From e018cac1f714626b1dca7eeab8eab0951cbfaed2 Mon Sep 17 00:00:00 2001 From: John Spray Date: Tue, 30 Apr 2024 18:00:24 +0100 Subject: [PATCH] tests: tweak log allow list in test_sharding_split_failures (#7549) ## Problem This test became flaky recently with failures like: ``` AssertionError: Log errors on storage_controller: (129, '2024-04-29T16:41:03.591506Z ERROR request{method=PUT path=/control/v1/tenant/b38c0447fbdbcf4e1c023f00b0f7c221/shard_split request_id=34df4975-2ef3-4ed8-b167-2956650e365c}: Error processing HTTP request: InternalServerError(Reconcile error on shard b38c0447fbdbcf4e1c023f00b0f7c221-0002: Cancelled\n') ``` Likely due to #7508 changing how errors are reported from Reconcilers. ## Summary of changes - Tolerate `Reconcile error.*Cancelled` log errors --- test_runner/regress/test_sharding.py | 2 ++ 1 file changed, 2 insertions(+) diff --git a/test_runner/regress/test_sharding.py b/test_runner/regress/test_sharding.py index 101d2620b0..bae5945338 100644 --- a/test_runner/regress/test_sharding.py +++ b/test_runner/regress/test_sharding.py @@ -928,6 +928,8 @@ def test_sharding_split_failures( ".*Reconcile error: receive body: error sending request for url.*", # Node offline cases will fail inside reconciler when detaching secondaries ".*Reconcile error on shard.*: receive body: error sending request for url.*", + # Node offline cases may eventually cancel reconcilers when the heartbeater realizes nodes are offline + ".*Reconcile error.*Cancelled.*", # While parent shard's client is stopped during split, flush loop updating LSNs will emit this warning ".*Failed to schedule metadata upload after updating disk_consistent_lsn.*", ]