Fix HanaSR sporadically fails on ssh cmd 124 error

Fix Public Cloud HanaSR sporadically failed on "Stop_site_b-primary/Crash_replica": ssh timed out, returned 124 TEAM-9601 - [PC] HanaSR sporadically failed on "Stop_site_b-primary/Crash_replica": ssh timed out, returned 124
lilyeyes · Aug 16, 2024 · 9484733 · 9484733
1 parent e144945
commit 9484733
Show file tree

Hide file tree

Showing 3 changed files with 9 additions and 1 deletion.
diff --git a/lib/sles4sap_publiccloud.pm b/lib/sles4sap_publiccloud.pm
@@ -1286,7 +1286,7 @@ sub wait_for_idle {
 
     my $rc = $self->run_cmd(cmd => 'cs_wait_for_idle --sleep 5', timeout => $timeout, rc_only => 1, proceed_on_failure => 1);
     if ($rc == 124) {
-        record_info("cs_wait_for_idle", "cs_wait_for_idle timed out after $timeout. Gathering info and retrying");
+        record_info("WARN cs_wait_for_idle", "cs_wait_for_idle timed out after $timeout. Gathering info and retrying");
         $self->run_cmd(cmd => 'cs_clusterstate', proceed_on_failure => 1);
         $self->run_cmd(cmd => 'crm_mon -r -R -n -N -1', proceed_on_failure => 1);
         $self->run_cmd(cmd => 'SAPHanaSR-showAttr', proceed_on_failure => 1);

diff --git a/tests/sles4sap/publiccloud/hana_sr_takeover.pm b/tests/sles4sap/publiccloud/hana_sr_takeover.pm
@@ -72,6 +72,10 @@ sub run {
         $self->wait_for_pacemaker();
     }
 
+    if ($takeover_action eq 'stop') {
+        sleep 60;
+    }
+
     record_info('Takeover check');
     $self->check_takeover;
 

diff --git a/tests/sles4sap/publiccloud/hana_sr_test_secondary.pm b/tests/sles4sap/publiccloud/hana_sr_test_secondary.pm
@@ -74,6 +74,10 @@ sub run {
         $self->wait_for_pacemaker();
     }
 
+    if ($db_action eq 'crash') {
+        sleep 60;
+    }
+
     # wait for DB to start with resources
     $self->is_hana_online(wait_for_start => 'true');
     my $hana_started = time;