Add release v1.9.2

Ignore modprobe errors in weave-kube/launch.sh

.ackrc

@@ -0,0 +1,2 @@
+--ignore-dir=vendor
+--ignore-dir=.pkg

.gitignore

@@ -25,25 +25,48 @@ _testmain.go
 *.prof
 profile.cov
 coverage.html
+.pkg
 
 # Emacs backup files
 *~
 
+# Vim backup files
+*.swp
+
 # Project specific
-weaver/weaver
-weavedns/weavedns
-weaveproxy/weaveproxy
-sigproxy/sigproxy
-weavewait/weavewait
-tools/bin
-tools/build
+prog/weaver/weaver
+prog/weavedns/weavedns
+prog/weavehosts/weavehosts
+prog/weaveproxy/weaveproxy
+prog/sigproxy/sigproxy
+prog/weavewait/weavewait
+prog/weavewait/weavewait_noop
+prog/weavewait/weavewait_nomcast
+prog/weaveutil/weaveutil
+prog/*/Dockerfile.weaveworks
+prog/kube-peers/kube-peers
+prog/weave-kube/kube-peers
+prog/weave-npc/weave-npc
+prog/plugin/plugin
+testing/cover/cover
+testing/runner/runner
 releases
-weave.tar
-weavedns.tar
-weaveexec.tar
-weaveexec/weave
-weaveexec/weaveproxy
-weaveexec/weavewait
-weaveexec/sigproxy
-weaveexec/docker*.tgz
+.*.uptodate
+weave*.tar.gz
+prog/weaveexec/weave
+prog/weaveexec/weavehosts
+prog/weaveexec/weaveproxy
+prog/weaveexec/weavewait
+prog/weaveexec/weavewait_noop
+prog/weaveexec/weavewait_nomcast
+prog/weaveexec/sigproxy
+prog/weaveexec/weaveutil
+prog/weaveexec/docker*
 Vagrantfile.local
+test/tls/tls
+test/tls/*.pem
+test/coverage
+test/coverage.*
+*qemu-*-static
+terraform.tfstate
+terraform.tfstate.backup

.gitmodules

@@ -0,0 +1,126 @@
+[submodule "tools"]
+	path = tools
+	url = https://github.com/weaveworks/build-tools
+[submodule "vendor/github.com/vishvananda/netlink"]
+	path = vendor/github.com/vishvananda/netlink
+	url = https://github.com/vishvananda/netlink.git
+[submodule "vendor/github.com/gorilla/mux"]
+	path = vendor/github.com/gorilla/mux
+	url = https://github.com/gorilla/mux.git
+[submodule "vendor/github.com/gorilla/context"]
+	path = vendor/github.com/gorilla/context
+	url = https://github.com/gorilla/context.git
+[submodule "vendor/github.com/google/gopacket"]
+	path = vendor/github.com/google/gopacket
+	url = https://github.com/google/gopacket.git
+[submodule "vendor/github.com/weaveworks/go-odp"]
+	path = vendor/github.com/weaveworks/go-odp
+	url = https://github.com/weaveworks/go-odp.git
+[submodule "vendor/github.com/opencontainers/runc"]
+	path = vendor/github.com/opencontainers/runc
+	url = https://github.com/opencontainers/runc.git
+[submodule "vendor/github.com/fsouza/go-dockerclient"]
+	path = vendor/github.com/fsouza/go-dockerclient
+	url = https://github.com/fsouza/go-dockerclient.git
+[submodule "vendor/github.com/docker/libnetwork"]
+	path = vendor/github.com/docker/libnetwork
+	url = https://github.com/docker/libnetwork.git
+[submodule "vendor/github.com/docker/docker"]
+	path = vendor/github.com/docker/docker
+	url = https://github.com/docker/docker.git
+[submodule "vendor/github.com/Sirupsen/logrus"]
+	path = vendor/github.com/Sirupsen/logrus
+	url = https://github.com/Sirupsen/logrus.git
+[submodule "vendor/github.com/andybalholm/go-bit"]
+	path = vendor/github.com/andybalholm/go-bit
+	url = https://github.com/andybalholm/go-bit.git
+[submodule "vendor/github.com/miekg/dns"]
+	path = vendor/github.com/miekg/dns
+	url = https://github.com/miekg/dns.git
+[submodule "vendor/github.com/stretchr/testify"]
+	path = vendor/github.com/stretchr/testify
+	url = https://github.com/stretchr/testify.git
+[submodule "vendor/golang.org/x/crypto"]
+	path = vendor/golang.org/x/crypto
+	url = https://github.com/golang/crypto.git
+[submodule "vendor/github.com/docker/machine"]
+	path = vendor/github.com/docker/machine
+	url = https://github.com/docker/machine.git
+[submodule "vendor/github.com/weaveworks/mesh"]
+	path = vendor/github.com/weaveworks/mesh
+	url = https://github.com/weaveworks/mesh
+[submodule "vendor/github.com/vishvananda/netns"]
+	path = vendor/github.com/vishvananda/netns
+	url = https://github.com/vishvananda/netns.git
+[submodule "vendor/github.com/boltdb/bolt"]
+	path = vendor/github.com/boltdb/bolt
+	url = https://github.com/boltdb/bolt
+[submodule "vendor/github.com/weaveworks/go-checkpoint"]
+	path = vendor/github.com/weaveworks/go-checkpoint
+	url = https://github.com/weaveworks/go-checkpoint
+[submodule "vendor/github.com/hashicorp/go-cleanhttp"]
+	path = vendor/github.com/hashicorp/go-cleanhttp
+	url = http://github.com/hashicorp/go-cleanhttp
+[submodule "vendor/github.com/appc/cni"]
+	path = vendor/github.com/appc/cni
+	url = https://github.com/appc/cni
+[submodule "vendor/github.com/coreos/go-iptables"]
+	path = vendor/github.com/coreos/go-iptables
+	url = https://github.com/coreos/go-iptables
+[submodule "vendor/github.com/pkg/profile"]
+	path = vendor/github.com/pkg/profile
+	url = https://github.com/pkg/profile
+[submodule "vendor/github.com/j-keck/arping"]
+	path = vendor/github.com/j-keck/arping
+	url = https://github.com/j-keck/arping
+[submodule "vendor/github.com/aws/aws-sdk-go"]
+	path = vendor/github.com/aws/aws-sdk-go
+	url = https://github.com/aws/aws-sdk-go
+[submodule "vendor/golang.org/x/sys"]
+	path = vendor/golang.org/x/sys
+	url = https://go.googlesource.com/sys
+[submodule "vendor/github.com/beorn7/perks"]
+	path = vendor/github.com/beorn7/perks
+	url = https://github.com/beorn7/perks
+[submodule "vendor/github.com/prometheus/procfs"]
+	path = vendor/github.com/prometheus/procfs
+	url = https://github.com/prometheus/procfs
+[submodule "vendor/github.com/prometheus/client_golang"]
+	path = vendor/github.com/prometheus/client_golang
+	url = https://github.com/prometheus/client_golang
+[submodule "vendor/github.com/prometheus/client_model"]
+	path = vendor/github.com/prometheus/client_model
+	url = https://github.com/prometheus/client_model
+[submodule "vendor/github.com/prometheus/common"]
+	path = vendor/github.com/prometheus/common
+	url = https://github.com/prometheus/common
+[submodule "vendor/github.com/golang/protobuf"]
+	path = vendor/github.com/golang/protobuf
+	url = https://github.com/golang/protobuf
+[submodule "vendor/github.com/matttproud/golang_protobuf_extensions"]
+	path = vendor/github.com/matttproud/golang_protobuf_extensions
+	url = https://github.com/matttproud/golang_protobuf_extensions
+[submodule "vendor/k8s.io/client-go"]
+	path = vendor/k8s.io/client-go
+	url = https://github.com/kubernetes/client-go
+[submodule "vendor/github.com/pkg/errors"]
+	path = vendor/github.com/pkg/errors
+	url = https://github.com/pkg/errors
+[submodule "vendor/github.com/spf13/cobra"]
+	path = vendor/github.com/spf13/cobra
+	url = https://github.com/spf13/cobra
+[submodule "vendor/github.com/spf13/plag"]
+	path = vendor/github.com/spf13/plag
+	url = https://github.com/spf13/pflag
+[submodule "vendor/github.com/spf13/pflag"]
+	path = vendor/github.com/spf13/pflag
+	url = https://github.com/spf13/pflag
+[submodule "vendor/github.com/mgutz/ansi"]
+	path = vendor/github.com/mgutz/ansi
+	url = https://github.com/mgutz/ansi
+[submodule "vendor/github.com/estesp/manifest-tool"]
+	path = vendor/github.com/estesp/manifest-tool
+	url = https://github.com/estesp/manifest-tool
+[submodule "vendor/github.com/weaveworks/common"]
+	path = vendor/github.com/weaveworks/common
+	url = https://github.com/weaveworks/common

.lintignore

@@ -0,0 +1,27 @@
+# IMPORTANT: Please only use GLOBs to ignore files and directories.
+
+# Do not lint the below bash scripts in Weave Net, in order to 
+# avoid breaking the build on make lint:
+bin/circle-deploy-issues
+bin/circle-deploy-master
+bin/circle-teardown-pre
+bin/circle-test-teardown
+bin/circle-test-unit
+bin/install-wordepress
+bin/multiweave
+bin/publish-site
+bin/release
+build/build.sh
+prog/weave-kube/launch.sh
+prog/weaveexec/symlink
+test/*_test.sh
+test/600_proxy_docker_py.sh
+test/assert.sh
+test/config.sh
+test/gce.sh
+test/gen_coverage_reports.sh
+test/run_all.sh
+test/sanity_check.sh
+test/setup.sh
+vendor/*.sh
+weave

.travis.yml

@@ -1,28 +0,0 @@
-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
-  - pip install --user --upgrade gcloud gsutil
-  - bin/setup-ci-secrets $encrypted_5ba036e89377_key $encrypted_5ba036e89377_iv
-  - make travis
-
-script:
-  - bin/lint .
-  - make tests
-
-after_success:
-  - go get github.com/mattn/goveralls
-  - $HOME/gopath/bin/goveralls -coverprofile=profile.cov -service=travis-ci
-  - test "${TRAVIS_PULL_REQUEST}" = "false" && site/build-and-publish.sh

CHANGELOG.md

@@ -1,3 +1,525 @@
+## Release 1.9.2
+
+Bug fixes and minor improvements
+
+* Fix a weave-kube bug when `br_netfilter` or `xt_set` module is compiled into
+  kernel #2820/#2821
+* Detect the absence of the required `xt_set` kernel module #2821
+
+## Release 1.9.1
+
+Bug fixes and minor improvements
+
+* Fix a race condition when the Weave Net container is restarted
+  which could allow a new container to be allocated the same IP
+  address as an existing one #2784,#2787
+* Handle the message type received when a pod has been deleted during
+  Kubernetes api-server fail-over #2772,#2773
+* Make weave-kube work with `dockerd --iptables=false` #2726
+* Ensure we have the right kernel modules loaded for Network Policy in weave-kube #2819
+* Reference-count addresses in Network Policy Controller, to avoid
+  errors when updates come in an unexpected order #2792,#2795
+* Allow the soft connection limit to be raised in weave-kube, so
+  larger clusters can be created #2781
+* WeaveDNS was incorrectly case-sensitive for reverse DNS lookups #2817,#2818
+
+Build and Testing
+
+* Scripts to create VMs to run automated tests were rewritten to use
+  Terraform and Ansible, to make it much easier to test with different
+  versions of components such as Docker and Kubernetes #2647,#2694,#2775,#2796
+* Upgrade to latest Weaveworks common build-tools #2780
+* Improve encryption tests #2793
+* Update vishvananda/netlink library to bring in changes we had previously forked #2790
+* Slight change to the build container to avoid permission errors and slow builds #2761,#2802
+
+## Release 1.9.0
+
+Highlights:
+
+* Encryption is now available for Fast Datapath connections, which
+  greatly improves the performance. #1644,#2687
+* We now build images for Intel/AMD 64-bit, ARM and ARM 64-bit. #2713
+* Weave Net Docker images are now labelled with description, vendor, etc. #2712
+* `weave status connections` now shows the MTU #2389,#2663
+* CNI plugin is now a stand-alone binary that does not depend on Docker #2594,#2662
+* Embedded docker client updated to version 1.10.3 #2395
+
+**NOTE:** The move to multi-architecture required that we update the
+  embedded Docker client, and this has the effect that this release of
+  Weave Net will not work with Docker installations older than
+  1.10.
+
+[Full list of changes](https://github.com/weaveworks/weave/issues?q=milestone%3A1.9.0).
+
+## Release 1.8.2
+
+Bug fixes and minor improvements
+
+* Fixed a bug where looping flows were installed which caused high CPU
+  usage #2650, #2674
+* Fixed a bug where Kubernetes master could not contact pods #2673, #2683
+* Fixed a bug where weave-kube was crashing in a loop due to invalid
+  Weave bridge state #2657
+* Fixed a bug where iptables NAT rules were not appended due to
+  "temporary unavailable" iptables error #2679
+* Added a detection of enabling the hairpin mode on the Weave bridge port
+  which caused installation of looping flows #2674
+* Added a detection of overlaps between Weave and the host IP address
+  ranges when launching weave-kube #2669, #2672
+* Added logging of connections blocked by weave-npc #2546, #2573
+
+More details in the [change log](https://github.com/weaveworks/weave/issues?q=milestone%3A1.8.2).
+
+## Release 1.8.1
+
+Bug fixes and minor improvements
+
+* Fixed weave-npc crash from Succeeded/Failed pods #2632,#2658
+* Fixed occasional failure to create Weave bridge on node reboot
+  #2617,#2637
+* Fixed a bug where weave-kube would fail to install when run with
+  unrelease snapshot builds #2642
+* Improved conformance to CNI spec by not releasing IP addresses when
+  a container dies #2643
+* Improved troubleshooting of install failure by creating CNI config
+  after Weave Net is up #2570
+* "up to date" shown even when the version check was blocked by
+  firewall #2537,#2565,#2645
+* "Unable to claim" message on re-launching Weave after using CNI
+  #2548,#2577
+* Eliminated spurious IP reclaim operations when IPAM was disabled
+  #2567,#2644
+* Include `jq` tool in our build VM configuration #2656
+
+## Release 1.8.0
+
+Highlights:
+
+* Exposed network policy controller Prometheus metrics
+  weaveworks/weave-npc#23, #2595, #2549
+* Exposed router Prometheus metrics #2535, #2547, #2523, #2579, #2578,
+  #2568, #2560, #2561
+
+More details in the [change log](https://github.com/weaveworks/weave/issues?q=milestone%3A1.8.0).
+
+## Release 1.7.2
+
+Bug fixes and minor improvements
+
+* Fixed an error where the Docker plugin could fail to attach a
+  container with a `bridge "weave" not present` error #2540/#2541
+* Fixed `cannot connect to itself` panic on weave launch #2527/#2543
+* Fixed inferred initial peer count when target peers includes self
+  #2481/#2543
+* Fixed compilation on Raspberry Pi #2506/#2538
+
+## Release 1.7.1
+
+Bug fixes and minor improvements
+
+* Added utility to recover container addresses without asking Docker #2531
+* Improved CI #2274
+
+## Release 1.7.0
+
+Highlights:
+
+* weave-kube - Deploy Weave Net to Kubernetes with a single command
+* weave-npc - Kubernetes network policy controller implementation
+
+More details in the [change log](https://github.com/weaveworks/weave/issues?q=milestone%3A1.7.0).
+
+## Release 1.6.2
+
+Bug fixes and minor improvements
+
+* Fixed hang after stopping and restarting on Docker 1.12 #2469/#2502
+* Avoid an error on Google container images by checking for tx offload support #2504
+* Fixed an issue where the supplied peer list could be ignored when restarting after failure #2503/#2509
+* Check for empty peer name on launch #2495/#2501
+
+More details in the [change log](https://github.com/weaveworks/weave/issues?q=milestone%3A1.6.2).
+
+## Release 1.6.1
+
+Bug fixes and minor improvements
+
+* `weave ps` was occasionally failing to list allocated addresses of containers #2388/#2418/#2445
+* `weave launch[-router]` on 4.2 kernel would appear to succeed even if the fast datapath VXLAN UDP port was in use by a different process #2375/#2474
+* Launching the proxy would fail when the Docker daemon could not be detected #2457/#2424
+* The CNI plugin did not work with Apache Mesos #2394/#2442
+* Router stopped working after a restart in the AWSVPC mode #2381/#2409
+* Router crashed when the Docker API endpoint parameter was explicitly set to empty #2421/#2467
+* The CNI plugin did not work on recent versions of Docker for Mac #2434/#2442
+* The CNI plugin assigns an IP to the bridge if necessary, which avoids failures if `weave expose` has not run yet #2471
+* Distinguish peer name collisions from attempts to connect to self in logs #2460
+* Improve host clock skew detection message #2174
+* Improve the error message returned when executing `weave launch-plugin` without the router running #2293/#2416
+* The `create-bridge` subcommand was not enabled in the fast datapath mode #2464/2466
+* Allow users to omit `weave setup[-cni]` by initializing the CNI plugin on the `launch[-router]` subcommand #2435/#2442
+* Reduce verbosity of fast datapath miss event logs #1852/#2417
+* Include the `ipam` option in the help output of the `status` subcommand #2425/#2426
+* Remove a harmless duplication of the `--no-dns` parameter #2430
+* Internal refactoring
+* Improvements to testing and building
+* Improvements to the documentation
+
+More details in the [change log](https://github.com/weaveworks/weave/issues?q=milestone%3A1.6.1).
+
+## Release 1.6.0
+
+## Highlights
+
+* A new [AWS VPC](https://weave.works/docs/net/latest/using-weave/awsvpc/) mode
+  that leverages Amazon Virtual Private Cloud for near-native network
+  performance, as an alternative to the Sleeve and Fast Datapath
+  overlays
+* Docker 1.12 introduced some internal changes that made it
+  incompatible with previous version of Weave Net - this version
+  restores compatibility
+* An [operational guide](https://weave.works/docs/net/latest/operational-guide)
+  detailing best practices for deploying and operating Weave Net
+* Changes to the target peer list are remembered across restarts,
+  making it much easier to deploy resilient networks
+* The version checkpoint now transmits network mode (e.g. 'awsvpc')
+  and kernel/docker versions to us to inform and guide our development
+  efforts. See the [installation documentation](https://weave.works/docs/net/latest/installing-weave/)
+  for instructions on disabling the checkpoint feature.
+
+More details in the [change log](https://github.com/weaveworks/weave/issues?q=milestone%3A1.6.0).
+
+## Release 1.5.2
+
+Bug fixes and minor improvements
+
+* Weave Proxy did not flush the initial http header in the Docker event stream, which could cause Docker Swarm to show all nodes pending. #2306/#2311
+* When using the CNI plugin, if a container was removed and quickly replaced by another using the same IP address, other containers might be unable to contact it. Send an address resolution protocol message to update them. #2313
+* Avoid Docker hanging for 1 minute in `weave launch` if the plugin had not shut down cleanly #2286/#2292
+* Print an error message when Weave bridge mode is changed without `weave reset` #2304
+* Eliminate spurious warning message from IP allocator on plugin shutdown #2300/#2319
+* Display error message when address requested in a subnet that is too small (/31 or /32) #2282/#2321
+* Add short wait after `weave reset` to allow updates to reach peers #2280
+* Weave was occasionally unable to claim existing IP address immediately after launch #2275/#2281
+* Refactor some integration tests to run faster and more reliably #2291
+
+## Release 1.5.1
+
+Bug fixes and minor improvements
+
+* Persisted data that was rendered invalid by changing peer name or
+  allocation range is detected and removed automatically, preventing
+  crashes and hangs #2246/#2209/#2249
+* `weave rmpeer` persists the range takeover in case the peer on which
+  it was executed dies subsequently #2238
+* Launching a container with an explicit `WEAVE_CIDR` in the
+  allocation range now waits instead of erroring if the allocator
+  hasn't finished initialising #2232/#2265
+* Weave DNS now responds to AAAA queries with an empty answer section,
+  instead of NXDOMAIN which could be cached and block subsequent
+  resolution of A records #2244/#2252
+* Many improvements to the documentation.
+
+More details in the [change log](https://github.com/weaveworks/weave/issues?q=milestone%3A1.5.1).
+
+## Release 1.5.0
+
+## Highlights
+
+- A new [Container Network Interface](https://github.com/appc/cni#cni---the-container-network-interface) plugin.
+- This release is much more robust against unscheduled restarts,
+  because it persists key data to disk.
+- New configuration options that are useful when you create or
+  auto-scale larger networks.
+- Weave now periodically checks for updates (can be disabled)
+
+Plus many bug fixes and minor enhancements. More details below and in
+the [change log](https://github.com/weaveworks/weave/issues?q=milestone%3A1.5.0).
+
+## Release 1.4.6
+
+Fixes some issues encountered by our users.
+
+* Restarting a peer could leave stale entries in WeaveDNS
+  #1867/#2023/#2081
+* Weave proxy occasionally failing to attach any new containers
+  #2016/#2049
+
+Other fixes:
+
+* Resolved a crash when a restarting peer re-connected to a peer that
+  had not received the latest IPAM data #2083/#2092
+* Make IP address space available immediately after a dead peer is
+  removed #2068
+
+## Release 1.4.5
+
+Higher performance for multicast and broadcast traffic when using
+Weave's Fast Datapath
+
+* The flow rule to deliver broadcast and multicast packets in-kernel
+  was not created correctly, hence every such packet caused a
+  context-switch to the software router #2003/#2008
+
+Other fixes:
+
+* Remove DNS entries for containers that are being restarted by Docker
+  but are not live yet #1977/#1989
+* Don't let one failing allocation attempt prevent others from
+  succeeding; they could be in different subnets which are more
+  available #1996/#2001
+* Don't complain on second router launch on kernels that lack support
+  for Fast Datapath #1929/#1983
+* Fix build broken by change in libnetwork IPAM API #1984/#1985
+
+## Release 1.4.4
+
+Fixing a rather serious issue that slipped through our preparations
+for Docker 1.10:
+
+* Restarting Docker or rebooting your machine while the Weave Net
+  plugin is running causes Docker 1.10.0 to fail to start #1959/#1963
+
+Also one other small fix:
+
+* Avoid a hang when trying to use plugin and proxy at the same time
+  #1956/#1961
+
+## Release 1.4.3
+
+Preparing for Docker 1.10, plus some bug-fixes.
+
+* Avoid hang in Docker v1.10 on `docker volume ls` after `weave stop`,
+  `weave stop-plugin` or `weave reset` #1934/#1936
+* Fix "unexpected EOF" from Docker 1.10 on `docker exec` with Weave
+  proxy `--rewrite-inspect` enabled #1911/#1917
+* Avoid losing DNS entries and potentially double-allocating IP
+  Addresses allocated via plugin, on router restart; also extend
+  `weave ps` to show IP addresses allocated via plugin #1745/#1921
+* Stop creating lots of copies of `weavewait` program in Docker
+  volumes #1757/#1935
+* Prevent container starting prematurely when proxy in
+`--no-multicast-route` mode #1942/#1943
+* Log error message from plugin rather than crashing when weave not
+  running #1906/#1918
+* Warn, don't error, if unable to remove plugin network in 'weave
+  stop', to avoid breaking the usual upgrade or config change process
+  #1900/#1919
+* Don't crash if network conditions suggest only very small packets
+  will get through #1905/#1926
+* Cope with unexpected errors during route traversal when starting
+  container via proxy #1909/#1910/#1932
+
+## Release 1.4.2
+
+Bug-fixes and minor improvements.
+
+* A race condition in weavewait that would occasionally hang
+  containers at startup #1882/#1884
+* Having the plugin auto-restart prevents successful `weave launch` on
+  reboot #1869
+* Work round weave router failure on CoreOS 4.3 caused by kernel bug
+  #1854
+* `weave launch` would exit with error code on docker <1.9 #1851
+* Running `eval $(weave env)` multiple times would break `eval $(weave
+  env --restore)` #1824/#1825
+* Don't complain in `weave stop` about "Plugin is not running" when
+  plugin is not enabled #1840/#1841
+* `weave --local launch` would fail if utility program
+  `docker_tls_args` could not be found #1844
+* Improved error reporting when TLS arg detection fails #1843
+* Improve error reporting when docker isn't running #1845
+* Add `--trusted-subnets` usage to `weave` script #1842
+* weave run can hang under rare combinations of options #1858
+
+## Release 1.4.1
+
+This is a bug-fix release to cover a few issues that came up since the
+release of 1.4.0.
+
+* Weave would fail to launch when `$DOCKER_HOST` was set to a TCP socket secured with TLS #1820/#1822
+* Weave would fail to stop when run against Docker pre-1.9 #1815/#1817
+* Issue a warning instead of failing on `--with-dns` option to proxy, which was removed #1810/#1812
+* Make `weave version` show the plugin version #1797/#1813
+* Make `weave launch` show when the a container is restarting #1778/#1814
+* Make `weave launch` fail if the plugin is running, for consistency with router and proxy. #1818/#1819
+
+More details in the [change log](https://github.com/weaveworks/weave/issues?q=milestone%3A1.4.1).
+
+## Release 1.4.0
+
+**Highlights**
+
+* The Docker Network plugin can now operate without a cluster store, so it is now run by default.
+* You can now use the fast datapath over trusted links and Weave encryption over untrusted links, in the same network.
+
+Plus many bug fixes and minor enhancements. More details below and in
+the [change log](https://github.com/weaveworks/weave/issues?q=milestone%3A1.4.0).
+
+## Release 1.3.1
+
+**Highlights**
+
+* The minimum Docker version has been increased to 1.6 due to the
+  [upcoming deprecation of Dockerhub access](https://blog.docker.com/2015/10/docker-hub-deprecation-1-5/)
+  for old clients. From December 7th onwards previous versions of the
+  `weave` script will fail to pull down images from the hub; if you
+  are unable to upgrade to 1.3.1 immediately you can work around this
+  by running `weave --local setup` in conjunction with a compatible
+  Docker client installation
+* Docker networking plugin now works with older kernels and allows you
+  to configure the MTU
+
+More details in the
+[change log](https://github.com/weaveworks/weave/issues?q=milestone%3A1.3.1).
+
+## Release 1.3.0
+
+**Highlights**
+
+This release includes a Docker Plugin, so you have the option to use
+Weave Net that way. More details in the
+[change log](https://github.com/weaveworks/weave/issues?q=milestone%3A1.3.0).
+
+## Release 1.2.1
+
+This release contains a number of bug fixes and minor
+enhancements. More details in the
+[change log](https://github.com/weaveworks/weave/issues?q=milestone%3A1.2.1).
+
+The release is fully compatible with 1.2.0 versions, so existing
+clusters can be upgraded incrementally.
+
+## Release 1.2.0
+
+**Highlights**
+
+This release introduces the 
+[Fast Data Path](http://docs.weave.works/weave/master/head/features.html#fast-data-path),
+which allows Weave networks to operate at near wire-level speeds. This
+new feature is enabled by default.
+
+Other highlights:
+
+- auto-configuration of TLS for the Weave Docker API proxy, making it
+  easier to run Weave on Macs and in conjunction with tools like
+  Docker Swarm
+- support for restart policies on application containers and weave
+  infrastructure containers
+- better compatibility with recent and future Docker versions
+
+More details in the 
+[change log](https://github.com/weaveworks/weave/issues?q=milestone%3A1.2.0).
+
+## Release 1.1.2
+
+This release contains a small number of bug fixes. More details in the
+[change log](https://github.com/weaveworks/weave/issues?q=milestone%3A1.1.2).
+
+The release is fully compatible with 1.1.0 versions, so existing
+clusters can be upgraded incrementally. When upgrading from 1.0.x,
+note the compatibility information in the
+[Installation & Upgrading instructions for Weave 1.1.0](https://github.com/weaveworks/weave/releases/tag/v1.1.0).
+
+## Release 1.1.1
+
+This release contains a number of bug fixes and minor
+enhancements. More details in the
+[change log](https://github.com/weaveworks/weave/issues?q=milestone%3A1.1.1).
+
+The release is fully compatible with 1.1.0 versions, so existing
+clusters can be upgraded incrementally. When upgrading from 1.0.x,
+note the compatibility information in the
+[Installation & Upgrading instructions for Weave 1.1.0](https://github.com/weaveworks/weave/releases/tag/v1.1.0).
+
+## 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:

CONTRIBUTING.md

@@ -0,0 +1,32 @@
+Thanks for your interest in contributing to this project and for
+taking the time to read this guide.
+
+# Code of conduct
+
+**Be respectful:** disagreements between people are to be expected and are usually the sign of healthy debate and engagement. Disagreements can lead to frustration and even anger for some members. Turning to personal insults, intimidation or threatening behaviour does not improve the situation. Participants should thus take care to ensure all communications / interactions stay professional at all times.
+
+**Be considerate:** remember that the community has members with a diverse background, many of whom have English as a second language. What might appear impolite, may simply be a result of a lack of knowledge of the English language. Bear in mind that actions will have an impact on other community members and the project as a whole, so take potential consequences into account before pursuing a course of action.
+
+**Be forgiving:** humans are fallible and as such prone to make mistakes and inexplicably change their positions at times. Don't assume that other members are acting with malicious intent. Be prepared to forgive people who make mistakes and assist each other in learning from them. Playing a blame game doesn't help anyone.
+
+# Issues
+* Before reporting an issue make sure you search first if anybody has already reported a similar issue and whether or not it has been fixed.
+* Make sure your issue report sufficiently details the problem:
+ * If you set up weave in some way other than that described by our [main instructions](https://github.com/zettio/weave#installation), please mention that.
+ * Include step-by-step instructions to reproduce the issue.
+ * State the OS platform you are using, i.e. `uname -a`
+ * `iptables` rules and firewalls can have a great impact on any Linux network; please note whether you have set up any rules and/or are running a firewall on your machine(s).
+* If you want to tackle any open issue, make sure you let people know you are working on it.
+
+## Pull Requests
+* Please be generous describing your changes.
+* Although it is highly suggested to include tests, they are not a hard requirement in order to get your contributions accepted.
+* Keep pull requests small so core developers can review them quickly.
+* Keep each pull request focused on a specific topic.  If you have two things to change, create two pull requests. This helps reviewers to understand the meat of your contribution.
+
+## Workflow
+See [WorkingOnWeave](https://github.com/weaveworks/weave/wiki/WorkingOnWeave)
+
+# Acknowledgements
+
+Much of this taken from https://github.com/cloudescape/gowsdl/blob/master/CONTRIBUTING.md

DEPENDENCIES

@@ -0,0 +1,3 @@
+DOCKER_VERSION=1.11.2
+KUBERNETES_VERSION=1.5.2
+KUBERNETES_CNI_VERSION=0.3.0.1

LICENSE

@@ -176,7 +176,7 @@
 
    END OF TERMS AND CONDITIONS
 
-   Copyright 2014-2015 Weaveworks Ltd.
+   Copyright 2014-2016 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

@@ -1,109 +1,378 @@
-PUBLISH=publish_weave publish_weavedns publish_weaveexec
-
 .DEFAULT: all
-.PHONY: all update tests publish $(PUBLISH) clean prerequisites build travis run-smoketests
+.PHONY: all exes testrunner update tests lint publish-one-arch $(PUBLISH) clean clean-bin prerequisites build run-smoketests
 
 # If you can use docker without being root, you can do "make SUDO="
-SUDO=sudo
+SUDO=$(shell docker info >/dev/null 2>&1 || echo "sudo -E")
+BUILD_IN_CONTAINER=true
+RM=--rm
+RUN_FLAGS=-ti
+COVERAGE=
 
-DOCKERHUB_USER=weaveworks
-WEAVE_VERSION=git-$(shell git rev-parse --short=12 HEAD)
-WEAVER_EXE=weaver/weaver
-WEAVEDNS_EXE=weavedns/weavedns
-WEAVEPROXY_EXE=weaveproxy/weaveproxy
-SIGPROXY_EXE=sigproxy/sigproxy
-WEAVEWAIT_EXE=weavewait/weavewait
-WEAVER_IMAGE=$(DOCKERHUB_USER)/weave
-WEAVEDNS_IMAGE=$(DOCKERHUB_USER)/weavedns
-WEAVEEXEC_IMAGE=$(DOCKERHUB_USER)/weaveexec
-WEAVER_EXPORT=weave.tar
-WEAVEDNS_EXPORT=weavedns.tar
-WEAVEEXEC_EXPORT=weaveexec.tar
+# This specifies the architecture we're building for
+ARCH?=amd64
 
-WEAVEEXEC_DOCKER_VERSION=1.3.1
-DOCKER_DISTRIB=weaveexec/docker-$(WEAVEEXEC_DOCKER_VERSION).tgz
-DOCKER_DISTRIB_URL=https://get.docker.com/builds/Linux/x86_64/docker-$(WEAVEEXEC_DOCKER_VERSION).tgz
+# We're using QEMU to be able to build Docker images for other architectures
+# from amd64 machines.
+QEMU_VERSION=v2.7.0
 
-all: $(WEAVER_EXPORT) $(WEAVEDNS_EXPORT) $(WEAVEEXEC_EXPORT)
+# A list of all supported architectures here. Should be named as Go is naming platforms
+# All supported architectures must have an "ifeq" block below that customizes the parameters
+ALL_ARCHITECTURES=amd64 arm arm64
+ML_PLATFORMS=linux/amd64,linux/arm,linux/arm64
 
-travis: $(WEAVER_EXE) $(WEAVEDNS_EXE)
+ifeq ($(ARCH),amd64)
+# The architecture to use when downloading the docker binary
+	WEAVEEXEC_DOCKER_ARCH?=x86_64
 
-update:
-	go get -u -f -v -tags -netgo ./$(dir $(WEAVER_EXE)) ./$(dir $(WEAVEDNS_EXE)) ./$(dir $(SIGPROXY_EXE)) ./$(dir $(WEAVEPROXY_EXE))
+# The name of the alpine baseimage to use as the base for weave images
+	ALPINE_BASEIMAGE?=alpine:3.4
 
-$(WEAVER_EXE) $(WEAVEDNS_EXE) $(WEAVEPROXY_EXE) $(WEAVEWAIT_EXE): common/*.go
-	go get -tags netgo ./$(@D)
-	go build -ldflags "-extldflags \"-static\" -X main.version $(WEAVE_VERSION)" -tags netgo -o $@ ./$(@D)
-	@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; \
-	}
+# The extension for the made images
+# Specifying none means for example weaveworks/weave:latest
+	ARCH_EXT?=
 
-$(WEAVER_EXE): router/*.go ipam/*.go ipam/*/*.go weaver/main.go
-$(WEAVEDNS_EXE): nameserver/*.go weavedns/main.go
-$(WEAVEPROXY_EXE): proxy/*.go weaveproxy/main.go
-$(WEAVEWAIT_EXE): weavewait/*.go weavewait/main.go
+# The name of the gcc we're using for compiling C code
+	CC=gcc
 
-# Sigproxy needs separate rule as it fails the netgo check in the main
-# build stanza due to not importing net package
-$(SIGPROXY_EXE): sigproxy/main.go
-	go build -o $@ ./$(@D)
+# Optional parameters that can be passed when linking C code into the Go binary
+	CGO_LDFLAGS=
+endif
+ifeq ($(ARCH),arm)
+# The architecture to use when downloading the docker binary
+	WEAVEEXEC_DOCKER_ARCH?=armel
 
-$(WEAVER_EXPORT): weaver/Dockerfile $(WEAVER_EXE)
-	$(SUDO) docker build -t $(WEAVER_IMAGE) weaver
-	$(SUDO) docker save $(WEAVER_IMAGE):latest > $@
+# Using the (semi-)official alpine image
+	ALPINE_BASEIMAGE?=armhf/alpine:3.4
 
-$(WEAVEDNS_EXPORT): weavedns/Dockerfile $(WEAVEDNS_EXE)
-	$(SUDO) docker build -t $(WEAVEDNS_IMAGE) weavedns
-	$(SUDO) docker save $(WEAVEDNS_IMAGE):latest > $@
+# arm images have the -arm suffix, for instance weaveworks/weave-arm:latest
+	ARCH_EXT?=-arm
 
-$(WEAVEEXEC_EXPORT): weaveexec/Dockerfile $(DOCKER_DISTRIB) weave $(SIGPROXY_EXE) $(WEAVEPROXY_EXE) $(WEAVEWAIT_EXE)
-	cp weave weaveexec/weave
-	cp $(SIGPROXY_EXE) weaveexec/sigproxy
-	cp $(WEAVEWAIT_EXE) weaveexec/weavewait
-	cp $(WEAVEPROXY_EXE) weaveexec/weaveproxy
-	cp $(DOCKER_DISTRIB) weaveexec/docker.tgz
-	$(SUDO) docker build -t $(WEAVEEXEC_IMAGE) weaveexec
-	$(SUDO) docker save $(WEAVEEXEC_IMAGE):latest > $@
+# The name of the gcc binary
+	CC=arm-linux-gnueabihf-gcc
+
+# The architecture name to use when downloading a prebuilt QEMU binary
+	QEMUARCH=arm
+
+# In the weaveworks/build image; libpcap libraries for arm are placed here
+# Tell the gcc linker to search for libpcap here
+	CGO_LDFLAGS="-L/usr/local/lib/$(CC)"
+endif
+ifeq ($(ARCH),arm64)
+# Use the arm 32-bit docker client variant
+	WEAVEEXEC_DOCKER_ARCH?=armel
+
+# Using the (semi-)official alpine image
+	ALPINE_BASEIMAGE?=aarch64/alpine:3.5
+
+# arm64 images have the -arm64 suffix, for instance weaveworks/weave-arm64:latest
+	ARCH_EXT?=-arm64
+
+# The name of the gcc binary
+	CC=aarch64-linux-gnu-gcc
+
+# The architecture name to use when downloading a prebuilt QEMU binary
+	QEMUARCH=aarch64
+
+# In the weaveworks/build image; libpcap libraries for arm64 are placed here
+# Tell the gcc linker to search for libpcap here
+	CGO_LDFLAGS="-L/usr/local/lib/$(CC)"
+endif
+
+# The name of the user that this Makefile should produce image artifacts for. Can/should be overridden
+DOCKERHUB_USER?=weaveworks
+# The default version that's chosen when pushing the images. Can/should be overridden
+WEAVE_VERSION?=git-$(shell git rev-parse --short=12 HEAD)
+
+# Paths to all relevant binaries that should be compiled
+WEAVER_EXE=prog/weaver/weaver
+WEAVEPROXY_EXE=prog/weaveproxy/weaveproxy
+SIGPROXY_EXE=prog/sigproxy/sigproxy
+KUBEPEERS_EXE=prog/kube-peers/kube-peers
+WEAVENPC_EXE=prog/weave-npc/weave-npc
+WEAVEWAIT_EXE=prog/weavewait/weavewait
+WEAVEWAIT_NOOP_EXE=prog/weavewait/weavewait_noop
+WEAVEWAIT_NOMCAST_EXE=prog/weavewait/weavewait_nomcast
+WEAVEUTIL_EXE=prog/weaveutil/weaveutil
+PLUGIN_EXE=prog/plugin/plugin
+RUNNER_EXE=tools/runner/runner
+MANIFEST_TOOL_DIR=vendor/github.com/estesp/manifest-tool
+MANIFEST_TOOL_EXE=$(MANIFEST_TOOL_DIR)/manifest-tool
+TEST_TLS_EXE=test/tls/tls
+
+# All binaries together in a list
+EXES=$(WEAVER_EXE) $(SIGPROXY_EXE) $(KUBEPEERS_EXE) $(WEAVENPC_EXE) $(WEAVEPROXY_EXE) $(WEAVEWAIT_EXE) $(WEAVEWAIT_NOOP_EXE) $(WEAVEWAIT_NOMCAST_EXE) $(WEAVEUTIL_EXE) $(PLUGIN_EXE) $(RUNNER_EXE) $(TEST_TLS_EXE) $(MANIFEST_TOOL_EXE)
+
+# These stamp files are used to mark the current state of the build; whether an image has been built or not
+BUILD_UPTODATE=.build.uptodate
+WEAVER_UPTODATE=.weaver$(ARCH_EXT).uptodate
+WEAVEEXEC_UPTODATE=.weaveexec$(ARCH_EXT).uptodate
+PLUGIN_UPTODATE=.plugin$(ARCH_EXT).uptodate
+WEAVEKUBE_UPTODATE=.weavekube$(ARCH_EXT).uptodate
+WEAVENPC_UPTODATE=.weavenpc$(ARCH_EXT).uptodate
+WEAVEDB_UPTODATE=.weavedb.uptodate
+
+IMAGES_UPTODATE=$(WEAVER_UPTODATE) $(WEAVEEXEC_UPTODATE) $(PLUGIN_UPTODATE) $(WEAVEKUBE_UPTODATE) $(WEAVENPC_UPTODATE)
+
+# The names of the images. Note that the images for other architectures than amd64 have a suffix in the image name.
+WEAVER_IMAGE=$(DOCKERHUB_USER)/weave$(ARCH_EXT)
+WEAVEEXEC_IMAGE=$(DOCKERHUB_USER)/weaveexec$(ARCH_EXT)
+PLUGIN_IMAGE=$(DOCKERHUB_USER)/plugin$(ARCH_EXT)
+WEAVEKUBE_IMAGE=$(DOCKERHUB_USER)/weave-kube$(ARCH_EXT)
+WEAVENPC_IMAGE=$(DOCKERHUB_USER)/weave-npc$(ARCH_EXT)
+BUILD_IMAGE=weaveworks/weavebuild
+WEAVEDB_IMAGE=$(DOCKERHUB_USER)/weavedb
+
+IMAGES=$(WEAVER_IMAGE) $(WEAVEEXEC_IMAGE) $(PLUGIN_IMAGE) $(WEAVEKUBE_IMAGE) $(WEAVENPC_IMAGE) $(WEAVEDB_IMAGE)
+
+PUBLISH=publish_weave publish_weaveexec publish_plugin publish_weave-kube publish_weave-npc
+PUSH_ML=push_ml_weave push_ml_weaveexec push_ml_plugin push_ml_weave-kube push_ml_weave-npc
+
+WEAVE_EXPORT=weave$(ARCH_EXT).tar.gz
+
+DOCKER_VERSION=1.10.3
+DOCKER_DISTRIB=prog/weaveexec/docker-$(DOCKER_VERSION).tgz
+DOCKER_DISTRIB_URL=https://get.docker.com/builds/Linux/$(WEAVEEXEC_DOCKER_ARCH)/docker-$(DOCKER_VERSION).tgz
+NETGO_CHECK=@strings $@ | grep cgo_stub\\\.go >/dev/null || { \
+	rm $@; \
+	echo "\nYour go standard library was built without the 'netgo' build tag."; \
+	echo "To fix that, run"; \
+	echo "    sudo go clean -i net"; \
+	echo "    sudo go install -tags netgo std"; \
+	false; \
+}
+# The flags we are passing to go build. -extldflags -static for making a static binary, 
+# -linkmode external for linking external C libraries into the binary, -X main.version for telling the
+# Go binary which version it is, -tags netgo for enforcing the native Go DNS resolver
+BUILD_FLAGS=-i -ldflags "-linkmode external -extldflags -static -X main.version=$(WEAVE_VERSION)" -tags netgo
+
+PACKAGE_BASE=$(shell go list -e ./)
+
+all: $(WEAVE_EXPORT)
+testrunner: $(RUNNER_EXE) $(TEST_TLS_EXE)
+
+$(WEAVER_EXE) $(WEAVEPROXY_EXE) $(WEAVEUTIL_EXE): common/*.go common/*/*.go net/*.go net/*/*.go
+$(WEAVER_EXE): router/*.go ipam/*.go ipam/*/*.go db/*.go nameserver/*.go prog/weaver/*.go
+$(WEAVEPROXY_EXE): proxy/*.go prog/weaveproxy/*.go
+$(WEAVEUTIL_EXE): prog/weaveutil/*.go net/*.go plugin/net/*.go plugin/ipam/*.go db/*.go
+$(SIGPROXY_EXE): prog/sigproxy/*.go
+$(KUBEPEERS_EXE): prog/kube-peers/*.go
+$(WEAVENPC_EXE): prog/weave-npc/*.go npc/*.go npc/*/*.go
+$(PLUGIN_EXE): prog/plugin/*.go plugin/*/*.go api/*.go common/*.go common/docker/*.go net/*.go
+$(TEST_TLS_EXE): test/tls/*.go
+$(RUNNER_EXE): tools/runner/*.go
+$(MANIFEST_TOOL_EXE): $(MANIFEST_TOOL_DIR)/*.go
+$(WEAVEWAIT_NOOP_EXE): prog/weavewait/*.go
+$(WEAVEWAIT_EXE): prog/weavewait/*.go net/*.go
+$(WEAVEWAIT_NOMCAST_EXE): prog/weavewait/*.go net/*.go
+tests: tools/.git
+lint: tools/.git
+
+ifeq ($(BUILD_IN_CONTAINER),true)
+
+# This make target compiles all binaries inside of the weaveworks/build container
+# It bind-mounts the source into the container and passes all important variables
+exes $(EXES) tests lint: $(BUILD_UPTODATE)
+	git submodule update --init
+	@mkdir -p $(shell pwd)/.pkg
+	$(SUDO) docker run $(RM) $(RUN_FLAGS) \
+	    -v $(shell pwd):/go/src/github.com/weaveworks/weave \
+		-v $(shell pwd)/.pkg:/go/pkg \
+		-e GOARCH=$(ARCH) -e CGO_ENABLED=1 -e GOOS=linux -e CIRCLECI -e CIRCLE_BUILD_NUM -e CIRCLE_NODE_TOTAL -e CIRCLE_NODE_INDEX -e COVERDIR -e SLOW -e DEBUG \
+		$(BUILD_IMAGE) COVERAGE=$(COVERAGE) WEAVE_VERSION=$(WEAVE_VERSION) CC=$(CC) QEMUARCH=$(QEMUARCH) CGO_LDFLAGS=$(CGO_LDFLAGS) $@
+
+else
+
+exes: $(EXES)
+
+$(WEAVER_EXE) $(WEAVEPROXY_EXE) $(PLUGIN_EXE):
+ifeq ($(COVERAGE),true)
+	$(eval COVERAGE_MODULES := $(shell (go list ./$(@D); go list -f '{{join .Deps "\n"}}' ./$(@D) | grep "^$(PACKAGE_BASE)/") | grep -v "^$(PACKAGE_BASE)/vendor/" | paste -s -d,))
+	go test -c -o ./$@ $(BUILD_FLAGS) -v -covermode=atomic -coverpkg $(COVERAGE_MODULES) ./$(@D)/
+else
+	go build $(BUILD_FLAGS) -o $@ ./$(@D)
+endif
+	$(NETGO_CHECK)
+
+$(WEAVEUTIL_EXE) $(KUBEPEERS_EXE) $(WEAVENPC_EXE):
+	go build $(BUILD_FLAGS) -o $@ ./$(@D)
+	$(NETGO_CHECK)
+
+$(WEAVEWAIT_EXE):
+	go build $(BUILD_FLAGS) -tags "netgo iface mcast" -o $@ ./$(@D)
+	$(NETGO_CHECK)
+
+$(WEAVEWAIT_NOMCAST_EXE):
+	go build $(BUILD_FLAGS) -tags "netgo iface" -o $@ ./$(@D)
+	$(NETGO_CHECK)
+
+# These programs need a separate rule as they fail the netgo check in
+# the main build stanza due to not importing net package
+$(SIGPROXY_EXE) $(TEST_TLS_EXE) $(WEAVEWAIT_NOOP_EXE) $(RUNNER_EXE) $(MANIFEST_TOOL_EXE):
+	go build $(BUILD_FLAGS) -o $@ ./$(@D)
+
+tests:
+	./tools/test -no-go-get -netgo -timeout 8m
+
+lint:
+	./tools/lint -nocomment -notestpackage
+
+endif
+
+# This rule makes sure the build image is up-to-date.
+# It also makes sure the multiarch hooks are reqistered in the kernel so the QEMU emulation works
+$(BUILD_UPTODATE): build/*
+	$(SUDO) docker build -t $(BUILD_IMAGE) build/
+	$(SUDO) docker run --rm --privileged multiarch/qemu-user-static:register --reset
+	touch $@
+
+# Creates the Dockerfile.your-user-here file from the template
+# Also replaces all placeholders with real values
+# If the architecture is amd64, it deletes all CROSS_BUILD lines
+# but otherwise, it only removes the "CROSS_BUILD_" placeholder and downloads QEMU
+%/Dockerfile.$(DOCKERHUB_USER): %/Dockerfile.template
+	echo "DOCKERHUB_USER|$(DOCKERHUB_USER)|g;s|ARCH_EXT|$(ARCH_EXT)|g;s|ALPINE_BASEIMAGE|$(ALPINE_BASEIMAGE)|g;s|QEMUARCH|$(QEMUARCH)"
+	sed -e "s|DOCKERHUB_USER|$(DOCKERHUB_USER)|g;s|ARCH_EXT|$(ARCH_EXT)|g;s|ALPINE_BASEIMAGE|$(ALPINE_BASEIMAGE)|g;s|QEMUARCH|$(QEMUARCH)|g" $^ > $@
+ifeq ($(ARCH),amd64)
+# When building "normally" for amd64, remove the whole line, it has no part in the amd64 image
+	sed -i "/CROSS_BUILD_/d" $@
+else
+# When cross-building, only the placeholder "CROSS_BUILD_" should be removed
+# Register /usr/bin/qemu-ARCH-static as the handler for ARM binaries in the kernel
+	curl -sSL https://github.com/multiarch/qemu-user-static/releases/download/$(QEMU_VERSION)/x86_64_qemu-$(QEMUARCH)-static.tar.gz | tar -xz -C $(shell dirname $@)
+	cd $(shell dirname $@) && sha256sum -c $(shell pwd)/build/shasums/qemu-$(QEMUARCH)-static.sha256sum
+	sed -i "s/CROSS_BUILD_//g" $@
+endif
+
+# The targets below builds the weave images
+$(WEAVER_UPTODATE): prog/weaver/Dockerfile.$(DOCKERHUB_USER) $(WEAVER_EXE) $(WEAVEEXEC_UPTODATE)
+	$(SUDO) DOCKER_HOST=$(DOCKER_HOST) docker build -f prog/weaver/Dockerfile.$(DOCKERHUB_USER) -t $(WEAVER_IMAGE) prog/weaver
+	touch $@
+
+$(WEAVEEXEC_UPTODATE): prog/weaveexec/Dockerfile.$(DOCKERHUB_USER) prog/weaveexec/symlink $(DOCKER_DISTRIB) weave $(SIGPROXY_EXE) $(WEAVEPROXY_EXE) $(WEAVEWAIT_EXE) $(WEAVEWAIT_NOOP_EXE) $(WEAVEWAIT_NOMCAST_EXE) $(WEAVEUTIL_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 $(WEAVEWAIT_NOOP_EXE) prog/weaveexec/weavewait_noop
+	cp $(WEAVEWAIT_NOMCAST_EXE) prog/weaveexec/weavewait_nomcast
+	cp $(WEAVEUTIL_EXE) prog/weaveexec/weaveutil
+	tar -xf $(DOCKER_DISTRIB) usr/local/bin/docker -O > prog/weaveexec/docker
+	chmod +x prog/weaveexec/docker
+	$(SUDO) DOCKER_HOST=$(DOCKER_HOST) docker build -f prog/weaveexec/Dockerfile.$(DOCKERHUB_USER) -t $(WEAVEEXEC_IMAGE) prog/weaveexec
+	touch $@
+
+$(PLUGIN_UPTODATE): prog/plugin/Dockerfile.$(DOCKERHUB_USER) $(PLUGIN_EXE) $(WEAVER_UPTODATE)
+	$(SUDO) docker build -f prog/plugin/Dockerfile.$(DOCKERHUB_USER) -t $(PLUGIN_IMAGE) prog/plugin
+	touch $@
+
+$(WEAVEKUBE_UPTODATE): prog/weave-kube/Dockerfile.$(DOCKERHUB_USER) prog/weave-kube/launch.sh $(KUBEPEERS_EXE) $(WEAVER_UPTODATE)
+	cp $(KUBEPEERS_EXE) prog/weave-kube/
+	$(SUDO) docker build -f prog/weave-kube/Dockerfile.$(DOCKERHUB_USER) -t $(WEAVEKUBE_IMAGE) prog/weave-kube
+	touch $@
+
+$(WEAVENPC_UPTODATE): prog/weave-npc/Dockerfile.$(DOCKERHUB_USER) $(WEAVENPC_EXE) prog/weave-npc/ulogd.conf
+	$(SUDO) docker build -f prog/weave-npc/Dockerfile.$(DOCKERHUB_USER) -t $(WEAVENPC_IMAGE) prog/weave-npc
+	touch $@
+
+$(WEAVEDB_UPTODATE): prog/weavedb/Dockerfile
+	$(SUDO) docker build -t $(WEAVEDB_IMAGE) prog/weavedb
+	touch $@
+
+$(WEAVE_EXPORT): $(IMAGES_UPTODATE) $(WEAVEDB_UPTODATE)
+	$(SUDO) DOCKER_HOST=$(DOCKER_HOST) docker save $(addsuffix :latest,$(IMAGES)) | gzip > $@
 
