest "github.com/weaveworks/weave/testing"
+)
+
+func TestMain(t *testing.T) {
+	weavetest.TrimTestArgs()
+	main()
+}

prog/weaver/Dockerfile

@@ -1,5 +1,6 @@
 FROM scratch
 MAINTAINER Weaveworks Inc <help@weave.works>
+LABEL works.weave.role=system
 WORKDIR /home/weave
 ADD ./weaver /home/weave/
-ENTRYPOINT ["/home/weave/weaver", "-wait", "20"]
+ENTRYPOINT ["/home/weave/weaver"]

prog/weaver/http.go

@@ -0,0 +1,198 @@
+package main
+
+import (
+	"encoding/json"
+	"fmt"
+	"github.com/gorilla/mux"
+	. "github.com/weaveworks/weave/common"
+	"github.com/weaveworks/weave/ipam"
+	"github.com/weaveworks/weave/nameserver"
+	"github.com/weaveworks/weave/net/address"
+	weave "github.com/weaveworks/weave/router"
+	"net/http"
+	"strings"
+	"text/template"
+)
+
+var rootTemplate = template.New("root").Funcs(map[string]interface{}{
+	"countDNSEntries": func(entries []nameserver.EntryStatus) int {
+		count := 0
+		for _, entry := range entries {
+			if entry.Tombstone == 0 {
+				count++
+			}
+		}
+		return count
+	},
+	"printConnectionCounts": func(conns []weave.LocalConnectionStatus) string {
+		counts := make(map[string]int)
+		for _, conn := range conns {
+			counts[conn.State]++
+		}
+		return printCounts(counts, []string{"established", "pending", "retrying", "failed", "connecting"})
+	},
+	"printPeerConnectionCounts": func(peers []weave.PeerStatus) string {
+		counts := make(map[string]int)
+		for _, peer := range peers {
+			for _, conn := range peer.Connections {
+				if conn.Established {
+					counts["established"]++
+				} else {
+					counts["pending"]++
+				}
+			}
+		}
+		return printCounts(counts, []string{"established", "pending"})
+	},
+	"printState": func(enabled bool) string {
+		if enabled {
+			return "enabled"
+		}
+		return "disabled"
+	},
+	"trimSuffix": strings.TrimSuffix,
+})
+
+// Print counts in a specified order
+func printCounts(counts map[string]int, keys []string) string {
+	var stringCounts []string
+	for _, key := range keys {
+		if count, ok := counts[key]; ok {
+			stringCounts = append(stringCounts, fmt.Sprintf("%d %s", count, key))
+		}
+	}
+	return strings.Join(stringCounts, ", ")
+}
+
+// Strip escaped newlines from template
+func escape(template string) string {
+	return strings.Replace(template, "\\\n", "", -1)
+}
+
+// Define a named template panicking on error
+func defTemplate(name string, text string) *template.Template {
+	return template.Must(rootTemplate.New(name).Parse(escape(text)))
+}
+
+var statusTemplate = defTemplate("status", `\
+       Version: {{.Version}}
+
+       Service: router
+      Protocol: {{.Router.Protocol}} \
+{{if eq .Router.ProtocolMinVersion .Router.ProtocolMaxVersion}}\
+{{.Router.ProtocolMaxVersion}}\
+{{else}}\
+{{.Router.ProtocolMinVersion}}..{{.Router.ProtocolMaxVersion}}\
+{{end}}
+          Name: {{.Router.Name}}({{.Router.NickName}})
+    Encryption: {{printState .Router.Encryption}}
+ PeerDiscovery: {{printState .Router.PeerDiscovery}}
+       Targets: {{len .Router.Targets}}
+   Connections: {{len .Router.Connections}}{{with printConnectionCounts .Router.Connections}} ({{.}}){{end}}
+         Peers: {{len .Router.Peers}}{{with printPeerConnectionCounts .Router.Peers}} (with {{.}} connections between them){{end}}
+{{if .IPAM}}\
+
+       Service: ipam
+{{if .IPAM.Entries}}\
+     Consensus: achieved
+{{else if .IPAM.Paxos}}\
+     Consensus: waiting (quorum: {{.IPAM.Paxos.Quorum}}, known: {{.IPAM.Paxos.KnownNodes}})
+{{else}}\
+     Consensus: deferred
+{{end}}\
+         Range: {{.IPAM.Range}}
+ DefaultSubnet: {{.IPAM.DefaultSubnet}}
+{{end}}\
+{{if .DNS}}\
+
+       Service: dns
+        Domain: {{.DNS.Domain}}
+           TTL: {{.DNS.TTL}}
+       Entries: {{countDNSEntries .DNS.Entries}}
+{{end}}\
+`)
+
+var targetsTemplate = defTemplate("targetsTemplate", `\
+{{range .Router.Targets}}{{.}}
+{{end}}\
+`)
+
+var connectionsTemplate = defTemplate("connectionsTemplate", `\
+{{range .Router.Connections}}\
+{{if .Outbound}}->{{else}}<-{{end}} {{printf "%-21v" .Address}} {{printf "%-11v" .State}} {{.Info}}
+{{end}}\
+`)
+
+var peersTemplate = defTemplate("peers", `\
+{{range .Router.Peers}}\
+{{.Name}}({{.NickName}})
+{{range .Connections}}\
+   {{if .Outbound}}->{{else}}<-{{end}} {{printf "%-21v" .Address}} \
+{{$nameNickName := printf "%v(%v)" .Name .NickName}}{{printf "%-32v" $nameNickName}} \
+{{if .Established}}established{{else}}pending{{end}}
+{{end}}\
+{{end}}\
+`)
+
+var dnsEntriesTemplate = defTemplate("dnsEntries", `\
+{{$domain := printf ".%v" .DNS.Domain}}\
+{{range .DNS.Entries}}\
+{{if eq .Tombstone 0}}\
+{{$hostname := trimSuffix .Hostname $domain}}\
+{{printf "%-12v" $hostname}} {{printf "%-15v" .Address}} {{printf "%12.12v" .ContainerID}} {{.Origin}}
+{{end}}\
+{{end}}\
+`)
+
+type WeaveStatus struct {
+	Version string
+	Router  *weave.Status      `json:"Router,omitempty"`
+	IPAM    *ipam.Status       `json:"IPAM,omitempty"`
+	DNS     *nameserver.Status `json:"DNS,omitempty"`
+}
+
+func HandleHTTP(muxRouter *mux.Router, version string, router *weave.Router, allocator *ipam.Allocator, defaultSubnet address.CIDR, ns *nameserver.Nameserver, dnsserver *nameserver.DNSServer) {
+	status := func() WeaveStatus {
+		return WeaveStatus{
+			version,
+			weave.NewStatus(router),
+			ipam.NewStatus(allocator, defaultSubnet),
+			nameserver.NewStatus(ns, dnsserver)}
+	}
+	muxRouter.Methods("GET").Path("/report").Headers("Accept", "application/json").HandlerFunc(
+		func(w http.ResponseWriter, r *http.Request) {
+			json, _ := json.MarshalIndent(status(), "", "    ")
+			w.Header().Set("Content-Type", "application/json")
+			w.Write(json)
+		})
+
+	muxRouter.Methods("GET").Path("/report").Queries("format", "{format}").HandlerFunc(
+		func(w http.ResponseWriter, r *http.Request) {
+			formatTemplate, err := template.New("format").Parse(mux.Vars(r)["format"])
+			if err != nil {
+				http.Error(w, err.Error(), http.StatusBadRequest)
+				return
+			}
+			if err := formatTemplate.Execute(w, status()); err != nil {
+				http.Error(w, "error during template execution", http.StatusInternalServerError)
+				Log.Error(err)
+			}
+		})
+
+	defHandler := func(path string, template *template.Template) {
+		muxRouter.Methods("GET").Path(path).HandlerFunc(
+			func(w http.ResponseWriter, r *http.Request) {
+				if err := template.Execute(w, status()); err != nil {
+					http.Error(w, "error during template execution", http.StatusInternalServerError)
+					Log.Error(err)
+				}
+			})
+	}
+
+	defHandler("/status", statusTemplate)
+	defHandler("/status/targets", targetsTemplate)
+	defHandler("/status/connections", connectionsTemplate)
+	defHandler("/status/peers", peersTemplate)
+	defHandler("/status/dns", dnsEntriesTemplate)
+
+}

prog/weaver/main.go

@@ -0,0 +1,333 @@
+package main
+
+import (
+	"crypto/sha256"
+	"fmt"
+	"net"
+	"net/http"
+	_ "net/http/pprof"
+	"os"
+	"runtime"
+	"strings"
+	"time"
+
+	"github.com/davecheney/profile"
+	"github.com/docker/docker/pkg/mflag"
+	"github.com/gorilla/mux"
+
+	. "github.com/weaveworks/weave/common"
+	"github.com/weaveworks/weave/common/docker"
+	"github.com/weaveworks/weave/ipam"
+	"github.com/weaveworks/weave/nameserver"
+	weavenet "github.com/weaveworks/weave/net"
+	"github.com/weaveworks/weave/net/address"
+	weave "github.com/weaveworks/weave/router"
+)
+
+var version = "(unreleased version)"
+
+func main() {
+	procs := runtime.NumCPU()
+	// packet sniffing can block an OS thread, so we need one thread
+	// for that plus at least one more.
+	if procs < 2 {
+		procs = 2
+	}
+	runtime.GOMAXPROCS(procs)
+
+	var (
+		config             weave.Config
+		justVersion        bool
+		protocolMinVersion int
+		ifaceName          string
+		routerName         string
+		nickName           string
+		password           string
+		pktdebug           bool
+		logLevel           string
+		prof               string
+		bufSzMB            int
+		noDiscovery        bool
+		httpAddr           string
+		iprangeCIDR        string
+		ipsubnetCIDR       string
+		peerCount          int
+		apiPath            string
+		peers              []string
+
+		noDNS                     bool
+		dnsDomain                 string
+		dnsListenAddress          string
+		dnsTTL                    int
+		dnsClientTimeout          time.Duration
+		dnsEffectiveListenAddress string
+	)
+
+	mflag.BoolVar(&justVersion, []string{"#version", "-version"}, false, "print version and exit")
+	mflag.IntVar(&config.Port, []string{"#port", "-port"}, weave.Port, "router port")
+	mflag.IntVar(&protocolMinVersion, []string{"-min-protocol-version"}, weave.ProtocolMinVersion, "minimum weave protocol version")
+	mflag.StringVar(&ifaceName, []string{"#iface", "-iface"}, "", "name of interface to capture/inject from (disabled if blank)")
+	mflag.StringVar(&routerName, []string{"#name", "-name"}, "", "name of router (defaults to MAC of interface)")
+	mflag.StringVar(&nickName, []string{"#nickname", "-nickname"}, "", "nickname of peer (defaults to hostname)")
+	mflag.StringVar(&password, []string{"#password", "-password"}, "", "network password")
+	mflag.StringVar(&logLevel, []string{"-log-level"}, "info", "logging level (debug, info, warning, error)")
+	mflag.BoolVar(&pktdebug, []string{"#pktdebug", "#-pktdebug", "-pkt-debug"}, false, "enable per-packet debug logging")
+	mflag.StringVar(&prof, []string{"#profile", "-profile"}, "", "enable profiling and write profiles to given path")
+	mflag.IntVar(&config.ConnLimit, []string{"#connlimit", "#-connlimit", "-conn-limit"}, 30, "connection limit (0 for unlimited)")
+	mflag.BoolVar(&noDiscovery, []string{"#nodiscovery", "#-nodiscovery", "-no-discovery"}, false, "disable peer discovery")
+	mflag.IntVar(&bufSzMB, []string{"#bufsz", "-bufsz"}, 8, "capture buffer size in MB")
+	mflag.StringVar(&httpAddr, []string{"#httpaddr", "#-httpaddr", "-http-addr"}, fmt.Sprintf(":%d", weave.HTTPPort), "address to bind HTTP interface to (disabled if blank, absolute path indicates unix domain socket)")
+	mflag.StringVar(&iprangeCIDR, []string{"#iprange", "#-iprange", "-ipalloc-range"}, "", "IP address range reserved for automatic allocation, in CIDR notation")
+	mflag.StringVar(&ipsubnetCIDR, []string{"#ipsubnet", "#-ipsubnet", "-ipalloc-default-subnet"}, "", "subnet to allocate within by default, in CIDR notation")
+	mflag.IntVar(&peerCount, []string{"#initpeercount", "#-initpeercount", "-init-peer-count"}, 0, "number of peers in network (for IP address allocation)")
+	mflag.StringVar(&apiPath, []string{"#api", "-api"}, "unix:///var/run/docker.sock", "Path to Docker API socket")
+	mflag.BoolVar(&noDNS, []string{"-no-dns"}, false, "disable DNS server")
+	mflag.StringVar(&dnsDomain, []string{"-dns-domain"}, nameserver.DefaultDomain, "local domain to server requests for")
+	mflag.StringVar(&dnsListenAddress, []string{"-dns-listen-address"}, nameserver.DefaultListenAddress, "address to listen on for DNS requests")
+	mflag.IntVar(&dnsTTL, []string{"-dns-ttl"}, nameserver.DefaultTTL, "TTL for DNS request from our domain")
+	mflag.DurationVar(&dnsClientTimeout, []string{"-dns-fallback-timeout"}, nameserver.DefaultClientTimeout, "timeout for fallback DNS requests")
+	mflag.StringVar(&dnsEffectiveListenAddress, []string{"-dns-effective-listen-address"}, "", "address DNS will actually be listening, after Docker port mapping")
+
+	// crude way of detecting that we probably have been started in a
+	// container, with `weave launch` --> suppress misleading paths in
+	// mflags error messages.
+	if os.Args[0] == "/home/weave/weaver" { // matches the Dockerfile ENTRYPOINT
+		os.Args[0] = "weave"
+		mflag.CommandLine.Init("weave", mflag.ExitOnError)
+	}
+	mflag.Parse()
+
+	peers = mflag.Args()
+
+	SetLogLevel(logLevel)
+	if justVersion {
+		fmt.Printf("weave router %s\n", version)
+		os.Exit(0)
+	}
+
+	Log.Println("Command line options:", options())
+	Log.Println("Command line peers:", peers)
+
+	if protocolMinVersion < weave.ProtocolMinVersion || protocolMinVersion > weave.ProtocolMaxVersion {
+		Log.Fatalf("--min-protocol-version must be in range [%d,%d]", weave.ProtocolMinVersion, weave.ProtocolMaxVersion)
+	}
+	config.ProtocolMinVersion = byte(protocolMinVersion)
+
+	var err error
+
+	if ifaceName != "" {
+		config.Iface, err = weavenet.EnsureInterface(ifaceName)
+		if err != nil {
+			Log.Fatal(err)
+		}
+	}
+
+	if routerName == "" {
+		if config.Iface == nil {
+			Log.Fatal("Either an interface must be specified with --iface or a name with -name")
+		}
+		routerName = config.Iface.HardwareAddr.String()
+	}
+	name, err := weave.PeerNameFromUserInput(routerName)
+	if err != nil {
+		Log.Fatal(err)
+	}
+
+	if nickName == "" {
+		nickName, err = os.Hostname()
+		if err != nil {
+			Log.Fatal(err)
+		}
+	}
+
+	if password == "" {
+		password = os.Getenv("WEAVE_PASSWORD")
+	}
+	if password == "" {
+		Log.Println("Communication between peers is unencrypted.")
+	} else {
+		config.Password = []byte(password)
+		Log.Println("Communication between peers is encrypted.")
+	}
+
+	if prof != "" {
+		p := *profile.CPUProfile
+		p.ProfilePath = prof
+		p.NoShutdownHook = true
+		defer profile.Start(&p).Stop()
+	}
+
+	config.BufSz = bufSzMB * 1024 * 1024
+	config.LogFrame = logFrameFunc(pktdebug)
+	config.PeerDiscovery = !noDiscovery
+
+	router := weave.NewRouter(config, name, nickName)
+	Log.Println("Our name is", router.Ourself)
+
+	dockerCli, err := docker.NewClient(apiPath)
+	if err != nil {
+		Log.Fatal("Unable to start docker client: ", err)
+	}
+
+	var allocator *ipam.Allocator
+	var defaultSubnet address.CIDR
+	if iprangeCIDR != "" {
+		allocator, defaultSubnet = createAllocator(router, iprangeCIDR, ipsubnetCIDR, determineQuorum(peerCount, peers))
+		if err = dockerCli.AddObserver(allocator); err != nil {
+			Log.Fatal("Unable to start watcher", err)
+		}
+	} else if peerCount > 0 {
+		Log.Fatal("--init-peer-count flag specified without --ipalloc-range")
+	}
+
+	var (
+		ns        *nameserver.Nameserver
+		dnsserver *nameserver.DNSServer
+	)
+	if !noDNS {
+		ns = nameserver.New(router.Ourself.Peer.Name, router.Peers, dockerCli, dnsDomain)
+		ns.SetGossip(router.NewGossip("nameserver", ns))
+		if err = dockerCli.AddObserver(ns); err != nil {
+			Log.Fatal("Unable to start watcher", err)
+		}
+		ns.Start()
+		defer ns.Stop()
+		dnsserver, err = nameserver.NewDNSServer(ns, dnsDomain, dnsListenAddress,
+			dnsEffectiveListenAddress, uint32(dnsTTL), dnsClientTimeout)
+		if err != nil {
+			Log.Fatal("Unable to start dns server: ", err)
+		}
+		dnsserver.ActivateAndServe()
+		defer dnsserver.Stop()
+	}
+
+	router.Start()
+	if errors := router.ConnectionMaker.InitiateConnections(peers, false); len(errors) > 0 {
+		Log.Fatal(ErrorMessages(errors))
+	}
+
+	// The weave script always waits for a status call to succeed,
+	// so there is no point in doing "weave launch --http-addr ''".
+	// This is here to support stand-alone use of weaver.
+	if httpAddr != "" {
+		muxRouter := mux.NewRouter()
+		if allocator != nil {
+			allocator.HandleHTTP(muxRouter, defaultSubnet, dockerCli)
+		}
+		if ns != nil {
+			ns.HandleHTTP(muxRouter)
+		}
+		router.HandleHTTP(muxRouter)
+		HandleHTTP(muxRouter, version, router, allocator, defaultSubnet, ns, dnsserver)
+		http.Handle("/", muxRouter)
+		go listenAndServeHTTP(httpAddr, muxRouter)
+	}
+
+	SignalHandlerLoop(router)
+}
+
+func options() map[string]string {
+	options := make(map[string]string)
+	mflag.Visit(func(f *mflag.Flag) {
+		value := f.Value.String()
+		name := canonicalName(f)
+		if name == "password" {
+			value = "<elided>"
+		}
+		options[name] = value
+	})
+	return options
+}
+
+func canonicalName(f *mflag.Flag) string {
+	for _, n := range f.Names {
+		if n[0] != '#' {
+			return strings.TrimLeft(n, "#-")
+		}
+	}
+	return ""
+}
+
+func logFrameFunc(debug bool) weave.LogFrameFunc {
+	if !debug {
+		return func(prefix string, frame []byte, dec *weave.EthernetDecoder) {}
+	}
+	return func(prefix string, frame []byte, dec *weave.EthernetDecoder) {
+		h := fmt.Sprintf("%x", sha256.Sum256(frame))
+		parts := []interface{}{prefix, len(frame), "bytes (", h, ")"}
+
+		if dec != nil {
+			parts = append(parts, dec.Eth.SrcMAC, "->", dec.Eth.DstMAC)
+
+			if dec.DF() {
+				parts = append(parts, "(DF)")
+			}
+		}
+
+		Log.Println(parts...)
+	}
+}
+
+func parseAndCheckCIDR(cidrStr string) address.CIDR {
+	_, cidr, err := address.ParseCIDR(cidrStr)
+	if err != nil {
+		Log.Fatal(err)
+	}
+	if cidr.Size() < ipam.MinSubnetSize {
+		Log.Fatalf("Allocation range smaller than minimum size %d: %s", ipam.MinSubnetSize, cidrStr)
+	}
+	return cidr
+}
+
+func createAllocator(router *weave.Router, ipRangeStr string, defaultSubnetStr string, quorum uint) (*ipam.Allocator, address.CIDR) {
+	ipRange := parseAndCheckCIDR(ipRangeStr)
+	defaultSubnet := ipRange
+	if defaultSubnetStr != "" {
+		defaultSubnet = parseAndCheckCIDR(defaultSubnetStr)
+		if !ipRange.Range().Overlaps(defaultSubnet.Range()) {
+			Log.Fatalf("IP address allocation default subnet %s does not overlap with allocation range %s", defaultSubnet, ipRange)
+		}
+	}
+	allocator := ipam.NewAllocator(router.Ourself.Peer.Name, router.Ourself.Peer.UID, router.Ourself.Peer.NickName, ipRange.Range(), quorum)
+
+	allocator.SetInterfaces(router.NewGossip("IPallocation", allocator))
+	allocator.Start()
+
+	return allocator, defaultSubnet
+}
+
+// Pick a quorum size heuristically based on the number of peer
+// addresses passed.
+func determineQuorum(initPeerCountFlag int, peers []string) uint {
+	if initPeerCountFlag > 0 {
+		return uint(initPeerCountFlag/2 + 1)
+	}
+
+	// Guess a suitable quorum size based on the list of peer
+	// addresses.  The peer list might or might not contain an
+	// address for this peer, so the conservative assumption is
+	// that it doesn't.  The list might contain multiple addresses
+	// that resolve to the same peer, in which case the quorum
+	// might be larger than it needs to be.  But the user can
+	// specify it explicitly if that becomes a problem.
+	clusterSize := uint(len(peers) + 1)
+	quorum := clusterSize/2 + 1
+	Log.Println("Assuming quorum size of", quorum)
+	return quorum
+}
+
+func listenAndServeHTTP(httpAddr string, muxRouter *mux.Router) {
+	protocol := "tcp"
+	if strings.HasPrefix(httpAddr, "/") {
+		os.Remove(httpAddr) // in case it's there from last time
+		protocol = "unix"
+	}
+	l, err := net.Listen(protocol, httpAddr)
+	if err != nil {
+		Log.Fatal("Unable to create http listener socket: ", err)
+	}
+	err = http.Serve(l, nil)
+	if err != nil {
+		Log.Fatal("Unable to create http server", err)
+	}
+}

prog/weaver/main_test.go

@@ -0,0 +1,12 @@
+package main
+
+import (
+	"testing"
+
+	weavetest "github.com/weaveworks/weave/testing"
+)
+
+func TestMain(t *testing.T) {
+	weavetest.TrimTestArgs()
+	main()
+}

prog/weavewait/main.go

@@ -0,0 +1,40 @@
+package main
+
+import (
+	"errors"
+	"fmt"
+	"os"
+	"os/exec"
+	"syscall"
+
+	weavenet "github.com/weaveworks/weave/net"
+)
+
+var (
+	ErrNoCommandSpecified = errors.New("No command specified")
+)
+
+func main() {
+	var (
+		args = os.Args[1:]
+	)
+
+	_, err := weavenet.EnsureInterfaceAndMcastRoute("ethwe")
+	checkErr(err)
+
+	if len(args) == 0 {
+		checkErr(ErrNoCommandSpecified)
+	}
+
+	binary, err := exec.LookPath(args[0])
+	checkErr(err)
+
+	checkErr(syscall.Exec(binary, args, os.Environ()))
+}
+
+func checkErr(err error) {
+	if err != nil {
+		fmt.Fprintln(os.Stderr, err)
+		os.Exit(1)
+	}
+}

