From: Sage Weil Date: Thu, 6 Jul 2017 21:58:16 +0000 (-0400) Subject: qa: whitelist health warnings X-Git-Tag: v12.1.1~58^2~7 X-Git-Url: http://git-server-git.apps.pok.os.sepia.ceph.com/?a=commitdiff_plain;h=93de19adcf1233ce4c68f1253e0b9abef6d97a9d;p=ceph.git qa: whitelist health warnings Signed-off-by: Sage Weil --- diff --git a/qa/suites/rados/basic-luminous/scrub_test.yaml b/qa/suites/rados/basic-luminous/scrub_test.yaml index 0d8c7a3759f..d87f5bfdd35 100644 --- a/qa/suites/rados/basic-luminous/scrub_test.yaml +++ b/qa/suites/rados/basic-luminous/scrub_test.yaml @@ -15,12 +15,12 @@ overrides: - 'attr name mistmatch' - 'deep-scrub 1 missing, 0 inconsistent objects' - 'failed to pick suitable auth object' - - HEALTH_WARN OSDMAP_FLAGS - - HEALTH_WARN OSD_ - - HEALTH_WARN PG_ - - HEALTH_ERR PG_ - - HEALTH_ERR OSD_SCRUB_ERRORS - - HEALTH_WARN TOO_FEW_PGS + - overall HEALTH_ + - (OSDMAP_FLAGS) + - (OSD_ + - (PG_ + - (OSD_SCRUB_ERRORS) + - (TOO_FEW_PGS) conf: osd: osd deep scrub update digest min age: 0 diff --git a/qa/suites/rados/basic/tasks/rados_api_tests.yaml b/qa/suites/rados/basic/tasks/rados_api_tests.yaml index b66423988d7..1d77207d2b4 100644 --- a/qa/suites/rados/basic/tasks/rados_api_tests.yaml +++ b/qa/suites/rados/basic/tasks/rados_api_tests.yaml @@ -3,6 +3,11 @@ overrides: log-whitelist: - reached quota - wrongly marked me down + - overall HEALTH_ + - (POOL_FULL) + - (SMALLER_PGP_NUM) + - (CACHE_POOL_NO_HIT_SET) + - (CACHE_POOL_NEAR_FULL) tasks: - workunit: clients: diff --git a/qa/suites/rados/basic/tasks/rados_python.yaml b/qa/suites/rados/basic/tasks/rados_python.yaml index d8b332b343d..aa22ccd16e1 100644 --- a/qa/suites/rados/basic/tasks/rados_python.yaml +++ b/qa/suites/rados/basic/tasks/rados_python.yaml @@ -2,6 +2,11 @@ overrides: ceph: log-whitelist: - wrongly marked me down + - overall HEALTH_ + - (OSDMAP_FLAGS) + - (PG_ + - (OSD_ + - (OBJECT_ tasks: - workunit: clients: diff --git a/qa/suites/rados/basic/tasks/rados_stress_watch.yaml b/qa/suites/rados/basic/tasks/rados_stress_watch.yaml index 0fd43cf6ac7..ded794c1741 100644 --- a/qa/suites/rados/basic/tasks/rados_stress_watch.yaml +++ b/qa/suites/rados/basic/tasks/rados_stress_watch.yaml @@ -1,8 +1,9 @@ -override: +overrides: ceph: log-whitelist: - - HEALTH_WARN OSD_CACHE_NO_HIT_SET - - HEALTH_WARN TOO_FEW_PGS + - overall HEALTH_ + - (CACHE_POOL_NO_HIT_SET) + - (TOO_FEW_PGS) tasks: - workunit: clients: diff --git a/qa/suites/rados/basic/tasks/repair_test.yaml b/qa/suites/rados/basic/tasks/repair_test.yaml index 41a5642f15c..8401c1a303f 100644 --- a/qa/suites/rados/basic/tasks/repair_test.yaml +++ b/qa/suites/rados/basic/tasks/repair_test.yaml @@ -17,9 +17,10 @@ overrides: - 'size 1 != size' - attr name mismatch - Regular scrub request, losing deep-scrub details - - HEALTH_WARN OSDMAP_FLAGS - - HEALTH_WARN OSD_ - - HEALTH_WARN PG_ + - overall HEALTH_ + - (OSDMAP_FLAGS) + - (OSD_ + - (PG_ conf: osd: filestore debug inject read err: true diff --git a/qa/suites/rados/mgr/tasks/failover.yaml b/qa/suites/rados/mgr/tasks/failover.yaml index be2c623e951..fd5eb8515c9 