 $(DOCKER_DISTRIB):
 	curl -o $(DOCKER_DISTRIB) $(DOCKER_DISTRIB_URL)
+	cd $(shell dirname $@) && sha256sum -c $(shell pwd)/build/shasums/docker-tgz-$(WEAVEEXEC_DOCKER_ARCH).sha256sum
 
-tests:
-	echo "mode: count" > profile.cov
-	fail=0 ;                                                                              \
-	for dir in $$(find . -type f -name '*_test.go' | xargs -n1 dirname | sort -u); do     \
-	    output=$$(mktemp cover.XXXXXXXXXX) ;                                              \
-	    if ! go test -tags netgo -covermode=count -coverprofile=$$output $$dir ; then     \
-            fail=1 ;                                                                          \
-        fi ;                                                                                  \
-	    if [ -f $$output ]; then                                                          \
-	        tail -n +2 <$$output >>profile.cov;                                           \
-	        rm $$output;                                                                  \
-	    fi                                                                                \
-	done ;                                                                                \
-	exit $$fail
-	go tool cover -html=profile.cov -o=coverage.html
+tools/.git $(MANIFEST_TOOL_DIR)/.git:
+	git submodule update --init
 
-$(PUBLISH): publish_%:
-	$(SUDO) docker tag -f $(DOCKERHUB_USER)/$* $(DOCKERHUB_USER)/$*:$(WEAVE_VERSION)
-	$(SUDO) docker push   $(DOCKERHUB_USER)/$*:$(WEAVE_VERSION)
-	$(SUDO) docker push   $(DOCKERHUB_USER)/$*:latest
+# CODE FOR PUBLISHING THE IMAGES
 
-publish: $(PUBLISH)
+# This target first runs "make publish" for each architecture
+# Then it pushes the manifest lists
+publish: $(addprefix sub-publish-,$(ALL_ARCHITECTURES)) $(WEAVEDB_UPTODATE)
+	$(MAKE) DOCKER_HOST=$(DOCKER_HOST) DOCKERHUB_USER=$(DOCKERHUB_USER) WEAVE_VERSION=$(WEAVE_VERSION) UPDATE_LATEST=$(UPDATE_LATEST) $(PUSH_ML)
+ifeq ($(PUBLISH_WEAVEDB),true)
+	$(SUDO) DOCKER_HOST=$(DOCKER_HOST) docker push $(DOCKERHUB_USER)/weavedb:latest
+endif
 
-clean:
-	-$(SUDO) docker rmi $(WEAVER_IMAGE) $(WEAVEDNS_IMAGE) $(WEAVEEXEC_IMAGE)
-	rm -f $(WEAVER_EXE) $(WEAVEDNS_EXE) $(SIGPROXY_EXE) $(WEAVEPROXY_EXE) $(WEAVEWAIT_EXE) $(WEAVER_EXPORT) $(WEAVEDNS_EXPORT) $(WEAVEEXEC_EXPORT)
+sub-publish-%:
+	$(MAKE) ARCH=$* DOCKER_HOST=$(DOCKER_HOST) clean-bin
+	$(MAKE) ARCH=$* DOCKER_HOST=$(DOCKER_HOST) DOCKERHUB_USER=$(DOCKERHUB_USER) WEAVE_VERSION=$(WEAVE_VERSION) UPDATE_LATEST=$(UPDATE_LATEST) $(IMAGES_UPTODATE)
+	$(MAKE) ARCH=$* DOCKER_HOST=$(DOCKER_HOST) DOCKERHUB_USER=$(DOCKERHUB_USER) WEAVE_VERSION=$(WEAVE_VERSION) UPDATE_LATEST=$(UPDATE_LATEST) publish-one-arch
+
+publish-one-arch: $(PUBLISH)
+
+# This rule handles the pushing of the built images
+$(PUBLISH): publish_%: $(IMAGES_UPTODATE)
+# Tag :latest with the real version
+	$(SUDO) DOCKER_HOST=$(DOCKER_HOST) docker tag  $(DOCKERHUB_USER)/$*$(ARCH_EXT) $(DOCKERHUB_USER)/$*$(ARCH_EXT):$(WEAVE_VERSION)
+# Push the image with the arch suffix for arm and arm64, and without suffix for amd64
+	$(MAKE) DOCKER_HOST=$(DOCKER_HOST) DOCKERHUB_USER=$(DOCKERHUB_USER) WEAVE_VERSION=$(WEAVE_VERSION) UPDATE_LATEST=$(UPDATE_LATEST) push_$*$(ARCH_EXT)
+
+ifeq ($(ARCH),amd64)
+# If the architecture is amd64, add the -amd64 suffix.
+	$(SUDO) DOCKER_HOST=$(DOCKER_HOST) docker tag  $(DOCKERHUB_USER)/$*:$(WEAVE_VERSION) $(DOCKERHUB_USER)/$*-amd64:$(WEAVE_VERSION)
+# If the version is latest, tag the -amd64 with latest as well
+ifneq ($(UPDATE_LATEST),false)
+	$(SUDO) DOCKER_HOST=$(DOCKER_HOST) docker tag  $(DOCKERHUB_USER)/$*-amd64:$(WEAVE_VERSION) $(DOCKERHUB_USER)/$*-amd64:latest
+endif
+# Push the image with the -amd64-suffix so BINARY-ARCH-named images exist for all arches, so manifest lists may be made and ARCH is replaceable in scripts
+	$(MAKE) DOCKER_HOST=$(DOCKER_HOST) DOCKERHUB_USER=$(DOCKERHUB_USER) WEAVE_VERSION=$(WEAVE_VERSION) UPDATE_LATEST=$(UPDATE_LATEST) push_$*-amd64
+endif
+
+# This target pushes an image, and if UPDATE_LATEST is anything but false, also updates the latest tag
+# It takes one parameter, the image name
+push_%:
+	$(SUDO) DOCKER_HOST=$(DOCKER_HOST) docker push $(DOCKERHUB_USER)/$*:$(WEAVE_VERSION)
+ifneq ($(UPDATE_LATEST),false)
+	$(SUDO) DOCKER_HOST=$(DOCKER_HOST) docker push $(DOCKERHUB_USER)/$*:latest
+endif
+
+# This target pushes a manifest list; it takes one parameter, the image name.
+# The variable UPDATE_LATEST controls whether it updates the versioned tag and/or the latest tag
+$(PUSH_ML): push_ml_%: $(MANIFEST_TOOL_EXE)
+ifneq ($(UPDATE_LATEST),latest-only)
+	$(MANIFEST_TOOL_EXE) push from-args --platforms $(ML_PLATFORMS) --template $(DOCKERHUB_USER)/$*-ARCH:$(WEAVE_VERSION) --target $(DOCKERHUB_USER)/$*:$(WEAVE_VERSION)
+endif
+ifneq ($(UPDATE_LATEST),false)
+# Push the manifest list to :latest as well
+	$(MANIFEST_TOOL_EXE) push from-args --platforms $(ML_PLATFORMS) --template $(DOCKERHUB_USER)/$*-ARCH:latest --target $(DOCKERHUB_USER)/$*:latest
+endif
+
+clean-bin:
+	-$(SUDO) DOCKER_HOST=$(DOCKER_HOST) docker rmi $(IMAGES)
+	find prog -type f -name "Dockerfile.*" -not -name "Dockerfile.template" -print | xargs rm -f
+	find prog -type f -name "*qemu-*" -print | xargs rm -f
+	rm -rf $(EXES) $(IMAGES_UPTODATE) $(WEAVEDB_UPTODATE) weave*.tar.gz $(DOCKER_DISTRIB) prog/weaveexec/docker .pkg
+
+clean: clean-bin
+	-$(SUDO) DOCKER_HOST=$(DOCKER_HOST) docker rmi $(BUILD_IMAGE)
+	rm -rf test/tls/*.pem test/coverage.* test/coverage $(BUILD_UPTODATE) $(MANIFEST_TOOL_EXE)
 
 build:
 	$(SUDO) go clean -i net
 	$(SUDO) go install -tags netgo std
 	$(MAKE)
 
-run-smoketests: all
+run-smoketests: all testrunner
 	cd test && ./setup.sh && ./run_all.sh
+
+integration-tests: all testrunner
+# Usage:
+#   $ make \
+#     NAME="<prefix used to name VMs and other resources>" \
+#     PROVIDER="<provider among {vagrant|gcp|aws|do}>" \
+#     NUM_HOSTS="<# test machines>" \
+#     PLAYBOOK="<filename>" \
+#     RUNNER_ARGS="<...>" \
+#     TESTS="<...>" \  # Can be set to only run one or a few tests instead of the full test suite.
+#     DOCKER_VERSION=<...> \
+#     KUBERNETES_VERSION=<...> \
+#     KUBERNETES_CNI_VERSION=<...> \
+#     <...> # See also run-integration-test.sh for all variables and individual functions.
+#     integration-tests
+#
+	RUNNER_ARGS="-parallel" ./test/run-integration-tests.sh

NOTICE

@@ -1,3 +1,3 @@
 Weave
-Copyright 2014-2015 Weaveworks Ltd.
+Copyright 2014-2016 Weaveworks Ltd.
 This product includes software developed at Weaveworks Ltd.

README.md

@@ -1,155 +1,42 @@
-# Weave - the Docker network
+# Weave Net - 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)
+[![Integration Tests](https://circleci.com/gh/weaveworks/weave/tree/master.svg?style=shield)](https://circleci.com/gh/weaveworks/weave)
+[![Coverage Status](https://coveralls.io/repos/weaveworks/weave/badge.svg)](https://coveralls.io/r/weaveworks/weave)
+[![Go Report Card](https://goreportcard.com/badge/github.com/weaveworks/weave)](https://goreportcard.com/report/github.com/weaveworks/weave)
+[![Slack Status](https://slack.weave.works/badge.svg)](https://slack.weave.works)
+[![Docker Pulls](https://img.shields.io/docker/pulls/weaveworks/weave.svg?maxAge=604800)](https://hub.docker.com/r/weaveworks/weave/)
 
-Weave creates a virtual network that connects Docker containers
-deployed across multiple hosts and enables their automatic discovery.
+# About Weaveworks
 
-![Weave Virtual Network](/docs/virtual-network.png?raw=true "Weave Virtual Network")
+[Weaveworks](https://www.weave.works) is the company that delivers the most productive way for developers to connect, observe and control
+Docker containers.
 
-Applications use the network just as if the containers were all
-plugged into the same network switch, with no need to configure port
-mappings, links, etc. Services provided by application containers on
-the weave network can be made accessible to the outside world,
-regardless of where those containers are running. Similarly, existing
-internal systems can be exposed to application containers irrespective
-of their location.
+This repository contains [Weave Net](https://www.weave.works/products/weave-net/), the first product developed by Weaveworks, and with over 8 million downloads to date, it enables you to get started with Docker clusters and portable apps in a fraction of the time compared with other solutions.
 
-![Weave Deployment](/docs/deployment.png?raw=true "Weave Deployment")
+Weaveworks' product [Weave Cloud](https://www.weave.works/solution/cloud/) takes the heavy lifting out of building, integrating and operating open source components, so you don’t have to manage databases, storage and availability.
 
-Weave can traverse firewalls and operate in partially connected
-networks. Traffic can be encrypted, allowing hosts to be connected
-across an untrusted network.
+Weave Cloud is built using these Open Source projects: [Weave Scope](https://www.weave.works/products/weave-scope/), a powerful container monitoring tool that automatically maps Docker containers and their interactions, [Weave Cortex](https://github.com/weaveworks/cortex), a horizontally-scalable version of Prometheus, and [Weave Flux](https://www.weave.works/products/weave-flux/), a continuous deployment tool that works with Kubernetes.
 
-With weave you can easily construct applications consisting of
-multiple containers, running anywhere.
+# Weave Net
 
-Weave works alongside Docker's existing (single host) networking
-capabilities, so these can continue to be used by containers.
+Weave Net creates a virtual network that connects Docker containers across multiple hosts and enables their automatic discovery. With Weave Net, portable microservices-based applications consisting of multiple containers can run anywhere: on one host, multiple hosts or even across cloud providers and data centers. Applications use the network just as if the containers were all plugged into the same network switch, without having to configure port mappings, ambassadors or links.
 
-## Installation
+Services provided by application containers on the Weave network can be exposed to the outside world, regardless of where they are running. Similarly, existing internal systems can be opened to accept connections from application containers irrespective of their location.
 
-Ensure you are running Linux (kernel 3.8 or later) and have Docker
-(version 1.3.1 or later) installed. Then install weave with
+## <a name="help"></a>Getting help
 
-    sudo wget -O /usr/local/bin/weave \
-      https://github.com/weaveworks/weave/releases/download/latest_release/weave
-    sudo chmod a+x /usr/local/bin/weave
+If you have any questions about, feedback for or a problem with Weave Net:
 
-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.
+- Read [the Weave Net docs](https://www.weave.works/docs/net/latest/introducing-weave/).
+- Invite yourself to the <a href="https://weaveworks.github.io/community-slack/" target="_blank"> #weave-community </a> slack channel.
+- Ask a question on the <a href="https://weave-community.slack.com/messages/general/"> #weave-community</a> slack channel.
+- Join the <a href="https://www.meetup.com/pro/Weave/"> Weave User Group </a> and get invited to online talks, hands-on training and meetups in your area.
+- Send an email to <a href="mailto:weave-users@weave.works">weave-users@weave.works</a>
+- <a href="https://github.com/weaveworks/weave/issues/new">File an issue.</a>
 
-Weave respects the environment variable `DOCKER_HOST`, so you can run
-it locally to control a weave network on a remote host.
+Your feedback is always welcome!
 
-## Quick Start Screencast
+##Further Information
 
-<a href="http://youtu.be/k6r7yuSr0hE" alt="Click to watch the screencast" target="_blank">
-  <img src="/docs/hello-screencast.png" />
-</a>
-
-## Example
-
-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 `$HOST1` run
-
-    host1$ weave launch
-    host1$ C=$(weave run 10.2.1.1/24 -t -i ubuntu)
-
-The first line starts the weave router, in a container. This needs to
-be done once on each host. The required docker image for the weave
-router container is downloaded automatically. There is also a `weave
-setup` command for downloading this and other images required for
-weave operation; this is a strictly optional step which is especially
-useful for automated installation of weave and ensures that any
-subsequent weave commands do not encounter delays due to image
-downloading.
-
-The second line runs our application container. We give it an IP
-address and network, in
-[CIDR notation](http://en.wikipedia.org/wiki/Classless_Inter-Domain_Routing#CIDR_notation).
-`weave run` invokes `docker run -d` with all the parameters following
-the IP address and network. So we could be launching any container
-this way; here we just take a stock ubuntu container and launch a
-shell in it. There's also a `weave start` command, which invokes
-`docker start` for starting existing containers.
-
-If our application consists of more than one container on this host we
-simply launch them with a variation on that second line.
-
-The IP addresses and netmasks can be anything you like, but make sure
-they don't conflict with any IP ranges in use on the hosts or IP
-addresses of external services the hosts or containers need to connect
-to. The same IP range must be used everywhere, and the individual IP
-addresses must, of course, be unique.
-
-We repeat similar steps on `$HOST2`...
-
-    host2$ weave launch $HOST1
-    host2$ C=$(weave run 10.2.1.2/24 -t -i ubuntu)
-
-The only difference, apart from the choice of IP address for the
-application container, is that we tell our weave that it should peer
-with the weave on `$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 `$HOST2`, you must open the weave port
-(6783 by default; this can be overriden by setting `WEAVE_PORT`) for
-TCP and UDP.
-
-Note that we could instead have told the weave on `$HOST1` to connect to
-`$HOST2`, or told both about each other. Order does not matter here;
-weave automatically (re)connects to peers when they become
-available. Also, we can tell weave to connect to multiple peers by
-supplying multiple addresses, separated by spaces. And we can
-[add peers dynamically](http://docs.weave.works/weave/latest_release/features.html#dynamic-topologies).
-
-Now that we've got everything set up, let's see whether our containers
-can talk to each other...
-
-On `$HOST1`...
-
-    host1$ docker attach $C
-    root@28841bd02eff:/# ping -c 1 -q 10.2.1.2
-    PING 10.2.1.2 (10.2.1.2): 48 data bytes
-    --- 10.2.1.2 ping statistics ---
-    1 packets transmitted, 1 packets received, 0% packet loss
-    round-trip min/avg/max/stddev = 1.048/1.048/1.048/0.000 ms
-
-Similarly, on `$HOST2`...
-
-    host2$ docker attach $C
-    root@f76829496120:/# ping -c 1 -q 10.2.1.1
-    PING 10.2.1.1 (10.2.1.1): 48 data bytes
-    --- 10.2.1.1 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
-
-So there we have it, two containers on separate hosts happily talking
-to each other.
-
-## Find out more
-
- * [Documentation homepage](http://docs.weave.works/weave/latest_release/)
- * [Features](http://docs.weave.works/weave/latest_release/features.html)
- * [Automatic Discovery with WeaveDNS](http://docs.weave.works/weave/latest_release/weavedns.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/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`.
-
-Follow weave on Twitter:
-[@weaveworks](https://twitter.com/weaveworks).
-
-Read the Weave blog:
-[Weaveblog](http://weaveblog.com/).
-
-IRC:
-[#weavenetwork](https://botbot.me/freenode/weavenetwork/)
+* [Installing Weave Net](https://www.weave.works/docs/net/latest/installing-weave/)
+* [Weave Net Product Overview](https://www.weave.works/products/weave-net/)

Vagrantfile

@@ -1,41 +1,36 @@
-VAGRANTFILE_API_VERSION = "2"
-
-require './vagrant-common.rb'
+require File.expand_path(File.join(File.dirname(__FILE__), 'vagrant-common.rb'))
 
 vm_ip = "172.16.0.3" # arbitrary private IP
 
-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 = "ubuntu/ubuntu-14.10-amd64"
-  config.vm.box_url = "https://cloud-images.ubuntu.com/vagrant/utopic/current/utopic-server-cloudimg-amd64-vagrant-disk1.box"
+  config.vm.box = VAGRANT_IMAGE
 
   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"]
+    vb.memory = 2048
+    configure_nat_dns(vb)
   end
 
+  # Disable default Vagrant shared folder, which we don't need:
   config.vm.synced_folder ".", "/vagrant", disabled: true
+  # Keep Weave Net sources' in sync:
   config.vm.synced_folder ".", "/home/vagrant/src/github.com/weaveworks/weave"
+  # Create a convenience symlink to $HOME/src/github.com/weaveworks/weave
+  config.vm.provision :shell, :inline => 'ln -sf ~vagrant/src/github.com/weaveworks/weave ~vagrant/'
 
-  install_build_deps config.vm, pkgs
-  install_go_toochain config.vm
-  tweak_user_env config.vm
-  tweak_docker_daemon config.vm
+  # Set SSH keys up to be able to run smoke tests straightaway:
+  config.vm.provision "file", source: "~/.vagrant.d/insecure_private_key", destination: "/home/vagrant/src/github.com/weaveworks/weave/test/insecure_private_key"
+  # Grant permissions on sources:
+  config.vm.provision :shell, :inline => 'sudo chown -R vagrant:vagrant ~vagrant/src', :privileged => false
   cleanup config.vm
 
+  config.vm.provision 'ansible' do |ansible|
+    ansible.playbook = 'tools/config_management/setup_weave-net_dev.yml'
+    ansible.extra_vars = {
+      go_version: GO_VERSION
+    }.merge(ansibleize(get_dependencies_version_from_file_and_env()))
+  end
 end
 
 begin

api/dns.go

@@ -0,0 +1,22 @@
+package api
+
+import (
+	"fmt"
+	"net/url"
+)
+
+func (client *Client) DNSDomain() (string, error) {
+	return client.httpVerb("GET", "/domain", nil)
+}
+
+func (client *Client) RegisterWithDNS(ID string, fqdn string, ip string) error {
+	data := url.Values{}
+	data.Add("fqdn", fqdn)
+	_, err := client.httpVerb("PUT", fmt.Sprintf("/name/%s/%s", ID, ip), data)
+	return err
+}
+
+func (client *Client) DeregisterWithDNS(ID string, ip string) error {
+	_, err := client.httpVerb("DELETE", fmt.Sprintf("/name/%s/%s", ID, ip), nil)
+	return err
+}

api/ipam.go

@@ -0,0 +1,72 @@
+package api
+
+import (
+	"fmt"
+	"net"
+)
+
+// Special token used in place of a container identifier when:
+// - the caller does not know the container ID, or
+// - the caller is unsure whether IPAM was previously told the container ID.
+//
+// While addresses are typically stored under their container IDs, when this
+// token is used, the address will be stored under its own string, something
+// which should be kept in mind if the entry needs to be removed at any point.
+const NoContainerID string = "_"
+
+func (client *Client) ipamOp(ID string, op string) (*net.IPNet, error) {
+	ip, err := client.httpVerb(op, fmt.Sprintf("/ip/%s", ID), nil)
+	if err != nil {
+		return nil, err
+	}
+	return parseIP(ip)
+}
+
+// returns an IP for the ID given, allocating a fresh one if necessary
+func (client *Client) AllocateIP(ID string) (*net.IPNet, error) {
+	return client.ipamOp(ID, "POST")
+}
+
+func (client *Client) AllocateIPInSubnet(ID string, subnet *net.IPNet) (*net.IPNet, error) {
+	ip, err := client.httpVerb("POST", fmt.Sprintf("/ip/%s/%s", ID, subnet), nil)
+	if err != nil {
+		return nil, err
+	}
+	return parseIP(ip)
+}
+
+// returns an IP for the ID given, or nil if one has not been
+// allocated
+func (client *Client) LookupIP(ID string) (*net.IPNet, error) {
+	return client.ipamOp(ID, "GET")
+}
+
+// Claim a specific IP on behalf of the ID
+func (client *Client) ClaimIP(ID string, cidr *net.IPNet) error {
+	_, err := client.httpVerb("PUT", fmt.Sprintf("/ip/%s/%s", ID, cidr), nil)
+	return err
+}
+
+// release all IPs owned by an ID
+func (client *Client) ReleaseIPsFor(ID string) error {
+	_, err := client.httpVerb("DELETE", fmt.Sprintf("/ip/%s", ID), nil)
+	return err
+}
+
+func (client *Client) DefaultSubnet() (*net.IPNet, error) {
+	cidr, err := client.httpVerb("GET", fmt.Sprintf("/ipinfo/defaultsubnet"), nil)
+	if err != nil {
+		return nil, err
+	}
+	_, ipnet, err := net.ParseCIDR(cidr)
+	return ipnet, err
+}
+
+func parseIP(body string) (*net.IPNet, error) {
+	ip, ipnet, err := net.ParseCIDR(string(body))
+	if err != nil {
+		return nil, err
+	}
+	ipnet.IP = ip
+	return ipnet, nil
+}

api/weaveapi.go

@@ -0,0 +1,82 @@
+package api
+
+import (
+	"errors"
+	"fmt"
+	"io"
+	"io/ioutil"
+	"net/http"
+	"net/url"
+	"strings"
+)
+
+const (
+	WeaveHTTPHost = "127.0.0.1"
+	WeaveHTTPPort = 6784
+)
+
+type Client struct {
+	baseURL string
+	log     Logger
+}
+
+func (client *Client) httpVerb(verb string, url string, values url.Values) (string, error) {
+	url = client.baseURL + url
+	client.log.Debugf("weave %s to %s with %v", verb, url, values)
+	var body io.Reader
+	if values != nil {
+		body = strings.NewReader(values.Encode())
+	}
+	req, err := http.NewRequest(verb, url, body)
+	if err != nil {
+		return "", err
+	}
+	if values != nil {
+		req.Header.Set("Content-Type", "application/x-www-form-urlencoded")
+	}
+	resp, err := http.DefaultClient.Do(req)
+	if err != nil {
+		return "", err
+	}
+	defer resp.Body.Close()
+	rbody, err := ioutil.ReadAll(resp.Body)
+	if err != nil {
+		return "", err
+	}
+	if resp.StatusCode == http.StatusOK || resp.StatusCode == http.StatusNoContent {
+		return string(rbody), nil
+	}
+	return "", errors.New(resp.Status + ": " + string(rbody))
+}
+
+func NewClient(addr string, log Logger) *Client {
+	host := WeaveHTTPHost
+	port := fmt.Sprintf("%d", WeaveHTTPPort)
+	switch parts := strings.Split(addr, ":"); len(parts) {
+	case 0:
+	case 1:
+		if parts[0] != "" {
+			host = parts[0]
+		}
+	case 2:
+		if parts[0] != "" {
+			host = parts[0]
+		}
+		if parts[1] != "" {
+			port = parts[1]
+		}
+	default:
+		return &Client{baseURL: fmt.Sprintf("http://%s", addr), log: log}
+	}
+	return &Client{baseURL: fmt.Sprintf("http://%s:%s", host, port), log: log}
+}
+
+func (client *Client) Connect(remote string) error {
+	_, err := client.httpVerb("POST", "/connect", url.Values{"peer": {remote}})
+	return err
+}
+
+type Logger interface {
+	Infof(string, ...interface{})
+	Debugf(string, ...interface{})
+}

bin/circle-dependencies-post

@@ -0,0 +1,17 @@
+#!/bin/bash
+
+set -e
+
+source "$STATE"
+
+if [ -n "$TEST_AND_PUBLISH" ]; then
+    cd "$SRCDIR"
+    git submodule update --init
+    cd "$SRCDIR/build"
+    ../tools/rebuild-image weaveworks/weavebuild . Dockerfile build.sh
+    touch "$SRCDIR/.build.uptodate"
+    sudo chown -R ubuntu /usr/local/go
+    cd "$SRCDIR"
+    make testrunner
+    make COVERAGE=true RM= exes all
+fi

bin/circle-dependencies-post-sources

@@ -0,0 +1,36 @@
+#!/bin/bash
+
+set -e
+
+echo "TEST_AND_PUBLISH=1" >"$STATE"
+
+# Avoid doing a full build if we can.  Note if the PR doesn't exist
+# when the build is kicked off, we can't run this check so we do a
+# full build.  Subsequent pushes to the same branch will have the desired behaviour
+if [ -n "$CI_PULL_REQUEST" -a "$CI_PULL_REQUEST" = "$CI_PULL_REQUESTS" ]; then
+    if PR=$(echo "$CI_PULL_REQUEST" | grep -oP '(?<=^https://github.com/weaveworks/weave/pull/)[0-9]+$'); then
+        echo "GH_PR=$PR" >>"$STATE"
+        if FILES=$(curl -s "https://api.github.com/repos/weaveworks/weave/pulls/$PR/files" | jq -r '.[]|.filename'); then
+            echo "PR touches [$FILES]"
+            if ! echo "$FILES" | grep -v ^site/; then
+                echo "PR contains site changes only - skipping tests"
+                echo "TEST_AND_PUBLISH=" >>"$STATE"
+            else
+                echo "PR contains non-site changes - running tests"
+            fi
+        else
+            echo "Unable to get files for PR $PR" >&2
+        fi
+    else
+        echo "Unable to extract PR number from $CI_PULL_REQUEST" >&2
+    fi
+fi
+
+source "$STATE"
+
+mkdir -p "$(dirname "$SRCDIR")" && cp -r "$(pwd)/" "$SRCDIR"
+
+if [ -n "$TEST_AND_PUBLISH" ]; then
+    cd "$SRCDIR"
+    git submodule update --init
+fi

bin/circle-deploy-issues

@@ -0,0 +1,43 @@
+#!/bin/bash
+
+set -e
+set -o pipefail
+
+source "$STATE"
+
+site_changes() {
+    curl -s https://api.github.com/repos/weaveworks/weave/pulls/$1/files |
+        jq -r '.[]|.status + " " + .filename' |
+        grep -oP '^(added|modified|removed) site/.*(?=\.md$)'
+}
+
+format_comment() {
+    if [ ! -d .git ] || ! BRANCH=$(git symbolic-ref --short HEAD) || [ -z "$BRANCH" ] ; then
+        echo "Could not determine branch" >&2
+        return 1
+    fi
+
+    echo "#### Documentation changes:"
+    while read ACTION PAGE; do
+        echo "$ACTION [${PAGE#site/}]($WP_DEV_URL/docs/net/${BRANCH#issues/}/${PAGE#site/}/)"
+    done | sort
+}
+
+post_comment() {
+    jq -s -R '. | tostring | { body: . }' |
+        curl -s -d @- \
+            -H "Authorization: Bearer $WP_GH_COMMENT_TOKEN" \
+            -H 'Content-Type: application/json' \
+            https://api.github.com/repos/weaveworks/weave/issues/$GH_PR/comments > /dev/null
+}
+
+cd $SRCDIR
+bin/install-wordepress v1.0.0
+bin/publish-site "$WP_DEV_URL" "$WP_DEV_USER" "$WP_DEV_PASSWORD"
+
+if [ -n "$WP_GH_COMMENT_TOKEN" -a -n "$GH_PR" ] ; then
+    echo ">>> Adding doc changelog to GitHub PR $GH_PR"
+    if CHANGES=$(site_changes $GH_PR) && [ -n "$CHANGES" ] ; then
+        echo "$CHANGES" | format_comment | post_comment
+    fi
+fi

bin/circle-deploy-master

@@ -0,0 +1,17 @@
+#!/bin/bash
+
+set -e
+
+source "$STATE"
+
+if [ -n "$TEST_AND_PUBLISH" ] ; then
+    docker login -e $DOCKER_EMAIL -u $DOCKER_USER -p $DOCKER_PASS
+    cd $SRCDIR
+    make clean-bin
+    # CircleCI doesn't let us install the qemu module to do ARM docker builds
+    make publish ALL_ARCHITECTURES=amd64 UPDATE_LATEST=latest-only
+fi
+
+cd $SRCDIR
+bin/install-wordepress v1.0.0
+bin/publish-site "$WP_DEV_URL" "$WP_DEV_USER" "$WP_DEV_PASSWORD"

bin/circle-deploy-release

@@ -0,0 +1,7 @@
+#!/bin/bash
+
+set -e
+
+cd $SRCDIR
+bin/install-wordepress v1.0.0
+bin/publish-site "$WP_LIVE_URL" "$WP_LIVE_USER" "$WP_LIVE_PASSWORD"

bin/circle-teardown-pre

@@ -0,0 +1,13 @@
+#!/bin/bash
+
+set -e
+
+source "$STATE"
+
+if [ -n "$TEST_AND_PUBLISH" ] ; then
+    if [ "$CIRCLE_NODE_INDEX" = "0" ] ; then
+        go get github.com/mattn/goveralls
+        goveralls -repotoken $COVERALLS_REPO_TOKEN -coverprofile=$SRCDIR/test/profile.cov -service=circleci
+        cd $SRCDIR/test; cp coverage.* $CIRCLE_ARTIFACTS
+    fi
+fi

bin/circle-test-pre

@@ -0,0 +1,30 @@
+#!/bin/bash
+
+set -e
+
+# Signal failures in lock file, in order to fail fast:
+function signal_failure() {
+    echo "KO" >"$TEST_VMS_READY_LOCK_FILE"
+    exit 1
+}
+trap signal_failure ERR
+
+source "$STATE"
+source "$(dirname "$0")/wait_for.sh"
+
+if [ -n "$TEST_AND_PUBLISH" ]; then
+    [ -n "$SECRET_KEY" ] || {
+        echo "Cannot run smoke tests: no secret key"
+        exit 1
+    }
+
+    # Provisioning from image typically take 90 seconds, 
+    # but if we are creating a GCP image, it can take more than 10 minutes:
+    wait_for 900 "$TEST_VMS_PROV_AND_CONF_LOCK_FILE"
+
+    # Upload built binaries to testing VMs:
+    cd "$SRCDIR/test" # Ensures we generate Terraform state files in the right folder, for later use by integration tests.
+    ./run-integration-tests.sh setup >>"$TEST_VMS_SETUP_OUTPUT_FILE" 2>&1
+    echo "OK" >"$TEST_VMS_READY_LOCK_FILE"
+    echo "Test VMs now ready. $(date)." >>"$TEST_VMS_SETUP_OUTPUT_FILE"
+fi

bin/circle-test-smoke

@@ -0,0 +1,23 @@
+#!/bin/bash
+
+set -e
+
+source "$STATE"
+source "$(dirname "$0")/wait_for.sh"
+
+if [ -n "$TEST_AND_PUBLISH" ]; then
+    [ -n "$SECRET_KEY" ] || {
+        echo "Cannot run smoke tests: no secret key"
+        exit 1
+    }
+
+    # Provisioning from image typically take 90 seconds, 
+    # but if we are creating a GCP image, it can take more than 10 minutes:
+    wait_for 900 "$TEST_VMS_READY_LOCK_FILE"
+
+    # Run integration tests:
+    export COVERAGE=true
+    export WEAVE_NET_SANITY_CHECKS_FILES="$CIRCLE_ARTIFACTS/weave_net_sanity_check_*.log"
+    cd "$SRCDIR/test" # Ensures we generate code coverage files in the right folder, and use the Terraform state of previously provisionned VMs.
+    ./run-integration-tests.sh test
+fi

bin/circle-test-teardown

@@ -0,0 +1,10 @@
+#!/bin/bash
+
+set -e
+
+source "$STATE"
+
+if [ -n "$TEST_AND_PUBLISH" ] ; then
+    cd $SRCDIR/test
+    test "$CIRCLE_NODE_INDEX" != "0" || (cd $SRCDIR/test; ./gen_coverage_reports.sh)
+fi

bin/circle-test-unit

@@ -0,0 +1,11 @@
+#!/bin/bash
+
+set -e
+
+source "$STATE"
+
+if [ -n "$TEST_AND_PUBLISH" ] ; then
+    cd $SRCDIR
+    make DEBUG=1 lint
+    COVERDIR=test/coverage make RM= tests
+fi

bin/install-wordepress

@@ -0,0 +1,12 @@
+#!/bin/bash
+
+if [ $# -ne 1 ] ; then
+    echo USAGE: install-wordepress [COMMIT-ISH] >&2
+    exit 1
+fi
+
+go get github.com/weaveworks/wordepress
+cd /home/ubuntu/src/github.com/weaveworks/wordepress
+git checkout $1
+cd cmd/wordepress
+go get

bin/lint

@@ -1,81 +0,0 @@
-#!/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 "${filename}")
-		if [ "$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 [ "${filename}" = "bin/lint" ]; then
-		return
-	fi
-
-	case "$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/multiweave

@@ -14,7 +14,8 @@ set -e
 START=${FIRST_WEAVE:-1}
 COUNT=${NUM_WEAVES:-28}
 FINISH=$((START+COUNT-1))
-PORT=6783
+
+SUBNET=192.168.7
 
 weavedir=$(dirname $0)/..
 
@@ -23,32 +24,45 @@ 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 | sed 's|^ ||;s| |:|;s|[0-3]:|2:|;s|[4-7]:|6:|;s|[89ab]:|a:|;s|[c-f]:|e:|;s| |:|g'
+    od -txC -An -N6 /dev/urandom | ( read a b c d e f && printf "%02x:$b:$c:$d:$e:$f" $((0x$a & ~1 | 2)) )
+}
+
+weave() {
+    i=$1
+    shift
+    WEAVE_CONTAINER_NAME=weave$i WEAVE_HTTP_ADDR=$SUBNET.$i:6784 $weavedir/weave "$@"
 }
 
 case "$1" in
     launch)
         shift 1
+        echo $(date -R) launching
+        ip link show multiweave >/dev/null 2>&1 || sudo ip link add name multiweave type bridge
         for i in $(seq $START $FINISH); do
-            WEAVE_CONTAINER_NAME=weave$i WEAVE_PORT=$((5000+i)) $weavedir/weave launch -iface '' -name $(random_mac) -nickname weave$i -port $PORT "$@"
+            IP=$SUBNET.$i
+            sudo ip addr add $IP/24 dev multiweave
+            weave $i launch-router --datapath '' --iface '' --no-dns --host $IP \
+                --name $(random_mac) --nickname weave$i "$@"
         done
-        if [ $START -ne 1 ] ; then
-            status=$(docker inspect --format='{{.State.Running}} {{.NetworkSettings.IPAddress}}' weave$((START-1)))
-            PREV="${status#true }"
-        fi
+        echo $(date -R) connecting
+        [ $START -gt 1 ] || START=2
         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 }"
+            TO=$SUBNET.$((i-1))
+            echo connecting weave$i to $TO
+            weave $i connect $TO
         done
+        echo $(date -R) done
         ;;
     stop)
-        for i in $(seq $START $FINISH); do
+        for i in $(seq $FINISH -1 $START); do
+            IP=$SUBNET.$i
             echo Stopping weave$i
-            WEAVE_CONTAINER_NAME=weave$i $weavedir/weave stop
+            weave $i stop-router
+            sudo ip addr del $IP/24 dev multiweave || true
         done
+        [ -z "$(ip -4 -o addr show multiweave)" ] && sudo ip link del multiweave
+        ;;
+    *)
+            weave "$@"
         ;;
 esac

bin/provision_test_vms.sh

@@ -0,0 +1,41 @@
+#!/bin/bash
+
+set -e
+
+# Signal failures in lock file, in order to fail fast:
+function signal_failure() {
+    echo "KO" >"$TEST_VMS_PROV_AND_CONF_LOCK_FILE"
+    exit 1
+}
+trap signal_failure ERR
+
+source "$STATE"
+
+function install_terraform() {
+    curl -fsS https://releases.hashicorp.com/terraform/0.8.5/terraform_0.8.5_linux_amd64.zip | gunzip >terraform && chmod +x terraform && sudo mv terraform /usr/bin
+}
+
+function install_ansible() {
+    sudo apt-get update || true
+    sudo apt-get install -qq -y python-pip python-dev libffi-dev libssl-dev && pip install --user -U cffi && pip install --user ansible
+    export PATH="$PATH:$HOME/.local/bin"
+}
+
+if [ -n "$TEST_AND_PUBLISH" ]; then
+    [ -n "$SECRET_KEY" ] || {
+        echo "Cannot run smoke tests: no secret key"
+        exit 1
+    }
+
+    install_terraform >>"$TEST_VMS_SETUP_OUTPUT_FILE" 2>&1
+    install_ansible >>"$TEST_VMS_SETUP_OUTPUT_FILE" 2>&1
+
+    # Only attempt to create GCP image in first container, wait for it to be created otherwise:
+    [ "$CIRCLE_NODE_INDEX" != "0" ] && export CREATE_IMAGE=0
+
+    # Provision and configure testing VMs:
+    cd "$SRCDIR/test" # Ensures we generate Terraform state files in the right folder, for later use by integration tests.
+    ./run-integration-tests.sh configure >>"$TEST_VMS_SETUP_OUTPUT_FILE" 2>&1
+    echo "OK" >"$TEST_VMS_PROV_AND_CONF_LOCK_FILE"
+    echo "Test VMs now provisioned and configured. $(date)." >>"$TEST_VMS_SETUP_OUTPUT_FILE"
+fi

bin/publish-site

@@ -0,0 +1,46 @@
+#!/bin/bash
+
+set -e
+set -o pipefail
+
+PRODUCT=net
+
+fatal() {
+    echo "$@" >&2
+    exit 1
+}
+
+if [ ! -d .git ] ; then
+    fatal "Current directory is not a git clone"
+fi
+
+if ! BRANCH=$(git symbolic-ref --short HEAD) || [ -z "$BRANCH" ] ; then
+    fatal "Could not determine branch"
+fi
+
+case "$BRANCH" in
+    issues/*)
+        VERSION="${BRANCH#issues/}"
+        TAGS="$VERSION"
+        ;;
+    *)
+        if echo "$BRANCH" | grep -qE '^[0-9]+\.[0-9]+' ; then
+            DESCRIBE=$(git describe --match 'v*')
+            if ! VERSION=$(echo "$DESCRIBE" | grep -oP '(?<=^v)[0-9]+\.[0-9]+\.[0-9]+') ; then
+                fatal "Could not infer latest $BRANCH version from $DESCRIBE"
+            fi
+            TAGS="latest"
+        else
+            VERSION="$BRANCH"
+            TAGS="$VERSION"
+        fi
+        ;;
+esac
+
+for TAG in $TAGS ; do
+    echo ">>> Publishing $PRODUCT $VERSION to $1/docs/$PRODUCT/$TAG"
+    wordepress \
+        --url "$1" --user "$2" --password "$3" \
+        --product "$PRODUCT" --version "$VERSION" --tag "$TAG" \
+        publish site
+done

bin/release

@@ -10,15 +10,53 @@ 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)
+    if [ "$RELEASE_TYPE" != 'PRERELEASE' ] ; then
+        VERSION=${LATEST_TAG#v}
+    else
+        VERSION=${LATEST_TAG}
+    fi
     # NB does not check that this tag is on master
     RELEASE_DIR=./releases/$LATEST_TAG
 }
@@ -39,8 +77,8 @@ 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 $VERSION" >&2
         exit 1
     fi
@@ -51,6 +89,7 @@ build() {
     ## Inject the version numbers and build the distributables
     ## (library versions?)
     sed -i "/SCRIPT_VERSION=/ c\SCRIPT_VERSION=\"$VERSION\"" ./weave
+    sed -i -e "s/:latest/:$VERSION/" -e "/imagePullPolicy: Always/d" ./prog/weave-kube/weave-daemonset.yaml
     make SUDO=$SUDO WEAVE_VERSION=$VERSION DOCKERHUB_USER=$DOCKERHUB_USER
 
     if make tests; then
@@ -61,7 +100,7 @@ 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 +110,13 @@ 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 +126,9 @@ 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 +138,13 @@ 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 +158,140 @@ publish() {
         --name "weave" \
         --file "./weave"
 
-    echo "** Published release $RELEASE_NAME $VERSION"
-    echo -e "\thttps://github.com/$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
-    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"
+        --tag $LATEST_TAG \
+        --name "weave-daemonset.yaml" \
+        --file "./prog/weave-kube/weave-daemonset.yaml"
 
-    echo "** Published $RELEASE_NAME as latest_release at"
-    echo -e "\thttps://github.com/$GITHUB_USER/weave/releases/latest_release"
+    echo "** Draft $TYPE $RELEASE_NAME $VERSION created at"
+    echo -e "\thttps://github.com/$GITHUB_USER/weave/releases/$LATEST_TAG"
+}
+
+publish() {
+    setup
+    cd $PWD/$RELEASE_DIR
+
+    IS_MAINLINE=false
+    if [ "$RELEASE_TYPE" = 'MAINLINE' ] ; then
+        IS_MAINLINE=true
+    fi
+
+    if [ "$RELEASE_TYPE" = 'PRERELEASE' ] ; then
+        echo "== Tagging and pushing images on docker hub as user $DOCKERHUB_USER"
+        make UPDATE_LATEST=$IS_MAINLINE SUDO=$SUDO WEAVE_VERSION=$VERSION DOCKERHUB_USER=$DOCKERHUB_USER publish
+        echo "** Docker images tagged and pushed"
+
+        echo "== Publishing pre-release on GitHub"
+
+        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 $DOCKERHUB_USER"
+        make PUBLISH_WEAVEDB=$IS_MAINLINE UPDATE_LATEST=$IS_MAINLINE SUDO=$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 ($VERSION)" \
+            --description "[Release Notes](https://github.com/$GITHUB_USER/weave/releases/$LATEST_TAG)"
+
+        github-release upload \
+            --user $GITHUB_USER \
+            --repo weave \
+            --tag latest_release \
+            --name "weave" \
+            --file "./weave"
+
+        github-release upload \
+            --user $GITHUB_USER \
+            --repo weave \
+            --tag latest_release \
+            --name "weave-daemonset.yaml" \
+            --file "./prog/weave-kube/weave-daemonset.yaml"
+
+        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/weaveworks/github-release" >&2
+    echo "and create a git token per https://github.com/weaveworks/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

