Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

report error creating cron #732

Open
wants to merge 7 commits into
base: master
Choose a base branch
from
Open

report error creating cron #732

Changes from 1 commit
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
c7297ce
report error creating cron
dtrager02 Dec 16, 2024
b19c2f7
add ut
dtrager02 Dec 16, 2024
435610b
validate cron in job definition constructor
dtrager02 Dec 17, 2024
0453f2b
fix unit test
dtrager02 Dec 17, 2024
a79dea6
fixed tests
dtrager02 Dec 17, 2024
1d02cf6
empty commit
dtrager02 Dec 19, 2024
c6b0034
empty
dtrager02 Dec 21, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
20 changes: 13 additions & 7 deletions ...tis-control-plane-server/src/main/java/io/mantisrx/master/jobcluster/JobClusterActor.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -716,9 +716,10 @@ public void onJobClusterInitialize(JobClusterProto.InitializeJobClusterRequest i
}

int count = 50;
String jobClusterName = jobClusterMetadata.getJobClusterDefinition().getName();
if(!initReq.jobList.isEmpty()) {
logger.info("Cluster {} is disabled however it has {} active/accepted jobs",
jobClusterMetadata.getJobClusterDefinition().getName(), initReq.jobList.size());
jobClusterName, initReq.jobList.size());
for(IMantisJobMetadata jobMeta : initReq.jobList) {
try {
if(count == 0) {
Expand All @@ -728,7 +729,7 @@ public void onJobClusterInitialize(JobClusterProto.InitializeJobClusterRequest i
if(!JobState.isTerminalState(jobMeta.getState())) {
logger.info("Job {} is in non terminal state {} for disabled cluster {}."
+ "Marking it complete", jobMeta.getJobId(), jobMeta.getState(),
jobClusterMetadata.getJobClusterDefinition().getName());
jobClusterName);
count--;
jobManager.markCompleted(jobMeta);
jobStore.archiveJob(jobMeta);
Expand All @@ -751,14 +752,15 @@ public void onJobClusterInitialize(JobClusterProto.InitializeJobClusterRequest i

return;
} else {
String jobClusterName = jobClusterMetadata.getJobClusterDefinition().getName();
// new cluster initialization
if (initReq.createInStore) {
try {
jobStore.createJobCluster(jobClusterMetadata);
eventPublisher.publishAuditEvent(
new LifecycleEventsProto.AuditEvent(
LifecycleEventsProto.AuditEvent.AuditEventType.JOB_CLUSTER_CREATE,
jobClusterMetadata.getJobClusterDefinition().getName(),
jobClusterName,
"saved job cluster " + name)
);
logger.info("successfully saved job cluster {}", name);
Expand Down Expand Up @@ -790,6 +792,10 @@ public void onJobClusterInitialize(JobClusterProto.InitializeJobClusterRequest i
cronManager = new CronManager(name, getSelf(), jobClusterMetadata.getJobClusterDefinition().getSLA());
} catch (Exception e) {
logger.warn("Exception initializing cron", e);
getSender().tell(new JobClusterManagerProto.CreateJobClusterResponse(
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

maybe separate this catch to known error (SchedulerException) and other error (exception) and use different error code + message.

initReq.requestId, CLIENT_ERROR,
"Job Cluster " + jobClusterName + " could not be created due to cron initialization error" + e.getMessage(),
jobClusterName), getSelf());
}
initRunningJobs(initReq, sender);

Expand Down Expand Up @@ -916,7 +922,7 @@ public void onJobClusterUpdate(final UpdateJobClusterRequest request) {
} catch (Exception e) {
logger.error("job cluster not created");
sender.tell(new UpdateJobClusterResponse(request.requestId, SERVER_ERROR, name
+ " Job cluster updation failed " + e.getMessage()), getSelf());
+ " Job cluster update failed " + e.getMessage()), getSelf());
numJobClusterUpdateErrors.increment();
}
}
Expand Down Expand Up @@ -2135,11 +2141,11 @@ public void onJobClusterUpdateSLA(UpdateJobClusterSLARequest slaRequest) {
);
} catch(IllegalArgumentException e) {
logger.error("Invalid arguement job cluster not updated ", e);
sender.tell(new UpdateJobClusterSLAResponse(slaRequest.requestId, CLIENT_ERROR, name + " Job cluster SLA updation failed " + e.getMessage()), getSelf());
sender.tell(new UpdateJobClusterSLAResponse(slaRequest.requestId, CLIENT_ERROR, name + " Job cluster SLA update failed " + e.getMessage()), getSelf());

} catch(Exception e) {
logger.error("job cluster not updated ", e);
sender.tell(new UpdateJobClusterSLAResponse(slaRequest.requestId, SERVER_ERROR, name + " Job cluster SLA updation failed " + e.getMessage()), getSelf());
sender.tell(new UpdateJobClusterSLAResponse(slaRequest.requestId, SERVER_ERROR, name + " Job cluster SLA update failed " + e.getMessage()), getSelf());
}
if(logger.isTraceEnabled()) { logger.trace("Exit onJobClusterUpdateSLA {}", slaRequest); }
}
Expand Down Expand Up @@ -3217,7 +3223,7 @@ private void initCron() throws Exception{
isCronActive = true;
} catch (IllegalArgumentException e) {
destroyCron();
logger.error("Failed to start cron for {}: {}", jobClusterName, e);
logger.error("Failed to start cron for {}: {}. The format of the cron schedule may be incorrect.", jobClusterName, e);
throw new SchedulerException(e.getMessage(), e);
}

Expand Down
Loading