Add release v1.4.6

Change invariant fail on Merge() from panic to error

Fixes #2083.

.travis.yml

@@ -1,28 +1,13 @@
-language: go
+language: python
 sudo: false
-go:
-  - 1.4
 
 env:
-  - PATH="${PATH}:${HOME}/.local/bin"
+  - PATH="${PATH}:${HOME}/gsutil"
-
-addons:
-  apt:
-    packages:
-    - libpcap-dev
 
 install:
-  - go clean -i net
+  - pip install pyopenssl
-  - go install -tags netgo std
+  - curl --silent --location https://storage.googleapis.com/pub/gsutil.tar.gz | tar xz -C $HOME
-  - go get github.com/golang/lint/golint
-  - pip install --user --upgrade gsutil
   - bin/setup-ci-secrets $encrypted_5ba036e89377_key $encrypted_5ba036e89377_iv
-  - make travis
-  - go get ./...
 
 script:
-  - make tests
+  - 'test "${TRAVIS_PULL_REQUEST}" = "true" || site/build-and-publish.sh'
-
-after_success:
-  - go get github.com/mattn/goveralls
-  - test "${TRAVIS_PULL_REQUEST}" = "false" && site/build-and-publish.sh

CHANGELOG.md

@@ -1,3 +1,52 @@
+## 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.

common/docker/client.go

@@ -4,12 +4,18 @@ 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)
@@ -72,21 +78,33 @@ func (c *Client) Info() string {
 
 // AddObserver adds an observer for docker events
 func (c *Client) AddObserver(ob ContainerObserver) error {
-	events := make(chan *docker.APIEvents)
-	if err := c.AddEventListener(events); err != nil {
-		Log.Errorf("[docker] Unable to add listener to Docker API: %s", err)
-		return err
-	}
-
 	go func() {
-		for event := range events {
+		retryInterval := InitialInterval
-			switch event.Status {
+		for {
-			case "start":
+			events := make(chan *docker.APIEvents)
-				id := event.ID
+			if err := c.AddEventListener(events); err != nil {
-				ob.ContainerStarted(id)
+				Log.Errorf("[docker] Unable to add listener to Docker API: %s - retrying in %ds", err, retryInterval/time.Second)
-			case "die":
+			} else {
-				id := event.ID
+				start := time.Now()
-				ob.ContainerDied(id)
+				for event := range events {
+					switch event.Status {
+					case "start":
+						id := event.ID
+						ob.ContainerStarted(id)
+					case "die":
+						id := event.ID
+						ob.ContainerDied(id)
+					}
+				}
+				if time.Since(start) > retryInterval {
+					retryInterval = InitialInterval
+				}
+				Log.Errorf("[docker] Event listener channel closed - retrying subscription in %ds", retryInterval/time.Second)
+			}
+			time.Sleep(retryInterval)
+			retryInterval = retryInterval * 3 / 2
+			if retryInterval > MaxInterval {
+				retryInterval = MaxInterval
 			}
 		}
 	}()
@@ -97,7 +115,7 @@ func (c *Client) AddObserver(ob ContainerObserver) error {
 func (c *Client) IsContainerNotRunning(idStr string) bool {
 	container, err := c.InspectContainer(idStr)
 	if err == nil {
-		return !container.State.Running
+		return !container.State.Running || container.State.Restarting
 	}
 	if _, notThere := err.(*docker.NoSuchContainer); notThere {
 		return true

ipam/allocator.go

@@ -140,29 +140,23 @@ func (alloc *Allocator) cancelOpsFor(ops *[]operation, ident string) bool {
 	return found
 }
 
-// Try all pending operations
+// Try all operations in a queue
-func (alloc *Allocator) tryPendingOps() {
+func (alloc *Allocator) tryOps(ops *[]operation) {
-	// The slightly different semantics requires us to operate on 'claims' and
+	for i := 0; i < len(*ops); {
-	// 'allocates' separately:
+		op := (*ops)[i]
-	// Claims must be tried before Allocates
-	for i := 0; i < len(alloc.pendingClaims); {
-		op := alloc.pendingClaims[i]
 		if !op.Try(alloc) {
 			i++
 			continue
 		}
-		alloc.pendingClaims = append(alloc.pendingClaims[:i], alloc.pendingClaims[i+1:]...)
+		*ops = append((*ops)[:i], (*ops)[i+1:]...)
 	}
+}
 