@@ -1,57 +0,0 @@
-#!/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
-mOYNzNsAdwva0LbB2YFMY9VgL0SITFu1bPrbOujyLtOrBNjmOYbzR5d/sG+ARMFr
-7NZ5OKcvMbItllz0n7TtNkzkCOMztMC870Wcx3nGJzbBephdcYwos4tBlp5bihTU
-AXgxLUiDT1broYAFKnbE1aZC/XyNxuLTN+nXJWIWeijaXTgvhkEEm3tab+z7ioCb
-tlg71W1BrUuocctAJAuVwH/uTZAaXaJGJj1s2S7F2DrFnG6sFlrp8rnCucPLWKnC
-4IwJFC5saR5gxK6wECffwmwbpeXVOoQ58OgzxoZTEyAr9nhVbaBt5UZz3tfHlx8W
-Rn5jHehACw5kg5eMtGPqMEksJ63LX4h3mfSTLJXJHEmOrzCRpFrigVrsbA408U2u
-8jJTHJmKrGfwBh5ZFzBg6NuV4VplOp+ZquJLgegv2WH/iu/ciopXqB2YDCdx5ZBi
-nHV2Puth7kjS4EMCKUGfeqpesjL9Djb8cygzv/J3ZBmLjNH9dqlSXWy2DcFZA1Iy
-pFTTHkVU3w5sNz3nYOuT2UPQvULBW0FUndDKX6olyVa0mlxPwGBP9N3yGg918/rw
-7rNV/r54lA334F5QMhDrVxar6sl9wfLA+Z+8qemBbNFlLog1uQGhuwWK2nFu1tRM
-9uyvQIq0oq5NHKpogWc7NEuk7CPe1JyfRIcbMVj8+ilmKjUPB2HPC43IDmKt9/56
-rY3IXAcxZ/ClGfGpeNHXqop9T/WhfaowponOZFcdGSUddG0OswqkTE4KIv71mgTF
-jXooMkTQBOG+gBnCe+8bCRdRCG3anxHX74za4dGD58cOJtl6DYWnjWuR91NWnxdT
-1Zr3iUe41txg9hCNY9LHo2QHGLPxe6pmNnSClQ1mcFhuY6NF8RmCX3HAGKJQkxJb
-vpLGbXTXjAIFgIYgLNgKP2RLvCif/LmSWgkvE3ZU9GXtCUbm6xgJodwOqXiI9uuO
-4H4+/vpGHnSFENiclkgMFrLG4yiMu8ArgmnCBzg9E2AoOX5zCrh/2ZRTU8Dk4mt7
-jUd5SKQLsjB9QtB+y3tRO7zY9RDvR6iBOPRsjx6t8EJMCfPb06KchfMJw+VGxvMM
-48jtmepREFnhd/8XDRGnw5bznjRuwohGik8BToltjIviMkkpifKWaLwlaOiDXaHh
-VBFNXnUKvOBwRMU+PZqv4+DP2qff1gSXnGKqA5GIURYrK9P7TqHHNTnmjBdfJLzc
-0x+W1DTiYhLT2vrLrkEpZ99o6qrg+lwvjat6IsJF8xoQEo4pLD/ZRPJ0WzoDyctT
-oWZ5rMsN1TzTvJrBrTAWIJyhIzZcuNwChMrU6qogMr0fd6TSxWhWn0sOJ5y8AaTR
-ej4JHx0qroS/9JPmgFYU61pX3c0ypdef/sSHWG23mcFzLTgwe2d4ty9VakypZy3T
-sXCl6EHVVXlUFWhY4zQCjdZpYJv/rtoKL1BL4fPE2NV5WTjCL2GNvaO5SfHR7pA0
-yQJR/iU+cS2n8UXsWNjyV+/qEn6+QXuyVHGLbxyH8EeqlliAbyHsc2rzVI8Xctzo
-W5DuIqxwHAkNNurhmx27ktIIQ6HhaCp028SWwvLttkbBBgF4v1mmd4u/2bKbKjUd
-dOaetaIUx1hU9OAeaePvVkeTDcc3mlFtPARCS9Fqj16hgJQ43onZyC0H1K2WAxmU
-GsmzjCHlTNquzFTuuQihYGZKfsWIh9z6HEOkvNJ3VEQ=
-EOF
-
-exec sh bin/do-setup-ci-secrets

bin/setup-circleci-secrets

@@ -1,115 +0,0 @@
-#!/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
-U2FsdGVkX1/3QHnDgpZn0srp+GiEQBTlag0CBdsw6Bp6iaIKy6Jy8gFshrsmvl3+
-c+7hn1nqsBVpzVH0S5QA3Ex5nx9rl7/dcGoogsySFcwMmBFcauT0UTMK1bvX0Hqx
-QrshYSndUkww72KA7EsSnjR1BBJWm3AhCDOTIcnO6nQhig1Fc+SBEj5FGS5xTQ5Z
-/8hDsKf54Ms49vOO6QeE5w5ndZ+k7IvVJfq9Evhb7htD20RntDhR86foAwMnLV7R
-Wh9qAqI3gnRq0GmbeRKaHmB7pcLq9f0OdScqM/Tn1D+q0556fqJjBziXpZiGbxVs
-DxEp8zDJ8yNDAi0Wb2NXjoA79SXJ8Q7iTieaST4y2OmXQpY+Vw8RVDXxi6ERyVnH
-41OeMzyLm0qvCoMl32pe1sSG5DRCUiAm7wOtDTVvNDRqmGJYUgwwexyayecJI1wQ
-LlhYLJavUvw3UGDZOld8BaMQhfOKBVCdFrjmA4HuVxmOf3029qkgzOCSZiQVNqs+
-fvM6J05zBuk+GPy8YInvRkzfxum/x00vmUyGjMs/lHDFfrmYDFK3ux41EoVqvWLG
-S5uYxdZJFdR3Xsrs+sMr51XNBQGMmz6KoEEzFYyHs5fZgtdpRdPAuQS1m6FqgZyi
-wSz6+EKsALtmGorEp+CF8JN5YzKJCrKzNkg0fILBqsqmJZGP64lmX69950lRLNGM
-/l3KVR2zH31b4AnnzTcvldVSCKDXjaMw3JA2Ce/MK6XhOWOcpEv4oDt/62lbhUKP
-QUQTPbfpQRvVfBcoIrfAm3ghi/CZc2TDVEuD7DhasLTZD3r7LoK261BWC9O5Wubi
-vlXuFIF+uyrpTDf6EJKE/+XywtArppffMP6RkHu1Iqnd8JtsqPaIZsmMmZbjgb6j
-BX4ZLb5U9R7jYoSgIke4+u6geFcrMQ+Lny4r7MxXaS0Y1UJ6Jo1bwpYw1TBIobZc
-eQ30+xhbSeRC9vEw1NXI6qM2Ai2gIHtAZvEiBkBBXTG5Ld7N/mBAmDIJEzVRxh6F
-jRkB3dzESF6eeTBm61OQepwV3aW6lslMaf26drPGv2W2q+K/WOpQOejfggtHUgVs
-9SWqtn7hHYSpIASe1Ihi14HAWv3kPhQien0zY1DLKJWf4ilbRaICn1QSJjNuKwtl
-A2ZwEw7FFddFcsF4okHPkxEoCre3shq0DEw9UA1gnwEaEF1Q+i9cvLtQg56zK3+R
-MfTzFUv2K1z3j1s5tC6Z6LzL8j682EFOll7MkihqiIWh+po1zcNs6Ln0SkjB3v9T
-OFRYVJis9GqXYO9PUW1mI69udR4nXbKlBl5tWNyAxn9hufJHLSAmbGMwActKLRM5
-kROapKrN1Ra/sHUmhoSSDUK9AXeYKkqPXVMbhly9xC1Kya4hFaFokjRQIMLPmXdQ
-lP46RL3HOq0v1BkXg05poSwDm+BtitZkcIhOzcmeucUqn1whsz39y3VoOhJqQu2j
-0dUcj19Fue1CDZfwzACb9mLZr643h0yCIHQaVT7is/yiN2vEt0S0zynvOA1D+Xgy
-4bFdjqed9DgBShLwF/lh4/hur5iZPpVr9A8rt3Vq0k5A1tdjsZpXP3qv5jLc7lJv
-cAQxdVLEuv8WPwwTV/EQsoH7lpoEdjktw/gu0v5PkUgR/WBxEqJq4liTekViQ+8X
-BAmdm/FGWeIxSSEm0a8I+muiBpIuKjuQoJit1f0k+lLUohoVDqpDDfeYHh1TxXHE
-xSKAKNmFSc2XOr5Zg2mOInxeH7WoxH6iylXKADBgEgAQ4C55DoAPRjFNtGGz2iJl
-WkzhQOfgsDss1VxpPZ4SWDQO+xxuuEnYcCYdJ6Tyi5hAwZ0+RZmXx0g9BCK+5qzc
-Ffei066kCItBcayekwCs0i86r8JvDtsMUUkzEKDQTSWHpP8ypIZoz3P+Skdqcs6p
-IcZHy2fODIsClctRAsHOjZ9BnWSY2rqf1lysqvRfOkNTViTOUVx2hf+LuL+8rT6g
-K4GvS39Q+c9FYSMjCNxv1m37NfHJv2W7AlqVV95gMBEFB97M3388T7PfvmSLsyPv
-qAKDE7genTOycQvEX9oeEACxPo08ai2Mgs/YXCig0g0btZoScoKPelQKtD0HLpZ+
-j7ruaKFy4/vySDMostB3AKSkCE/SkGu/W9oI37n1guSYC/9yJjtTcwZULXAClfwt
-LyHvLAw4+7BdGJqDe9Tf8z4zqVLax+BcBHkW7pbP+pvxC6fhIA4PO8k5HwwAVlRw
-68lG6e3z9+Vst4zrFLewHJvkDRSOTSecs9h9SPOjReTK0ovlDzMHVakfUvqpk9mv
-nCj8SWaMPF70z138AuRuKN7X4exNXPBFnOcseKp/NpT1DyvgoHm/oIO65mq9vvo+
-42uSbyyegYiTdVK4SaXBc2hixkhaTteqdEy6GxfWqKCvHtYuRD2LyUSjZn/0Y6CG
-3wZapylKL1sxfH+b1gogv2wAA8KtZAfiTlMISuymwQr5RbOFma7UVMVecCa7XrNG
-fZwO8R+6++ru0efDzeC/gtLOItjn+yVfsbk2gfu0FikHIV1sogOjnsv3dl6IpH/s
-w6WbuK/yZhyrrmhIIueHF30ES512Peogf/Gxp8U/ZAmqBa7p4qsv93XWDR52IPYz
-yU1MtboLD02J39daBNrYZuO4Yfo/xAvU7Ijg2KIR9HS0bSWNuSFAZaZXlJ2bSag3
-8l0dZMx2fZa0FALxWvY2+nd1tWcH+Wo99RSxX+4TH3guCpe1x/58yKOKL4d1xRpu
-02nGaqerV9bHU6WjCUYTrrZurTp6yqivpSFCALDMhAU5Ihd/Qjz69zg4uZ7iqbNd
-WqIYJ3SAOei2tSfoOJbdh8mohotnMFFbupck3Fv+lXAXYDp0V/sSuK32MSeJxan1
-q3t0eenAh6zoBP0Tj53N8B9YmrgZ1i1AljQqYsAdb8N5Z3vecuzQa946U8H4axEc
-BL5fgmqSfsbj1EjJVUrw3cE9hgqeqAYBBvZsyW5zSAsLq/RJKYtBxDGADqr0TOOu
-TjVqfPObb1u9EAQj15ALBhhPORa2gBAK5gnhJWW5deNgA0UOYoWARFYfATuQvr1T
-9xTVbqzZ0VJR4n7X5JyxJo2tZ44QYVzA0fqX0lt+uRkarrkbZMgplKp4MJTFCp2N
-tLciWS0YSHPbKTm7svw5mROazUvEoj1N3SYrJT+Ai9UgSL1cA4FmQ5Jsi+GOeQbH
-7E4pzjeST4b1aATY9ZZSy4TzK+UNYBcCVqY1dN5Xnk0e5yPMnrkkcYI41s/6oOaW
-lQkp/yrHkvpzQWZa7vF2yWg54j3eX8YWx/TsLvmuJmSQqiIHfu9TXcAIPDispCpF
-gp4ZbYPZ8RDQLw3ROc+bZ9E0J8e+FHwgXEELsMLW9n4d3PTj9pLFej1vmBKa03o3
-g+JViNxb1gUPNmC6ADk4o7TQzBrjV2pmmuCza16kOmq6oAbJPOeCLtVWA5HJTX8d
-AuOzBLO37tWP457dNqoNDaCMik3LCy8cslZjAz02D6VG/QGOAXP9x8bJ3zg9N7vW
-EOn1BMtIeMI4yIxpC6HgotNWDNbUBWremAFWYQRgYQqo9L1SdW4hz6X8FqdlBFvK
-ml7sdUwjEy2tNW+aiZI4cgAlI/VvMWYr5kPfhvaUu1wGYeS1TD1B+DPcjcXpOGWo
-vB1f/uvGc61zZWD0ph9f3S9OnvEko5qV3VhxOnxYUZTrqlM7LVgy/sHrSaPdR7Eo
-nb4QGdi5wEGMxVgQlDGwOmEmS5nCaA0RcfHbkQV4SebRleocLB9qcSwj5JzPICAB
-sn1qeSv45LnGdTzUnCQErw1EzgrK1FXOknujjZ3GX5dM7a6Gag0E6cAxoQeC8Mh0
-aUWolyBo9aSXltn7Vnywoe4X3v96eVH6tUQtN3wt51LBlfSDTWOQDeXLFyW57oYL
-/ErbmJLaSHpANBcC9InI+rxNYePTTba7K8rdPDppmMEmdOXjaL+5aPay2Bay9K8T
-FUyZdoyrbzxFZYT9/YyVJV/ukVcT9ru3HpzLTg9Vgc/CyRfIvCZY/Gzh+pPUbRsR
-pHYDT09BFS+mjszTkcdbceweYXJvknXpajMiISrPUUkb9rwCTmLS4QR4y7I9zAgJ
-9U72mCZB9yhhzS17kyKAANihXvOFrMXCO7QTWZbtSkobMBS2SybDxYP3rM5b6824
-HQaY4MZW5qCndydfz4fa908XbPTDka9Nu3CZfI3fhGiiGDFWViotGEYE4i9BuGZJ
-vmtzII7zeIoHwM4t5fb5mYDd9H+Rkct1yATGEIFEx7cu1fj4Ht2177EzhdkF3Q6I
-Fccn43yGDW06nFvEjnjb+Lz4EvtGp6dDefUhNBohdzd4Rm2o+etKobm0lZ1xOX74
-2gOGBLfXS6PF+msNkWP76mqKE6hG0+R1iPrN06Arti+ZRBhNGJDp1pnOERl7IyB0
-hiLUqae7xVSMVRDeq4O04EUpMXh5ixs3RJXjthYILt7vX+6qskJC3rMuyThrsvMi
-Kk0wErDpzR5U7KFnM2fk4jY5by/0b/jHZ/PWFGnaFrXNOiwK/mV1RIJtg5FCrvMv
-xJN5Qo7o2ZYzUL+IBf5mP5O49FCnz3e++9r4ySY/K57ybhQft1l+cQPWS7xuvVAg
-wZGM9DPl9AhBus0I3V3XzfkcWWHkMynMRcfTnkBHrmKjMopIOggsq05JPalM9b0V
-NfwZngVvTFbQejbGjgQQQ+G7spav/icCIA8Iu8JPHaKZt2IX77L1xMcQOouqMrx8
-JCXnJ7zsuU+8W3GQGm70H2kcen4bf4beA8TSkFmbVsaqDNtGaG+ZopWO8ctZX3CP
-jFgIYgEGi137IWvs1KD5QNFHZI6l0JMzglmvcfnViRPDHLi+EQXAoL/98j/YzA9t
-a9L4xMO0oucovKkqYOS2cdFaQKVIUM9L5ibcbW7Tol4ugMo5ibIsTgjZoyFohG6t
-acg+h2wTTyxtrIapvOOBeAo9V/iQowTAPQf38LKQZ5tApksiCG1qvJerKALTMp1J
-yUHjTCPCPsaiXVVO0mfa9OPtzVvi/icLmlz7umk82mew13djedgMS3/ghq5aEHbg
-e7rtI5snFlm/GQnV6IaCDytb+jYxqQ0DZ9Mb0CHcMpnLyiBO6nzHfadpZYlrxrpx
-dPx9MVqfLavj1UVjKuVj4Mgec9J38IBBRGMJZ4MGhde2hrw/s2jVzG1BzaIzcvFa
-bWiJOkKKRC4BY9DBDYfae5c/obwzkxLmvkbWAVzoFXc+46K1IK6bbC2a4EerOAxc
-C7B3X8BucD8OtiPORwXgjctd9AJ7cXq0EEVGoZZ8jkILnklsK6RXsxrT4gSOGFpx
-cBU7TF4kHpH+o4KGQmjlFA2VYP1tXirjEep57LOHfL+zy+HiSXdsbexf6odkqLYA
-1RR0TzSkmqJYvP0GfHPMvp2xredx1kP934fhTIUcWvErrG3NPd/Dod4BzQye1nNK
-8Y8aFYF6fACcD4SFZ11ecK9DJmB+WXGlsxtO3w1LeEysny2lVkkH6HuMRIzPyXAM
-/sEpwh3hwPJosAh6vGM6JxuL7CXP8hC1oUvK91VR0hxeDcO/LgdcHtDnlNMqt1wC
-jvYt9Hg+3aY5GehBnQPRppnIMaGhiBrRC6HjBg8Umt6UTUr5PXNY2aia5wRcx4M6
-Tj0O0dAt8WWZ9ySgzOoq4SRoaAp6m4E7CpRNMgXH031OWEeHqtt8rsYqAcvcQLuW
-vIwts5hiXZOfgXyR6SBY3ANE1SjDY46na2G4oiG8FI7eAqYgehjHrXqCnGrzjefE
-V1eVcIr7DBYuM8wq7C9x+qdMir6RNV4MrVD+7rO/drivnd3MaqDHlG0LfMZo6GIK
-QZGIy0z1W5lOXm9x3RAz7/Ea11ynkZyPDDxBE5NRcV6JfukdjDrvsaQA/Qk2Wo7h
-PdUZjv17H4syMdap6tUDTc8Cohut6n1UxnDnhaAYEDGR3TgPqI5vEaJ+yoaM9itv
-b2I/K+0uK6GfWwca7PeTtYn92/5etO4czG99xEBFzw7tiEmBTA8KfseZIUe/i3fr
-9LO+rKEGalFB4mVTYyCKPYYx4hOIvjdCox/jEBTFyYUEhgGnZvArgw9XabvII7eM
-c1FmwnN2CM/MHUzM0Kw7cS/oaoRFcG/PqioO/krL2Bd+xThwSH4Zn+Y1UVO7aXNy
-90MOehHSc2nhN984Y2re3ffVsjPhC3KdWxr8jbho/Az65rUkYg64roiO2ZqdqRvf
-aYtX9fCe8N8SzgLTlWZt+l8sjY8HP2k9NoajphV1nG4iC/pX0ZJiVQ+VBRNaGhSl
-6IhM9gM1ZsI86cULJpOTAhNu1fZBv+Mq8IXYD8SqlNVwVtjvshtlzBN4InSGEKiO
-HM7coo7aDuu+Go5AEiIVMbR09jAa0VINsCVScfSbTFhlGRTrZr2DSO/s8WxbV+Mb
-EQAfZmyrLF71Z3MfIukg+ps5iuqFhZ+gJSXXSFwumpg=
-EOF
-
-exec sh bin/do-setup-circleci-secrets

bin/wait_for.sh

@@ -0,0 +1,21 @@
+#!/bin/bash
+
+# shellcheck disable=SC2155
+wait_for() {
+    local timeout=$1
+    local lock_file=$2
+    for i in $(seq 1 "$timeout"); do
+        if [ -f "$lock_file" ]; then
+            local status="$(cat "$lock_file")"
+            if [ "$status" == "OK" ]; then
+                echo "[$i seconds]: $lock_file found and status: $status." && return
+            else
+                echo "[$i seconds]: $lock_file found and status: $status." && return 1
+            fi
+        fi
+        if ! ((i % 10)); then echo "[$i seconds]: Waiting for $lock_file to be created..."; fi
+        sleep 1
+    done
+    echo "Timed out waiting for test VMs to be ready. See details in: $TEST_VMS_SETUP_OUTPUT_FILE" >&2
+    return 1
+}

build/Dockerfile

@@ -1,21 +1,84 @@
-FROM ubuntu
+FROM golang:1.7.4
 
-RUN apt-get -y update && apt-get -y install --no-install-recommends build-essential git ca-certificates docker.io mercurial libpcap-dev curl make pkg-config gcc bison flex
+# Support Raspberry Pi 2 and newer
+ENV GOARM 7
 
-# 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
+# The names of the architectures that we're fetching cross-compilers for from the Ubuntu packages
+ENV DEB_CROSSPLATFORMS \
+	armhf \
+	arm64
 
-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
+# The go platforms we are supporting to cross-compile
+ENV GO_CROSSPLATFORMS \
+	linux/arm \
+	linux/arm64
 
-# So that sudo does not trample on PATH
-RUN sed -ie '/secure_path/d' /etc/sudoers
+# The names of the gcc cross-compilers we have installed
+ENV GCC_CROSSCOMPILERS \
+	arm-linux-gnueabihf \
+	aarch64-linux-gnu
+
+# Temporarily add the Ubuntu repositories, because we're going to install gcc cross-compilers from there
+# Install the build-essential and crossbuild-essential-ARCH packages
+RUN echo "deb http://archive.ubuntu.com/ubuntu xenial main universe" > /etc/apt/sources.list.d/cgocrosscompiling.list \
+  && apt-key adv --keyserver keyserver.ubuntu.com --recv-keys 40976EAF437D05B5 3B4FE6ACC0B21F32 \
+  && apt-get update \
+  && apt-get install -y build-essential \
+  && for platform in ${DEB_CROSSPLATFORMS}; do apt-get install -y crossbuild-essential-${platform}; done \
+  && rm /etc/apt/sources.list.d/cgocrosscompiling.list \
+  && apt-get update \
+  && apt-get clean && rm -rf /var/lib/apt/lists/*
+
+# Install some required packages
+# libpcap is required because we're linking against its C libraries from the prog/weaver binary
+# flex and bison are required packages for compiling libpcap manually later
+RUN apt-get update \
+	&& apt-get install -y \
+		libpcap-dev \
+		python-requests \
+		time \
+		file \
+		flex \
+		bison
+
+# Install common Go tools
+RUN go get \
+	github.com/golang/lint/golint \
+	github.com/fzipp/gocyclo \
+	gopkg.in/mvdan/sh.v1/cmd/shfmt \
+	github.com/fatih/hclfmt \
+	github.com/client9/misspell/cmd/misspell
+
+# First clean, because we're gonna rebuild the std both with -race enabled and disabled
+# Running go install std twice is intentional and required, as content is written in two different directories
+# (/usr/local/go/pkg/linux_amd64 vs /usr/local/go/pkg/linux_amd64_race)
+# The other architectures do not have support for -race
+RUN go clean -i net \
+	&& go install -tags netgo std \
+	&& go install -race -tags netgo std
+
+# Prebuild std for the other architectures
+RUN for platform in ${GO_CROSSPLATFORMS}; do \
+		GOOS=${platform%/*} GOARCH=${platform##*/} \
+			go install -tags netgo std; done
+
+# Allow full write access to the Go folders for anyone
+RUN chmod -R a+w /usr/local/go
+
+# The libpcap version from Debian packages is 1.6.2, matching that version here although newer versions of libpcap have been released
+# We have to cross-compile the libpcap library for the new architectures, that's what we're doing here
+ENV LIBPCAP_CROSS_VERSION=1.6.2
+RUN curl -sSL http://www.tcpdump.org/release/libpcap-${LIBPCAP_CROSS_VERSION}.tar.gz | tar -xz \
+	&& cd libpcap-${LIBPCAP_CROSS_VERSION} \
+	&& for crosscompiler in ${GCC_CROSSCOMPILERS}; do \
+		CC=${crosscompiler}-gcc ac_cv_linux_vers=2 ./configure --host=${crosscompiler} --with-pcap=linux \
+		&& make \
+		&& export LIB_DIR="/usr/local/lib/${crosscompiler}-gcc" VER="$(cat ./VERSION)" MAJOR_VER="$(sed 's/\([0-9][0-9]*\)\..*/\1/' ./VERSION)" \
+		&& mkdir -p ${LIB_DIR} \
+		&& cp -f libpcap.a libpcap.so.${VER} ${LIB_DIR} \
+		&& ln -sf libpcap.so.${VER} /usr/local/lib/libpcap.so.${MAJOR_VER} \
+		&& ln -sf libpcap.so.${MAJOR_VER} /usr/local/lib/libpcap.so \
+		&& make clean; done
 
 COPY build.sh /
 ENTRYPOINT ["sh", "/build.sh"]

build/build.sh

@@ -1,44 +1,28 @@
 #!/bin/sh
-set -e
 
-GOPATH=/home/go
-export GOPATH
+set -eu
 
 WEAVE_SRC=$GOPATH/src/github.com/weaveworks/weave
 
-if [ $# -eq 0 ] ; 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
+if ! [ -e $WEAVE_SRC ] ; then
+    cat 2>&1 <<EOF
+Nothing at ${WEAVE_SRC}.  Please bind-mount the weave repo 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
+    $ cd weave
+	$ docker run -v $(pwd):/go/src/github.com/weaveworks/weave \\
+		weaveworks/weave-build
 EOF
-        exit 1
-    fi
-
-    # If we run make directly, any files created on the bind mount
-    # will have awkward ownership.  So we switch to a user with the
-    # same user and group IDs as source directory.  We have to set a
-    # few things up so that sudo works without complaining later on.
-    uid=$(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
-    su weave -c "PATH=$PATH make -C $WEAVE_SRC build"
-else
-    # There are arguments to pass to git-clone
-    mkdir -p ${WEAVE_SRC%/*}
-    git clone "$@" $WEAVE_SRC
-    make -C $WEAVE_SRC build
 fi
+
+# If we run make directly, any files created on the bind mount
+# will have awkward ownership.  So we switch to a user with the
+# same user and group IDs as source directory.  We have to set a
+# few things up so that sudo works without complaining later on.
+uid=$(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
+
+su weave -c "PATH=$PATH make -C $WEAVE_SRC BUILD_IN_CONTAINER=false $*"

build/shasums/docker-tgz-armel.sha256sum

@@ -0,0 +1 @@
+8f313a9df867c207ae9ceac6e0935d1d2a0360aafce780dd5d1e0687ee98e0c3 docker-1.10.3.tgz

build/shasums/docker-tgz-x86_64.sha256sum

@@ -0,0 +1 @@
+7541b5490cee1183d911f909c0e91d3d9d57b2b775e40f14a1a7a6de216ca4a8 docker-1.10.3.tgz

build/shasums/qemu-aarch64-static.sha256sum

@@ -0,0 +1 @@
+c02d861383d035ba020b361ef93bf14beb3964a42a6ae645b505b6148493e7ec qemu-aarch64-static

build/shasums/qemu-arm-static.sha256sum

@@ -0,0 +1 @@
+0ff63682b8868620d771aa812d3053dc3c579dc8633ce62d3d7ae7eee83beb06 qemu-arm-static

circle.yml

@@ -2,45 +2,75 @@ general:
   branches:
     ignore:
       - gh\-pages
-      - /pull\/.*/
 
 machine:
+  pre:
+    - curl -sSL https://s3.amazonaws.com/circle-downloads/install-circleci-docker.sh | bash -s -- 1.10.0
   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/
+    PATH: $PATH:$HOME/.local/bin
     CLOUDSDK_CORE_DISABLE_PROMPTS: 1
-    WEAVE_BUILD: $HOME/docker/weave-build.tar
+    STATE: /home/ubuntu/state.env
+    # Base name of VMs for integration tests:
+    NAME: test-$CIRCLE_BUILD_NUM-$CIRCLE_NODE_INDEX
+    TEST_VMS_SETUP_OUTPUT_FILE: $CIRCLE_ARTIFACTS/test_vms_setup_output.txt
+    TEST_VMS_PROV_AND_CONF_LOCK_FILE: $CIRCLE_ARTIFACTS/test_vms_provisioned_and_configured.txt
+    TEST_VMS_READY_LOCK_FILE: $CIRCLE_ARTIFACTS/test_vms_ready.txt
+    # Google Cloud Platorm images for integration tests:
+    USE_IMAGE: 1
+    DISK_NAME_PREFIX: test-$CIRCLE_BUILD_NUM-0
 
 dependencies:
   cache_directories:
     - "~/docker"
-  override:
-    - if [[ -e "$WEAVE_BUILD" ]]; then
-        docker load -i $WEAVE_BUILD;
-      else
-        docker pull weaveworks/weave-build;
-        mkdir -p $(dirname "$WEAVE_BUILD");
-        docker save weaveworks/weave-build >$WEAVE_BUILD;
-      fi
   post:
-    - curl https://sdk.cloud.google.com | bash
-    - bin/setup-circleci-secrets "$SECRET_PASSWORD"
-    - mkdir -p $(dirname $SRCDIR)
-    - cp -r $(pwd)/ $SRCDIR
+    - bin/circle-dependencies-post-sources
+    # Provision & configure testing VMs:
+    - "while [ ! -d $SRCDIR ]; do sleep 1; done; $SRCDIR/bin/provision_test_vms.sh":
+        parallel: true
+        background: true
+    - bin/circle-dependencies-post
 
 test:
+  pre:
+    - "$SRCDIR/bin/circle-test-pre":
+        parallel: true
+        background: true
   override:
-    - docker run -v /var/run/docker.sock:/run/docker.sock -v /home/ubuntu:/home/go weaveworks/weave-build:
+    - "$SRCDIR/bin/circle-test-unit":
         parallel: true
-    - cd $SRCDIR/test; ./gce.sh setup:
-        parallel: true
-    - cd $SRCDIR/test; . ./gce.sh hosts; ./setup.sh:
-        parallel: true
-    - cd $SRCDIR/test; . ./gce.sh hosts; ./run_all.sh:
+    - "$SRCDIR/bin/circle-test-smoke":
         parallel: true
+        timeout: 300
   post:
-    - cd $SRCDIR/test; ./gce.sh destroy:
+    - "$SRCDIR/bin/circle-test-teardown":
         parallel: true
+
+teardown:
+  pre:
+    # Destroy testing VMs:
+    - "cd $SRCDIR/test && ./run-integration-tests.sh destroy":
+        parallel: true
+        background: true
+    - "$SRCDIR/bin/circle-teardown-pre":
+        parallel: true
+
+deployment:
+  release:
+    branch: /[0-9]+\.[0-9]+/
+    owner: weaveworks
+    commands:
+      - "$SRCDIR/bin/circle-deploy-release"
+  master:
+    branch: master
+    owner: weaveworks
+    commands:
+      - "$SRCDIR/bin/circle-deploy-master"
+  issues:
+    branch: /.*/
+    owner: weaveworks
+    commands:
+      - "$SRCDIR/bin/circle-deploy-issues"

common/docker/client.go

@@ -0,0 +1,220 @@
+package docker
+
+import (
+	"errors"
+	"fmt"
+	"strings"
+	"time"
+
+	docker "github.com/fsouza/go-dockerclient"
+
+	"github.com/weaveworks/weave/common"
+)
+
+const (
+	InitialInterval = 1 * time.Second
+	MaxInterval     = 20 * time.Second
+)
+
+// An observer for container events
+type ContainerObserver interface {
+	ContainerStarted(ident string)
+	ContainerDied(ident string)
+	ContainerDestroyed(ident string)
+}
+
+type Client struct {
+	*docker.Client
+}
+
+type syncPair struct {
+	stop chan struct{}
+	done chan struct{}
+}
+
+type pendingStarts map[string]*syncPair
+
+// NewClient creates a new Docker client and checks we can talk to Docker
+func NewClient(apiPath string) (*Client, error) {
+	if apiPath != "" && !strings.Contains(apiPath, "://") {
+		apiPath = "tcp://" + apiPath
+	}
+	dc, err := docker.NewClient(apiPath)
+	if err != nil {
+		return nil, err
+	}
+	client := &Client{dc}
+
+	return client, client.checkWorking()
+}
+
+func NewVersionedClient(apiPath string, apiVersionString string) (*Client, error) {
+	if !strings.Contains(apiPath, "://") {
+		apiPath = "tcp://" + apiPath
+	}
+	dc, err := docker.NewVersionedClient(apiPath, apiVersionString)
+	if err != nil {
+		return nil, err
+	}
+	client := &Client{dc}
+
+	return client, client.checkWorking()
+}
+
+func NewVersionedClientFromEnv(apiVersionString string) (*Client, error) {
+	dc, err := docker.NewVersionedClientFromEnv(apiVersionString)
+	if err != nil {
+		return nil, err
+	}
+	client := &Client{dc}
+
+	return client, client.checkWorking()
+}
+
+func (c *Client) checkWorking() error {
+	_, err := c.Version()
+	return err
+}
+
+func (c *Client) Info() string {
+	env, err := c.Version()
+	if err != nil {
+		return fmt.Sprintf("Docker API error: %s", err)
+	}
+	return fmt.Sprintf("Docker API on %s: %v", c.Endpoint(), env)
+}
+
+func (c *Client) DockerVersion() string {
+	if env, err := c.Version(); err == nil {
+		if v, found := env.Map()["Version"]; found {
+			return v
+		}
+	}
+	return "unknown"
+}
+
+// AddObserver adds an observer for docker events
+func (c *Client) AddObserver(ob ContainerObserver) error {
+	go func() {
+		pending := make(pendingStarts)
+		retryInterval := InitialInterval
+		for {
+			events := make(chan *docker.APIEvents)
+			if err := c.AddEventListener(events); err != nil {
+				c.errorf("Unable to add listener to Docker API: %s - retrying in %ds", err, retryInterval/time.Second)
+			} else {
+				start := time.Now()
+				for event := range events {
+					switch event.Status {
+					case "start":
+						pending.finish(event.ID)
+						pending.start(event.ID, c, ob)
+					case "die":
+						pending.finish(event.ID)
+						ob.ContainerDied(event.ID)
+					case "destroy":
+						pending.finish(event.ID)
+						ob.ContainerDestroyed(event.ID)
+					}
+				}
+				if time.Since(start) > retryInterval {
+					retryInterval = InitialInterval
+				}
+				c.errorf("Event listener channel closed - retrying subscription in %ds", retryInterval/time.Second)
+			}
+			time.Sleep(retryInterval)
+			retryInterval = retryInterval * 3 / 2
+			if retryInterval > MaxInterval {
+				retryInterval = MaxInterval
+			}
+		}
+	}()
+	return nil
+}
+
+// Docker sends a 'start' event before it has attempted to start the
+// container.  Delay notifying the observer until the container has a
+// pid, or we are told to stop when a 'die' event arrives.
+//
+// Note we always deliver the event, even if the container seems to
+// have gone away.
+func (pending pendingStarts) start(id string, c *Client, ob ContainerObserver) {
+	sync := syncPair{make(chan struct{}), make(chan struct{})}
+	pending[id] = &sync
+	go func() {
+		defer close(sync.done)
+		defer ob.ContainerStarted(id)
+		for {
+			if container, err := c.InspectContainer(id); err != nil || container.State.Pid != 0 {
+				return
+			}
+			select {
+			case <-sync.stop:
+				return
+			case <-time.After(200 * time.Millisecond):
+			}
+		}
+	}()
+}
+
+func (pending pendingStarts) finish(id string) {
+	if sync, found := pending[id]; found {
+		close(sync.stop)
+		<-sync.done
+		delete(pending, id)
+	}
+}
+
+func (c *Client) AllContainerIDs() ([]string, error) {
+	all, err := c.ListContainers(docker.ListContainersOptions{All: true})
+	if err != nil {
+		return nil, err
+	}
+	var ids []string
+	for _, c := range all {
+		ids = append(ids, c.ID)
+	}
+	return ids, 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 || container.State.Restarting
+	}
+	if _, notThere := err.(*docker.NoSuchContainer); notThere {
+		return true
+	}
+	c.errorf("Could not check container status: %s", err)
+	return false
+}
+
+// This is intended to find an IP address that we can reach the container on;
+// if it is on the Docker bridge network then that address; if on the host network
+// then localhost
+func (c *Client) GetContainerIP(nameOrID string) (string, error) {
+	info, err := c.InspectContainer(nameOrID)
+	if err != nil {
+		return "", err
+	}
+	if info.NetworkSettings.Networks != nil {
+		if bridgeNetwork, ok := info.NetworkSettings.Networks["bridge"]; ok {
+			return bridgeNetwork.IPAddress, nil
+		} else if _, ok := info.NetworkSettings.Networks["host"]; ok {
+			return "127.0.0.1", nil
+		}
+	} else if info.HostConfig.NetworkMode == "host" {
+		return "127.0.0.1", nil
+	}
+	if info.NetworkSettings.IPAddress == "" {
+		return "", errors.New("No IP address found for container " + nameOrID)
+	}
+	return info.NetworkSettings.IPAddress, nil
+}
+
+// logging
+
+func (c *Client) errorf(fmt string, args ...interface{}) {
+	common.Log.Errorf("[docker] "+fmt, args...)
+}

common/errors.go

@@ -1,20 +0,0 @@
-package common
-
-func CheckFatal(e error) {
-	if e != nil {
-		Error.Fatal(e)
-	}
-}
-
-func CheckWarn(e error) {
-	if e != nil {
-		Warning.Println(e)
-	}
-}
-
-// Assert test is true, panic otherwise
-func Assert(test bool) {
-	if !test {
-		panic("Assertion failure")
-	}
-}

common/http.go

@@ -0,0 +1,18 @@
+package common
+
+import (
+	"net/http"
+)
+
+type loggingHandler struct {
+	next http.Handler
+}
+
+func (l *loggingHandler) ServeHTTP(w http.ResponseWriter, r *http.Request) {
+	Log.Debugf("[http] %s %s", r.Method, r.URL.RequestURI())
+	l.next.ServeHTTP(w, r)
+}
+
+func LoggingHTTPHandler(h http.Handler) http.Handler {
+	return &loggingHandler{next: h}
+}

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 +1,87 @@
 package common
 
 import (
-	"io"
-	"io/ioutil"
+	"bytes"
+	"fmt"
 	"log"
-	"os"
+	"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
+}
+
+func CheckFatal(e error) {
+	if e != nil {
+		Log.Fatal(e)
+	}
+}
+
+func CheckWarn(e error) {
+	if e != nil {
+		Log.Warnln(e)
+	}
+}
+
+// Adaptor type to go from Logrus to something expecting a standard library log.Logger
+type logLogger struct {
+	logger *logrus.Logger
+}
+
+// io.Writer interface
+func (l logLogger) Write(p []byte) (n int, err error) {
+	ln := len(p)
+	// Strip a trailing newline, because logrus formatter adds one
+	if ln > 0 && p[ln-1] == '\n' {
+		p = p[:ln-1]
+	}
+	l.logger.Info(string(p))
+	return ln, nil
+}
+
+func LogLogger() *log.Logger {
+	return log.New(logLogger{Log}, "", 0)
 }

common/odp/odp.go

@@ -0,0 +1,91 @@
+package odp
+
+import (
+	"fmt"
+	"net"
+	"syscall"
+
+	"github.com/weaveworks/go-odp/odp"
+)
+
+// ODP admin functionality
+
+func CreateDatapath(dpname string) (supported bool, err error) {
+	dpif, err := odp.NewDpif()
+	if err != nil {
+		if odp.IsKernelLacksODPError(err) {
+			return false, nil
+		}
+		return true, err
+	}
+	defer dpif.Close()
+
+	dp, err := dpif.CreateDatapath(dpname)
+	if err != nil {
+		if !odp.IsDatapathNameAlreadyExistsError(err) {
+			return true, err
+		}
+		if dp, err = dpif.LookupDatapath(dpname); err != nil {
+			return true, err
+		}
+	}
+
+	// Pick an ephemeral port number to use in probing for vxlan
+	// support.
+	udpconn, err := net.ListenUDP("udp4", nil)
+	if err != nil {
+		return true, err
+	}
+	defer udpconn.Close()
+
+	// we leave the UDP socket open, so creating a vxlan vport on
+	// the same port number should fail.  But that's fine: It's
+	// still sufficient to probe for support.
+	portno := uint16(udpconn.LocalAddr().(*net.UDPAddr).Port)
+	vpid, err := dp.CreateVport(odp.NewVxlanVportSpec(fmt.Sprintf("vxlan-%d", portno), portno))
+	if nlerr, ok := err.(odp.NetlinkError); ok {
+		if syscall.Errno(nlerr) == syscall.EAFNOSUPPORT {
+			dp.Delete()
+			return false, fmt.Errorf("kernel does not have Open vSwitch VXLAN support")
+		}
+	}
+	if err == nil {
+		dp.DeleteVport(vpid)
+	}
+
+	return true, nil
+}
+
+func DeleteDatapath(dpname string) error {
+	dpif, err := odp.NewDpif()
+	if err != nil {
+		return err
+	}
+	defer dpif.Close()
+
+	dp, err := dpif.LookupDatapath(dpname)
+	if err != nil {
+		if odp.IsNoSuchDatapathError(err) {
+			return nil
+		}
+		return err
+	}
+
+	return dp.Delete()
+}
+
+func AddDatapathInterface(dpname string, ifname string) error {
+	dpif, err := odp.NewDpif()
+	if err != nil {
+		return err
+	}
+	defer dpif.Close()
+
+	dp, err := dpif.LookupDatapath(dpname)
+	if err != nil {
+		return err
+	}
+
+	_, err = dp.CreateVport(odp.NewNetdevVportSpec(ifname))
+	return err
+}

common/process.go

@@ -0,0 +1,27 @@
+package common
+
+import (
+	"os"
+	"strconv"
+)
+
+func AllPids(procRoot string) ([]int, error) {
+	fh, err := os.Open(procRoot)
+	if err != nil {
+		return nil, err
+	}
+	defer fh.Close()
+	dirNames, err := fh.Readdirnames(-1)
+	if err != nil {
+		return nil, err
+	}
+	pids := make([]int, len(dirNames))
+	for _, dirName := range dirNames {
+		pid, err := strconv.Atoi(dirName)
+		if err != nil { // Only interested in numeric entries - skip /proc/stat, etc.
+			continue
+		}
+		pids = append(pids, pid)
+	}
+	return pids, err
+}

common/signals.go

@@ -1,37 +0,0 @@
-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
-	Status() string
-}
-
-func SignalHandlerLoop(ss ...SignalReceiver) {
-	sigs := make(chan os.Signal, 1)
-	signal.Notify(sigs, syscall.SIGINT, syscall.SIGQUIT, syscall.SIGUSR1)
-	buf := make([]byte, 1<<20)
-	for {
-		switch <-sigs {
-		case syscall.SIGINT:
-			Info.Printf("=== received SIGINT ===\n*** exiting\n")
-			for _, subsystem := range ss {
-				subsystem.Stop()
-			}
-			return
-		case syscall.SIGQUIT:
-			stacklen := runtime.Stack(buf, true)
-			Info.Printf("=== received SIGQUIT ===\n*** goroutine dump...\n%s\n*** end\n", buf[:stacklen])
-		case syscall.SIGUSR1:
-			for _, subsystem := range ss {
-				Info.Printf("=== received SIGUSR1 ===\n*** status...\n%s\n*** end\n", subsystem.Status())
-			}
-		}
-	}
-}

common/updater/updater.go

@@ -1,47 +0,0 @@
-package updater
-
-import (
-	"github.com/fsouza/go-dockerclient"
-	. "github.com/weaveworks/weave/common"
-)
-
-type ContainerObserver interface {
-	ContainerDied(ident string) error
-}
-
-func checkError(err error, apiPath string) {
-	if err != nil {
-		Error.Fatalf("[updater] Unable to connect to Docker API on %s: %s",
-			apiPath, err)
-	}
-}
-
-func Start(apiPath string, ob ContainerObserver) 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(ob, event, client)
-		}
-	}()
-	return nil
-}
-
-func handleEvent(ob ContainerObserver, event *docker.APIEvents, client *docker.Client) error {
-	switch event.Status {
-	case "die":
-		id := event.ID
-		ob.ContainerDied(id)
-	}
-	return nil
-}

common/utils.go

@@ -0,0 +1,18 @@
+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")
+}

db/boltdb.go

@@ -0,0 +1,109 @@
+package db
+
+import (
+	"bytes"
+	"encoding/gob"
+	"fmt"
+	"time"
+
+	"github.com/boltdb/bolt"
+)
+
+type DB interface {
+	Load(string, interface{}) (bool, error)
+	Save(string, interface{}) error
+}
+
+type BoltDB struct {
+	db *bolt.DB
+}
+
+var (
+	versionIdent       = []byte("version")
+	persistenceVersion = []byte{1, 0} // major.minor
+	topBucket          = []byte("top")
+)
+
+const (
+	NameIdent = "peername"
+	FileName  = "data.db"
+)
+
+func NewBoltDB(dbPathname string) (*BoltDB, error) {
+	db, err := bolt.Open(dbPathname, 0660, nil)
+	if err != nil {
+		return nil, fmt.Errorf("[boltDB] Unable to open %s: %s", dbPathname, err)
+	}
+	err = db.Update(checkVersion(false))
+	return &BoltDB{db: db}, err
+}
+
+func NewBoltDBReadOnly(dbPathname string) (*BoltDB, error) {
+	options := bolt.Options{Timeout: time.Millisecond * 50, ReadOnly: true}
+	db, err := bolt.Open(dbPathname, 0660, &options)
+	if err != nil {
+		return nil, fmt.Errorf("[boltDB] Unable to open %s: %s", dbPathname, err)
+	}
+	err = db.View(checkVersion(true))
+	if err != nil {
+		return nil, fmt.Errorf("[boltDB] Cannot use persistence file %s: %s", dbPathname, err)
+	}
+	return &BoltDB{db: db}, nil
+}
+
+func checkVersion(readOnly bool) func(tx *bolt.Tx) error {
+	return func(tx *bolt.Tx) error {
+		if top := tx.Bucket(topBucket); top == nil {
+			if readOnly {
+				return fmt.Errorf("no top bucket")
+			}
+			top, err := tx.CreateBucket(topBucket)
+			if err != nil {
+				return err
+			}
+			if err := top.Put(versionIdent, persistenceVersion); err != nil {
+				return err
+			}
+		} else {
+			if checkVersion := top.Get(versionIdent); checkVersion != nil {
+				if checkVersion[0] != persistenceVersion[0] {
+					return fmt.Errorf("mismatched version %x", checkVersion)
+				}
+			}
+		}
+		return nil
+	}
+}
+
+func (d *BoltDB) Load(ident string, data interface{}) (bool, error) {
+	found := true
+	err := d.db.View(func(tx *bolt.Tx) error {
+		b := tx.Bucket(topBucket)
+		v := b.Get([]byte(ident))
+		if v == nil {
+			found = false
+			return nil
+		}
+		reader := bytes.NewReader(v)
+		decoder := gob.NewDecoder(reader)
+		err := decoder.Decode(data)
+		return err
+	})
+	return found, err
+}
+
+func (d *BoltDB) Save(ident string, data interface{}) error {
+	return d.db.Update(func(tx *bolt.Tx) error {
+		b := tx.Bucket(topBucket)
+		buf := new(bytes.Buffer)
+		enc := gob.NewEncoder(buf)
+		if err := enc.Encode(data); err != nil {
+			return err
+		}
+		return b.Put([]byte(ident), buf.Bytes())
+	})
+}
+
+func (d *BoltDB) Close() error {
+	return d.db.Close()
+}

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
@@ -66,23 +66,23 @@ Router:
     simply responds to traffic received from the remote peer via TCP
   5. We register this connection with the local peer
   6a. If we initiated this connection then we now start sending fast
-    heartbeats to the remote peer so that the remote peer can determine what
-    address/port it should use to send UDP back to us. To do this, we
-    spawn off two further threads which are the forwarder
-    loops. These receive frames which are to be sent to the remote
-    peer. One of them sends frames without the DF flag set. To do this
-    it just sends the packets out of the UDP Listener socket. The
-    other needs to send frames with the DF flag set and needs its own
-    socket so that it can do PMTU discovery easily. To do this, it
-    uses a Raw IP socket (IP has no ports, so there's no collision
-    issue with the UDP Listener socket) and so it must add UDP headers
-    itself.
-  6b. If we did not initiate this connection then the UDP Listener
+    heartbeats to the remote peer so that the remote peer can
+    determine what address/port it should use to send UDP back to
+    us. To do this, we spawn off a "forwarder" thread to send
+    heartbeats, monitor incoming heartbeats, and some other auxiliary
+    duties.  It also consumes frames to be encapsulated and send via
+    UDP from two channels, for DF and non-DF cases.  In the non-DF
+    case, it can just send the packets out of the UDP Listener
+    socket. In the DF case, it needs its own socket so that it can do
+    PMTU discovery easily. To do this, it uses a Raw IP socket (IP has
+    no ports, so there's no collision issue with the UDP Listener
+    socket) and so it must add UDP headers itself.
+ 6b. If we did not initiate this connection then the UDP Listener
     should start receiving fast heartbeats from the remote peer. From
     those it should be able to identify the local connection via the
     local peer. It will tell the local connection (communicating to
     the actor thread) about the UDP address of the remote peer. The
-    local connection will then start its forwarder threads as
+    local connection will then start its forwarder thread as
     described in 6a, and start sending fast heartbeats. We send to the
     remote peer via TCP a ConnectionEstablished message. The remote
     peer receives this (on the TCP receiver process), tells the

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 192.168.122.2
+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/fastdp-crypto.md

