From 765ba43438f91bf75773e9de358dbf58f34c5d87 Mon Sep 17 00:00:00 2001 From: Arseny Sher Date: Fri, 31 Jan 2025 13:33:24 +0300 Subject: [PATCH] Allow pageserver unreachable errors in test_scrubber_tenant_snapshot (#10585) ## Problem test_scrubber_tenant_snapshot restarts pageservers, but log validation fails tests on any non white listed storcon warnings, making the test flaky. ## Summary of changes Allow warns like 2025-01-29T12:37:42.622179Z WARN reconciler{seq=1 tenant_id=2011077aea9b4e8a60e8e8a19407634c shard_id=0004}: Call to node 2 (localhost:15352) management API failed, will retry (attempt 1): receive body: error sending request for url (http://localhost:15352/v1/tenant/2011077aea9b4e8a60e8e8a19407634c-0004/location_config): client error (Connect) ref https://github.com/neondatabase/neon/issues/10462 --- test_runner/regress/test_storage_scrubber.py | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/test_runner/regress/test_storage_scrubber.py b/test_runner/regress/test_storage_scrubber.py index 1304d302b7..7e92cc01cd 100644 --- a/test_runner/regress/test_storage_scrubber.py +++ b/test_runner/regress/test_storage_scrubber.py @@ -32,6 +32,12 @@ def test_scrubber_tenant_snapshot(neon_env_builder: NeonEnvBuilder, shard_count: neon_env_builder.num_pageservers = shard_count if shard_count is not None else 1 env = neon_env_builder.init_start() + # We restart pageserver(s), which will cause storage storage controller + # requests to fail and warn. + env.storage_controller.allowed_errors.append(".*management API still failed.*") + env.storage_controller.allowed_errors.append( + ".*Reconcile error.*error sending request for url.*" + ) tenant_id = env.initial_tenant timeline_id = env.initial_timeline branch = "main"