-	// When the first Allocate fails, bail - no need to
+// Try all pending operations
-	// send too many begs for space.
+func (alloc *Allocator) tryPendingOps() {
-	for i := 0; i < len(alloc.pendingAllocates); {
+	// Process existing claims before servicing new allocations
-		op := alloc.pendingAllocates[i]
+	alloc.tryOps(&alloc.pendingClaims)
-		if !op.Try(alloc) {
+	alloc.tryOps(&alloc.pendingAllocates)
-			break
-		}
-		alloc.pendingAllocates = append(alloc.pendingAllocates[:i], alloc.pendingAllocates[i+1:]...)
-	}
 }
 
 func (alloc *Allocator) spaceRequestDenied(sender mesh.PeerName, r address.Range) {
@@ -340,7 +334,10 @@ func (alloc *Allocator) AdminTakeoverRanges(peerNameOrNickname string) error {
 		}
 
 		newRanges, err := alloc.ring.Transfer(peername, alloc.ourName)
-		alloc.space.AddRanges(newRanges)
+		if err == nil && len(newRanges) > 0 {
+			alloc.space.AddRanges(newRanges)
+			alloc.gossip.GossipBroadcast(alloc.Gossip())
+		}
 		resultChan <- err
 	}
 	return <-resultChan

ipam/ring/ring.go

@@ -46,33 +46,37 @@ var (
 )
 
 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++ {
+	for i := 1; i < len(entries); i++ {
-		if r.Entries[i-1].Token == r.Entries[i].Token {
+		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 {
+	for i, entry := range entries {
-		next := r.Entries.entry(i + 1)
+		next := entries.entry(i + 1)
 		distance := r.distance(entry.Token, next.Token)
 
 		if entry.Free > distance {
@@ -181,7 +185,6 @@ func (r *Ring) GrantRangeToHost(start, end address.Address, peer mesh.PeerName)
 // Merge the given ring into this ring and return any new ranges added
 func (r *Ring) Merge(gossip Ring) error {
 	r.assertInvariants()
-	defer r.assertInvariants()
 	defer r.updateExportedVariables()
 
 	// Don't panic when checking the gossiped in ring.
@@ -267,6 +270,10 @@ func (r *Ring) Merge(gossip Ring) error {
 		previousOwner = nil
 	}
 
+	if err := r.checkEntries(result); err != nil {
+		return fmt.Errorf("Merge of incoming data causes: %s", err)
+	}
+
 	if len(r.Seeds) == 0 {
 		r.Seeds = gossip.Seeds
 	}

mesh/connection_maker.go

@@ -32,6 +32,7 @@ const (
 	TargetWaiting    TargetState = iota // we are waiting to connect there
 	TargetAttempting                    // we are attempting to connect there
 	TargetConnected                     // we are connected to there
+	TargetSuspended                     // not currently attempting to connect here
 )
 
 // Information about an address where we may find a peer
@@ -266,16 +267,23 @@ func (cm *ConnectionMaker) connectToTargets(validTarget map[string]struct{}, dir
 	now := time.Now() // make sure we catch items just added
 	after := MaxDuration
 	for address, target := range cm.targets {
-		if target.state != TargetWaiting {
+		if target.state != TargetWaiting && target.state != TargetSuspended {
 			continue
 		}
 		if _, valid := validTarget[address]; !valid {
-			delete(cm.targets, address)
+			// Not valid: suspend reconnects if direct peer,
+			// otherwise forget this target entirely
+			if _, direct := directTarget[address]; direct {
+				target.state = TargetSuspended
+			} else {
+				delete(cm.targets, address)
+			}
 			continue
 		}
 		if target.tryAfter.IsZero() {
 			continue
 		}
+		target.state = TargetWaiting
 		switch duration := target.tryAfter.Sub(now); {
 		case duration <= 0:
 			target.state = TargetAttempting

mesh/status.go

@@ -181,6 +181,7 @@ func NewLocalConnectionStatusSlice(cm *ConnectionMaker) []LocalConnectionStatus
 					add("retrying", target.lastError.Error())
 				}
 			case TargetConnected:
+			case TargetSuspended:
 			}
 		}
 		resultChan <- slice

nameserver/entry.go

@@ -93,6 +93,9 @@ func (e1 *Entry) merge(e2 *Entry) bool {
 		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
 }
@@ -105,6 +108,11 @@ func (e1 *Entry) addLowercase() {
 	e1.lHostname = strings.ToLower(e1.Hostname)
 }
 