@@ -0,0 +1,155 @@
+This document describes implementation details of the fast datapath encryption.
+
+# Overview
+
+At the high level, we use the ESP protocol ([RFC 2406][esp]) in the Transport
+mode. Each packet is encrypted with AES in GCM mode ([RFC 4106][aesgcm]), with
+32 byte key and 4 byte salt. This combo provides the following security
+properties:
+
+* Data confidentiality.
+* Data origin authentication.
+* Integrity.
+* Anti-replay.
+* Limited traffic flow confidentiality as fast datapath VXLAN packets are fully
+  encrypted.
+
+## Notation
+
+* `SAin`:  IPsec security association for inbound connections.
+* `SAout`: IPsec security association for outbound connections.
+* `SPout`: IPsec security policy for outbound connections. Used to match
+           outbound flows to SAout.
+
+## SA Key Derivation
+
+For each connection direction, a different AES-GCM key and salt is used.
+The pairs are derived with HKDF ([RFC 5869][hkdf]):
+
+```
+SAin[KeyAndSalt] = HKDF(sha256, ikm=sessionKey, salt=nonceIn, info=localPeerName)
+SAout[KeyAndSalt] = HKDF(sha256, ikm=sessionKey, salt=nonceOut, info=remotePeerName)
+```
+
+Where:
+
+* the mutual `sessionKey` is derived by the [Mesh][mesh] library during
+  the control plane connection establishment between the local peer and
+  the remote peer.
+* `nonceIn` and `nonceOut` are randomly generated 32byte nonces which
+  are exchanged over the encrypted control plane channel.
+
+## SPI
+
+A directional secure connection between two peers is identified with SPI.
+
+The kernel requires the pair of SPI and dst IP to be unique among security
+associations. Thus, to avoid collisions, we generate outbound SPI on a remote
+peer.
+
+## Connection Establishment
+
+```
+Peer A                                                        Peer B
+-----------------------------------------------------------------------------------------------------------------
+
+fastdp.fwd.Confirm():
+    install iptables blocking rules,                          fastdp.fwd.Confirm():
+    nonce_BA = rand(),                                            install iptables blocking rules,
+    {key,salt}_BA = hkdf(sessionKey, nonce_BA, A),                nonce_AB = rand(),
+    spi_BA = allocspi(),                                          {key,salt}_AB = hkdf(sessionKey, nonce_AB, B),
+    create SA_BA(B<-A, spi_BA, key_BA, salt_BA),                  spi_AB = allocspi(),
+    send InitSARemote(spi_BA, nonce_BA). -->                      create SA_AB(A<-B, spi_AB, key_AB, salt_AB),
+                                                              <-- send InitSARemote(spi_AB, nonce_AB).
+
+
+                                                          --> recv InitSARemote(spi_BA, nonce_BA):
+recv InitSARemote(spi_AB, nonce_AB): <--                          {key,salt}_BA = hkdf(sessionKey, nonce_BA, A),
+    {key,salt}_AB = hkdf(sessionKey, nonce_AB, B),                create SA_BA(B<-A, spi_BA, key_BA, salt_BA),
+    create SA_AB(A<-B, spi_AB, key_AB, salt_AB),                  create SP_BA(B<-A, spi_BA),
+    create SP_AB(A<-B, spi_AB),                                   install marking rule.
+    install marking rule.
+```
+
+# Implementation Details
+
+## XFRM
+
+The implementation is based on the kernel IP packet transformation framework
+called XFRM. Unfortunately, docs are barely existing and the complexity of
+the framework is high. The best resource I found is Chapter 10 in
+"Linux Kernel Networking: Implementation and Theory" by Rami Rosen.
+
+## iptables Rules
+
+The kernel VXLAN driver does not set a dst port of a tunnel in the ip flow
+descriptor, thus XFRM policy lookup cannot match a policy (SPout) which includes
+the port. This makes impossible to encrypt only tunneled traffic between
+peers. To work around, we mark such outgoing packets with iptables and set
+the same mark in the policy selector (funnily enough, `iptables_mangle` module
+eventually sets the missing dst port in the flow descriptor). The challenge
+here is to pick a mark that it would not interfere with other networking
+applications before OUTPUT'ing a packet. For example, Kubernetes by default
+uses 1<<14 and 1<<15 marks and we choose 1<<17 (0x20000). Additionally,
+such workaround brings the requirement for at least the 4.2 kernel.
+
+The marking rules are the following:
+
+```
+iptables -t mangle -A OUTPUT -j WEAVE-IPSEC-OUT
+iptables -t mangle -A WEAVE-IPSEC-OUT -s ${LOCAL_PEER_IP} -d ${REMOTE_PEER_IP} \
+         -p udp --dport ${TUNNEL_PORT} -j WEAVE-IPSEC-OUT-MARK
+iptables -t mangle -A WEAVE-IPSEC-OUT-MARK --set-xmark ${MARK} -j MARK
+```
+
+As Linux does not implement [IP Security Levels][ipseclevel], we install
+additional iptables rules to prevent from accidentally sending unencrypted
+traffic between peers which have previously established the secure connection.
+
+For inbound traffic, we mark each ESP packet with the mark and drop non-marked
+tunnel traffic:
+
+```
+iptables -t mangle -A INPUT -j WEAVE-IPSEC-IN
+iptables -t mangle -A WEAVE-IPSEC-IN -s ${REMOTE_PEER_IP} -d ${LOCAL_PEER_IP} \
+         -m esp --espspi ${SPIin} -j WEAVE-IPSEC-IN-MARK
+iptables -t mangle -A WEAVE-IPSEC-IN-MARK --set-xmark ${MARK} -j MARK
+
+iptables -t filter -A INPUT -j WEAVE-IPSEC-IN
+iptables -t filter -A WEAVE-IPSEC-IN -s ${REMOTE_PEER_IP} -d ${LOCAL_PEER_IP} \
+         -p udp --dport ${TUNNEL_PORT} -m mark ! --mark ${MARK} -j DROP
+```
+
+For outbound traffic, we drop marked traffic which does not match any SPout:
+
+```
+iptables -t filter -A OUTPUT ! -p esp -m policy --dir out --pol none \
+         -m mark --mark ${MARK} -j DROP
+```
+
+## ESN
+
+To prevent from cycling SeqNo which makes replay attacks possible, we use
+64-bit extended sequence numbers known as [ESN](esn).
+
+## MTU
+
+In addition to the VXLAN overhead, the MTU calculation should take into account
+the ESP overhead which is 34-37 bytes (encrypted Payload is 4 bytes aligned) and
+consists of:
+
+* 4 bytes (SPI).
+* 4 bytes (Sequence Number).
+* 8 bytes (ESP IV).
+* 1 byte (Pad Length).
+* 1 byte (NextHeader).
+* 16 bytes (ICV).
+* 0-3 bytes (Padding).
+
+
+[esp]:              https://tools.ietf.org/html/rfc2406
+[aesgcm]:           https://tools.ietf.org/html/rfc4106
+[hkdf]:             https://tools.ietf.org/html/rfc5869
+[esn]:              https://tools.ietf.org/html/rfc4304
+[ipseclevel]:       https://tools.ietf.org/html/draft-mcdonald-simple-ipsec-api-01)
+[mesh]:             https://github.com/weaveworks/mesh

docs/fastdp.md

@@ -0,0 +1,170 @@
+# Overlay Method Selection
+
+Weave automatically selects the best working overlay implementation
+when connecting to a new peer. It does this by initiating both
+forwarders in parallel, eventually settling on the most preferred
+established forwarder at which point the other forwarder is shut down,
+assuming it had not failed already. In the event that the remaining
+forwarder fails at a later time (e.g. because of a heartbeat timeout)
+the control plane TCP connection will recycle allowing the selection
+algorithm to run again. By default fast datapath is preferred over
+Sleeve.
+
+# Local Bridging
+
+Unlike the weave bridge netdev used by Sleeve, the OVS datapath has no
+inherent bridging capability. Consequently fastdp implements an
+ethernet bridge in addition to the vxlan overlay, maintaining its own
+forwarding database by learning MAC addresses and dispatching
+broadcast, unicast & multicast traffic accordingly.
+
+# Short Peer IDs
+
+The router relies on having access to the source and destination peer
+when deciding how to forward packets. When the Sleeve overlay is in
+use this information is conveyed directly within the encapsulation by
+including the names of the peers in question, a solution not
+accommodated directly by the vxlan wire format. Fortunately vxlan does
+have a twenty four bit segment ID field in the header we can use to
+encode this data - the challenge is to identify peers uniquely with a
+twelve bit identifier instead of the seventeen bytes used by Sleeve.
+In practice this is achieved by peers adopting a random 'short ID' and
+resolving ownership collisions of same via the existing gossip
+mechanism.
+
+# Heartbeats via vxlan
+
+Heartbeats are implemented by sending an encapsulated ethernet frame
+with source and destination MAC addresses of `00:00:00:00:00:00` and a
+payload consisting of the connection UID and total ethernet frame
+length. The vxlan vport miss handler on the receiving side detects the
+all-zero addresses and acknowledges the heartbeat via the TCP control
+channel after validating the connection UID and frame length against
+their expected values.
+
+# PMTU Discovery
+
+The length of the heartbeat ethernet frame is set to the MTU of the
+datapath interface. In the event the vxlan packet is dropped or
+truncated, the heartbeat will not be acknowledged; this lack of
+acknowledgement will cause the peers to fall back to the Sleeve
+overlay, which has a more sophisticated dynamic mechanism for coping
+with low path MTUs.
+
+To avoid triggering this fallback in typical deployments, the datapath
+interface is statically configured with an MTU of 1376 bytes allowing
+it to work with most underlay network provider MTUs, including GCE at
+1460 bytes (the eighty four byte difference accommodates the encrypted vxlan overhead).
+This value can be overridden by setting `WEAVE_MTU` at launch if
+necessary.
+
+# Virtual Ports
+
+There are three kinds of virtual port associated with the weave
+datapath:
+
+* `internal` - one of these is created automatically, named after the
+  datapath. It corresponds to the network interface of the same name
+  that appears on the host when the datapath is created; it is the
+  ingress/egress port for `weave expose`
+* `netdev` - one for each application container, corresponding to the
+  host end of the veth pair
+* `vxlan` - one for each UDP port on which we are listening for vxlan
+  encapsulated packets. Typically there is only one of these, but
+  there may be more in a network in which peers do not all use the same
+  port configuration
+
+# Misses and Flow Creation
+
+As mentioned above, the datapath has no inherent behaviour - any
+ingressing packet which does not match a flow is passed to a userspace
+miss handler. The miss handler is then responsible for a) instructing
+the datapath to take actions for the packet that caused the miss (for
+example by copying it to one or more ports) and optionally b)
+installing flow rules which will allow the datapath to act on similar
+packets in future without invoking the miss handler.
+
+At a high level the fast datapath implementation can be viewed as a
+set of miss handlers that determine what actions the OVS datapath
+should take based on router topology information, together with some
+additional machinery that manages the expiry of resulting flows when
+that state changes.
+
+When a miss handler is invoked, it has two pieces of context: a byte
+array containing the packet that triggered the miss, and a set of
+'flow keys' that have been extracted from the packet by the kernel
+module. The following flow keys are of interest to weave:
+
+* `InPort` - the identifier of the ingress virtual port
+* `Ethernet` - the source and destination MAC addresses of the
+  ethernet frame
+* `Tunnel` - tunnel identifier (see section on short peer IDs above),
+  and source/dest IPv4 addresses. Only present for ingress via a vxlan
+  vport
+
+Crucially, the router must use this information alone to determine
+which actions to take - this allows the specification of a flow which
+matches these keys and instructs the kernel to take action
+automatically in future without further userspace involvement.
+
+Two actions are of interest:
+
+* `Output` - output the packet to the specified vport
+* `SetTunnel` - update the effective vxlan tunnel parameters. Only
+  required prior to output from a vxlan vport
+
+It is possible to have multiple actions in a flow, so the router can
+for example create a single rule that copies broadcast traffic to all
+'local' vports (save the ingress vport obviously) as well as to vxlan
+vports for onward peers as dictated by the routing topology.
+
+Every flow specified by the router has the following characteristics:
+
+* An `InPort` key matching the ingress vport
+* A `Tunnel` key if the ingress vport is of type vxlan
+* An `Ethernet` key matching the source and destination MAC
+* A list of `Output` (for internal and netdev vports) and
+  `SetTunnel`+`Output` (for vxlan vports) actions
+
+Under certain circumstances the miss handler will instruct the
+datapath to execute a set of actions for a packet without creating a
+corresponding flow:
+
+* When broadcasting packets to discover the path to unknown
+  destination MACs. This condition is transient in the overwhelming
+  majority of cases and so the benefit of creating a flow is
+  outweighed by the need to invalidate it once the MAC is learned
+* When the packet also needs to be forwarded to one or more peers via
+  Sleeve. In this case the router needs to handle all subsequent
+  matching packets as there is no OVS flow action to do it without
+  userspace involvement
+
+# Flow Invalidation
+
+Once a flow has been created for a particular combination of keys, the
+miss handler will never again be invoked for matching packets. It is
+therefore extremely important that we detect events which invalidate
+existing flow actions:
+
+* Addition of netdev vports to the datapath
+* Route invalidation (topology change)
+* Short peer ID collision
+
+The response in each case is the same - delete all flows from the
+datapath, allowing them to be recreated taking into account the
+updated state.
+
+In addition to these event based invalidations there is an expiry
+process that executes every five minutes. This process enumerates all
+flows in the datapath, removing any which have not been used since the
+last check; this cleans up:
+
+* Flows referring to netdev vports which have been removed
+* Flows created by forwarders which have been stopped
+* Flows related to MAC addresses which have not communicated recently
+
+Flows keyed on tunnel IPv4 address do not need to be cleared when a
+peer appears to change IP address due to NAT; this will cause a miss
+resulting in a new flow, and the old flow will expire naturally via
+the timer mechanism.
+

docs/ipam.md

@@ -20,11 +20,16 @@ plugin) uses to request IP addresses.
 
 The commands supported by the allocator via the http interface are:
 
-- Allocate: request one IP address for a container
+- 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.
@@ -48,25 +53,42 @@ freed.
 
 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 (all owned ranges are full), it will ask another peer for space:
+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
+    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.
+    copy of the ring tells it all peers are full in that subnet.
+
+### Data persistence
+
+Key IPAM data is saved to disk, in a [BoltDB](https://github.com/boltdb/bolt)
+file, stored within a [data volume container](https://docs.docker.com/engine/userguide/containers/dockervolumes/#creating-and-mounting-a-data-volume-container)
+named `weavedb`.
+
+This file is used to persist data for various Weave Net components; for IPAM it contains:
+
+* the division of the IP allocation range amongst peers, and
+* allocation of addresses to containers on the local peer,
+
+so that it is immediately available when the peer restarts.
 
 ### 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.
+If a Weave process is restarted,
+
+- if `weavedb` is present, then it loads persisted IPAM data from there, as
+described, in the previous section;
+- else, it learns from other peers which ranges it used to own.
+
+Weave Net then consults the allocator to know which individual IP addresses
+are assigned to containers, and therefore avoid giving the same address out in
+subsequent allocation requests.
 
 When the Allocator is told to claim an address, there are four
 possibilities:
@@ -204,11 +226,3 @@ 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 +1,157 @@
+# 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 `$GITHUB_TOKEN` with this value
+
+## Release Types
+
+The release script behaves differently depending on the kind of
+release you are doing. There are three types:
+
+* **Mainline** - a release (typically from master) with version tag
+  `vX.Y.Z` where Z is zero (e.g. `v2.1.0`)
+* **Branch** - a bugfix release (typically from a branch) with version tag
+  `vX.Y.Z` where Z is non-zero (e.g `v2.1.1`)
+* **Prerelease** - a release from an arbitrary branch with an arbitrary
+  version tag (e.g. `feature-preview-20150904`)
+
+N.B. the release script _infers the release type from the format of the
+version tag_. Ensure your tag is in the correct format and the desired
+behaviours for that type of release will be obtained from the script.
+
+## Build Phase
+### Update CHANGELOG.md
+
+* Checkout the branch from which you wish to release
+* Choose a version tag (see above) henceforth referred to as `$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` for **Prerelease** builds, `## Release ${TAG#v}` otherwise.
+
+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 branch and version tag upstream, so that an
+associated GitHub release may be created:
+
+    git push git@github.com:weaveworks/weave
+    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
+
+### Finish up
+
+* If not on master, merge branch into master and push to GitHub.
+* Close the [milestone](https://github.com/weaveworks/weave/milestones) in GitHub and create the next milestone
+* Update the `#weavenetwork` topic heading on freenode (requires 'chanops' permission)
+* For a mainline release vX.Y.0, create a release branch X.Y from the
+  tag and push to GitHub - this will result in X.Y.0 site docs being
+  published to https://www.weave.works
+* Add the new version of `weave-net` to the checkpoint system at
+  https://checkpoint-api.weave.works/admin
+* File a PR to update the version of the daemonset at
+  https://github.com/kubernetes/kops/tree/master/upup/models/cloudup/resources/addons/networking.weave
+
+## 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.

docs/weavedns-design.md

@@ -0,0 +1,83 @@
+---
+title: WeaveDNS (service discovery) Design Notes
+layout: default
+---
+
+# WeaveDNS (service discovery) Design Notes
+
+The model is that each host has a service that is notified of
+hostnames and weave addresses for containers on the host.  Like IPAM,
+this service is embedded within the router.  It binds to
+the host bridge to answer DNS queries from local containers; for
+anything it can't answer, it uses the information in the host's
+/etc/resolv.conf to query an 'fallback' server.
+
+The service is comprised of a DNS server, which answers all DNS queries
+from containers, and a in-memory database of hostnames and IPs.  The
+database on each node contains a complete copy of the hostnames and IPs
+for every containers in the cluster.
+
+For hostname queries in the local domain (default weave.local), the DNS
+server will consult the in-memory database.  For reverse queries, we
+first consult the local database, and if not found we query the
+upstream server.  For all other queries, we consult the upstream
+server.
+
+Updates to the in-memory database are broadcast to other DNS servers
+within the cluster.  The in-memory database only contains entries from
+connected DNS servers; if a DNS server becomes partitioned from the
+cluster, entries belonging to that server are removed from each node in
+the cluster.  When the partitioned DNS server reconnects, the entries
+are re-broadcast around the cluster.
+
+The DNS server also listens to the Docker event stream, and removes
+entries for containers when they die.  Entries removed in this way are
+tombstoned, and the tombstone lazily broadcast around the cluster.
+After a short timeout the tombstones are independently removed from
+each host.
+
+
+## DNS server API
+
+The DNS server accepts HTTP requests on the following URL (patterns)
+and methods:
+
+`PUT /name/<identifier>/<ip-address>`
+
+Put a record for an IP, bound to a host-scoped identifier (e.g., a
+container ID), in the DNS database.  The request body must contain
+a `fqdn=foo.weave.local` key pair.
+
+`DELETE /name/<identifier>/<ip-address>`
+
+Remove a specific record for an IP and host-scoped identifier. The request
+body can optionally contain a `fqdn=foo.weave.local` key pair.
+
+`DELETE /name/<identifier>`
+
+Remove all records for the host-scoped identifier.
+
+`GET /name/<fqdn>`
+
+List of all IPs (in JSON format) for givne FQDN.
+
+## DNS updater
+
+The updater component uses the Docker remote API to monitor containers
+coming and going, and tells the DNS server to update its records via
+its HTTP interface. It does not need to be attached to the weave
+network.
+
+The updater starts by subscribing to the events, and getting a list of
+the current containers. Any containers given a domain ending with
+".weave" are considered for inclusion in the name database.
+
+When it sees a container start or stop, the updater checks the weave
+network attachment of the container, and updates the DNS server.
+
+> How does it check the network attachment from within a container?
+
+> Will it need to delay slightly so that `attach` has a chance to run?
+> Perhaps it could put containers on a watch list when it's noticed
+> them.
+

docs/weavenpc-design.md

@@ -0,0 +1,106 @@
+# Overview
+
+# ipsets
+
+The policy controller maintains a number of ipsets which are
+subsequently referred to by the iptables rules used to effect network
+policy specifications. These ipsets are created, modified and
+destroyed automatically in response to Pod, Namespace and
+NetworkPolicy object updates from the k8s API server:
+
+* A `hash:ip` set per namespace, containing the IP addresses of all
+  pods in that namespace
+* A `list:set` per distinct (across all network policies in all
+  namespaces) namespace selector mentioned in a network policy,
+  containing the names of any of the above hash:ip sets whose
+  corresponding namespace labels match the selector
+* A `hash:ip` set for each distinct (within the scope of the
+  containing network policy's namespace) pod selector mentioned in a
+  network policy, containing the IP addresses of all pods in the
+  namespace whose labels match that selector
+
+IPsets are implemented by the kernel module `xt_set`, without which
+weave-npc will not work.
+
+ipset names are generated deterministically from a string
+representation of the corresponding label selector. Because ipset
+names are limited to 31 characters in length, this is done by taking a
+SHA hash of the selector string and then printing that out as a base
+85 string with a "weave-" prefix e.g.:
+
+    weave-k?Z;25^M}|1s7P3|H9i;*;MhG
+
+Because pod selectors are scoped to a namespace, we need to make sure
+that if the same selector definition is used in different namespaces
+that we maintain distinct ipsets. Consequently, for such selectors the
+namespace name is prepended to the label selector string before
+hashing to avoid clashes.
+
+# iptables chains
+
+The policy controller maintains two iptables chains in response to
+changes to pods, namespaces and network policies. One chain contains
+the ingress rules that implement the network policy specifications,
+and the other is used to bypass the ingress rules for namespaces which
+have an ingress isolation policy of `DefaultAllow`.
+
+## Dynamically maintained `WEAVE-NPC-DEFAULT` chain
+
+The policy controller maintains a rule in this chain for every
+namespace whose ingress isolation policy is `DefaultAllow`. The
+purpose of this rule is simply to ACCEPT any traffic destined for such
+namespaces before it reaches the ingress chain.
+
+```
+iptables -A WEAVE-NPC-DEFAULT -m set --match-set $NSIPSET dst -j ACCEPT
+```
+
+## Dynamically maintained `WEAVE-NPC-INGRESS` chain
+
+For each namespace network policy ingress rule peer/port combination:
+
+```
+iptables -A WEAVE-NPC-INGRESS -p $PROTO [-m set --match-set $SRCSET] -m set --match-set $DSTSET --dport $DPORT -j ACCEPT
+```
+
+## Static `WEAVE-NPC` chain
+
+Static configuration:
+
+```
+iptables -A WEAVE-NPC -m state --state RELATED,ESTABLISHED -j ACCEPT
+iptables -A WEAVE-NPC -m state --state NEW -j WEAVE-NPC-DEFAULT
+iptables -A WEAVE-NPC -m state --state NEW -j WEAVE-NPC-INGRESS
+```
+
+# Steering traffic into the policy engine
+
+To direct traffic into the policy engine:
+
+iptables -A FORWARD -o weave -m physdev ! --physdev-out vethwe-bridge -j WEAVE-NPC
+iptables -A FORWARD -o weave -m physdev ! --physdev-out vethwe-bridge -j DROP
+
+Note this only affects traffic which egresses the bridge on a physical
+port which is not the Weave Net router - in other words, it is
+destined for an application container veth. The following traffic is
+affected:
+
+* Traffic bridged between local application containers
+* Traffic bridged from the router to a local application container
+* Traffic originating from the internet destined for nodeports - this
+  is routed via the FORWARD chain to a container pod IP after DNAT
+
+The following traffic is NOT affected:
+
+* Traffic bridged from a local application container to the router
+* Traffic originating from processes in the host network namespace
+  (e.g. kubelet health checks)
+* Traffic routed from an application container to the internet
+
+The above mechanism relies on the kernel module `br_netfilter` being
+loaded and enabled via `/proc/sys/net/bridge/bridge-nf-call-iptables`.
+
+See these resources for helpful context:
+
+* http://ebtables.netfilter.org/br_fw_ia/br_fw_ia.html
+* https://commons.wikimedia.org/wiki/File:Netfilter-packet-flow.svg

ipam/address/address.go

@@ -1,61 +0,0 @@
-package address
-
-import (
-	"github.com/weaveworks/weave/common"
-	"net"
-)
-
-// 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 ParseIP(s string) (Address, error) {
-	if ip := net.ParseIP(s); ip == nil {
-		return 0, &net.ParseError{Type: "IP Address", Text: s}
-	} else {
-		return FromIP4(ip), nil
-	}
-}
-
-// 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) 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
-}

ipam/allocate.go

@@ -2,7 +2,9 @@ package ipam
 
 import (
 	"fmt"
-	"github.com/weaveworks/weave/ipam/address"
+
+	"github.com/weaveworks/weave/api"
+	"github.com/weaveworks/weave/net/address"
 )
 
 type allocateResult struct {
@@ -12,8 +14,10 @@ type allocateResult struct {
 
 type allocate struct {
 	resultChan       chan<- allocateResult
+	ident            string       // a container ID, something like "weave:expose", or api.NoContainerID
+	r                address.CIDR // Subnet we are trying to allocate within
+	isContainer      bool         // true if ident is a container ID
 	hasBeenCancelled func() bool
-	ident            string
 }
 
 // Try returns true if the request is completed, false if pending
@@ -23,34 +27,48 @@ func (g *allocate) Try(alloc *Allocator) bool {
 		return true
 	}
 
-	// If we have previously stored an address for this container, return it.
-	if addr, found := alloc.owned[g.ident]; found {
-		g.resultChan <- allocateResult{addr, nil}
+	if addrs := alloc.ownedInRange(g.ident, g.r.Range()); len(addrs) > 0 {
+		// If we had heard that this container died, resurrect it
+		delete(alloc.dead, g.ident) // delete is no-op if key not in map
+		g.resultChan <- allocateResult{addrs[0].Addr, nil}
 		return true
 	}
 
-	if ok, addr := alloc.space.Allocate(); ok {
-		alloc.debugln("Allocated", addr, "for", g.ident)
-		alloc.addOwned(g.ident, addr)
+	if !alloc.universe.Range().Overlaps(g.r.Range()) {
+		g.resultChan <- allocateResult{err: fmt.Errorf("range %s out of bounds: %s", g.r, alloc.universe)}
+		return true
+	}
+
+	alloc.establishRing()
+
+	if ok, addr := alloc.space.Allocate(g.r.HostRange()); ok {
+		// If caller hasn't supplied a unique ID, file it under the IP address
+		// which lets the caller then release the address using DELETE /ip/address
+		if g.ident == api.NoContainerID {
+			g.ident = addr.String()
+		}
+		alloc.debugln("Allocated", addr, "for", g.ident, "in", g.r)
+		alloc.addOwned(g.ident, address.MakeCIDR(g.r, addr), g.isContainer)
 		g.resultChan <- allocateResult{addr, nil}
 		return true
 	}
 
 	// out of space
-	if donor, err := alloc.ring.ChoosePeerToAskForSpace(); err == nil {
-		alloc.debugln("Decided to ask peer", donor, "for space")
-		alloc.sendRequest(donor, msgSpaceRequest)
+	donors := alloc.ring.ChoosePeersToAskForSpace(g.r.Addr, g.r.Range().End)
+	for _, donor := range donors {
+		if err := alloc.sendSpaceRequest(donor, g.r.Range()); 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) String() string {
-	return fmt.Sprintf("Allocate for %s", g.ident)
+	g.resultChan <- allocateResult{err: &errorCancelled{"Allocate", g.ident}}
 }
 
 func (g *allocate) ForContainer(ident string) bool {

ipam/allocator_test.go

@@ -7,10 +7,11 @@ import (
 	"testing"
 	"time"
 
+	"github.com/stretchr/testify/require"
+
 	"github.com/weaveworks/weave/common"
-	"github.com/weaveworks/weave/ipam/address"
-	"github.com/weaveworks/weave/router"
-	wt "github.com/weaveworks/weave/testing"
+	"github.com/weaveworks/weave/net/address"
+	"github.com/weaveworks/weave/testing/gossip"
 )
 
 const (
@@ -19,46 +20,82 @@ const (
 	testStart3 = "10.0.3.0"
 )
 
+func returnFalse() bool { return false }
+
+func (alloc *Allocator) SimplyAllocate(ident string, cidr address.CIDR) (address.Address, error) {
+	return alloc.Allocate(ident, cidr, true, returnFalse)
+}
+
+func (alloc *Allocator) SimplyClaim(ident string, cidr address.CIDR) error {
+	return alloc.Claim(ident, cidr, true, true, returnFalse)
+}
+
 func TestAllocFree(t *testing.T) {
 	const (
 		container1 = "abcdef"
 		container2 = "baddf00d"
 		container3 = "b01df00d"
-		universe   = "10.0.3.0/28"
-		testAddr1  = "10.0.3.1" // first address allocated should be .1 because .0 is network addr
-		spaceSize  = 14         // 16 IP addresses in /28, minus .0 and .15
+		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 := makeAllocatorWithMockGossip(t, "01:00:00:01:00:00", universe, 1)
+	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, _ := alloc.Allocate(container1, nil)
-	wt.AssertEqualString(t, addr1.String(), testAddr1, "address")
+	addr1, err := alloc.SimplyAllocate(container1, cidr1)
+	require.NoError(t, err)
+	require.Equal(t, testAddr1, addr1.String(), "address")
+
+	addr2, err := alloc.SimplyAllocate(container1, cidr2)
+	require.NoError(t, err)
+	require.Equal(t, testAddr2, addr2.String(), "address")
+
+	addrs, err := alloc.Lookup(container1, subnet.Range())
+	require.NoError(t, err)
+	require.Equal(t, []address.CIDR{address.MakeCIDR(cidr1, addr1), address.MakeCIDR(cidr2, addr2)}, addrs)
 
 	// Ask for another address for a different container and check it's different
-	addr2, _ := alloc.Allocate(container2, nil)
-	if addr2.String() == testAddr1 {
-		t.Fatalf("Expected different address but got %s", addr2.String())
+	addr1b, _ := alloc.SimplyAllocate(container2, cidr1)
+	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 address again
-	addr1a, _ := alloc.Allocate(container1, nil)
-	wt.AssertEqualString(t, addr1a.String(), testAddr1, "address")
+	// Ask for the first container again and we should get the same addresses again
+	addr1a, _ := alloc.SimplyAllocate(container1, cidr1)
+	require.Equal(t, testAddr1, addr1a.String(), "address")
+	addr2a, _ := alloc.SimplyAllocate(container1, cidr2)
+	require.Equal(t, testAddr2, addr2a.String(), "address")
 
-	// Now free the first one, and we should get it back when we ask
-	wt.AssertSuccess(t, alloc.Free(container1))
-	addr3, _ := alloc.Allocate(container3, nil)
-	wt.AssertEqualString(t, addr3.String(), testAddr1, "address")
+	// Now delete the first container, and we should get its addresses back
+	require.NoError(t, alloc.Delete(container1))
+	addr3, _ := alloc.SimplyAllocate(container3, cidr1)
+	require.Equal(t, testAddr1, addr3.String(), "address")
+	addr4, _ := alloc.SimplyAllocate(container3, cidr2)
+	require.Equal(t, testAddr2, addr4.String(), "address")
 
 	alloc.ContainerDied(container2)
+
+	// Resurrect
+	addr1c, err := alloc.SimplyAllocate(container2, cidr1)
+	require.NoError(t, err)
+	require.Equal(t, addr1b, addr1c, "address")
+
 	alloc.ContainerDied(container3)
-	alloc.String() // force sync-up after async call
-	wt.AssertEquals(t, alloc.space.NumFreeAddresses(), address.Offset(spaceSize))
+	alloc.Encode() // sync up
+	// Move the clock forward and clear out the dead container
+	alloc.actionChan <- func() { alloc.now = func() time.Time { return time.Now().Add(containerDiedTimeout * 2) } }
+	alloc.actionChan <- func() { alloc.removeDeadContainers() }
+	require.Equal(t, address.Count(spaceSize+1), alloc.NumFreeAddresses(subnet.Range()))
 }
 
 func TestBootstrap(t *testing.T) {
-	common.InitDefaultLogging(false)
 	const (
 		donateSize     = 5
 		donateStart    = "10.0.1.7"
@@ -66,21 +103,21 @@ func TestBootstrap(t *testing.T) {
 		peerNameString = "02:00:00:02:00:00"
 	)
 
-	alloc1 := makeAllocatorWithMockGossip(t, ourNameString, testStart1+"/22", 2)
+	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)
+	alloc2, _ := makeAllocatorWithMockGossip(t, peerNameString, testStart1+"/22", 2)
 	defer alloc2.Stop()
 
-	alloc1.OnGossipBroadcast(alloc2.encode())
+	alloc1.OnGossipBroadcast(alloc2.ourName, alloc2.Encode())
 
-	alloc1.tryPendingOps()
+	alloc1.actionChan <- func() { alloc1.tryPendingOps() }
 
 	ExpectBroadcastMessage(alloc1, nil) // alloc1 will try to form consensus
 	done := make(chan bool)
 	go func() {
-		alloc1.Allocate("somecontainer", nil)
+		alloc1.Allocate("somecontainer", subnet, true, returnFalse)
 		done <- true
 	}()
 	time.Sleep(100 * time.Millisecond)
@@ -88,26 +125,37 @@ func TestBootstrap(t *testing.T) {
 
 	CheckAllExpectedMessagesSent(alloc1, alloc2)
 
-	alloc1.tryPendingOps()
+	// Check that tryPendingOps doesn't cause anything to happen here
+	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.encode())
+	alloc2.OnGossipBroadcast(alloc1.ourName, alloc1.Encode())
 
 	ExpectBroadcastMessage(alloc1, nil)
-	alloc1.OnGossipBroadcast(alloc2.encode())
+	alloc1.OnGossipBroadcast(alloc2.ourName, alloc2.Encode())
 
-	// both nodes will get consensus now so initialize the ring
+	CheckAllExpectedMessagesSent(alloc1, alloc2)
+
+	// at this point, both nodes have seen each other, but don't have a valid proposal
+	// so there is another exchange of messages
 	ExpectBroadcastMessage(alloc2, nil)
-	ExpectBroadcastMessage(alloc2, nil)
-	alloc2.OnGossipBroadcast(alloc1.encode())
+	alloc2.OnGossipBroadcast(alloc1.ourName, alloc1.Encode())
+
+	// we have consensus now so alloc1 will initialize the ring
+	ExpectBroadcastMessage(alloc1, nil)
+	alloc1.OnGossipBroadcast(alloc2.ourName, alloc2.Encode())
+
+	CheckAllExpectedMessagesSent(alloc1, alloc2)
+
+	// alloc2 receives the ring and does not reply
+	alloc2.OnGossipBroadcast(alloc1.ourName, alloc1.Encode())
 
 	CheckAllExpectedMessagesSent(alloc1, alloc2)
 
-	alloc1.OnGossipBroadcast(alloc2.encode())
 	// now alloc1 should have space
 
 	AssertSent(t, done)
@@ -118,26 +166,54 @@ func TestBootstrap(t *testing.T) {
 func TestAllocatorClaim(t *testing.T) {
 	const (
 		container1 = "abcdef"
-		container2 = "baddf00d"
 		container3 = "b01df00d"
-		universe   = "10.0.3.0/30"
-		testAddr1  = "10.0.3.1" // first address allocated should be .1 because .0 is network addr
+		universe   = "10.0.3.0/24"
+		testAddr1  = "10.0.3.5/24"
+		testAddr2  = "10.0.4.2/24"
+		testPre    = "10.0.3.1/24"
 	)
 
-	alloc := makeAllocatorWithMockGossip(t, "01:00:00:01:00:00", universe, 1)
-	defer alloc.Stop()
+	preAddr, _ := address.ParseCIDR(testPre)
+	allocs, router, subnet := makeNetworkOfAllocators(2, universe, []PreClaim{{container1, true, preAddr}})
+	defer stopNetworkOfAllocators(allocs, router)
+	alloc := allocs[1]
+	addr1, _ := address.ParseCIDR(testAddr1)
 
-	alloc.claimRingForTesting()
-	addr1, _ := alloc.Allocate(container1, nil)
-	alloc.Allocate(container2, nil)
+	// First claim should trigger "dunno, I'm going to wait"
+	err := alloc.SimplyClaim(container3, addr1)
+	require.NoError(t, err)
 
-	// Now free the first one, and try to claim it
-	wt.AssertSuccess(t, alloc.Free(container1))
-	t.Log(alloc)
-	err := alloc.Claim(container3, addr1, nil)
-	wt.AssertNoErr(t, err)
-	addr3, _ := alloc.Allocate(container3, nil)
-	wt.AssertEqualString(t, addr3.String(), testAddr1, "address")
+	alloc.Prime()
+	// Do an allocate on the other peer, which we will try to claim later
+	addrx, err := allocs[0].Allocate(container1, subnet, true, returnFalse)
+	// Should not get the address we pre-claimed
+	require.NotEqual(t, addrx, preAddr)
+	router.Flush()
+
+	// Now try the claim again
+	err = alloc.SimplyClaim(container3, addr1)
+	require.NoError(t, err)
+	// Check we get this address back if we try an allocate
+	addr3, _ := alloc.SimplyAllocate(container3, subnet)
+	require.Equal(t, testAddr1, address.MakeCIDR(subnet, addr3).String(), "address")
+	// one more claim should still work
+	err = alloc.SimplyClaim(container3, addr1)
+	require.NoError(t, err)
+	// claim for a different container should fail
+	err = alloc.SimplyClaim(container1, addr1)
+	require.Error(t, err)
+	// claiming the address allocated on the other peer should fail
+	err = alloc.SimplyClaim(container1, address.MakeCIDR(subnet, addrx))
+	require.Error(t, err, "claiming address allocated on other peer should fail")
+	// claiming the pre-claimed address should fail on both peers
+	err = alloc.SimplyClaim(container3, preAddr)
+	require.Error(t, err, "claiming address allocated on other peer should fail")
+	err = allocs[0].SimplyClaim(container3, preAddr)
+	require.Error(t, err, "claiming address allocated on other peer should fail")
+	// Check an address outside of our universe
+	addr2, _ := address.ParseCIDR(testAddr2)
+	err = alloc.SimplyClaim(container1, addr2)
+	require.NoError(t, err)
 }
 
 func (alloc *Allocator) pause() func() {
@@ -153,18 +229,14 @@ func (alloc *Allocator) pause() func() {
 }
 
 func TestCancel(t *testing.T) {
-	common.InitDefaultLogging(false)
-	const (
-		CIDR = "10.0.1.7/26"
-	)
+	const cidr = "10.0.4.0/26"
+	router := gossip.NewTestRouter(0.0)
 
-	router := TestGossipRouter{make(map[router.PeerName]chan gossipMessage), 0.0}
+	alloc1, subnet := makeAllocator("01:00:00:02:00:00", cidr, 2)
+	alloc1.SetInterfaces(router.Connect(alloc1.ourName, alloc1))
 
-	alloc1 := 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))
+	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)
 
@@ -172,15 +244,15 @@ func TestCancel(t *testing.T) {
 	alloc2.Start()
 
 	// tell peers about each other
-	alloc1.OnGossipBroadcast(alloc2.encode())
+	alloc1.OnGossipBroadcast(alloc2.ourName, alloc2.Encode())
 
 	// Get some IPs, so each allocator has some space
-	res1, _ := alloc1.Allocate("foo", nil)
-	common.Debug.Printf("res1 = %s", res1.String())
-	res2, _ := alloc2.Allocate("bar", nil)
-	common.Debug.Printf("res2 = %s", res2.String())
+	res1, _ := alloc1.Allocate("foo", subnet, true, returnFalse)
+	common.Log.Debugf("res1 = %s", res1.String())
+	res2, _ := alloc2.Allocate("bar", subnet, true, returnFalse)
+	common.Log.Debugf("res2 = %s", res2.String())
 	if res1 == res2 {
-		wt.Fatalf(t, "Error: got same ips!")
+		require.FailNow(t, "Error: got same ips!")
 	}
 
 	// Now we're going to pause alloc2 and ask alloc1
@@ -188,24 +260,64 @@ func TestCancel(t *testing.T) {
 	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.space.NumFreeAddresses() > 0; i++ {
-		alloc1.Allocate(fmt.Sprintf("tmp%d", i), nil)
+	for i := 0; alloc1.NumFreeAddresses(subnet.HostRange()) > 0; i++ {
+		alloc1.Allocate(fmt.Sprintf("tmp%d", i), subnet, true, returnFalse)
 	}
 	cancelChan := make(chan bool, 1)
 	doneChan := make(chan bool)
 	go func() {
-		_, ok := alloc1.Allocate("baz", cancelChan)
+		_, ok := alloc1.Allocate("baz", subnet, true,
+			func() bool {
+				select {
+				case <-cancelChan:
+					return true
+				default:
+					return false
+				}
+			})
 		doneChan <- ok == nil
 	}()
 
-	AssertNothingSent(t, doneChan)
 	time.Sleep(100 * time.Millisecond)
 	AssertNothingSent(t, doneChan)
 
 	cancelChan <- true
 	unpause()
 	if <-doneChan {
-		wt.Fatalf(t, "Error: got result from Allocate")
+		require.FailNow(t, "Error: got result from Allocate")
+	}
+}
+
+func TestCancelOnDied(t *testing.T) {
+	const (
+		cidr       = "10.0.4.0/26"
+		container1 = "abcdef"
+	)
+
+	router := gossip.NewTestRouter(0.0)
+	alloc1, subnet := makeAllocator("01:00:00:02:00:00", cidr, 2)
+	alloc1.SetInterfaces(router.Connect(alloc1.ourName, alloc1))
+	alloc1.Start()
+
+	doneChan := make(chan bool)
+	f := func() {
+		_, ok := alloc1.Allocate(container1, subnet, true, returnFalse)
+		doneChan <- ok == nil
+	}
+
+	// Attempt two allocations in parallel, to check that this is handled correctly
+	go f()
+	go f()
+
+	// Nothing should happen, because we declared the quorum as 2
+	time.Sleep(100 * time.Millisecond)
+	AssertNothingSent(t, doneChan)
+
+	alloc1.ContainerDied(container1)
+
+	// Check that the two allocations both exit with an error
+	if <-doneChan || <-doneChan {
+		require.FailNow(t, "Error: got result from Allocate")
 	}
 }
 
@@ -214,82 +326,100 @@ func TestGossipShutdown(t *testing.T) {
 		container1 = "abcdef"
 		container2 = "baddf00d"
 		universe   = "10.0.3.0/30"
-		testAddr1  = "10.0.3.1" // first address allocated should be .1 because .0 is network addr
 	)
 
-	alloc := makeAllocatorWithMockGossip(t, "01:00:00:01:00:00", universe, 1)
+	alloc, subnet := makeAllocatorWithMockGossip(t, "01:00:00:01:00:00", universe, 1)
 	defer alloc.Stop()
 
 	alloc.claimRingForTesting()
-	addr1, _ := alloc.Allocate(container1, nil)
-	wt.AssertEqualString(t, addr1.String(), testAddr1, "address")
+	alloc.SimplyAllocate(container1, subnet)
 
 	alloc.Shutdown()
 
-	_, err := alloc.Allocate(container2, nil) // trying to allocate after shutdown should fail
-	wt.AssertFalse(t, err == nil, "no address")
+	_, err := alloc.SimplyAllocate(container2, subnet) // trying to allocate after shutdown should fail
+	require.False(t, err == nil, "no address")
 
 	CheckAllExpectedMessagesSent(alloc)
 }
 
+func TestNoFrag(t *testing.T) {
+	const cidr = "10.0.4.0/22"
+	resultChan := make(chan int)
+	for i := 0; i < 100; i++ {
+		allocs, router, subnet := makeNetworkOfAllocators(3, cidr)
+		allocs[1].Allocate("foo", subnet, true, returnFalse)
+		allocs[2].Allocate("bar", subnet, true, returnFalse)
+		allocs[2].actionChan <- func() {
+			resultChan <- len(allocs[2].ring.Entries)
+		}
+		require.True(t, <-resultChan < 6, "excessive ring fragmentation")
+		stopNetworkOfAllocators(allocs, router)
+	}
+}
+
 func TestTransfer(t *testing.T) {
-	const (
-		cidr = "10.0.1.7/22"
-	)
-	allocs, router := makeNetworkOfAllocators(3, cidr)
-	alloc1 := allocs[0]
-	alloc2 := allocs[1]
-	alloc3 := allocs[2] // This will be 'master' and get the first range
+	const cidr = "10.0.4.0/22"
+	allocs, router, subnet := makeNetworkOfAllocators(3, cidr)
+	defer stopNetworkOfAllocators(allocs, router)
+	alloc0 := allocs[0]
+	alloc1 := allocs[1]
+	alloc2 := allocs[2]
 
-	_, err := alloc2.Allocate("foo", nil)
-	wt.AssertTrue(t, err == nil, "Failed to get address")
+	_, err := alloc1.Allocate("foo", subnet, true, returnFalse)
+	require.True(t, err == nil, "Failed to get address")
 
-	_, err = alloc3.Allocate("bar", nil)
-	wt.AssertTrue(t, err == nil, "Failed to get address")
+	_, err = alloc2.Allocate("bar", subnet, true, returnFalse)
+	require.True(t, err == nil, "Failed to get address")
 
-	router.GossipBroadcast(alloc2.Gossip())
-	router.GossipBroadcast(alloc3.Gossip())
-	router.removePeer(alloc2.ourName)
-	router.removePeer(alloc3.ourName)
-	alloc2.Stop()
-	alloc3.Stop()
-	wt.AssertSuccess(t, alloc1.AdminTakeoverRanges(alloc2.ourName.String()))
-	wt.AssertSuccess(t, alloc1.AdminTakeoverRanges(alloc3.ourName.String()))
+	// simulation of periodic gossip
+	alloc2.gossip.GossipBroadcast(alloc2.Gossip())
+	router.Flush()
+	alloc1.gossip.GossipBroadcast(alloc1.Gossip())
+	router.Flush()
 
-	wt.AssertEquals(t, alloc1.space.NumFreeAddresses(), address.Offset(1022))
+	free1 := alloc1.NumFreeAddresses(subnet.Range())
+	free2 := alloc2.NumFreeAddresses(subnet.Range())
 
-	_, err = alloc1.Allocate("foo", nil)
-	wt.AssertTrue(t, err == nil, "Failed to get address")
+	router.RemovePeer(alloc1.ourName)
+	router.RemovePeer(alloc2.ourName)
 	alloc1.Stop()
+	alloc2.Stop()
+	router.Flush()
+
+	require.Equal(t, free1+1, alloc0.AdminTakeoverRanges(alloc1.ourName.String()))
+	require.Equal(t, free2+1, alloc0.AdminTakeoverRanges(alloc2.ourName.String()))
+	router.Flush()
+
+	require.Equal(t, address.Count(1024), alloc0.NumFreeAddresses(subnet.Range()))
+
+	_, err = alloc0.Allocate("foo", subnet, true, returnFalse)
+	require.True(t, err == nil, "Failed to get address")
+	alloc0.Stop()
 }
 
 func TestFakeRouterSimple(t *testing.T) {
-	common.InitDefaultLogging(false)
-	const (
-		cidr = "10.0.1.7/22"
-	)
-	allocs, _ := makeNetworkOfAllocators(2, cidr)
-	defer stopNetworkOfAllocators(allocs)
+	const cidr = "10.0.4.0/22"
+	allocs, router, subnet := makeNetworkOfAllocators(2, cidr)
+	defer stopNetworkOfAllocators(allocs, router)
 
 	alloc1 := allocs[0]
 	//alloc2 := allocs[1]
 
-	addr, _ := alloc1.Allocate("foo", nil)
-	println("Got addr", addr)
+	_, err := alloc1.Allocate("foo", subnet, true, returnFalse)
+	require.NoError(t, err, "Failed to get address")
 }
 
 func TestAllocatorFuzz(t *testing.T) {
-	common.InitDefaultLogging(false)
 	const (
 		firstpass    = 1000
-		secondpass   = 5000
-		nodes        = 10
+		secondpass   = 10000
+		nodes        = 5
 		maxAddresses = 1000
-		concurrency  = 10
-		cidr         = "10.0.1.7/22"
+		concurrency  = 5
+		cidr         = "10.0.4.0/22"
 	)
-	allocs, _ := makeNetworkOfAllocators(nodes, cidr)
-	defer stopNetworkOfAllocators(allocs)
+	allocs, router, subnet := makeNetworkOfAllocators(nodes, cidr)
+	defer stopNetworkOfAllocators(allocs, router)
 
 	// Test state
 	// For each IP issued we store the allocator
@@ -298,6 +428,7 @@ func TestAllocatorFuzz(t *testing.T) {
 	type result struct {
 		name  string
 		alloc int32
+		block bool
 	}
 	stateLock := sync.Mutex{}
 	state := make(map[string]result)
@@ -316,28 +447,19 @@ func TestAllocatorFuzz(t *testing.T) {
 		return xs[:ls]
 	}
 
-	// Do a Allocate and check the address
-	// is unique.  Needs a unique container
-	// name.
-	allocate := func(name string) {
+	bumpPending := func() bool {
 		stateLock.Lock()
 		if len(addrs)+numPending >= maxAddresses {
 			stateLock.Unlock()
-			return
+			return false
 		}
 		numPending++
 		stateLock.Unlock()
+		return true
+	}
 
-		allocIndex := rand.Int31n(nodes)
-		alloc := allocs[allocIndex]
-		//common.Info.Printf("Allocate: asking allocator %d", allocIndex)
-		addr, err := alloc.Allocate(name, nil)
-
-		if err != nil {
-			panic(fmt.Sprintf("Could not allocate addr"))
-		}
-
-		//common.Info.Printf("Allocate: got address %s for name %s", addr, name)
+	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()
@@ -348,11 +470,31 @@ func TestAllocatorFuzz(t *testing.T) {
 				name, res.name))
 		}
 
-		state[addrStr] = result{name, allocIndex}
+		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.SimplyAllocate(name, subnet)
+
+		if err != nil {
+			panic(fmt.Sprintf("Could not allocate addr"))
+		}
+
+		noteAllocation(allocIndex, name, addr)
+	}
+
 	// Free a random address.
 	free := func() {
 		stateLock.Lock()
@@ -365,14 +507,22 @@ func TestAllocatorFuzz(t *testing.T) {
 		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.Info.Printf("Freeing %s on allocator %d", addr, res.alloc)
+		//common.Log.Infof("Freeing %s (%s) on allocator %d", res.name, addr, res.alloc)
 
-		wt.AssertSuccess(t, alloc.Free(res.name))
+		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
@@ -382,15 +532,41 @@ func TestAllocatorFuzz(t *testing.T) {
 		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.Info.Printf("Asking for %s on allocator %d again", addr, res.alloc)
+		//common.Log.Infof("Asking for %s (%s) on allocator %d again", res.name, addr, res.alloc)
 
-		newAddr, _ := alloc.Allocate(res.name, nil)
+		newAddr, _ := alloc.SimplyAllocate(res.name, subnet)
 		oldAddr, _ := address.ParseIP(addr)
 		if newAddr != oldAddr {
-			panic(fmt.Sprintf("Got different address for repeat request"))
+			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.Addr, address.Offset(addressIndex))
+		err := alloc.SimplyClaim(name, address.MakeCIDR(subnet, addr))
+		if err == nil {
+			noteAllocation(allocIndex, name, addr)
 		}
 	}
 
@@ -433,21 +609,47 @@ func TestAllocatorFuzz(t *testing.T) {
 			// free a random addr
 			free()
 
-		case 0.8 <= r && r < 1.0:
+		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()
+func TestSpaceRequest(t *testing.T) {
+	const (
+		container1 = "cont-1"
+		container2 = "cont-2"
+		universe   = "10.32.0.0/12"
+	)
+	allocs, router, subnet := makeNetworkOfAllocators(1, universe)
+	defer stopNetworkOfAllocators(allocs, router)
+	alloc1 := allocs[0]
 
-	if _, err := alloc1.OnGossipBroadcast(alloc2.encode()); err == nil {
-		t.Fail()
-	}
+	addr, err := alloc1.Allocate(container1, subnet, true, returnFalse)
+	require.Nil(t, err, "")
+	// free it again so the donation splits the range neatly
+	err = alloc1.Free(container1, addr)
+	require.Nil(t, err, "")
+	require.Equal(t, cidrRanges(universe), alloc1.OwnedRanges(), "")
+
+	// Start a new peer
+	alloc2, _ := makeAllocator("02:00:00:02:00:00", universe, 2)
+	alloc2.SetInterfaces(router.Connect(alloc2.ourName, alloc2))
+	alloc2.Start()
+	defer alloc2.Stop()
+	alloc2.Allocate(container2, subnet, true, returnFalse)
+
+	// Test whether the universe has been split into two equal halves (GH #2009)
+	require.Equal(t, cidrRanges("10.32.0.0/13"), alloc1.OwnedRanges(), "")
+	require.Equal(t, cidrRanges("10.40.0.0/13"), alloc2.OwnedRanges(), "")
+}
+
+func cidrRanges(s string) []address.Range {
+	c, _ := address.ParseCIDR(s)
+	return []address.Range{c.Range()}
 }

ipam/claim.go

@@ -3,75 +3,126 @@ package ipam
 import (
 	"fmt"
 
-	"github.com/weaveworks/weave/ipam/address"
-	"github.com/weaveworks/weave/router"
+	"github.com/weaveworks/mesh"
+
+	"github.com/weaveworks/weave/api"
+	"github.com/weaveworks/weave/common"
+	"github.com/weaveworks/weave/net/address"
 )
 
 type claim struct {
 	resultChan       chan<- error
+	ident            string       // a container ID, something like "weave:expose", or api.NoContainerID
+	cidr             address.CIDR // single address being claimed
+	isContainer      bool         // true if ident is a container ID
+	noErrorOnUnknown bool         // if false, error or block if we don't know; if true return ok but keep trying
 	hasBeenCancelled func() bool
-	ident            string
-	addr             address.Address
+}
+
+// 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 (c.hasBeenCancelled)() {
+	if c.hasBeenCancelled != nil && c.hasBeenCancelled() {
 		c.Cancel()
 		return true
 	}
 
-	if !alloc.ring.Contains(c.addr) {
+	if !alloc.ring.Contains(c.cidr.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\n", c.addr, c.ident)
-		c.resultChan <- nil
+		alloc.infof("Address %s claimed by %s - not in our range", c.cidr, c.ident)
+		alloc.addOwned(c.ident, c.cidr, c.isContainer)
+		c.sendResult(nil)
 		return true
 	}
 
