Merge pull request #55717 from kamoltat/wip-ksirivad-pacific-release-…

…whitelist

pacific: qa/suites: added more whitelisting + fix typo

qa/cephfs/overrides/ignorelist_health.yaml

@@ -2,7 +2,10 @@ overrides:
   ceph:
     log-ignorelist:
       - overall HEALTH_
+      - \(CEPHADM_STRAY_DAEMON\)
       - \(FS_DEGRADED\)
+      - FS_
+      - \(CEPHADM_
       - \(MDS_FAILED\)
       - \(MDS_DEGRADED\)
       - \(FS_WITH_FAILED_MDS\)
@@ -13,6 +16,7 @@ overrides:
       - \(PG_DEGRADED\)
       - Degraded data redundancy
       - \(PG_
+      - acting
       - MDS_INSUFFICIENT_STANDBY
       - deprecated feature inline_data
       - compat changed unexpectedly

qa/cephfs/overrides/ignorelist_wrongly_marked_down.yaml

@@ -7,3 +7,5 @@ overrides:
       - but it is still running
 # MDS daemon 'b' is not responding, replacing it as rank 0 with standby 'a'
       - is not responding
+      - is down
+      - osds down

qa/suites/orch/cephadm/dashboard/task/test_e2e.yaml

@@ -4,6 +4,25 @@ overrides:
       - \(HOST_IN_MAINTENANCE\)
       - \(OSD_DOWN\)
       - \(MON_DOWN\)
+      - down
+      - overall HEALTH_
+      - \(CEPHADM_STRAY_DAEMON\)
+      - stray daemon
+      - \(FS_DEGRADED\)
+      - \(MDS_FAILED\)
+      - \(MDS_DEGRADED\)
+      - \(FS_WITH_FAILED_MDS\)
+      - \(MDS_DAMAGE\)
+      - \(MDS_ALL_DOWN\)
+      - \(MDS_UP_LESS_THAN_MAX\)
+      - \(FS_INLINE_DATA_DEPRECATED\)
+      - \(PG_DEGRADED\)
+      - Degraded data redundancy
+      - \(PG_
+      - acting
+      - MDS_INSUFFICIENT_STANDBY
+      - deprecated feature inline_data
+      - compat changed unexpectedly
 roles:
 # 3 osd roles on host.a is required for cephadm task. It checks if the cluster is healthy.
 # More daemons will be deployed on both hosts in e2e tests.

qa/suites/orch/cephadm/mgr-nfs-upgrade/1-start.yaml

@@ -1,7 +1,3 @@
-overrides:
-  ceph:
-    log-ignorelist:
-      - slow requests
 tasks:
 - cephadm.shell:
     host.a:
@@ -28,6 +24,21 @@ openstack:
     size: 10 # GB
 overrides:
   ceph:
+    log-ignorelist:
+      - slow requests
+      - \(PG_
+      - PG_
+      - \(CEPHADM_STRAY_DAEMON\)
+      - slow request
+      - \(MDS_
+      - MDS_
+      - osds down
+      - OSD_
+      - \(OSD_
+      - client
+      - FS_
+      - \(FS_
+      - degraded
     conf:
       osd:
         osd shutdown pgref assert: true

qa/suites/orch/cephadm/osds/2-ops/rmdir-reactivate.yaml

@@ -5,6 +5,7 @@ overrides:
       - \(OSD_DOWN\)
       - \(PG_
       - but it is still running
+      - \(CEPHADM_STRAY_DAEMON\)
 tasks:
 - cephadm.shell:
     host.a:

qa/suites/orch/cephadm/thrash/2-thrash.yaml

@@ -7,9 +7,19 @@ overrides:
     - \(OSDMAP_FLAGS\)
     - flag\(s\) set
     - \(CACHE_POOL_NO_HIT_SET\)
+    - \(CACHE_
     - \(PG_
     - \(OSD_
-    - mons down:
+    - \(POOL_
+    - \(CEPHADM_STRAY_DAEMON\)
+    - PG_
+    - CACHE_
+    - degraded
+    - backfill
+    - mons down
+    - OSD_
+    - is down
+    - acting
     conf:
       osd:
         osd debug reject backfill probability: .3

qa/suites/orch/cephadm/workunits/task/test_nfs.yaml

@@ -3,6 +3,7 @@ overrides:
     log-ignorelist:
     - Replacing daemon mds
     - FS_DEGRADED
+    - \(CEPHADM_STRAY_DAEMON\)
 roles:
 - - host.a
   - osd.0

qa/suites/orch/cephadm/workunits/task/test_orch_cli.yaml

@@ -3,6 +3,7 @@ overrides:
     log-ignorelist:
       - \(MON_DOWN\)
       - \(OSD_DOWN\)
+      - \(CEPHADM_PAUSED\)
       - mons down
 roles:
 - - host.a

qa/suites/rados/basic/tasks/rados_api_tests.yaml

@@ -12,6 +12,7 @@ overrides:
     - \(PG_AVAILABILITY\)
     - \(PG_DEGRADED\)
     - \(MON_DOWN\)
+    - \(CEPHADM_STRAY_DAEMON\)
     - missing hit_sets
     - do not have an application enabled
     - application not enabled on pool

qa/tasks/thrashosds-health.yaml

@@ -24,3 +24,7 @@ overrides:
       - PG_
       - Reduced data availability
       - stuck undersized
+      - backfill_toofull
+      - is down
+      - stuck peering
+      - acting