+func (e1 *Entry) tombstone() {
+	e1.Version++
+	e1.Tombstone = now()
+}
+
 func check(es SortableEntries) error {
 	if !sort.IsSorted(es) {
 		return fmt.Errorf("Not sorted!")
@@ -182,8 +190,7 @@ func (es *Entries) tombstone(ourname mesh.PeerName, f func(*Entry) bool) Entries
 	tombstoned := Entries{}
 	for i, e := range *es {
 		if f(&e) && e.Origin == ourname {
-			e.Version++
+			e.tombstone()
-			e.Tombstone = now()
 			(*es)[i] = e
 			tombstoned = append(tombstoned, e)
 		}
@@ -191,6 +198,7 @@ func (es *Entries) tombstone(ourname mesh.PeerName, f func(*Entry) bool) Entries
 	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()
 
@@ -205,6 +213,16 @@ func (es *Entries) filter(f func(*Entry) bool) {
 	*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()
 

nameserver/entry_test.go

@@ -86,6 +86,21 @@ func TestTombstone(t *testing.T) {
 		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) {

nameserver/nameserver.go

@@ -84,8 +84,8 @@ func (n *Nameserver) broadcastEntries(es ...Entry) error {
 }
 
 func (n *Nameserver) AddEntry(hostname, containerid string, origin mesh.PeerName, addr address.Address) error {
-	n.infof("adding entry %s -> %s", hostname, addr.String())
 	n.Lock()
+	n.infof("adding entry for %s: %s -> %s", containerid, hostname, addr.String())
 	entry := n.entries.add(hostname, containerid, origin, addr)
 	n.Unlock()
 	return n.broadcastEntries(entry)
@@ -203,11 +203,31 @@ func (n *Nameserver) receiveGossip(msg []byte) (mesh.GossipData, mesh.GossipData
 		return nil, nil, fmt.Errorf("clock skew of %d detected", delta)
 	}
 
+	// Filter to remove entries from unknown peers, done before we take
+	// the nameserver lock, so we don't have to worry what isKnownPeer locks.
+	gossip.Entries.filter(func(e *Entry) bool {
+		return n.isKnownPeer(e.Origin)
+	})
+
 	n.Lock()
 	defer n.Unlock()
 
+	// Check entries claiming to originate from us against our current data
 	gossip.Entries.filter(func(e *Entry) bool {
-		return n.isKnownPeer(e.Origin)
+		if e.Origin == n.ourName {
+			if ourEntry, ok := n.entries.findEqual(e); ok {
+				if ourEntry.Version < e.Version ||
+					(ourEntry.Version == e.Version && ourEntry.Tombstone != e.Tombstone) {
+					// Take our version of the data, but make the version higher than the incoming
+					nextVersion := e.Version + 1
+					*e = *ourEntry
+					e.Version = nextVersion
+				}
+			} else { // We have no entry matching the one that came in with us as Origin
+				e.tombstone()
+			}
+		}
+		return true
 	})
 
 	newEntries := n.entries.merge(gossip.Entries)

net/if.go

@@ -53,7 +53,7 @@ func EnsureInterfaceAndMcastRoute(ifaceName string) (*net.Interface, error) {
 	}
 	dest := net.IPv4(224, 0, 0, 0)
 	check := func(route netlink.Route) bool {
-		return route.LinkIndex == iface.Index && route.Dst != nil && route.Dst.IP.Equal(dest)
+		return route.Dst != nil && route.Dst.IP.Equal(dest)
 	}
 	// check for currently-existing route after subscribing, to avoid race
 	routes, err := netlink.RouteList(nil, netlink.FAMILY_V4)

plugin/ipam/driver.go

@@ -4,6 +4,7 @@ import (
 	"fmt"
 	"net"
 