proxy/chunked.go

@@ -0,0 +1,123 @@
+// Based on net/http/internal
+package proxy
+
+import (
+	"bufio"
+	"bytes"
+	"errors"
+	"io"
+	"io/ioutil"
+	"strconv"
+)
+
+var (
+	ErrLineTooLong        = errors.New("header line too long")
+	ErrInvalidChunkLength = errors.New("invalid byte in chunk length")
+)
+
+// Unlike net/http/internal.chunkedReader, this has an interface where we can
+// handle individual chunks. The interface is based on database/sql.Rows.
+func NewChunkedReader(r io.Reader) *ChunkedReader {
+	br, ok := r.(*bufio.Reader)
+	if !ok {
+		br = bufio.NewReader(r)
+	}
+	return &ChunkedReader{r: br}
+}
+
+type ChunkedReader struct {
+	r     *bufio.Reader
+	chunk *io.LimitedReader
+	err   error
+	buf   [2]byte
+}
+
+// Next prepares the next chunk for reading. It returns true on success, or
+// false if there is no next chunk or an error happened while preparing
+// it. Err should be consulted to distinguish between the two cases.
+//
+// Every call to Chunk, even the first one, must be preceded by a call to Next.
+//
+// Calls to Next will discard any unread bytes in the current Chunk.
+func (cr *ChunkedReader) Next() bool {
+	if cr.err != nil {
+		return false
+	}
+
+	// Check the termination of the previous chunk
+	if cr.chunk != nil {
+		// Make sure the remainder is drained, in case the user of this quit
+		// reading early.
+		if _, cr.err = io.Copy(ioutil.Discard, cr.chunk); cr.err != nil {
+			return false
+		}
+
+		// Check the next two bytes after the chunk are \r\n
+		if _, cr.err = io.ReadFull(cr.r, cr.buf[:2]); cr.err != nil {
+			return false
+		}
+		if cr.buf[0] != '\r' || cr.buf[1] != '\n' {
+			cr.err = errors.New("malformed chunked encoding")
+			return false
+		}
+	} else {
+		cr.chunk = &io.LimitedReader{R: cr.r}
+	}
+
+	// Setup the next chunk
+	if n := cr.beginChunk(); n > 0 {
+		cr.chunk.N = int64(n)
+	} else if cr.err == nil {
+		cr.err = io.EOF
+	}
+	return cr.err == nil
+}
+
+// Chunk returns the io.Reader of the current chunk. On each call, this returns
+// the same io.Reader for a given chunk.
+func (cr *ChunkedReader) Chunk() io.Reader {
+	return cr.chunk
+}
+
+// Err returns the error, if any, that was encountered during iteration.
+func (cr *ChunkedReader) Err() error {
+	if cr.err == io.EOF {
+		return nil
+	}
+	return cr.err
+}
+
+func (cr *ChunkedReader) beginChunk() uint64 {
+	var (
+		line []byte
+		n    uint64
+	)
+	// chunk-size CRLF
+	line, cr.err = readLine(cr.r)
+	if cr.err != nil {
+		return 0
+	}
+	n, cr.err = strconv.ParseUint(string(line), 16, 64)
+	if cr.err != nil {
+		cr.err = ErrInvalidChunkLength
+	}
+	return n
+}
+
+// Read a line of bytes (up to \n) from b.
+// Give up if the line exceeds the buffer size.
+// The returned bytes are a pointer into storage in
+// the bufio, so they are only valid until the next bufio read.
+func readLine(b *bufio.Reader) (p []byte, err error) {
+	if p, err = b.ReadSlice('\n'); err != nil {
+		// We always know when EOF is coming.
+		// If the caller asked for a line, there should be a line.
+		if err == io.EOF {
+			err = io.ErrUnexpectedEOF
+		} else if err == bufio.ErrBufferFull {
+			err = ErrLineTooLong
+		}
+		return nil, err
+	}
+	return bytes.TrimRight(p, " \t\n\r"), nil
+}

proxy/chunked_test.go

@@ -0,0 +1,174 @@
+// Based on net/http/internal
+package proxy
+
+import (
+	"bytes"
+	"io"
+	"io/ioutil"
+	"strconv"
+	"strings"
+	"testing"
+)
+
+func TestChunk(t *testing.T) {
+	r := NewChunkedReader(bytes.NewBufferString(
+		"7\r\nhello, \r\n17\r\nworld! 0123456789abcdef\r\n0\r\n",
+	))
+
+	assertNextChunk(t, r, "hello, ")
+	assertNextChunk(t, r, "world! 0123456789abcdef")
+	assertNoMoreChunks(t, r)
+}
+
+func TestIncompleteReadOfChunk(t *testing.T) {
+	r := NewChunkedReader(bytes.NewBufferString(
+		"7\r\nhello, \r\n17\r\nworld! 0123456789abcdef\r\n0\r\n",
+	))
+
+	// Incomplete read of first chunk
+	{
+		if !r.Next() {
+			t.Fatalf("Expected chunk, but ran out early: %v", r.Err())
+		}
+		if r.Err() != nil {
+			t.Fatalf("Error reading chunk: %q", r.Err())
+		}
+		// Read just 2 bytes
+		buf := make([]byte, 2)
+		if _, err := io.ReadFull(r.Chunk(), buf[:2]); err != nil {
+			t.Fatalf("Error reading first bytes of chunk: %q", err)
+		}
+		if buf[0] != 'h' || buf[1] != 'e' {
+			t.Fatalf("Unexpected first 2 bytes of chunk: %q", buf)
+		}
+	}
+
+	assertNextChunk(t, r, "world! 0123456789abcdef")
+	assertNoMoreChunks(t, r)
+}
+
+func TestMalformedChunks(t *testing.T) {
+	r := NewChunkedReader(bytes.NewBufferString(
+		"7\r\nhello, GARBAGEBYTES17\r\nworld! 0123456789abcdef\r\n0\r\n",
+	))
+
+	assertNextChunk(t, r, "hello, ")
+	assertError(t, r, "malformed chunked encoding")
+}
+
+type charReader byte
+
+// Read an infinite sequence of some char
+func (r *charReader) Read(p []byte) (int, error) {
+	b := byte(*r)
+	for i := range p {
+		p[i] = b
+	}
+	return len(p), nil
+}
+
+func TestLargeChunks(t *testing.T) {
+	var expected int64 = 1024 * 1024
+	chars := charReader('a')
+	r := NewChunkedReader(io.MultiReader(
+		strings.NewReader(strconv.FormatInt(expected, 16)+"\r\n"),
+		&io.LimitedReader{N: expected, R: &chars},
+		strings.NewReader("\r\n0\r\n"),
+	))
+
+	if !r.Next() {
+		t.Fatalf("Expected chunk, but ran out early: %v", r.Err())
+	}
+	if r.Err() != nil {
+		t.Fatalf("Error reading chunk: %q", r.Err())
+	}
+	n, err := io.Copy(ioutil.Discard, r.Chunk())
+	if n != expected {
+		t.Errorf("chunk reader read %q; want %q", n, expected)
+	}
+	if err != nil {
+		t.Fatalf("reading chunk: %v", err)
+	}
+	assertNoMoreChunks(t, r)
+}
+
+func TestInvalidChunkSize(t *testing.T) {
+	r := NewChunkedReader(bytes.NewBufferString(
+		"foobar\r\nhello, \r\n0\r\n",
+	))
+
+	assertError(t, r, "invalid byte in chunk length")
+}
+
+func TestChunkSizeLineTooLong(t *testing.T) {
+	var (
+		maxLineLength = 4096
+		chunkSize     string
+	)
+	for i := 0; i < maxLineLength; i++ {
+		chunkSize = chunkSize + "0"
+	}
+	chunkSize = chunkSize + "7"
+
+	r := NewChunkedReader(bytes.NewBufferString(
+		chunkSize + "\r\nhello, \r\n0\r\n",
+	))
+
+	assertError(t, r, "header line too long")
+}
+
+func TestBytesAfterLastChunkAreIgnored(t *testing.T) {
+	r := NewChunkedReader(bytes.NewBufferString(
+		"7\r\nhello, \r\n0\r\nGARBAGEBYTES",
+	))
+
+	assertNextChunk(t, r, "hello, ")
+	assertNoMoreChunks(t, r)
+}
+
+func assertNextChunk(t *testing.T, r *ChunkedReader, expected string) {
+	if !r.Next() {
+		t.Fatalf("Expected chunk, but ran out early: %v", r.Err())
+	}
+	if r.Err() != nil {
+		t.Fatalf("Error reading chunk: %q", r.Err())
+	}
+	data, err := ioutil.ReadAll(r.Chunk())
+	if string(data) != expected {
+		t.Errorf("chunk reader read %q; want %q", data, expected)
+	}
+	if err != nil {
+		t.Logf(`data: %q`, data)
+		t.Fatalf("reading chunk: %v", err)
+	}
+}
+
+func assertError(t *testing.T, r *ChunkedReader, e string) {
+	if r.Next() {
+		t.Errorf("Expected failure when reading chunks, but got one")
+	}
+	if r.Err() == nil || r.Err().Error() != e {
+		t.Errorf("chunk reader errored %q; want %q", r.Err(), e)
+	}
+	data, err := ioutil.ReadAll(r.Chunk())
+	if len(data) != 0 {
+		t.Errorf("chunk should have been empty. got %q", data)
+	}
+	if err != nil {
+		t.Logf(`data: %q`, data)
+		t.Errorf("reading chunk: %v", err)
+	}
+
+	if r.Next() {
+		t.Errorf("Expected no more chunks, but found too many")
+	}
+}
+
+func assertNoMoreChunks(t *testing.T, r *ChunkedReader) {
+	if r.Next() {
+		t.Errorf("Expected no more chunks, but found too many")
+	}
+	if r.Err() != nil {
+		t.Errorf("Expected no error, but found: %q", r.Err())
+	}
+}

proxy/common.go

@@ -0,0 +1,139 @@
+package proxy
+
+import (
+	"bytes"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"io/ioutil"
+	"net"
+	"net/http"
+	"os"
+	"os/exec"
+	"regexp"
+	"strings"
+
+	"github.com/fsouza/go-dockerclient"
+	. "github.com/weaveworks/weave/common"
+)
+
+var (
+	containerIDRegexp   = regexp.MustCompile("^(/v[0-9\\.]*)?/containers/([^/]*)/.*")
+	weaveWaitEntrypoint = []string{"/w/w"}
+)
+
+func callWeave(args ...string) ([]byte, []byte, error) {
+	args = append([]string{"--local"}, args...)
+	Log.Debug("Calling weave", args)
+	cmd := exec.Command("./weave", args...)
+	cmd.Env = []string{
+		"PATH=/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin",
+		"PROCFS=/hostproc",
+	}
+	if bridge := os.Getenv("DOCKER_BRIDGE"); bridge != "" {
+		cmd.Env = append(cmd.Env, fmt.Sprintf("DOCKER_BRIDGE=%s", bridge))
+	}
+	var stdout, stderr bytes.Buffer
+	cmd.Stdout = &stdout
+	cmd.Stderr = &stderr
+	err := cmd.Run()
+	return stdout.Bytes(), stderr.Bytes(), err
+}
+
+func unmarshalRequestBody(r *http.Request, target interface{}) error {
+	body, err := ioutil.ReadAll(r.Body)
+	if err != nil {
+		return err
+	}
+	if err := r.Body.Close(); err != nil {
+		return err
+	}
+	r.Body = ioutil.NopCloser(bytes.NewReader(body))
+
+	d := json.NewDecoder(bytes.NewReader(body))
+	d.UseNumber() // don't want large numbers in scientific format
+	return d.Decode(&target)
+}
+
+func marshalRequestBody(r *http.Request, body interface{}) error {
+	newBody, err := json.Marshal(body)
+	if err != nil {
+		return err
+	}
+	r.Body = ioutil.NopCloser(bytes.NewReader(newBody))
+	r.ContentLength = int64(len(newBody))
+	return nil
+}
+
+func unmarshalResponseBody(r *http.Response, target interface{}) error {
+	body, err := ioutil.ReadAll(r.Body)
+	if err != nil {
+		return err
+	}
+	if err := r.Body.Close(); err != nil {
+		return err
+	}
+	r.Body = ioutil.NopCloser(bytes.NewReader(body))
+
+	d := json.NewDecoder(bytes.NewReader(body))
+	d.UseNumber() // don't want large numbers in scientific format
+	return d.Decode(&target)
+}
+
+func marshalResponseBody(r *http.Response, body interface{}) error {
+	newBody, err := json.Marshal(body)
+	if err != nil {
+		return err
+	}
+	r.Body = ioutil.NopCloser(bytes.NewReader(newBody))
+	r.ContentLength = int64(len(newBody))
+	// Stop it being chunked, because that hangs
+	r.TransferEncoding = nil
+	return nil
+
+}
+
+func inspectContainerInPath(client *docker.Client, path string) (*docker.Container, error) {
+	subs := containerIDRegexp.FindStringSubmatch(path)
+	if subs == nil {
+		err := fmt.Errorf("No container id found in request with path %s", path)
+		Log.Warningln(err)
+		return nil, err
+	}
+	containerID := subs[2]
+
+	container, err := client.InspectContainer(containerID)
+	if err != nil {
+		Log.Warningf("Error inspecting container %s: %v", containerID, err)
+	}
+	return container, err
+}
+
+func weaveContainerIPs(containerID string) (mac string, ips []net.IP, nets []*net.IPNet, err error) {
+	stdout, stderr, err := callWeave("ps", containerID)
+	if err != nil || len(stderr) > 0 {
+		err = errors.New(string(stderr))
+		return
+	}
+	if len(stdout) <= 0 {
+		return
+	}
+
+	fields := strings.Fields(string(stdout))
+	if len(fields) < 2 {
+		return
+	}
+	mac = fields[1]
+
+	var ip net.IP
+	var ipnet *net.IPNet
+	for _, cidr := range fields[2:] {
+		ip, ipnet, err = net.ParseCIDR(cidr)
+		if err != nil {
+			return
+		}
+		ips = append(ips, ip)
+		nets = append(nets, ipnet)
+	}
+	return
+}

proxy/create_container_interceptor.go

@@ -0,0 +1,180 @@
+package proxy
+
+import (
+	"errors"
+	"fmt"
+	"io/ioutil"
+	"net/http"
+	"strings"
+
+	"github.com/fsouza/go-dockerclient"
+
+	. "github.com/weaveworks/weave/common"
+	"github.com/weaveworks/weave/nameserver"
+	"github.com/weaveworks/weave/router"
+)
+
+const MaxDockerHostname = 64
+
+var (
+	ErrNoCommandSpecified = errors.New("No command specified")
+)
+
+type createContainerInterceptor struct{ proxy *Proxy }
+
+type createContainerRequestBody struct {
+	*docker.Config
+	HostConfig *docker.HostConfig `json:"HostConfig,omitempty" yaml:"HostConfig,omitempty"`
+	MacAddress string             `json:"MacAddress,omitempty" yaml:"MacAddress,omitempty"`
+}
+
+// ErrNoSuchImage replaces docker.NoSuchImage, which does not contain the image
+// name, which in turn breaks docker clients post 1.7.0 since they expect the
+// image name to be present in errors.
+type ErrNoSuchImage struct {
+	Name string
+}
+
+func (err *ErrNoSuchImage) Error() string {
+	return "No such image: " + err.Name
+}
+
+func (i *createContainerInterceptor) InterceptRequest(r *http.Request) error {
+	container := createContainerRequestBody{}
+	if err := unmarshalRequestBody(r, &container); err != nil {
+		return err
+	}
+
+	if cidrs, err := i.proxy.weaveCIDRsFromConfig(container.Config, container.HostConfig); err != nil {
+		Log.Infof("Leaving container alone because %s", err)
+	} else {
+		Log.Infof("Creating container with WEAVE_CIDR \"%s\"", strings.Join(cidrs, " "))
+		if container.HostConfig == nil {
+			container.HostConfig = &docker.HostConfig{}
+		}
+		if container.Config == nil {
+			container.Config = &docker.Config{}
+		}
+		i.addWeaveWaitVolume(container.HostConfig)
+		if err := i.setWeaveWaitEntrypoint(container.Config); err != nil {
+			return err
+		}
+		hostname := r.URL.Query().Get("name")
+		if i.proxy.Config.HostnameFromLabel != "" {
+			if labelValue, ok := container.Labels[i.proxy.Config.HostnameFromLabel]; ok {
+				hostname = labelValue
+			}
+		}
+		hostname = i.proxy.hostnameMatchRegexp.ReplaceAllString(hostname, i.proxy.HostnameReplacement)
+		if err := i.setWeaveDNS(&container, hostname); err != nil {
+			return err
+		}
+
+		return marshalRequestBody(r, container)
+	}
+
+	return nil
+}
+
+func (i *createContainerInterceptor) addWeaveWaitVolume(hostConfig *docker.HostConfig) {
+	var binds []string
+	for _, bind := range hostConfig.Binds {
+		s := strings.Split(bind, ":")
+		if len(s) >= 2 && s[1] == "/w" {
+			continue
+		}
+		binds = append(binds, bind)
+	}
+	hostConfig.Binds = append(binds, fmt.Sprintf("%s:/w:ro", i.proxy.weaveWaitVolume))
+}
+
+func (i *createContainerInterceptor) setWeaveWaitEntrypoint(container *docker.Config) error {
+	if len(container.Entrypoint) == 0 {
+		image, err := i.proxy.client.InspectImage(container.Image)
+		if err == docker.ErrNoSuchImage {
+			return &ErrNoSuchImage{container.Image}
+		} else if err != nil {
+			return err
+		}
+
+		if len(container.Cmd) == 0 {
+			container.Cmd = image.Config.Cmd
+		}
+
+		if container.Entrypoint == nil {
+			container.Entrypoint = image.Config.Entrypoint
+		}
+	}
+
+	if len(container.Entrypoint) == 0 && len(container.Cmd) == 0 {
+		return ErrNoCommandSpecified
+	}
+
+	if len(container.Entrypoint) == 0 || container.Entrypoint[0] != weaveWaitEntrypoint[0] {
+		container.Entrypoint = append(weaveWaitEntrypoint, container.Entrypoint...)
+	}
+
+	return nil
+}
+
+func (i *createContainerInterceptor) setWeaveDNS(container *createContainerRequestBody, name string) error {
+	if i.proxy.WithoutDNS {
+		return nil
+	}
+
+	dnsDomain, dnsRunning := i.getDNSDomain()
+	if !(dnsRunning || i.proxy.WithDNS) {
+		return nil
+	}
+
+	container.HostConfig.DNS = append(container.HostConfig.DNS, i.proxy.dockerBridgeIP)
+
+	if container.Hostname == "" && name != "" {
+		// Strip trailing period because it's unusual to see it used on the end of a host name
+		trimmedDNSDomain := strings.TrimSuffix(dnsDomain, ".")
+		if len(name)+1+len(trimmedDNSDomain) > MaxDockerHostname {
+			Log.Warningf("Container name [%s] too long to be used as hostname", name)
+		} else {
+			container.Hostname = name
+			container.Domainname = trimmedDNSDomain
+		}
+	}
+
+	if len(container.HostConfig.DNSSearch) == 0 {
+		if container.Hostname == "" {
+			container.HostConfig.DNSSearch = []string{dnsDomain}
+		} else {
+			container.HostConfig.DNSSearch = []string{"."}
+		}
+	}
+
+	return nil
+}
+
+func (i *createContainerInterceptor) getDNSDomain() (domain string, running bool) {
+	domain = nameserver.DefaultDomain
+	weaveContainer, err := i.proxy.client.InspectContainer("weave")
+	if err != nil ||
+		weaveContainer.NetworkSettings == nil ||
+		weaveContainer.NetworkSettings.IPAddress == "" {
+		return
+	}
+
+	url := fmt.Sprintf("http://%s:%d/domain", weaveContainer.NetworkSettings.IPAddress, router.HTTPPort)
+	resp, err := http.Get(url)
+	if err != nil || resp.StatusCode != http.StatusOK {
+		return
+	}
+	defer resp.Body.Close()
+
+	b, err := ioutil.ReadAll(resp.Body)
+	if err != nil {
+		return
+	}
+
+	return string(b), true
+}
+
+func (i *createContainerInterceptor) InterceptResponse(r *http.Response) error {
+	return nil
+}

proxy/create_exec_interceptor.go

@@ -0,0 +1,42 @@
+package proxy
+
+import (
+	"net/http"
+	"strings"
+
+	"github.com/fsouza/go-dockerclient"
+	. "github.com/weaveworks/weave/common"
+)
+
+type createExecInterceptor struct{ proxy *Proxy }
+
+func (i *createExecInterceptor) InterceptRequest(r *http.Request) error {
+	options := docker.CreateExecOptions{}
+	if err := unmarshalRequestBody(r, &options); err != nil {
+		return err
+	}
+
+	container, err := inspectContainerInPath(i.proxy.client, r.URL.Path)
+	if err != nil {
+		return err
+	}
+
+	if _, hasWeaveWait := container.Volumes["/w"]; !hasWeaveWait {
+		return nil
+	}
+
+	cidrs, err := i.proxy.weaveCIDRsFromConfig(container.Config, container.HostConfig)
+	if err != nil {
+		Log.Infof("Leaving container %s alone because %s", container.ID, err)
+		return nil
+	}
+
+	Log.Infof("Exec in container %s with WEAVE_CIDR \"%s\"", container.ID, strings.Join(cidrs, " "))
+	options.Cmd = append(weaveWaitEntrypoint, options.Cmd...)
+
+	return marshalRequestBody(r, options)
+}
+
+func (i *createExecInterceptor) InterceptResponse(r *http.Response) error {
+	return nil
+}

proxy/inspect_container_interceptor.go

@@ -0,0 +1,51 @@
+package proxy
+
+import (
+	"net/http"
+
+	. "github.com/weaveworks/weave/common"
+)
+
+type inspectContainerInterceptor struct{ proxy *Proxy }
+
+func (i *inspectContainerInterceptor) InterceptRequest(r *http.Request) error {
+	return nil
+}
+
+func (i *inspectContainerInterceptor) InterceptResponse(r *http.Response) error {
+	if !i.proxy.RewriteInspect {
+		return nil
+	}
+
+	container := map[string]interface{}{}
+	if err := unmarshalResponseBody(r, &container); err != nil {
+		return err
+	}
+
+	if err := updateContainerNetworkSettings(container); err != nil {
+		Log.Warningf("Inspecting container %s failed: %s", container["Id"], err)
+	}
+
+	return marshalResponseBody(r, container)
+}
+
+func updateContainerNetworkSettings(container map[string]interface{}) error {
+	containerID, err := lookupString(container, "Id")
+	if err != nil {
+		return err
+	}
+
+	mac, ips, nets, err := weaveContainerIPs(containerID)
+	if err != nil || len(ips) == 0 {
+		return err
+	}
+
+	networkSettings, err := lookupObject(container, "NetworkSettings")
+	if err != nil {
+		return err
+	}
+	networkSettings["MacAddress"] = mac
+	networkSettings["IPAddress"] = ips[0].String()
+	networkSettings["IPPrefixLen"], _ = nets[0].Mask.Size()
+	return nil
+}

proxy/inspect_exec_interceptor.go

@@ -0,0 +1,35 @@
+package proxy
+
+import (
+	"net/http"
+
+	. "github.com/weaveworks/weave/common"
+)
+
+type inspectExecInterceptor struct{ proxy *Proxy }
+
+func (i *inspectExecInterceptor) InterceptRequest(r *http.Request) error {
+	return nil
+}
+
+func (i *inspectExecInterceptor) InterceptResponse(r *http.Response) error {
+	if !i.proxy.RewriteInspect {
+		return nil
+	}
+
+	exec := map[string]interface{}{}
+	if err := unmarshalResponseBody(r, &exec); err != nil {
+		return err
+	}
+
+	container, err := lookupObject(exec, "Container")
+	if err != nil {
+		return err
+	}
+
+	if err := updateContainerNetworkSettings(container); err != nil {
+		Log.Warningf("Inspecting exec %s failed: %s", exec["Id"], err)
+	}
+
+	return marshalResponseBody(r, exec)
+}

proxy/interceptor.go

@@ -0,0 +1,19 @@
+package proxy
+
+import "net/http"
+
+type interceptor interface {
+	InterceptRequest(*http.Request) error
+	InterceptResponse(*http.Response) error
+}
+
+type nullInterceptor struct {
+}
+
+func (i nullInterceptor) InterceptRequest(r *http.Request) error {
+	return nil
+}
+
+func (i nullInterceptor) InterceptResponse(r *http.Response) error {
+	return nil
+}

proxy/json.go

@@ -0,0 +1,46 @@
+package proxy
+
+import (
+	"fmt"
+)
+
+type UnmarshalWrongTypeError struct {
+	Field, Expected string
+	Got             interface{}
+}
+
+func (e *UnmarshalWrongTypeError) Error() string {
+	return fmt.Sprintf("Wrong type for %s field, expected %s, but got %T", e.Field, e.Expected, e.Got)
+}
+
+// For parsing json objects. Look up (or create) a child object in the given map.
+func lookupObject(m map[string]interface{}, key string) (map[string]interface{}, error) {
+	iface, ok := m[key]
+	if !ok || iface == nil {
+		result := map[string]interface{}{}
+		m[key] = result
+		return result, nil
+	}
+
+	result, ok := iface.(map[string]interface{})
+	if !ok {
+		return nil, &UnmarshalWrongTypeError{key, "object", iface}
+	}
+
+	return result, nil
+}
+
+// For parsing json objects. Look up (or create) a string in the given map.
+func lookupString(m map[string]interface{}, key string) (string, error) {
+	iface, ok := m[key]
+	if !ok || iface == nil {
+		return "", nil
+	}
+
+	result, ok := iface.(string)
+	if !ok {
+		return "", &UnmarshalWrongTypeError{key, "string", iface}
+	}
+
+	return result, nil
+}

