fix(aws): CleanupAlarmsAgent cycle to catch exceptions (#6333)

spinnaker · Jan 22, 2025 · c4df136 · c4df136
1 parent fcc5394
commit c4df136
Show file tree

Hide file tree

Showing 2 changed files with 32 additions and 27 deletions.
diff --git a/...aws/src/main/groovy/com/netflix/spinnaker/clouddriver/aws/agent/CleanupAlarmsAgent.groovy b/...aws/src/main/groovy/com/netflix/spinnaker/clouddriver/aws/agent/CleanupAlarmsAgent.groovy
@@ -86,36 +86,38 @@ class CleanupAlarmsAgent implements RunnableAgent, CustomScheduledAgent {
     getAccounts().each { NetflixAmazonCredentials credentials ->
       credentials.regions.each { AmazonCredentials.AWSRegion region ->
         log.info("Looking for alarms to delete")
-
-        def cloudWatch = amazonClientProvider.getCloudWatch(credentials, region.name)
-        Set<String> attachedAlarms = getAttachedAlarms(amazonClientProvider.getAutoScaling(credentials, region.name))
-        def describeAlarmsRequest = new DescribeAlarmsRequest().withStateValue(StateValue.INSUFFICIENT_DATA)
-
-        while (true) {
-          def result = cloudWatch.describeAlarms(describeAlarmsRequest)
-
-          List<MetricAlarm> alarmsToDelete = result.metricAlarms.findAll {
-            it.stateUpdatedTimestamp.before(DateTime.now().minusDays(daysToLeave).toDate()) &&
-              !attachedAlarms.contains(it.alarmName) &&
-              ALARM_NAME_PATTERN.matcher(it.alarmName).matches()
-          }
-
-          if (alarmsToDelete) {
-            // terminate up to 20 alarms at a time (avoids any AWS limits on # of concurrent deletes)
-            alarmsToDelete.collate(20).each {
-              log.info("Deleting ${it.size()} alarms in ${credentials.name}/${region.name} " +
-                "(alarms: ${it.alarmName.join(", ")})")
-              cloudWatch.deleteAlarms(new DeleteAlarmsRequest().withAlarmNames(it.alarmName))
-              Thread.sleep(500)
+        try {
+          def cloudWatch = amazonClientProvider.getCloudWatch(credentials, region.name)
+          Set<String> attachedAlarms = getAttachedAlarms(amazonClientProvider.getAutoScaling(credentials, region.name))
+          def describeAlarmsRequest = new DescribeAlarmsRequest().withStateValue(StateValue.INSUFFICIENT_DATA)
+
+          while (true) {
+            def result = cloudWatch.describeAlarms(describeAlarmsRequest)
+
+            List<MetricAlarm> alarmsToDelete = result.metricAlarms.findAll {
+              it.stateUpdatedTimestamp.before(DateTime.now().minusDays(daysToLeave).toDate()) &&
+                !attachedAlarms.contains(it.alarmName) &&
+                ALARM_NAME_PATTERN.matcher(it.alarmName).matches()
             }
 
-          }
+            if (alarmsToDelete) {
+              // terminate up to 20 alarms at a time (avoids any AWS limits on # of concurrent deletes)
+              alarmsToDelete.collate(20).each {
+                log.info("Deleting ${it.size()} alarms in ${credentials.name}/${region.name} " +
+                  "(alarms: ${it.alarmName.join(", ")})")
+                cloudWatch.deleteAlarms(new DeleteAlarmsRequest().withAlarmNames(it.alarmName))
+                Thread.sleep(500)
+              }
+            }
 
-          if (result.nextToken) {
-            describeAlarmsRequest.withNextToken(result.nextToken)
-          } else {
-            break
+            if (result.nextToken) {
+              describeAlarmsRequest.withNextToken(result.nextToken)
+            } else {
+              break
+            }
           }
+        } catch (Exception e) {
+          log.error("Error occurred while processing alarms for ${credentials.name}/${region.name}: ${e.message}", e)
         }
       }
     }

diff --git a/...n/groovy/com/netflix/spinnaker/clouddriver/aws/agent/CleanupDetachedInstancesAgent.groovy b/...n/groovy/com/netflix/spinnaker/clouddriver/aws/agent/CleanupDetachedInstancesAgent.groovy
@@ -74,7 +74,7 @@ class CleanupDetachedInstancesAgent implements RunnableAgent, CustomScheduledAge
     getAccounts().each { NetflixAmazonCredentials credentials ->
       credentials.regions.each { AmazonCredentials.AWSRegion region ->
         log.info("Looking for instances pending termination in ${credentials.name}:${region.name}")
-
+        try {
         def amazonEC2 = amazonClientProvider.getAmazonEC2(credentials, region.name, true)
         def describeInstancesRequest = new DescribeInstancesRequest().withFilters(
           new Filter("tag-key", [DetachInstancesAtomicOperation.TAG_PENDING_TERMINATION])
@@ -103,6 +103,9 @@ class CleanupDetachedInstancesAgent implements RunnableAgent, CustomScheduledAge
             break
           }
         }
+        } catch (Exception e) {
+          log.error("Error occurred while processing instances pending termination for ${credentials.name}/${region.name}: ${e.message}", e)
+        }
       }
     }
   }