+	"github.com/docker/libnetwork/discoverapi"
 	"github.com/docker/libnetwork/ipamapi"
 	"github.com/docker/libnetwork/netlabel"
 	godocker "github.com/fsouza/go-dockerclient"
@@ -67,3 +68,13 @@ func (i *ipam) ReleaseAddress(poolID string, address net.IP) error {
 	Log.Debugln("ReleaseAddress", poolID, address)
 	return i.weave.ReleaseIP(address.String())
 }
+
+// Functions required by ipamapi "contract" but not actually used.
+
+func (i *ipam) DiscoverNew(discoverapi.DiscoveryType, interface{}) error {
+	return nil
+}
+
+func (i *ipam) DiscoverDelete(discoverapi.DiscoveryType, interface{}) error {
+	return nil
+}

prog/plugin/main.go

@@ -106,9 +106,6 @@ func run(dockerClient *docker.Client, address, meshAddress, meshNetworkName, nam
 	select {
 	case sig := <-sigChan:
 		Log.Debugf("Caught signal %s; shutting down", sig)
-		if meshNetworkName != "" {
-			return dockerClient.Client.RemoveNetwork(meshNetworkName)
-		}
 		return nil
 	case err := <-endChan:
 		return err

proxy/proxy.go

@@ -132,7 +132,8 @@ func (proxy *Proxy) AttachExistingContainers() {
 			}
 			continue
 		}
-		if containerShouldAttach(container) && (container.State.Running || container.State.Paused) {
+		// The 'Running' check is purely an optimisation.
+		if containerShouldAttach(container) && container.State.Running {
 			proxy.attach(container, false)
 		}
 	}

router/fastdp.go

@@ -775,10 +775,10 @@ func (fwd *fastDatapathForwarder) Forward(key ForwardPacketKey) FlowOp {
 	defer fwd.lock.RUnlock()
 
 	if fwd.remoteAddr == nil {
-		// Returning nil would discard the packet, but also
+		// Returning a DiscardingFlowOp would discard the
-		// result in a flow rule, which we would have to
+		// packet, but also result in a flow rule, which we
-		// invalidate when we learn the remote IP.  So for
+		// would have to invalidate when we learn the remote
-		// now, just prevent flows.
+		// IP.  So for now, just prevent flows.
 		return vetoFlowCreationFlowOp{}
 	}
 
@@ -1086,6 +1086,10 @@ func (fastdp *FastDatapath) send(fops FlowOp, frame []byte, lock *fastDatapathLo
 		case vetoFlowCreationFlowOp:
 			createFlow = false
 		default:
+			if xfop.Discards() {
+				continue
+			}
+
 			// A foreign FlowOp (e.g. a sleeve forwarding
 			// FlowOp), so send the packet through the
 			// FlowOp interface, decoding the packet

router/flow.go

@@ -84,15 +84,12 @@ func (mfop *MultiFlowOp) Discards() bool {
 	return true
 }
 
+// Flatten out a FlowOp to eliminate any MultiFlowOps
 func FlattenFlowOp(fop FlowOp) []FlowOp {
 	return collectFlowOps(nil, fop)
 }
 
 func collectFlowOps(into []FlowOp, fop FlowOp) []FlowOp {
-	if fop == nil {
-		return into
-	}
-
 	if mfop, ok := fop.(*MultiFlowOp); ok {
 		for _, op := range mfop.ops {
 			into = collectFlowOps(into, op)

site/features.md

@@ -87,7 +87,12 @@ launched via the Docker
 [command-line interface](https://docs.docker.com/reference/commandline/cli/)
 or
 [remote API](https://docs.docker.com/reference/api/docker_remote_api/)
-are attached to the weave network before they begin execution.
+are attached to the weave network before they begin execution. To use
+the proxy, run
+
+    $ eval $(weave env)
+
+and then start containers as usual.
 
 Containers started in this way that subsequently restart, either by an
 explicit `docker restart` command or by Docker restart policy, are
@@ -100,6 +105,9 @@ named `weave` is created by `weave launch`, which you can use like this:
 
     $ docker run --net=weave -ti ubuntu
 
+> NB: The plugin is an *alternative* to the proxy, hence one should
+> *not* run `eval $(weave env)` beforehand.
+
 For more details see the [plugin documentation](plugin.html).
 
 ### <a name="addressing"></a>Address allocation

site/ipam.md

@@ -48,17 +48,6 @@ time, you can give the number of peers like this:
 
     host3$ weave launch --init-peer-count 3 $HOST2
 
-The consensus mechanism used to determine a majority transitions
-through three states: 'deferred', 'waiting' and 'achieved':
-
-* 'deferred' - no allocation requests or claims have been made yet;
-  consensus is deferred until then
-* 'waiting' - an attempt to achieve consensus is ongoing, triggered by
-  an allocation or claim request; allocations will block. This state
-  persists until a quorum of peers are able to communicate amongst
-  themselves successfully
-* 'achieved' - consensus achieved; allocations proceed normally
-
 ### More on `--init-peer-count`
 
 TL;DR: it isn't a problem to over-estimate by a bit, but if you supply
@@ -214,7 +203,7 @@ reports on the current status of the weave router and IP allocator:
 ...
 