proxy/proxy.go

@@ -0,0 +1,262 @@
+package proxy
+
+import (
+	"crypto/tls"
+	"errors"
+	"fmt"
+	"net"
+	"net/http"
+	"os"
+	"regexp"
+	"strings"
+	"syscall"
+
+	"github.com/fsouza/go-dockerclient"
+	. "github.com/weaveworks/weave/common"
+)
+
+const (
+	defaultCaFile   = "ca.pem"
+	defaultKeyFile  = "key.pem"
+	defaultCertFile = "cert.pem"
+	dockerSock      = "/var/run/docker.sock"
+	dockerSockUnix  = "unix://" + dockerSock
+)
+
+var (
+	containerCreateRegexp  = dockerAPIEndpoint("containers/create")
+	containerStartRegexp   = dockerAPIEndpoint("containers/[^/]*/(re)?start")
+	containerInspectRegexp = dockerAPIEndpoint("containers/[^/]*/json")
+	execCreateRegexp       = dockerAPIEndpoint("containers/[^/]*/exec")
+	execInspectRegexp      = dockerAPIEndpoint("exec/[^/]*/json")
+
+	ErrWeaveCIDRNone = errors.New("the container was created with the '-e WEAVE_CIDR=none' option")
+	ErrNoDefaultIPAM = errors.New("the container was created without specifying an IP address with '-e WEAVE_CIDR=...' and the proxy was started with the '--no-default-ipalloc' option")
+)
+
+func dockerAPIEndpoint(endpoint string) *regexp.Regexp {
+	return regexp.MustCompile("^(/v[0-9\\.]*)?/" + endpoint + "$")
+}
+
+type Config struct {
+	HostnameFromLabel   string
+	HostnameMatch       string
+	HostnameReplacement string
+	ListenAddrs         []string
+	RewriteInspect      bool
+	NoDefaultIPAM       bool
+	NoRewriteHosts      bool
+	TLSConfig           TLSConfig
+	Version             string
+	WithDNS             bool
+	WithoutDNS          bool
+}
+
+type Proxy struct {
+	Config
+	client              *docker.Client
+	dockerBridgeIP      string
+	hostnameMatchRegexp *regexp.Regexp
+	weaveWaitVolume     string
+}
+
+func NewProxy(c Config) (*Proxy, error) {
+	p := &Proxy{Config: c}
+
+	if err := p.TLSConfig.loadCerts(); err != nil {
+		Log.Fatalf("Could not configure tls for proxy: %s", err)
+	}
+
+	// We pin the protocol version to 1.15 (which corresponds to
+	// Docker 1.3.x; the earliest version supported by weave) in order
+	// to insulate ourselves from breaking changes to the API, as
+	// happened in 1.20 (Docker 1.8.0) when the presentation of
+	// volumes changed in `inspect`.
+	client, err := docker.NewVersionedClient(dockerSockUnix, "1.15")
+	if err != nil {
+		return nil, err
+	}
+	p.client = client
+
+	if !p.WithoutDNS {
+		dockerBridgeIP, stderr, err := callWeave("docker-bridge-ip")
+		if err != nil {
+			return nil, fmt.Errorf(string(stderr))
+		}
+		p.dockerBridgeIP = string(dockerBridgeIP)
+	}
+
+	p.hostnameMatchRegexp, err = regexp.Compile(c.HostnameMatch)
+	if err != nil {
+		err := fmt.Errorf("Incorrect hostname match '%s': %s", c.HostnameMatch, err.Error())
+		return nil, err
+	}
+
+	if err = p.findWeaveWaitVolume(); err != nil {
+		return nil, err
+	}
+
+	return p, nil
+}
+
+func (proxy *Proxy) Dial() (net.Conn, error) {
+	return net.Dial("unix", dockerSock)
+}
+
+func (proxy *Proxy) findWeaveWaitVolume() error {
+	container, err := proxy.client.InspectContainer("weaveproxy")
+	if err != nil {
+		return fmt.Errorf("Could not find the weavewait volume: %s", err)
+	}
+
+	if container.Volumes == nil {
+		return fmt.Errorf("Could not find the weavewait volume")
+	}
+
+	volume, ok := container.Volumes["/w"]
+	if !ok {
+		return fmt.Errorf("Could not find the weavewait volume")
+	}
+
+	proxy.weaveWaitVolume = volume
+	return nil
+}
+
+func (proxy *Proxy) ServeHTTP(w http.ResponseWriter, r *http.Request) {
+	Log.Infof("%s %s", r.Method, r.URL)
+	path := r.URL.Path
+	var i interceptor
+	switch {
+	case containerCreateRegexp.MatchString(path):
+		i = &createContainerInterceptor{proxy}
+	case containerStartRegexp.MatchString(path):
+		i = &startContainerInterceptor{proxy}
+	case containerInspectRegexp.MatchString(path):
+		i = &inspectContainerInterceptor{proxy}
+	case execCreateRegexp.MatchString(path):
+		i = &createExecInterceptor{proxy}
+	case execInspectRegexp.MatchString(path):
+		i = &inspectExecInterceptor{proxy}
+	default:
+		i = &nullInterceptor{}
+	}
+	proxy.Intercept(i, w, r)
+}
+
+func (proxy *Proxy) ListenAndServe() {
+	listeners := []net.Listener{}
+	addrs := []string{}
+	for _, addr := range proxy.ListenAddrs {
+		listener, normalisedAddr, err := proxy.listen(addr)
+		if err != nil {
+			Log.Fatalf("Cannot listen on %s: %s", addr, err)
+		}
+		listeners = append(listeners, listener)
+		addrs = append(addrs, normalisedAddr)
+	}
+
+	for _, addr := range addrs {
+		Log.Infoln("proxy listening on", addr)
+	}
+
+	errs := make(chan error)
+	for _, listener := range listeners {
+		go func(listener net.Listener) {
+			errs <- (&http.Server{Handler: proxy}).Serve(listener)
+		}(listener)
+	}
+	for range listeners {
+		err := <-errs
+		if err != nil {
+			Log.Fatalf("Serve failed: %s", err)
+		}
+	}
+}
+
+func copyOwnerAndPermissions(from, to string) error {
+	stat, err := os.Stat(from)
+	if err != nil {
+		return err
+	}
+	if err = os.Chmod(to, stat.Mode()); err != nil {
+		return err
+	}
+
+	moreStat, ok := stat.Sys().(*syscall.Stat_t)
+	if !ok {
+		return nil
+	}
+
+	if err = os.Chown(to, int(moreStat.Uid), int(moreStat.Gid)); err != nil {
+		return err
+	}
+
+	return nil
+}
+
+func (proxy *Proxy) listen(protoAndAddr string) (net.Listener, string, error) {
+	var (
+		listener    net.Listener
+		err         error
+		proto, addr string
+	)
+
+	if protoAddrParts := strings.SplitN(protoAndAddr, "://", 2); len(protoAddrParts) == 2 {
+		proto, addr = protoAddrParts[0], protoAddrParts[1]
+	} else if strings.HasPrefix(protoAndAddr, "/") {
+		proto, addr = "unix", protoAndAddr
+	} else {
+		proto, addr = "tcp", protoAndAddr
+	}
+
+	switch proto {
+	case "tcp":
+		listener, err = net.Listen(proto, addr)
+		if err != nil {
+			return nil, "", err
+		}
+		if proxy.TLSConfig.enabled() {
+			listener = tls.NewListener(listener, proxy.TLSConfig.Config)
+		}
+
+	case "unix":
+		// remove socket from last invocation
+		if err := os.Remove(addr); err != nil && !os.IsNotExist(err) {
+			return nil, "", err
+		}
+		listener, err = net.Listen(proto, addr)
+		if err != nil {
+			return nil, "", err
+		}
+		if err = copyOwnerAndPermissions(dockerSock, addr); err != nil {
+			return nil, "", err
+		}
+
+	default:
+		Log.Fatalf("Invalid protocol format: %q", proto)
+	}
+
+	return listener, fmt.Sprintf("%s://%s", proto, addr), nil
+}
+
+func (proxy *Proxy) weaveCIDRsFromConfig(config *docker.Config, hostConfig *docker.HostConfig) ([]string, error) {
+	netMode := ""
+	if hostConfig != nil {
+		netMode = hostConfig.NetworkMode
+	}
+	if netMode == "host" || strings.HasPrefix(netMode, "container:") {
+		return nil, fmt.Errorf("the container was created with the '--net=%s'", netMode)
+	}
+	for _, e := range config.Env {
+		if strings.HasPrefix(e, "WEAVE_CIDR=") {
+			if e[11:] == "none" {
+				return nil, ErrWeaveCIDRNone
+			}
+			return strings.Fields(e[11:]), nil
+		}
+	}
+	if proxy.NoDefaultIPAM {
+		return nil, ErrNoDefaultIPAM
+	}
+	return nil, nil
+}

proxy/proxy_intercept.go

@@ -0,0 +1,167 @@
+package proxy
+
+import (
+	"bufio"
+	"errors"
+	"fmt"
+	"io"
+	"net"
+	"net/http"
+	"net/http/httputil"
+	"sync"
+
+	"github.com/fsouza/go-dockerclient"
+	. "github.com/weaveworks/weave/common"
+)
+
+func (proxy *Proxy) Intercept(i interceptor, w http.ResponseWriter, r *http.Request) {
+	if err := i.InterceptRequest(r); err != nil {
+		switch err.(type) {
+		case *docker.NoSuchContainer:
+			http.Error(w, err.Error(), http.StatusNotFound)
+		case *ErrNoSuchImage:
+			http.Error(w, err.Error(), http.StatusNotFound)
+		default:
+			http.Error(w, err.Error(), http.StatusInternalServerError)
+			Log.Warning("Error intercepting request: ", err)
+		}
+		return
+	}
+
+	conn, err := proxy.Dial()
+	if err != nil {
+		http.Error(w, "Could not connect to target", http.StatusInternalServerError)
+		Log.Warning(err)
+		return
+	}
+	client := httputil.NewClientConn(conn, nil)
+	defer client.Close()
+
+	resp, err := client.Do(r)
+	if err != nil && err != httputil.ErrPersistEOF {
+		http.Error(w, fmt.Sprintf("Could not make request to target: %v", err), http.StatusInternalServerError)
+		Log.Warning("Error forwarding request: ", err)
+		return
+	}
+	err = i.InterceptResponse(resp)
+	if err != nil {
+		http.Error(w, err.Error(), http.StatusInternalServerError)
+		Log.Warning("Error intercepting response: ", err)
+		return
+	}
+
+	hdr := w.Header()
+	for k, vs := range resp.Header {
+		for _, v := range vs {
+			hdr.Add(k, v)
+		}
+	}
+	Log.Debugf("Response from target: %s %v", resp.Status, w.Header())
+
+	if resp.Header.Get("Content-Type") == "application/vnd.docker.raw-stream" {
+		doRawStream(w, resp, client)
+	} else if resp.TransferEncoding != nil && resp.TransferEncoding[0] == "chunked" {
+		doChunkedResponse(w, resp, client)
+	} else {
+		w.WriteHeader(resp.StatusCode)
+		if _, err := io.Copy(w, resp.Body); err != nil {
+			Log.Warning(err)
+		}
+	}
+}
+
+func doRawStream(w http.ResponseWriter, resp *http.Response, client *httputil.ClientConn) {
+	down, downBuf, up, remaining, err := hijack(w, client)
+	if err != nil {
+		http.Error(w, "Unable to hijack connection for raw stream mode", http.StatusInternalServerError)
+		return
+	}
+	defer down.Close()
+	defer up.Close()
+
+	if _, err := down.Write([]byte("HTTP/1.1 200 OK\n")); err != nil {
+		Log.Warning(err)
+		return
+	}
+
+	if err := resp.Header.Write(down); err != nil {
+		Log.Warning(err)
+		return
+	}
+
+	if _, err := down.Write([]byte("\n")); err != nil {
+		Log.Warning(err)
+		return
+	}
+
+	var wg sync.WaitGroup
+	wg.Add(2)
+	go copyStream(down, io.MultiReader(remaining, up), &wg)
+	go copyStream(up, downBuf, &wg)
+	wg.Wait()
+}
+
+type closeWriter interface {
+	CloseWrite() error
+}
+
+func copyStream(dst io.WriteCloser, src io.Reader, wg *sync.WaitGroup) {
+	defer wg.Done()
+	if _, err := io.Copy(dst, src); err != nil {
+		Log.Warning(err)
+	}
+	var err error
+	if c, ok := dst.(closeWriter); ok {
+		err = c.CloseWrite()
+	} else {
+		err = dst.Close()
+	}
+	if err != nil {
+		Log.Warningf("Error closing connection: %s", err)
+	}
+}
+
+type writeFlusher interface {
+	io.Writer
+	http.Flusher
+}
+
+func doChunkedResponse(w http.ResponseWriter, resp *http.Response, client *httputil.ClientConn) {
+	wf, ok := w.(writeFlusher)
+	if !ok {
+		http.Error(w, "Error forwarding chunked response body: flush not available", http.StatusInternalServerError)
+		return
+	}
+
+	w.WriteHeader(resp.StatusCode)
+
+	up, remaining := client.Hijack()
+	defer up.Close()
+
+	var err error
+	chunks := NewChunkedReader(io.MultiReader(remaining, up))
+	for chunks.Next() && err == nil {
+		_, err = io.Copy(wf, chunks.Chunk())
+		wf.Flush()
+	}
+	if err == nil {
+		err = chunks.Err()
+	}
+	if err != nil {
+		Log.Errorf("Error forwarding chunked response body: %s", err)
+	}
+}
+
+func hijack(w http.ResponseWriter, client *httputil.ClientConn) (down net.Conn, downBuf *bufio.ReadWriter, up net.Conn, remaining io.Reader, err error) {
+	hj, ok := w.(http.Hijacker)
+	if !ok {
+		err = errors.New("Unable to cast to Hijack")
+		return
+	}
+	down, downBuf, err = hj.Hijack()
+	if err != nil {
+		return
+	}
+	up, remaining = client.Hijack()
+	return
+}

proxy/start_container_interceptor.go

@@ -0,0 +1,47 @@
+package proxy
+
+import (
+	"errors"
+	"net/http"
+	"strings"
+
+	. "github.com/weaveworks/weave/common"
+)
+
+type startContainerInterceptor struct{ proxy *Proxy }
+
+func (i *startContainerInterceptor) InterceptRequest(r *http.Request) error {
+	return nil
+}
+
+func (i *startContainerInterceptor) InterceptResponse(r *http.Response) error {
+	if r.StatusCode < 200 || r.StatusCode >= 300 { // Docker didn't do the start
+		return nil
+	}
+
+	container, err := inspectContainerInPath(i.proxy.client, r.Request.URL.Path)
+	if err != nil {
+		return err
+	}
+
+	cidrs, err := i.proxy.weaveCIDRsFromConfig(container.Config, container.HostConfig)
+	if err != nil {
+		Log.Infof("Leaving container %s alone because %s", container.ID, err)
+		return nil
+	}
+	Log.Infof("Attaching container %s with WEAVE_CIDR \"%s\" to weave network", container.ID, strings.Join(cidrs, " "))
+	args := []string{"attach"}
+	args = append(args, cidrs...)
+	if !i.proxy.NoRewriteHosts {
+		args = append(args, "--rewrite-hosts")
+	}
+	args = append(args, "--or-die", container.ID)
+	if _, stderr, err := callWeave(args...); err != nil {
+		Log.Warningf("Attaching container %s to weave network failed: %s", container.ID, string(stderr))
+		return errors.New(string(stderr))
+	} else if len(stderr) > 0 {
+		Log.Warningf("Attaching container %s to weave network: %s", container.ID, string(stderr))
+	}
+
+	return nil
+}

proxy/tls.go

@@ -0,0 +1,76 @@
+package proxy
+
+import (
+	"crypto/tls"
+	"crypto/x509"
+	"fmt"
+	"io/ioutil"
+	"os"
+	"path/filepath"
+
+	"github.com/docker/docker/pkg/homedir"
+)
+
+type TLSConfig struct {
+	Enabled, Verify   bool
+	Cert, Key, CACert string
+	*tls.Config
+}
+
+func (c *TLSConfig) enabled() bool {
+	if c == nil {
+		return false
+	}
+	return c.Enabled || c.Verify
+}
+
+func (c *TLSConfig) loadCerts() error {
+	if !c.enabled() {
+		return nil
+	}
+
+	dockerCertPath := os.Getenv("DOCKER_CERT_PATH")
+	if dockerCertPath == "" {
+		dockerCertPath = filepath.Join(homedir.Get(), ".docker")
+	}
+
+	if c.CACert == "" {
+		c.CACert = filepath.Join(dockerCertPath, defaultCaFile)
+	}
+	if c.Cert == "" {
+		c.Cert = filepath.Join(dockerCertPath, defaultCertFile)
+	}
+	if c.Key == "" {
+		c.Key = filepath.Join(dockerCertPath, defaultKeyFile)
+	}
+
+	tlsConfig := &tls.Config{
+		NextProtos: []string{"http/1.1"},
+		// Avoid fallback on insecure SSL protocols
+		MinVersion: tls.VersionTLS10,
+	}
+
+	if c.Verify {
+		certPool := x509.NewCertPool()
+		file, err := ioutil.ReadFile(c.CACert)
+		if err != nil {
+			return fmt.Errorf("Couldn't read CA certificate: %v", err)
+		}
+		certPool.AppendCertsFromPEM(file)
+		tlsConfig.ClientAuth = tls.RequireAndVerifyClientCert
+		tlsConfig.ClientCAs = certPool
+	}
+
+	_, errCert := os.Stat(c.Cert)
+	_, errKey := os.Stat(c.Key)
+	if errCert == nil && errKey == nil {
+		cert, err := tls.LoadX509KeyPair(c.Cert, c.Key)
+		if err != nil {
+			return fmt.Errorf("Couldn't load X509 key pair: %q. Make sure the key is encrypted", err)
+		}
+		tlsConfig.Certificates = []tls.Certificate{cert}
+	}
+
+	c.Config = tlsConfig
+	return nil
+}

router/connection.go

@@ -2,10 +2,8 @@ package router
 
 import (
 	"encoding/binary"
-	"encoding/gob"
-	"encoding/hex"
+	"errors"
 	"fmt"
-	"log"
 	"net"
 	"strconv"
 	"sync"
@@ -15,10 +13,12 @@ import (
 type Connection interface {
 	Local() *Peer
 	Remote() *Peer
-	BreakTie(Connection) ConnectionTieBreak
 	RemoteTCPAddr() string
+	Outbound() bool
 	Established() bool
+	BreakTie(Connection) ConnectionTieBreak
 	Shutdown(error)
+	Log(args ...interface{})
 }
 
 type ConnectionTieBreak int
@@ -29,105 +29,88 @@ const (
 	TieBreakTied
 )
 
+var ErrConnectToSelf = errors.New("Cannot connect to ourself")
+
 type RemoteConnection struct {
 	local         *Peer
 	remote        *Peer
 	remoteTCPAddr string
+	outbound      bool
 	established   bool
 }
 
 type LocalConnection struct {
 	sync.RWMutex
 	RemoteConnection
-	TCPConn            *net.TCPConn
-	tcpSender          TCPSender
-	remoteUDPAddr      *net.UDPAddr
-	receivedHeartbeat  bool
-	stackFrag          bool
-	effectivePMTU      int
-	SessionKey         *[32]byte
-	establishedTimeout *time.Timer
-	heartbeatFrame     *ForwardedFrame
-	heartbeat          *time.Ticker
-	fragTest           *time.Ticker
-	forwardChan        chan<- *ForwardedFrame
-	forwardChanDF      chan<- *ForwardedFrame
-	stopForward        chan<- interface{}
-	stopForwardDF      chan<- interface{}
-	verifyPMTU         chan<- int
-	Decryptor          Decryptor
-	Router             *Router
-	uid                uint64
-	queryChan          chan<- *ConnectionInteraction
+	TCPConn           *net.TCPConn
+	version           byte
+	tcpSender         TCPSender
+	remoteUDPAddr     *net.UDPAddr
+	receivedHeartbeat bool
+	stackFrag         bool
+	effectivePMTU     int
+	SessionKey        *[32]byte
+	heartbeatTCP      *time.Ticker
+	heartbeatTimeout  *time.Timer
+	heartbeatFrame    []byte
+	heartbeat         *time.Ticker
+	fragTest          *time.Ticker
+	forwarder         *Forwarder
+	forwarderDF       *ForwarderDF
+	Decryptor         Decryptor
+	Router            *Router
+	uid               uint64
+	actionChan        chan<- ConnectionAction
+	finished          <-chan struct{} // closed to signal that actorLoop has finished
 }
 
-type ConnectionInteraction struct {
-	Interaction
-	payload interface{}
-}
+type ConnectionAction func() error
 
-func NewRemoteConnection(from, to *Peer, tcpAddr string, established bool) *RemoteConnection {
+func NewRemoteConnection(from, to *Peer, tcpAddr string, outbound bool, established bool) *RemoteConnection {
 	return &RemoteConnection{
 		local:         from,
 		remote:        to,
 		remoteTCPAddr: tcpAddr,
-		established:   established}
-}
-
-func (conn *RemoteConnection) Local() *Peer {
-	return conn.local
-}
-
-func (conn *RemoteConnection) Remote() *Peer {
-	return conn.remote
-}
-
-func (conn *RemoteConnection) BreakTie(Connection) ConnectionTieBreak {
-	return TieBreakTied
-}
-
-func (conn *RemoteConnection) RemoteTCPAddr() string {
-	return conn.remoteTCPAddr
-}
-
-func (conn *RemoteConnection) Established() bool {
-	return conn.established
-}
-
-func (conn *RemoteConnection) Shutdown(error) {
-}
-
-func (conn *RemoteConnection) String() string {
-	from := "<nil>"
-	if conn.local != nil {
-		from = conn.local.Name.String()
+		outbound:      outbound,
+		established:   established,
 	}
-	to := "<nil>"
-	if conn.remote != nil {
-		to = conn.remote.Name.String()
-	}
-	return fmt.Sprint("Connection ", from, "->", to)
 }
 
-func NewLocalConnection(connRemote *RemoteConnection, tcpConn *net.TCPConn, udpAddr *net.UDPAddr, router *Router) *LocalConnection {
+func (conn *RemoteConnection) Local() *Peer                           { return conn.local }
+func (conn *RemoteConnection) Remote() *Peer                          { return conn.remote }
+func (conn *RemoteConnection) RemoteTCPAddr() string                  { return conn.remoteTCPAddr }
+func (conn *RemoteConnection) Outbound() bool                         { return conn.outbound }
+func (conn *RemoteConnection) Established() bool                      { return conn.established }
+func (conn *RemoteConnection) BreakTie(Connection) ConnectionTieBreak { return TieBreakTied }
+func (conn *RemoteConnection) Shutdown(error)                         {}
+
+func (conn *RemoteConnection) Log(args ...interface{}) {
+	log.Println(append(append([]interface{}{}, fmt.Sprintf("->[%s|%s]:", conn.remoteTCPAddr, conn.remote)), args...)...)
+}
+
+func (conn *RemoteConnection) ErrorLog(args ...interface{}) {
+	log.Errorln(append(append([]interface{}{}, fmt.Sprintf("->[%s|%s]:", conn.remoteTCPAddr, conn.remote)), args...)...)
+}
+
+// Does not return anything. If the connection is successful, it will
+// end up in the local peer's connections map.
+func StartLocalConnection(connRemote *RemoteConnection, tcpConn *net.TCPConn, udpAddr *net.UDPAddr, router *Router, acceptNewPeer bool) {
 	if connRemote.local != router.Ourself.Peer {
 		log.Fatal("Attempt to create local connection from a peer which is not ourself")
 	}
 	// NB, we're taking a copy of connRemote here.
-	return &LocalConnection{
+	actionChan := make(chan ConnectionAction, ChannelSize)
+	finished := make(chan struct{})
+	conn := &LocalConnection{
 		RemoteConnection: *connRemote,
 		Router:           router,
 		TCPConn:          tcpConn,
 		remoteUDPAddr:    udpAddr,
-		effectivePMTU:    DefaultPMTU}
-}
-
-// Async. Does not return anything. If the connection is successful,
-// it will end up in the local peer's connections map.
-func (conn *LocalConnection) Start(acceptNewPeer bool) {
-	queryChan := make(chan *ConnectionInteraction, ChannelSize)
-	conn.queryChan = queryChan
-	go conn.run(queryChan, acceptNewPeer)
+		effectivePMTU:    DefaultPMTU,
+		uid:              randUint64(),
+		actionChan:       actionChan,
+		finished:         finished}
+	go conn.run(actionChan, finished, acceptNewPeer)
 }
 
 func (conn *LocalConnection) BreakTie(dupConn Connection) ConnectionTieBreak {
@@ -163,37 +146,55 @@ func (conn *LocalConnection) setEffectivePMTU(pmtu int) {
 	defer conn.Unlock()
 	if conn.effectivePMTU != pmtu {
 		conn.effectivePMTU = pmtu
-		conn.log("Effective PMTU set to", pmtu)
+		conn.Log("Effective PMTU set to", pmtu)
 	}
 }
 
 // Called by the connection's actor process, and by the connection's
-// TCP received process. StackFrag is read in conn.Forward (called by
-// router udp listener and sniffer processes)
+// TCP receiver process. StackFrag is read in conn.forward
 func (conn *LocalConnection) setStackFrag(frag bool) {
 	conn.Lock()
 	defer conn.Unlock()
 	conn.stackFrag = frag
 }
 
-func (conn *LocalConnection) log(args ...interface{}) {
-	log.Println(append(append([]interface{}{}, fmt.Sprintf("->[%s]:", conn.remote.Name)), args...)...)
+// Called by the connection's TCP receiver process.
+func (conn *LocalConnection) pmtuVerified(pmtu int) {
+	conn.RLock()
+	fwd := conn.forwarderDF
+	conn.RUnlock()
+	if fwd != nil {
+		fwd.PMTUVerified(pmtu)
+	}
 }
 
-// ACTOR client API
+// Send directly, not via the Actor.  If it goes via the Actor we can
+// get a deadlock where LocalConnection is blocked talking to
+// LocalPeer and LocalPeer is blocked trying send a ProtocolMsg via
+// LocalConnection, and the channels are full in both directions so
+// nothing can proceed.
+func (conn *LocalConnection) SendProtocolMsg(m ProtocolMsg) {
+	if err := conn.sendProtocolMsg(m); err != nil {
+		conn.Shutdown(err)
+	}
+}
 
-const (
-	CSendProtocolMsg = iota
-	CSetEstablished
-	CReceivedHeartbeat
-	CShutdown
-)
+// ACTOR methods
+
+// NB: The conn.* fields are only written by the connection actor
+// process, which is the caller of the ConnectionAction funs. Hence we
+// do not need locks for reading, and only need write locks for fields
+// read by other processes.
 
