From: Laura Flores <lflores@ibm.com>
Date: Fri, 9 Feb 2024 21:20:26 +0000 (-0600)
Subject: qa/suites/orch: whitelist warnings that are expected in test environments
X-Git-Tag: v16.2.15~3^2
X-Git-Url: http://git-server-git.apps.pok.os.sepia.ceph.com/?a=commitdiff_plain;h=275f1a43d17fa76eaaeaa5a9b5f0c30bd6001d0b;p=ceph.git

qa/suites/orch: whitelist warnings that are expected in test environments

Semi-backport of 00fc7960f682a16aa7a02aeb0300780a1bf56476. Some changes
had to be made though for yaml files and warnings that are specific to pacific.

Fixes: https://tracker.ceph.com/issues/64343
Signed-off-by: Laura Flores <lflores@ibm.com>
---

diff --git a/qa/cephfs/overrides/ignorelist_health.yaml b/qa/cephfs/overrides/ignorelist_health.yaml
index 7f0d49eab63c..ac6d32045c8d 100644
--- a/qa/cephfs/overrides/ignorelist_health.yaml
+++ b/qa/cephfs/overrides/ignorelist_health.yaml
@@ -10,3 +10,9 @@ overrides:
       - \(MDS_ALL_DOWN\)
       - \(MDS_UP_LESS_THAN_MAX\)
       - \(FS_INLINE_DATA_DEPRECATED\)
+      - \(PG_DEGRADED\)
+      - Degraded data redundancy
+      - \(PG_
+      - MDS_INSUFFICIENT_STANDBY
+      - deprecated feature inline_data
+      - compat changed unexpectedly
diff --git a/qa/cephfs/overrides/ignorelist_wrongly_marked_down.yaml b/qa/cephfs/overrides/ignorelist_wrongly_marked_down.yaml
index 41ba84f04db5..abd26643bacf 100644
--- a/qa/cephfs/overrides/ignorelist_wrongly_marked_down.yaml
+++ b/qa/cephfs/overrides/ignorelist_wrongly_marked_down.yaml
@@ -2,8 +2,8 @@ overrides:
   ceph:
     log-ignorelist:
       - overall HEALTH_
-      - \(OSD_DOWN\)
-      - \(OSD_
+      - OSD_DOWN
+      - OSD_
       - but it is still running
 # MDS daemon 'b' is not responding, replacing it as rank 0 with standby 'a'
       - is not responding
diff --git a/qa/suites/orch/cephadm/dashboard/task/test_e2e.yaml b/qa/suites/orch/cephadm/dashboard/task/test_e2e.yaml
index cb6ffb22fe0c..b4ed447bf582 100644
--- a/qa/suites/orch/cephadm/dashboard/task/test_e2e.yaml
+++ b/qa/suites/orch/cephadm/dashboard/task/test_e2e.yaml
@@ -1,3 +1,9 @@
+overrides:
+  ceph:
+    log-ignorelist:
+      - \(HOST_IN_MAINTENANCE\)
+      - \(OSD_DOWN\)
+      - \(MON_DOWN\)
 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.
diff --git a/qa/suites/orch/cephadm/mgr-nfs-upgrade/1-start.yaml b/qa/suites/orch/cephadm/mgr-nfs-upgrade/1-start.yaml
index 2d9f09a4e76d..8a45050d4083 100644
--- a/qa/suites/orch/cephadm/mgr-nfs-upgrade/1-start.yaml
+++ b/qa/suites/orch/cephadm/mgr-nfs-upgrade/1-start.yaml
@@ -1,3 +1,7 @@
+overrides:
+  ceph:
+    log-ignorelist:
+      - slow requests
 tasks:
 - cephadm.shell:
     host.a:
diff --git a/qa/suites/orch/cephadm/osds/2-ops/repave-all.yaml b/qa/suites/orch/cephadm/osds/2-ops/repave-all.yaml
index 16413aba8c2c..fd1f9c6c35fa 100644
--- a/qa/suites/orch/cephadm/osds/2-ops/repave-all.yaml
+++ b/qa/suites/orch/cephadm/osds/2-ops/repave-all.yaml
@@ -1,3 +1,10 @@
+overrides:
+  ceph:
+    log-ignorelist:
+      - \(MON_DOWN\)
+      - \(OSD_DOWN\)
+      - \(PG_
+      - but it is still running
 tasks:
 - cephadm.shell:
     host.a:
diff --git a/qa/suites/orch/cephadm/osds/2-ops/rm-zap-add.yaml b/qa/suites/orch/cephadm/osds/2-ops/rm-zap-add.yaml
index 09be72f11f02..fb925e88ad65 100644
--- a/qa/suites/orch/cephadm/osds/2-ops/rm-zap-add.yaml
+++ b/qa/suites/orch/cephadm/osds/2-ops/rm-zap-add.yaml
@@ -1,3 +1,10 @@
+overrides:
+  ceph:
+    log-ignorelist:
+      - \(MON_DOWN\)
+      - \(OSD_DOWN\)