100644 --- a/qa/suites/rados/mgr/tasks/failover.yaml +++ b/qa/suites/rados/mgr/tasks/failover.yaml @@ -6,8 +6,9 @@ tasks: # to invoke e.g. pg dump during teardown. wait-for-scrub: false log-whitelist: - - HEALTH_WRN MGR_DOWN - - HEALTH_ERR MGR_DOWN + - overall HEALTH_ + - (MGR_DOWN) + - (PG_ - cephfs_test_runner: modules: - tasks.mgr.test_failover diff --git a/qa/suites/rados/monthrash/thrashers/force-sync-many.yaml b/qa/suites/rados/monthrash/thrashers/force-sync-many.yaml index c7473bd48b2..38570fcf615 100644 --- a/qa/suites/rados/monthrash/thrashers/force-sync-many.yaml +++ b/qa/suites/rados/monthrash/thrashers/force-sync-many.yaml @@ -1,8 +1,9 @@ overrides: ceph: log-whitelist: - - HEALTH_WARN MON_DOWN - - HEALTH_WARN TOO_FEW_PGS + - overall HEALTH_ + - (MON_DOWN) + - (TOO_FEW_PGS) tasks: - mon_thrash: revive_delay: 90 diff --git a/qa/suites/rados/monthrash/thrashers/many.yaml b/qa/suites/rados/monthrash/thrashers/many.yaml index 3755f8b1239..e940c42ad74 100644 --- a/qa/suites/rados/monthrash/thrashers/many.yaml +++ b/qa/suites/rados/monthrash/thrashers/many.yaml @@ -1,7 +1,8 @@ overrides: ceph: log-whitelist: - - HEALTH_WARN MON_DOWN + - overall HEALTH_ + - (MON_DOWN) conf: osd: mon client ping interval: 4 diff --git a/qa/suites/rados/monthrash/thrashers/one.yaml b/qa/suites/rados/monthrash/thrashers/one.yaml index 99b66ec242f..92c9eb3a808 100644 --- a/qa/suites/rados/monthrash/thrashers/one.yaml +++ b/qa/suites/rados/monthrash/thrashers/one.yaml @@ -1,7 +1,8 @@ overrides: ceph: log-whitelist: - - HEALTH_WARN MON_DOWN + - overall HEALTH_ + - (MON_DOWN) tasks: - mon_thrash: revive_delay: 20 diff --git a/qa/suites/rados/monthrash/thrashers/sync-many.yaml b/qa/suites/rados/monthrash/thrashers/sync-many.yaml index 25e40e9b3fb..68020cd6651 100644 --- a/qa/suites/rados/monthrash/thrashers/sync-many.yaml +++ b/qa/suites/rados/monthrash/thrashers/sync-many.yaml @@ -1,7 +1,8 @@ overrides: ceph: log-whitelist: - - HEALTH_WARN MON_DOWN + - overall HEALTH_ + - (MON_DOWN) conf: mon: paxos min: 10 diff --git a/qa/suites/rados/monthrash/thrashers/sync.yaml b/qa/suites/rados/monthrash/thrashers/sync.yaml index 958b0822493..b07f8b511f6 100644 --- a/qa/suites/rados/monthrash/thrashers/sync.yaml +++ b/qa/suites/rados/monthrash/thrashers/sync.yaml @@ -1,7 +1,8 @@ overrides: ceph: log-whitelist: - - HEALTH_WARN MON_DOWN + - overall HEALTH_ + - (MON_DOWN) conf: mon: paxos min: 10 diff --git a/qa/suites/rados/monthrash/workloads/rados_api_tests.yaml b/qa/suites/rados/monthrash/workloads/rados_api_tests.yaml index b536557fdba..0834f9c34c1 100644 --- a/qa/suites/rados/monthrash/workloads/rados_api_tests.yaml +++ b/qa/suites/rados/monthrash/workloads/rados_api_tests.yaml @@ -2,6 +2,12 @@ overrides: ceph: log-whitelist: - reached quota + - overall HEALTH_ + - (CACHE_POOL_NO_HIT_SET) + - (POOL_FULL) + - (REQUEST_SLOW) + - (MON_DOWN) + - (PG_ conf: global: debug objecter: 20 diff --git a/qa/suites/rados/monthrash/workloads/rados_mon_workunits.yaml b/qa/suites/rados/monthrash/workloads/rados_mon_workunits.yaml index 31465cffe71..86818b58dff 