 // Async
 func (conn *LocalConnection) Shutdown(err error) {
-	conn.queryChan <- &ConnectionInteraction{
-		Interaction: Interaction{code: CShutdown},
-		payload:     err}
+	// err should always be a real error, even if only io.EOF
+	if err == nil {
+		panic("nil error")
+	}
+
+	// Run on its own goroutine in case the channel is backed up
+	go func() { conn.sendAction(func() error { return err }) }()
 }
 
 // Async
@@ -205,198 +206,296 @@ func (conn *LocalConnection) ReceivedHeartbeat(remoteUDPAddr *net.UDPAddr, connU
 	if remoteUDPAddr == nil || connUID != conn.uid {
 		return
 	}
-	conn.queryChan <- &ConnectionInteraction{
-		Interaction: Interaction{code: CReceivedHeartbeat},
-		payload:     remoteUDPAddr}
+	conn.sendAction(func() error {
+		oldRemoteUDPAddr := conn.remoteUDPAddr
+		old := conn.receivedHeartbeat
+		conn.Lock()
+		conn.remoteUDPAddr = remoteUDPAddr
+		conn.receivedHeartbeat = true
+		conn.Unlock()
+		conn.heartbeatTimeout.Reset(HeartbeatTimeout)
+		if !old {
+			if err := conn.sendSimpleProtocolMsg(ProtocolConnectionEstablished); err != nil {
+				return err
+			}
+		}
+		if oldRemoteUDPAddr == nil {
+			return conn.sendFastHeartbeats()
+		} else if oldRemoteUDPAddr.String() != remoteUDPAddr.String() {
+			log.Println("Peer", conn.remote, "moved from", oldRemoteUDPAddr, "to", remoteUDPAddr)
+		}
+		return nil
+	})
 }
 
 // Async
 func (conn *LocalConnection) SetEstablished() {
-	conn.queryChan <- &ConnectionInteraction{Interaction: Interaction{code: CSetEstablished}}
+	conn.sendAction(func() error {
+		stopTicker(conn.heartbeat)
+		old := conn.established
+		conn.Lock()
+		conn.established = true
+		conn.Unlock()
+		if old {
+			return nil
+		}
+		conn.Router.Ourself.ConnectionEstablished(conn)
+		if err := conn.ensureForwarders(); err != nil {
+			return err
+		}
+		// Send a large frame down the DF channel in order to prompt
+		// PMTU discovery to start.
+		conn.Send(true, PMTUDiscovery)
+		conn.heartbeat = time.NewTicker(SlowHeartbeat)
+		conn.fragTest = time.NewTicker(FragTestInterval)
+		// avoid initial waits for timers to fire
+		conn.Send(true, conn.heartbeatFrame)
+		conn.performFragTest()
+		return nil
+	})
 }
 
-// Async
-func (conn *LocalConnection) SendProtocolMsg(m ProtocolMsg) {
-	conn.queryChan <- &ConnectionInteraction{
-		Interaction: Interaction{code: CSendProtocolMsg},
-		payload:     m}
+// Send an actor request to the actorLoop, but don't block if
+// actorLoop has exited - see http://blog.golang.org/pipelines for
+// pattern
+func (conn *LocalConnection) sendAction(action ConnectionAction) {
+	select {
+	case conn.actionChan <- action:
+	case <-conn.finished:
+	}
 }
 
 // ACTOR server
 
-func (conn *LocalConnection) run(queryChan <-chan *ConnectionInteraction, acceptNewPeer bool) {
-	defer conn.handleShutdown()
+func (conn *LocalConnection) run(actionChan <-chan ConnectionAction, finished chan<- struct{}, acceptNewPeer bool) {
+	var err error // important to use this var and not create another one with 'err :='
+	defer func() { conn.shutdown(err) }()
+	defer close(finished)
 
-	tcpConn := conn.TCPConn
-	tcpConn.SetLinger(0)
-	enc := gob.NewEncoder(tcpConn)
-	dec := gob.NewDecoder(tcpConn)
-
-	if err := conn.handshake(enc, dec, acceptNewPeer); err != nil {
-		log.Printf("->[%s] connection shutting down due to error during handshake: %v\n", conn.remoteTCPAddr, err)
+	conn.TCPConn.SetLinger(0)
+	intro, err := ProtocolIntroParams{
+		MinVersion: conn.Router.ProtocolMinVersion,
+		MaxVersion: ProtocolMaxVersion,
+		Features:   conn.makeFeatures(),
+		Conn:       conn.TCPConn,
+		Password:   conn.Router.Password,
+		Outbound:   conn.outbound,
+	}.DoIntro()
+	if err != nil {
 		return
 	}
-	log.Printf("->[%s] completed handshake with %s\n", conn.remoteTCPAddr, conn.remote.Name)
 
-	// We invoke AddConnection in the same goroutine that subsequently
-	// becomes the tcp receive loop, rather than outside, because a)
-	// the ordering relative to the receive loop is the only one that
-	// matters [1], b) it prevents unnecessary delays in entering the
-	// main connection loop, and c) it guards against potential
-	// deadlocks.
-	go func() {
-		conn.Router.Ourself.AddConnection(conn)
-		conn.receiveTCP(dec)
-	}()
+	conn.SessionKey = intro.SessionKey
+	conn.tcpSender = intro.Sender
+	conn.version = intro.Version
 
-	heartbeatFrameBytes := make([]byte, EthernetOverhead+8)
-	binary.BigEndian.PutUint64(heartbeatFrameBytes[EthernetOverhead:], conn.uid)
-	conn.heartbeatFrame = &ForwardedFrame{
-		srcPeer: conn.local,
-		dstPeer: conn.remote,
-		frame:   heartbeatFrameBytes}
+	remote, err := conn.parseFeatures(intro.Features)
+	if err != nil {
+		return
+	}
+
+	if err = conn.registerRemote(remote, acceptNewPeer); err != nil {
+		return
+	}
+
+	if conn.SessionKey == nil {
+		conn.Decryptor = NewNonDecryptor()
+	} else {
+		conn.Decryptor = NewNaClDecryptor(conn.SessionKey, conn.outbound)
+	}
+
+	conn.Log("connection ready; using protocol version", conn.version)
+
+	// The ordering of the following is very important. [1]
 
 	if conn.remoteUDPAddr != nil {
-		if err := conn.sendFastHeartbeats(); err != nil {
-			conn.log("connection shutting down due to error:", err)
+		if err = conn.ensureForwarders(); err != nil {
 			return
 		}
 	}
+	if err = conn.Router.Ourself.AddConnection(conn); err != nil {
+		return
+	}
+	if err = conn.initHeartbeats(); err != nil {
+		return
+	}
 
-	conn.establishedTimeout = time.NewTimer(EstablishedTimeout)
+	go conn.receiveTCP(intro.Receiver)
+	err = conn.actorLoop(actionChan)
+}
 
-	if err := conn.queryLoop(queryChan); err != nil {
-		conn.log("connection shutting down due to error:", err)
-	} else {
-		conn.log("connection shutting down")
+// [1] Ordering constraints:
+//
+// (a) AddConnections must precede initHeartbeats. It is only after
+// the former completes that we know the connection is valid, in
+// particular is not a duplicate connection to the same peer. Sending
+// heartbeats on a duplicate connection can trip up crypto at the
+// other end, since the associated UDP packets may get decoded by the
+// other connection. It is also generally wasteful to engage in any
+// interaction with the remote on a connection that turns out to be
+// invald.
+//
+// (b) AddConnection must precede receiveTCP. In the absence of any
+// indirect connectivity to the remote peer, the first we hear about
+// it (and any peers reachable from it) is through topology gossip it
+// sends us on the connection. We must ensure that the connection has
+// been added to Ourself prior to processing any such gossip,
+// otherwise we risk immediately gc'ing part of that newly received
+// portion of the topology (though not the remote peer itself, since
+// that will have a positive ref count), leaving behind dangling
+// references to peers. Hence we must invoke AddConnection, which is
+// *synchronous*, first.
+//
+// (c) AddConnection must precede actorLoop. More precisely, it must
+// precede shutdown, since that invokes DeleteConnection and is
+// invoked on termination of this entire function. Essentially this
+// boils down to a prohibition on running AddConnection in a separate
+// goroutine, at least not without some synchronisation. Which in turn
+// requires us the launching of the receiveTCP goroutine to precede
+// actorLoop.
+//
+// (d) AddConnection should precede receiveTCP. There is no point
+// starting the latter if the former fails.
+//
+// (e) initHeartbeats should precede actorLoop. The former is setting
+// LocalConnection fields accessed by the latter. Since the latter
+// runs in a separate goroutine, we'd have to add some synchronisation
+// if initHeartbeats isn't run first.
+//
+// (f) ensureForwarders should precede AddConnection. As soon as a
+// connection has been added to LocalPeer by the latter, it becomes
+// visible to the packet routing logic, which will end up dropping
+// packets if the forwarders haven't been created yet. We cannot
+// prevent that completely, since, for example, forwarder can only be
+// created when we know the remote UDP address, but it helps to try.
+
+func (conn *LocalConnection) makeFeatures() map[string]string {
+	return map[string]string{
+		"PeerNameFlavour": PeerNameFlavour,
+		"Name":            conn.local.Name.String(),
+		"NickName":        conn.local.NickName,
+		"UID":             fmt.Sprint(conn.local.UID),
+		"ConnID":          fmt.Sprint(conn.uid),
 	}
 }
 
-// [1] In the absence of any indirect connectivity to the remote peer,
-// the first we hear about it (and any peers reachable from it) is
-// through topology gossip it sends us on the connection. We must
-// ensure that the connection has been added to Ourself prior to
-// processing any such gossip, otherwise we risk immediately gc'ing
-// part of that newly received portion of the topology (though not the
-// remote peer itself, since that will have a positive ref count),
-// leaving behind dangling references to peers. Therefore we invoke
-// AddConnection, which is *synchronous*, before entering the tcp
-// receive loop.
+type features map[string]string
 
-func (conn *LocalConnection) queryLoop(queryChan <-chan *ConnectionInteraction) (err error) {
-	terminate := false
-	for !terminate && err == nil {
+func (features features) MustHave(keys []string) error {
+	for _, key := range keys {
+		if _, ok := features[key]; !ok {
+			return fmt.Errorf("Field %s is missing", key)
+		}
+	}
+	return nil
+}
+
+func (features features) Get(key string) string {
+	return features[key]
+}
+
+func (conn *LocalConnection) parseFeatures(features features) (*Peer, error) {
+	if err := features.MustHave([]string{"PeerNameFlavour", "Name", "NickName", "UID", "ConnID"}); err != nil {
+		return nil, err
+	}
+
+	remotePeerNameFlavour := features.Get("PeerNameFlavour")
+	if remotePeerNameFlavour != PeerNameFlavour {
+		return nil, fmt.Errorf("Peer name flavour mismatch (ours: '%s', theirs: '%s')", PeerNameFlavour, remotePeerNameFlavour)
+	}
+
+	name, err := PeerNameFromString(features.Get("Name"))
+	if err != nil {
+		return nil, err
+	}
+
+	nickName := features.Get("NickName")
+
+	uid, err := ParsePeerUID(features.Get("UID"))
+	if err != nil {
+		return nil, err
+	}
+
+	remoteConnID, err := strconv.ParseUint(features.Get("ConnID"), 10, 64)
+	if err != nil {
+		return nil, err
+	}
+
+	conn.uid ^= remoteConnID
+	return NewPeer(name, nickName, uid, 0), nil
+}
+
+func (conn *LocalConnection) registerRemote(remote *Peer, acceptNewPeer bool) error {
+	if acceptNewPeer {
+		conn.remote = conn.Router.Peers.FetchWithDefault(remote)
+	} else {
+		conn.remote = conn.Router.Peers.FetchAndAddRef(remote.Name)
+		if conn.remote == nil {
+			return fmt.Errorf("Found unknown remote name: %s at %s", remote.Name, conn.remoteTCPAddr)
+		}
+	}
+
+	if conn.remote.UID != remote.UID {
+		return fmt.Errorf("Connection appears to be with different version of a peer we already know of")
+	}
+
+	if conn.remote == conn.local {
+		return ErrConnectToSelf
+	}
+
+	return nil
+}
+
+func (conn *LocalConnection) initHeartbeats() error {
+	conn.heartbeatTCP = time.NewTicker(TCPHeartbeat)
+	conn.heartbeatTimeout = time.NewTimer(HeartbeatTimeout)
+	conn.heartbeatFrame = make([]byte, EthernetOverhead+8)
+	binary.BigEndian.PutUint64(conn.heartbeatFrame[EthernetOverhead:], conn.uid)
+	if conn.remoteUDPAddr == nil {
+		return nil
+	}
+	return conn.sendFastHeartbeats()
+}
+
+func (conn *LocalConnection) actorLoop(actionChan <-chan ConnectionAction) (err error) {
+	for err == nil {
 		select {
-		case query, ok := <-queryChan:
-			if !ok {
-				break
-			}
-			switch query.code {
-			case CShutdown:
-				err = query.payload.(error)
-				terminate = true
-			case CReceivedHeartbeat:
-				err = conn.handleReceivedHeartbeat(query.payload.(*net.UDPAddr))
-			case CSetEstablished:
-				conn.establishedTimeout.Stop()
-				err = conn.handleSetEstablished()
-			case CSendProtocolMsg:
-				err = conn.handleSendProtocolMsg(query.payload.(ProtocolMsg))
-			}
-		case <-conn.establishedTimeout.C:
-			if !conn.established {
-				err = fmt.Errorf("failed to establish UDP connectivity")
-			}
+		case action := <-actionChan:
+			err = action()
+		case <-conn.heartbeatTCP.C:
+			err = conn.sendSimpleProtocolMsg(ProtocolHeartbeat)
+		case <-conn.heartbeatTimeout.C:
+			err = fmt.Errorf("timed out waiting for UDP heartbeat")
 		case <-tickerChan(conn.heartbeat):
-			conn.Forward(true, conn.heartbeatFrame, nil)
+			conn.Send(true, conn.heartbeatFrame)
 		case <-tickerChan(conn.fragTest):
-			conn.setStackFrag(false)
-			err = conn.handleSendSimpleProtocolMsg(ProtocolStartFragmentationTest)
+			conn.performFragTest()
 		}
 	}
 	return
 }
 
-// Handlers
-//
-// NB: The conn.* fields are only written by the connection actor
-// process, which is the caller of the handlers. Hence we do not need
-// locks for reading, and only need write locks for fields read by
-// other processes.
-
-func (conn *LocalConnection) handleReceivedHeartbeat(remoteUDPAddr *net.UDPAddr) error {
-	oldRemoteUDPAddr := conn.remoteUDPAddr
-	old := conn.receivedHeartbeat
-	conn.Lock()
-	conn.remoteUDPAddr = remoteUDPAddr
-	conn.receivedHeartbeat = true
-	conn.Unlock()
-	if !old {
-		if err := conn.handleSendSimpleProtocolMsg(ProtocolConnectionEstablished); err != nil {
-			return err
-		}
+func (conn *LocalConnection) shutdown(err error) {
+	if conn.remote == nil {
+		log.Errorf("->[%s] connection shutting down due to error during handshake: %v", conn.remoteTCPAddr, err)
+	} else {
+		conn.ErrorLog("connection shutting down due to error:", err)
 	}
-	if oldRemoteUDPAddr == nil {
-		return conn.sendFastHeartbeats()
-	} else if oldRemoteUDPAddr.String() != remoteUDPAddr.String() {
-		log.Println("Peer", conn.remote.Name, "moved from", old, "to", remoteUDPAddr)
-	}
-	return nil
-}
 
-func (conn *LocalConnection) handleSetEstablished() error {
-	stopTicker(conn.heartbeat)
-	old := conn.established
-	conn.Lock()
-	conn.established = true
-	conn.Unlock()
-	if old {
-		return nil
-	}
-	conn.Router.Ourself.ConnectionEstablished(conn)
-	if err := conn.ensureForwarders(); err != nil {
-		return err
-	}
-	// Send a large frame down the DF channel in order to prompt
-	// PMTU discovery to start.
-	conn.Forward(true, &ForwardedFrame{
-		srcPeer: conn.local,
-		dstPeer: conn.remote,
-		frame:   PMTUDiscovery},
-		nil)
-	conn.heartbeat = time.NewTicker(SlowHeartbeat)
-	conn.fragTest = time.NewTicker(FragTestInterval)
-	// avoid initial waits for timers to fire
-	conn.Forward(true, conn.heartbeatFrame, nil)
-	conn.setStackFrag(false)
-	if err := conn.handleSendSimpleProtocolMsg(ProtocolStartFragmentationTest); err != nil {
-		return err
-	}
-	return nil
-}
-
-func (conn *LocalConnection) handleSendSimpleProtocolMsg(tag ProtocolTag) error {
-	return conn.handleSendProtocolMsg(ProtocolMsg{tag: tag})
-}
-
-func (conn *LocalConnection) handleSendProtocolMsg(m ProtocolMsg) error {
-	return conn.tcpSender.Send(Concat([]byte{byte(m.tag)}, m.msg))
-}
-
-func (conn *LocalConnection) handleShutdown() {
 	if conn.TCPConn != nil {
 		checkWarn(conn.TCPConn.Close())
 	}
 
 	if conn.remote != nil {
-		conn.remote.DecrementLocalRefCount()
+		conn.Router.Peers.Dereference(conn.remote)
 		conn.Router.Ourself.DeleteConnection(conn)
 	}
 
-	if conn.establishedTimeout != nil {
-		conn.establishedTimeout.Stop()
+	if conn.heartbeatTimeout != nil {
+		conn.heartbeatTimeout.Stop()
 	}
 
+	stopTicker(conn.heartbeatTCP)
 	stopTicker(conn.heartbeat)
 	stopTicker(conn.fragTest)
 
@@ -404,165 +503,30 @@ func (conn *LocalConnection) handleShutdown() {
 	// try to send any more
 	conn.stopForwarders()
 
-	conn.Router.ConnectionMaker.ConnectionTerminated(conn.remoteTCPAddr)
+	conn.Router.ConnectionMaker.ConnectionTerminated(conn.remoteTCPAddr, err)
 }
 
 // Helpers
 
-func (conn *LocalConnection) handshake(enc *gob.Encoder, dec *gob.Decoder, acceptNewPeer bool) error {
-	// We do not need to worry about locking in here as at this point
-	// the connection is not reachable by any go-routine other than
-	// ourself. Only when we add this connection to the conn.local
-	// peer will it be visible from multiple go-routines.
-
-	conn.extendReadDeadline()
-
-	localConnID := randUint64()
-	versionStr := fmt.Sprint(ProtocolVersion)
-	handshakeSend := map[string]string{
-		"Protocol":        Protocol,
-		"ProtocolVersion": versionStr,
-		"PeerNameFlavour": PeerNameFlavour,
-		"Name":            conn.local.Name.String(),
-		"UID":             fmt.Sprint(conn.local.UID),
-		"ConnID":          fmt.Sprint(localConnID)}
-	handshakeRecv := map[string]string{}
-
-	usingPassword := conn.Router.UsingPassword()
-	var public, private *[32]byte
-	var err error
-	if usingPassword {
-		public, private, err = GenerateKeyPair()
-		if err != nil {
-			return err
-		}
-		handshakeSend["PublicKey"] = hex.EncodeToString(public[:])
-	}
-	enc.Encode(handshakeSend)
-
-	err = dec.Decode(&handshakeRecv)
-	if err != nil {
-		return err
-	}
-	_, err = checkHandshakeStringField("Protocol", Protocol, handshakeRecv)
-	if err != nil {
-		return err
-	}
-	_, err = checkHandshakeStringField("ProtocolVersion", versionStr, handshakeRecv)
-	if err != nil {
-		return err
-	}
-	_, err = checkHandshakeStringField("PeerNameFlavour", PeerNameFlavour, handshakeRecv)
-	if err != nil {
-		return err
-	}
-	nameStr, err := checkHandshakeStringField("Name", "", handshakeRecv)
-	if err != nil {
-		return err
-	}
-	name, err := PeerNameFromString(nameStr)
-	if err != nil {
-		return err
-	}
-	if !acceptNewPeer {
-		if _, found := conn.Router.Peers.Fetch(name); !found {
-			return fmt.Errorf("Found unknown remote name: %s at %s", name, conn.remoteTCPAddr)
-		}
-	}
-	if existingConn, found := conn.local.ConnectionTo(name); found && existingConn.Established() {
-		return fmt.Errorf("Already have connection to %s at %s", name, existingConn.RemoteTCPAddr())
-	}
-
-	uidStr, err := checkHandshakeStringField("UID", "", handshakeRecv)
-	if err != nil {
-		return err
-	}
-	uid, err := strconv.ParseUint(uidStr, 10, 64)
-	if err != nil {
-		return err
-	}
-
-	remoteConnIdStr, err := checkHandshakeStringField("ConnID", "", handshakeRecv)
-	if err != nil {
-		return err
-	}
-	remoteConnID, err := strconv.ParseUint(remoteConnIdStr, 10, 64)
-	if err != nil {
-		return err
-	}
-	conn.uid = localConnID ^ remoteConnID
-
-	if usingPassword {
-		remotePublicStr, rpErr := checkHandshakeStringField("PublicKey", "", handshakeRecv)
-		if rpErr != nil {
-			return rpErr
-		}
-		remotePublicSlice, rpErr := hex.DecodeString(remotePublicStr)
-		if rpErr != nil {
-			return rpErr
-		}
-		remotePublic := [32]byte{}
-		for idx, elem := range remotePublicSlice {
-			remotePublic[idx] = elem
-		}
-		conn.SessionKey = FormSessionKey(&remotePublic, private, conn.Router.Password)
-		conn.tcpSender = NewEncryptedTCPSender(enc, conn)
-		conn.Decryptor = NewNaClDecryptor(conn)
-	} else {
-		if _, found := handshakeRecv["PublicKey"]; found {
-			return fmt.Errorf("Remote network is encrypted. Password required.")
-		}
-		conn.tcpSender = NewSimpleTCPSender(enc)
-		conn.Decryptor = NewNonDecryptor(conn)
-	}
-
-	toPeer := NewPeer(name, uid, 0)
-	toPeer = conn.Router.Peers.FetchWithDefault(toPeer)
-	switch toPeer {
-	case nil:
-		return fmt.Errorf("Connection appears to be with different version of a peer we already know of")
-	case conn.local:
-		conn.remote = toPeer // have to do assigment here to ensure Shutdown releases ref count
-		return fmt.Errorf("Cannot connect to ourself")
-	default:
-		conn.remote = toPeer
-		return nil
-	}
+func (conn *LocalConnection) sendSimpleProtocolMsg(tag ProtocolTag) error {
+	return conn.sendProtocolMsg(ProtocolMsg{tag: tag})
 }
 