+      - \(PG_
+      - but it is still running
 tasks:
 - cephadm.shell:
     host.a:
diff --git a/qa/suites/orch/cephadm/osds/2-ops/rm-zap-flag.yaml b/qa/suites/orch/cephadm/osds/2-ops/rm-zap-flag.yaml
index 8f07f6d53743..db612a16c2ba 100644
--- a/qa/suites/orch/cephadm/osds/2-ops/rm-zap-flag.yaml
+++ b/qa/suites/orch/cephadm/osds/2-ops/rm-zap-flag.yaml
@@ -1,3 +1,10 @@
+overrides:
+  ceph:
+    log-ignorelist:
+      - \(MON_DOWN\)
+      - \(OSD_DOWN\)
+      - \(PG_
+      - but it is still running
 tasks:
 - cephadm.shell:
     host.a:
diff --git a/qa/suites/orch/cephadm/osds/2-ops/rm-zap-wait.yaml b/qa/suites/orch/cephadm/osds/2-ops/rm-zap-wait.yaml
index 78161aa49dd6..72c043e8b006 100644
--- a/qa/suites/orch/cephadm/osds/2-ops/rm-zap-wait.yaml
+++ b/qa/suites/orch/cephadm/osds/2-ops/rm-zap-wait.yaml
@@ -1,3 +1,10 @@
+overrides:
+  ceph:
+    log-ignorelist:
+      - \(MON_DOWN\)
+      - \(OSD_DOWN\)
+      - \(PG_
+      - but it is still running
 tasks:
 - cephadm.shell:
     host.a:
diff --git a/qa/suites/orch/cephadm/osds/2-ops/rmdir-reactivate.yaml b/qa/suites/orch/cephadm/osds/2-ops/rmdir-reactivate.yaml
index a971a02e4562..e0706e0dce91 100644
--- a/qa/suites/orch/cephadm/osds/2-ops/rmdir-reactivate.yaml
+++ b/qa/suites/orch/cephadm/osds/2-ops/rmdir-reactivate.yaml
@@ -1,3 +1,10 @@
+overrides:
+  ceph:
+    log-ignorelist:
+      - \(MON_DOWN\)
+      - \(OSD_DOWN\)
+      - \(PG_
+      - but it is still running
 tasks:
 - cephadm.shell:
     host.a:
diff --git a/qa/suites/orch/cephadm/smoke/start.yaml b/qa/suites/orch/cephadm/smoke/start.yaml
index 77f493ca1b9f..6a43d0f3d46d 100644
--- a/qa/suites/orch/cephadm/smoke/start.yaml
+++ b/qa/suites/orch/cephadm/smoke/start.yaml
@@ -1,3 +1,11 @@
+overrides:
+  ceph:
+    log-ignorelist:
+      - \(MON_DOWN\)
+      - \(PG_AVAILABILITY\)
+      - mon down
+      - mons down
+      - out of quorum
 tasks:
 - cephadm:
     conf:
diff --git a/qa/suites/orch/cephadm/thrash/2-thrash.yaml b/qa/suites/orch/cephadm/thrash/2-thrash.yaml
index 05e0f8e76d11..591538bad9ca 100644
--- a/qa/suites/orch/cephadm/thrash/2-thrash.yaml
+++ b/qa/suites/orch/cephadm/thrash/2-thrash.yaml
@@ -3,6 +3,13 @@ overrides:
     log-ignorelist:
     - but it is still running
     - objects unfound and apparently lost
+    - \(MON_DOWN\)
+    - \(OSDMAP_FLAGS\)
+    - flag\(s\) set
+    - \(CACHE_POOL_NO_HIT_SET\)
+    - \(PG_
+    - \(OSD_
+    - mons down:
     conf:
       osd:
         osd debug reject backfill probability: .3
diff --git a/qa/suites/orch/cephadm/upgrade/4-wait.yaml b/qa/suites/orch/cephadm/upgrade/4-wait.yaml
index 58afe00c5be8..ddba90e93d99 100644
--- a/qa/suites/orch/cephadm/upgrade/4-wait.yaml
+++ b/qa/suites/orch/cephadm/upgrade/4-wait.yaml
@@ -1,3 +1,14 @@
+overrides:
+  ceph:
+    log-ignorelist:
+      - \(MON_DOWN\)
+      - \(PG_
+      - mons down
+      - pg inactive
+      - out of quorum
+      - \(OSD_
+      - osds down
+      - osd down
 tasks:
 - cephadm.shell:
     env: [sha1]
diff --git a/qa/suites/orch/cephadm/workunits/task/test_nfs.yaml b/qa/suites/orch/cephadm/workunits/task/test_nfs.yaml
index 8448c1a2fa70..5e1ea3d5e03b 100644
--- a/qa/suites/orch/cephadm/workunits/task/test_nfs.yaml
+++ b/qa/suites/orch/cephadm/workunits/task/test_nfs.yaml
@@ -1,3 +1,8 @@
+overrides:
+  ceph:
+    log-ignorelist:
+    - Replacing daemon mds
+    - FS_DEGRADED
 roles:
 - - host.a
   - osd.0
diff --git a/qa/suites/orch/cephadm/workunits/task/test_orch_cli.yaml b/qa/suites/orch/cephadm/workunits/task/test_orch_cli.yaml