100644 --- a/qa/suites/rados/monthrash/workloads/rados_mon_workunits.yaml +++ b/qa/suites/rados/monthrash/workloads/rados_mon_workunits.yaml @@ -2,6 +2,9 @@ overrides: ceph: log-whitelist: - wrongly marked me down + - overall HEALTH_ + - (PG_ + - (MON_DOWN) tasks: - workunit: clients: diff --git a/qa/suites/rados/multimon/tasks/mon_clock_no_skews.yaml b/qa/suites/rados/multimon/tasks/mon_clock_no_skews.yaml index 1a504f14714..ec761e2955e 100644 --- a/qa/suites/rados/multimon/tasks/mon_clock_no_skews.yaml +++ b/qa/suites/rados/multimon/tasks/mon_clock_no_skews.yaml @@ -5,6 +5,7 @@ tasks: - slow request - .*clock.*skew.* - clocks not synchronized - - HEALTH_WARN MON_CLOCK_SKEW + - overall HEALTH_ + - (MON_CLOCK_SKEW) - mon_clock_skew_check: expect-skew: false diff --git a/qa/suites/rados/multimon/tasks/mon_clock_with_skews.yaml b/qa/suites/rados/multimon/tasks/mon_clock_with_skews.yaml index 87d1d9f13d7..2bba607152e 100644 --- a/qa/suites/rados/multimon/tasks/mon_clock_with_skews.yaml +++ b/qa/suites/rados/multimon/tasks/mon_clock_with_skews.yaml @@ -9,6 +9,7 @@ tasks: - slow request - .*clock.*skew.* - clocks not synchronized - - HEALTH_WARN MON_CLOCK_SKEW + - overall HEALTH_ + - (MON_CLOCK_SKEW) - mon_clock_skew_check: expect-skew: true diff --git a/qa/suites/rados/multimon/tasks/mon_recovery.yaml b/qa/suites/rados/multimon/tasks/mon_recovery.yaml index 94721ea53a4..4234bf73e68 100644 --- a/qa/suites/rados/multimon/tasks/mon_recovery.yaml +++ b/qa/suites/rados/multimon/tasks/mon_recovery.yaml @@ -1,4 +1,7 @@ tasks: - install: - ceph: + log-whitelist: + - overall HEALTH_ + - (MON_DOWN) - mon_recovery: diff --git a/qa/suites/rados/objectstore/ceph_objectstore_tool.yaml b/qa/suites/rados/objectstore/ceph_objectstore_tool.yaml index 3dac70a2035..2001faa3fe8 100644 --- a/qa/suites/rados/objectstore/ceph_objectstore_tool.yaml +++ b/qa/suites/rados/objectstore/ceph_objectstore_tool.yaml @@ -13,10 +13,10 @@ tasks: osd max object name len: 460 osd max object namespace len: 64 log-whitelist: - - HEALTH_WARN OSDMAP_FLAGS - - HEALTH_WARN OSD_ - - HEALTH_WARN PG_ - - HEALTH_ERR PG_ - - HEALTH_WARN TOO_FEW_PGS + - overall HEALTH_ + - (OSDMAP_FLAGS) + - (OSD_ + - (PG_ + - (TOO_FEW_PGS) - ceph_objectstore_tool: objects: 20 diff --git a/qa/suites/rados/rest/mgr-restful.yaml b/qa/suites/rados/rest/mgr-restful.yaml index 571857c2511..5dd16fda288 100644 --- a/qa/suites/rados/rest/mgr-restful.yaml +++ b/qa/suites/rados/rest/mgr-restful.yaml @@ -3,6 +3,9 @@ roles: tasks: - install: - ceph: + log-whitelist: + - overall HEALTH_ + - (MGR_DOWN) - exec: mon.a: - ceph config-key put mgr/restful/x/server_addr 127.0.0.1 diff --git a/qa/suites/rados/singleton-bluestore/all/cephtool.yaml b/qa/suites/rados/singleton-bluestore/all/cephtool.yaml index f03bb4e69ae..7e1a1f7b389 100644 --- a/qa/suites/rados/singleton-bluestore/all/cephtool.yaml +++ b/qa/suites/rados/singleton-bluestore/all/cephtool.yaml @@ -21,11 +21,11 @@ tasks: - must scrub before tier agent can activate - failsafe engaged, dropping updates - failsafe disengaged, no longer dropping updates - - HEALTH_WARN OSDMAP_FLAGS - - HEALTH_WARN OSD_ - - HEALTH_WARN PG_ - - HEALTH_ERR PG_ - - HEALTH_WARN SMALLER_PG_NUM + - overall HEALTH_ + - (OSDMAP_FLAGS) + - (OSD_ + - (PG_ + - (SMALLER_PG_NUM) - workunit: clients: all: diff --git a/qa/suites/rados/singleton-nomsgr/all/admin_socket_output.yaml b/qa/suites/rados/singleton-nomsgr/all/admin_socket_output.yaml index 31c904d2ed7..3aaca875940 100644 --- a/qa/suites/rados/singleton-nomsgr/all/admin_socket_output.yaml +++ b/qa/suites/rados/singleton-nomsgr/all/admin_socket_output.yaml @@ -5,9 +5,10 @@ overrides: log-whitelist: - MDS in read-only mode - force file system read-only - - HEALTH_WARN OSD_FLAGS - - HEALTH_ERR OSD_FULL - - HEALTH_WARN MDS_READ_ONLY + - overall HEALTH_ + - (OSDMAP_FLAGS) + - (OSD_FULL) + - (MDS_READ_ONLY) tasks: - install: - ceph: diff --git a/qa/suites/rados/singleton-nomsgr/all/cache-fs-trunc.yaml b/qa/suites/rados/singleton-nomsgr/all/cache-fs-trunc.yaml index 826a4ea21e3..ac64165aaaa 100644 --- a/qa/suites/rados/singleton-nomsgr/all/cache-fs-trunc.yaml +++ b/qa/suites/rados/singleton-nomsgr/all/cache-fs-trunc.yaml @@ -4,7 +4,8 @@ tasks: - install: - ceph: log-whitelist: - - HEALTH_WARN OSD_CACHE_NO_HIT_SET + - overall HEALTH_ + - (CACHE_POOL_NO_HIT_SET) conf: global: osd max object name len: 460 diff --git a/qa/suites/rados/singleton-nomsgr/all/export-after-evict.yaml b/qa/suites/rados/singleton-nomsgr/all/export-after-evict.yaml index e0badd4d3af..1b777ab0f00 100644 --- a/qa/suites/rados/singleton-nomsgr/all/export-after-evict.yaml +++ b/qa/suites/rados/singleton-nomsgr/all/export-after-evict.yaml @@ -8,6 +8,9 @@ roles: tasks: - install: - ceph: + log-whitelist: + - overall HEALTH_ + - (CACHE_POOL_NO_HIT_SET) conf: global: osd max object name len: 460 diff --git a/qa/suites/rados/singleton-nomsgr/all/full-tiering.yaml b/qa/suites/rados/singleton-nomsgr/all/full-tiering.yaml index 38d602aa2db..5eb42f4dd63 100644 --- a/qa/suites/rados/singleton-nomsgr/all/full-tiering.yaml +++ b/qa/suites/rados/singleton-nomsgr/all/full-tiering.yaml @@ -5,8 +5,10 @@ overrides: ceph: log-whitelist: - is full - - HEALTH_ERR POOL_FULL - - HEALTH_WARN POOL_NEAR_FULL + - overall HEALTH_ + - (POOL_FULL) + - (POOL_NEAR_FULL) + - (CACHE_POOL_NO_HIT_SET) tasks: - install: - ceph: diff --git a/qa/suites/rados/singleton-nomsgr/all/health-warnings.yaml b/qa/suites/rados/singleton-nomsgr/all/health-warnings.yaml index 7f55a885856..749bd8d39c3 100644 --- a/qa/suites/rados/singleton-nomsgr/all/health-warnings.yaml +++ b/qa/suites/rados/singleton-nomsgr/all/health-warnings.yaml @@ -10,9 +10,10 @@ tasks: osd max object namespace len: 64 log-whitelist: - wrongly marked me down - - HEALTH_WARN OSDMAP_FLAGS - - HEALTH_WARN OSD_ - - HEALTH_WARN PG_ + - overall HEALTH_ + - (OSDMAP_FLAGS) + - (OSD_ + - (PG_ - workunit: clients: all: diff --git a/qa/suites/rados/singleton-nomsgr/all/multi-backfill-reject.yaml b/qa/suites/rados/singleton-nomsgr/all/multi-backfill-reject.yaml index b73899738e6..cadf3044a1d 100644 --- a/qa/suites/rados/singleton-nomsgr/all/multi-backfill-reject.yaml +++ b/qa/suites/rados/singleton-nomsgr/all/multi-backfill-reject.yaml @@ -11,6 +11,11 @@ roles: tasks: - install: - ceph: + log-whitelist: + - overall HEALTH_ + - (PG_ + - (OSD_ + - (OBJECT_ conf: osd: osd debug reject backfill probability: .3 diff --git a/qa/suites/rados/singleton-nomsgr/all/valgrind-leaks.yaml b/qa/suites/rados/singleton-nomsgr/all/valgrind-leaks.yaml index e5d5702a32b..65af1a2e817 100644 --- a/qa/suites/rados/singleton-nomsgr/all/valgrind-leaks.yaml +++ b/qa/suites/rados/singleton-nomsgr/all/valgrind-leaks.yaml @@ -7,6 +7,9 @@ overrides: flavor: notcmalloc debuginfo: true ceph: + log-whitelist: + - overall HEALTH_ + - (PG_ conf: global: osd heartbeat grace: 40 diff --git a/qa/suites/rados/singleton/all/divergent_priors.yaml b/qa/suites/rados/singleton/all/divergent_priors.yaml index ac0f713e952..f15fb889615 100644 --- a/qa/suites/rados/singleton/all/divergent_priors.yaml +++ b/qa/suites/rados/singleton/all/divergent_priors.yaml @@ -13,10 +13,11 @@ openstack: overrides: ceph: log-whitelist: - - HEALTH_WARN OSDMAP_FLAGS - - HEALTH_WARN OSD_ - - HEALTH_WARN PG_ - - HEALTH_WARN DEGRADED_OBJECTS + - overall HEALTH_ + - (OSDMAP_FLAGS) + - (OSD_ + - (PG_ + - (OBJECT_DEGRADED) conf: osd: debug osd: 5 diff --git a/qa/suites/rados/singleton/all/divergent_priors2.yaml b/qa/suites/rados/singleton/all/divergent_priors2.yaml index 6c00496eb1f..90d8b1838b9 100644 --- a/qa/suites/rados/singleton/all/divergent_priors2.yaml +++ b/qa/suites/rados/singleton/all/divergent_priors2.yaml @@ -13,10 +13,11 @@ openstack: overrides: ceph: log-whitelist: - - HEALTH_WARN OSDMAP_FLAGS - - HEALTH_WARN OSD_ - - HEALTH_WARN PG_ - - HEALTH_WARN DEGRADED_OBJECTS + - overall HEALTH_ + - (OSDMAP_FLAGS) + - (OSD_ + - (PG_ + - (OBJECT_DEGRADED) conf: osd: debug osd: 5 diff --git a/qa/suites/rados/singleton/all/dump-stuck.yaml b/qa/suites/rados/singleton/all/dump-stuck.yaml index 26b8c7c1d38..f3900e121fe 100644 --- a/qa/suites/rados/singleton/all/dump-stuck.yaml +++ b/qa/suites/rados/singleton/all/dump-stuck.yaml @@ -12,7 +12,8 @@ tasks: - ceph: log-whitelist: - wrongly marked me down - - HEALTH_WARN OSDMAP_FLAGS - - HEALTH_WARN OSD_ - - HEALTH_WARN PG_ + - overall HEALTH_ + - (OSDMAP_FLAGS) + - (OSD_ + - (PG_ - dump_stuck: diff --git a/qa/suites/rados/singleton/all/ec-lost-unfound.yaml b/qa/suites/rados/singleton/all/ec-lost-unfound.yaml index 324bc5b9ee5..e095fd0d586 100644 --- a/qa/suites/rados/singleton/all/ec-lost-unfound.yaml +++ b/qa/suites/rados/singleton/all/ec-lost-unfound.yaml @@ -16,9 +16,9 @@ tasks: - ceph: log-whitelist: - objects unfound and apparently lost - - HEALTH_WARN OSDMAP_FLAGS - - HEALTH_WARN OSD_ - - HEALTH_WARN PG_ - - HEALTH_WARN UNFOUND_OBJECTS - - HEALTH_WARN DEGRADED_OBJECTS + - overall HEALTH_ + - (OSDMAP_FLAGS) + - (OSD_ + - (PG_ + - (OBJECT_ - ec_lost_unfound: diff --git a/qa/suites/rados/singleton/all/lost-unfound-delete.yaml b/qa/suites/rados/singleton/all/lost-unfound-delete.yaml index aae7ff82364..5502b5c9b0f 100644 --- a/qa/suites/rados/singleton/all/lost-unfound-delete.yaml +++ b/qa/suites/rados/singleton/all/lost-unfound-delete.yaml @@ -15,11 +15,9 @@ tasks: - ceph: log-whitelist: - objects unfound and apparently lost - - HEALTH_WARN OSDMAP_FLAGS - - HEALTH_WARN OSD_ - - HEALTH_WARN PG_ - - HEALTH_ERR PG_ - - HEALTH_WARN UNFOUND_OBJECTS - - HEALTH_WARN MISPLACED_OBJECTS - - HEALTH_WARN DEGRADED_OBJECTS + - overall HEALTH_ + - (OSDMAP_FLAGS) + - (OSD_ + - (PG_ + - (OBJECT_ - rep_lost_unfound_delete: diff --git a/qa/suites/rados/singleton/all/lost-unfound.yaml b/qa/suites/rados/singleton/all/lost-unfound.yaml index 9458373a421..bb0bb2c0afe 100644 --- a/qa/suites/rados/singleton/all/lost-unfound.yaml +++ b/qa/suites/rados/singleton/all/lost-unfound.yaml @@ -15,11 +15,9 @@ tasks: - ceph: log-whitelist: - objects unfound and apparently lost - - HEALTH_WARN OSDMAP_FLAGS - - HEALTH_WARN OSD_ - - HEALTH_WARN PG_ - - HEALTH_ERR PG_ - - HEALTH_WARN UNFOUND_OBJECTS - - HEALTH_WARN MISPLACED_OBJECTS - - HEALTH_WARN DEGRADED_OBJECTS + - overall HEALTH_ + - (OSDMAP_FLAGS) + - (OSD_ + - (PG_ + - (OBJECT_ - lost_unfound: diff --git a/qa/suites/rados/singleton/all/mon-thrasher.yaml b/qa/suites/rados/singleton/all/mon-thrasher.yaml index 1b4622998f9..66a1e905f3b 100644 --- a/qa/suites/rados/singleton/all/mon-thrasher.yaml +++ b/qa/suites/rados/singleton/all/mon-thrasher.yaml @@ -13,6 +13,10 @@ openstack: tasks: - install: - ceph: + log-whitelist: + - overall HEALTH_ + - (MON_DOWN) + - (PG_ - mon_thrash: revive_delay: 20 thrash_delay: 1 diff --git a/qa/suites/rados/singleton/all/osd-backfill.yaml b/qa/suites/rados/singleton/all/osd-backfill.yaml index c30bb50b910..84e2273d3f8 100644 --- a/qa/suites/rados/singleton/all/osd-backfill.yaml +++ b/qa/suites/rados/singleton/all/osd-backfill.yaml @@ -15,9 +15,11 @@ tasks: - ceph: log-whitelist: - wrongly marked me down - - HEALTH_WARN OSDMAP_FLAGS - - HEALTH_WARN OSD_ - - HEALTH_WARN PG_ + - overall HEALTH_ + - (OSDMAP_FLAGS) + - (OSD_ + - (PG_ + - (OBJECT_ conf: osd: osd min pg log entries: 5 diff --git a/qa/suites/rados/singleton/all/osd-recovery-incomplete.yaml b/qa/suites/rados/singleton/all/osd-recovery-incomplete.yaml index 850671dd811..60789d5ca68 100644 --- a/qa/suites/rados/singleton/all/osd-recovery-incomplete.yaml +++ b/qa/suites/rados/singleton/all/osd-recovery-incomplete.yaml @@ -16,9 +16,11 @@ tasks: - ceph: log-whitelist: - wrongly marked me down - - HEALTH_WARN OSDMAP_FLAGS - - HEALTH_WARN OSD_ - - HEALTH_WARN PG_ + - overall HEALTH_ + - (OSDMAP_FLAGS) + - (OSD_ + - (PG_ + - (OBJECT_ conf: osd: osd min pg log entries: 5 diff --git a/qa/suites/rados/singleton/all/osd-recovery.yaml b/qa/suites/rados/singleton/all/osd-recovery.yaml index 8e82f1140e4..d6e5e957f24 100644 --- a/qa/suites/rados/singleton/all/osd-recovery.yaml +++ b/qa/suites/rados/singleton/all/osd-recovery.yaml @@ -15,9 +15,11 @@ tasks: - ceph: log-whitelist: - wrongly marked me down - - HEALTH_WARN OSDMAP_FLAGS - - HEALTH_WARN OSD_ - - HEALTH_WARN PG_ + - overall HEALTH_ + - (OSDMAP_FLAGS) + - (OSD_ + - (PG_ + - (OBJECT_DEGRADED) conf: osd: osd min pg log entries: 5 diff --git a/qa/suites/rados/singleton/all/peer.yaml