-func checkHandshakeStringField(fieldName string, expectedValue string, handshake map[string]string) (string, error) {
-	val, found := handshake[fieldName]
-	if !found {
-		return "", fmt.Errorf("Field %s is missing", fieldName)
-	}
-	if expectedValue != "" && val != expectedValue {
-		return "", fmt.Errorf("Field %s has wrong value; expected '%s', received '%s'", fieldName, expectedValue, val)
-	}
-	return val, nil
+func (conn *LocalConnection) sendProtocolMsg(m ProtocolMsg) error {
+	return conn.tcpSender.Send(Concat([]byte{byte(m.tag)}, m.msg))
 }
 
-func (conn *LocalConnection) receiveTCP(decoder *gob.Decoder) {
-	defer conn.Decryptor.Shutdown()
-	usingPassword := conn.SessionKey != nil
-	var receiver TCPReceiver
-	if usingPassword {
-		receiver = NewEncryptedTCPReceiver(conn)
-	} else {
-		receiver = NewSimpleTCPReceiver()
-	}
+func (conn *LocalConnection) receiveTCP(receiver TCPReceiver) {
 	var err error
 	for {
-		var msg []byte
 		conn.extendReadDeadline()
-		if err = decoder.Decode(&msg); err != nil {
-			break
-		}
-		msg, err = receiver.Decode(msg)
-		if err != nil {
+
+		var msg []byte
+		if msg, err = receiver.Receive(); err != nil {
 			break
 		}
 		if len(msg) < 1 {
-			conn.log("ignoring blank msg")
+			conn.Log("ignoring blank msg")
 			continue
 		}
 		if err = conn.handleProtocolMsg(ProtocolTag(msg[0]), msg[1:]); err != nil {
@@ -574,52 +538,43 @@ func (conn *LocalConnection) receiveTCP(decoder *gob.Decoder) {
 
 func (conn *LocalConnection) handleProtocolMsg(tag ProtocolTag, payload []byte) error {
 	switch tag {
+	case ProtocolHeartbeat:
 	case ProtocolConnectionEstablished:
 		// We sent fast heartbeats to the remote peer, which has now
 		// received at least one of them and told us via this message.
 		// We can now consider the connection as established from our
 		// end.
 		conn.SetEstablished()
-	case ProtocolStartFragmentationTest:
-		conn.Forward(false, &ForwardedFrame{
-			srcPeer: conn.local,
-			dstPeer: conn.remote,
-			frame:   FragTest},
-			nil)
 	case ProtocolFragmentationReceived:
 		conn.setStackFrag(true)
-	case ProtocolNonce:
-		if conn.SessionKey == nil {
-			return fmt.Errorf("unexpected nonce on unencrypted connection")
-		}
-		conn.Decryptor.ReceiveNonce(payload)
 	case ProtocolPMTUVerified:
-		conn.verifyPMTU <- int(binary.BigEndian.Uint16(payload))
-	case ProtocolGossipUnicast:
-		return conn.Router.handleGossip(payload, deliverGossipUnicast)
-	case ProtocolGossipBroadcast:
-		return conn.Router.handleGossip(payload, deliverGossipBroadcast)
-	case ProtocolGossip:
-		return conn.Router.handleGossip(payload, deliverGossip)
+		conn.pmtuVerified(int(binary.BigEndian.Uint16(payload)))
+	case ProtocolGossipUnicast, ProtocolGossipBroadcast, ProtocolGossip:
+		return conn.Router.handleGossip(tag, payload)
 	default:
-		conn.log("ignoring unknown protocol tag:", tag)
+		conn.Log("ignoring unknown protocol tag:", tag)
 	}
 	return nil
 }
 
 func (conn *LocalConnection) extendReadDeadline() {
-	conn.TCPConn.SetReadDeadline(time.Now().Add(ReadTimeout))
+	conn.TCPConn.SetReadDeadline(time.Now().Add(TCPHeartbeat * 2))
 }
 
 func (conn *LocalConnection) sendFastHeartbeats() error {
 	err := conn.ensureForwarders()
 	if err == nil {
 		conn.heartbeat = time.NewTicker(FastHeartbeat)
-		conn.Forward(true, conn.heartbeatFrame, nil) // avoid initial wait
+		conn.Send(true, conn.heartbeatFrame) // avoid initial wait
 	}
 	return err
 }
 
+func (conn *LocalConnection) performFragTest() {
+	conn.setStackFrag(false)
+	conn.Send(false, FragTest)
+}
+
 func tickerChan(ticker *time.Ticker) <-chan time.Time {
 	if ticker != nil {
 		return ticker.C

router/connection_maker.go

@@ -1,111 +1,116 @@
 package router
 
 import (
-	"bytes"
 	"fmt"
-	"log"
 	"math/rand"
 	"net"
 	"time"
 )
 
 const (
-	InitialInterval = 5 * time.Second
-	MaxInterval     = 10 * time.Minute
+	InitialInterval = 2 * time.Second
+	MaxInterval     = 6 * time.Minute
 )
 
-const (
-	CMInitiate = iota
-	CMTerminated
-	CMRefresh
-	CMStatus
-)
+type peerAddrs map[string]*net.TCPAddr
 
 type ConnectionMaker struct {
-	ourself        *LocalPeer
-	peers          *Peers
-	targets        map[string]*Target
-	cmdLineAddress map[string]bool
-	queryChan      chan<- *ConnectionMakerInteraction
+	ourself     *LocalPeer
+	peers       *Peers
+	port        int
+	discovery   bool
+	targets     map[string]*Target
+	directPeers peerAddrs
+	actionChan  chan<- ConnectionMakerAction
 }
 
 // Information about an address where we may find a peer
 type Target struct {
 	attempting  bool          // are we currently attempting to connect there?
+	lastError   error         // reason for disconnection last time
 	tryAfter    time.Time     // next time to try this address
-	tryInterval time.Duration // backoff time on next failure
+	tryInterval time.Duration // retry delay on next failure
 }
 
-type ConnectionMakerInteraction struct {
-	Interaction
-	address string
+type ConnectionMakerAction func() bool
+
+func NewConnectionMaker(ourself *LocalPeer, peers *Peers, port int, discovery bool) *ConnectionMaker {
+	actionChan := make(chan ConnectionMakerAction, ChannelSize)
+	cm := &ConnectionMaker{
+		ourself:     ourself,
+		peers:       peers,
+		port:        port,
+		discovery:   discovery,
+		directPeers: peerAddrs{},
+		targets:     make(map[string]*Target),
+		actionChan:  actionChan}
+	go cm.queryLoop(actionChan)
+	return cm
 }
 
-func NewConnectionMaker(ourself *LocalPeer, peers *Peers) *ConnectionMaker {
-	return &ConnectionMaker{
-		ourself:        ourself,
-		peers:          peers,
-		cmdLineAddress: make(map[string]bool),
-		targets:        make(map[string]*Target)}
+func (cm *ConnectionMaker) InitiateConnections(peers []string, replace bool) []error {
+	errors := []error{}
+	addrs := peerAddrs{}
+	for _, peer := range peers {
+		host, port, err := net.SplitHostPort(peer)
+		if err != nil {
+			host = peer
+			port = "0" // we use that as an indication that "no port was supplied"
+		}
+		if addr, err := net.ResolveTCPAddr("tcp4", fmt.Sprintf("%s:%s", host, port)); err != nil {
+			errors = append(errors, err)
+		} else {
+			addrs[peer] = addr
+		}
+	}
+	cm.actionChan <- func() bool {
+		if replace {
+			cm.directPeers = peerAddrs{}
+		}
+		for peer, addr := range addrs {
+			cm.directPeers[peer] = addr
+			// curtail any existing reconnect interval
+			if target, found := cm.targets[addr.String()]; found {
+				target.tryNow()
+			}
+		}
+		return true
+	}
+	return errors
 }
 
-func (cm *ConnectionMaker) Start() {
-	queryChan := make(chan *ConnectionMakerInteraction, ChannelSize)
-	cm.queryChan = queryChan
-	go cm.queryLoop(queryChan)
+func (cm *ConnectionMaker) ForgetConnections(peers []string) {
+	cm.actionChan <- func() bool {
+		for _, peer := range peers {
+			delete(cm.directPeers, peer)
+		}
+		return false
+	}
 }
 
-func (cm *ConnectionMaker) InitiateConnection(address string) {
-	cm.queryChan <- &ConnectionMakerInteraction{
-		Interaction: Interaction{code: CMInitiate},
-		address:     address}
-}
-
-func (cm *ConnectionMaker) ConnectionTerminated(address string) {
-	cm.queryChan <- &ConnectionMakerInteraction{
-		Interaction: Interaction{code: CMTerminated},
-		address:     address}
+func (cm *ConnectionMaker) ConnectionTerminated(address string, err error) {
+	cm.actionChan <- func() bool {
+		if target, found := cm.targets[address]; found {
+			target.attempting = false
+			target.lastError = err
+			target.retry()
+		}
+		return true
+	}
 }
 
 func (cm *ConnectionMaker) Refresh() {
-	cm.queryChan <- &ConnectionMakerInteraction{
-		Interaction: Interaction{code: CMRefresh}}
+	cm.actionChan <- func() bool { return true }
 }
 
-func (cm *ConnectionMaker) String() string {
-	resultChan := make(chan interface{}, 0)
-	cm.queryChan <- &ConnectionMakerInteraction{
-		Interaction: Interaction{code: CMStatus, resultChan: resultChan}}
-	result := <-resultChan
-	return result.(string)
-}
-
-func (cm *ConnectionMaker) queryLoop(queryChan <-chan *ConnectionMakerInteraction) {
+func (cm *ConnectionMaker) queryLoop(actionChan <-chan ConnectionMakerAction) {
 	timer := time.NewTimer(MaxDuration)
 	run := func() { timer.Reset(cm.checkStateAndAttemptConnections()) }
 	for {
 		select {
-		case query, ok := <-queryChan:
-			if !ok {
-				return
-			}
-			switch query.code {
-			case CMInitiate:
-				cm.cmdLineAddress[NormalisePeerAddr(query.address)] = true
+		case action := <-actionChan:
+			if action() {
 				run()
-			case CMTerminated:
-				if target, found := cm.targets[query.address]; found {
-					target.attempting = false
-					target.tryAfter, target.tryInterval = tryAfter(target.tryInterval)
-				}
-				run()
-			case CMRefresh:
-				run()
-			case CMStatus:
-				run()
-				query.resultChan <- cm.status()
-			default:
-				log.Fatal("Unexpected connection maker query:", query)
 			}
 		case <-timer.C:
 			run()
@@ -114,62 +119,126 @@ func (cm *ConnectionMaker) queryLoop(queryChan <-chan *ConnectionMakerInteractio
 }
 
 func (cm *ConnectionMaker) checkStateAndAttemptConnections() time.Duration {
-	validTarget := make(map[string]bool)
-
-	// copy the set of things we are connected to, so we can access them without locking
-	our_connected_peers := make(map[PeerName]bool)
-	our_connected_targets := make(map[string]bool)
-	cm.ourself.ForEachConnection(func(peer PeerName, conn Connection) {
-		our_connected_peers[peer] = true
-		our_connected_targets[conn.RemoteTCPAddr()] = true
-	})
+	var (
+		validTarget  = make(map[string]struct{})
+		directTarget = make(map[string]struct{})
+	)
+	// Copy the set of things we are connected to, so we can access
+	// them without locking.  Also clear out any entries in cm.targets
+	// for existing connections.
+	ourConnectedPeers, ourConnectedTargets, ourInboundIPs := cm.ourConnections()
 
 	addTarget := func(address string) {
-		if !our_connected_targets[address] {
-			validTarget[address] = true
-			cm.addTarget(address)
+		if _, connected := ourConnectedTargets[address]; connected {
+			return
 		}
+		validTarget[address] = void
+		if _, found := cm.targets[address]; found {
+			return
+		}
+		target := &Target{}
+		target.tryNow()
+		cm.targets[address] = target
 	}
 
-	// Add command-line targets that are not connected
-	for address, _ := range cm.cmdLineAddress {
-		addTarget(address)
+	// Add direct targets that are not connected
+	for _, addr := range cm.directPeers {
+		completeAddr := *addr
+		attempt := true
+		if completeAddr.Port == 0 {
+			completeAddr.Port = cm.port
+			// If a peer was specified w/o a port, then we do not
+			// attempt to connect to it if we have any inbound
+			// connections from that IP.
+			if _, connected := ourInboundIPs[completeAddr.IP.String()]; connected {
+				attempt = false
+			}
+		}
+		address := completeAddr.String()
+		directTarget[address] = void
+		if attempt {
+			addTarget(address)
+		}
 	}
 
 	// Add targets for peers that someone else is connected to, but we
 	// aren't
-	cm.peers.ForEach(func(name PeerName, peer *Peer) {
-		peer.ForEachConnection(func(otherPeer PeerName, conn Connection) {
-			if otherPeer == cm.ourself.Name || our_connected_peers[otherPeer] {
-				return
+	if cm.discovery {
+		cm.addPeerTargets(ourConnectedPeers, addTarget)
+	}
+
+	return cm.connectToTargets(validTarget, directTarget)
+}
+
+func (cm *ConnectionMaker) ourConnections() (PeerNameSet, map[string]struct{}, map[string]struct{}) {
+	var (
+		ourConnectedPeers   = make(PeerNameSet)
+		ourConnectedTargets = make(map[string]struct{})
+		ourInboundIPs       = make(map[string]struct{})
+	)
+	for conn := range cm.ourself.Connections() {
+		address := conn.RemoteTCPAddr()
+		delete(cm.targets, address)
+		ourConnectedPeers[conn.Remote().Name] = void
+		ourConnectedTargets[address] = void
+		if conn.Outbound() {
+			continue
+		}
+		if ip, _, err := net.SplitHostPort(address); err == nil { // should always succeed
+			ourInboundIPs[ip] = void
+		}
+	}
+	return ourConnectedPeers, ourConnectedTargets, ourInboundIPs
+}
+
+func (cm *ConnectionMaker) addPeerTargets(ourConnectedPeers PeerNameSet, addTarget func(string)) {
+	cm.peers.ForEach(func(peer *Peer) {
+		if peer == cm.ourself.Peer {
+			return
+		}
+		// Modifying peer.connections requires a write lock on Peers,
+		// and since we are holding a read lock (due to the ForEach),
+		// access without locking the peer is safe.
+		for otherPeer, conn := range peer.connections {
+			if otherPeer == cm.ourself.Name {
+				continue
+			}
+			if _, connected := ourConnectedPeers[otherPeer]; connected {
+				continue
 			}
 			address := conn.RemoteTCPAddr()
-			// try both portnumber of connection and standard port
-			addTarget(address)
-			if host, _, err := net.SplitHostPort(address); err == nil {
-				addTarget(NormalisePeerAddr(host))
+			if conn.Outbound() {
+				addTarget(address)
+			} else if ip, _, err := net.SplitHostPort(address); err == nil {
+				// There is no point connecting to the (likely
+				// ephemeral) remote port of an inbound connection
+				// that some peer has. Let's try to connect to on the
+				// weave port instead.
+				addTarget(fmt.Sprintf("%s:%d", ip, cm.port))
 			}
-		})
+		}
 	})
+}
 
+func (cm *ConnectionMaker) connectToTargets(validTarget map[string]struct{}, directTarget map[string]struct{}) time.Duration {
 	now := time.Now() // make sure we catch items just added
 	after := MaxDuration
 	for address, target := range cm.targets {
-		if our_connected_targets[address] {
-			delete(cm.targets, address)
-			continue
-		}
 		if target.attempting {
 			continue
 		}
-		if !validTarget[address] {
+		if _, valid := validTarget[address]; !valid {
 			delete(cm.targets, address)
 			continue
 		}
+		if target.tryAfter.IsZero() {
+			continue
+		}
 		switch duration := target.tryAfter.Sub(now); {
 		case duration <= 0:
 			target.attempting = true
-			go cm.attemptConnection(address, cm.cmdLineAddress[address])
+			_, isCmdLineTarget := directTarget[address]
+			go cm.attemptConnection(address, isCmdLineTarget)
 		case duration < after:
 			after = duration
 		}
@@ -177,45 +246,30 @@ func (cm *ConnectionMaker) checkStateAndAttemptConnections() time.Duration {
 	return after
 }
 
-func (cm *ConnectionMaker) addTarget(address string) {
-	if _, found := cm.targets[address]; !found {
-		target := &Target{}
-		target.tryAfter, target.tryInterval = tryImmediately()
-		cm.targets[address] = target
-	}
-}
-
-func (cm *ConnectionMaker) status() string {
-	var buf bytes.Buffer
-	for address, target := range cm.targets {
-		var fmtStr string
-		if target.attempting {
-			fmtStr = "%s (trying since %v)\n"
-		} else {
-			fmtStr = "%s (next try at %v)\n"
-		}
-		buf.WriteString(fmt.Sprintf(fmtStr, address, target.tryAfter))
-	}
-	return buf.String()
-}
-
 func (cm *ConnectionMaker) attemptConnection(address string, acceptNewPeer bool) {
-	log.Printf("->[%s] attempting connection\n", address)
+	log.Printf("->[%s] attempting connection", address)
 	if err := cm.ourself.CreateConnection(address, acceptNewPeer); err != nil {
-		log.Printf("->[%s] error during connection attempt: %v\n", address, err)
-		cm.ConnectionTerminated(address)
+		log.Errorf("->[%s] error during connection attempt: %v", address, err)
+		cm.ConnectionTerminated(address, err)
 	}
 }
 
-func tryImmediately() (time.Time, time.Duration) {
-	interval := time.Duration(rand.Int63n(int64(InitialInterval)))
-	return time.Now(), interval
+func (t *Target) tryNow() {
+	t.tryAfter = time.Now()
+	t.tryInterval = InitialInterval
 }
 
-func tryAfter(interval time.Duration) (time.Time, time.Duration) {
-	interval += time.Duration(rand.Int63n(int64(interval)))
-	if interval > MaxInterval {
-		interval = MaxInterval
+// The delay at the nth retry is a random value in the range
+// [i-i/2,i+i/2], where i = InitialInterval * 1.5^(n-1).
+func (t *Target) retry() {
+	if t.lastError == ErrConnectToSelf {
+		t.tryAfter = time.Time{}
+		t.tryInterval = MaxInterval
+		return
+	}
+	t.tryAfter = time.Now().Add(t.tryInterval/2 + time.Duration(rand.Int63n(int64(t.tryInterval))))
+	t.tryInterval = t.tryInterval * 3 / 2
+	if t.tryInterval > MaxInterval {
+		t.tryInterval = MaxInterval
 	}
-	return time.Now().Add(interval), interval
 }

router/consts.go

@@ -6,24 +6,26 @@ import (
 )
 
 const (
-	EthernetOverhead   = 14
-	UDPOverhead        = 28 // 20 bytes for IPv4, 8 bytes for UDP
-	Port               = 6783
-	HttpPort           = Port + 1
-	DefaultPMTU        = 65535
-	MaxUDPPacketSize   = 65536
-	ChannelSize        = 16
-	UDPNonceSendAt     = 8192
-	FragTestSize       = 60001
-	PMTUDiscoverySize  = 60000
-	FastHeartbeat      = 500 * time.Millisecond
-	SlowHeartbeat      = 10 * time.Second
-	FragTestInterval   = 5 * time.Minute
-	EstablishedTimeout = 30 * time.Second
-	ReadTimeout        = 1 * time.Minute
-	PMTUVerifyAttempts = 8
-	PMTUVerifyTimeout  = 10 * time.Millisecond // gets doubled with every attempt
-	MaxDuration        = time.Duration(math.MaxInt64)
+	EthernetOverhead    = 14
+	UDPOverhead         = 28 // 20 bytes for IPv4, 8 bytes for UDP
+	Port                = 6783
+	HTTPPort            = Port + 1
+	DefaultPMTU         = 65535
+	MaxUDPPacketSize    = 65535
+	ChannelSize         = 16
+	FragTestSize        = 60001
+	PMTUDiscoverySize   = 60000
+	TCPHeartbeat        = 30 * time.Second
+	FastHeartbeat       = 500 * time.Millisecond
+	SlowHeartbeat       = 10 * time.Second
+	FragTestInterval    = 5 * time.Minute
+	GossipInterval      = 30 * time.Second
+	PMTUVerifyAttempts  = 8
+	PMTUVerifyTimeout   = 10 * time.Millisecond // gets doubled with every attempt
+	MaxDuration         = time.Duration(math.MaxInt64)
+	MaxMissedHeartbeats = 6
+	HeartbeatTimeout    = MaxMissedHeartbeats * SlowHeartbeat
+	MaxTCPMsgSize       = 10 * 1024 * 1024
 )
 
 var (

router/crypto.go

@@ -1,113 +1,39 @@
 package router
 
 import (
-	"bytes"
-	"code.google.com/p/go-bit/bit"
-	"code.google.com/p/go.crypto/nacl/box"
-	"code.google.com/p/go.crypto/nacl/secretbox"
 	"crypto/rand"
 	"crypto/sha256"
 	"encoding/binary"
 	"encoding/gob"
 	"fmt"
-	"log"
-	"net"
+	"io"
 	"sync"
+
+	"github.com/andybalholm/go-bit"
+	"golang.org/x/crypto/nacl/box"
+	"golang.org/x/crypto/nacl/secretbox"
 )
 
 func GenerateKeyPair() (publicKey, privateKey *[32]byte, err error) {
 	return box.GenerateKey(rand.Reader)
 }
 
-func FormSessionKey(remotePublicKey, localPrivateKey *[32]byte, secretKey *[]byte) *[32]byte {
+func FormSessionKey(remotePublicKey, localPrivateKey *[32]byte, secretKey []byte) *[32]byte {
 	var sharedKey [32]byte
 	box.Precompute(&sharedKey, remotePublicKey, localPrivateKey)
 	sharedKeySlice := sharedKey[:]
-	sharedKeySlice = append(sharedKeySlice, *secretKey...)
+	sharedKeySlice = append(sharedKeySlice, secretKey...)
 	sessionKey := sha256.Sum256(sharedKeySlice)
 	return &sessionKey
 }
 
-func GenerateRandomNonce() ([24]byte, error) {
-	var nonce [24]byte
-	n, err := rand.Read(nonce[:])
-	if err != nil {
-		return nonce, err
-	}
-	if n != 24 {
-		return nonce, fmt.Errorf("Did not read enough - wanted 24, got %v", n)
-	}
-	return nonce, nil
-}
-
-func EncryptPrefixNonce(plaintxt []byte, nonce *[24]byte, secret *[32]byte) []byte {
-	buf := make([]byte, 24, 24+len(plaintxt)+secretbox.Overhead)
-	copy(buf, nonce[:])
-	// Seal *appends* to buf
-	return secretbox.Seal(buf, plaintxt, nonce, secret)
-}
-
-func DecryptPrefixNonce(ciphertxt []byte, secret *[32]byte) ([]byte, bool) {
-	if len(ciphertxt) < secretbox.Overhead+24 {
-		return nil, false
-	}
-	// There is no way to nicely convert from a slice to an
-	// array. So have to used the following loop.
-	var nonce [24]byte
-	for idx, e := range ciphertxt[0:24] {
-		nonce[idx] = e
-	}
-	ciphertxt = ciphertxt[24:]
-	return secretbox.Open(nil, ciphertxt, &nonce, secret)
-}
-
-func SetNonceLow15Bits(nonce *[24]byte, offset uint16) {
-	// ensure top bit of offset is 0
-	offset = offset & ((1 << 15) - 1)
-	// grab top bit of nonce[22:24] (and clear out lower bits)
-	nonceBits := binary.BigEndian.Uint16(nonce[22:24]) & (1 << 15)
-	// Big endian => the MSB is stored at the *lowest* address. So
-	// that top bit in nonce[22] should stay as the top bit in
-	// nonce[22]
-	binary.BigEndian.PutUint16(nonce[22:24], nonceBits+offset)
-}
-
-// Nonce encoding/decoding
-
-func EncodeNonce(df bool) (*[24]byte, []byte, error) {
-	nonce, err := GenerateRandomNonce()
-	if err != nil {
-		return nil, []byte{}, err
-	}
-	// wipe out lowest 15 bits, but encode the df right at the bottom
-	flags := uint16(0)
-	if df {
-		flags = flags | 1
-	}
-	SetNonceLow15Bits(&nonce, flags)
-	// NB: need to make a copy since callers may modify the array
-	return &nonce, Concat(nonce[:]), nil
-}
-
-func DecodeNonce(msg []byte) (bool, *[24]byte) {
-	flags := uint16(msg[23])
-	df := 0 != (flags & 1)
-	nonce := [24]byte{}
-	// upper bound is exclusive so this avoids copying the flags
-	for idx, elem := range msg[:23] {
-		nonce[idx] = elem
-	}
-	return df, &nonce
-}
-
 // Frame Encryptors
 
 type Encryptor interface {
 	FrameOverhead() int
 	PacketOverhead() int
-	IsEmpty() bool
-	Bytes() []byte
-	AppendFrame(*ForwardedFrame)
+	Bytes() ([]byte, error)
+	AppendFrame(src []byte, dst []byte, frame []byte)
 	TotalLen() int
 }
 
