From ed7b7de5070722fb01498b4ddb987ca16644a304 Mon Sep 17 00:00:00 2001
From: Tero Saarni <tero.saarni@est.tech>
Date: Fri, 16 Aug 2024 13:05:45 +0300
Subject: [PATCH] Poll synctracker HasSynced() during startup

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>
---
 internal/contour/handler.go | 29 ++++++++++-------------------
 1 file changed, 10 insertions(+), 19 deletions(-)

diff --git a/internal/contour/handler.go b/internal/contour/handler.go
index a66d590f158..368af1d331b 100644
--- a/internal/contour/handler.go
+++ b/internal/contour/handler.go
@@ -135,11 +135,14 @@ func (e *EventHandler) Start(ctx context.Context) error {
 		// yet included in a DAG rebuild.
 		outstanding int
 
-		// timer holds the timer which will expire after e.HoldoffDelay
-		timer *time.Timer
+		// Polling interval during startup, for the initial informer synchronization.
+		initialSyncPollPeriod = 100 * time.Millisecond
+
+		// timer triggers delayed DAG rebuilds.
+		timer *time.Timer = time.NewTimer(initialSyncPollPeriod)
 
 		// pending is a reference to the current timer's channel.
-		pending <-chan time.Time
+		pending <-chan time.Time = timer.C
 
 		// lastDAGRebuild holds the last time rebuildDAG was called.
 		// lastDAGRebuild is seeded to the current time on entry to
@@ -153,12 +156,6 @@ func (e *EventHandler) Start(ctx context.Context) error {
 		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
@@ -196,21 +193,15 @@ 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)
-					}
+					// Note that we don't need to check syncTracker.HasSynced() here, as it sometimes returns false
+					// for a short period after the initial list is processed.
 				}
 			}
 		case <-pending:
-			// Ensure informer caches are synced.
-			// Schedule a retry for dag rebuild if cache is not synced yet.
+			// Ensure informer caches are synced, schedule a retry if cache is not synced yet.
 			// Note that we can't block and wait for the cache sync as it depends on progress of this loop.
 			if !e.syncTracker.HasSynced() {
-				e.Info("skipping dag rebuild as cache is not synced")
-				timer.Reset(e.holdoffDelay)
+				timer.Reset(initialSyncPollPeriod)
 				break
 			}