Merge #108357 #108583

108357: jobs: fix mixed-version jobs flake r=knz a=adityamaru Similar to #107570 this is a short term fix for when an a query is executed with an AS OF SYSTEM TIME picks a transaction timestamp before the job_info migration has run. In which case parts of the jobs infrastructure will attempt to query the job_info column even though it doesn't exist at the transaction's timestamp. As a short term fix, when we encounter an UndefinedObject error for the job_info table we generate a synthetic retryable error so that the txn is pushed to a higher timestamp at which the upgrade will have completed and the job_info table will be visible. The longer term fix is being tracked in #106764. On master I can no longer reproduce the failure in #105032 but on 23.1 with this change I can successfully run 30 iterations of the test on a seed (-8690666577594439584) which previously saw occurrences of this flake. Fixes: #103239 Fixes: #105032 Release note: None 108583: rangefeed: deflake `TestBudgetReleaseOnOneStreamError` r=erikgrinaker a=erikgrinaker The test could fail with `REASON_SLOW_CONSUMER` if the registration goroutine did not drain the queue in time (1 ms). Increase the timeout. Resolves #108555. Epic: none Release note: None Co-authored-by: adityamaru <[email protected]> Co-authored-by: Erik Grinaker <[email protected]>
cockroachdb · Aug 12, 2023 · 9184ffb · 9184ffb
3 parents a37cff6 + 79cc2ea + e35eb38
commit 9184ffb
Show file tree

Hide file tree

Showing 2 changed files with 5 additions and 2 deletions.
diff --git a/pkg/jobs/job_info_storage.go b/pkg/jobs/job_info_storage.go
@@ -237,7 +237,10 @@ func (i InfoStorage) Write(ctx context.Context, infoKey string, value []byte) er
 	if value == nil {
 		return errors.AssertionFailedf("missing value (infoKey %q)", infoKey)
 	}
-	return i.write(ctx, infoKey, value)
+	if err := i.write(ctx, infoKey, value); err != nil {
+		return MaybeGenerateForcedRetryableError(ctx, i.txn.KV(), err)
+	}
+	return nil
 }
 
 // Delete removes the info record for the provided infoKey.

diff --git a/pkg/kv/kvserver/rangefeed/processor_test.go b/pkg/kv/kvserver/rangefeed/processor_test.go
@@ -1301,7 +1301,7 @@ func TestBudgetReleaseOnOneStreamError(t *testing.T) {
 		PushTxnsInterval: pushTxnInterval,
 		PushTxnsAge:      pushTxnAge,
 		EventChanCap:     channelCapacity,
-		EventChanTimeout: time.Millisecond,
+		EventChanTimeout: 100 * time.Millisecond, // enough time for registration to process events
 		MemBudget:        fb,
 		Metrics:          NewMetrics(),
 	})