@@ -120,14 +46,12 @@ type NonEncryptor struct {
 
 type NaClEncryptor struct {
 	NonEncryptor
-	buf       []byte
-	offset    uint16
-	nonce     *[24]byte
-	nonceChan chan *[24]byte
-	flags     uint16
-	prefixLen int
-	conn      *LocalConnection
-	df        bool
+	buf        []byte
+	prefixLen  int
+	sessionKey *[32]byte
+	nonce      [24]byte
+	seqNo      uint64
+	df         bool
 }
 
 func NewNonEncryptor(prefix []byte) *NonEncryptor {
@@ -148,95 +72,71 @@ func (ne *NonEncryptor) FrameOverhead() int {
 	return NameSize + NameSize + 2
 }
 
-func (ne *NonEncryptor) IsEmpty() bool {
-	return ne.buffered == ne.prefixLen
-}
-
-func (ne *NonEncryptor) Bytes() []byte {
+func (ne *NonEncryptor) Bytes() ([]byte, error) {
 	buf := ne.buf[:ne.buffered]
 	ne.buffered = ne.prefixLen
 	ne.bufTail = ne.buf[ne.prefixLen:]
-	return buf
+	return buf, nil
 }
 
-func (ne *NonEncryptor) AppendFrame(frame *ForwardedFrame) {
+func (ne *NonEncryptor) AppendFrame(src []byte, dst []byte, frame []byte) {
 	bufTail := ne.bufTail
-	srcLen := copy(bufTail, frame.srcPeer.NameByte)
+	srcLen := copy(bufTail, src)
 	bufTail = bufTail[srcLen:]
-	dstLen := copy(bufTail, frame.dstPeer.NameByte)
+	dstLen := copy(bufTail, dst)
 	bufTail = bufTail[dstLen:]
-	frameLen := len(frame.frame)
-	binary.BigEndian.PutUint16(bufTail, uint16(frameLen))
+	binary.BigEndian.PutUint16(bufTail, uint16(len(frame)))
 	bufTail = bufTail[2:]
-	copy(bufTail, frame.frame)
-	ne.bufTail = bufTail[frameLen:]
-	ne.buffered += srcLen + dstLen + 2 + frameLen
+	copy(bufTail, frame)
+	ne.bufTail = bufTail[len(frame):]
+	ne.buffered += srcLen + dstLen + 2 + len(frame)
 }
 
 func (ne *NonEncryptor) TotalLen() int {
 	return ne.buffered
 }
 
-func NewNaClEncryptor(prefix []byte, conn *LocalConnection, df bool) *NaClEncryptor {
+func NewNaClEncryptor(prefix []byte, sessionKey *[32]byte, outbound bool, df bool) *NaClEncryptor {
 	buf := make([]byte, MaxUDPPacketSize)
 	prefixLen := copy(buf, prefix)
-	flags := uint16(0)
-	if df {
-		flags = flags | (1 << 15)
-	}
-	return &NaClEncryptor{
+	ne := &NaClEncryptor{
 		NonEncryptor: *NewNonEncryptor([]byte{}),
 		buf:          buf,
-		offset:       0,
-		nonce:        nil,
-		nonceChan:    make(chan *[24]byte, ChannelSize),
-		flags:        flags,
 		prefixLen:    prefixLen,
-		conn:         conn,
+		sessionKey:   sessionKey,
 		df:           df}
+	if outbound {
+		ne.nonce[0] |= (1 << 7)
+	}
+	return ne
 }
 
-func (ne *NaClEncryptor) Bytes() []byte {
-	plaintext := ne.NonEncryptor.Bytes()
-	offsetFlags := ne.offset | ne.flags
+func (ne *NaClEncryptor) Bytes() ([]byte, error) {
+	plaintext, err := ne.NonEncryptor.Bytes()
+	if err != nil {
+		return nil, err
+	}
+	// We carry the DF flag in the (unencrypted portion of the)
+	// payload, rather than just extracting it from the packet headers
+	// at the receiving end, since we do not trust routers not to mess
+	// with headers. As we have different decryptors for non-DF and
+	// DF, that would result in hard to track down packet drops due to
+	// crypto errors.
+	seqNoAndDF := ne.seqNo
+	if ne.df {
+		seqNoAndDF |= (1 << 63)
+	}
 	ciphertext := ne.buf
-	binary.BigEndian.PutUint16(ciphertext[ne.prefixLen:], offsetFlags)
-	nonce := ne.nonce
-	if nonce == nil {
-		freshNonce, encodedNonce, err := EncodeNonce(ne.df)
-		if err != nil {
-			ne.conn.Shutdown(err)
-			return []byte{}
-		}
-		ne.conn.SendProtocolMsg(ProtocolMsg{ProtocolNonce, encodedNonce})
-		ne.nonce = freshNonce
-		nonce = freshNonce
-	}
-	offset := ne.offset
-	SetNonceLow15Bits(nonce, offset)
+	binary.BigEndian.PutUint64(ciphertext[ne.prefixLen:], seqNoAndDF)
+	binary.BigEndian.PutUint64(ne.nonce[16:24], seqNoAndDF)
 	// Seal *appends* to ciphertext
-	ciphertext = secretbox.Seal(ciphertext[:ne.prefixLen+2], plaintext, nonce, ne.conn.SessionKey)
-
-	offset = (offset + 1) & ((1 << 15) - 1)
-	if offset == 0 {
-		// need a new nonce please
-		ne.nonce = <-ne.nonceChan
-	} else if offset == 1<<14 { // half way through range, send new nonce
-		nonce, encodedNonce, err := EncodeNonce(ne.df)
-		if err != nil {
-			ne.conn.Shutdown(err)
-			return []byte{}
-		}
-		ne.nonceChan <- nonce
-		ne.conn.SendProtocolMsg(ProtocolMsg{ProtocolNonce, encodedNonce})
-	}
-	ne.offset = offset
-
-	return ciphertext
+	ciphertext = secretbox.Seal(ciphertext[:ne.prefixLen+8], plaintext, &ne.nonce, ne.sessionKey)
+	ne.seqNo++
+	return ciphertext, nil
 }
 
 func (ne *NaClEncryptor) PacketOverhead() int {
-	return ne.prefixLen + 2 + secretbox.Overhead + ne.NonEncryptor.PacketOverhead()
+	return ne.prefixLen + 8 + secretbox.Overhead + ne.NonEncryptor.PacketOverhead()
 }
 
 func (ne *NaClEncryptor) TotalLen() int {
@@ -245,314 +145,306 @@ func (ne *NaClEncryptor) TotalLen() int {
 
 // Frame Decryptors
 
-type FrameConsumer func(*LocalConnection, *net.UDPAddr, []byte, []byte, uint16, []byte) error
+type FrameConsumer func(src []byte, dst []byte, frame []byte)
 
 type Decryptor interface {
-	IterateFrames(FrameConsumer, *UDPPacket) error
-	ReceiveNonce([]byte)
-	Shutdown()
+	IterateFrames([]byte, FrameConsumer) error
 }
 
 type NonDecryptor struct {
-	conn *LocalConnection
 }
 
 type NaClDecryptor struct {
 	NonDecryptor
+	sessionKey *[32]byte
 	instance   *NaClDecryptorInstance
 	instanceDF *NaClDecryptorInstance
 }
 
 type NaClDecryptorInstance struct {
-	nonce               *[24]byte
-	previousNonce       *[24]byte
+	nonce               [24]byte
+	currentWindow       uint64
 	usedOffsets         *bit.Set
 	previousUsedOffsets *bit.Set
-	highestOffsetSeen   uint16
-	nonceChan           chan *[24]byte
+}
+
+func NewNaClDecryptorInstance(outbound bool) *NaClDecryptorInstance {
+	di := &NaClDecryptorInstance{usedOffsets: bit.New()}
+	if !outbound {
+		di.nonce[0] |= (1 << 7)
+	}
+	return di
 }
 
 type PacketDecodingError struct {
-	Fatal bool
-	Desc  string
+	Desc string
 }
 
-func NewNonDecryptor(conn *LocalConnection) *NonDecryptor {
-	return &NonDecryptor{conn: conn}
+func NewNonDecryptor() *NonDecryptor {
+	return &NonDecryptor{}
 }
 
-func (nd *NonDecryptor) IterateFrames(fun FrameConsumer, packet *UDPPacket) error {
-	buf := packet.Packet
-	for len(buf) >= (2 + NameSize + NameSize) {
-		srcNameByte := buf[:NameSize]
-		buf = buf[NameSize:]
-		dstNameByte := buf[:NameSize]
-		buf = buf[NameSize:]
-		length := binary.BigEndian.Uint16(buf[:2])
-		buf = buf[2:]
-		if len(buf) < int(length) {
-			return PacketDecodingError{Desc: fmt.Sprintf("too short; expected frame of length %d, got %d", length, len(buf))}
-		}
-		frame := buf[:length]
-		buf = buf[length:]
-		err := fun(nd.conn, packet.Sender, srcNameByte, dstNameByte, length, frame)
-		if err != nil {
-			return err
+func (nd *NonDecryptor) IterateFrames(packet []byte, consumer FrameConsumer) error {
+	for len(packet) >= (2 + NameSize + NameSize) {
+		srcNameByte := packet[:NameSize]
+		packet = packet[NameSize:]
+		dstNameByte := packet[:NameSize]
+		packet = packet[NameSize:]
+		length := binary.BigEndian.Uint16(packet[:2])
+		packet = packet[2:]
+		if len(packet) < int(length) {
+			return PacketDecodingError{Desc: fmt.Sprintf("too short; expected frame of length %d, got %d", length, len(packet))}
 		}
+		frame := packet[:length]
+		packet = packet[length:]
+		consumer(srcNameByte, dstNameByte, frame)
 	}
-	if len(buf) > 0 {
-		return PacketDecodingError{Desc: fmt.Sprintf("%d octets of trailing garbage", len(buf))}
+	if len(packet) > 0 {
+		return PacketDecodingError{Desc: fmt.Sprintf("%d octets of trailing garbage", len(packet))}
 	}
 	return nil
 }
 
-func (nd *NonDecryptor) Shutdown() {
-}
-
-func (nd *NonDecryptor) ReceiveNonce(msg []byte) {
-	log.Println("Received Nonce on non-encrypted channel. Ignoring.")
-}
-
-func NewNaClDecryptor(conn *LocalConnection) *NaClDecryptor {
-	inst := NaClDecryptorInstance{
-		nonce:               nil,
-		previousNonce:       nil,
-		usedOffsets:         bit.New(),
-		previousUsedOffsets: nil,
-		highestOffsetSeen:   0,
-		nonceChan:           make(chan *[24]byte, ChannelSize)}
-	instDF := NaClDecryptorInstance{
-		nonce:               nil,
-		previousNonce:       nil,
-		usedOffsets:         bit.New(),
-		previousUsedOffsets: nil,
-		highestOffsetSeen:   0,
-		nonceChan:           make(chan *[24]byte, ChannelSize)}
+func NewNaClDecryptor(sessionKey *[32]byte, outbound bool) *NaClDecryptor {
 	return &NaClDecryptor{
-		NonDecryptor: *NewNonDecryptor(conn),
-		instance:     &inst,
-		instanceDF:   &instDF}
+		NonDecryptor: *NewNonDecryptor(),
+		sessionKey:   sessionKey,
+		instance:     NewNaClDecryptorInstance(outbound),
+		instanceDF:   NewNaClDecryptorInstance(outbound)}
 }
 
-func (nd *NaClDecryptor) Shutdown() {
-	close(nd.instance.nonceChan)
-	close(nd.instanceDF.nonceChan)
+func (nd *NaClDecryptor) IterateFrames(packet []byte, consumer FrameConsumer) error {
+	if len(packet) < 8 {
+		return PacketDecodingError{Desc: fmt.Sprintf("encrypted UDP packet too short; expected length >= 8, got %d", len(packet))}
+	}
+	buf, success := nd.decrypt(packet)
+	if !success {
+		return PacketDecodingError{Desc: fmt.Sprint("UDP packet decryption failed")}
+	}
+	return nd.NonDecryptor.IterateFrames(buf, consumer)
 }
 
-func (nd *NaClDecryptor) ReceiveNonce(msg []byte) {
-	df, nonce := DecodeNonce(msg)
+func (nd *NaClDecryptor) decrypt(buf []byte) ([]byte, bool) {
+	seqNoAndDF := binary.BigEndian.Uint64(buf[:8])
+	df := (seqNoAndDF & (1 << 63)) != 0
+	seqNo := seqNoAndDF & ((1 << 63) - 1)
+	var di *NaClDecryptorInstance
 	if df {
-		nd.instanceDF.nonceChan <- nonce
+		di = nd.instanceDF
 	} else {
-		nd.instance.nonceChan <- nonce
+		di = nd.instance
+	}
+	binary.BigEndian.PutUint64(di.nonce[16:24], seqNoAndDF)
+	result, success := secretbox.Open(nil, buf[8:], &di.nonce, nd.sessionKey)
+	if !success {
+		return nil, false
+	}
+	// Drop duplicates. We do this *after* decryption since we must
+	// not advance our state unless decryption succeeded. Doing so
+	// would open an easy attack vector where an adversary could
+	// inject a packet with a sequence number of (1 << 63) - 1,
+	// causing all subsequent genuine packets to get dropped.
+	offset, usedOffsets := di.advanceState(seqNo)
+	if usedOffsets == nil || usedOffsets.Contains(offset) {
+		// We have detected a possible replay attack, but it is
+		// possible we may have just received a very old packet, or
+		// duplication may have occurred in the network. So let's just
+		// drop the packet silently.
+		return nil, true
+	}
+	usedOffsets.Add(offset)
+	return result, success
+}
+
+// We record seen message sequence numbers in a sliding window of
+// 2*WindowSize which slides in WindowSize increments. This allows us
+// to process out-of-order delivery within the window, while
+// accurately discarding duplicates. By contrast any messages with
+// sequence numbers below the window are discarded as potential
+// duplicates.
+//
+// There are two sets, corresponding to the lower and upper half of
+// the window. We slide the window s.t. that 2nd set always contains
+// the highest seen sequence number. We do this regardless of how far
+// ahead of the current window that sequence number might be, so we
+// can cope with large gaps resulting from packet loss.
+
+const (
+	WindowSize = 20 // bits
+)
+
+func (di *NaClDecryptorInstance) advanceState(seqNo uint64) (int, *bit.Set) {
+	var (
+		offset = int(seqNo & ((1 << WindowSize) - 1))
+		window = seqNo >> WindowSize
+	)
+	switch delta := int64(window - di.currentWindow); {
+	case delta < -1:
+		return offset, nil
+	case delta == -1:
+		return offset, di.previousUsedOffsets
+	default:
+		return offset, di.usedOffsets
+	case delta == +1:
+		di.currentWindow = window
+		di.previousUsedOffsets = di.usedOffsets
+		di.usedOffsets = bit.New()
+		return offset, di.usedOffsets
+	case delta > +1:
+		di.currentWindow = window
+		di.previousUsedOffsets = bit.New()
+		di.usedOffsets = bit.New()
+		return offset, di.usedOffsets
 	}
 }
 
-func (nd *NaClDecryptor) IterateFrames(fun FrameConsumer, packet *UDPPacket) error {
-	buf, err := nd.decrypt(packet.Packet)
-	if err != nil {
-		return PacketDecodingError{Fatal: true, Desc: fmt.Sprint("decryption failed; ", err)}
-	}
-	packet.Packet = buf
-	return nd.NonDecryptor.IterateFrames(fun, packet)
+// TCP Senders/Receivers
+
+// The lowest 64 bits of the nonce contain the message sequence
+// number. The top most bit indicates the connection polarity at the
+// sender - '1' for outbound; the next indicates protocol type - '1'
+// for TCP. The remaining 126 bits are zero. The polarity is needed so
+// that the two ends of a connection do not use the same nonces; the
+// protocol type so that the TCP and UDP sender nonces are disjoint.
+// This is a requirement of the NaCl Security Model; see
+// http://nacl.cr.yp.to/box.html.
+type TCPCryptoState struct {
+	sessionKey *[32]byte
+	nonce      [24]byte
+	seqNo      uint64
 }
 
-func (nd *NaClDecryptor) decrypt(buf []byte) ([]byte, error) {
-	offset := binary.BigEndian.Uint16(buf[:2])
-	df := (offset & (1 << 15)) != 0
-	offsetNoFlags := offset & ((1 << 15) - 1)
-	var decState *NaClDecryptorInstance
-	if df {
-		decState = nd.instanceDF
-	} else {
-		decState = nd.instance
-	}
-	var nonce *[24]byte
-	var usedOffsets *bit.Set
-	var ok bool
-	if decState.nonce == nil {
-		if offsetNoFlags > (1 << 13) {
-			// offset is already beyond the first quarter and it's the
-			// first thing we've seen?! I don't think so.
-			return nil, fmt.Errorf("Unexpected offset when decrypting UDP packet")
-		}
-		decState.nonce, ok = <-decState.nonceChan
-		if !ok {
-			return nil, fmt.Errorf("Nonce chan closed")
-		}
-		decState.highestOffsetSeen = offsetNoFlags
-		nonce = decState.nonce
-		usedOffsets = decState.usedOffsets
-	} else {
-		highestOffsetSeen := decState.highestOffsetSeen
-		switch {
-		case offsetNoFlags < (1<<13) && highestOffsetSeen > ((1<<14)+(1<<13)) &&
-			(highestOffsetSeen-offsetNoFlags) > ((1<<14)+(1<<13)):
-			// offset is in the first quarter, highestOffsetSeen is in
-			// the top quarter and under a quarter behind us. We
-			// interpret this as we need to move to the next nonce
-			decState.previousUsedOffsets = decState.usedOffsets
-			decState.usedOffsets = bit.New()
-			decState.previousNonce = decState.nonce
-			decState.nonce, ok = <-decState.nonceChan
-			if !ok {
-				return nil, fmt.Errorf("Nonce chan closed")
-			}
-			decState.highestOffsetSeen = offsetNoFlags
-			nonce = decState.nonce
-			usedOffsets = decState.usedOffsets
-		case offsetNoFlags > highestOffsetSeen &&
-			(offsetNoFlags-highestOffsetSeen) < (1<<13):
-			// offset is under a quarter above highestOffsetSeen. This
-			// is ok - maybe some packet loss
-			decState.highestOffsetSeen = offsetNoFlags
-			nonce = decState.nonce
-			usedOffsets = decState.usedOffsets
-		case offsetNoFlags <= highestOffsetSeen &&
-			(highestOffsetSeen-offsetNoFlags) < (1<<13):
-			// offset is within a quarter of the highest we've
-			// seen. This is ok - just assuming some out-of-order
-			// delivery.
-			nonce = decState.nonce
-			usedOffsets = decState.usedOffsets
-		case highestOffsetSeen < (1<<13) && offsetNoFlags > ((1<<14)+(1<<13)) &&
-			(offsetNoFlags-highestOffsetSeen) > ((1<<14)+(1<<13)):
-			// offset is in the last quarter, highestOffsetSeen is in
-			// the first quarter, and offset is under a quarter behind
-			// us. This is ok - as above, just some out of order. But
-			// here it means we're dealing with the previous nonce
-			nonce = decState.previousNonce
-			usedOffsets = decState.previousUsedOffsets
-		default:
-			return nil, fmt.Errorf("Unexpected offset when decrypting UDP packet")
-		}
-	}
-	offsetNoFlagsInt := int(offsetNoFlags)
-	if usedOffsets.Contains(offsetNoFlagsInt) {
-		return nil, fmt.Errorf("Suspected replay attack detected when decrypting UDP packet")
-	}
-	SetNonceLow15Bits(nonce, offsetNoFlags)
-	result, success := secretbox.Open(nil, buf[2:], nonce, nd.conn.SessionKey)
-	if success {
-		usedOffsets.Add(offsetNoFlagsInt)
-		return result, nil
-	} else {
-		return nil, fmt.Errorf("Unable to decrypt UDP packet")
+func NewTCPCryptoState(sessionKey *[32]byte, outbound bool) *TCPCryptoState {
+	s := &TCPCryptoState{sessionKey: sessionKey}
+	if outbound {
+		s.nonce[0] |= (1 << 7)
 	}
+	// Ensure that TCP and UDP sequences are disjoint
+	s.nonce[0] |= (1 << 6)
+	return s
 }
 
-// TCP Senders
+func (s *TCPCryptoState) advance() {
+	s.seqNo++
+	binary.BigEndian.PutUint64(s.nonce[16:24], s.seqNo)
+}
 
 type TCPSender interface {
 	Send([]byte) error
 }
 
-type SimpleTCPSender struct {
+type GobTCPSender struct {
 	encoder *gob.Encoder
 }
 
+type LengthPrefixTCPSender struct {
+	writer io.Writer
+}
+
 type EncryptedTCPSender struct {
 	sync.RWMutex
-	outerEncoder *gob.Encoder
-	innerEncoder *gob.Encoder
-	buffer       *bytes.Buffer
-	conn         *LocalConnection
-	msgCount     int
+	sender TCPSender
+	state  *TCPCryptoState
 }
 
-type EncryptedTCPMessage struct {
-	Number int
-	Body   []byte
+func NewGobTCPSender(encoder *gob.Encoder) *GobTCPSender {
+	return &GobTCPSender{encoder: encoder}
 }
 
-func NewSimpleTCPSender(encoder *gob.Encoder) *SimpleTCPSender {
-	return &SimpleTCPSender{encoder: encoder}
-}
-
-func (sender *SimpleTCPSender) Send(msg []byte) error {
+func (sender *GobTCPSender) Send(msg []byte) error {
 	return sender.encoder.Encode(msg)
 }
 
-func NewEncryptedTCPSender(encoder *gob.Encoder, conn *LocalConnection) *EncryptedTCPSender {
-	buffer := new(bytes.Buffer)
-	return &EncryptedTCPSender{
-		outerEncoder: encoder,
-		innerEncoder: gob.NewEncoder(buffer),
-		buffer:       buffer,
-		conn:         conn,
-		msgCount:     0}
+func NewLengthPrefixTCPSender(writer io.Writer) *LengthPrefixTCPSender {
+	return &LengthPrefixTCPSender{writer: writer}
+}
+
+func (sender *LengthPrefixTCPSender) Send(msg []byte) error {
+	l := len(msg)
+	if l > MaxTCPMsgSize {
+		return fmt.Errorf("outgoing message exceeds maximum size: %d > %d", l, MaxTCPMsgSize)
+	}
+	// We copy the message so we can send it in a single Write
+	// operation, thus making this thread-safe without locking.
+	prefixedMsg := make([]byte, 4+l)
+	binary.BigEndian.PutUint32(prefixedMsg, uint32(l))
+	copy(prefixedMsg[4:], msg)
+	_, err := sender.writer.Write(prefixedMsg)
+	return err
+}
+
+func NewEncryptedTCPSender(sender TCPSender, sessionKey *[32]byte, outbound bool) *EncryptedTCPSender {
+	return &EncryptedTCPSender{sender: sender, state: NewTCPCryptoState(sessionKey, outbound)}
 }
 
 func (sender *EncryptedTCPSender) Send(msg []byte) error {
-	nonce, err := GenerateRandomNonce()
-	if err != nil {
-		return err
-	}
 	sender.Lock()
 	defer sender.Unlock()
-	wrappedMsg := EncryptedTCPMessage{Number: sender.msgCount, Body: msg}
-	buffer := sender.buffer
-	buffer.Reset()
-	err = sender.innerEncoder.Encode(wrappedMsg)
-	if err != nil {
-		return err
-	}
-	sender.msgCount = sender.msgCount + 1
-	return sender.outerEncoder.Encode(
-		EncryptPrefixNonce(buffer.Bytes(), &nonce, sender.conn.SessionKey))
+	encodedMsg := secretbox.Seal(nil, msg, &sender.state.nonce, sender.state.sessionKey)
+	sender.state.advance()
+	return sender.sender.Send(encodedMsg)
 }
 