-	// If our ring doesn't know, it must be empty.  We will have initiated the
-	// bootstrap of the ring, so wait until we find some owner for this
-	// range (might be us).
-	owner := alloc.ring.Owner(c.addr)
-	if owner == router.UnknownPeerName {
-		alloc.infof("Ring is empty; will try later.\n", c.addr, owner)
+	alloc.establishRing()
+
+	// If we had heard that this container died, resurrect it
+	delete(alloc.dead, c.ident) // (delete is no-op if key not in map)
+
+	switch owner := alloc.ring.Owner(c.cidr.Addr); owner {
+	case alloc.ourName:
+		// success
+	case mesh.UnknownPeerName:
+		// If our ring doesn't know, it must be empty.
+		alloc.infof("Claim %s for %s: is in the range %s, but the allocator is not initialized yet; will try later.",
+			c.cidr, c.ident, alloc.universe)
+		if c.noErrorOnUnknown {
+			c.sendResult(nil)
+		}
+		return false
+	default:
+		alloc.debugf("requesting address %s from other peer %s", c.cidr, owner)
+		err := alloc.sendSpaceRequest(owner, address.NewRange(c.cidr.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.cidr, c.ident, err)
+				c.sendResult(nil)
+			} else { // just tell the user they can't do this.
+				c.deniedBy(alloc, owner)
+			}
+		}
 		return false
 	}
-	if owner != alloc.ourName {
-		name, found := alloc.nicknames[owner]
-		if found {
-			name = " (" + name + ")"
-		}
-		c.resultChan <- fmt.Errorf("address %s is owned by other peer %s%s", c.addr.String(), owner, name)
-		return true
-	}
+
 	// We are the owner, check we haven't given it to another container
-	existingIdent := alloc.findOwner(c.addr)
-	if existingIdent == c.ident {
-		// same identifier is claiming same address; that's OK
-		c.resultChan <- nil
-		return true
-	}
-	if existingIdent == "" {
-		err := alloc.space.Claim(c.addr)
-		if err != nil {
-			c.resultChan <- err
-			return true
+	existingIdent := alloc.findOwner(c.cidr.Addr)
+	switch {
+	case existingIdent == "":
+		// Unused address, we try to claim it:
+		if err := alloc.space.Claim(c.cidr.Addr); err == nil {
+			alloc.debugln("Claimed", c.cidr, "for", c.ident)
+			if c.ident == api.NoContainerID {
+				alloc.addOwned(c.cidr.Addr.String(), c.cidr, c.isContainer)
+			} else {
+				alloc.addOwned(c.ident, c.cidr, c.isContainer)
+			}
+			c.sendResult(nil)
+		} else {
+			c.sendResult(err)
 		}
-		alloc.addOwned(c.ident, c.addr)
-		c.resultChan <- nil
-		return true
+	case (existingIdent == c.ident) || (c.ident == api.NoContainerID && existingIdent == c.cidr.Addr.String()):
+		// same identifier is claiming same address; that's OK
+		alloc.debugln("Re-Claimed", c.cidr, "for", c.ident)
+		c.sendResult(nil)
+	case existingIdent == c.cidr.Addr.String():
+		// Address already allocated via api.NoContainerID name and current ID is a real container ID:
+		c.sendResult(fmt.Errorf("address %s already in use", c.cidr))
+	case c.ident == api.NoContainerID:
+		// We do not know whether this is the same container or another one,
+		// but we also cannot prove otherwise, so we let it reclaim the address:
+		alloc.debugln("Re-Claimed", c.cidr, "for ID", c.ident, "having existing ID as", existingIdent)
+		c.sendResult(nil)
+	default:
+		// Addr already owned by container on this machine
+		c.sendResult(fmt.Errorf("address %s is already owned by %s", c.cidr.String(), existingIdent))
 	}
-	// Addr already owned by container on this machine
-	c.resultChan <- fmt.Errorf("address %s is already owned by %s", c.addr.String(), existingIdent)
 	return true
 }
 
-func (c *claim) Cancel() {
-	c.resultChan <- fmt.Errorf("Operation cancelled.")
+func (c *claim) deniedBy(alloc *Allocator, owner mesh.PeerName) {
+	name, found := alloc.nicknames[owner]
+	if found {
+		name = " (" + name + ")"
+	}
+	c.sendResult(fmt.Errorf("address %s is owned by other peer %s%s", c.cidr.String(), owner, name))
 }
 
-func (c *claim) String() string {
-	return fmt.Sprintf("Claim %s -> %s", c.ident, c.addr.String())
+func (c *claim) Cancel() {
+	c.sendResult(&errorCancelled{"Claim", c.ident})
 }
 
 func (c *claim) ForContainer(ident string) bool {

ipam/dummy.go

@@ -1,36 +0,0 @@
-package ipam
-
-import (
-	"errors"
-
-	"github.com/weaveworks/weave/router"
-)
-
-// Exists solely for the purpose of detecting a network in which some
-// peers are configured with IPAM on and some with IPAM off.
-type DummyAllocator struct {
-}
-
-var (
-	ErrMixedConfig = errors.New("Mixed IPAM/non-IPAM configuration not supported")
-)
-
-func (alloc *DummyAllocator) OnGossipUnicast(sender router.PeerName, msg []byte) error {
-	return ErrMixedConfig
-}
-
-func (alloc *DummyAllocator) OnGossipBroadcast(msg []byte) (router.GossipData, error) {
-	return nil, ErrMixedConfig
-}
-
-func (alloc *DummyAllocator) OnGossip(msg []byte) (router.GossipData, error) {
-	return nil, ErrMixedConfig
-}
-
-func (alloc *DummyAllocator) Gossip() router.GossipData {
-	return nil
-}
-
-func (alloc *DummyAllocator) Encode() []byte {
-	return nil
-}

ipam/http.go

@@ -7,47 +7,156 @@ import (
 	"github.com/gorilla/mux"
 
 	"github.com/weaveworks/weave/common"
-	"github.com/weaveworks/weave/ipam/address"
+	"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.Warning.Println("[allocator]:", err.Error())
+	common.Log.Warningln("[allocator]:", err.Error())
+}
+
+func parseCIDR(w http.ResponseWriter, cidrStr string, net bool) (address.CIDR, bool) {
+	var cidr address.CIDR
+	var err error
+	if net {
+		cidr, err = ParseCIDRSubnet(cidrStr)
+	} else {
+		cidr, err = address.ParseCIDR(cidrStr)
+	}
+	if err != nil {
+		badRequest(w, err)
+		return address.CIDR{}, false
+	}
+	return cidr, true
+}
+
+func writeAddresses(w http.ResponseWriter, cidrs []address.CIDR) {
+	for i, cidr := range cidrs {
+		fmt.Fprint(w, cidr)
+		if i < len(cidrs)-1 {
+			w.Write([]byte{' '})
+		}
+	}
+}
+
+func hasBeenCancelled(dockerCli *docker.Client, closedChan <-chan bool, ident string, checkAlive bool) func() bool {
+	return func() bool {
+		select {
+		case <-closedChan:
+			return true
+		default:
+			res := checkAlive && dockerCli != nil && dockerCli.IsContainerNotRunning(ident)
+			checkAlive = false // we check only once; if the container dies later we learn about that through events
+			return res
+		}
+	}
+}
+
+func cancellationErr(w http.ResponseWriter, err error) bool {
+	if _, ok := err.(*errorCancelled); ok {
+		common.Log.Infoln("[allocator]:", err.Error())
+		fmt.Fprint(w, "cancelled")
+		return true
+	}
+	return false
+}
+
+func (alloc *Allocator) handleHTTPAllocate(dockerCli *docker.Client, w http.ResponseWriter, ident string, checkAlive bool, subnet address.CIDR) {
+	addr, err := alloc.Allocate(ident, subnet, checkAlive,
+		hasBeenCancelled(dockerCli, w.(http.CloseNotifier).CloseNotify(), ident, checkAlive))
+	if err != nil {
+		if !cancellationErr(w, err) {
+			badRequest(w, err)
+		}
+		return
+	}
+	fmt.Fprintf(w, "%s/%d", addr, subnet.PrefixLen)
+}
+
+func (alloc *Allocator) handleHTTPClaim(dockerCli *docker.Client, w http.ResponseWriter, ident string, cidr address.CIDR, checkAlive, noErrorOnUnknown bool) {
+	err := alloc.Claim(ident, cidr, checkAlive, noErrorOnUnknown,
+		hasBeenCancelled(dockerCli, w.(http.CloseNotifier).CloseNotify(), ident, checkAlive))
+	if err != nil {
+		if !cancellationErr(w, err) {
+			badRequest(w, fmt.Errorf("Unable to claim: %s", err))
+		}
+		return
+	}
+	w.WriteHeader(204)
 }
 
 // HandleHTTP wires up ipams HTTP endpoints to the provided mux.
-func (alloc *Allocator) HandleHTTP(router *mux.Router) {
-	router.Methods("PUT").Path("/ip/{id}/{ip}").HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
-		closedChan := w.(http.CloseNotifier).CloseNotify()
+func (alloc *Allocator) HandleHTTP(router *mux.Router, defaultSubnet address.CIDR, tracker string, dockerCli *docker.Client) {
+	router.Methods("GET").Path("/ipinfo/defaultsubnet").HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		fmt.Fprintf(w, "%s", defaultSubnet)
+	})
+
+	router.Methods("PUT").Path("/ip/{id}/{ip}/{prefixlen}").HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		vars := mux.Vars(r)
+		if cidr, ok := parseCIDR(w, vars["ip"]+"/"+vars["prefixlen"], false); ok {
+			ident := vars["id"]
+			checkAlive := r.FormValue("check-alive") == "true"
+			noErrorOnUnknown := r.FormValue("noErrorOnUnknown") == "true"
+			alloc.handleHTTPClaim(dockerCli, w, ident, cidr, checkAlive, noErrorOnUnknown)
+		}
+	})
+
+	router.Methods("GET").Path("/ring").HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		alloc.Prime()
+	})
+
+	router.Methods("GET").Path("/ip/{id}/{ip}/{prefixlen}").HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		vars := mux.Vars(r)
+		if subnet, ok := parseCIDR(w, vars["ip"]+"/"+vars["prefixlen"], true); ok {
+			cidrs, err := alloc.Lookup(vars["id"], subnet.HostRange())
+			if err != nil {
+				http.NotFound(w, r)
+				return
+			}
+			writeAddresses(w, cidrs)
+		}
+	})
+
+	router.Methods("GET").Path("/ip/{id}").HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		addrs, err := alloc.Lookup(mux.Vars(r)["id"], defaultSubnet.HostRange())
+		if err != nil {
+			http.NotFound(w, r)
+			return
+		}
+		writeAddresses(w, addrs)
+	})
+
+	router.Methods("POST").Path("/ip/{id}/{ip}/{prefixlen}").HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		vars := mux.Vars(r)
+		if subnet, ok := parseCIDR(w, vars["ip"]+"/"+vars["prefixlen"], true); ok {
+			alloc.handleHTTPAllocate(dockerCli, w, vars["id"], r.FormValue("check-alive") == "true", subnet)
+		}
+	})
+
+	router.Methods("POST").Path("/ip/{id}").HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		vars := mux.Vars(r)
+		alloc.handleHTTPAllocate(dockerCli, w, vars["id"], r.FormValue("check-alive") == "true", defaultSubnet)
+	})
+
+	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.Claim(ident, ip, closedChan); err != nil {
-			badRequest(w, fmt.Errorf("Unable to claim: %s", err))
+		} else if err := alloc.Free(ident, ip); err != nil {
+			badRequest(w, fmt.Errorf("Unable to free: %s", err))
 			return
 		}
 
 		w.WriteHeader(204)
 	})
 
-	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, closedChan)
-		if err != nil {
-			badRequest(w, err)
-			return
-		}
-
-		fmt.Fprintf(w, "%s/%d", newAddr.String(), alloc.prefixLen)
-	})
-
 	router.Methods("DELETE").Path("/ip/{id}").HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
 		ident := mux.Vars(r)["id"]
-		if err := alloc.Free(ident); err != nil {
+		if err := alloc.Delete(ident); err != nil {
 			badRequest(w, err)
 			return
 		}
@@ -62,11 +171,11 @@ func (alloc *Allocator) HandleHTTP(router *mux.Router) {
 
 	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
-		}
+		transferred := alloc.AdminTakeoverRanges(ident)
+		fmt.Fprintf(w, "%d IPs taken over from %s\n", transferred, ident)
+	})
 
-		w.WriteHeader(204)
+	router.Methods("GET").Path("/ipinfo/tracker").HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		fmt.Fprintf(w, tracker)
 	})
 }

ipam/http_test.go

@@ -4,22 +4,30 @@ import (
 	"fmt"
 	"io"
 	"io/ioutil"
-	"math/rand"
+	"net"
 	"net/http"
 	"strings"
 	"testing"
 	"time"
 
 	"github.com/gorilla/mux"
-
+	"github.com/stretchr/testify/require"
 	"github.com/weaveworks/weave/common"
-	wt "github.com/weaveworks/weave/testing"
+	"github.com/weaveworks/weave/net/address"
 )
 
 func HTTPPost(t *testing.T, url string) string {
 	resp, err := http.Post(url, "", nil)
-	wt.AssertNoErr(t, err)
-	wt.AssertStatus(t, resp.StatusCode, http.StatusOK, "http response")
+	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)
@@ -30,60 +38,76 @@ func doHTTP(method string, url string) (resp *http.Response, err error) {
 	return http.DefaultClient.Do(req)
 }
 
-func listenHTTP(port int, alloc *Allocator) {
+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)
+	alloc.HandleHTTP(router, subnet, "", nil)
 
-	srv := &http.Server{
-		Addr:    fmt.Sprintf(":%d", port),
-		Handler: router,
-	}
-	if err := srv.ListenAndServe(); err != nil {
-		common.Error.Fatal("Unable to create http listener: ", err)
+	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 allocURL(port int, containerID string) string {
+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"
-		testAddr1   = "10.0.3.9"
-		netSuffix   = "/29"
-		testCIDR1   = "10.0.3.8" + netSuffix
+		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", testCIDR1, 1)
-	port := rand.Intn(10000) + 32768
-	fmt.Println("Http test on port", port)
-	go listenHTTP(port, alloc)
-
-	time.Sleep(100 * time.Millisecond) // Allow for http server to get going
-
+	alloc, _ := makeAllocatorWithMockGossip(t, "08:00:27:01:c3:9a", universe, 1)
+	cidr, _ := address.ParseCIDR(universe)
+	port := listenHTTP(alloc, cidr)
 	alloc.claimRingForTesting()
-	// Ask the http server for a new address
-	cidr1 := HTTPPost(t, allocURL(port, containerID))
-	wt.AssertEqualString(t, cidr1, testAddr1+netSuffix, "address")
 
-	// Ask the http server for another address and check it's different
-	cidr2 := HTTPPost(t, allocURL(port, container2))
-	wt.AssertFalse(t, cidr2 == testAddr1+netSuffix, "address")
+	// 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 for the first container again and we should get the same address again
-	cidr1a := HTTPPost(t, allocURL(port, containerID))
-	wt.AssertEqualString(t, cidr1a, testAddr1+netSuffix, "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 one, and we should get it back when we ask
-	doHTTP("DELETE", allocURL(port, containerID))
-	cidr3 := HTTPPost(t, allocURL(port, container3))
-	wt.AssertEqualString(t, cidr3, testAddr1+netSuffix, "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.
@@ -96,69 +120,54 @@ func TestBadHttp(t *testing.T) {
 		testCIDR1   = "10.0.0.0/8"
 	)
 
-	alloc := makeAllocatorWithMockGossip(t, "08:00:27:01:c3:9a", testCIDR1, 1)
+	alloc, _ := makeAllocatorWithMockGossip(t, "08:00:27:01:c3:9a", testCIDR1, 1)
 	defer alloc.Stop()
-	port := rand.Intn(10000) + 32768
-	fmt.Println("BadHttp test on port", port)
-	go listenHTTP(port, alloc)
+	cidr, _ := address.ParseCIDR(testCIDR1)
+	port := listenHTTP(alloc, cidr)
 
 	alloc.claimRingForTesting()
-	cidr1 := HTTPPost(t, allocURL(port, containerID))
+	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))
-	wt.AssertNoErr(t, err)
-	wt.AssertStatus(t, resp.StatusCode, http.StatusNotFound, "http response")
+	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))
-	wt.AssertNoErr(t, err)
-	wt.AssertStatus(t, resp.StatusCode, http.StatusNotFound, "http response")
+	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))
-	wt.AssertNoErr(t, err)
-	wt.AssertStatus(t, resp.StatusCode, http.StatusNotFound, "http response")
+	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) {
-	common.InitDefaultLogging(true)
 	var (
 		containerID = "deadbeef"
-		testCIDR1   = "10.0.3.5/29"
+		testCIDR1   = "10.0.3.0/29"
 	)
 
-	alloc := makeAllocatorWithMockGossip(t, "08:00:27:01:c3:9a", testCIDR1, 1)
+	// Say quorum=2, so the allocate won't go ahead
+	alloc, _ := makeAllocatorWithMockGossip(t, "08:00:27:01:c3:9a", testCIDR1, 2)
 	defer alloc.Stop()
-	alloc.claimRingForTesting()
-	port := rand.Intn(10000) + 32768
-	fmt.Println("Http test on port", port)
-	go listenHTTP(port, alloc)
-
-	time.Sleep(100 * time.Millisecond) // Allow for http server to get going
-
-	// Stop the alloc so nothing actually works
-	unpause := alloc.pause()
+	ExpectBroadcastMessage(alloc, nil) // trying to form consensus
+	cidr, _ := address.ParseCIDR(testCIDR1)
+	port := listenHTTP(alloc, cidr)
 
 	// Ask the http server for a new address
-	done := make(chan *http.Response)
-	req, _ := http.NewRequest("POST", allocURL(port, containerID), nil)
+	req, _ := http.NewRequest("POST", allocURL(port, testCIDR1, containerID), nil)
+	// On another goroutine, wait for a bit then cancel the request
 	go func() {
-		res, _ := http.DefaultClient.Do(req)
-		done <- res
+		time.Sleep(100 * time.Millisecond)
+		common.Log.Debug("Cancelling allocate")
+		http.DefaultTransport.(*http.Transport).CancelRequest(req)
 	}()
 
-	time.Sleep(100 * time.Millisecond)
-	fmt.Println("Cancelling allocate")
-	http.DefaultTransport.(*http.Transport).CancelRequest(req)
-	unpause()
-	res := <-done
+	res, _ := http.DefaultClient.Do(req)
 	if res != nil {
-		wt.Fatalf(t, "Error: Allocate returned non-nil")
+		body, _ := ioutil.ReadAll(res.Body)
+		require.FailNow(t, "Error: Allocate returned non-nil", string(body))
 	}
 }

ipam/paxos/participant.go

@@ -0,0 +1,44 @@
+package paxos
+
+type Participant interface {
+	GossipState() GossipState
+	Update(from GossipState) bool
+	SetQuorum(uint)
+	Propose()
+	Think() bool
+	Consensus() (bool, AcceptedValue)
+	IsElector() bool
+}
+
+type Observer struct {
+}
+
+func NewObserver() Participant {
+	return &Observer{}
+}
+
+func (observer *Observer) GossipState() GossipState {
+	return nil
+}
+
+func (observer *Observer) Update(from GossipState) bool {
+	return false
+}
+
+func (observer *Observer) Propose() {
+}
+
+func (observer *Observer) SetQuorum(uint) {
+}
+
+func (observer *Observer) Think() bool {
+	return false
+}
+
+func (observer *Observer) Consensus() (bool, AcceptedValue) {
+	return false, AcceptedValue{}
+}
+
+func (observer *Observer) IsElector() bool {
+	return false
+}

ipam/paxos/paxos.go

@@ -1,8 +1,7 @@
 package paxos
 
 import (
-	"fmt"
-	"github.com/weaveworks/weave/router"
+	"github.com/weaveworks/mesh"
 )
 
 // The node identifier.  The use of the UID here is important: Paxos
@@ -10,8 +9,8 @@ import (
 // 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
+	Name mesh.PeerName
+	UID  mesh.PeerUID
 }
 
 // note all fields exported in structs so we can Gob them
@@ -40,7 +39,7 @@ func (a ProposalID) valid() bool {
 }
 
 // For seeding IPAM, the value we want consensus on is a set of peer names
-type Value []router.PeerName
+type Value []mesh.PeerName
 
 // An AcceptedValue is a Value plus the proposal which originated that
 // Value.  The origin is not essential, but makes comparing
@@ -73,7 +72,7 @@ type Node struct {
 	knows  GossipState
 }
 
-func NewNode(name router.PeerName, uid router.PeerUID, quorum uint) *Node {
+func NewNode(name mesh.PeerName, uid mesh.PeerUID, quorum uint) *Node {
 	return &Node{
 		id:     NodeID{name, uid},
 		quorum: quorum,
@@ -81,6 +80,10 @@ func NewNode(name router.PeerName, uid router.PeerUID, quorum uint) *Node {
 	}
 }
 
+func (node *Node) SetQuorum(quorum uint) {
+	node.quorum = quorum
+}
+
 func (node *Node) GossipState() GossipState {
 	return node.knows
 }
@@ -117,15 +120,17 @@ func (node *Node) Update(from GossipState) bool {
 func max(a uint, b uint) uint {
 	if a > b {
 		return a
-	} else {
-		return b
 	}
+	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() {
+	if node.quorum == 0 {
+		panic("Paxos node.Propose() called with no quorum set")
+	}
 	// Find the highest round number around
 	round := uint(0)
 
@@ -225,7 +230,7 @@ func (node *Node) Think() bool {
 // 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))
+	val := make([]mesh.PeerName, len(node.knows))
 	i := 0
 	for id := range node.knows {
 		val[i] = id.Name
@@ -236,6 +241,9 @@ func (node *Node) pickValue() Value {
 
 // Has a consensus been reached, based on the known claims of other nodes?
 func (node *Node) Consensus() (bool, AcceptedValue) {
+	if node.quorum == 0 {
+		return false, AcceptedValue{}
+	}
 	counts := map[ProposalID]uint{}
 
 	for _, claims := range node.knows {
@@ -252,10 +260,16 @@ func (node *Node) Consensus() (bool, AcceptedValue) {
 	return false, AcceptedValue{}
 }
 
-func (node *Node) String() string {
-	if ok, val := node.Consensus(); ok {
-		return fmt.Sprintf("Consensus reached with size %d", len(val.Value))
-	} else {
-		return fmt.Sprintf("Nodes known: %d, Quorum size: %d", len(node.knows), node.quorum)
-	}
+func (node *Node) IsElector() bool {
+	return true
+}
+
+type Status struct {
+	Elector    bool
+	KnownNodes int
+	Quorum     uint
+}
+
+func NewStatus(node *Node) *Status {
+	return &Status{true, len(node.knows), node.quorum}
 }

ipam/paxos/paxos_test.go

@@ -2,10 +2,11 @@ package paxos
 
 import (
 	"fmt"
-	"github.com/weaveworks/weave/router"
 	"math/rand"
 	"testing"
 	"time"
+
+	"github.com/weaveworks/mesh"
 )
 
 type TestNode struct {
@@ -96,8 +97,8 @@ func makeRandomModel(params *TestParams, r *rand.Rand, t *testing.T) *Model {
 	}
 
 	for i := range m.nodes {
-		m.nodes[i].Node = NewNode(router.PeerName(i/2+1),
-			router.PeerUID(r.Int63()), m.quorum)
+		m.nodes[i].Node = NewNode(mesh.PeerName(i/2+1),
+			mesh.PeerUID(r.Int63()), m.quorum)
 		m.nodes[i].Propose()
 	}
 
@@ -171,8 +172,8 @@ func (m *Model) isolateNode(node *TestNode) {
 
 // Restart a node
 func (m *Model) restart(node *TestNode) {
-	node.Node = NewNode(router.PeerName(m.nextID),
-		router.PeerUID(m.r.Int63()), m.quorum)
+	node.Node = NewNode(mesh.PeerName(m.nextID),
+		mesh.PeerUID(m.r.Int63()), m.quorum)
 	m.nextID++
 	node.Propose()
 
@@ -299,14 +300,14 @@ func (m *Model) validate() {
 	for i := range m.nodes {
 		ok, val := m.nodes[i].Consensus()
 		if !ok {
-			//m.dump()
+			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.dump()
 			m.t.Fatal("Consensus mismatch")
 		}
 

ipam/prime.go

@@ -0,0 +1,24 @@
+package ipam
+
+type prime struct {
+	resultChan chan<- struct{}
+}
+
+func (c *prime) Try(alloc *Allocator) bool {
+	if !alloc.ring.Empty() {
+		close(c.resultChan)
+		return true
+	}
+
+	alloc.establishRing()
+
+	return false
+}
+
+func (c *prime) Cancel() {
+	close(c.resultChan)
+}
+
+func (c *prime) ForContainer(ident string) bool {
+	return false
+}

ipam/ring/entry.go

@@ -3,17 +3,18 @@ package ring
 import (
 	"sort"
 
+	"github.com/weaveworks/mesh"
+
 	"github.com/weaveworks/weave/common"
-	"github.com/weaveworks/weave/ipam/address"
-	"github.com/weaveworks/weave/router"
+	"github.com/weaveworks/weave/net/address"
 )
 
 // Entry represents entries around the ring
 type entry struct {
 	Token   address.Address // The start of this range
-	Peer    router.PeerName // Who owns this range
+	Peer    mesh.PeerName   // Who owns this range
 	Version uint32          // Version of this range
-	Free    address.Offset  // Number of free IPs in this range
+	Free    address.Count   // Number of free IPs in this range
 }
 
 func (e *entry) Equal(e2 *entry) bool {
@@ -21,7 +22,7 @@ func (e *entry) Equal(e2 *entry) bool {
 		e.Version == e2.Version
 }
 
-func (e *entry) update(peername router.PeerName, free address.Offset) {
+func (e *entry) update(peername mesh.PeerName, free address.Count) {
 	e.Peer = peername
 	e.Version++
 	e.Free = free
@@ -68,10 +69,6 @@ func (es entries) get(token address.Address) (*entry, bool) {
 	return nil, false
 }
 
-func (es *entries) remove(i int) {
-	*es = (*es)[:i+copy((*es)[i:], (*es)[i+1:])]
-}
-
 // 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

ipam/ring/expvar.go

@@ -1,31 +0,0 @@
-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

@@ -10,17 +10,23 @@ import (
 	"io"
 	"math/rand"
 	"sort"
+	"time"
+
+	"github.com/weaveworks/mesh"
 
 	"github.com/weaveworks/weave/common"
-	"github.com/weaveworks/weave/ipam/address"
-	"github.com/weaveworks/weave/router"
+	"github.com/weaveworks/weave/net/address"
 )
 
+type OnUpdate func(prev, curr []address.Range, local bool)
+
 // 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
+	Peer       mesh.PeerName   // name of peer owning this ring instance
 	Entries    entries         // list of entries sorted by token
+	Seeds      []mesh.PeerName // peers with which the ring was seeded
+	onUpdate   OnUpdate
 }
 
 func (r *Ring) assertInvariants() {
@@ -32,46 +38,55 @@ func (r *Ring) assertInvariants() {
 
 // 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")
-	ErrDifferentSubnets = errors.New("IP Allocator with different subnet detected")
-	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!")
-	ErrNoFreeSpace      = errors.New("No free space found!")
-	ErrInvalidTimeout   = errors.New("dt must be greater than 0")
-	ErrNotFound         = errors.New("No entries for peer found")
+	ErrNotSorted       = errors.New("Ring not sorted")
+	ErrTokenRepeated   = errors.New("Token appears twice in ring")
+	ErrTokenOutOfRange = errors.New("Token is out of range")
+	ErrDifferentSeeds  = errors.New("Received ring was seeded differently from ours")
+	ErrDifferentRange  = errors.New("Received range differs from ours")
 )
 
+func errInconsistentEntry(mine, theirs *entry) error {
+	return fmt.Errorf("Inconsistent entries for %s: owned by %s but incoming message says %s", mine.Token, mine.Peer, theirs.Peer)
+}
+func errEntryInMyRange(theirs *entry) error {
+	return fmt.Errorf("Peer %s says it owns the IP range from %s, which I think I own", theirs.Peer, theirs.Token)
+}
+func errNewerVersion(mine, theirs *entry) error {
+	return fmt.Errorf("Received update for IP range I own at %s v%d: incoming message says owner %s v%d", mine.Token, mine.Version, theirs.Peer, theirs.Version)
+}
+
 func (r *Ring) checkInvariants() error {
-	if !sort.IsSorted(r.Entries) {
+	return r.checkEntries(r.Entries)
+}
+
+func (r *Ring) checkEntries(entries entries) error {
+	if !sort.IsSorted(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 {
+	for i := 1; i < len(entries); i++ {
+		if entries[i-1].Token == entries[i].Token {
 			return ErrTokenRepeated
 		}
 	}
 
-	if len(r.Entries) == 0 {
+	if len(entries) == 0 {
 		return nil
 	}
 
 	// Check tokens are in range
-	if r.Entries.entry(0).Token < r.Start {
+	if entries.entry(0).Token < r.Start {
 		return ErrTokenOutOfRange
 	}
-	if r.Entries.entry(-1).Token >= r.End {
+	if 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)
+	for i, entry := range entries {
+		next := entries.entry(i + 1)
 		distance := r.distance(entry.Token, next.Token)
 
 		if entry.Free > distance {
@@ -82,35 +97,46 @@ func (r *Ring) checkInvariants() error {
 	return nil
 }
 
+func (r *Ring) trackUpdates() func() {
+	return r.trackUpdatesOfPeer(r.Peer)
+}
+
+func (r *Ring) trackUpdatesOfPeer(peer mesh.PeerName) func() {
+	if r.onUpdate == nil {
+		return func() {}
+	}
+	ranges := r.OwnedRangesOfPeer(peer)
+	return func() { r.onUpdate(ranges, r.OwnedRangesOfPeer(peer), peer == r.Peer) }
+}
+
 // New creates an empty ring belonging to peer.
-func New(start, end address.Address, peer router.PeerName) *Ring {
+func New(start, end address.Address, peer mesh.PeerName, f OnUpdate) *Ring {
 	common.Assert(start < end)
 
-	ring := &Ring{Start: start, End: end, Peer: peer, Entries: make([]*entry, 0)}
-	ring.updateExportedVariables()
+	ring := &Ring{Start: start, End: end, Peer: peer, Entries: make([]*entry, 0), onUpdate: f}
 	return ring
 }
 
-// TotalRemoteFree returns the approximate number of free IPs
-// on other hosts.
-func (r *Ring) TotalRemoteFree() address.Offset {
-	result := address.Offset(0)
-	for _, entry := range r.Entries {
-		if entry.Peer != r.Peer {
-			result += entry.Free
-		}
-	}
-	return result
+func (r *Ring) Restore(other *Ring) {
+	defer r.trackUpdates()()
+
+	onUpdate := r.onUpdate
+	*r = *other
+	r.onUpdate = onUpdate
+}
+
+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 {
+func (r *Ring) distance(start, end address.Address) address.Count {
 	if end > start {
-		return address.Offset(end - start)
+		return address.Count(end - start)
 	}
 
-	return address.Offset((r.End - start) + (end - r.Start))
+	return address.Count((r.End - start) + (end - r.Start))
 }
 
 // GrantRangeToHost modifies the ring such that range [start, end)
@@ -118,12 +144,12 @@ func (r *Ring) distance(start, end address.Address) address.Offset {
 // Preconditions:
 // - start < end
 // - [start, end) must be owned by the calling peer
-func (r *Ring) GrantRangeToHost(start, end address.Address, peer router.PeerName) {
+func (r *Ring) GrantRangeToHost(start, end address.Address, peer mesh.PeerName) {
 	//fmt.Printf("%s GrantRangeToHost [%v,%v) -> %s\n", r.Peer, start, end, peer)
 
 	r.assertInvariants()
+	defer r.trackUpdates()()
 	defer r.assertInvariants()
-	defer r.updateExportedVariables()
 
 	// ----------------- Start of Checks -----------------
 
@@ -185,32 +211,69 @@ func (r *Ring) GrantRangeToHost(start, end address.Address, peer router.PeerName
 	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 {
+// Merge the given ring into this ring and indicate whether this ring
+// got updated as a result.
+func (r *Ring) Merge(gossip Ring) (bool, error) {
 	r.assertInvariants()
-	defer r.assertInvariants()
-	defer r.updateExportedVariables()
+	defer r.trackUpdates()()
 
 	// 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
+		return false, err
+	}
+
+	if len(gossip.Seeds) > 0 && len(r.Seeds) > 0 {
+		if len(gossip.Seeds) != len(r.Seeds) {
+			return false, ErrDifferentSeeds
+		}
+		for i, seed := range gossip.Seeds {
+			if seed != r.Seeds[i] {
+				return false, ErrDifferentSeeds
+			}
+		}
 	}
 
 	if r.Start != gossip.Start || r.End != gossip.End {
-		return ErrDifferentSubnets
+		return false, ErrDifferentRange
 	}
 
-	// Now merge their ring with yours, in a temporary ring.
-	var result entries
-	addToResult := func(e entry) { result = append(result, &e) }
+	result, updated, err := r.Entries.merge(gossip.Entries, r.Peer)
 
+	if err != nil {
+		return false, err
+	}
+
+	if err := r.checkEntries(result); err != nil {
+		return false, fmt.Errorf("Merge of incoming data causes: %s", err)
+	}
+
+	if len(r.Seeds) == 0 {
+		r.Seeds = gossip.Seeds
+	}
+	r.Entries = result
+
+	return updated, nil
+}
+
+// Merge other entries into ours, and complain when that stomps on
+// entries belonging to ourPeer. Returns the merged entries and an
+// indication whether the merge resulted in any changes, i.e. the
+// result differs from the original.
+func (es entries) merge(other entries, ourPeer mesh.PeerName) (result entries, updated bool, err error) {
 	var mine, theirs *entry
-	var previousOwner *router.PeerName
-	// i is index into r.Entries; j is index into gossip.Entries
+	var previousOwner *mesh.PeerName
+	addToResult := func(e entry) { result = append(result, &e) }
+	addTheirs := func(e entry) {
+		addToResult(e)
+		updated = true
+		previousOwner = nil
+	}
+
+	// i is index into es; j is index into other
 	var i, j int
-	for i < len(r.Entries) && j < len(gossip.Entries) {
-		mine, theirs = r.Entries[i], gossip.Entries[j]
+	for i < len(es) && j < len(other) {
+		mine, theirs = es[i], other[j]
 		switch {
 		case mine.Token < theirs.Token:
 			addToResult(*mine)
@@ -218,53 +281,52 @@ func (r *Ring) Merge(gossip Ring) error {
 			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
+			if previousOwner != nil && *previousOwner == ourPeer && theirs.Peer != ourPeer {
+				err = errEntryInMyRange(theirs)
+				return
 			}
-			addToResult(*theirs)
-			previousOwner = nil
+			addTheirs(*theirs)
 			j++
 		case mine.Token == theirs.Token:
 			// merge
 			switch {
 			case mine.Version >= theirs.Version:
 				if mine.Version == theirs.Version && !mine.Equal(theirs) {
-					common.Debug.Printf("Error merging entries at %s - %v != %v\n", mine.Token, mine, theirs)
-					return ErrInvalidEntry
+					err = errInconsistentEntry(mine, theirs)
+					return
 				}
 				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
+				if mine.Peer == ourPeer { // We shouldn't receive updates to our own tokens
+					err = errNewerVersion(mine, theirs)
+					return
 				}
-				addToResult(*theirs)
-				previousOwner = nil
+				addTheirs(*theirs)
 			}
 			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.
+	// At this point, either i is at the end of es or j is at the end
+	// of other, so copy over the remaining entries.
 
-	for ; i < len(r.Entries); i++ {
-		mine = r.Entries[i]
+	for ; i < len(es); i++ {
+		mine = es[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
+	for ; j < len(other); j++ {
+		theirs = other[j]
+		if previousOwner != nil && *previousOwner == ourPeer && theirs.Peer != ourPeer {
+			err = errEntryInMyRange(theirs)
+			return
 		}
-		addToResult(*theirs)
-		previousOwner = nil
+		addTheirs(*theirs)
 	}
 
-	r.Entries = result
-	return nil
+	return
 }
 
 // Empty returns true if the ring has no entries
@@ -297,10 +359,14 @@ func (r *Ring) splitRangesOverZero(ranges []address.Range) []address.Range {
 // ranges are owned by this peer.  Will split ranges which
 // span 0 in the ring.
 func (r *Ring) OwnedRanges() (result []address.Range) {
+	return r.OwnedRangesOfPeer(r.Peer)
+}
+
+func (r *Ring) OwnedRangesOfPeer(peer mesh.PeerName) (result []address.Range) {
 	r.assertInvariants()
 
 	for i, entry := range r.Entries {
-		if entry.Peer == r.Peer {
+		if entry.Peer == peer {
 			nextEntry := r.Entries.entry(i + 1)
 			result = append(result, address.Range{Start: entry.Token, End: nextEntry.Token})
 		}
@@ -309,43 +375,58 @@ func (r *Ring) OwnedRanges() (result []address.Range) {
 	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()
+// For printing status
+type RangeInfo struct {
+	Peer mesh.PeerName
+	address.Range
+	Version uint32
+}
 
-	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
-			}
+func (r *Ring) AllRangeInfo() (result []RangeInfo) {
+	for i, entry := range r.Entries {
+		nextEntry := r.Entries.entry(i + 1)
+		ranges := []address.Range{{Start: entry.Token, End: nextEntry.Token}}
+		ranges = r.splitRangesOverZero(ranges)
+		for _, r := range ranges {
+			result = append(result, RangeInfo{entry.Peer, r, entry.Version})
 		}
-
-		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)
+	return
 }
 
-func (r *Ring) ClaimItAll() {
-	r.ClaimForPeers([]router.PeerName{r.Peer})
+// ClaimForPeers claims the entire ring for the array of peers passed
+// in.  Only works for empty rings. Each claimed range is CIDR-aligned.
+func (r *Ring) ClaimForPeers(peers []mesh.PeerName) {
+	common.Assert(r.Empty())
+
+	defer r.trackUpdates()()
+	defer r.assertInvariants()
+	defer func() {
+		e := r.Entries[len(r.Entries)-1]
+		common.Assert(address.Add(e.Token, address.Offset(e.Free)) == r.End)
+	}()
+
+	r.subdivide(r.Start, r.End, peers)
+	r.Seeds = peers
 }
 
-func (r *Ring) FprintWithNicknames(w io.Writer, m map[router.PeerName]string) {
+// subdivide subdivides the [from,to) CIDR for the given peers into
+// CIDR-aligned subranges.
+func (r *Ring) subdivide(from, to address.Address, peers []mesh.PeerName) {
+	share := address.Length(to, from)
+	if share == 0 {
+		return
+	}
+	if share == 1 || len(peers) == 1 {
+		r.Entries.insert(entry{Token: from, Peer: peers[0], Free: share})
+		return
+	}
+	mid := address.Add(from, address.Offset(share/2))
+	r.subdivide(from, mid, peers[:len(peers)/2])
+	r.subdivide(address.Add(mid, address.Offset(share%2)), to, peers[len(peers)/2:])
+}
+
+func (r *Ring) FprintWithNicknames(w io.Writer, m map[mesh.PeerName]string) {
 	for _, entry := range r.Entries {
 		nickname, found := m[entry.Peer]
 		if found {
@@ -360,17 +441,16 @@ func (r *Ring) FprintWithNicknames(w io.Writer, m map[router.PeerName]string) {
 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))
+	r.FprintWithNicknames(&buffer, make(map[mesh.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 ChoosePeerToAskForSpace
-// can make more intelligent decisions.
-func (r *Ring) ReportFree(freespace map[address.Address]address.Offset) {
+// 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.  Returns true if any changes made.
+func (r *Ring) ReportFree(freespace map[address.Address]address.Count) (updated bool) {
 	r.assertInvariants()
 	defer r.assertInvariants()
-	defer r.updateExportedVariables()
 
 	common.Assert(!r.Empty())
 	entries := r.Entries
@@ -397,27 +477,44 @@ func (r *Ring) ReportFree(freespace map[address.Address]address.Offset) {
 		// 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)
+		common.Assert(free <= address.Count(maxSize))
 
 		if entries[i].Free == free {
-			return
+			continue
 		}
 
 		entries[i].Free = free
 		entries[i].Version++
+		updated = true
 	}
+	return
 }
 
-// ChoosePeerToAskForSpace chooses a weighted-random peer to ask
-// for space.
-func (r *Ring) ChoosePeerToAskForSpace() (result router.PeerName, err error) {
-	var (
-		sum               address.Offset
-		totalSpacePerPeer = make(map[router.PeerName]address.Offset) // Compute total free space per peer
-	)
+type weightedPeer struct {
+	weight   float64
+	peername mesh.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) []mesh.PeerName {
+	totalSpacePerPeer := make(map[mesh.PeerName]address.Count)
 
 	// iterate through tokens
-	for _, entry := range r.Entries {
+	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
@@ -429,59 +526,51 @@ func (r *Ring) ChoosePeerToAskForSpace() (result router.PeerName, err error) {
 		}
 
 		totalSpacePerPeer[entry.Peer] += entry.Free
-		sum += entry.Free
 	}
 
-	if sum == 0 {
-		err = ErrNoFreeSpace
-		return
-	}
-
-	// Pick random peer, weighted by total free space
-	rn := rand.Int63n(int64(sum))
+	// 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 {
-		rn -= int64(space)
-		if rn < 0 {
-			return peername, nil
-		}
+		ws = append(ws, weightedPeer{weight: float64(space) * rand.Float64(), peername: peername})
 	}
-
-	panic("Should never reach this point")
+	sort.Sort(ws)
+	result := make([]mesh.PeerName, len(ws))
+	for i, wp := range ws {
+		result[i] = wp.peername
+	}
+	return result
 }
 
-func (r *Ring) PickPeerForTransfer() router.PeerName {
+func (r *Ring) PickPeerForTransfer(isValid func(mesh.PeerName) bool) mesh.PeerName {
 	for _, entry := range r.Entries {
-		if entry.Peer != r.Peer {
+		if entry.Peer != r.Peer && isValid(entry.Peer) {
 			return entry.Peer
 		}
 	}
-	return router.UnknownPeerName
+	return mesh.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) (error, []address.Range) {
+func (r *Ring) Transfer(from, to mesh.PeerName) []address.Range {
 	r.assertInvariants()
+	defer r.trackUpdates()()
+	defer r.trackUpdatesOfPeer(from)()
 	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 ErrNotFound, nil
-	}
-
-	return nil, r.splitRangesOverZero(newRanges)
+	return r.splitRangesOverZero(newRanges)
 }
 
 // Contains returns true if addr is in this ring
@@ -490,13 +579,13 @@ func (r *Ring) Contains(addr address.Address) bool {
 }
 
 // Owner returns the peername which owns the range containing addr
-func (r *Ring) Owner(token address.Address) router.PeerName {
+func (r *Ring) Owner(token address.Address) mesh.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
+		return mesh.UnknownPeerName
 	}
 
 	// Look for the right-most entry, less than or equal to token
@@ -509,8 +598,8 @@ func (r *Ring) Owner(token address.Address) router.PeerName {
 }
 
 // Get the set of PeerNames mentioned in the ring
-func (r *Ring) PeerNames() map[router.PeerName]struct{} {
-	res := make(map[router.PeerName]struct{})
+func (r *Ring) PeerNames() map[mesh.PeerName]struct{} {
+	res := make(map[mesh.PeerName]struct{})
 
 	for _, entry := range r.Entries {
 		res[entry.Peer] = struct{}{}
@@ -518,3 +607,7 @@ func (r *Ring) PeerNames() map[router.PeerName]struct{} {
 
 	return res
 }
+
+func init() {
+	rand.Seed(time.Now().UTC().UnixNano())
+}

ipam/ring/ring_test.go

@@ -7,18 +7,20 @@ import (
 	"sort"
 	"testing"
 
+	"github.com/stretchr/testify/require"
+	"github.com/weaveworks/mesh"
+
 	"github.com/weaveworks/weave/common"
-	"github.com/weaveworks/weave/ipam/address"
-	"github.com/weaveworks/weave/router"
-	wt "github.com/weaveworks/weave/testing"
+	"github.com/weaveworks/weave/net/address"
 )
 
 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")
+	peer1name, _ = mesh.PeerNameFromString("01:00:00:00:02:00")
+	peer2name, _ = mesh.PeerNameFromString("02:00:00:00:02:00")
+	peer3name, _ = mesh.PeerNameFromString("03:00:00:00:02:00")
 
-	start, end    = ParseIP("10.0.0.0"), ParseIP("10.0.0.255")
+	start, end    = ParseIP("10.0.0.0"), ParseIP("10.0.1.0")
+	dot8          = ParseIP("10.0.0.8")
 	dot10, dot245 = ParseIP("10.0.0.10"), ParseIP("10.0.0.245")
 	dot250        = ParseIP("10.0.0.250")
 	middle        = ParseIP("10.0.0.128")
@@ -29,54 +31,69 @@ func ParseIP(s string) address.Address {
 	return addr
 }
 
+func merge(r1, r2 *Ring) error {
+	_, err := r1.Merge(*r2)
+	return err
+}
+
+func NewRing(start, end address.Address, peer mesh.PeerName) *Ring {
+	return New(start, end, peer, nil)
+}
+
 func TestInvariants(t *testing.T) {
-	ring := New(start, end, peer1name)
+	ring := NewRing(start, end, peer1name)
 
 	// Check ring is sorted
 	ring.Entries = []*entry{{Token: dot245, Peer: peer1name}, {Token: dot10, Peer: peer2name}}
-	wt.AssertTrue(t, ring.checkInvariants() == ErrNotSorted, "Expected error")
+	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}}
-	wt.AssertTrue(t, ring.checkInvariants() == ErrTokenRepeated, "Expected error")
+	require.True(t, ring.checkInvariants() == ErrTokenRepeated, "Expected error")
 
 	// Check tokens are in bounds
-	ring = New(dot10, dot245, peer1name)
+	ring = NewRing(dot10, dot245, peer1name)
 	ring.Entries = []*entry{{Token: start, Peer: peer1name}}
-	wt.AssertTrue(t, ring.checkInvariants() == ErrTokenOutOfRange, "Expected error")
+	require.True(t, ring.checkInvariants() == ErrTokenOutOfRange, "Expected error")
 
 	ring.Entries = []*entry{{Token: end, Peer: peer1name}}
-	wt.AssertTrue(t, ring.checkInvariants() == ErrTokenOutOfRange, "Expected error")
+	require.True(t, ring.checkInvariants() == ErrTokenOutOfRange, "Expected error")
 }
 
 func TestInsert(t *testing.T) {
-	ring := New(start, end, peer1name)
+	ring := NewRing(start, end, peer1name)
 	ring.Entries = []*entry{{Token: start, Peer: peer1name, Free: 255}}
 
-	wt.AssertPanic(t, func() {
+	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}}
-	wt.AssertEquals(t, ring, ring2)
+	check := []RangeInfo{
+		{Peer: peer1name, Range: address.Range{Start: start, End: dot245}},
+		{Peer: peer1name, Range: address.Range{Start: dot245, End: end}},
+	}
+	require.Equal(t, check, ring.AllRangeInfo())
 
 	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}}
-	wt.AssertEquals(t, ring, ring2)
+	check2 := []RangeInfo{
+		{Peer: peer1name, Range: address.Range{Start: start, End: dot10}},
+		{Peer: peer1name, Range: address.Range{Start: dot10, End: dot245}},
+		{Peer: peer1name, Range: address.Range{Start: dot245, End: end}},
+	}
+	require.Equal(t, check2, ring.AllRangeInfo())
 }
 
 func TestBetween(t *testing.T) {
-	ring1 := New(start, end, peer1name)
+	ring1 := NewRing(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))
-		wt.AssertTrue(t, ring1.Entries.between(ip, 0, 1), "between should be true!")
+		require.True(t, ring1.Entries.between(ip, 0, 1), "between should be true!")
 	}
 
 	// Now, construct a ring with entries at +10 and -10
@@ -87,151 +104,157 @@ func TestBetween(t *testing.T) {
 	for i := 10; i <= 244; i++ {
 		ipStr := fmt.Sprintf("10.0.0.%d", i)
 		ip := ParseIP(ipStr)
-		wt.AssertTrue(t, ring1.Entries.between(ip, 0, 1),
+		require.True(t, ring1.Entries.between(ip, 0, 1),
 			fmt.Sprintf("Between should be true for %s!", ipStr))
-		wt.AssertFalse(t, ring1.Entries.between(ip, 1, 2),
+		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)
-		wt.AssertFalse(t, ring1.Entries.between(ip, 0, 1),
+		require.False(t, ring1.Entries.between(ip, 0, 1),
 			fmt.Sprintf("Between should be false for %s!", ipStr))
-		wt.AssertTrue(t, ring1.Entries.between(ip, 1, 2),
+		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)
-		wt.AssertFalse(t, ring1.Entries.between(ip, 0, 1),
+		require.False(t, ring1.Entries.between(ip, 0, 1),
 			fmt.Sprintf("Between should be false for %s!", ipStr))
-		wt.AssertTrue(t, ring1.Entries.between(ip, 1, 2),
+		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)
+	ring1 := NewRing(start, end, peer1name)
+	ring2 := NewRing(start, end, peer2name)
 
 	// Claim everything for peer1
 	ring1.ClaimItAll()
-	wt.AssertEquals(t, ring1.Entries, entries{{Token: start, Peer: peer1name, Free: 255}})
+	require.Equal(t, entries{{Token: start, Peer: peer1name, Free: 256}}, ring1.Entries)
 
 	// Now grant everything to peer2
 	ring1.GrantRangeToHost(start, end, peer2name)
-	ring2.Entries = []*entry{{Token: start, Peer: peer2name, Free: 255, Version: 1}}
-	wt.AssertEquals(t, ring1.Entries, ring2.Entries)
+	ring2.Entries = []*entry{{Token: start, Peer: peer2name, Free: 256, 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}}
-	wt.AssertEquals(t, ring1.Entries, ring2.Entries)
+		{Token: dot10, Peer: peer1name, Free: 246}}
+	require.Equal(t, ring2.Entries, ring1.Entries)
 
 	// And spint back to peer 2 again
 	ring1.GrantRangeToHost(dot245, end, peer2name)
-	wt.AssertEquals(t, ring1.Entries, entries{{Token: start, Peer: peer2name, Free: 10, Version: 2},
+	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}})
+		{Token: dot245, Peer: peer2name, Free: 11}}, 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)
-	wt.AssertEquals(t, ring1.Entries, entries{{Token: start, Peer: peer1name, Free: 10, Version: 2},
+	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}})
+		{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)
+	ring1 := NewRing(start, end, peer1name)
+	ring2 := NewRing(start, end, peer2name)
 
 	// Claim everything for peer1
-	ring1.Entries = []*entry{{Token: start, Peer: peer1name, Free: 255}}
-	ring2.Merge(*ring1)
-	wt.AssertEquals(t, ring1.Entries, ring2.Entries)
+	ring1.Entries = []*entry{{Token: start, Peer: peer1name, Free: 256}}
+	merge(ring2, ring1)
+	require.Equal(t, ring2.Entries, ring1.Entries)
 
