From: Matan Breizman <mbreizma@redhat.com>
Date: Wed, 27 Mar 2024 08:37:40 +0000 (+0000)
Subject: qa/suites/crimson-rados/thrash: enable chance_down
X-Git-Tag: v19.1.1~346^2
X-Git-Url: http://git-server-git.apps.pok.os.sepia.ceph.com/?a=commitdiff_plain;h=refs%2Fpull%2F57502%2Fhead;p=ceph.git

qa/suites/crimson-rados/thrash: enable chance_down

As the thrash tests were introduced, some options were disabled
until the tests are stabilized.

Re-enable chance_down option (default is 0.4) to detect bugs on restart.

Since it will probably take few iterations before thrash and recovery tests ('default.yaml')
will pass successfully, add anoter 'simple.yaml' which should remain stable.

Fixes: https://tracker.ceph.com/issues/65130

Signed-off-by: Matan Breizman <mbreizma@redhat.com>
(cherry picked from commit 372751789be1725ed06fd077d029295c8cab4c35)
---

diff --git a/qa/suites/crimson-rados/thrash/thrashers/default.yaml b/qa/suites/crimson-rados/thrash/thrashers/default.yaml
index bbb33324706b..aa44b6101ff9 100644
--- a/qa/suites/crimson-rados/thrash/thrashers/default.yaml
+++ b/qa/suites/crimson-rados/thrash/thrashers/default.yaml
@@ -25,7 +25,6 @@ tasks:
     sighup_delay: 0
     min_in: 3
     noscrub_toggle_delay: 0
-    chance_down: 0
     chance_thrash_pg_upmap: 0
     reweight_osd: 0
     thrash_primary_affinity: false
diff --git a/qa/suites/crimson-rados/thrash/thrashers/simple.yaml b/qa/suites/crimson-rados/thrash/thrashers/simple.yaml
new file mode 100644
index 000000000000..bbb33324706b
--- /dev/null
+++ b/qa/suites/crimson-rados/thrash/thrashers/simple.yaml
@@ -0,0 +1,35 @@
+overrides:
+  ceph:
+    log-ignorelist:
+    - but it is still running
+    - objects unfound and apparently lost
+    conf:
+      osd:
+        osd debug reject backfill probability: .3
+        osd scrub min interval: 60
+        osd scrub max interval: 120
+        osd max backfills: 3
+        osd snap trim sleep: 2
+        osd delete sleep: 1
+      mon:
+        mon min osdmap epochs: 50
+        paxos service trim min: 10
+        # prune full osdmaps regularly
+        mon osdmap full prune min: 15
+        mon osdmap full prune interval: 2
+        mon osdmap full prune txsize: 2
+tasks:
+- thrashosds:
+    timeout: 2400
+    dump_ops_enable: false
+    sighup_delay: 0
+    min_in: 3
+    noscrub_toggle_delay: 0
+    chance_down: 0
+    chance_thrash_pg_upmap: 0
+    reweight_osd: 0
+    thrash_primary_affinity: false
+    ceph_objectstore_tool: false
+    chance_inject_pause_short: 0
+    chance_thrash_cluster_full: 0
+    chance_reset_purged_snaps_last: 0