index ec65fb116f71..723c6ad16dc6 100644
--- a/qa/suites/orch/cephadm/workunits/task/test_orch_cli.yaml
+++ b/qa/suites/orch/cephadm/workunits/task/test_orch_cli.yaml
@@ -1,3 +1,9 @@
+overrides:
+  ceph:
+    log-ignorelist:
+      - \(MON_DOWN\)
+      - \(OSD_DOWN\)
+      - mons down
 roles:
 - - host.a
   - osd.0
diff --git a/qa/suites/orch/cephadm/workunits/task/test_orch_cli_mon.yaml b/qa/suites/orch/cephadm/workunits/task/test_orch_cli_mon.yaml
index 2a33dc8399c1..5e8d286db78c 100644
--- a/qa/suites/orch/cephadm/workunits/task/test_orch_cli_mon.yaml
+++ b/qa/suites/orch/cephadm/workunits/task/test_orch_cli_mon.yaml
@@ -1,3 +1,10 @@
+overrides:
+  ceph:
+    log-ignorelist:
+      - \(MON_DOWN\)
+      - mons down
+      - \(MGR_DOWN\)
+      - out of quorum
 roles:
 - - host.a
   - osd.0
diff --git a/qa/suites/rados/basic/tasks/rados_api_tests.yaml b/qa/suites/rados/basic/tasks/rados_api_tests.yaml
index a54e03b1a9c8..c5c8c45ff6db 100644
--- a/qa/suites/rados/basic/tasks/rados_api_tests.yaml
+++ b/qa/suites/rados/basic/tasks/rados_api_tests.yaml
@@ -11,6 +11,14 @@ overrides:
     - \(POOL_APP_NOT_ENABLED\)
     - \(PG_AVAILABILITY\)
     - \(PG_DEGRADED\)
+    - \(MON_DOWN\)
+    - missing hit_sets
+    - do not have an application enabled
+    - application not enabled on pool
+    - pool application
+    - mons down
+    - out of quorum
+    - needs hit_set_type to be set but it is not
     conf:
       client:
         debug ms: 1
diff --git a/qa/suites/rados/basic/tasks/rados_cls_all.yaml b/qa/suites/rados/basic/tasks/rados_cls_all.yaml
index 8f5b79027932..8896ccb446c7 100644
--- a/qa/suites/rados/basic/tasks/rados_cls_all.yaml
+++ b/qa/suites/rados/basic/tasks/rados_cls_all.yaml
@@ -2,6 +2,7 @@ overrides:
   ceph:
     log-ignorelist:
     - \(PG_AVAILABILITY\)
+    - \(POOL_APP_NOT_ENABLED\)
     conf:
       osd:
         osd_class_load_list: "*"
diff --git a/qa/suites/rados/basic/tasks/rados_python.yaml b/qa/suites/rados/basic/tasks/rados_python.yaml
index 965909450186..f89b07ca17f2 100644
--- a/qa/suites/rados/basic/tasks/rados_python.yaml
+++ b/qa/suites/rados/basic/tasks/rados_python.yaml
@@ -8,6 +8,13 @@ overrides:
     - \(OSD_
     - \(OBJECT_
     - \(POOL_APP_NOT_ENABLED\)
+    - \(MON_DOWN\)
+    - mons down
+    - application not enabled on pool
+    - do not have an application enabled
+    - pool application
+    - out of quorum
+    - needs hit_set_type to be set but it is not
 tasks:
 - workunit:
     clients:
diff --git a/qa/suites/rados/verify/tasks/rados_cls_all.yaml b/qa/suites/rados/verify/tasks/rados_cls_all.yaml
index 163bc2c08725..0236326f3a8a 100644
--- a/qa/suites/rados/verify/tasks/rados_cls_all.yaml
+++ b/qa/suites/rados/verify/tasks/rados_cls_all.yaml
@@ -4,6 +4,8 @@ overrides:
       osd:
         osd_class_load_list: "*"
         osd_class_default_list: "*"
+    log-ignorelist:
+      - \(POOL_APP_NOT_ENABLED\)
 tasks:
 - workunit:
     clients:
diff --git a/qa/tasks/thrashosds-health.yaml b/qa/tasks/thrashosds-health.yaml
index 1b2560d4ebae..b3101abf2d55 100644
--- a/qa/tasks/thrashosds-health.yaml
+++ b/qa/tasks/thrashosds-health.yaml
@@ -16,3 +16,11 @@ overrides:
       - \(REQUEST_SLOW\)
       - \(TOO_FEW_PGS\)
       - slow request
+      - \(MON_DOWN\)
+      - osds down
+      - mons down
+      - flag\(s\) set
+      - out of quorum
+      - PG_
+      - Reduced data availability
+      - stuck undersized