 	// Now grant a split range to peer2
 	ring1.GrantRangeToHost(dot10, dot245, peer2name)
-	wt.AssertEquals(t, ring1.Entries, entries{{Token: start, Peer: peer1name, Free: 10, Version: 1},
+	require.Equal(t, entries{{Token: start, Peer: peer1name, Free: 10, Version: 1},
 		{Token: dot10, Peer: peer2name, Free: 235},
-		{Token: dot245, Peer: peer1name, Free: 10}})
+		{Token: dot245, Peer: peer1name, Free: 11}}, 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)
-	wt.AssertEquals(t, ring1.Entries, entries{{Token: start, Peer: peer1name, Free: 10, Version: 2},
+	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}})
+		{Token: dot245, Peer: peer1name, Free: 11, Version: 0}}, ring1.Entries)
+
 	ring1.assertInvariants()
 }
 
 func TestMergeSimple(t *testing.T) {
-	ring1 := New(start, end, peer1name)
-	ring2 := New(start, end, peer2name)
+	ring1 := NewRing(start, end, peer1name)
+	ring2 := NewRing(start, end, peer2name)
 
 	// Claim everything for peer1
 	ring1.ClaimItAll()
 	ring1.GrantRangeToHost(middle, end, peer2name)
-	wt.AssertSuccess(t, ring2.Merge(*ring1))
+	require.NoError(t, merge(ring2, ring1))
 
-	wt.AssertEquals(t, ring1.Entries, entries{{Token: start, Peer: peer1name, Free: 128, Version: 1},
-		{Token: middle, Peer: peer2name, Free: 127}})
-	wt.AssertEquals(t, ring1.Entries, ring2.Entries)
+	require.Equal(t, entries{{Token: start, Peer: peer1name, Free: 128, Version: 1},
+		{Token: middle, Peer: peer2name, Free: 128}}, 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)
 
-	wt.AssertSuccess(t, ring2.Merge(*ring1))
-	wt.AssertSuccess(t, ring1.Merge(*ring2))
+	require.NoError(t, merge(ring2, ring1))
+	require.NoError(t, merge(ring1, ring2))
 
-	wt.AssertEquals(t, ring1.Entries, entries{{Token: start, Peer: peer2name, Free: 128, Version: 2},
-		{Token: middle, Peer: peer1name, Free: 127, Version: 1}})
-	wt.AssertEquals(t, ring1.Entries, ring2.Entries)
+	require.Equal(t, entries{{Token: start, Peer: peer2name, Free: 128, Version: 2},
+		{Token: middle, Peer: peer1name, Free: 128, 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)
+	ring1 := NewRing(start, end, peer1name)
+	ring2 := NewRing(start, end, peer2name)
 	ring2.Entries = []*entry{{Token: middle, Peer: peer2name}, {Token: start, Peer: peer2name}}
-	wt.AssertTrue(t, ring1.Merge(*ring2) == ErrNotSorted, "Expected ErrNotSorted")
+	require.True(t, merge(ring1, ring2) == ErrNotSorted, "Expected ErrNotSorted")
 
 	// Should Merge two rings for different ranges
-	ring2 = New(start, middle, peer2name)
+	ring2 = NewRing(start, middle, peer2name)
 	ring2.Entries = []*entry{}
-	wt.AssertTrue(t, ring1.Merge(*ring2) == ErrDifferentSubnets, "Expected ErrDifferentSubnets")
+	require.True(t, merge(ring1, ring2) == ErrDifferentRange, "Expected ErrDifferentRange")
 
 	// Cannot Merge newer version of entry I own
-	ring2 = New(start, end, peer2name)
+	ring2 = NewRing(start, end, peer2name)
 	ring1.Entries = []*entry{{Token: start, Peer: peer1name}}
 	ring2.Entries = []*entry{{Token: start, Peer: peer1name, Version: 1}}
-	wt.AssertTrue(t, ring1.Merge(*ring2) == ErrNewerVersion, "Expected ErrNewerVersion")
+	fmt.Println(merge(ring1, ring2))
+	require.Error(t, merge(ring1, ring2), "Expected error")
 
 	// Cannot Merge two entries with same version but different hosts
 	ring1.Entries = []*entry{{Token: start, Peer: peer1name}}
 	ring2.Entries = []*entry{{Token: start, Peer: peer2name}}
-	wt.AssertTrue(t, ring1.Merge(*ring2) == ErrInvalidEntry, "Expected ErrInvalidEntry")
+	require.Error(t, merge(ring1, ring2), "Expected error")
 
 	// Cannot Merge an entry into a range I own
 	ring1.Entries = []*entry{{Token: start, Peer: peer1name}}
 	ring2.Entries = []*entry{{Token: middle, Peer: peer2name}}
-	wt.AssertTrue(t, ring1.Merge(*ring2) == ErrEntryInMyRange, "Expected ErrEntryInMyRange")
+	require.Error(t, merge(ring1, ring2), "Expected error")
 }
 
 func TestMergeMore(t *testing.T) {
-	ring1 := New(start, end, peer1name)
-	ring2 := New(start, end, peer2name)
+	ring1 := NewRing(start, end, peer1name)
+	ring2 := NewRing(start, end, peer2name)
 
 	assertRing := func(ring *Ring, entries entries) {
-		wt.AssertEquals(t, ring.Entries, entries)
+		require.Equal(t, entries, ring.Entries)
 	}
 
 	assertRing(ring1, []*entry{})
@@ -239,93 +262,97 @@ func TestMergeMore(t *testing.T) {
 
 	// Claim everything for peer1
 	ring1.ClaimItAll()
-	assertRing(ring1, []*entry{{Token: start, Peer: peer1name, Free: 255}})
+	assertRing(ring1, []*entry{{Token: start, Peer: peer1name, Free: 256}})
 	assertRing(ring2, []*entry{})
 
 	// Check the Merge sends it to the other ring
-	wt.AssertSuccess(t, ring2.Merge(*ring1))
-	assertRing(ring1, []*entry{{Token: start, Peer: peer1name, Free: 255}})
-	assertRing(ring2, []*entry{{Token: start, Peer: peer1name, Free: 255}})
+	require.NoError(t, merge(ring2, ring1))
+	assertRing(ring1, []*entry{{Token: start, Peer: peer1name, Free: 256}})
+	assertRing(ring2, []*entry{{Token: start, Peer: peer1name, Free: 256}})
 
 	// 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}})
+	assertRing(ring1, []*entry{{Token: start, Peer: peer2name, Free: 256, Version: 1}})
+	assertRing(ring2, []*entry{{Token: start, Peer: peer1name, Free: 256}})
 
-	wt.AssertSuccess(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}})
+	require.NoError(t, merge(ring2, ring1))
+	assertRing(ring1, []*entry{{Token: start, Peer: peer2name, Free: 256, Version: 1}})
+	assertRing(ring2, []*entry{{Token: start, Peer: peer2name, Free: 256, 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}})
+		{Token: middle, Peer: peer1name, Free: 128}})
+	assertRing(ring1, []*entry{{Token: start, Peer: peer2name, Free: 256, Version: 1}})
 
 	// And Merge back
-	wt.AssertSuccess(t, ring1.Merge(*ring2))
+	require.NoError(t, merge(ring1, ring2))
 	assertRing(ring1, []*entry{{Token: start, Peer: peer2name, Free: 128, Version: 2},
-		{Token: middle, Peer: peer1name, Free: 127}})
+		{Token: middle, Peer: peer1name, Free: 128}})
 	assertRing(ring2, []*entry{{Token: start, Peer: peer2name, Free: 128, Version: 2},
-		{Token: middle, Peer: peer1name, Free: 127}})
+		{Token: middle, Peer: peer1name, Free: 128}})
 
 	// This should be a no-op
-	wt.AssertSuccess(t, ring2.Merge(*ring1))
+	require.NoError(t, merge(ring2, ring1))
 	assertRing(ring1, []*entry{{Token: start, Peer: peer2name, Free: 128, Version: 2},
-		{Token: middle, Peer: peer1name, Free: 127}})
+		{Token: middle, Peer: peer1name, Free: 128}})
 	assertRing(ring2, []*entry{{Token: start, Peer: peer2name, Free: 128, Version: 2},
-		{Token: middle, Peer: peer1name, Free: 127}})
+		{Token: middle, Peer: peer1name, Free: 128}})
 }
 
 func TestMergeSplit(t *testing.T) {
-	ring1 := New(start, end, peer1name)
-	ring2 := New(start, end, peer2name)
+	ring1 := NewRing(start, end, peer1name)
+	ring2 := NewRing(start, end, peer2name)
 
 	// Claim everything for peer2
-	ring1.Entries = []*entry{{Token: start, Peer: peer2name, Free: 255}}
-	wt.AssertSuccess(t, ring2.Merge(*ring1))
-	wt.AssertEquals(t, ring1.Entries, ring2.Entries)
+	ring1.Entries = []*entry{{Token: start, Peer: peer2name, Free: 256}}
+	require.NoError(t, merge(ring2, ring1))
+	require.Equal(t, ring2.Entries, ring1.Entries)
 
 	// Now grant a split range to peer1
 	ring2.GrantRangeToHost(dot10, dot245, peer1name)
-	wt.AssertEquals(t, ring2.Entries, entries{{Token: start, Peer: peer2name, Free: 10, Version: 1},
+	require.Equal(t, entries{{Token: start, Peer: peer2name, Free: 10, Version: 1},
 		{Token: dot10, Peer: peer1name, Free: 235},
-		{Token: dot245, Peer: peer2name, Free: 10}})
-	wt.AssertSuccess(t, ring1.Merge(*ring2))
-	wt.AssertEquals(t, ring1.Entries, entries{{Token: start, Peer: peer2name, Free: 10, Version: 1},
+		{Token: dot245, Peer: peer2name, Free: 11}}, ring2.Entries)
+
+	require.NoError(t, merge(ring1, 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}})
-	wt.AssertEquals(t, ring1.Entries, ring2.Entries)
+		{Token: dot245, Peer: peer2name, Free: 11}}, ring1.Entries)
+
+	require.Equal(t, ring2.Entries, ring1.Entries)
 }
 
 func TestMergeSplit2(t *testing.T) {
-	ring1 := New(start, end, peer1name)
-	ring2 := New(start, end, peer2name)
+	ring1 := NewRing(start, end, peer1name)
+	ring2 := NewRing(start, end, peer2name)
 
 	// Claim everything for peer2
 	ring1.Entries = []*entry{{Token: start, Peer: peer2name, Free: 250}, {Token: dot250, Peer: peer2name, Free: 5}}
-	wt.AssertSuccess(t, ring2.Merge(*ring1))
-	wt.AssertEquals(t, ring1.Entries, ring2.Entries)
+	require.NoError(t, merge(ring2, ring1))
+	require.Equal(t, ring2.Entries, ring1.Entries)
 
 	// Now grant a split range to peer1
 	ring2.GrantRangeToHost(dot10, dot245, peer1name)
-	wt.AssertEquals(t, ring2.Entries, entries{{Token: start, Peer: peer2name, Free: 10, Version: 1},
+	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}})
-	wt.AssertSuccess(t, ring1.Merge(*ring2))
-	wt.AssertEquals(t, ring1.Entries, entries{{Token: start, Peer: peer2name, Free: 10, Version: 1},
+		{Token: dot245, Peer: peer2name, Free: 5}, {Token: dot250, Peer: peer2name, Free: 5}}, ring2.Entries)
+
+	require.NoError(t, merge(ring1, 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}})
-	wt.AssertEquals(t, ring1.Entries, ring2.Entries)
+		{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)
+	ring1 := NewRing(start, end, peer1name)
+	ring2 := NewRing(start, end, peer2name)
 
 	assertRing := func(ring *Ring, entries entries) {
-		wt.AssertEquals(t, ring.Entries, entries)
+		require.Equal(t, entries, ring.Entries)
 	}
 
 	assertRing(ring1, []*entry{})
@@ -333,57 +360,66 @@ func TestGossip(t *testing.T) {
 
 	// Claim everything for peer1
 	ring1.ClaimItAll()
-	assertRing(ring1, []*entry{{Token: start, Peer: peer1name, Free: 255}})
+	assertRing(ring1, []*entry{{Token: start, Peer: peer1name, Free: 256}})
 	assertRing(ring2, []*entry{})
 
 	// Check the Merge sends it to the other ring
-	wt.AssertSuccess(t, ring2.Merge(*ring1))
-	assertRing(ring1, []*entry{{Token: start, Peer: peer1name, Free: 255}})
-	assertRing(ring2, []*entry{{Token: start, Peer: peer1name, Free: 255}})
+	require.NoError(t, merge(ring2, ring1))
+	assertRing(ring1, []*entry{{Token: start, Peer: peer1name, Free: 256}})
+	assertRing(ring2, []*entry{{Token: start, Peer: peer1name, Free: 256}})
+}
+
+func assertPeersWithSpace(t *testing.T, ring *Ring, start, end address.Address, expected int) []mesh.PeerName {
+	peers := ring.ChoosePeersToAskForSpace(start, end)
+	require.Equal(t, expected, len(peers))
+	return peers
 }
 
 func TestFindFree(t *testing.T) {
-	ring1 := New(start, end, peer1name)
+	ring1 := NewRing(start, end, peer1name)
 
-	_, err := ring1.ChoosePeerToAskForSpace()
-	wt.AssertTrue(t, err == ErrNoFreeSpace, "Expected ErrNoFreeSpace")
+	assertPeersWithSpace(t, ring1, start, end, 0)
 
 	ring1.Entries = []*entry{{Token: start, Peer: peer1name}}
-	_, err = ring1.ChoosePeerToAskForSpace()
-	wt.AssertTrue(t, err == ErrNoFreeSpace, "Expected ErrNoFreeSpace")
+	assertPeersWithSpace(t, ring1, start, end, 0)
 
 	// We shouldn't return outselves
-	ring1.ReportFree(map[address.Address]address.Offset{start: 10})
-	_, err = ring1.ChoosePeerToAskForSpace()
-	wt.AssertTrue(t, err == ErrNoFreeSpace, "Expected ErrNoFreeSpace")
+	ring1.ReportFree(map[address.Address]address.Count{start: 10})
+	assertPeersWithSpace(t, ring1, start, end, 0)
 
 	ring1.Entries = []*entry{{Token: start, Peer: peer1name, Free: 1},
-		{Token: start, Peer: peer1name, Free: 1}}
-	_, err = ring1.ChoosePeerToAskForSpace()
-	wt.AssertTrue(t, err == ErrNoFreeSpace, "Expected ErrNoFreeSpace")
+		{Token: middle, Peer: peer1name, Free: 1}}
+	assertPeersWithSpace(t, ring1, start, end, 0)
+	ring1.assertInvariants()
 
 	// We should return others
+	var peers []mesh.PeerName
+
 	ring1.Entries = []*entry{{Token: start, Peer: peer2name, Free: 1}}
-	peer, err := ring1.ChoosePeerToAskForSpace()
-	wt.AssertSuccess(t, err)
-	wt.AssertEquals(t, peer, peer2name)
+	peers = assertPeersWithSpace(t, ring1, start, end, 1)
+	require.Equal(t, peer2name, peers[0])
 
 	ring1.Entries = []*entry{{Token: start, Peer: peer2name, Free: 1},
-		{Token: start, Peer: peer2name, Free: 1}}
-	peer, err = ring1.ChoosePeerToAskForSpace()
-	wt.AssertSuccess(t, err)
-	wt.AssertEquals(t, peer, peer2name)
+		{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 := NewRing(start, end, peer1name)
+	ring2 := NewRing(start, end, peer2name)
 
 	ring1.ClaimItAll()
 	ring1.GrantRangeToHost(middle, end, peer2name)
-	wt.AssertSuccess(t, ring2.Merge(*ring1))
+	require.NoError(t, merge(ring2, ring1))
 
-	freespace := make(map[address.Address]address.Offset)
+	freespace := make(map[address.Address]address.Count)
 	for _, r := range ring2.OwnedRanges() {
 		freespace[r.Start] = 0
 	}
@@ -391,100 +427,130 @@ func TestReportFree(t *testing.T) {
 }
 
 func TestMisc(t *testing.T) {
-	ring := New(start, end, peer1name)
+	ring := NewRing(start, end, peer1name)
 
-	wt.AssertTrue(t, ring.Empty(), "empty")
+	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 := NewRing(start, end, peer1name)
+	ring2 := NewRing(start, end, peer2name)
 
 	ring1.ClaimItAll()
 	// This used to panic, and it shouldn't
-	wt.AssertSuccess(t, ring1.Merge(*ring2))
+	require.NoError(t, merge(ring1, ring2))
 }
 
 func TestMergeOldMessage(t *testing.T) {
-	ring1 := New(start, end, peer1name)
-	ring2 := New(start, end, peer2name)
+	ring1 := NewRing(start, end, peer1name)
+	ring2 := NewRing(start, end, peer2name)
 
 	ring1.ClaimItAll()
-	wt.AssertSuccess(t, ring2.Merge(*ring1))
+	require.NoError(t, merge(ring2, ring1))
 
 	ring1.GrantRangeToHost(middle, end, peer1name)
-	wt.AssertSuccess(t, ring1.Merge(*ring2))
+	require.NoError(t, merge(ring1, ring2))
 }
 
 func TestSplitRangeAtBeginning(t *testing.T) {
-	ring1 := New(start, end, peer1name)
-	ring2 := New(start, end, peer2name)
+	ring1 := NewRing(start, end, peer1name)
+	ring2 := NewRing(start, end, peer2name)
 
 	ring1.ClaimItAll()
-	wt.AssertSuccess(t, ring2.Merge(*ring1))
+	require.NoError(t, merge(ring2, ring1))
 
 	ring1.GrantRangeToHost(start, middle, peer2name)
-	wt.AssertSuccess(t, ring2.Merge(*ring1))
+	require.NoError(t, merge(ring2, ring1))
 }
 
 func TestOwnedRange(t *testing.T) {
-	ring1 := New(start, end, peer1name)
+	ring1 := NewRing(start, end, peer1name)
 	ring1.ClaimItAll()
 
-	wt.AssertEquals(t, ring1.OwnedRanges(), []address.Range{{Start: start, End: end}})
+	require.Equal(t, []address.Range{{Start: start, End: end}}, ring1.OwnedRanges())
 
 	ring1.GrantRangeToHost(middle, end, peer2name)
-	wt.AssertEquals(t, ring1.OwnedRanges(), []address.Range{{Start: start, End: middle}})
+	require.Equal(t, []address.Range{{Start: start, End: middle}}, ring1.OwnedRanges())
 
-	ring2 := New(start, end, peer2name)
-	ring2.Merge(*ring1)
-	wt.AssertEquals(t, ring2.OwnedRanges(), []address.Range{{Start: middle, End: end}})
+	ring2 := NewRing(start, end, peer2name)
+	merge(ring2, ring1)
+	require.Equal(t, []address.Range{{Start: middle, End: end}}, ring2.OwnedRanges())
 
 	ring2.Entries = []*entry{{Token: middle, Peer: peer2name}}
-	wt.AssertEquals(t, ring2.OwnedRanges(),
-		[]address.Range{{Start: start, End: middle}, {Start: middle, End: end}})
+	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}}
-	wt.AssertEquals(t, ring2.OwnedRanges(),
-		[]address.Range{{Start: start, End: dot10}, {Start: dot10, End: middle},
-			{Start: middle, End: end}})
+	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 := NewRing(start, end, peer1name)
 	ring1.ClaimItAll()
 	ring1.GrantRangeToHost(middle, end, peer2name)
 	ring1.Transfer(peer2name, peer1name)
-	wt.AssertEquals(t, ring1.OwnedRanges(), []address.Range{{start, middle}, {middle, end}})
+	require.Equal(t, []address.Range{{Start: start, End: middle}, {Start: middle, End: 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 = NewRing(start, end, peer1name)
 	ring1.ClaimItAll()
 	ring1.GrantRangeToHost(middle, end, peer2name)
 	ring1.Transfer(peer2name, peer1name)
 	ring1.GrantRangeToHost(dot10, middle, peer2name)
-	wt.AssertEquals(t, ring1.OwnedRanges(), []address.Range{{start, dot10}, {middle, end}})
+	require.Equal(t, []address.Range{{Start: start, End: dot10}, {Start: middle, End: end}}, ring1.OwnedRanges())
 }
 
 func TestOwner(t *testing.T) {
-	ring1 := New(start, end, peer1name)
-	wt.AssertTrue(t, ring1.Contains(start), "start should be in ring")
-	wt.AssertFalse(t, ring1.Contains(end), "end should not be in ring")
+	ring1 := NewRing(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")
 
-	wt.AssertEquals(t, ring1.Owner(start), router.UnknownPeerName)
+	require.Equal(t, mesh.UnknownPeerName, ring1.Owner(start))
 
 	ring1.ClaimItAll()
 	ring1.GrantRangeToHost(middle, end, peer2name)
-	wt.AssertEquals(t, ring1.Owner(start), peer1name)
-	wt.AssertEquals(t, ring1.Owner(middle), peer2name)
-	wt.AssertPanic(t, func() {
+	require.Equal(t, peer1name, ring1.Owner(start))
+	require.Equal(t, peer2name, ring1.Owner(middle))
+	require.Panics(t, func() {
 		ring1.Owner(end)
 	})
+
+}
+
+func makePeerName(i int) mesh.PeerName {
+	if i >= 10000 {
+		panic("makePeerName: invalid value")
+	}
+	peer, _ := mesh.PeerNameFromString(fmt.Sprintf("%02d:%02d:00:00:00:ff", i/100, i%100))
+	return peer
+}
+
+func makePeers(numPeers int) []mesh.PeerName {
+	peers := make([]mesh.PeerName, numPeers)
+	for i := 0; i < numPeers; i++ {
+		peers[i] = makePeerName(i)
+	}
+	return peers
+}
+
+func TestClaimForPeers(t *testing.T) {
+	const numPeers = 12
+	// Different end to usual so we get a number of addresses that a)
+	// is smaller than the max number of peers, and b) is divisible by
+	// some number of peers. This maximises coverage of edge cases.
+	end := dot8
+	peers := makePeers(numPeers)
+	// Test for a range of peer counts
+	for i := 0; i < numPeers; i++ {
+		ring := NewRing(start, end, peers[0])
+		ring.ClaimForPeers(peers[:i+1])
+	}
 }
 
 type addressSlice []address.Address
@@ -499,10 +565,9 @@ func TestFuzzRing(t *testing.T) {
 		iterations = 1000
 	)
 
-	peers := make([]router.PeerName, numPeers)
+	peers := make([]mesh.PeerName, numPeers)
 	for i := 0; i < numPeers; i++ {
-		peer, _ := router.PeerNameFromString(fmt.Sprintf("%02d:00:00:00:02:00", i))
-		peers[i] = peer
+		peers[i] = makePeerName(i)
 	}
 
 	// Make a valid, random ring
@@ -521,7 +586,7 @@ func TestFuzzRing(t *testing.T) {
 		sort.Sort(addressSlice(tokens))
 
 		peer := peers[rand.Intn(len(peers))]
-		ring := New(start, end, peer)
+		ring := NewRing(start, end, peer)
 		for _, token := range tokens {
 			peer = peers[rand.Intn(len(peers))]
 			ring.Entries = append(ring.Entries, &entry{Token: start + token, Peer: peer})
@@ -538,7 +603,7 @@ func TestFuzzRing(t *testing.T) {
 
 		// Merge them - this might fail, we don't care
 		// We just want to make sure it doesn't panic
-		ring1.Merge(*ring2)
+		merge(ring1, ring2)
 
 		// Check whats left still passes assertions
 		ring1.assertInvariants()
@@ -555,7 +620,7 @@ func TestFuzzRing(t *testing.T) {
 		}
 
 		peer := peers[rand.Intn(len(peers))]
-		ring := New(start, end, peer)
+		ring := NewRing(start, end, peer)
 		for _, token := range tokens {
 			peer = peers[rand.Intn(len(peers))]
 			ring.Entries = append(ring.Entries, &entry{Token: start + token, Peer: peer})
@@ -571,7 +636,7 @@ func TestFuzzRing(t *testing.T) {
 
 		// Merge them - this might fail, we don't care
 		// We just want to make sure it doesn't panic
-		ring1.Merge(*ring2)
+		merge(ring1, ring2)
 
 		// Check whats left still passes assertions
 		ring1.assertInvariants()
@@ -579,21 +644,21 @@ func TestFuzzRing(t *testing.T) {
 }
 
 func TestFuzzRingHard(t *testing.T) {
-	//common.InitDefaultLogging(true)
+	//common.SetLogLevel("debug")
 	var (
 		numPeers   = 100
 		iterations = 3000
-		peers      []router.PeerName
+		peers      []mesh.PeerName
 		rings      []*Ring
 		nextPeerID = 0
 	)
 
 	addPeer := func() {
-		peer, _ := router.PeerNameFromString(fmt.Sprintf("%02d:%02d:00:00:00:00", nextPeerID/10, nextPeerID%10))
-		common.Debug.Printf("%s: Adding peer", peer)
+		peer := makePeerName(nextPeerID)
+		common.Log.Debugf("%s: Adding peer", peer)
 		nextPeerID++
 		peers = append(peers, peer)
-		rings = append(rings, New(start, end, peer))
+		rings = append(rings, NewRing(start, end, peer))
 	}
 
 	for i := 0; i < numPeers; i++ {
@@ -602,7 +667,7 @@ func TestFuzzRingHard(t *testing.T) {
 
 	rings[0].ClaimItAll()
 
-	randomPeer := func(exclude int) (int, router.PeerName, *Ring) {
+	randomPeer := func(exclude int) (int, mesh.PeerName, *Ring) {
 		var peerIndex int
 		if exclude >= 0 {
 			peerIndex = rand.Intn(len(peers) - 1)
@@ -626,27 +691,27 @@ func TestFuzzRingHard(t *testing.T) {
 			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, merge(otherRing, 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)
 
-		// Transfer the space for this peer on another peer, but not this one
-		_, otherPeername, otherRing := randomPeer(peerIndex)
-
-		// We need to be in a ~converged ring to rmpeer
-		for _, ring := range rings {
-			wt.AssertSuccess(t, otherRing.Merge(*ring))
-		}
-
-		common.Debug.Printf("%s: transferring from peer %s", otherPeername, peername)
-		otherRing.Transfer(peername, peername)
-
 		// And now tell everyone about the transfer - rmpeer is
 		// not partition safe
 		for i, ring := range rings {
-			wt.AssertSuccess(t, ring.Merge(*otherRing))
+			require.NoError(t, merge(ring, otherRing))
 			theRanges[i] = ring.OwnedRanges()
 		}
 	}
@@ -669,13 +734,13 @@ func TestFuzzRingHard(t *testing.T) {
 			size := address.Subtract(rangeToSplit.End, rangeToSplit.Start)
 			ipInRange := address.Add(rangeToSplit.Start, address.Offset(rand.Intn(int(size))))
 			_, peerToGiveTo, _ := randomPeer(-1)
-			common.Debug.Printf("%s: Granting [%v, %v) to %s", ring.Peer, ipInRange, rangeToSplit.End, peerToGiveTo)
+			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.Debug.Printf("%s: 'Gossiping' to %s", ring.Peer, otherRing.Peer)
-			wt.AssertSuccess(t, otherRing.Merge(*ring))
+			common.Log.Debugf("%s: 'Gossiping' to %s", ring.Peer, otherRing.Peer)
+			require.NoError(t, merge(otherRing, ring))
 
 			theRanges[indexWithRanges] = ring.OwnedRanges()
 			theRanges[otherIndex] = otherRing.OwnedRanges()
@@ -693,8 +758,8 @@ func TestFuzzRingHard(t *testing.T) {
 		}
 		ring1 := ringsWithEntries[rand.Intn(len(ringsWithEntries))]
 		ring2index, _, ring2 := randomPeer(-1)
-		common.Debug.Printf("%s: 'Gossiping' to %s", ring1.Peer, ring2.Peer)
-		wt.AssertSuccess(t, ring2.Merge(*ring1))
+		common.Log.Debugf("%s: 'Gossiping' to %s", ring1.Peer, ring2.Peer)
+		require.NoError(t, merge(ring2, ring1))
 		theRanges[ring2index] = ring2.OwnedRanges()
 	}
 
@@ -710,6 +775,10 @@ func TestFuzzRingHard(t *testing.T) {
 	}
 }
 
+func (r *Ring) ClaimItAll() {
+	r.ClaimForPeers([]mesh.PeerName{r.Peer})
+}
+
 func (es entries) String() string {
 	var buffer bytes.Buffer
 	fmt.Fprintf(&buffer, "[")

ipam/space/space.go

@@ -6,11 +6,9 @@ import (
 	"sort"
 
 	"github.com/weaveworks/weave/common"
-	"github.com/weaveworks/weave/ipam/address"
+	"github.com/weaveworks/weave/net/address"
 )
 
-type Addr address.Address
-
 type Space struct {
 	// ours and free represent a set of addresses as a sorted
 	// sequences of ranges.  Even elements give the inclusive
@@ -33,19 +31,51 @@ func (s *Space) Add(start address.Address, size address.Offset) {
 
 // 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]
+	s.free = s.free[:0]
 }
 
-func (s *Space) Allocate() (bool, address.Address) {
-	if len(s.free) == 0 {
-		return false, 0
-	} else {
-		res := s.free[0]
-		s.ours = add(s.ours, res, res+1)
-		s.free = subtract(s.free, res, res+1)
-		return true, res
+// 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 {
@@ -58,32 +88,31 @@ func (s *Space) Claim(addr address.Address) error {
 	return nil
 }
 
-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])
+func (s *Space) NumOwnedAddresses() address.Count {
+	res := address.Count(0)
+	for i := 0; i < len(s.ours); i += 2 {
+		res += address.Length(s.ours[i+1], s.ours[i])
 	}
 	return res
 }
 
-func (s *Space) NumFreeAddressesInRange(start, end address.Address) address.Offset {
-	res := address.Offset(0)
+func (s *Space) NumFreeAddresses() address.Count {
+	res := address.Count(0)
 	for i := 0; i < len(s.free); i += 2 {
-		s, e := s.free[i], s.free[i+1]
-		if s < start {
-			s = start
-		}
-		if e > end {
-			e = end
-		}
-		if s >= e {
-			continue
-		}
-		res += address.Subtract(e, s)
+		res += address.Length(s.free[i+1], s.free[i])
 	}
 	return res
 }
 
+func (s *Space) NumFreeAddressesInRange(r address.Range) address.Count {
+	res := address.Count(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)
@@ -97,35 +126,38 @@ func (s *Space) Free(addr address.Address) error {
 	return nil
 }
 
-func (s *Space) biggestFreeRange() (int, address.Offset) {
-	pos := -1
-	biggest := address.Offset(0)
-
-	for i := 0; i < len(s.free); i += 2 {
-		size := address.Subtract(s.free[i+1], s.free[i])
-		if size >= biggest {
-			pos = i
-			biggest = size
+func (s *Space) biggestFreeRange(r address.Range) (biggest address.Range) {
+	biggestSize := address.Count(0)
+	s.walkFree(r, func(chunk address.Range) bool {
+		if size := chunk.Size(); size >= biggestSize {
+			chunk = chunk.BiggestCIDRRange()
+			if size = chunk.Size(); size >= biggestSize {
+				biggest = chunk
+				biggestSize = size
+			}
 		}
-	}
-	return pos, biggest
+		return false
+	})
+	return
 }
 
-func (s *Space) Donate() (address.Address, address.Offset, bool) {
-	if len(s.free) == 0 {
-		return 0, 0, false
+func (s *Space) Donate(r address.Range) (address.Range, bool) {
+	biggest := s.biggestFreeRange(r)
+
+	if biggest.Size() == 0 {
+		return address.Range{}, false
 	}
 
-	pos, biggest := s.biggestFreeRange()
+	// Donate no more than half what we have available
+	if biggest.Size() > s.NumFreeAddressesInRange(r)/2 {
+		// 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, address.Offset(biggest.Size()/2))
+	}
 
-	// Donate half of that biggest free range, rounding up so
-	// that the donation can't be empty
-	end := s.free[pos+1]
-	start := end - address.Address((biggest+1)/2)
-
-	s.ours = subtract(s.ours, start, end)
-	s.free = subtract(s.free, start, end)
-	return start, address.Subtract(end, start), true
+	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 {
@@ -152,25 +184,25 @@ func subtract(addrs []address.Address, start address.Address, end address.Addres
 }
 
 func addSub(addrs []address.Address, start address.Address, end address.Address, sense int) []address.Address {
-	start_pos := firstGreaterOrEq(addrs, start)
-	end_pos := firstGreater(addrs[start_pos:], end) + start_pos
+	startPos := firstGreaterOrEq(addrs, start)
+	endPos := firstGreater(addrs[startPos:], end) + startPos
 
-	// Boundaries up to start_pos are unaffected
-	res := make([]address.Address, start_pos, len(addrs)+2)
+	// 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 start_pos&1 == sense {
+	if startPos&1 == sense {
 		res = append(res, start)
 	}
 
-	if end_pos&1 == sense {
+	if endPos&1 == sense {
 		res = append(res, end)
 	}
 
-	// Boundaries after end_pos are unaffected
-	return append(res, addrs[end_pos:]...)
+	// Boundaries after endPos are unaffected
+	return append(res, addrs[endPos:]...)
 }
 
 func (s *Space) String() string {

ipam/space/space_test.go

@@ -1,10 +1,10 @@
 package space
 
 import (
-	"reflect"
 	"testing"
 
-	"github.com/weaveworks/weave/ipam/address"
+	"github.com/stretchr/testify/require"
+	"github.com/weaveworks/weave/net/address"
 	wt "github.com/weaveworks/weave/testing"
 )
 
@@ -22,194 +22,202 @@ func ip(s string) address.Address {
 func TestLowlevel(t *testing.T) {
 	a := []address.Address{}
 	a = add(a, 100, 200)
-	wt.AssertEquals(t, a, []address.Address{100, 200})
-	wt.AssertTrue(t, !contains(a, 99), "")
-	wt.AssertTrue(t, contains(a, 100), "")
-	wt.AssertTrue(t, contains(a, 199), "")
-	wt.AssertTrue(t, !contains(a, 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)
-	wt.AssertEquals(t, a, []address.Address{100, 200, 700, 800})
+	require.Equal(t, []address.Address{100, 200, 700, 800}, a)
 	a = add(a, 300, 400)
-	wt.AssertEquals(t, a, []address.Address{100, 200, 300, 400, 700, 800})
+	require.Equal(t, []address.Address{100, 200, 300, 400, 700, 800}, a)
 	a = add(a, 400, 500)
-	wt.AssertEquals(t, a, []address.Address{100, 200, 300, 500, 700, 800})
+	require.Equal(t, []address.Address{100, 200, 300, 500, 700, 800}, a)
 	a = add(a, 600, 700)
-	wt.AssertEquals(t, a, []address.Address{100, 200, 300, 500, 600, 800})
+	require.Equal(t, []address.Address{100, 200, 300, 500, 600, 800}, a)
 	a = add(a, 500, 600)
-	wt.AssertEquals(t, a, []address.Address{100, 200, 300, 800})
+	require.Equal(t, []address.Address{100, 200, 300, 800}, a)
 	a = subtract(a, 500, 600)
-	wt.AssertEquals(t, a, []address.Address{100, 200, 300, 500, 600, 800})
+	require.Equal(t, []address.Address{100, 200, 300, 500, 600, 800}, a)
 	a = subtract(a, 600, 700)
-	wt.AssertEquals(t, a, []address.Address{100, 200, 300, 500, 700, 800})
+	require.Equal(t, []address.Address{100, 200, 300, 500, 700, 800}, a)
 	a = subtract(a, 400, 500)
-	wt.AssertEquals(t, a, []address.Address{100, 200, 300, 400, 700, 800})
+	require.Equal(t, []address.Address{100, 200, 300, 400, 700, 800}, a)
 	a = subtract(a, 300, 400)
-	wt.AssertEquals(t, a, []address.Address{100, 200, 700, 800})
+	require.Equal(t, []address.Address{100, 200, 700, 800}, a)
 	a = subtract(a, 700, 800)
-	wt.AssertEquals(t, a, []address.Address{100, 200})
+	require.Equal(t, []address.Address{100, 200}, a)
 	a = subtract(a, 100, 200)
-	wt.AssertEquals(t, a, []address.Address{})
+	require.Equal(t, []address.Address{}, a)
 
 	s := New()
-	wt.AssertEquals(t, s.NumFreeAddresses(), address.Offset(0))
-	ok, got := s.Allocate()
-	wt.AssertFalse(t, ok, "allocate in empty space should fail")
+	require.Equal(t, address.Count(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)
-	wt.AssertEquals(t, s.NumFreeAddresses(), address.Offset(100))
-	ok, got = s.Allocate()
-	wt.AssertTrue(t, ok && got == 100, "allocate")
-	wt.AssertEquals(t, s.NumFreeAddresses(), address.Offset(99))
-	wt.AssertNoErr(t, s.Claim(150))
-	wt.AssertEquals(t, s.NumFreeAddresses(), address.Offset(98))
-	wt.AssertNoErr(t, s.Free(100))
-	wt.AssertEquals(t, s.NumFreeAddresses(), address.Offset(99))
-	wt.AssertErrorInterface(t, s.Free(0), (*error)(nil), "free not allocated")
-	wt.AssertErrorInterface(t, s.Free(100), (*error)(nil), "double free")
+	require.Equal(t, address.Count(100), s.NumFreeAddresses())
+	ok, got = s.Allocate(address.NewRange(0, 1000))
+	require.True(t, ok && got == 100, "allocate")
+	require.Equal(t, address.Count(99), s.NumFreeAddresses())
+	require.NoError(t, s.Claim(150))
+	require.Equal(t, address.Count(98), s.NumFreeAddresses())
+	require.NoError(t, s.Free(100))
+	require.Equal(t, address.Count(99), s.NumFreeAddresses())
+	wt.AssertErrorInterface(t, (*error)(nil), s.Free(0), "free not allocated")
+	wt.AssertErrorInterface(t, (*error)(nil), s.Free(100), "double free")
 
-	start, size, ok := s.Donate()
-	wt.AssertTrue(t, ok && start == 125 && size == 25, "donate")
+	r, ok := s.Donate(address.NewRange(0, 1000))
+	require.Equal(t, address.NewRange(0xa0, 0x20), r, "donate")
 
 	// test Donate when addresses are scarce
 	s = New()
-	start, size, ok = s.Donate()
-	wt.AssertTrue(t, !ok, "donate on empty space should fail")
+	r, ok = s.Donate(address.NewRange(0, 1000))
+	require.True(t, !ok, "donate on empty space should fail")
 	s.Add(0, 3)
-	wt.AssertNoErr(t, s.Claim(0))
-	wt.AssertNoErr(t, s.Claim(2))
-	start, size, ok = s.Donate()
-	wt.AssertTrue(t, ok && start == 1 && size == 1, "donate")
-	start, size, ok = s.Donate()
-	wt.AssertTrue(t, !ok, "donate should fail")
+	require.NoError(t, s.Claim(0))
+	require.NoError(t, s.Claim(2))
+	r, ok = s.Donate(address.NewRange(0, 1000))
+	require.Equal(t, address.NewRange(1, 1), r, "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(ip(testAddr1), 20)
-	wt.AssertEquals(t, space1.NumFreeAddresses(), address.Offset(20))
+	space1 := makeSpace(start, size)
+	require.Equal(t, address.Count(20), space1.NumFreeAddresses())
+	require.Equal(t, address.Count(0), space1.NumOwnedAddresses())
 	space1.assertInvariants()
 
-	_, addr1 := space1.Allocate()
-	wt.AssertEqualString(t, addr1.String(), testAddr1, "address")
-	wt.AssertEquals(t, space1.NumFreeAddresses(), address.Offset(19))
+	_, addr1 := space1.Allocate(address.NewRange(start, size))
+	require.Equal(t, testAddr1, addr1.String(), "address")
+	require.Equal(t, address.Count(19), space1.NumFreeAddresses())
+	require.Equal(t, address.Count(1), space1.NumOwnedAddresses())
 	space1.assertInvariants()
 
-	_, addr2 := space1.Allocate()
-	wt.AssertFalse(t, addr2.String() == testAddr1, "address")
-	wt.AssertEquals(t, space1.NumFreeAddresses(), address.Offset(18))
-	wt.AssertEquals(t, space1.NumFreeAddressesInRange(ip(testAddr1), ip(testAddrx)), address.Offset(13))
-	wt.AssertEquals(t, space1.NumFreeAddressesInRange(ip(testAddr1), ip(testAddry)), address.Offset(18))
+	_, addr2 := space1.Allocate(address.NewRange(start, size))
+	require.False(t, addr2.String() == testAddr1, "address")
+	require.Equal(t, address.Count(18), space1.NumFreeAddresses())
+	require.Equal(t, address.Count(2), space1.NumOwnedAddresses())
+	require.Equal(t, address.Count(13), space1.NumFreeAddressesInRange(address.Range{Start: ip(testAddr1), End: ip(testAddrx)}))
+	require.Equal(t, address.Count(18), space1.NumFreeAddressesInRange(address.Range{Start: ip(testAddr1), End: ip(testAddry)}))
 	space1.assertInvariants()
 
 	space1.Free(addr2)
 	space1.assertInvariants()
 
-	wt.AssertErrorInterface(t, space1.Free(addr2), (*error)(nil), "double free")
-	wt.AssertErrorInterface(t, space1.Free(ip(testAddrx)), (*error)(nil), "address not allocated")
-	wt.AssertErrorInterface(t, space1.Free(ip(testAddry)), (*error)(nil), "wrong out of range")
+	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"
+		testAddr1   = "10.0.3.16"
 		testAddrx   = "10.0.3.19"
 		testAddry   = "10.0.9.19"
 		containerID = "deadbeef"
+		size        = 16
 	)
 
-	space := makeSpace(ip(testAddr1), 20)
+	entireRange := address.NewRange(ip(testAddr1), size)
+	space := makeSpace(ip(testAddr1), size)
 
 	// Check we are prepared to give up the entire space
-	pos, size := space.biggestFreeRange()
-	wt.AssertTrue(t, space.free[pos] == ip(testAddr1) && size == 20, "Wrong space")
+	r := space.biggestFreeRange(entireRange)
+	require.Equal(t, address.NewRange(ip(testAddr1), size), r, "Wrong space")
 
-	for i := 0; i < 20; i++ {
-		ok, _ := space.Allocate()
-		wt.AssertTrue(t, ok, "Failed to get address")
+	for i := 0; i < size; i++ {
+		ok, _ := space.Allocate(entireRange)
+		require.True(t, ok, "Failed to get address")
 	}
 
 	// Check we are full
-	ok, _ := space.Allocate()
-	wt.AssertTrue(t, !ok, "Should have failed to get address")
-	_, size, ok = space.Donate()
-	wt.AssertTrue(t, size == 0, "Wrong space")
+	ok, _ := space.Allocate(entireRange)
+	require.True(t, !ok, "Should have failed to get address")
+	r, _ = space.Donate(entireRange)
+	require.True(t, r.Size() == 0, "Wrong space")
 
 	// Free in the middle
-	wt.AssertSuccess(t, space.Free(ip("10.0.3.13")))
-	pos, size = space.biggestFreeRange()
-	wt.AssertTrue(t, space.free[pos] == ip("10.0.3.13") && size == 1, "Wrong space")
+	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")
 
 	// Free one at the end
-	wt.AssertSuccess(t, space.Free(ip("10.0.3.23")))
-	pos, size = space.biggestFreeRange()
-	wt.AssertTrue(t, space.free[pos] == ip("10.0.3.23") && size == 1, "Wrong space")
+	require.NoError(t, space.Free(ip("10.0.3.31")))
+	r = space.biggestFreeRange(entireRange)
+	require.True(t, r.Start == ip("10.0.3.31") && r.Size() == 1, "Wrong space")
 
 	// Now free a few at the end
-	wt.AssertSuccess(t, space.Free(ip("10.0.3.22")))
-	wt.AssertSuccess(t, space.Free(ip("10.0.3.21")))
+	require.NoError(t, space.Free(ip("10.0.3.30")))
+	require.NoError(t, space.Free(ip("10.0.3.29")))
 
-	wt.AssertEquals(t, space.NumFreeAddresses(), address.Offset(4))
+	require.Equal(t, address.Count(4), space.NumFreeAddresses())
 
-	// Now get the biggest free space; should be 3.21
-	pos, size = space.biggestFreeRange()
-	wt.AssertTrue(t, space.free[pos] == ip("10.0.3.21") && size == 3, "Wrong space")
+	// Now get the biggest free space; should be 3.30
+	r = space.biggestFreeRange(entireRange)
+	require.Equal(t, address.NewRange(ip("10.0.3.30"), 2), r, "Wrong space")
 
 	// Now free a few in the middle
-	wt.AssertSuccess(t, space.Free(ip("10.0.3.12")))
-	wt.AssertSuccess(t, space.Free(ip("10.0.3.11")))
-	wt.AssertSuccess(t, space.Free(ip("10.0.3.10")))
+	require.NoError(t, space.Free(ip("10.0.3.24")))
+	require.NoError(t, space.Free(ip("10.0.3.22")))
+	require.NoError(t, space.Free(ip("10.0.3.21")))
 
-	wt.AssertEquals(t, space.NumFreeAddresses(), address.Offset(7))
+	require.Equal(t, address.Count(7), space.NumFreeAddresses())
 
-	// Now get the biggest free space; should be 3.21
-	pos, size = space.biggestFreeRange()
-	wt.AssertTrue(t, space.free[pos] == ip("10.0.3.10") && size == 4, "Wrong space")
+	// Now get the biggest free space; should be 3.30
+	r = space.biggestFreeRange(entireRange)
+	require.Equal(t, address.NewRange(ip("10.0.3.30"), 2), r, "Wrong space")
 
-	wt.AssertEquals(t, space.OwnedRanges(), []address.Range{address.Range{Start: ip("10.0.3.4"), End: ip("10.0.3.24")}})
-}
-
-func (s1 *Space) Equal(s2 *Space) bool {
-	return reflect.DeepEqual(s1.ours, s2.ours) && reflect.DeepEqual(s1.free, s2.free)
+	require.Equal(t, []address.Range{{Start: ip("10.0.3.16"), End: ip("10.0.3.32")}}, space.OwnedRanges())
 }
 
 func TestDonateSimple(t *testing.T) {
 	const (
 		testAddr1 = "10.0.1.0"
 		testAddr2 = "10.0.1.32"
+		size      = 64
 	)
 
 	var (
 		ipAddr1 = ip(testAddr1)
 	)
 
-	ps1 := makeSpace(ipAddr1, 48)
+	ps1 := makeSpace(ipAddr1, size)
 
 	// Empty space set should split in two and give me the second half
-	start, numGivenUp, ok := ps1.Donate()
-	wt.AssertTrue(t, ok, "Donate result")
-	wt.AssertEqualString(t, start.String(), "10.0.1.24", "Invalid start")
-	wt.AssertEquals(t, numGivenUp, address.Offset(24))
-	wt.AssertEquals(t, ps1.NumFreeAddresses(), address.Offset(24))
+	r, ok := ps1.Donate(address.NewRange(ip(testAddr1), size))
+	numGivenUp := r.Size()
+	require.True(t, ok, "Donate result")
+	require.Equal(t, "10.0.1.32", r.Start.String(), "Invalid start")
+	require.Equal(t, address.Count(size/2), numGivenUp)
+	require.Equal(t, address.Count(size/2), ps1.NumFreeAddresses())
 
 	// Now check we can give the rest up.
 	count := 0 // count to avoid infinite loop
 	for ; count < 1000; count++ {
-		_, size, ok := ps1.Donate()
+		r, ok := ps1.Donate(address.NewRange(ip(testAddr1), size))
 		if !ok {
 			break
 		}
-		numGivenUp += size
+		numGivenUp += r.Size()
 	}
-	wt.AssertEquals(t, ps1.NumFreeAddresses(), address.Offset(0))
-	wt.AssertEquals(t, numGivenUp, address.Offset(48))
+	require.Equal(t, address.Count(0), ps1.NumFreeAddresses())
+	require.Equal(t, address.Count(size), numGivenUp)
 }
 
 func TestDonateHard(t *testing.T) {
@@ -222,28 +230,28 @@ func TestDonateHard(t *testing.T) {
 	// Fill a fresh space
 	spaceset := makeSpace(start, size)
 	for i := address.Offset(0); i < size; i++ {
-		ok, _ := spaceset.Allocate()
-		wt.AssertTrue(t, ok, "Failed to get IP!")
+		ok, _ := spaceset.Allocate(address.NewRange(start, size))
+		require.True(t, ok, "Failed to get IP!")
 	}
 
-	wt.AssertEquals(t, spaceset.NumFreeAddresses(), address.Offset(0))
+	require.Equal(t, address.Count(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++ {
-		wt.AssertSuccess(t, spaceset.Free(address.Add(start, i)))
+		require.NoError(t, spaceset.Free(address.Add(start, i)))
 	}
 