-// TCP Receivers
-
 type TCPReceiver interface {
-	Decode([]byte) ([]byte, error)
+	Receive() ([]byte, error)
 }
 
-type SimpleTCPReceiver struct {
+type GobTCPReceiver struct {
+	decoder *gob.Decoder
+}
+
+type LengthPrefixTCPReceiver struct {
+	reader io.Reader
 }
 
 type EncryptedTCPReceiver struct {
-	conn     *LocalConnection
-	decoder  *gob.Decoder
-	buffer   *bytes.Buffer
-	msgCount int
+	receiver TCPReceiver
+	state    *TCPCryptoState
 }
 
-func NewSimpleTCPReceiver() *SimpleTCPReceiver {
-	return &SimpleTCPReceiver{}
+func NewGobTCPReceiver(decoder *gob.Decoder) *GobTCPReceiver {
+	return &GobTCPReceiver{decoder: decoder}
 }
 
-func (receiver *SimpleTCPReceiver) Decode(msg []byte) ([]byte, error) {
-	return msg, nil
+func (receiver *GobTCPReceiver) Receive() ([]byte, error) {
+	var msg []byte
+	err := receiver.decoder.Decode(&msg)
+	return msg, err
 }
 
-func NewEncryptedTCPReceiver(conn *LocalConnection) *EncryptedTCPReceiver {
-	buffer := new(bytes.Buffer)
-	return &EncryptedTCPReceiver{
-		conn:     conn,
-		decoder:  gob.NewDecoder(buffer),
-		buffer:   buffer,
-		msgCount: 0}
+func NewLengthPrefixTCPReceiver(reader io.Reader) *LengthPrefixTCPReceiver {
+	return &LengthPrefixTCPReceiver{reader: reader}
 }
 
-func (receiver *EncryptedTCPReceiver) Decode(msg []byte) ([]byte, error) {
-	plaintext, success := DecryptPrefixNonce(msg, receiver.conn.SessionKey)
+func (receiver *LengthPrefixTCPReceiver) Receive() ([]byte, error) {
+	lenPrefix := make([]byte, 4)
+	if _, err := io.ReadFull(receiver.reader, lenPrefix); err != nil {
+		return nil, err
+	}
+	l := binary.BigEndian.Uint32(lenPrefix)
+	if l > MaxTCPMsgSize {
+		return nil, fmt.Errorf("incoming message exceeds maximum size: %d > %d", l, MaxTCPMsgSize)
+	}
+	msg := make([]byte, l)
+	_, err := io.ReadFull(receiver.reader, msg)
+	return msg, err
+}
+
+func NewEncryptedTCPReceiver(receiver TCPReceiver, sessionKey *[32]byte, outbound bool) *EncryptedTCPReceiver {
+	return &EncryptedTCPReceiver{receiver: receiver, state: NewTCPCryptoState(sessionKey, !outbound)}
+}
+
+func (receiver *EncryptedTCPReceiver) Receive() ([]byte, error) {
+	msg, err := receiver.receiver.Receive()
+	if err != nil {
+		return nil, err
+	}
+
+	decodedMsg, success := secretbox.Open(nil, msg, &receiver.state.nonce, receiver.state.sessionKey)
 	if !success {
-		return msg, fmt.Errorf("Unable to decrypt TCP msg")
+		return nil, fmt.Errorf("Unable to decrypt TCP msg")
 	}
-	receiver.buffer.Reset()
-	_, err := receiver.buffer.Write(plaintext)
-	if err != nil {
-		return msg, err
-	}
-	wrappedMsg := new(EncryptedTCPMessage)
-	err = receiver.decoder.Decode(wrappedMsg)
-	if err != nil {
-		return msg, err
-	}
-	if wrappedMsg.Number != receiver.msgCount {
-		return msg, fmt.Errorf("Received TCP message with wrong sequence number; possible replay attack")
-	}
-	receiver.msgCount = receiver.msgCount + 1
-	return wrappedMsg.Body, nil
+
+	receiver.state.advance()
+	return decodedMsg, nil
 }

router/ethernet_decoder.go

@@ -2,74 +2,66 @@ package router
 
 import (
 	"bytes"
-	"code.google.com/p/gopacket"
-	"code.google.com/p/gopacket/layers"
-	"log"
 	"net"
+
+	"github.com/google/gopacket"
+	"github.com/google/gopacket/layers"
 )
 
 type EthernetDecoder struct {
-	eth     layers.Ethernet
-	ip      layers.IPv4
+	Eth     layers.Ethernet
+	IP      layers.IPv4
 	decoded []gopacket.LayerType
 	parser  *gopacket.DecodingLayerParser
 }
 
 func NewEthernetDecoder() *EthernetDecoder {
 	dec := &EthernetDecoder{}
-	dec.parser = gopacket.NewDecodingLayerParser(layers.LayerTypeEthernet, &dec.eth, &dec.ip)
+	dec.parser = gopacket.NewDecodingLayerParser(layers.LayerTypeEthernet, &dec.Eth, &dec.IP)
 	return dec
 }
 
-func (dec *EthernetDecoder) DecodeLayers(data []byte) error {
-	return dec.parser.DecodeLayers(data, &dec.decoded)
+func (dec *EthernetDecoder) DecodeLayers(data []byte) {
+	// We intentionally discard the error return here, because it
+	// is normal for gopacket to return an error saying that it
+	// cannot decode a layer beyond the ones we specified when
+	// setting up the parser.
+	dec.parser.DecodeLayers(data, &dec.decoded)
 }
 
-func (dec *EthernetDecoder) CheckFrameTooBig(err error, sendFrame func([]byte) error) error {
-	if ftbe, ok := err.(FrameTooBigError); ok {
-		// we know: 1. ip is valid, 2. it was ip and DF was set
-		icmpFrame, err := dec.formICMPMTUPacket(ftbe.EPMTU)
-		if err != nil {
-			return err
-		}
-		log.Printf("Sending ICMP 3,4 (%v -> %v): PMTU= %v\n", dec.ip.DstIP, dec.ip.SrcIP, ftbe.EPMTU)
-		return sendFrame(icmpFrame)
-	} else {
-		return err
-	}
-}
-
-func (dec *EthernetDecoder) formICMPMTUPacket(mtu int) ([]byte, error) {
+func (dec *EthernetDecoder) sendICMPFragNeeded(mtu int, sendFrame func([]byte) error) error {
 	buf := gopacket.NewSerializeBuffer()
 	opts := gopacket.SerializeOptions{
 		FixLengths:       true,
 		ComputeChecksums: true}
-	ipHeaderSize := int(dec.ip.IHL) * 4 // IHL is the number of 32-byte words in the header
-	payload := gopacket.Payload(dec.ip.BaseLayer.Contents[:ipHeaderSize+8])
+	ipHeaderSize := int(dec.IP.IHL) * 4 // IHL is the number of 32-byte words in the header
+	payload := gopacket.Payload(dec.IP.BaseLayer.Contents[:ipHeaderSize+8])
 	err := gopacket.SerializeLayers(buf, opts,
 		&layers.Ethernet{
-			SrcMAC:       dec.eth.DstMAC,
-			DstMAC:       dec.eth.SrcMAC,
-			EthernetType: dec.eth.EthernetType},
+			SrcMAC:       dec.Eth.DstMAC,
+			DstMAC:       dec.Eth.SrcMAC,
+			EthernetType: dec.Eth.EthernetType},
 		&layers.IPv4{
 			Version:    4,
-			TOS:        dec.ip.TOS,
+			TOS:        dec.IP.TOS,
 			Id:         0,
 			Flags:      0,
 			FragOffset: 0,
 			TTL:        64,
 			Protocol:   layers.IPProtocolICMPv4,
-			DstIP:      dec.ip.SrcIP,
-			SrcIP:      dec.ip.DstIP},
+			DstIP:      dec.IP.SrcIP,
+			SrcIP:      dec.IP.DstIP},
 		&layers.ICMPv4{
 			TypeCode: 0x304,
 			Id:       0,
 			Seq:      uint16(mtu)},
 		&payload)
 	if err != nil {
-		return []byte{}, err
+		return err
 	}
-	return buf.Bytes(), nil
+
+	log.Printf("Sending ICMP 3,4 (%v -> %v): PMTU= %v", dec.IP.DstIP, dec.IP.SrcIP, mtu)
+	return sendFrame(buf.Bytes())
 }
 
 var (
@@ -79,10 +71,14 @@ var (
 )
 
 func (dec *EthernetDecoder) DropFrame() bool {
-	return bytes.Equal(stpMACPrefix, dec.eth.DstMAC[:len(stpMACPrefix)])
+	return bytes.Equal(stpMACPrefix, dec.Eth.DstMAC[:len(stpMACPrefix)])
 }
 
 func (dec *EthernetDecoder) IsSpecial() bool {
-	return dec.eth.Length == 0 && dec.eth.EthernetType == layers.EthernetTypeLLC &&
-		bytes.Equal(zeroMAC, dec.eth.SrcMAC) && bytes.Equal(zeroMAC, dec.eth.DstMAC)
+	return dec.Eth.Length == 0 && dec.Eth.EthernetType == layers.EthernetTypeLLC &&
+		bytes.Equal(zeroMAC, dec.Eth.SrcMAC) && bytes.Equal(zeroMAC, dec.Eth.DstMAC)
+}
+
+func (dec *EthernetDecoder) DF() bool {
+	return len(dec.decoded) == 2 && (dec.IP.Flags&layers.IPv4DontFragment != 0)
 }

router/forwarder.go

@@ -1,10 +1,11 @@
 package router
 
 import (
-	"code.google.com/p/gopacket"
-	"code.google.com/p/gopacket/layers"
 	"syscall"
 	"time"
+
+	"github.com/google/gopacket"
+	"github.com/google/gopacket/layers"
 )
 
 type ForwardedFrame struct {
@@ -18,7 +19,7 @@ type FrameTooBigError struct {
 }
 
 func (conn *LocalConnection) ensureForwarders() error {
-	if conn.forwardChan != nil || conn.forwardChanDF != nil {
+	if conn.forwarder != nil || conn.forwarderDF != nil {
 		return nil
 	}
 	udpSender := NewSimpleUDPSender(conn)
@@ -30,74 +31,65 @@ func (conn *LocalConnection) ensureForwarders() error {
 	usingPassword := conn.SessionKey != nil
 	var encryptor, encryptorDF Encryptor
 	if usingPassword {
-		encryptor = NewNaClEncryptor(conn.local.NameByte, conn, false)
-		encryptorDF = NewNaClEncryptor(conn.local.NameByte, conn, true)
+		encryptor = NewNaClEncryptor(conn.local.NameByte, conn.SessionKey, conn.outbound, false)
+		encryptorDF = NewNaClEncryptor(conn.local.NameByte, conn.SessionKey, conn.outbound, true)
 	} else {
 		encryptor = NewNonEncryptor(conn.local.NameByte)
 		encryptorDF = NewNonEncryptor(conn.local.NameByte)
 	}
 
-	var (
-		forwardChan   = make(chan *ForwardedFrame, ChannelSize)
-		forwardChanDF = make(chan *ForwardedFrame, ChannelSize)
-		stopForward   = make(chan interface{}, 0)
-		stopForwardDF = make(chan interface{}, 0)
-		verifyPMTU    = make(chan int, ChannelSize)
-	)
-	//NB: only forwarderDF can ever encounter EMSGSIZE errors, and
-	//thus perform PMTU verification
-	forwarder := NewForwarder(conn, forwardChan, stopForward, nil, encryptor, udpSender, DefaultPMTU)
-	forwarderDF := NewForwarder(conn, forwardChanDF, stopForwardDF, verifyPMTU, encryptorDF, udpSenderDF, DefaultPMTU)
+	forwarder := NewForwarder(conn, encryptor, udpSender, DefaultPMTU)
+	forwarderDF := NewForwarderDF(conn, encryptorDF, udpSenderDF, DefaultPMTU)
 
 	// Various fields in the conn struct are read by other processes,
 	// so we have to use locks.
 	conn.Lock()
-	conn.forwardChan = forwardChan
-	conn.forwardChanDF = forwardChanDF
-	conn.stopForward = stopForward
-	conn.stopForwardDF = stopForwardDF
-	conn.verifyPMTU = verifyPMTU
-	conn.effectivePMTU = forwarder.unverifiedPMTU
+	conn.forwarder = forwarder
+	conn.forwarderDF = forwarderDF
 	conn.Unlock()
 
-	forwarder.Start()
-	forwarderDF.Start()
-
 	return nil
 }
 
 func (conn *LocalConnection) stopForwarders() {
-	conn.Lock()
-	conn.forwardChan = nil
-	conn.forwardChanDF = nil
-	conn.Unlock()
-	// Now signal the forwarder loops to exit. They will drain the
-	// forwarder chans in order to unblock any router processes
-	// blocked on sending.
-	if conn.stopForward != nil {
-		conn.stopForward <- nil
-		conn.stopForwardDF <- nil
+	if conn.forwarder == nil || conn.forwarderDF == nil {
+		return
 	}
+	conn.forwarder.Shutdown()
+	conn.forwarderDF.Shutdown()
 }
 
-// Called from peer.Relay[Broadcast] which is itself invoked from
-// router (both UDP listener process and sniffer process). Also called
-// from connection's heartbeat process, and from the connection's TCP
-// receiver process.
-func (conn *LocalConnection) Forward(df bool, frame *ForwardedFrame, dec *EthernetDecoder) error {
+// Called from connection's actor process, and from the connection's
+// TCP receiver process.
+func (conn *LocalConnection) Send(df bool, frameBytes []byte) error {
+	frame := &ForwardedFrame{
+		srcPeer: conn.local,
+		dstPeer: conn.remote,
+		frame:   frameBytes}
+	return conn.forward(frame, nil, df)
+}
+
+// Called from LocalPeer.Relay[Broadcast] which is itself invoked from
+// router (both UDP listener process and sniffer process).
+func (conn *LocalConnection) Forward(frame *ForwardedFrame, dec *EthernetDecoder) error {
+	return conn.forward(frame, dec, dec != nil && dec.DF())
+}
+
+func (conn *LocalConnection) forward(frame *ForwardedFrame, dec *EthernetDecoder, df bool) error {
 	conn.RLock()
 	var (
-		forwardChan   = conn.forwardChan
-		forwardChanDF = conn.forwardChanDF
+		forwarder     = conn.forwarder
+		forwarderDF   = conn.forwarderDF
 		effectivePMTU = conn.effectivePMTU
 		stackFrag     = conn.stackFrag
 	)
 	conn.RUnlock()
 
-	if forwardChan == nil || forwardChanDF == nil {
-		conn.log("Cannot forward frame yet - awaiting contact")
+	if forwarder == nil || forwarderDF == nil {
+		conn.Log("Cannot forward frame yet - awaiting contact")
 		return nil
 	}
+
 	// We could use non-blocking channel sends here, i.e. drop frames
 	// on the floor when the forwarder is busy. This would allow our
 	// caller - the capturing loop in the router - to read frames more
@@ -110,29 +102,28 @@ func (conn *LocalConnection) Forward(df bool, frame *ForwardedFrame, dec *Ethern
 	// of our pipeline.
 	if df {
 		if !frameTooBig(frame, effectivePMTU) {
-			forwardChanDF <- frame
+			forwarderDF.Forward(frame)
 			return nil
 		}
 		return FrameTooBigError{EPMTU: effectivePMTU}
-	} else {
-		if stackFrag || dec == nil || len(dec.decoded) < 2 {
-			forwardChan <- frame
-			return nil
-		}
-		// Don't have trustworthy stack, so we're going to have to
-		// send it DF in any case.
-		if !frameTooBig(frame, effectivePMTU) {
-			forwardChanDF <- frame
-			return nil
-		}
-		conn.Router.LogFrame("Fragmenting", frame.frame, &dec.eth)
-		// We can't trust the stack to fragment, we have IP, and we
-		// have a frame that's too big for the MTU, so we have to
-		// fragment it ourself.
-		return fragment(dec.eth, dec.ip, effectivePMTU, frame, func(segFrame *ForwardedFrame) {
-			forwardChanDF <- segFrame
-		})
 	}
+
+	if stackFrag || dec == nil || len(dec.decoded) < 2 {
+		forwarder.Forward(frame)
+		return nil
+	}
+	// Don't have trustworthy stack, so we're going to have to
+	// send it DF in any case.
+	if !frameTooBig(frame, effectivePMTU) {
+		forwarderDF.Forward(frame)
+		return nil
+	}
+	// We can't trust the stack to fragment, we have IP, and we
+	// have a frame that's too big for the MTU, so we have to
+	// fragment it ourself.
+	return fragment(dec.Eth, dec.IP, effectivePMTU, frame, func(segFrame *ForwardedFrame) {
+		forwarderDF.Forward(segFrame)
+	})
 }
 
 func frameTooBig(frame *ForwardedFrame, effectivePMTU int) bool {
@@ -192,7 +183,7 @@ func fragment(eth layers.Ethernet, ip layers.IPv4, pmtu int, frame *ForwardedFra
 			return err
 		}
 		// make copies of the frame we received
-		var segFrame ForwardedFrame = *frame
+		segFrame := *frame
 		segFrame.frame = buf.Bytes()
 		forward(&segFrame)
 	}
@@ -202,52 +193,163 @@ func fragment(eth layers.Ethernet, ip layers.IPv4, pmtu int, frame *ForwardedFra
 // Forwarder
 
 type Forwarder struct {
-	conn            *LocalConnection
-	ch              <-chan *ForwardedFrame
-	stop            <-chan interface{}
+	conn             *LocalConnection
+	ch               chan<- *ForwardedFrame
+	finished         <-chan struct{}
+	enc              Encryptor
+	udpSender        UDPSender
+	maxPayload       int
+	processSendError func(error) error
+}
+
+func NewForwarder(conn *LocalConnection, enc Encryptor, udpSender UDPSender, pmtu int) *Forwarder {
+	ch := make(chan *ForwardedFrame, ChannelSize)
+	finished := make(chan struct{})
+	fwd := &Forwarder{
+		conn:             conn,
+		ch:               ch,
+		finished:         finished,
+		enc:              enc,
+		udpSender:        udpSender,
+		maxPayload:       pmtu - UDPOverhead,
+		processSendError: func(err error) error { return err }}
+	go fwd.run(ch, finished)
+	return fwd
+}
+
+func (fwd *Forwarder) Shutdown() {
+	fwd.ch <- nil
+}
+
+func (fwd *Forwarder) Forward(frame *ForwardedFrame) {
+	select {
+	case fwd.ch <- frame:
+	case <-fwd.finished:
+	}
+}
+
+func (fwd *Forwarder) run(ch <-chan *ForwardedFrame, finished chan<- struct{}) {
+	defer fwd.udpSender.Shutdown()
+	for {
+		if !fwd.accumulateAndSendFrames(ch, <-ch) {
+			close(finished)
+			return
+		}
+	}
+}
+
+func (fwd *Forwarder) effectiveOverhead() int {
+	return UDPOverhead + fwd.enc.PacketOverhead() + fwd.enc.FrameOverhead() + EthernetOverhead
+}
+
+// Drain the inbound channel of frames, aggregating them into larger
+// packets for efficient transmission.
+//
+// FIXME Depending on the golang scheduler, and the rate at which
+// franes get sent to the forwarder, we can be going around this loop
+// forever. That is bad since there may be other stuff for us to do,
+// i.e. the other branches in the run loop.
+func (fwd *Forwarder) accumulateAndSendFrames(ch <-chan *ForwardedFrame, frame *ForwardedFrame) bool {
+	if frame == nil {
+		return false
+	}
+	if !fwd.appendFrame(frame) {
+		fwd.logDrop(frame)
+		// [1] The buffer is empty at this point and therefore we must
+		// not flush it. The easiest way to accomplish that is simply
+		// by returning to the surrounding run loop.
+		return true
+	}
+	for {
+		select {
+		case frame = <-ch:
+			if frame == nil {
+				return false
+			}
+			if !fwd.appendFrame(frame) {
+				fwd.flush()
+				if !fwd.appendFrame(frame) {
+					fwd.logDrop(frame)
+					return true // see [1]
+				}
+			}
+		default:
+			fwd.flush()
+			return true
+		}
+	}
+}
+
+func (fwd *Forwarder) logDrop(frame *ForwardedFrame) {
+	fwd.conn.ErrorLog("Dropping too big frame during forwarding: frame len:", len(frame.frame), "; effective PMTU:", fwd.maxPayload+UDPOverhead-fwd.effectiveOverhead())
+}
+
+func (fwd *Forwarder) appendFrame(frame *ForwardedFrame) bool {
+	frameLen := len(frame.frame)
+	if fwd.enc.TotalLen()+fwd.enc.FrameOverhead()+frameLen > fwd.maxPayload {
+		return false
+	}
+	fwd.enc.AppendFrame(frame.srcPeer.NameByte, frame.dstPeer.NameByte, frame.frame)
+	return true
+}
+
+func (fwd *Forwarder) flush() {
+	msg, err := fwd.enc.Bytes()
+	if err != nil {
+		fwd.conn.Shutdown(err)
+	}
+	err = fwd.processSendError(fwd.udpSender.Send(msg))
+	if err != nil && PosixError(err) != syscall.ENOBUFS {
+		fwd.conn.Shutdown(err)
+	}
+}
+
+type ForwarderDF struct {
+	Forwarder
 	verifyPMTUTick  <-chan time.Time
-	verifyPMTU      <-chan int
+	verifyPMTU      chan<- int
 	pmtuVerifyCount uint
-	enc             Encryptor
-	udpSender       UDPSender
-	maxPayload      int
 	pmtuVerified    bool
 	highestGoodPMTU int
 	unverifiedPMTU  int
 	lowestBadPMTU   int
 }
 
-func NewForwarder(conn *LocalConnection, ch <-chan *ForwardedFrame, stop <-chan interface{}, verifyPMTU <-chan int, enc Encryptor, udpSender UDPSender, pmtu int) *Forwarder {
-	fwd := &Forwarder{
-		conn:       conn,
-		ch:         ch,
-		stop:       stop,
-		verifyPMTU: verifyPMTU,
-		enc:        enc,
-		udpSender:  udpSender}
+func NewForwarderDF(conn *LocalConnection, enc Encryptor, udpSender UDPSender, pmtu int) *ForwarderDF {
+	ch := make(chan *ForwardedFrame, ChannelSize)
+	finished := make(chan struct{})
+	verifyPMTU := make(chan int, ChannelSize)
+	fwd := &ForwarderDF{
+		Forwarder: Forwarder{
+			conn:       conn,
+			ch:         ch,
+			finished:   finished,
+			enc:        enc,
+			udpSender:  udpSender,
+			maxPayload: pmtu - UDPOverhead},
+		verifyPMTU: verifyPMTU}
+	fwd.Forwarder.processSendError = fwd.processSendError
 	fwd.unverifiedPMTU = pmtu - fwd.effectiveOverhead()
-	fwd.maxPayload = pmtu - UDPOverhead
+	conn.setEffectivePMTU(fwd.unverifiedPMTU)
+	go fwd.run(ch, finished, verifyPMTU)
 	return fwd
 }
 
-func (fwd *Forwarder) Start() {
-	go fwd.run()
+func (fwd *ForwarderDF) PMTUVerified(pmtu int) {
+	select {
+	case fwd.verifyPMTU <- pmtu:
+	case <-fwd.finished:
+	}
 }
 