        Service: ipam
-     Consensus: waiting(quorum: 2, known: 0)
+        Status: awaiting consensus (quorum: 2, known: 0)
          Range: 10.32.0.0-10.47.255.255
  DefaultSubnet: 10.32.0.0/12
 
@@ -225,4 +214,21 @@ The first section covers the router; see the [troubleshooting
 guide](troubleshooting.html#weave-status) for full details.
 
 The 'Service: ipam' section displays the consensus state as well as
-the total allocation range and default subnet.
+the total allocation range and default subnet. Columns are as follows:
+
+* 'Status' - allocator state
+    * 'idle' - no allocation requests or claims have been made yet;
+      consensus is deferred until then
+    * 'awaiting consensus' - an attempt to achieve consensus is
+      ongoing, triggered by an allocation or claim request;
+      allocations will block.  This state persists until a quorum of
+      peers are able to communicate amongst themselves successfully
+    * 'ready' - consensus achieved; allocations proceed normally
+    * 'waiting for IP range grant from peers' - peer has exhausted its
+      agreed portion of the range and is waiting to be granted some
+      more
+    * 'all IP ranges owned by unreachable peers' - peer has exhausted
+      its agreed portion of the range but cannot reach anyone to ask
+      for more
+* 'Range' - total allocation range set by `--ipalloc-range`
+* 'DefaultSubnet' - default subnet set by `--ipalloc-default-subnet`

site/plugin.md

@@ -18,13 +18,33 @@ Subsequently you can start containers with, e.g.
 
 on any of the hosts, and they can all communicate with each other.
 
+> WARNING: It is inadvisable to attach containers to the weave network
+> using both the Weave Docker Networking Plugin and
+> [Weave Docker API Proxy](proxy.html) simultaneously. Such containers
+> will end up with two weave network interfaces and two IP addresses,
+> which is rarely desirable. To ensure the proxy is not being used,
+> *do not run `eval $(weave env)`, or `docker $(weave config) ...`*.
+
 In order to use Weave's [Service Discovery](weavedns.html), you
 need to pass the additional arguments `--dns` and `-dns-search`, for
 which we provide a helper in the weave script:
 
     $ docker run --net=weave -h foo.weave.local $(weave dns-args) -tdi ubuntu
-    $ docker run --net=weave -h bar.weave.local $(weave dns-args) -ti ubuntu
+
-    # ping foo
+Here is a complete example of using the plugin for connectivity
+between two containers running on different hosts:
+
+    host1$ weave launch
+    host1$ docker run --net=weave -h foo.weave.local $(weave dns-args) -tdi ubuntu
+    
+    host2$ weave launch $HOST1
+    host2$ docker run --net=weave $(weave dns-args) -ti ubuntu
+    root@cb73d1a8aece:/# ping -c1 -q foo
+    PING foo (10.32.0.1) 56(84) bytes of data.
+    
+    --- foo ping statistics ---
+    1 packets transmitted, 1 received, 0% packet loss, time 0ms
+    rtt min/avg/max/mdev = 1.341/1.341/1.341/0.000 ms
 
 ## Under the hood
 

site/troubleshooting.md

@@ -62,7 +62,7 @@ $ weave status
  TrustedSubnets: none
 
         Service: ipam
-      Consensus: achieved
+         Status: ready
           Range: 10.32.0.0-10.47.255.255
   DefaultSubnet: 10.32.0.0/12
 
@@ -124,6 +124,13 @@ Proxy](proxy.html#troubleshooting).
 