 	// Now split
-	newRange, numGivenUp, ok := spaceset.Donate()
-	wt.AssertTrue(t, ok, "GiveUpSpace result")
-	wt.AssertEquals(t, newRange, ip("10.0.1.23"))
-	wt.AssertEquals(t, numGivenUp, address.Offset(24))
-	wt.AssertEquals(t, spaceset.NumFreeAddresses(), address.Offset(23))
+	newRange, ok := spaceset.Donate(address.NewRange(start, size))
+	require.True(t, ok, "GiveUpSpace result")
+	require.Equal(t, address.NewRange(ip("10.0.1.16"), 16), newRange, "Wrong space")
+	require.Equal(t, address.Count(31), 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"))
-	wt.AssertEquals(t, spaceset, expected)
+	//Space set should now have 3 spaces
+	expected := &Space{
+		ours: add(nil, ip("10.0.1.47"), ip("10.0.1.48")),
+		free: add(add(nil, ip("10.0.1.0"), ip("10.0.1.16")), ip("10.0.1.32"), ip("10.0.1.47")),
+	}
+	require.Equal(t, expected, spaceset)
 }

ipam/status.go

@@ -0,0 +1,103 @@
+package ipam
+
+import (
+	"fmt"
+	"github.com/weaveworks/weave/ipam/paxos"
+	"github.com/weaveworks/weave/net/address"
+)
+
+type Status struct {
+	Paxos            *paxos.Status
+	Range            string
+	RangeNumIPs      int
+	ActiveIPs        int
+	DefaultSubnet    string
+	Entries          []EntryStatus
+	PendingClaims    []ClaimStatus
+	PendingAllocates []string
+}
+
+type EntryStatus struct {
+	Token       string
+	Size        uint32
+	Peer        string
+	Nickname    string
+	IsKnownPeer bool
+	Version     uint32
+}
+
+type ClaimStatus struct {
+	Ident string
+	CIDR  address.CIDR
+}
+
+func NewStatus(allocator *Allocator, defaultSubnet address.CIDR) *Status {
+	if allocator == nil {
+		return nil
+	}
+
+	var paxosStatus *paxos.Status
+	if allocator.awaitingConsensus && allocator.paxos != nil {
+		if allocator.paxos.IsElector() {
+			if node, ok := allocator.paxos.(*paxos.Node); ok {
+				paxosStatus = paxos.NewStatus(node)
+			}
+		} else {
+			paxosStatus = &paxos.Status{Elector: false}
+		}
+	}
+
+	resultChan := make(chan *Status)
+	allocator.actionChan <- func() {
+		resultChan <- &Status{
+			paxosStatus,
+			allocator.universe.String(),
+			int(allocator.universe.Size()),
+			int(allocator.space.NumOwnedAddresses()),
+			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 _, r := range allocator.ring.AllRangeInfo() {
+		slice = append(slice, EntryStatus{
+			Token:       r.Start.String(),
+			Size:        uint32(r.Size()),
+			Peer:        r.Peer.String(),
+			Nickname:    allocator.nicknames[r.Peer],
+			IsKnownPeer: allocator.isKnownPeer(r.Peer),
+			Version:     r.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.cidr})
+	}
+	return slice
+}
+
+func newAllocateIdentSlice(allocator *Allocator) []string {
+	var slice []string
+	for _, op := range allocator.pendingAllocates {
+		allocate := op.(*allocate)
+		slice = append(slice, fmt.Sprintf("%s %s", allocate.ident, allocate.r.String()))
+	}
+	return slice
+}

ipam/testutils_test.go

@@ -3,16 +3,19 @@ package ipam
 import (
 	"fmt"
 	"math/rand"
+	"sync"
 	"testing"
 	"time"
 
-	"github.com/weaveworks/weave/common"
-	"github.com/weaveworks/weave/router"
-	wt "github.com/weaveworks/weave/testing"
+	"github.com/weaveworks/mesh"
+
+	"github.com/stretchr/testify/require"
+	"github.com/weaveworks/weave/net/address"
+	"github.com/weaveworks/weave/testing/gossip"
 )
 
 type mockMessage struct {
-	dst     router.PeerName
+	dst     mesh.PeerName
 	msgType byte
 	buf     []byte
 }
@@ -30,12 +33,15 @@ func toStringArray(messages []mockMessage) []string {
 }
 
 type mockGossipComms struct {
-	t        *testing.T
+	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)
 }
 
@@ -43,19 +49,20 @@ func (m *mockGossipComms) String() string {
 // 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 {
+func (m *mockGossipComms) GossipBroadcast(update mesh.GossipData) {
+	m.Lock()
+	defer m.Unlock()
 	buf := []byte{}
 	if len(m.messages) == 0 {
-		m.Fatalf("%s: Gossip broadcast message unexpected: \n%x", m.name, buf)
-	} else if msg := m.messages[0]; msg.dst != router.UnknownPeerName {
-		m.Fatalf("%s: Expected Gossip message to %s but got broadcast", m.name, msg.dst)
+		require.FailNow(m, fmt.Sprintf("%s: Gossip broadcast message unexpected: \n%x", m.name, buf))
+	} else if msg := m.messages[0]; msg.dst != mesh.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) {
-		m.Fatalf("%s: Gossip message not sent as expected: \nwant: %x\ngot : %x", m.name, 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 {
@@ -70,22 +77,19 @@ func equalByteBuffer(a, b []byte) bool {
 	return true
 }
 
-func (m *mockGossipComms) Fatalf(format string, args ...interface{}) {
-	// this sometimes hangs: wt.Fatalf(m.t, args...)
-	panic(fmt.Sprintf(format, args...))
-}
-
-func (m *mockGossipComms) GossipUnicast(dstPeerName router.PeerName, buf []byte) error {
+func (m *mockGossipComms) GossipUnicast(dstPeerName mesh.PeerName, buf []byte) error {
+	m.Lock()
+	defer m.Unlock()
 	if len(m.messages) == 0 {
-		m.Fatalf("%s: Gossip message to %s unexpected: \n%s", m.name, dstPeerName, buf)
-	} else if msg := m.messages[0]; msg.dst == router.UnknownPeerName {
-		m.Fatalf("%s: Expected Gossip broadcast message but got dest %s", m.name, dstPeerName)
+		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 == mesh.UnknownPeerName {
+		require.FailNow(m, fmt.Sprintf("%s: Expected Gossip broadcast message but got dest %s", m.name, dstPeerName))
 	} else if msg.dst != dstPeerName {
-		m.Fatalf("%s: Expected Gossip message to %s but got dest %s", m.name, 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 {
-		m.Fatalf("%s: Expected Gossip message of type %d but got type %d", m.name, msg.msgType, buf[0])
+		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:]) {
-		m.Fatalf("%s: Gossip message not sent as expected: \nwant: %x\ngot : %x", m.name, 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:]
@@ -95,49 +99,69 @@ func (m *mockGossipComms) GossipUnicast(dstPeerName router.PeerName, buf []byte)
 
 func ExpectMessage(alloc *Allocator, dst string, msgType byte, buf []byte) {
 	m := alloc.gossip.(*mockGossipComms)
-	dstPeerName, _ := router.PeerNameFromString(dst)
+	dstPeerName, _ := mesh.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.messages = append(m.messages, mockMessage{router.UnknownPeerName, 0, buf})
+	m.Lock()
+	m.messages = append(m.messages, mockMessage{mesh.UnknownPeerName, 0, buf})
+	m.Unlock()
 }
 
 func CheckAllExpectedMessagesSent(allocs ...*Allocator) {
 	for _, alloc := range allocs {
 		m := alloc.gossip.(*mockGossipComms)
+		m.RLock()
 		if len(m.messages) > 0 {
-			wt.Fatalf(m.t, "%s: Gossip message(s) not sent as expected: \n%x", m.name, m.messages)
+			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, cidr string, quorum uint) *Allocator {
-	peername, err := router.PeerNameFromString(name)
+type mockDB struct{}
+
+func (d *mockDB) Load(_ string, _ interface{}) (bool, error) { return false, nil }
+func (d *mockDB) Save(_ string, _ interface{}) error         { return nil }
+
+func makeAllocator(name string, cidrStr string, quorum uint, preClaims ...PreClaim) (*Allocator, address.CIDR) {
+	peername, err := mesh.PeerNameFromString(name)
 	if err != nil {
 		panic(err)
 	}
 
-	alloc, err := NewAllocator(peername, router.PeerUID(rand.Int63()),
-		"nick-"+name, cidr, quorum)
+	cidr, err := address.ParseCIDR(cidrStr)
 	if err != nil {
 		panic(err)
 	}
 
-	return alloc
+	return NewAllocator(Config{
+		OurName:     peername,
+		OurUID:      mesh.PeerUID(rand.Int63()),
+		OurNickname: "nick-" + name,
+		Universe:    cidr,
+		IsObserver:  quorum == 0,
+		PreClaims:   preClaims,
+		Quorum:      func() uint { return quorum },
+		Db:          new(mockDB),
+		IsKnownPeer: func(mesh.PeerName) bool { return true },
+	}), cidr
 }
 
-func makeAllocatorWithMockGossip(t *testing.T, name string, universeCIDR string, quorum uint) *Allocator {
-	alloc := makeAllocator(name, universeCIDR, quorum)
-	gossip := &mockGossipComms{t: t, name: name}
+func makeAllocatorWithMockGossip(t *testing.T, name string, universeCIDR string, quorum uint) (*Allocator, address.CIDR) {
+	alloc, subnet := makeAllocator(name, universeCIDR, quorum)
+	gossip := &mockGossipComms{T: t, name: name}
 	alloc.SetInterfaces(gossip)
 	alloc.Start()
-	return alloc
+	return alloc, subnet
 }
 
 func (alloc *Allocator) claimRingForTesting(allocs ...*Allocator) {
-	peers := []router.PeerName{alloc.ourName}
+	peers := []mesh.PeerName{alloc.ourName}
 	for _, alloc2 := range allocs {
 		peers = append(peers, alloc2.ourName)
 	}
@@ -145,6 +169,22 @@ func (alloc *Allocator) claimRingForTesting(allocs ...*Allocator) {
 	alloc.space.AddRanges(alloc.ring.OwnedRanges())
 }
 
+func (alloc *Allocator) NumFreeAddresses(r address.Range) address.Count {
+	resultChan := make(chan address.Count)
+	alloc.actionChan <- func() {
+		resultChan <- alloc.space.NumFreeAddressesInRange(r)
+	}
+	return <-resultChan
+}
+
+func (alloc *Allocator) OwnedRanges() (result []address.Range) {
+	resultChan := make(chan []address.Range)
+	alloc.actionChan <- func() {
+		resultChan <- alloc.ring.OwnedRanges()
+	}
+	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)
@@ -152,14 +192,14 @@ func AssertSent(t *testing.T, ch <-chan bool) {
 	case <-ch:
 		// This case is ok
 	case <-timeout:
-		wt.Fatalf(t, "Nothing sent on channel")
+		require.FailNow(t, "Nothing sent on channel")
 	}
 }
 
 func AssertNothingSent(t *testing.T, ch <-chan bool) {
 	select {
 	case val := <-ch:
-		wt.Fatalf(t, "Unexpected value on channel: %t", val)
+		require.FailNow(t, fmt.Sprintf("Unexpected value on channel: %v", val))
 	default:
 		// no message received
 	}
@@ -168,118 +208,39 @@ func AssertNothingSent(t *testing.T, ch <-chan bool) {
 func AssertNothingSentErr(t *testing.T, ch <-chan error) {
 	select {
 	case val := <-ch:
-		wt.Fatalf(t, "Unexpected value on channel: %t", val)
+		require.FailNow(t, fmt.Sprintf("Unexpected value on channel: %v", val))
 	default:
 		// no message received
 	}
 }
 
-// Router to convey gossip from one gossiper to another, for testing
-type gossipMessage struct {
-	isUnicast bool
-	sender    *router.PeerName
-	buf       []byte
-	exitChan  chan bool
-}
-
-type TestGossipRouter struct {
-	gossipChans map[router.PeerName]chan gossipMessage
-	loss        float32 // 0.0 means no loss
-}
-
-func (grouter *TestGossipRouter) GossipBroadcast(update router.GossipData) error {
-	for _, gossipChan := range grouter.gossipChans {
-		select {
-		case gossipChan <- gossipMessage{buf: update.(*ipamGossipData).alloc.encode()}:
-		default: // drop the message if we cannot send it
-		}
-	}
-	return nil
-}
-
-func (grouter *TestGossipRouter) removePeer(peer router.PeerName) {
-	gossipChan := grouter.gossipChans[peer]
-	resultChan := make(chan bool)
-	gossipChan <- gossipMessage{exitChan: resultChan}
-	<-resultChan
-	delete(grouter.gossipChans, peer)
-}
-
-type TestGossipRouterClient struct {
-	router *TestGossipRouter
-	sender router.PeerName
-}
-
-func (grouter *TestGossipRouter) connect(sender router.PeerName, gossiper router.Gossiper) router.Gossip {
-	gossipChan := make(chan gossipMessage, 100)
-
-	go func() {
-		gossipTimer := time.Tick(10 * time.Second)
-		for {
-			select {
-			case message := <-gossipChan:
-				if message.exitChan != nil {
-					message.exitChan <- true
-					return
-				}
-
-				if rand.Float32() > (1.0 - grouter.loss) {
-					continue
-				}
-
-				if message.isUnicast {
-					err := gossiper.OnGossipUnicast(*message.sender, message.buf)
-					if err != nil {
-						panic(fmt.Sprintf("Error doing gossip unicast to %s: %s", sender, err))
-					}
-				} else {
-					_, err := gossiper.OnGossipBroadcast(message.buf)
-					if err != nil {
-						panic(fmt.Sprintf("Error doing gossip broadcast to %s: %s", sender, err))
-					}
-				}
-			case <-gossipTimer:
-				grouter.GossipBroadcast(gossiper.Gossip())
-			}
-		}
-	}()
-
-	grouter.gossipChans[sender] = gossipChan
-	return TestGossipRouterClient{grouter, sender}
-}
-
-func (client TestGossipRouterClient) GossipUnicast(dstPeerName router.PeerName, buf []byte) error {
-	select {
-	case client.router.gossipChans[dstPeerName] <- gossipMessage{isUnicast: true, sender: &client.sender, buf: buf}:
-	default: // drop the message if we cannot send it
-		common.Error.Printf("Dropping message")
-	}
-	return nil
-}
-
-func (client TestGossipRouterClient) GossipBroadcast(update router.GossipData) error {
-	return client.router.GossipBroadcast(update)
-}
-
-func makeNetworkOfAllocators(size int, cidr string) ([]*Allocator, TestGossipRouter) {
-
-	gossipRouter := TestGossipRouter{make(map[router.PeerName]chan gossipMessage), 0.0}
+func makeNetworkOfAllocators(size int, cidr string, preClaims ...[]PreClaim) ([]*Allocator, *gossip.TestRouter, address.CIDR) {
+	gossipRouter := gossip.NewTestRouter(0.0)
 	allocs := make([]*Allocator, size)
+	var subnet address.CIDR
 
 	for i := 0; i < size; i++ {
-		alloc := makeAllocator(fmt.Sprintf("%02d:00:00:02:00:00", i),
-			cidr, uint(size/2+1))
-		alloc.SetInterfaces(gossipRouter.connect(alloc.ourName, alloc))
+		var alloc *Allocator
+		preClaim := []PreClaim{}
+		if i < len(preClaims) {
+			preClaim = preClaims[i]
+		}
+		alloc, subnet = makeAllocator(fmt.Sprintf("%02d:00:00:02:00:00", i),
+			cidr, uint(size/2+1), preClaim...)
+		alloc.SetInterfaces(gossipRouter.Connect(alloc.ourName, alloc))
 		alloc.Start()
 		allocs[i] = alloc
 	}
 
-	gossipRouter.GossipBroadcast(allocs[size-1].Gossip())
-	time.Sleep(1000 * time.Millisecond)
-	return allocs, gossipRouter
+	allocs[size-1].gossip.GossipBroadcast(allocs[size-1].Gossip())
+	gossipRouter.Flush()
+	return allocs, gossipRouter, subnet
 }
 
-func stopNetworkOfAllocators(allocs []*Allocator) {
+func stopNetworkOfAllocators(allocs []*Allocator, gossipRouter *gossip.TestRouter) {
+	// NB: We must stop the router first since ipam gossip makes
+	// synchronous calls into the allocator.
+	gossipRouter.Stop()
 	for _, alloc := range allocs {
 		alloc.Stop()
 	}

ipam/tracker/awsvpc.go

@@ -0,0 +1,285 @@
+package tracker
+
+// The AWSVPC tracker tracks the IPAM ring changes and accordingly updates
+// the AWS VPC route table and, if the announced change is local
+// (denoted by local=true) to the host, the host route table.
+//
+// During the initialization, the tracker detects AWS VPC route table id which
+// is associated with the host's subnet on the AWS network. If such a table does
+// not exist, the default VPC route table is used.
+//
+// When a host A donates a range to a host B, the necessary route table
+// updates (removal) happen on the host A first, and afterwards on
+// the host B (installation).
+//
+// NB: there is a hard limit for 50 routes within any VPC route table
+// (practically, it is 48, because one route is used by the AWS Internet GW and
+// one by the AWS host subnet), therefore it is suggested to avoid
+// an excessive fragmentation within the IPAM ring which might happen due to
+// the claim operations or uneven distribution of containers across the hosts.
+
+import (
+	"fmt"
+	"net"
+	"syscall"
+
+	"github.com/aws/aws-sdk-go/aws"
+	"github.com/aws/aws-sdk-go/aws/ec2metadata"
+	"github.com/aws/aws-sdk-go/aws/session"
+	"github.com/aws/aws-sdk-go/service/ec2"
+	"github.com/vishvananda/netlink"
+
+	"github.com/weaveworks/weave/common"
+	wnet "github.com/weaveworks/weave/net"
+	"github.com/weaveworks/weave/net/address"
+)
+
+type AWSVPCTracker struct {
+	ec2          *ec2.EC2
+	instanceID   string // EC2 Instance ID
+	routeTableID string // VPC Route Table ID
+	linkIndex    int    // The weave bridge link index
+}
+
+// NewAWSVPCTracker creates and initialises AWS VPC based tracker.
+func NewAWSVPCTracker() (*AWSVPCTracker, error) {
+	var (
+		err     error
+		session = session.New()
+		t       = &AWSVPCTracker{}
+	)
+
+	// Detect region and instance id
+	meta := ec2metadata.New(session)
+	t.instanceID, err = meta.GetMetadata("instance-id")
+	if err != nil {
+		return nil, fmt.Errorf("cannot detect instance-id: %s", err)
+	}
+	region, err := meta.Region()
+	if err != nil {
+		return nil, fmt.Errorf("cannot detect region: %s", err)
+	}
+
+	t.ec2 = ec2.New(session, aws.NewConfig().WithRegion(region))
+
+	routeTableID, err := t.detectRouteTableID()
+	if err != nil {
+		return nil, err
+	}
+	t.routeTableID = *routeTableID
+
+	// Detect Weave bridge link index
+	link, err := netlink.LinkByName(wnet.WeaveBridgeName)
+	if err != nil {
+		return nil, fmt.Errorf("cannot find \"%s\" interface: %s", wnet.WeaveBridgeName, err)
+	}
+	t.linkIndex = link.Attrs().Index
+
+	t.infof("AWSVPC has been initialized on %s instance for %s route table at %s region",
+		t.instanceID, t.routeTableID, region)
+
+	return t, nil
+}
+
+// HandleUpdate method updates the AWS VPC and the host route tables.
+func (t *AWSVPCTracker) HandleUpdate(prevRanges, currRanges []address.Range, local bool) error {
+	t.debugf("replacing %q by %q; local(%t)", prevRanges, currRanges, local)
+
+	prev, curr := removeCommon(address.NewCIDRs(merge(prevRanges)), address.NewCIDRs(merge(currRanges)))
+
+	// It might make sense to do the removal first and then add entries
+	// because of the 50 routes limit. However, in such case a container might
+	// not be reachable for a short period of time which is not a desired behavior.
+
+	// Add new entries
+	for _, cidr := range curr {
+		cidrStr := cidr.String()
+		t.debugf("adding route %s to %s", cidrStr, t.instanceID)
+		if _, err := t.createVPCRoute(cidrStr); err != nil {
+			return fmt.Errorf("createVPCRoutes failed: %s", err)
+		}
+		if local {
+			if err := t.createHostRoute(cidrStr); err != nil {
+				if errno, ok := err.(syscall.Errno); !(ok && errno == syscall.EEXIST) {
+					return fmt.Errorf("createHostRoute failed: %s", err)
+				}
+			}
+		}
+	}
+
+	// Remove obsolete entries
+	for _, cidr := range prev {
+		cidrStr := cidr.String()
+		t.debugf("removing %s route", cidrStr)
+		if _, err := t.deleteVPCRoute(cidrStr); err != nil {
+			return fmt.Errorf("deleteVPCRoute failed: %s", err)
+		}
+		if local {
+			if err := t.deleteHostRoute(cidrStr); err != nil {
+				return fmt.Errorf("deleteHostRoute failed: %s", err)
+			}
+		}
+	}
+
+	return nil
+}
+
+func (t *AWSVPCTracker) createVPCRoute(cidr string) (*ec2.CreateRouteOutput, error) {
+	route := &ec2.CreateRouteInput{
+		RouteTableId:         &t.routeTableID,
+		InstanceId:           &t.instanceID,
+		DestinationCidrBlock: &cidr,
+	}
+	return t.ec2.CreateRoute(route)
+}
+
+func (t *AWSVPCTracker) createHostRoute(cidr string) error {
+	dst, err := parseCIDR(cidr)
+	if err != nil {
+		return err
+	}
+	route := &netlink.Route{
+		LinkIndex: t.linkIndex,
+		Dst:       dst,
+		Scope:     netlink.SCOPE_LINK,
+	}
+	return netlink.RouteAdd(route)
+}
+
+func (t *AWSVPCTracker) deleteVPCRoute(cidr string) (*ec2.DeleteRouteOutput, error) {
+	route := &ec2.DeleteRouteInput{
+		RouteTableId:         &t.routeTableID,
+		DestinationCidrBlock: &cidr,
+	}
+	return t.ec2.DeleteRoute(route)
+}
+
+func (t *AWSVPCTracker) deleteHostRoute(cidr string) error {
+	dst, err := parseCIDR(cidr)
+	if err != nil {
+		return err
+	}
+	route := &netlink.Route{
+		LinkIndex: t.linkIndex,
+		Dst:       dst,
+		Scope:     netlink.SCOPE_LINK,
+	}
+	return netlink.RouteDel(route)
+}
+
+// detectRouteTableID detects AWS VPC Route Table ID of the given tracker instance.
+func (t *AWSVPCTracker) detectRouteTableID() (*string, error) {
+	instancesParams := &ec2.DescribeInstancesInput{
+		InstanceIds: []*string{aws.String(t.instanceID)},
+	}
+	instancesResp, err := t.ec2.DescribeInstances(instancesParams)
+	if err != nil {
+		return nil, fmt.Errorf("DescribeInstances failed: %s", err)
+	}
+	if len(instancesResp.Reservations) == 0 ||
+		len(instancesResp.Reservations[0].Instances) == 0 {
+		return nil, fmt.Errorf("cannot find %s instance within reservations", t.instanceID)
+	}
+	vpcID := instancesResp.Reservations[0].Instances[0].VpcId
+	subnetID := instancesResp.Reservations[0].Instances[0].SubnetId
+
+	// First try to find a routing table associated with the subnet of the instance
+	tablesParams := &ec2.DescribeRouteTablesInput{
+		Filters: []*ec2.Filter{
+			{
+				Name:   aws.String("association.subnet-id"),
+				Values: []*string{subnetID},
+			},
+		},
+	}
+	tablesResp, err := t.ec2.DescribeRouteTables(tablesParams)
+	if err != nil {
+		return nil, fmt.Errorf("DescribeRouteTables failed: %s", err)
+	}
+	if len(tablesResp.RouteTables) != 0 {
+		return tablesResp.RouteTables[0].RouteTableId, nil
+	}
+	// Fallback to the default routing table
+	tablesParams = &ec2.DescribeRouteTablesInput{
+		Filters: []*ec2.Filter{
+			{
+				Name:   aws.String("association.main"),
+				Values: []*string{aws.String("true")},
+			},
+			{
+				Name:   aws.String("vpc-id"),
+				Values: []*string{vpcID},
+			},
+		},
+	}
+	tablesResp, err = t.ec2.DescribeRouteTables(tablesParams)
+	if err != nil {
+		return nil, fmt.Errorf("DescribeRouteTables failed: %s", err)
+	}
+	if len(tablesResp.RouteTables) != 0 {
+		return tablesResp.RouteTables[0].RouteTableId, nil
+	}
+
+	return nil, fmt.Errorf("cannot find routetable for %s instance", t.instanceID)
+}
+
+func (t *AWSVPCTracker) debugf(fmt string, args ...interface{}) {
+	common.Log.Debugf("[tracker] "+fmt, args...)
+}
+
+func (t *AWSVPCTracker) infof(fmt string, args ...interface{}) {
+	common.Log.Infof("[tracker] "+fmt, args...)
+}
+
+// Helpers
+
+// merge merges adjacent range entries.
+// The given slice has to be sorted in increasing order.
+func merge(r []address.Range) []address.Range {
+	var merged []address.Range
+
+	for i := range r {
+		if prev := len(merged) - 1; prev >= 0 && merged[prev].End == r[i].Start {
+			merged[prev].End = r[i].End
+		} else {
+			merged = append(merged, r[i])
+		}
+	}
+
+	return merged
+}
+
+// removeCommon filters out CIDR ranges which are contained in both a and b slices.
+// Both slices have to be sorted in increasing order.
+func removeCommon(a, b []address.CIDR) (newA, newB []address.CIDR) {
+	i, j := 0, 0
+
+	for i < len(a) && j < len(b) {
+		switch {
+		case a[i].Start() < b[j].Start() || a[i].End() < b[j].End():
+			newA = append(newA, a[i])
+			i++
+		case a[i].Start() > b[j].Start() || a[i].End() > b[j].End():
+			newB = append(newB, b[j])
+			j++
+		default:
+			i++
+			j++
+		}
+
+	}
+	newA = append(newA, a[i:]...)
+	newB = append(newB, b[j:]...)
+
+	return
+}
+
+func parseCIDR(cidr string) (*net.IPNet, error) {
+	ip, ipnet, err := net.ParseCIDR(cidr)
+	if err != nil {
+		return nil, err
+	}
+	ipnet.IP = ip
+
+	return ipnet, nil
+}

ipam/tracker/awsvpc_test.go

@@ -0,0 +1,52 @@
+package tracker
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/require"
+
+	"github.com/weaveworks/weave/net/address"
+)
+
+var (
+	r0to127     = cidr("10.0.0.0", "10.0.0.127")
+	r128to255   = cidr("10.0.0.128", "10.0.0.255")
+	r0to255     = cidr("10.0.0.0", "10.0.0.255")
+	r1dot0to255 = cidr("10.0.1.0", "10.0.1.255")
+	r2dot0to255 = cidr("10.0.2.0", "10.0.2.255")
+)
+
+func TestRemoveCommon(t *testing.T) {
+	a := []address.CIDR{r0to127, r1dot0to255}
+	b := []address.CIDR{r1dot0to255, r2dot0to255}
+	newA, newB := removeCommon(a, b)
+	require.Equal(t, []address.CIDR{r0to127}, newA)
+	require.Equal(t, []address.CIDR{r2dot0to255}, newB)
+}
+
+func TestMerge(t *testing.T) {
+	ranges := []address.Range{
+		r0to127.Range(),
+		r128to255.Range(),
+		r2dot0to255.Range(),
+	}
+	require.Equal(t, []address.Range{r0to255.Range(), r2dot0to255.Range()}, merge(ranges))
+}
+
+// Helper
+
+// TODO(mp) DRY with helpers of other tests.
+
+func ip(s string) address.Address {
+	addr, _ := address.ParseIP(s)
+	return addr
+}
+
+// [start; end]
+func cidr(start, end string) address.CIDR {
+	c := address.Range{Start: ip(start), End: ip(end) + 1}.CIDRs()
+	if len(c) != 1 {
+		panic("invalid cidr")
+	}
+	return c[0]
+}

ipam/tracker/tracker.go

@@ -0,0 +1,20 @@
+package tracker
+
+import (
+	"github.com/weaveworks/weave/net/address"
+)
+
+// LocalRangeTracker is an interface for tracking changes in the IPAM ring.
+type LocalRangeTracker interface {
+	// HandleUpdate is called whenever an address ring gets updated.
+	//
+	// prevRanges corresponds to ranges which were owned by a peer before
+	// a change in the ring, while currRanges to the ones which are currently
+	// owned by the peer.
+	// Both slices have to be sorted in increasing order.
+	// Adjacent ranges within each slice might appear as separate ranges.
+	//
+	// The local parameter indicates whether the ranges belong to the peer
+	// by which the method is called.
+	HandleUpdate(prevRanges, currRanges []address.Range, local bool) error
+}

nameserver/addrs.go

@@ -1,125 +0,0 @@
-package nameserver
-
-import (
-	"bytes"
-	"fmt"
-	"net"
-)
-
-// A zone record
-// Note: we will try to keep all the zone records information is concentrated here. Maybe not all queries will
-//       use things like priorities or weights, but we do not want to create a hierarchy for dealing with all
-//       possible queries...
-type ZoneRecord interface {
-	Name() string  // The name for this IP
-	IP() net.IP    // The IP (v4) address
-	Priority() int // The priority
-	Weight() int   // The weight
-	TTL() int      // TTL
-}
-
-type ZoneLookup interface {
-	// Lookup for a name
-	LookupName(name string) ([]ZoneRecord, error)
-	// Lookup for an address
-	LookupInaddr(inaddr string) ([]ZoneRecord, error)
-}
-
-type ZoneObserver interface {
-	// Observe anything that affects a particular name in the zone
-	ObserveName(name string, observer ZoneRecordObserver) error
-	// Observe anything that affects a particular IP in the zone
-	ObserveInaddr(inaddr string, observer ZoneRecordObserver) error
-}
-
-type ZoneRecordObserver func()
-
-/////////////////////////////////////////////////////////////
-
-// A basic record struct (satisfying the ZoneRecord interface)
-type Record struct {
-	name     string
-	ip       net.IP
-	priority int
-	weight   int
-	ttl      int
-}
-
-func (r Record) Name() string  { return r.name }
-func (r Record) IP() net.IP    { return r.ip }
-func (r Record) Priority() int { return r.priority }
-func (r Record) Weight() int   { return r.weight }
-func (r Record) TTL() int      { return r.ttl }
-
-func (r Record) String() string {
-	var buf bytes.Buffer
-	if len(r.Name()) > 0 {
-		fmt.Fprintf(&buf, "%s", r.Name())
-	}
-	if !r.IP().IsUnspecified() {
-		fmt.Fprintf(&buf, "[%s]", r.IP())
-	}
-	if r.Priority() > 0 {
-		fmt.Fprintf(&buf, "/P:%d", r.Priority())
-	}
-	if r.Weight() > 0 {
-		fmt.Fprintf(&buf, "/W:%d", r.Weight())
-	}
-	if r.TTL() > 0 {
-		fmt.Fprintf(&buf, "/TTL:%d", r.TTL())
-	}
-
-	return buf.String()
-}
-
-/////////////////////////////////////////////////////////////
-
-func newParseError(reason string, addr string) *net.ParseError {
-	return &net.ParseError{Type: reason, Text: addr}
-}
-
-// simple IPv4 type that can be used as a key in a map (in contrast with net.IP), used for sets of IPs, etc...
-type IPv4 [4]byte
-
-func (ip IPv4) toNetIP() net.IP { return net.IPv4(ip[0], ip[1], ip[2], ip[3]) }
-func (ip IPv4) String() string  { return ip.toNetIP().String() }
-func ipToIPv4(nip net.IP) IPv4  { ip := nip.To4(); return IPv4([4]byte{ip[0], ip[1], ip[2], ip[3]}) }
-
-// Parse an address (eg, "10.13.12.11") and return the corresponding IPv4 (eg, "10.13.12.11")
-func addrToIPv4(addr string) (IPv4, error) {
-	ip := net.ParseIP(addr)
-	if ip == nil {
-		return IPv4{}, newParseError("IP address", addr)
-	}
-	return ipToIPv4(ip), nil
-}
-
-// Parse a reverse address (eg, "11.12.13.10.in-addr.arpa.") and return the corresponding IPv4 (eg, "10.13.12.11")
-func raddrToIPv4(addr string) (IPv4, error) {
-	l := len(addr)
-	if l < rdnsDomainLen+1 {
-		return IPv4{}, newParseError("too short reverse IP address", addr)
-	}
-
-	suffixLen := l - rdnsDomainLen
-	suffix := addr[suffixLen+1:]
-	if suffix != RDNSDomain {
-		return IPv4{}, newParseError("suffix of reverse IP address", addr)
-	}
-	ipStr := addr[:suffixLen]
-	revIP := net.ParseIP(ipStr)
-	if revIP == nil {
-		return IPv4{}, newParseError("reverse IP address", addr)
-	}
-
-	revIP4 := revIP.To4()
-	return IPv4([4]byte{revIP4[3], revIP4[2], revIP4[1], revIP4[0]}), nil
-}
-
-func raddrToIP(addr string) (net.IP, error) {
-	r, err := raddrToIPv4(addr)
-	if err != nil {
-		return net.IP{}, err
-	}
-	return r.toNetIP(), nil
-}

nameserver/addrs_test.go

@@ -1,31 +0,0 @@
-package nameserver
-
-import (
-	. "github.com/weaveworks/weave/common"
-	wt "github.com/weaveworks/weave/testing"
-	"net"
-	"testing"
-)
-
-func TestAddrs(t *testing.T) {
-	InitDefaultLogging(testing.Verbose())
-	Info.Println("TestAddrs starting")
-
-	ip, err := addrToIPv4("10.13.12.11")
-	wt.AssertNoErr(t, err)
-	wt.AssertTrue(t, net.ParseIP("10.13.12.11").Equal(ip.toNetIP()), "IP")
-
-	ip, err = raddrToIPv4("11.12.13.10.in-addr.arpa.")
-	wt.AssertNoErr(t, err)
-	wt.AssertTrue(t, net.ParseIP("10.13.12.11").Equal(ip.toNetIP()), "IP")
-
-	// some malformed addresses
-	ip, err = addrToIPv4("10.13.12")
-	wt.AssertTrue(t, err != nil, "when parsing malformed address")
-	ip, err = addrToIPv4("10.13.AA.12")
-	wt.AssertTrue(t, err != nil, "when parsing malformed address")
-	ip, err = raddrToIPv4("11.12.13.10.in-axxx.arpa.")
-	wt.AssertTrue(t, err != nil, "when parsing malformed address")
-	ip, err = raddrToIPv4("11.12.13.10.in-addr")
-	wt.AssertTrue(t, err != nil, "when parsing malformed address")
-}

nameserver/cache.go

@@ -1,401 +0,0 @@
-package nameserver
-
-import (
-	"bytes"
-	"container/heap"
-	"errors"
-	"fmt"
-	"math"
-	"math/rand"
-	"sync"
-	"time"
-
-	"github.com/benbjohnson/clock"
-	"github.com/miekg/dns"
-	. "github.com/weaveworks/weave/common"
-)
-
-var (
-	errInvalidCapacity = errors.New("Invalid cache capacity")
-	errCouldNotResolve = errors.New("Could not resolve")
-	errTimeout         = errors.New("Timeout while waiting for resolution")
-	errNoLocalReplies  = errors.New("No local replies")
-)
-
-const (
-	defPendingTimeout int = 5 // timeout for a resolution
-)
-
-const nullTTL = 0 // a null TTL
-
-type entryStatus uint8
-
-const (
-	stPending  entryStatus = iota // someone is waiting for the resolution
-	stResolved entryStatus = iota // resolved
-)
-
-var statusToString = map[entryStatus]string{
-	stPending:  "pending",
-	stResolved: "resolved",
-}
-
-const (
-	CacheNoLocalReplies uint8 = 1 << iota // not found in local network (stored in the cache so we skip another local lookup or some time)
-)
-
-// shuffleAnswers reorders answers for very basic load balancing
-func shuffleAnswers(answers []dns.RR) []dns.RR {
-	n := len(answers)
-	if n > 1 {
-		rand.Seed(time.Now().UTC().UnixNano())
-
-		for i := 0; i < n; i++ {
-			r := i + rand.Intn(n-i)
-			answers[r], answers[i] = answers[i], answers[r]
-		}
-	}
-
-	return answers
-}
-
-// a cache entry
-type cacheEntry struct {
-	Status   entryStatus // status of the entry
-	Flags    uint8       // some extra flags
-	ReplyLen int
-
-	question dns.Question
-	protocol dnsProtocol
-	reply    dns.Msg
-
-	validUntil time.Time // obtained from the reply and stored here for convenience/speed
-	putTime    time.Time
-
-	index int // for fast lookups in the heap
-}
-
-func newCacheEntry(question *dns.Question, now time.Time) *cacheEntry {
-	e := &cacheEntry{
-		Status:     stPending,
-		validUntil: now.Add(time.Second * time.Duration(defPendingTimeout)),
-		question:   *question,
-		index:      -1,
-	}
-
-	return e
-}
-
-// Get a copy of the reply stored in the entry, but with some values adjusted like the TTL
-func (e *cacheEntry) getReply(request *dns.Msg, maxLen int, now time.Time) (*dns.Msg, error) {
-	if e.Status != stResolved {
-		return nil, nil
-	}
-
-	// if the reply has expired or is invalid, force the caller to start a new resolution
-	if e.hasExpired(now) {
-		return nil, nil
-	}
-
-	if e.Flags&CacheNoLocalReplies != 0 {
-		return nil, errNoLocalReplies
-	}
-
-	if e.ReplyLen >= maxLen {
-		Debug.Printf("[cache msgid %d] returning truncated reponse: %d > %d", request.MsgHdr.Id, e.ReplyLen, maxLen)
-		return makeTruncatedReply(request), nil
-	}
-
-	// create a copy of the reply, with values for this particular query
-	reply := e.reply.Copy()
-	reply.SetReply(request)
-
-	// adjust the TTLs
-	passedSecs := uint32(now.Sub(e.putTime).Seconds())
-	for _, rr := range reply.Answer {
-		hdr := rr.Header()
-		ttl := hdr.Ttl
-		if passedSecs < ttl {
-			hdr.Ttl = ttl - passedSecs
-		} else {
-			return nil, nil // it is expired: do not spend more time and return nil...
-		}
-	}
-
-	reply.Rcode = e.reply.Rcode
-	reply.Authoritative = true
-
-	// shuffle the values, etc...
-	reply.Answer = shuffleAnswers(reply.Answer)
-
-	return reply, nil
-}
-
-func (e cacheEntry) hasExpired(now time.Time) bool {
-	return e.validUntil.Before(now) || e.validUntil == now
-}
-
-// set the reply for the entry
-// returns True if the entry has changed the validUntil time
-func (e *cacheEntry) setReply(reply *dns.Msg, ttl int, flags uint8, now time.Time) bool {
-	var prevValidUntil time.Time
-	if e.Status == stResolved {
-		if reply != nil {
-			Debug.Printf("[cache msgid %d] replacing response in cache", reply.MsgHdr.Id)
-		}
-		prevValidUntil = e.validUntil
-	}
-
-	// make sure we do not overwrite noLocalReplies entries
-	if flags&CacheNoLocalReplies != 0 {
-		if e.Flags&CacheNoLocalReplies != 0 {
-			return false
-		}
-	}
-
-	if ttl != nullTTL {
-		e.validUntil = now.Add(time.Second * time.Duration(ttl))
-	} else if reply != nil {
-		// calculate the validUntil from the reply TTL
-		var minTTL uint32 = math.MaxUint32
-		for _, rr := range reply.Answer {
-			ttl := rr.Header().Ttl
-			if ttl < minTTL {
-				minTTL = ttl // TODO: improve the minTTL calculation (maybe we should skip some RRs)
-			}
-		}
-		e.validUntil = now.Add(time.Second * time.Duration(minTTL))
-	} else {
-		Warning.Printf("[cache] no valid TTL could be calculated")
-	}
-
-	e.Status = stResolved
-	e.Flags = flags
-	e.putTime = now
-
-	if reply != nil {
-		e.reply = *reply
-		e.ReplyLen = reply.Len()
-	}
-
-	return (prevValidUntil != e.validUntil)
-}
-
-func (e *cacheEntry) String() string {
-	var buf bytes.Buffer
-	q := e.question
-	fmt.Fprintf(&buf, "'%s'[%s]: ", q.Name, dns.TypeToString[q.Qtype])
-	if e.Flags&CacheNoLocalReplies != 0 {
-		fmt.Fprintf(&buf, "neg-local")
-	} else {
-		fmt.Fprintf(&buf, "%s", statusToString[e.Status])
-	}
-	fmt.Fprintf(&buf, "(%d bytes)", e.ReplyLen)
-	return buf.String()
-}
-
-//////////////////////////////////////////////////////////////////////////////////////
-
-// An entriesPtrHeap is a min-heap of cache entries.
-type entriesPtrsHeap []*cacheEntry
-
-func (h entriesPtrsHeap) Len() int           { return len(h) }
-func (h entriesPtrsHeap) Less(i, j int) bool { return h[i].validUntil.Before(h[j].validUntil) }
-func (h entriesPtrsHeap) Swap(i, j int) {
-	h[i], h[j] = h[j], h[i]
-	h[i].index = i
-	h[j].index = j
-}
-
-func (h *entriesPtrsHeap) Push(x interface{}) {
-	// Push and Pop use pointer receivers because they modify the slice's length,
-	// not just its contents.
-	n := len(*h)
-	entry := x.(*cacheEntry)
-	entry.index = n
-	*h = append(*h, entry)
-}
-
-func (h *entriesPtrsHeap) Pop() interface{} {
-	old := *h
-	n := len(old)
-	item := old[n-1]
-	item.index = -1 // for safety
-	*h = old[0 : n-1]
-	return item
-}
-
-//////////////////////////////////////////////////////////////////////////////////////
-
-// The cache interface
-type ZoneCache interface {
-	// Get from the cache
-	Get(request *dns.Msg, maxLen int) (reply *dns.Msg, err error)
-	// Put in the cache
-	Put(request *dns.Msg, reply *dns.Msg, ttl int, flags uint8) int
-	// Remove from the cache
-	Remove(question *dns.Question)
-	// Purge all expired entries from the cache
-	Purge()
-	// Remove all entries
-	Clear()
-	// Return the cache length
-	Len() int
-	// Return the max capacity
-	Capacity() int
-}
-
-type cacheKey dns.Question
-type entries map[cacheKey]*cacheEntry
-
-// Cache is a thread-safe fixed capacity LRU cache.
-type Cache struct {
-	capacity int
-	entries  entries
-	entriesH entriesPtrsHeap // len(entriesH) <= len(entries), as pending entries can be in entries but not in entriesH
-	clock    clock.Clock
-	lock     sync.RWMutex
-}
-
-// NewCache creates a cache of the given capacity
-func NewCache(capacity int, clk clock.Clock) (*Cache, error) {
-	if capacity <= 0 {
-		return nil, errInvalidCapacity
-	}
-	c := &Cache{
-		capacity: capacity,
-		entries:  make(entries, capacity),
-		clock:    clk,
-	}
-
-	if c.clock == nil {
-		c.clock = clock.New()
-	}
-
-	heap.Init(&c.entriesH)
-	return c, nil
-}
-
-// Clear removes all the entries in the cache
-func (c *Cache) Clear() {
-	c.lock.Lock()
-	defer c.lock.Unlock()
-
-	c.entries = make(entries, c.capacity)
-	heap.Init(&c.entriesH)
-}
-
-// Purge removes the old elements in the cache
-func (c *Cache) Purge() {
-	c.lock.Lock()
-	defer c.lock.Unlock()
-
-	now := c.clock.Now()
-	for i, entry := range c.entriesH {
-		if entry.hasExpired(now) {
-			heap.Remove(&c.entriesH, i)
-			delete(c.entries, cacheKey(entry.question))
-		} else {
-			return // all remaining entries must be still valid...
-		}
-	}
-}
-
-// Add adds a reply to the cache.
-// When `ttl` is equal to `nullTTL`, the cache entry will be valid until the closest TTL in the `reply`
-func (c *Cache) Put(request *dns.Msg, reply *dns.Msg, ttl int, flags uint8) int {
-	c.lock.Lock()
-	defer c.lock.Unlock()
-
-	now := c.clock.Now()
-	question := request.Question[0]
-	key := cacheKey(question)
-	ent, found := c.entries[key]
-	if found {
-		updated := ent.setReply(reply, ttl, flags, now)
-		if updated {
-			heap.Fix(&c.entriesH, ent.index)
-		}
-	} else {
-		// If we will add a new item and the capacity has been exceeded, make some room...
-		if len(c.entriesH) >= c.capacity {
-			lowestEntry := heap.Pop(&c.entriesH).(*cacheEntry)
-			delete(c.entries, cacheKey(lowestEntry.question))
-		}
-		ent = newCacheEntry(&question, now)
-		ent.setReply(reply, ttl, flags, now)
-		heap.Push(&c.entriesH, ent)
-		c.entries[key] = ent
-	}
-	return ent.ReplyLen
-}
-
-// Look up for a question's reply from the cache.
-// If no reply is stored in the cache, it returns a `nil` reply and no error.
-func (c *Cache) Get(request *dns.Msg, maxLen int) (reply *dns.Msg, err error) {
-	c.lock.Lock()
-	defer c.lock.Unlock()
-
-	now := c.clock.Now()
-	question := request.Question[0]
-	key := cacheKey(question)
-	if ent, found := c.entries[key]; found {
-		reply, err = ent.getReply(request, maxLen, now)
-		if ent.hasExpired(now) {
-			Debug.Printf("[cache msgid %d] expired: removing", request.MsgHdr.Id)
-			if ent.index > 0 {
-				heap.Remove(&c.entriesH, ent.index)
-			}
-			delete(c.entries, key)
-			reply = nil
-		}
-	} else {
-		// we are the first asking for this name: create an entry with no reply... the caller must wait
-		Debug.Printf("[cache msgid %d] addind in pending state", request.MsgHdr.Id)
-		c.entries[key] = newCacheEntry(&question, now)
-	}
-	return
-}
-
-// Remove removes the provided question from the cache.
-func (c *Cache) Remove(question *dns.Question) {
-	c.lock.Lock()
-	defer c.lock.Unlock()
-
-	key := cacheKey(*question)
-	if entry, found := c.entries[key]; found {
-		Debug.Printf("[cache] removing %s-response for '%s'", dns.TypeToString[question.Qtype], question.Name)
-		if entry.index > 0 {
-			heap.Remove(&c.entriesH, entry.index)
-		}
-		delete(c.entries, key)
-	}
-}
-
-// Len returns the number of entries in the cache.
-func (c *Cache) Len() int {
-	c.lock.RLock()
-	defer c.lock.RUnlock()
-
-	return len(c.entries)
-}
-
-// Return the max capacity
-func (c *Cache) Capacity() int {
-	c.lock.RLock()
-	defer c.lock.RUnlock()
-
-	return c.capacity
-}
-
-// Return the max capacity
-func (c *Cache) String() string {
-	c.lock.RLock()
-	defer c.lock.RUnlock()
-
-	var buf bytes.Buffer
-	for _, entry := range c.entries {
-		fmt.Fprintf(&buf, "%s\n", entry)
-	}
-	return buf.String()
-}