b/qa/suites/rados/singleton/all/peer.yaml index 6f7e11977e8..e87cd543ce6 100644 --- a/qa/suites/rados/singleton/all/peer.yaml +++ b/qa/suites/rados/singleton/all/peer.yaml @@ -18,7 +18,8 @@ tasks: osd pool default min size : 1 log-whitelist: - objects unfound and apparently lost - - HEALTH_WARN OSDMAP_FLAGS - - HEALTH_WARN OSD_ - - HEALTH_WARN PG_ + - overall HEALTH_ + - (OSDMAP_FLAGS) + - (OSD_ + - (PG_ - peer: diff --git a/qa/suites/rados/singleton/all/pg-removal-interruption.yaml b/qa/suites/rados/singleton/all/pg-removal-interruption.yaml index 05358e6e0ee..856b08dd437 100644 --- a/qa/suites/rados/singleton/all/pg-removal-interruption.yaml +++ b/qa/suites/rados/singleton/all/pg-removal-interruption.yaml @@ -15,9 +15,10 @@ tasks: log-whitelist: - wrongly marked me down - slow request - - HEALTH_WARN OSDMAP_FLAGS - - HEALTH_WARN OSD_ - - HEALTH_WARN PG_ + - overall HEALTH_ + - (OSDMAP_FLAGS) + - (OSD_ + - (PG_ - exec: client.0: - sudo ceph osd pool create foo 128 128 diff --git a/qa/suites/rados/singleton/all/radostool.yaml b/qa/suites/rados/singleton/all/radostool.yaml index 8bc9dbdcd0f..700b3a33a3c 100644 --- a/qa/suites/rados/singleton/all/radostool.yaml +++ b/qa/suites/rados/singleton/all/radostool.yaml @@ -17,6 +17,8 @@ tasks: - had wrong client addr - had wrong cluster addr - reached quota + - overall HEALTH_ + - (POOL_FULL) - workunit: clients: all: diff --git a/qa/suites/rados/singleton/all/rebuild-mondb.yaml b/qa/suites/rados/singleton/all/rebuild-mondb.yaml index ea48501873b..6847cef8da2 100644 --- a/qa/suites/rados/singleton/all/rebuild-mondb.yaml +++ b/qa/suites/rados/singleton/all/rebuild-mondb.yaml @@ -16,10 +16,11 @@ tasks: - ceph: log-whitelist: - no reply from - - HEALTH_WARN MON_DOWN - - HEALTH_WARN OSDMAP_FLAGS - - HEALTH_WARN OSD_ - - HEALTH_WARN PG_ + - overall HEALTH_ + - (MON_DOWN) + - (OSDMAP_FLAGS) + - (OSD_ + - (PG_ - full_sequential: - radosbench: clients: [client.0] diff --git a/qa/suites/rados/singleton/all/resolve_stuck_peering.yaml b/qa/suites/rados/singleton/all/resolve_stuck_peering.yaml index c64593212a5..97da1379096 100644 --- a/qa/suites/rados/singleton/all/resolve_stuck_peering.yaml +++ b/qa/suites/rados/singleton/all/resolve_stuck_peering.yaml @@ -6,5 +6,11 @@ tasks: - install: - ceph: fs: xfs + log-whitelist: + - overall HEALTH_ + - (OSDMAP_FLAGS) + - (OSD_ + - (PG_ + - (OBJECT_DEGRADED) - resolve_stuck_peering: diff --git a/qa/suites/rados/singleton/all/rest-api.yaml b/qa/suites/rados/singleton/all/rest-api.yaml index cbd90e4097d..77c881b0ee5 100644 --- a/qa/suites/rados/singleton/all/rest-api.yaml +++ b/qa/suites/rados/singleton/all/rest-api.yaml @@ -16,8 +16,13 @@ tasks: - install: - ceph: log-whitelist: - - wrongly marked me down - - had wrong client addr + - wrongly marked me down + - had wrong client addr + - overall HEALTH_ + - (OSDMAP_FLAGS) + - (OSD_ + - (PG_ + - (OBJECT_DEGRADED) conf: client.rest0: debug ms: 1 diff --git a/qa/suites/rados/singleton/all/thrash-eio.yaml b/qa/suites/rados/singleton/all/thrash-eio.yaml index a70636549cd..6ff629033cd 100644 --- a/qa/suites/rados/singleton/all/thrash-eio.yaml +++ b/qa/suites/rados/singleton/all/thrash-eio.yaml @@ -24,6 +24,11 @@ tasks: - wrongly marked me down - missing primary copy of - objects unfound and apparently lost + - overall HEALTH_ + - (OSDMAP_FLAGS) + - (REQUEST_SLOW) + - (PG_ + - (OSD_ - thrashosds: op_delay: 30 clean_interval: 120 diff --git a/qa/suites/rados/singleton/all/thrash_cache_writeback_proxy_none.yaml b/qa/suites/rados/singleton/all/thrash_cache_writeback_proxy_none.yaml index 1875da409a2..02fee3e88ea 100644 --- a/qa/suites/rados/singleton/all/thrash_cache_writeback_proxy_none.yaml +++ b/qa/suites/rados/singleton/all/thrash_cache_writeback_proxy_none.yaml @@ -16,8 +16,10 @@ tasks: - install: - ceph: log-whitelist: - - wrongly marked me down - - slow request + - wrongly marked me down + - slow request + - overall HEALTH_ + - (CACHE_POOL_ - exec: client.0: - sudo ceph osd pool create base 4 diff --git a/qa/suites/rados/singleton/all/watch-notify-same-primary.yaml b/qa/suites/rados/singleton/all/watch-notify-same-primary.yaml index ad1fd17d5f5..3efdb955fe6 100644 --- a/qa/suites/rados/singleton/all/watch-notify-same-primary.yaml +++ b/qa/suites/rados/singleton/all/watch-notify-same-primary.yaml @@ -22,6 +22,11 @@ tasks: debug objecter: 20 debug rados: 20 log-whitelist: - - objects unfound and apparently lost + - objects unfound and apparently lost + - overall HEALTH_ + - (OSDMAP_FLAGS) + - (OSD_ + - (PG_ + - (OBJECT_DEGRADED) - watch_notify_same_primary: clients: [client.0] diff --git a/qa/suites/rados/verify/tasks/mon_recovery.yaml b/qa/suites/rados/verify/tasks/mon_recovery.yaml index 6986303409e..412db863022 100644 --- a/qa/suites/rados/verify/tasks/mon_recovery.yaml +++ b/qa/suites/rados/verify/tasks/mon_recovery.yaml @@ -1,2 +1,9 @@ +overrides: + ceph: + log-whitelist: + - overall HEALTH_ + - (MON_DOWN) + - (OSDMAP_FLAGS) + - (SMALLER_PGP_NUM) tasks: - mon_recovery: diff --git a/qa/suites/rados/verify/tasks/rados_api_tests.yaml b/qa/suites/rados/verify/tasks/rados_api_tests.yaml index 11e3858f6a7..7c06248d254 100644 --- a/qa/suites/rados/verify/tasks/rados_api_tests.yaml +++ b/qa/suites/rados/verify/tasks/rados_api_tests.yaml @@ -2,6 +2,12 @@ overrides: ceph: log-whitelist: - reached quota + - overall HEALTH_ + - (CACHE_POOL_NO_HIT_SET) + - (POOL_FULL) + - (SMALLER_PGP_NUM) + - (REQUEST_SLOW) + - (CACHE_POOL_NEAR_FULL) conf: client: debug ms: 1 diff --git a/qa/tasks/thrashosds-health.yaml b/qa/tasks/thrashosds-health.yaml index 82ffc7c4fab..7113e5948aa 100644 --- a/qa/tasks/thrashosds-health.yaml +++ b/qa/tasks/thrashosds-health.yaml @@ -1,14 +1,13 @@ -override: +overrides: ceph: log-whitelist: - - HEALTH_WARN OSDMAP_FLAGS - - HEALTH_WARN OSD_ - - HEALTH_WARN OSDMAP_FLAGS - - HEALTH_WARN PG_ - - HEALTH_ERR OSD_ - - HEALTH_ERR PG_ - - HEALTH_WARN SMALLER_PGP_NUM - - HEALTH_WARN DEGRADED_OBJECTS - - HEALTH_WARN MISPLACED_OBJECTS - - HEALTH_WARN SLOW_REQUESTS - - HEALTH_WARN TOO_FEW_PGS + - overall HEALTH_ + - (OSDMAP_FLAGS) + - (OSD_ + - (PG_ + - (POOL_ + - (CACHE_POOL_ + - (SMALLER_PGP_NUM) + - (OBJECT_ + - (REQUEST_SLOW) + - (TOO_FEW_PGS)