 ### <a name="weave-status-connections"></a>List connections
 
+Connections between weave peers carry control traffic over TCP and
+data traffic over UDP. For a connection to be fully established, the
+TCP connection and UDP data path must be able to transmit information
+in both directions. Weave routers check this regularly with
+heartbeats. Failed connections are automatically retried, with an
+exponential back-off.
+
 Detailed information on the local weave router's connections can be
 obtained with `weave status connections`:
 

site/weavedns.md

@@ -18,7 +18,6 @@ hosts.
 * [Adding and removing extra DNS entries](#add-remove)
 * [Resolve weaveDNS entries from host](#resolve-weavedns-entries-from-host)
 * [Hot-swapping service containers](#hot-swapping)
-* [Retaining DNS entries when containers stop](#retain-stopped)
 * [Configuring a custom TTL](#ttl)
 * [Configuring the domain search path](#domain-search-path)
 * [Using a different local domain](#local-domain)

test/215_stale_dns_3_test.sh

@@ -0,0 +1,31 @@
+#! /bin/bash
+
+. ./config.sh
+
+start_suite "Check propagation of DNS entries when gossip is delayed"
+
+weave_on $HOST1 launch-router --no-discovery
+weave_on $HOST2 launch-router --no-discovery $HOST1
+weave_on $HOST3 launch-router --no-discovery $HOST2
+
+start_container $HOST1 --name=c1
+C1=$(container_ip $HOST1 c1)
+start_container_with_dns $HOST3 --name=c3
+
+assert_dns_record $HOST3 c3 c1.weave.local $C1
+
+# Stall the propagation of gossip, stop weave and kill the container
+run_on $HOST3 "sudo iptables -A INPUT -s $HOST2 -j DROP"
+
+weave_on $HOST1 stop-router
+docker_on $HOST1 rm -f c1
+
+weave_on $HOST1 launch-router --no-discovery $HOST3
+
+# Now re-enable gossip
+run_on $HOST3 "sudo iptables -D INPUT -s $HOST2 -j DROP"
+
+# Currently failing due to Mesh #28
+# assert_no_dns_record $HOST3 c3 c1.weave.local
+
+end_suite

test/690_proxy_config_test.sh

@@ -34,8 +34,8 @@ assert_raises "proxy docker_on $HOST1 ps"
 weave_on $HOST1 stop-proxy
 
 # Booting it over tls errors
-assert_raises "DOCKER_CLIENT_ARGS='--tls' weave_on $HOST1 launch-proxy" 1
+assert_raises "! DOCKER_CLIENT_ARGS='--tls' weave_on $HOST1 launch-proxy"
-assert_raises "DOCKER_CERT_PATH='./tls' DOCKER_TLS_VERIFY=1 weave_on $HOST1 launch-proxy" 1
+assert_raises "! DOCKER_CERT_PATH='./tls' DOCKER_TLS_VERIFY=1 weave_on $HOST1 launch-proxy"
 
 # Booting it with a specific -H overrides defaults
 weave_on $HOST1 launch-proxy -H tcp://0.0.0.0:12345

test/695_proxy_failure_modes_test.sh

@@ -6,7 +6,7 @@ start_suite "Proxy failure modes"
 
 # docker run should fail when weave router is not running
 weave_on $HOST1 launch-proxy
-assert_raises "proxy docker_on $HOST1 run --rm $SMALL_IMAGE true" 1
+assert_raises "! proxy docker_on $HOST1 run --rm $SMALL_IMAGE true"
 assert_raises "proxy docker_on $HOST1 run --rm $SMALL_IMAGE true 2>&1 1>/dev/null | grep 'Error response from daemon: weave container is not present. Have you launched it?'"
 
 end_suite

test/gce.sh

@@ -11,7 +11,7 @@ set -e
 : ${SSH_KEY_FILE:=$HOME/.ssh/gce_ssh_key}
 : ${PROJECT:=positive-cocoa-90213}
 : ${IMAGE:=ubuntu-14-04}
-: ${TEMPLATE_NAME:=test-template-9}
+: ${TEMPLATE_NAME:=test-template-10}
 : ${ZONE:=us-central1-a}
 : ${NUM_HOSTS:=5}
 SUFFIX=""

weave

@@ -536,7 +536,9 @@ create_bridge() {
         add_iptables_rule nat POSTROUTING -j WEAVE
     else
         if [ -n "$LAUNCHING_ROUTER" ] ; then
-            if [ "$BRIDGE_TYPE" = bridge -a -z "$WEAVE_NO_FASTDP" ] ; then
+            if [ "$BRIDGE_TYPE" = bridge -a -z "$WEAVE_NO_FASTDP" ] &&
+                util_op create-datapath $DATAPATH 2>/dev/null &&
+                util_op delete-datapath $DATAPATH 2>/dev/null ; then
                 cat <<EOF >&1
 WEAVE_NO_FASTDP is not set, but there is already a bridge present of
 the wrong type for fast datapath.  Please do 'weave reset' to remove