nameserver/cache_test.go

@@ -1,228 +0,0 @@
-package nameserver
-
-import (
-	"fmt"
-	"net"
-	"testing"
-	"time"
-
-	"github.com/benbjohnson/clock"
-	"github.com/miekg/dns"
-	. "github.com/weaveworks/weave/common"
-	wt "github.com/weaveworks/weave/testing"
-)
-
-// Check that the cache keeps its intended capacity constant
-func TestCacheLength(t *testing.T) {
-	InitDefaultLogging(testing.Verbose())
-	Info.Println("TestCacheLength starting")
-
-	const cacheLen = 128
-
-	l, err := NewCache(cacheLen, nil)
-	wt.AssertNoErr(t, err)
-
-	insTime := time.Now()
-
-	t.Logf("Inserting 256 questions in the cache at '%s', with TTL from 0 to 255", insTime)
-	for i := 0; i < cacheLen*2; i++ {
-		name := fmt.Sprintf("name%d", i)
-		questionMsg := new(dns.Msg)
-		questionMsg.SetQuestion(name, dns.TypeA)
-		questionMsg.RecursionDesired = true
-
-		question := &questionMsg.Question[0]
-
-		ip := net.ParseIP(fmt.Sprintf("10.0.1.%d", i))
-		records := []ZoneRecord{Record{name, ip, 0, 0, 0}}
-
-		reply := makeAddressReply(questionMsg, question, records)
-		reply.Answer[0].Header().Ttl = uint32(i)
-
-		l.Put(questionMsg, reply, 0, 0)
-	}
-
-	wt.AssertEqualInt(t, l.Len(), cacheLen, "cache length")
-
-	minExpectedTime := insTime.Add(time.Duration(cacheLen) * time.Second)
-	t.Logf("Checking all remaining entries expire after insert_time + %d secs='%s'", cacheLen, minExpectedTime)
-	for _, entry := range l.entries {
-		if entry.validUntil.Before(minExpectedTime) {
-			t.Fatalf("Entry valid until %s", entry.validUntil)
-		}
-	}
-}
-
-// Check that the cache entries are ok
-func TestCacheEntries(t *testing.T) {
-	InitDefaultLogging(testing.Verbose())
-	Info.Println("TestCacheEntries starting")
-
-	Info.Println("Checking cache consistency")
-
-	const cacheLen = 128
-	clk := clock.NewMock()
-
-	l, err := NewCache(cacheLen, clk)
-	wt.AssertNoErr(t, err)
-
-	questionMsg := new(dns.Msg)
-	questionMsg.SetQuestion("some.name", dns.TypeA)
-	questionMsg.RecursionDesired = true
-
-	question := &questionMsg.Question[0]
-
-	t.Logf("Trying to get a name")
-	resp, err := l.Get(questionMsg, minUDPSize)
-	wt.AssertNoErr(t, err)
-	if resp != nil {
-		t.Logf("Got\n%s", resp)
-		t.Fatalf("ERROR: Did not expect a reponse from Get() yet")
-	}
-	t.Logf("Trying to get it again")
-	resp, err = l.Get(questionMsg, minUDPSize)
-	wt.AssertNoErr(t, err)
-	if resp != nil {
-		t.Logf("Got\n%s", resp)
-		t.Fatalf("ERROR: Did not expect a reponse from Get() yet")
-	}
-
-	t.Logf("Inserting the reply")
-	records := []ZoneRecord{Record{"some.name", net.ParseIP("10.0.1.1"), 0, 0, 0}}
-	reply1 := makeAddressReply(questionMsg, question, records)
-	l.Put(questionMsg, reply1, nullTTL, 0)
-
-	t.Logf("Checking we can Get() the reply now")
-	resp, err = l.Get(questionMsg, minUDPSize)
-	wt.AssertNoErr(t, err)
-	wt.AssertTrue(t, resp != nil, "reponse from Get()")
-	t.Logf("Received '%s'", resp.Answer[0])
-	wt.AssertType(t, resp.Answer[0], (*dns.A)(nil), "DNS record")
-	ttlGet1 := resp.Answer[0].Header().Ttl
-
-	clk.Add(time.Duration(1) * time.Second)
-	t.Logf("Checking that a second Get(), after 1 second, gets the same result, but with reduced TTL")
-	resp, err = l.Get(questionMsg, minUDPSize)
-	wt.AssertNoErr(t, err)
-	wt.AssertTrue(t, resp != nil, "reponse from a second Get()")
-	t.Logf("Received '%s'", resp.Answer[0])
-	wt.AssertType(t, resp.Answer[0], (*dns.A)(nil), "DNS record")
-	ttlGet2 := resp.Answer[0].Header().Ttl
-	wt.AssertEqualInt(t, int(ttlGet1-ttlGet2), 1, "TTL difference")
-
-	clk.Add(time.Duration(localTTL) * time.Second)
-	t.Logf("Checking that a third Get(), after %d second, gets no result", localTTL)
-	resp, err = l.Get(questionMsg, minUDPSize)
-	wt.AssertNoErr(t, err)
-	if resp != nil {
-		t.Logf("Got\n%s", resp)
-		t.Fatalf("ERROR: Did NOT expect a reponse from the second Get()")
-	}
-
-	t.Logf("Checking that an Remove() results in Get() returning nothing")
-	records = []ZoneRecord{Record{"some.name", net.ParseIP("10.0.9.9"), 0, 0, 0}}
-	replyTemp := makeAddressReply(questionMsg, question, records)
-	l.Put(questionMsg, replyTemp, nullTTL, 0)
-	lenBefore := l.Len()
-	l.Remove(question)
-	wt.AssertEqualInt(t, l.Len(), lenBefore-1, "cache length")
-	l.Remove(question) // do it again: should have no effect...
-	wt.AssertEqualInt(t, l.Len(), lenBefore-1, "cache length")
-
-	resp, err = l.Get(questionMsg, minUDPSize)
-	wt.AssertNoErr(t, err)
-	wt.AssertTrue(t, resp == nil, "reponse from the Get() after a Remove()")
-
-	t.Logf("Inserting a two replies for the same query")
-	records = []ZoneRecord{Record{"some.name", net.ParseIP("10.0.1.2"), 0, 0, 0}}
-	reply2 := makeAddressReply(questionMsg, question, records)
-	l.Put(questionMsg, reply2, nullTTL, 0)
-	clk.Add(time.Duration(1) * time.Second)
-	records = []ZoneRecord{Record{"some.name", net.ParseIP("10.0.1.3"), 0, 0, 0}}
-	reply3 := makeAddressReply(questionMsg, question, records)
-	l.Put(questionMsg, reply3, nullTTL, 0)
-
-	t.Logf("Checking we get the last one...")
-	resp, err = l.Get(questionMsg, minUDPSize)
-	wt.AssertNoErr(t, err)
-	wt.AssertTrue(t, resp != nil, "reponse from the Get()")
-	t.Logf("Received '%s'", resp.Answer[0])
-	wt.AssertType(t, resp.Answer[0], (*dns.A)(nil), "DNS record")
-	wt.AssertEqualString(t, resp.Answer[0].(*dns.A).A.String(), "10.0.1.3", "IP address")
-	wt.AssertEqualInt(t, int(resp.Answer[0].Header().Ttl), int(localTTL), "TTL")
-
-	clk.Add(time.Duration(localTTL-1) * time.Second)
-	resp, err = l.Get(questionMsg, minUDPSize)
-	wt.AssertNoErr(t, err)
-	wt.AssertTrue(t, resp != nil, "reponse from the Get()")
-	t.Logf("Received '%s'", resp.Answer[0])
-	wt.AssertType(t, resp.Answer[0], (*dns.A)(nil), "DNS record")
-	wt.AssertEqualString(t, resp.Answer[0].(*dns.A).A.String(), "10.0.1.3", "IP address")
-	wt.AssertEqualInt(t, int(resp.Answer[0].Header().Ttl), 1, "TTL")
-
-	t.Logf("Checking we get empty replies when they are expired...")
-	lenBefore = l.Len()
-	clk.Add(time.Duration(localTTL) * time.Second)
-	resp, err = l.Get(questionMsg, minUDPSize)
-	wt.AssertNoErr(t, err)
-	if resp != nil {
-		t.Logf("Got\n%s", resp.Answer[0])
-		t.Fatalf("ERROR: Did NOT expect a reponse from the Get()")
-	}
-	wt.AssertEqualInt(t, l.Len(), lenBefore-1, "cache length (after getting an expired entry)")
-
-	questionMsg2 := new(dns.Msg)
-	questionMsg2.SetQuestion("some.other.name", dns.TypeA)
-	questionMsg2.RecursionDesired = true
-	question2 := &questionMsg2.Question[0]
-
-	t.Logf("Trying to Get() a name")
-	resp, err = l.Get(questionMsg2, minUDPSize)
-	wt.AssertNoErr(t, err)
-	wt.AssertNil(t, resp, "reponse from Get() yet")
-
-	t.Logf("Checking that an Remove() between Get() and Put() does not break things")
-	records = []ZoneRecord{Record{"some.name", net.ParseIP("10.0.9.9"), 0, 0, 0}}
-	replyTemp2 := makeAddressReply(questionMsg2, question2, records)
-	l.Remove(question2)
-	l.Put(questionMsg2, replyTemp2, nullTTL, 0)
-	resp, err = l.Get(questionMsg2, minUDPSize)
-	wt.AssertNoErr(t, err)
-	wt.AssertNotNil(t, resp, "reponse from Get()")
-
-	questionMsg3 := new(dns.Msg)
-	questionMsg3.SetQuestion("some.other.name", dns.TypeA)
-	questionMsg3.RecursionDesired = true
-	question3 := &questionMsg3.Question[0]
-
-	t.Logf("Checking that a entry with CacheNoLocalReplies return an error")
-	l.Put(questionMsg3, nil, negLocalTTL, CacheNoLocalReplies)
-	resp, err = l.Get(questionMsg3, minUDPSize)
-	wt.AssertNil(t, resp, "Get() response with CacheNoLocalReplies")
-	wt.AssertTrue(t, err == errNoLocalReplies, "Get() error with CacheNoLocalReplies")
-
-	t.Logf("Checking that more Put's do not make the negative TTL longer")
-	clk.Add(time.Duration(negLocalTTL/2) * time.Second)
-	l.Put(questionMsg3, nil, negLocalTTL, CacheNoLocalReplies)
-	clk.Add(time.Duration(1) * time.Second)
-	l.Put(questionMsg3, nil, negLocalTTL, CacheNoLocalReplies)
-	clk.Add(time.Duration(1) * time.Second)
-	l.Put(questionMsg3, nil, negLocalTTL, CacheNoLocalReplies)
-	resp, err = l.Get(questionMsg3, minUDPSize)
-	wt.AssertNil(t, resp, "Get() response with CacheNoLocalReplies")
-	wt.AssertTrue(t, err == errNoLocalReplies, "Get() error with CacheNoLocalReplies")
-
-	clk.Add(time.Duration(negLocalTTL/2) * time.Second)
-	t.Logf("Checking that we get an expired response after %f seconds", negLocalTTL)
-	resp, err = l.Get(questionMsg3, minUDPSize)
-	wt.AssertNil(t, resp, "expired Get() response with CacheNoLocalReplies")
-	wt.AssertNil(t, err, "expired Get() error with CacheNoLocalReplies")
-
-	l.Remove(question3)
-	t.Logf("Checking that Put&Get with CacheNoLocalReplies with a Remove in the middle returns nothing")
-	l.Put(questionMsg3, nil, nullTTL, CacheNoLocalReplies)
-	l.Remove(question3)
-	resp, err = l.Get(questionMsg3, minUDPSize)
-	wt.AssertNil(t, resp, "Get() reponse with CacheNoLocalReplies")
-	wt.AssertNil(t, err, "Get() error with CacheNoLocalReplies")
-}

nameserver/dns.go

@@ -1,86 +1,351 @@
 package nameserver
 
 import (
+	"bytes"
+	"fmt"
+	"math/rand"
+	"net"
+	"os"
+	"sort"
+	"strings"
+	"sync"
+	"time"
+
 	"github.com/miekg/dns"
+
+	"github.com/weaveworks/weave/net/address"
 )
 
 const (
-	localTTL    uint32 = 30 // somewhat arbitrary; we don't expect anyone downstream to cache results
-	negLocalTTL        = 30 // TTL for negative local resolutions
-	minUDPSize         = 512
-	maxUDPSize         = 65535
+	topDomain        = "."
+	reverseDNSdomain = "in-addr.arpa."
+	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 Upstream interface {
+	Config() (*dns.ClientConfig, error)
 }
 
-func makeReply(r *dns.Msg, as []dns.RR) *dns.Msg {
-	m := new(dns.Msg)
-	m.SetReply(r)
-	m.RecursionAvailable = true
-	m.Answer = as
-	return m
+func NewUpstream(resolvConf, filterAddress string) Upstream {
+	return &upstream{
+		resolvConf:    resolvConf,
+		filterAddress: filterAddress,
+		cachedConfig:  &dns.ClientConfig{}}
 }
 
-func makeTruncatedReply(r *dns.Msg) *dns.Msg {
-	// for truncated response, we create a minimal reply with the Truncated bit set
-	reply := new(dns.Msg)
-	reply.SetReply(r)
-	reply.Truncated = true
-	return reply
+type upstream struct {
+	sync.Mutex
+
+	resolvConf    string
+	filterAddress string
+	cachedConfig  *dns.ClientConfig
+	lastStat      time.Time
+	lastModified  time.Time
 }
 
-func makeAddressReply(r *dns.Msg, q *dns.Question, addrs []ZoneRecord) *dns.Msg {
-	answers := make([]dns.RR, len(addrs))
-	header := makeHeader(r, q)
-	count := 0
-	for _, addr := range addrs {
-		ip := addr.IP()
-		ip4 := ip.To4()
+func (u *upstream) Config() (*dns.ClientConfig, error) {
+	u.Lock()
+	defer u.Unlock()
 
-		switch q.Qtype {
-		case dns.TypeA:
-			if ip4 != nil {
-				answers[count] = &dns.A{Hdr: *header, A: ip}
-				count++
-			}
-		case dns.TypeAAAA:
-			if ip4 == nil {
-				answers[count] = &dns.AAAA{Hdr: *header, AAAA: ip}
-				count++
-			}
+	// If we checked less than five seconds ago return what we already have
+	now := time.Now()
+	if now.Sub(u.lastStat) < 5*time.Second {
+		return u.cachedConfig, nil
+	}
+	u.lastStat = now
+
+	// Reread file if it has changed
+	if fi, err := os.Stat(u.resolvConf); err != nil {
+		return u.cachedConfig, err
+	} else if fi.ModTime() != u.lastModified {
+		if config, err := dns.ClientConfigFromFile(u.resolvConf); err == nil {
+			config.Servers = filter(config.Servers, u.filterAddress)
+			u.lastModified = fi.ModTime()
+			u.cachedConfig = config
+		} else {
+			return u.cachedConfig, err
 		}
 	}
-	return makeReply(r, answers[:count])
+
+	return u.cachedConfig, nil
 }
 
-func makePTRReply(r *dns.Msg, q *dns.Question, names []ZoneRecord) *dns.Msg {
-	answers := make([]dns.RR, len(names))
-	header := makeHeader(r, q)
-	for i, name := range names {
-		answers[i] = &dns.PTR{Hdr: *header, Ptr: name.Name()}
+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 makeReply(r, answers)
+	return ss
 }
 
-func makeDNSFailResponse(r *dns.Msg) *dns.Msg {
-	m := new(dns.Msg)
-	m.SetReply(r)
-	m.RecursionAvailable = true
-	m.Rcode = dns.RcodeNameError
+type DNSServer struct {
+	ns      *Nameserver
+	domain  string
+	ttl     uint32
+	address string
+
+	servers   []*dns.Server
+	upstream  Upstream
+	tcpClient *dns.Client
+	udpClient *dns.Client
+}
+
+func NewDNSServer(ns *Nameserver, domain, address string, upstream Upstream, ttl uint32, clientTimeout time.Duration) (*DNSServer, error) {
+	s := &DNSServer{
+		ns:        ns,
+		domain:    dns.Fqdn(domain),
+		ttl:       ttl,
+		address:   address,
+		upstream:  upstream,
+		tcpClient: &dns.Client{Net: "tcp", ReadTimeout: clientTimeout},
+		udpClient: &dns.Client{Net: "udp", ReadTimeout: clientTimeout, UDPSize: udpBuffSize},
+	}
+
+	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
 }
 
-// get the maximum UDP-reply length
-func getMaxReplyLen(r *dns.Msg, proto dnsProtocol) int {
-	maxLen := minUDPSize
-	if proto == protTCP {
-		maxLen = maxUDPSize
-	} else if opt := r.IsEdns0(); opt != nil {
-		maxLen = int(opt.UDPSize())
+func (h *handler) handleLocal(w dns.ResponseWriter, req *dns.Msg) {
+	h.ns.debugf("local request: %+v", *req)
+	if len(req.Question) != 1 {
+		h.nameError(w, req)
+		return
+	}
+
+	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
+	}
+	// Per RFC4074, if we have an A but another type was requested,
+	// return 'no error' with empty answer section
+	if req.Question[0].Qtype != dns.TypeA {
+		h.respond(w, h.makeResponse(req, nil))
+		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 (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(strings.ToLower(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 {
+		hostname := dns.Fqdn(req.Question[0].Name)
+		if strings.Count(hostname, ".") == 1 {
+			h.handleLocal(w, req)
+			return
+		}
+	}
+
+	upstreamConfig, err := h.upstream.Config()
+	if err != nil {
+		h.ns.errorf("unable to read upstream config: %s", err)
+	}
+	for _, server := range upstreamConfig.Servers {
+		reqCopy := req.Copy()
+		reqCopy.Id = dns.Id()
+		response, _, err := h.client.Exchange(reqCopy, fmt.Sprintf("%s:%s", server, upstreamConfig.Port))
+		if (err != nil && err != dns.ErrTruncated) || 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 maxLen
 }

nameserver/dns_test.go

@@ -0,0 +1,177 @@
+package nameserver
+
+import (
+	"fmt"
+	"math/rand"
+	"net"
+	"strconv"
+	"testing"
+	"time"
+
+	"github.com/miekg/dns"
+	"github.com/stretchr/testify/require"
+
+	"github.com/weaveworks/mesh"
+	"github.com/weaveworks/weave/net/address"
+)
+
+type mockUpstream struct {
+	config *dns.ClientConfig
+}
+
+func (mu *mockUpstream) Config() (*dns.ClientConfig, error) {
+	return mu.config, nil
+}
+
+func startServer(t *testing.T, upstream *dns.ClientConfig) (*DNSServer, *Nameserver, int, int) {
+	peername, err := mesh.PeerNameFromString("00:00:00:02:00:00")
+	require.Nil(t, err)
+	nameserver := New(peername, "", func(mesh.PeerName) bool { return true })
+	dnsserver, err := NewDNSServer(nameserver, "weave.local.", "0.0.0.0:0", &mockUpstream{upstream}, 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, nil)
+	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.", "", mesh.UnknownPeerName, i)
+	}
+
+	doRequest := func(client *dns.Client, request *dns.Msg, port int, expectedErr error) *dns.Msg {
+		request.SetQuestion("foo.weave.local.", dns.TypeA)
+		response, _, err := client.Exchange(request, fmt.Sprintf("127.0.0.1:%d", port))
+		require.Equal(t, expectedErr, 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, dns.ErrTruncated)
+		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, nil)
+		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, nil)
+		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 = make(chan struct{}, 1)
+	handleRecursive := func(w dns.ResponseWriter, req *dns.Msg) {
+		gotRequest <- struct{}{}
+		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, &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, len(gotRequest) > 0)
+	require.True(t, res.Len() > maxSize)
+}

nameserver/entry.go

@@ -0,0 +1,304 @@
+package nameserver
+
+import (
+	"bytes"
+	"encoding/gob"
+	"fmt"
+	"sort"
+	"strings"
+	"time"
+
+	"github.com/weaveworks/mesh"
+
+	"github.com/weaveworks/weave/net/address"
+)
+
+var now = func() int64 { return time.Now().Unix() }
+
+type Entry struct {
+	ContainerID string
+	Origin      mesh.PeerName
+	Addr        address.Address
+	Hostname    string // as supplied
+	lHostname   string // lowercased (not exported, so not encoded by gob)
+	Version     int
+	Tombstone   int64 // timestamp of when it was deleted
+}
+
+type Entries []Entry
+type CaseSensitive Entries
+type CaseInsensitive Entries
+type SortableEntries interface {
+	sort.Interface
+	Get(i int) Entry
+}
+
+// Gossip messages are sorted in a case sensitive order...
+func (es CaseSensitive) Len() int           { return len(es) }
+func (es CaseSensitive) Swap(i, j int)      { es[i], es[j] = es[j], es[i] }
+func (es CaseSensitive) Get(i int) Entry    { return es[i] }
+func (es CaseSensitive) Less(i, j int) bool { return es[i].less(&es[j]) }
+
+// ... but we store entries in a case insensitive order.
+func (es CaseInsensitive) Len() int           { return len(es) }
+func (es CaseInsensitive) Swap(i, j int)      { es[i], es[j] = es[j], es[i] }
+func (es CaseInsensitive) Get(i int) Entry    { return es[i] }
+func (es CaseInsensitive) Less(i, j int) bool { return es[i].insensitiveLess(&es[j]) }
+
+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
+	}
+}
+
+func (e1 *Entry) insensitiveLess(e2 *Entry) bool {
+	// Entries are kept sorted by Hostname, Origin, ContainerID then address
+	e1Hostname, e2Hostname := e1.lHostname, e2.lHostname
+	switch {
+	case e1Hostname != e2Hostname:
+		return e1Hostname < e2Hostname
+
+	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
+	} else if e2.Version == e1.Version && e2.Tombstone > e1.Tombstone {
+		e1.Tombstone = e2.Tombstone
+		return true
+	}
+	return false
+}
+
+func (e1 *Entry) String() string {
+	return fmt.Sprintf("%s -> %s", e1.Hostname, e1.Addr.String())
+}
+
+func (e1 *Entry) addLowercase() {
+	e1.lHostname = strings.ToLower(e1.Hostname)
+}
+
+func (e1 *Entry) tombstone() bool {
+	if e1.Tombstone > 0 {
+		return false
+	}
+	e1.Tombstone = now()
+	e1.Version++
+	return true
+}
+
+func check(es SortableEntries) error {
+	if !sort.IsSorted(es) {
+		return fmt.Errorf("Not sorted")
+	}
+	for i := 1; i < es.Len(); i++ {
+		if es.Get(i).equal(es.Get(i - 1)) {
+			return fmt.Errorf("Duplicate entry: %d:%v and %d:%v", i-1, es.Get(i-1), i, es.Get(i))
+		}
+	}
+	return nil
+}
+
+func checkAndPanic(es SortableEntries) {
+	if err := check(es); err != nil {
+		panic(err)
+	}
+}
+
+func (es *Entries) checkAndPanic() *Entries {
+	checkAndPanic(CaseInsensitive(*es))
+	return es
+}
+
+func (es *Entries) add(hostname, containerid string, origin mesh.PeerName, addr address.Address) Entry {
+	defer es.checkAndPanic().checkAndPanic()
+
+	entry := Entry{Hostname: hostname, lHostname: strings.ToLower(hostname),
+		Origin: origin, ContainerID: containerid, Addr: addr}
+	i := sort.Search(len(*es), func(i int) bool {
+		return !(*es)[i].insensitiveLess(&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 {
+	defer es.checkAndPanic().checkAndPanic()
+	incoming.checkAndPanic()
+
+	newEntries := Entries{}
+	i := 0
+
+	for _, entry := range incoming {
+		for i < len(*es) && (*es)[i].insensitiveLess(&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 mesh.PeerName, f func(*Entry) bool) Entries {
+	defer es.checkAndPanic().checkAndPanic()
+
+	tombstoned := Entries{}
+	for i, e := range *es {
+		if f(&e) && e.Origin == ourname && e.tombstone() {
+			(*es)[i] = e
+			tombstoned = append(tombstoned, e)
+		}
+	}
+	return tombstoned
+}
+
+// note f() may only modify entries such that they remain in order defined by less()
+func (es *Entries) filter(f func(*Entry) bool) {
+	defer es.checkAndPanic().checkAndPanic()
+
+	i := 0
+	for _, e := range *es {
+		if !f(&e) {
+			continue
+		}
+		(*es)[i] = e
+		i++
+	}
+	*es = (*es)[:i]
+}
+
+func (es Entries) findEqual(e *Entry) (*Entry, bool) {
+	i := sort.Search(len(es), func(i int) bool {
+		return !es[i].insensitiveLess(e)
+	})
+	if i < len(es) && es[i].equal(*e) {
+		return &es[i], true
+	}
+	return nil, false
+}
+
+func (es Entries) lookup(hostname string) Entries {
+	es.checkAndPanic()
+
+	lowerHostname := strings.ToLower(hostname)
+	i := sort.Search(len(es), func(i int) bool {
+		return es[i].lHostname >= lowerHostname
+	})
+	if i >= len(es) || es[i].lHostname != lowerHostname {
+		return Entries{}
+	}
+
+	j := sort.Search(len(es)-i, func(j int) bool {
+		return es[i+j].lHostname > lowerHostname
+	})
+
+	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")
+}
+
+func (es Entries) addLowercase() {
+	for i := range es {
+		es[i].addLowercase()
+	}
+}
+
+type GossipData struct {
+	Timestamp int64
+	Entries
+}
+
+func (g *GossipData) Merge(o mesh.GossipData) mesh.GossipData {
+	other := o.(*GossipData)
+	gossip := g.copy()
+	gossip.Entries.merge(other.Entries)
+	if gossip.Timestamp < other.Timestamp {
+		gossip.Timestamp = other.Timestamp
+	}
+	return gossip
+}
+
+func (g *GossipData) Decode(msg []byte) error {
+	if err := gob.NewDecoder(bytes.NewReader(msg)).Decode(g); err != nil {
+		return err
+	}
+
+	g.Entries.addLowercase() // lowercase strings not sent on the wire
+	sort.Sort(CaseInsensitive(g.Entries))
+	return nil
+}
+
+func (g *GossipData) Encode() [][]byte {
+	g2 := g.copy()
+	sort.Sort(CaseSensitive(g2.Entries))
+	buf := &bytes.Buffer{}
+	if err := gob.NewEncoder(buf).Encode(g2); err != nil {
+		panic(err)
+	}
+	return [][]byte{buf.Bytes()}
+}
+
+func (g *GossipData) copy() *GossipData {
+	g2 := &GossipData{Timestamp: g.Timestamp, Entries: make(Entries, len(g.Entries))}
+	copy(g2.Entries, g.Entries)
+	return g2
+}

nameserver/entry_test.go

@@ -0,0 +1,138 @@
+package nameserver
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/require"
+	"github.com/weaveworks/mesh"
+
+	"github.com/weaveworks/weave/net/address"
+)
+
+func l(es Entries) Entries {
+	es.addLowercase()
+	return es
+}
+
+func makeEntries(values string) Entries {
+	entries := make(Entries, len(values))
+	for i, c := range values {
+		entries[i] = Entry{Hostname: string(c)}
+	}
+	return l(entries)
+}
+
+func TestAdd(t *testing.T) {
+	oldNow := now
+	defer func() { now = oldNow }()
+	now = func() int64 { return 1234 }
+
+	entries := Entries{}
+	entries.add("A", "", mesh.UnknownPeerName, address.Address(0))
+	expected := l(Entries{
+		Entry{Hostname: "A", Origin: mesh.UnknownPeerName, Addr: address.Address(0)},
+	})
+	require.Equal(t, entries, expected)
+
+	entries.tombstone(mesh.UnknownPeerName, func(e *Entry) bool { return e.Hostname == "A" })
+	expected = l(Entries{
+		Entry{Hostname: "A", Origin: mesh.UnknownPeerName, Addr: address.Address(0), Version: 1, Tombstone: 1234},
+	})
+	require.Equal(t, entries, expected)
+
+	entries.add("A", "", mesh.UnknownPeerName, address.Address(0))
+	expected = l(Entries{
+		Entry{Hostname: "A", Origin: mesh.UnknownPeerName, Addr: address.Address(0), Version: 2},
+	})
+	require.Equal(t, entries, expected)
+}
+
+func TestMerge(t *testing.T) {
+	e1 := makeEntries("ACDF")
+	e2 := makeEntries("BEF")
+
+	diff := e1.merge(e2)
+
+	require.Equal(t, makeEntries("BE"), diff)
+	require.Equal(t, makeEntries("ABCDEF"), e1)
+
+	diff = e1.merge(e1)
+	require.Equal(t, Entries{}, diff)
+}
+
+func TestOldMerge(t *testing.T) {
+	e1 := l(Entries{Entry{Hostname: "A", Version: 0}})
+	diff := e1.merge(l(Entries{Entry{Hostname: "A", Version: 1}}))
+	require.Equal(t, l(Entries{Entry{Hostname: "A", Version: 1}}), diff)
+	require.Equal(t, l(Entries{Entry{Hostname: "A", Version: 1}}), e1)
+
+	diff = e1.merge(l(Entries{Entry{Hostname: "A", Version: 0}}))
+	require.Equal(t, Entries{}, diff)
+	require.Equal(t, l(Entries{Entry{Hostname: "A", Version: 1}}), e1)
+}
+
+func TestTombstone(t *testing.T) {
+	oldNow := now
+	defer func() { now = oldNow }()
+	now = func() int64 { return 1234 }
+
+	es := makeEntries("AB")
+
+	es.tombstone(mesh.UnknownPeerName, func(e *Entry) bool {
+		return e.Hostname == "B"
+	})
+	expected := l(Entries{
+		Entry{Hostname: "A"},
+		Entry{Hostname: "B", Version: 1, Tombstone: 1234},
+	})
+	require.Equal(t, expected, es)
+
+	// Now try a merge including two entries which differ only in tombstone
+	e2 := make(Entries, len(es))
+	copy(e2, es)
+	e2[1].Tombstone = 5555
+
+	diff := es.merge(e2)
+
+	expected2 := l(Entries{
+		Entry{Hostname: "A"},
+		Entry{Hostname: "B", Version: 1, Tombstone: 5555},
+	})
+	require.Equal(t, expected2, es)
+	expectedDiff := l(Entries{Entry{Hostname: "B", Version: 1, Tombstone: 5555}})
+	require.Equal(t, expectedDiff, diff)
+}
+
+func TestDelete(t *testing.T) {
+	es := makeEntries("AB")
+
+	es.filter(func(e *Entry) bool {
+		return e.Hostname != "A"
+	})
+	require.Equal(t, makeEntries("B"), es)
+}
+
+func TestLookup(t *testing.T) {
+	es := l(Entries{
+		Entry{Hostname: "A"},
+		Entry{Hostname: "B", ContainerID: "bar"},
+		Entry{Hostname: "B", ContainerID: "foo"},
+		Entry{Hostname: "C"},
+	})
+
+	have := es.lookup("B")
+	want := l(Entries{
+		Entry{Hostname: "B", ContainerID: "bar"},
+		Entry{Hostname: "B", ContainerID: "foo"},
+	})
+	require.Equal(t, have, want)
+}
+
+func TestGossipDataMerge(t *testing.T) {
+	g1 := GossipData{Entries: makeEntries("AcDf")}
+	g2 := GossipData{Entries: makeEntries("BEf")}
+
+	g3 := g1.Merge(&g2).(*GossipData)
+
+	require.Equal(t, GossipData{Entries: makeEntries("ABcDEf")}, *g3)
+}

nameserver/http.go

@@ -1,95 +1,91 @@
 package nameserver
 
 import (
+	"encoding/json"
 	"fmt"
+	"net/http"
+
 	"github.com/gorilla/mux"
 	"github.com/miekg/dns"
-	. "github.com/weaveworks/weave/common"
-	"log"
-	"net"
-	"net/http"
+
+	"github.com/weaveworks/weave/common/docker"
+	"github.com/weaveworks/weave/net/address"
 )
 
-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 (n *Nameserver) badRequest(w http.ResponseWriter, err error) {
+	http.Error(w, err.Error(), http.StatusBadRequest)
+	n.infof("%v", err)
 }
 
-func ListenHTTP(version string, server *DNSServer, domain string, db Zone, port int) {
-
-	muxRouter := mux.NewRouter()
-
-	muxRouter.Methods("GET").Path("/status").HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
-		fmt.Fprintln(w, "weave DNS", version)
-		fmt.Fprintln(w, server.Status())
+func (n *Nameserver) HandleHTTP(router *mux.Router, dockerCli *docker.Client) {
+	router.Methods("GET").Path("/domain").HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		fmt.Fprint(w, n.domain)
 	})
 
-	muxRouter.Methods("PUT").Path("/name/{id:.+}/{ip:.+}").HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
-		reqError := func(msg string, logmsg string, logargs ...interface{}) {
-			httpErrorAndLog(Warning, w, msg, http.StatusBadRequest, logmsg, logargs...)
+	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 !dns.IsSubDomain(n.domain, hostname) {
+			n.infof("Ignoring registration %s %s %s (not a subdomain of %s)", hostname, ipStr, container, n.domain)
+			return
+		}
+
+		n.AddEntry(hostname, container, n.ourName, ip)
+
+		if r.FormValue("check-alive") == "true" && dockerCli != nil && dockerCli.IsContainerNotRunning(container) {
+			n.infof("container '%s' is not running: removing", container)
+			n.Delete(hostname, container, ipStr, ip)
+		}
+
+		w.WriteHeader(204)
+	})
+
+	deleteHandler := func(w http.ResponseWriter, r *http.Request) {
 		vars := mux.Vars(r)
-		idStr := vars["id"]
-		ipStr := vars["ip"]
-		name := r.FormValue("fqdn")
 
-		if name == "" {
-			reqError("Invalid FQDN", "Invalid FQDN in 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(idStr, 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.
-			}
+		hostname := r.FormValue("fqdn")
+		if hostname == "" {
+			hostname = "*"
 		} else {
-			Info.Printf("[http] Ignoring name %s, not in %s", name, domain)
-		}
-	})
-
-	muxRouter.Methods("DELETE").Path("/name/{id:.+}/{ip:.+}").HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
-		reqError := func(msg string, logmsg string, logargs ...interface{}) {
-			httpErrorAndLog(Warning, w, msg, http.StatusBadRequest, logmsg, logargs...)
+			hostname = dns.Fqdn(hostname)
 		}
 
-		vars := mux.Vars(r)
-		idStr := vars["id"]
-		ipStr := vars["ip"]
+		container, ok := vars["container"]
+		if !ok {
+			container = "*"
+		}
 
-		ip := net.ParseIP(ipStr)
-		if ip == nil {
-			reqError("Invalid IP in request", "Invalid IP in request: %s", ipStr)
+		ipStr, ok := vars["ip"]
+		ip, err := address.ParseIP(ipStr)
+		if ok && err != nil {
+			n.badRequest(w, err)
 			return
+		} else if !ok {
+			ipStr = "*"
 		}
-		Info.Printf("[http] Deleting %s (%s)", idStr, ipStr)
-		if err := db.DeleteRecord(idStr, ip); err != nil {
-			if _, ok := err.(LookupError); !ok {
-				httpErrorAndLog(
-					Error, w, "Internal error", http.StatusInternalServerError,
-					"Unexpected error from DB: %s", err)
-				return
-			}
+
+		n.Delete(hostname, container, ipStr, ip)
+		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))
 		}
 	})
-
-	http.Handle("/", muxRouter)
-
-	address := fmt.Sprintf(":%d", port)
-	if err := http.ListenAndServe(address, nil); err != nil {
-		Error.Fatal("[http] Unable to create http listener: ", err)
-	}
 }

nameserver/http_test.go

@@ -1,91 +0,0 @@
-package nameserver
-
-import (
-	"fmt"
-	wt "github.com/weaveworks/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       = "10.2.2.1/24"
-		dockerIP        = "9.8.7.6"
-	)
-
-	zone := NewZoneDb(DefaultLocalDomain)
-
-	port := rand.Intn(10000) + 32768
-	fmt.Println("Http test on port", port)
-	go ListenHTTP("", nil, 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.
-	ip, _, _ := net.ParseCIDR(testAddr1)
-	foundIP, err := zone.LookupName(successTestName)
-	wt.AssertNoErr(t, err)
-	if !foundIP[0].IP().Equal(ip) {
-		t.Fatalf("Unexpected result for %s: received %s, expected %s", successTestName, foundIP, ip)
-	}
-
-	// 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.
-	x, err := zone.LookupName(successTestName)
-	t.Logf("Got %s", x)
-	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
-	x, err = zone.LookupName(successTestName)
-	t.Logf("Got %s", x)
-	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

@@ -1,296 +0,0 @@
-package nameserver
-
-import (
-	"bytes"
-	"fmt"
-	"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
-	ttl  int
-	err  error
-}
-
-func (r Response) Name() string  { return r.name }
-func (r Response) IP() net.IP    { return r.addr }
-func (r Response) Priority() int { return 0 }
-func (r Response) Weight() int   { return 0 }
-func (r Response) TTL() int      { return r.ttl }
-
-func (r Response) Equal(r2 *Response) bool {
-	if r.name != r2.name {
-		return false
-	}
-	if !r.addr.Equal(r2.addr) {
-		return false
-	}
-	if r.err != r2.err {
-		return false
-	}
-	return true
-}
-
-func (r Response) String() string {
-	var buf bytes.Buffer
-	if r.err != nil {
-		fmt.Fprintf(&buf, "%s", r.err)
-	} else {
-		if len(r.Name()) > 0 {
-			fmt.Fprintf(&buf, "%s", r.Name())
-		}
-		if !r.IP().IsUnspecified() {
-			fmt.Fprintf(&buf, "[%s]", r.IP())
-		}
-		if r.ttl > 0 {
-			fmt.Fprintf(&buf, "(TTL:%d)", r.TTL())
-		}
-	}
-	return buf.String()
-}
-
-type responseInfo struct {
-	timeout   time.Time // if no answer by this time, give up
-	insistent bool      // insistent queries are not removed on the first reply
-	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
-	actionChan chan<- MDNSAction
-	running    bool
-}
-
-type mDNSQueryInfo struct {
-	name       string
-	querytype  uint16
-	responseCh chan<- *Response
-}
-
-func NewMDNSClient() (*MDNSClient, error) {
-	return &MDNSClient{
-		addr:     ipv4Addr,
-		running:  false,
-		inflight: make(map[string]*inflightQuery)}, nil
-}
-
-func (c *MDNSClient) Start(ifi *net.Interface) (err error) {
-	if c.running {
-		return nil
-	}
-
-	if c.conn, err = net.ListenUDP("udp4", &net.UDPAddr{IP: net.IPv4zero, Port: 0}); err != nil {
-		return err
-	}
-
-	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()
-
-	actionChan := make(chan MDNSAction, MailboxSize)
-	c.actionChan = actionChan
-	go c.actorLoop(actionChan)
-	return nil
-}
-
-func (c *MDNSClient) Stop() error {
-	if c.running {
-		c.actionChan <- nil
-	}
-	return nil
-}
-
-func LinkLocalMulticastListener(ifi *net.Interface) (net.PacketConn, error) {
-	return net.ListenMulticastUDP("udp", ifi, ipv4Addr)
-}
-
-// ACTOR client API
-
-type MDNSAction func()
-
-// Async
-func (c *MDNSClient) SendQuery(name string, querytype uint16, insistent bool, responseCh chan<- *Response) {
-	c.actionChan <- func() {
-		query, found := c.inflight[name]
-		if !found {
-			m := new(dns.Msg)
-			m.SetQuestion(name, querytype)
-			m.RecursionDesired = false
-			buf, err := m.Pack()
-			if err != nil {
-				responseCh <- &Response{err: err}
-				close(responseCh)
-				return
-			}
-			query = &inflightQuery{
-				name: name,
-				id:   m.Id,
-			}
-			if _, err = c.conn.WriteTo(buf, c.addr); err != nil {
-				responseCh <- &Response{err: err}
-				close(responseCh)
-				return
-			}
-			c.inflight[name] = query
-		}
-		info := &responseInfo{
-			ch:        responseCh,
-			timeout:   time.Now().Add(mDNSTimeout),
-			insistent: insistent,
-		}
-		// 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)
-	}
-}
-
-// Async - called from dns library multiplexer
-func (c *MDNSClient) ResponseCallback(r *dns.Msg) {
-	c.actionChan <- func() {
-		for _, answer := range r.Answer {
-			var name string
-			var res *Response
-
-			switch rr := answer.(type) {
-			case *dns.A:
-				name = rr.Hdr.Name
-				res = &Response{name: name, addr: rr.A, ttl: int(rr.Hdr.Ttl)}
-			case *dns.PTR:
-				name = rr.Hdr.Name
-				raddr, _ := raddrToIP(name)
-				res = &Response{name: rr.Ptr, addr: raddr, ttl: int(rr.Hdr.Ttl)}
-			default:
-				return
-			}
-
-			if query, found := c.inflight[name]; found {
-				var newResponseInfos []*responseInfo
-				for _, resp := range query.responseInfos {
-					resp.ch <- res
-					// insistent queries are not removed on the first reply, but on the timeout
-					if resp.insistent {
-						newResponseInfos = append(newResponseInfos, resp)
-					} else {
-						close(resp.ch)
-					}
-				}
-				if len(newResponseInfos) == 0 {
-					delete(c.inflight, name)
-				} else {
-					query.responseInfos = newResponseInfos
-				}
-			} else {
-				// We've received a response that didn't match a query
-				// Do we want to cache it?
-			}
-		}
-	}
-}
-
-// 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) actorLoop(actionChan <-chan MDNSAction) {
-	timer := time.NewTimer(MaxDuration)
-	run := func() { timer.Reset(c.checkInFlightQueries()) }
-	c.running = true
-	for c.running {
-		select {
-		case action := <-actionChan:
-			if action == nil {
-				c.listener.Shutdown()
-				c.running = false
-			} else {
-				action()
-				run()
-			}
-		case <-timer.C:
-			run()
-		}
-	}
-
-	// Close all response channels at termination
-	for _, query := range c.inflight {
-		for _, item := range query.responseInfos {
-			close(item.ch)
-		}
-	}
-}

nameserver/mdns_client_test.go

@@ -1,197 +0,0 @@
-package nameserver
-
-import (
-	"github.com/miekg/dns"
-	. "github.com/weaveworks/weave/common"
-	wt "github.com/weaveworks/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: hdr, A: 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: hdr, Ptr: successTestName}
-		m.Answer = append(m.Answer, a)
-		sendAnswer(m)
-	}
-}
-
-func RunLocalMulticastServer() (*dns.Server, error) {
-	multicast, err := LinkLocalMulticastListener(nil)
-	if err != nil {
-		return nil, err
-	}
-	server := &dns.Server{
-		PacketConn:  multicast,
-		Handler:     dns.HandlerFunc(minimalServer),
-		ReadTimeout: 100 * time.Millisecond}
-	go server.ActivateAndServe()
-	return server, nil
-}
-
-func setup(t *testing.T) (*MDNSClient, *dns.Server, error) {
-	InitDefaultLogging(testing.Verbose())
-
-	server, err := RunLocalMulticastServer()
-	if err != nil {
-		t.Fatalf("Unable to run test server: %s. No default multicast interface?", err)
-	}
-
-	mdnsClient, err := NewMDNSClient()
-	wt.AssertNoErr(t, err)
-	err = mdnsClient.Start(nil)
-	wt.AssertNoErr(t, err)
-
-	return mdnsClient, server, err
-}
-
-func (c *MDNSClient) Shutdown() {
-	c.actionChan <- nil
-}
-
-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.IP())
-	c.receivedAddr = resp.IP()
-	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, false, 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, false, 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, false, context1.channel)
-	go mdnsClient.SendQuery(successTestName, dns.TypeA, false, 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()
-
-	ips, err := mdnsClient.LookupName(successTestName)
-	wt.AssertNoErr(t, err)
-	if !testAddr.Equal(ips[0].IP()) {
-		t.Fatalf("Returned address incorrect %s", ips)
-	}
-
-	ips, err = mdnsClient.LookupName("foo.example.com.")
-	wt.AssertErrorType(t, err, (*LookupError)(nil), "unknown hostname")
-
-	names, err := mdnsClient.LookupInaddr(testInAddr)
-	wt.AssertNoErr(t, err)
-	if !(successTestName == names[0].Name()) {
-		t.Fatalf("Expected name %s, got %s", successTestName, names)
-	}
-}

nameserver/mdns_lookup.go

@@ -1,71 +0,0 @@
-package nameserver
-
-import (
-	"github.com/miekg/dns"
-	. "github.com/weaveworks/weave/common"
-)
-
-func mdnsLookup(client *MDNSClient, name string, qtype uint16, insistent bool) ([]ZoneRecord, error) {
-	var responses []*Response
-	channel := make(chan *Response)
-	client.SendQuery(name, qtype, insistent, 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
-		}
-		Debug.Printf("[mdns] Got response name for %s-query about name '%s': name '%s', addr '%s'",
-			dns.TypeToString[qtype], name, resp.name, resp.addr)
-
-		if !insistent {
-			return []ZoneRecord{resp}, nil // non-background queries return the first response...
-		}
-
-		// add the response, avoiding duplicates
-		// TODO: replace this linear search by something better... (not a big deal as we don't expect long responses)
-		duplicate := false
-		for _, r := range responses {
-			if r.Equal(resp) {
-				duplicate = true
-				break
-			}
-		}
-		if !duplicate {
-			responses = append(responses, resp)
-		}
-	}
-
-	if len(responses) == 0 {
-		return nil, LookupError(name)
-	}
-
-	// convert []Response to []ZoneRecord
-	res := make([]ZoneRecord, len(responses))
-	for i, rr := range responses {
-		res[i] = ZoneRecord(rr)
-	}
-	return res, nil
-}
-
-// Perform a lookup for a name, returning either an IP address or an error
-func (client *MDNSClient) LookupName(name string) ([]ZoneRecord, error) {
-	return mdnsLookup(client, name, dns.TypeA, false)
-}
-
-// Perform a lookup for an IP address, returning either a name or an error
-func (client *MDNSClient) LookupInaddr(inaddr string) ([]ZoneRecord, error) {
-	return mdnsLookup(client, inaddr, dns.TypePTR, false)
-}
-
-// Perform lookup for a name, returning either a list of IP addresses or an error
-// Insistent queries will wait up to `mDNSTimeout` milliseconds for responses
-func (client *MDNSClient) InsistentLookupName(name string) ([]ZoneRecord, error) {
-	return mdnsLookup(client, name, dns.TypeA, true)
-}
-
-// Perform an insistent lookup for an IP address, returning either a list of names or an error
-// Insistent queries will wait up to `mDNSTimeout` milliseconds for responses
-func (client *MDNSClient) InsistentLookupInaddr(inaddr string) ([]ZoneRecord, error) {
-	return mdnsLookup(client, inaddr, dns.TypePTR, true)
-}

nameserver/mdns_server.go

@@ -1,143 +0,0 @@
-package nameserver
-
-import (
-	"github.com/miekg/dns"
-	. "github.com/weaveworks/weave/common"
-	"net"
-)
-
-type MDNSServer struct {
-	localAddrs []net.Addr
-	sendconn   *net.UDPConn
-	srv        *dns.Server
-	zone       Zone
-	running    bool
-}
-
-// Create a new mDNS server
-// Nothing will be done (including port bindings) until you `Start()` the server
-func NewMDNSServer(zone Zone) (*MDNSServer, error) {
-	return &MDNSServer{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
-}
-
-// Start the mDNS server
-func (s *MDNSServer) Start(ifi *net.Interface) (err error) {
-	// skip double initialization
-	if s.running {
-		return nil
-	}
-
-	// This is a bit of a kludge - per the RFC we should send responses from 5353, but that doesn't seem to work
-	s.sendconn, err = net.ListenUDP("udp4", &net.UDPAddr{IP: net.IPv4zero, Port: 0})
-	if err != nil {
-		return err
-	}
-
-	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 ZoneLookup, r *dns.Msg, q *dns.Question) *dns.Msg {
-			if ips, err := zone.LookupName(q.Name); err == nil {
-				return makeAddressReply(r, q, ips)
-			}
-			return nil
-		})
-
-	handleReverse := s.makeHandler(dns.TypePTR,
-		func(zone ZoneLookup, r *dns.Msg, q *dns.Question) *dns.Msg {
-			if names, err := zone.LookupInaddr(q.Name); err == nil {
-				return makePTRReply(r, q, names)
-			}
-			return nil
-		})
-
-	mux := dns.NewServeMux()
-	mux.HandleFunc(s.zone.Domain(), handleLocal)
-	mux.HandleFunc(RDNSDomain, handleReverse)
-
-	s.srv = &dns.Server{
-		Listener:   nil,
-		PacketConn: conn,
-		Handler:    mux,
-	}
-	go s.srv.ActivateAndServe()
-	s.running = true
-	return err
-}
-
-// Stop the mDNS server
-func (s *MDNSServer) Stop() error {
-	s.running = false
-	return s.srv.Shutdown()
-}
-
-func (s *MDNSServer) Zone() Zone {
-	return s.zone
-}
-
-type LookupFunc func(ZoneLookup, *dns.Msg, *dns.Question) *dns.Msg
-
-func (s *MDNSServer) makeHandler(qtype uint16, lookup LookupFunc) dns.HandlerFunc {
-	return func(rw 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.
-		// TODO: use any Answer in the query for adding records in the Zone database...
-		if len(r.Answer) == 0 && len(r.Question) > 0 {
-			q := &r.Question[0]
-			if q.Qtype == qtype {
-				Debug.Printf("[mdns msgid %d] srv: trying to answer to mDNS query '%s'", r.MsgHdr.Id, q.Name)
-				if m := lookup(s.zone, r, q); m != nil {
-					Debug.Printf("[mdns msgid %d] srv: found local answer to mDNS query '%s'", r.MsgHdr.Id, q.Name)
-					if err := s.sendResponse(m); err != nil {
-						Warning.Printf("[mdns msgid %d] srv: error writing mDNS response to %v", r.MsgHdr.Id, s.sendconn)
-					} else {
-						Debug.Printf("[mdns msgid %d] srv: response sent: %d answers", r.MsgHdr.Id, len(m.Answer))
-					}
-				} else {
-					Debug.Printf("[mdns msgid %d] srv: no local answer for answering 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

@@ -1,120 +0,0 @@
-package nameserver
-
-import (
-	"github.com/miekg/dns"
-	. "github.com/weaveworks/weave/common"
-	wt "github.com/weaveworks/weave/testing"
-	"net"
-	"testing"
-	"time"
-)
-
-func TestServerSimpleQuery(t *testing.T) {
-	var (
-		testRecord1 = Record{"test.weave.local.", net.ParseIP("10.20.20.10"), 0, 0, 0}
-		testRecord2 = Record{"test.weave.local.", net.ParseIP("10.20.20.20"), 0, 0, 0}
-		testInAddr1 = "10.20.20.10.in-addr.arpa."
-	)
-
-	InitDefaultLogging(testing.Verbose())
-	Info.Println("TestServerSimpleQuery starting")
-
-	mzone := newMockedZoneWithRecords([]ZoneRecord{testRecord1, testRecord2})
-	mdnsServer, err := NewMDNSServer(mzone)
-	wt.AssertNoErr(t, err)
-	err = mdnsServer.Start(nil)
-	wt.AssertNoErr(t, err)
-	defer mdnsServer.Stop()
-
-	var receivedAddrs []net.IP
-	receivedName := ""
-	recvChan := make(chan interface{})
-	receivedCount := 0
-
-	// 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 {
-			t.Logf("Received %d answer(s)", len(r.Answer))
-			for _, answer := range r.Answer {
-				switch rr := answer.(type) {
-				case *dns.A:
-					t.Logf("... A:\n%+v", rr)
-					receivedAddrs = append(receivedAddrs, rr.A)
-					receivedCount++
-				case *dns.PTR:
-					t.Logf("... PTR:\n%+v", rr)
-					receivedName = rr.Ptr
-					receivedCount++
-				}
-			}
-			recvChan <- "ok"
-		}
-	}
-
-	sendQuery := func(name string, querytype uint16) {
-		receivedAddrs = make([]net.IP, 0)
-		receivedName = ""
-		receivedCount = 0
-		recvChan = make(chan interface{})
-
-		m := new(dns.Msg)
-		m.SetQuestion(name, querytype)
-		m.RecursionDesired = false
-		buf, err := m.Pack()
-		wt.AssertNoErr(t, err)
-		conn, err := net.ListenUDP("udp4", &net.UDPAddr{IP: net.IPv4zero, Port: 0})
-		wt.AssertNoErr(t, err)
-		Debug.Printf("Sending UDP packet to %s", ipv4Addr)
-		_, err = conn.WriteTo(buf, ipv4Addr)
-		wt.AssertNoErr(t, err)
-
-		Debug.Printf("Waiting for response")
-		select {
-		case <-recvChan:
-			return
-		case <-time.After(100 * time.Millisecond):
-			Debug.Printf("Timeout while waiting for response")
-			return
-		}
-	}
-
-	listener := &dns.Server{
-		Unsafe:      true,
-		PacketConn:  multicast,
-		Handler:     dns.HandlerFunc(handleMDNS),
-		ReadTimeout: 100 * time.Millisecond}
-	go listener.ActivateAndServe()
-	defer listener.Shutdown()
-
-	time.Sleep(100 * time.Millisecond) // Allow for server to get going
-
-	Debug.Printf("Checking that we get 2 IPs fo name '%s' [A]", testRecord1.Name())
-	sendQuery(testRecord1.Name(), dns.TypeA)
-	if receivedCount != 2 {
-		t.Fatalf("Unexpected result count %d for %s", receivedCount, testRecord1.Name())
-	}
-	if !(receivedAddrs[0].Equal(testRecord1.IP()) || receivedAddrs[0].Equal(testRecord2.IP())) {
-		t.Fatalf("Unexpected result %s for %s", receivedAddrs, testRecord1.Name())
-	}
-	if !(receivedAddrs[1].Equal(testRecord1.IP()) || receivedAddrs[1].Equal(testRecord2.IP())) {
-		t.Fatalf("Unexpected result %s for %s", receivedAddrs, testRecord1.Name())
-	}
-
-	Debug.Printf("Checking that 'testfail.weave.' [A] gets no answers")
-	sendQuery("testfail.weave.", dns.TypeA)
-	if receivedCount != 0 {
-		t.Fatalf("Unexpected result count %d for testfail.weave", receivedCount)
-	}
-
-	Debug.Printf("Checking that '%s' [PTR] gets one name", testInAddr1)
-	sendQuery(testInAddr1, dns.TypePTR)
-	if receivedCount != 1 {
-		t.Fatalf("Expected an answer to %s, got %d answers", testInAddr1, receivedCount)
-	} else if !(testRecord1.Name() == receivedName) {
-		t.Fatalf("Expected answer %s to query for %s, got %s", testRecord1.Name(), testInAddr1, receivedName)
-	}
-}