-func (fwd *Forwarder) run() {
+func (fwd *ForwarderDF) run(ch <-chan *ForwardedFrame, finished chan<- struct{}, verifyPMTU <-chan int) {
 	defer fwd.udpSender.Shutdown()
-	var flushed, ok bool
-	var frame *ForwardedFrame
 	for {
-		flushed = false
 		select {
-		case <-fwd.stop:
-			fwd.drain()
-			return
 		case <-fwd.verifyPMTUTick:
-			// We only do this case here when we know the buffers are
-			// all empty so that we don't risk appending verify-frames
-			// to other data.
+			// We only do this case here when we know the
+			// buffers are all empty so that we don't risk
+			// appending verify-frames to other data.
 			fwd.verifyPMTUTick = nil
 			if fwd.pmtuVerified {
 				continue
@@ -256,12 +358,12 @@ func (fwd *Forwarder) run() {
 				fwd.pmtuVerifyCount--
 				fwd.attemptVerifyEffectivePMTU()
 			} else {
-				// we've exceeded the verification attempts of the
-				// unverifiedPMTU
+				// we've exceeded the verification
+				// attempts of the unverifiedPMTU
 				fwd.lowestBadPMTU = fwd.unverifiedPMTU
 				fwd.verifyEffectivePMTU((fwd.highestGoodPMTU + fwd.lowestBadPMTU) / 2)
 			}
-		case epmtu := <-fwd.verifyPMTU:
+		case epmtu := <-verifyPMTU:
 			if fwd.pmtuVerified || epmtu != fwd.unverifiedPMTU {
 				continue
 			}
@@ -272,101 +374,46 @@ func (fwd *Forwarder) run() {
 				fwd.pmtuVerified = true
 				fwd.maxPayload = epmtu + fwd.effectiveOverhead() - UDPOverhead
 				fwd.conn.setEffectivePMTU(epmtu)
-				fwd.conn.log("Effective PMTU verified at", epmtu)
+				fwd.conn.Log("Effective PMTU verified at", epmtu)
 			}
-		case frame = <-fwd.ch:
-			if !fwd.appendFrame(frame) {
-				fwd.logDrop(frame)
-				continue
-			}
-			for !flushed {
-				select {
-				case frame, ok = <-fwd.ch:
-					if !ok {
-						return
-					}
-					if !fwd.appendFrame(frame) {
-						fwd.flush()
-						if !fwd.appendFrame(frame) {
-							fwd.logDrop(frame)
-							flushed = true
-						}
-					}
-				default:
-					fwd.flush()
-					flushed = true
-				}
+		case frame := <-ch:
+			if !fwd.accumulateAndSendFrames(ch, frame) {
+				close(finished)
+				return
 			}
 		}
 	}
 }
 
-func (fwd *Forwarder) effectiveOverhead() int {
-	return UDPOverhead + fwd.enc.PacketOverhead() + fwd.enc.FrameOverhead() + EthernetOverhead
-}
-
-func (fwd *Forwarder) verifyEffectivePMTU(newUnverifiedPMTU int) {
+func (fwd *ForwarderDF) verifyEffectivePMTU(newUnverifiedPMTU int) {
 	fwd.unverifiedPMTU = newUnverifiedPMTU
 	fwd.pmtuVerifyCount = PMTUVerifyAttempts
 	fwd.attemptVerifyEffectivePMTU()
 }
 
-func (fwd *Forwarder) attemptVerifyEffectivePMTU() {
-	pmtuVerifyFrame := &ForwardedFrame{
-		srcPeer: fwd.conn.local,
-		dstPeer: fwd.conn.remote,
-		frame:   make([]byte, fwd.unverifiedPMTU+EthernetOverhead)}
-	fwd.enc.AppendFrame(pmtuVerifyFrame)
+func (fwd *ForwarderDF) attemptVerifyEffectivePMTU() {
+	fwd.enc.AppendFrame(fwd.conn.local.NameByte, fwd.conn.remote.NameByte,
+		make([]byte, fwd.unverifiedPMTU+EthernetOverhead))
 	fwd.flush()
 	if fwd.verifyPMTUTick == nil {
 		fwd.verifyPMTUTick = time.After(PMTUVerifyTimeout << (PMTUVerifyAttempts - fwd.pmtuVerifyCount))
 	}
 }
 
-func (fwd *Forwarder) appendFrame(frame *ForwardedFrame) bool {
-	frameLen := len(frame.frame)
-	if fwd.enc.TotalLen()+fwd.enc.FrameOverhead()+frameLen > fwd.maxPayload {
-		return false
-	}
-	fwd.enc.AppendFrame(frame)
-	return true
-}
-
-func (fwd *Forwarder) flush() {
-	err := fwd.udpSender.Send(fwd.enc.Bytes())
-	if err != nil {
-		if mtbe, ok := err.(MsgTooBigError); ok {
-			newUnverifiedPMTU := mtbe.PMTU - fwd.effectiveOverhead()
-			if newUnverifiedPMTU >= fwd.unverifiedPMTU {
-				return
-			}
+func (fwd *ForwarderDF) processSendError(err error) error {
+	if mtbe, ok := err.(MsgTooBigError); ok {
+		newUnverifiedPMTU := mtbe.PMTU - fwd.effectiveOverhead()
+		if newUnverifiedPMTU < fwd.unverifiedPMTU {
 			fwd.pmtuVerified = false
 			fwd.maxPayload = mtbe.PMTU - UDPOverhead
 			fwd.highestGoodPMTU = 8
 			fwd.lowestBadPMTU = newUnverifiedPMTU + 1
 			fwd.conn.setEffectivePMTU(newUnverifiedPMTU)
 			fwd.verifyEffectivePMTU(newUnverifiedPMTU)
-		} else if PosixError(err) == syscall.ENOBUFS {
-			// TODO handle this better
-		} else {
-			fwd.conn.Shutdown(err)
 		}
-	}
-}
 
-func (fwd *Forwarder) drain() {
-	// We want to drain before exiting otherwise we could get the
-	// packet sniffer or udp listener blocked on sending to a full
-	// chan
-	for {
-		select {
-		case <-fwd.ch:
-		default:
-			return
-		}
+		return nil
 	}
-}
 
-func (fwd *Forwarder) logDrop(frame *ForwardedFrame) {
-	fwd.conn.log("Dropping too big frame during forwarding: frame len:", len(frame.frame), "; effective PMTU:", fwd.maxPayload+UDPOverhead-fwd.effectiveOverhead())
+	return err
 }

router/gossip.go

@@ -1,162 +1,171 @@
 package router
 
 import (
-	"bytes"
-	"encoding/gob"
 	"fmt"
-	"log"
-	"time"
 )
 
-const GossipInterval = 30 * time.Second
+type GossipData interface {
+	Encode() [][]byte
+	Merge(GossipData)
+}
 
 type Gossip interface {
 	// specific message from one peer to another
 	// intermediate peers relay it using unicast topology.
-	GossipUnicast(dstPeerName PeerName, buf []byte) error
-	// send a message to every peer, relayed using broadcast topology.
-	GossipBroadcast(buf []byte) error
+	GossipUnicast(dstPeerName PeerName, msg []byte) error
+	// send gossip to every peer, relayed using broadcast topology.
+	GossipBroadcast(update GossipData) error
 }
 
 type Gossiper interface {
 	OnGossipUnicast(sender PeerName, msg []byte) error
-	OnGossipBroadcast(msg []byte) error
-	// Return state of everything we know; gets called periodically
-	Gossip() []byte
-	// merge in state and return "everything new I've just learnt",
-	// or nil if nothing in the received message was new
-	OnGossip(buf []byte) ([]byte, error)
+	// merge received data into state and return a representation of
+	// the received data, for further propagation
+	OnGossipBroadcast(sender PeerName, update []byte) (GossipData, error)
+	// return state of everything we know; gets called periodically
+	Gossip() GossipData
+	// merge received data into state and return "everything new I've
+	// just learnt", or nil if nothing in the received data was new
+	OnGossip(update []byte) (GossipData, error)
 }
 
-type GossipChannel struct {
-	ourself  *LocalPeer
-	name     string
-	hash     uint32
-	gossiper Gossiper
+// Accumulates GossipData that needs to be sent to one destination,
+// and sends it when possible.
+type GossipSender struct {
+	send func(GossipData)
+	cell chan GossipData
+	// for testing
+	sent    bool
+	flushch chan chan bool
 }
 
+func NewGossipSender(send func(GossipData)) *GossipSender {
+	cell := make(chan GossipData, 1)
+	flushch := make(chan chan bool)
+	sender := &GossipSender{
+		send:    send,
+		cell:    cell,
+		flushch: flushch,
+	}
+	go sender.run()
+	return sender
+}
+
+func (sender *GossipSender) run() {
+	for {
+		select {
+		case pending := <-sender.cell:
+			if pending == nil { // receive zero value when chan is closed
+				return
+			}
+			sender.send(pending)
+			sender.sent = true
+		case ch := <-sender.flushch:
+			// send anything pending, then reply back whether we sent
+			// anything since previous flush
+			select {
+			case pending := <-sender.cell:
+				sender.send(pending)
+				sender.sent = true
+			default:
+			}
+			ch <- sender.sent
+			sender.sent = false
+		}
+	}
+}
+
+func (sender *GossipSender) Send(data GossipData) {
+	// NB: this must not be invoked concurrently
+	select {
+	case pending := <-sender.cell:
+		pending.Merge(data)
+		sender.cell <- pending
+	default:
+		sender.cell <- data
+	}
+}
+
+func (sender *GossipSender) Stop() {
+	close(sender.cell)
+}
+
+type GossipChannels map[string]*GossipChannel
+
 func (router *Router) NewGossip(channelName string, g Gossiper) Gossip {
-	channelHash := hash(channelName)
-	channel := &GossipChannel{router.Ourself, channelName, channelHash, g}
-	router.GossipChannels[channelHash] = channel
+	channel := NewGossipChannel(channelName, router.Ourself, router.Routes, g)
+	router.gossipLock.Lock()
+	defer router.gossipLock.Unlock()
+	if _, found := router.gossipChannels[channelName]; found {
+		checkFatal(fmt.Errorf("[gossip] duplicate channel %s", channelName))
+	}
+	router.gossipChannels[channelName] = channel
 	return channel
 }
 
+func (router *Router) gossipChannel(channelName string) *GossipChannel {
+	router.gossipLock.RLock()
+	channel, found := router.gossipChannels[channelName]
+	router.gossipLock.RUnlock()
+	if found {
+		return channel
+	}
+	router.gossipLock.Lock()
+	defer router.gossipLock.Unlock()
+	if channel, found = router.gossipChannels[channelName]; found {
+		return channel
+	}
+	channel = NewGossipChannel(channelName, router.Ourself, router.Routes, &surrogateGossiper)
+	channel.log("created surrogate channel")
+	router.gossipChannels[channelName] = channel
+	return channel
+}
+
+func (router *Router) gossipChannelSet() map[*GossipChannel]struct{} {
+	channels := make(map[*GossipChannel]struct{})
+	router.gossipLock.RLock()
+	defer router.gossipLock.RUnlock()
+	for _, channel := range router.gossipChannels {
+		channels[channel] = void
+	}
+	return channels
+}
+
 func (router *Router) SendAllGossip() {
-	for _, channel := range router.GossipChannels {
-		channel.SendGossipMsg(channel.gossiper.Gossip())
+	for channel := range router.gossipChannelSet() {
+		if gossip := channel.gossiper.Gossip(); gossip != nil {
+			channel.Send(router.Ourself.Name, gossip)
+		}
 	}
 }
 
 func (router *Router) SendAllGossipDown(conn Connection) {
-	for _, channel := range router.GossipChannels {
-		protocolMsg := channel.gossipMsg(channel.gossiper.Gossip())
-		conn.(ProtocolSender).SendProtocolMsg(protocolMsg)
-	}
-}
-
-func (router *Router) handleGossip(payload []byte, onok func(*GossipChannel, PeerName, []byte, *gob.Decoder) error) error {
-	decoder := gob.NewDecoder(bytes.NewReader(payload))
-	var channelHash uint32
-	if err := decoder.Decode(&channelHash); err != nil {
-		return err
-	}
-	channel, found := router.GossipChannels[channelHash]
-	if !found {
-		return fmt.Errorf("[gossip] received unknown channel with hash %v", channelHash)
-	}
-	var srcName PeerName
-	if err := decoder.Decode(&srcName); err != nil {
-		return err
-	}
-	if err := onok(channel, srcName, payload, decoder); err != nil {
-		return err
-	}
-	return nil
-}
-
-func deliverGossipUnicast(channel *GossipChannel, srcName PeerName, origPayload []byte, dec *gob.Decoder) error {
-	var destName PeerName
-	if err := dec.Decode(&destName); err != nil {
-		return err
-	}
-	if channel.ourself.Name == destName {
-		var payload []byte
-		if err := dec.Decode(&payload); err != nil {
-			return err
-		}
-		return channel.gossiper.OnGossipUnicast(srcName, payload)
-	} else {
-		return channel.relayGossipUnicast(destName, origPayload)
-	}
-}
-
-func deliverGossipBroadcast(channel *GossipChannel, srcName PeerName, origPayload []byte, dec *gob.Decoder) error {
-	var payload []byte
-	if err := dec.Decode(&payload); err != nil {
-		return err
-	}
-	if err := channel.gossiper.OnGossipBroadcast(payload); err != nil {
-		return err
-	}
-	return channel.relayGossipBroadcast(srcName, origPayload)
-}
-
-func deliverGossip(channel *GossipChannel, srcName PeerName, _ []byte, dec *gob.Decoder) error {
-	var payload []byte
-	if err := dec.Decode(&payload); err != nil {
-		return err
-	}
-	if newBuf, err := channel.gossiper.OnGossip(payload); err != nil {
-		return err
-	} else if newBuf != nil {
-		channel.SendGossipMsg(newBuf)
-	}
-	return nil
-}
-
-func (c *GossipChannel) SendGossipMsg(buf []byte) {
-	protocolMsg := c.gossipMsg(buf)
-	c.ourself.ForEachConnection(func(_ PeerName, conn Connection) {
-		conn.(ProtocolSender).SendProtocolMsg(protocolMsg)
-	})
-}
-
-func (c *GossipChannel) gossipMsg(buf []byte) ProtocolMsg {
-	return ProtocolMsg{ProtocolGossip, GobEncode(c.hash, c.ourself.Name, buf)}
-}
-
-func (c *GossipChannel) GossipUnicast(dstPeerName PeerName, buf []byte) error {
-	return c.relayGossipUnicast(dstPeerName, GobEncode(c.hash, c.ourself.Name, dstPeerName, buf))
-}
-
-func (c *GossipChannel) GossipBroadcast(buf []byte) error {
-	return c.relayGossipBroadcast(c.ourself.Name, GobEncode(c.hash, c.ourself.Name, buf))
-}
-
-func (c *GossipChannel) relayGossipUnicast(dstPeerName PeerName, msg []byte) error {
-	if relayPeerName, found := c.ourself.Router.Routes.Unicast(dstPeerName); !found {
-		c.log("unknown relay destination:", dstPeerName)
-	} else if conn, found := c.ourself.ConnectionTo(relayPeerName); !found {
-		c.log("unable to find connection to relay peer", relayPeerName)
-	} else {
-		conn.(ProtocolSender).SendProtocolMsg(ProtocolMsg{ProtocolGossipUnicast, msg})
-	}
-	return nil
-}
-
-func (c *GossipChannel) relayGossipBroadcast(srcName PeerName, msg []byte) error {
-	if srcPeer, found := c.ourself.Router.Peers.Fetch(srcName); !found {
-		c.log("unable to relay broadcast from unknown peer", srcName)
-	} else {
-		protocolMsg := ProtocolMsg{ProtocolGossipBroadcast, msg}
-		for _, conn := range c.ourself.NextBroadcastHops(srcPeer) {
-			conn.SendProtocolMsg(protocolMsg)
+	for channel := range router.gossipChannelSet() {
+		if gossip := channel.gossiper.Gossip(); gossip != nil {
+			channel.SendDown(conn, channel.gossiper.Gossip())
 		}
 	}
-	return nil
 }
 
-func (c *GossipChannel) log(args ...interface{}) {
-	log.Println(append(append([]interface{}{}, "[gossip "+c.name+"]:"), args...)...)
+// for testing
+
+func (router *Router) sendPendingGossip() bool {
+	sentSomething := false
+	for channel := range router.gossipChannelSet() {
+		channel.Lock()
+		for _, sender := range channel.senders {
+			sentSomething = sender.flush() || sentSomething
+		}
+		for _, sender := range channel.broadcasters {
+			sentSomething = sender.flush() || sentSomething
+		}
+		channel.Unlock()
+	}
+	return sentSomething
+}
+
+func (sender *GossipSender) flush() bool {
+	ch := make(chan bool)
+	sender.flushch <- ch
+	return <-ch
 }

router/gossip_channel.go

@@ -0,0 +1,234 @@
+package router
+
+import (
+	"bytes"
+	"encoding/gob"
+	"fmt"
+	"sync"
+)
+
+type GossipChannel struct {
+	sync.Mutex
+	name         string
+	ourself      *LocalPeer
+	routes       *Routes
+	gossiper     Gossiper
+	senders      connectionSenders
+	broadcasters peerSenders
+}
+
+type connectionSenders map[Connection]*GossipSender
+type peerSenders map[PeerName]*GossipSender
+
+func NewGossipChannel(channelName string, ourself *LocalPeer, routes *Routes, g Gossiper) *GossipChannel {
+	return &GossipChannel{
+		name:         channelName,
+		ourself:      ourself,
+		routes:       routes,
+		gossiper:     g,
+		senders:      make(connectionSenders),
+		broadcasters: make(peerSenders)}
+}
+
+func (router *Router) handleGossip(tag ProtocolTag, payload []byte) error {
+	decoder := gob.NewDecoder(bytes.NewReader(payload))
+	var channelName string
+	if err := decoder.Decode(&channelName); err != nil {
+		return err
+	}
+	channel := router.gossipChannel(channelName)
+	var srcName PeerName
+	if err := decoder.Decode(&srcName); err != nil {
+		return err
+	}
+	switch tag {
+	case ProtocolGossipUnicast:
+		return channel.deliverUnicast(srcName, payload, decoder)
+	case ProtocolGossipBroadcast:
+		return channel.deliverBroadcast(srcName, payload, decoder)
+	case ProtocolGossip:
+		return channel.deliver(srcName, payload, decoder)
+	}
+	return nil
+}
+
+func (c *GossipChannel) deliverUnicast(srcName PeerName, origPayload []byte, dec *gob.Decoder) error {
+	var destName PeerName
+	if err := dec.Decode(&destName); err != nil {
+		return err
+	}
+	if c.ourself.Name != destName {
+		if err := c.relayUnicast(destName, origPayload); err != nil {
+			// just log errors from relayUnicast; a problem between us and destination
+			// is not enough reason to break the connection from the source
+			c.log(err)
+		}
+		return nil
+	}
+	var payload []byte
+	if err := dec.Decode(&payload); err != nil {
+		return err
+	}
+	return c.gossiper.OnGossipUnicast(srcName, payload)
+}
+
+func (c *GossipChannel) deliverBroadcast(srcName PeerName, _ []byte, dec *gob.Decoder) error {
+	var payload []byte
+	if err := dec.Decode(&payload); err != nil {
+		return err
+	}
+	data, err := c.gossiper.OnGossipBroadcast(srcName, payload)
+	if err != nil || data == nil {
+		return err
+	}
+	return c.relayBroadcast(srcName, data)
+}
+
+func (c *GossipChannel) deliver(srcName PeerName, _ []byte, dec *gob.Decoder) error {
+	var payload []byte
+	if err := dec.Decode(&payload); err != nil {
+		return err
+	}
+	if data, err := c.gossiper.OnGossip(payload); err != nil {
+		return err
+	} else if data != nil {
+		c.Send(srcName, data)
+	}
+	return nil
+}
+
+func (c *GossipChannel) Send(srcName PeerName, data GossipData) {
+	// do this outside the lock below so we avoid lock nesting
+	c.routes.EnsureRecalculated()
+	selectedConnections := make(ConnectionSet)
+	for name := range c.routes.RandomNeighbours(srcName) {
+		if conn, found := c.ourself.ConnectionTo(name); found {
+			selectedConnections[conn] = void
+		}
+	}
+	if len(selectedConnections) == 0 {
+		return
+	}
+	connections := c.ourself.Connections()
+	c.Lock()
+	defer c.Unlock()
+	c.gcSenders(connections)
+	for conn := range selectedConnections {
+		c.sendDown(conn, data)
+	}
+}
+
+func (c *GossipChannel) SendDown(conn Connection, data GossipData) {
+	connections := c.ourself.Connections()
+	c.Lock()
+	defer c.Unlock()
+	c.gcSenders(connections)
+	c.sendDown(conn, data)
+}
+
+// GC - randomly (courtesy of go's map iterator) pick some existing
+// senders and stop&remove them if the associated connection is no
+// longer active.  We stop as soon as we encounter a valid entry; the
+// idea being that when there is little or no garbage then this
+// executes close to O(1)[1], whereas when there is lots of garbage we
+// remove it quickly.
+//
+// [1] TODO Unfortunately, due to the desire to avoid nested locks,
+// instead of simply invoking LocalPeer.ConnectionTo(name), we pass in
+// the result of LocalPeer.Connections(). That is O(n_our_connections)
+// at best.
+func (c *GossipChannel) gcSenders(connections ConnectionSet) {
+	for conn, sender := range c.senders {
+		if _, found := connections[conn]; !found {
+			delete(c.senders, conn)
+			sender.Stop()
+		} else {
+			break
+		}
+	}
+}
+
+func (c *GossipChannel) sendDown(conn Connection, data GossipData) {
+	sender, found := c.senders[conn]
+	if !found {
+		sender = NewGossipSender(func(pending GossipData) {
+			for _, msg := range pending.Encode() {
+				protocolMsg := ProtocolMsg{ProtocolGossip, GobEncode(c.name, c.ourself.Name, msg)}
+				conn.(ProtocolSender).SendProtocolMsg(protocolMsg)
+			}
+		})
+		c.senders[conn] = sender
+	}
+	sender.Send(data)
+}
+
+func (c *GossipChannel) GossipUnicast(dstPeerName PeerName, msg []byte) error {
+	return c.relayUnicast(dstPeerName, GobEncode(c.name, c.ourself.Name, dstPeerName, msg))
+}
+
+func (c *GossipChannel) GossipBroadcast(update GossipData) error {
+	return c.relayBroadcast(c.ourself.Name, update)
+}
+
+func (c *GossipChannel) relayUnicast(dstPeerName PeerName, buf []byte) (err error) {
+	if relayPeerName, found := c.routes.UnicastAll(dstPeerName); !found {
+		err = fmt.Errorf("unknown relay destination: %s", dstPeerName)
+	} else if conn, found := c.ourself.ConnectionTo(relayPeerName); !found {
+		err = fmt.Errorf("unable to find connection to relay peer %s", relayPeerName)
+	} else {
+		conn.(ProtocolSender).SendProtocolMsg(ProtocolMsg{ProtocolGossipUnicast, buf})
+	}
+	return err
+}
+
+func (c *GossipChannel) relayBroadcast(srcName PeerName, update GossipData) error {
+	names := c.routes.PeerNames() // do this outside the lock so they don't nest
+	c.Lock()
+	defer c.Unlock()
+	// GC - randomly (courtesy of go's map iterator) pick some
+	// existing broadcasters and stop&remove them if their source peer
+	// is unknown. We stop as soon as we encounter a valid entry; the
+	// idea being that when there is little or no garbage then this
+	// executes close to O(1)[1], whereas when there is lots of
+	// garbage we remove it quickly.
+	//
+	// [1] TODO Unfortunately, due to the desire to avoid nested
+	// locks, instead of simply invoking Peers.Fetch(name) below, we
+	// have that Peers.Names() invocation above. That is O(n_peers) at
+	// best.
+	for name, broadcaster := range c.broadcasters {
+		if _, found := names[name]; !found {
+			delete(c.broadcasters, name)
+			broadcaster.Stop()
+		} else {
+			break
+		}
+	}
+	broadcaster, found := c.broadcasters[srcName]
+	if !found {
+		broadcaster = NewGossipSender(func(pending GossipData) { c.sendBroadcast(srcName, pending) })
+		c.broadcasters[srcName] = broadcaster
+	}
+	broadcaster.Send(update)
+	return nil
+}
+
+func (c *GossipChannel) sendBroadcast(srcName PeerName, update GossipData) {
+	c.routes.EnsureRecalculated()
+	nextHops := c.routes.BroadcastAll(srcName)
+	if len(nextHops) == 0 {
+		return
+	}
+	connections := c.ourself.ConnectionsTo(nextHops)
+	for _, msg := range update.Encode() {
+		protocolMsg := ProtocolMsg{ProtocolGossipBroadcast, GobEncode(c.name, srcName, msg)}
+		// FIXME a single blocked connection can stall us
+		for _, conn := range connections {
+			conn.(ProtocolSender).SendProtocolMsg(protocolMsg)
+		}
+	}
+}
+
+func (c *GossipChannel) log(args ...interface{}) {
+	log.Println(append(append([]interface{}{}, "[gossip "+c.name+"]:"), args...)...)
+}