Skip to content

Commit

Permalink
Poll synctracker HasSynced() during startup (#6614)
Browse files Browse the repository at this point in the history
The "upstream" informer trackers do not always return HasSynced() == true
immediately, even if we have already processed all events the informer
dispatched us.  Change to polling so that we can progress also in that case.

Signed-off-by: Tero Saarni <tero.saarni@est.tech>
  • Loading branch information
tsaarni authored Oct 23, 2024
1 parent 9179db9 commit 96dc403
Show file tree
Hide file tree
Showing 2 changed files with 16 additions and 15 deletions.
1 change: 1 addition & 0 deletions changelogs/unreleased/6614-tsaarni-small.md
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
Fixed a bug where follower Contour instance occasionally got stuck in a non-ready state when using `--watch-namespaces` flag.
30 changes: 15 additions & 15 deletions internal/contour/handler.go
Original file line number Diff line number Diff line change
Expand Up @@ -146,19 +146,22 @@ func (e *EventHandler) Start(ctx context.Context) error {
// run to allow the holdoff timer to batch the updates from
// the API informers.
lastDAGRebuild = time.Now()

// initialSyncPollPeriod defines the duration to wait between polling attempts during the initial informer synchronization.
initialSyncPollPeriod = 100 * time.Millisecond

// initialSyncPollTicker is the ticker that will trigger the periodic polling.
initialSyncPollTicker = time.NewTicker(initialSyncPollPeriod)

// initialSyncPoll is the channel that will receive a signal when to poll the initial informer synchronization status.
initialSyncPoll = initialSyncPollTicker.C
)

reset := func() (v int) {
v, outstanding = outstanding, 0
return
}

// It may be that there are no resources at all to process in watched namespaces.
// Initial (empty) DAG build is not needed and we can mark it as built immediately to allow the XDS server to start.
if e.syncTracker.HasSynced() {
e.initialDagBuilt.Store(true)
}

for {
// In the main loop one of four things can happen.
// 1. We're waiting for an event on op, stop, or pending, noting that
Expand Down Expand Up @@ -196,12 +199,6 @@ func (e *EventHandler) Start(ctx context.Context) error {
if updateOpAdd, ok := op.(opAdd); ok {
if updateOpAdd.isInInitialList {
e.syncTracker.Finished()

// If this was the last event in the initial list but none of the events triggered DAG rebuild,
// then we can mark the (empty) DAG as built to allow the XDS server to start.
if e.syncTracker.HasSynced() && timer == nil {
e.initialDagBuilt.Store(true)
}
}
}
case <-pending:
Expand All @@ -220,16 +217,19 @@ func (e *EventHandler) Start(ctx context.Context) error {
latestDAG := e.builder.Build()
e.observer.OnChange(latestDAG)

// Allow XDS server to start (if it hasn't already).
e.initialDagBuilt.Store(true)

// Update the status on objects.
for _, upd := range latestDAG.StatusCache.GetStatusUpdates() {
e.statusUpdater.Send(upd)
}

e.incSequence()
lastDAGRebuild = time.Now()
case <-initialSyncPoll:
if e.syncTracker.HasSynced() {
// Informer caches are synced, stop the polling and allow xDS server to start.
initialSyncPollTicker.Stop()
e.initialDagBuilt.Store(true)
}
case <-ctx.Done():
// shutdown
return nil
Expand Down

0 comments on commit 96dc403

Please sign in to comment.