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

Jump to bottom

NO-JIRA: (refactor) job completion uses event instead polling #888

Merged
merged 8 commits into from
Mar 5, 2024
Merged

NO-JIRA: (refactor) job completion uses event instead polling #888

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
d3baad7
refactor: job completion uses event instead polling
Dec 18, 2023
21b8348
chore: add watch permission to batch
Feb 8, 2024
8cbe5b0
fix: handle event job as nil
Feb 8, 2024
8e4d5d1
fix: listen only modified event
Feb 9, 2024
600b198
fix: missing job name log
Feb 9, 2024
6bcef5c
fix: clean up debug stuff
Feb 9, 2024
0834d8f
fix: handle event job casting fail
Feb 9, 2024
5526179
refactor: codereview feedback
Feb 15, 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
13 changes: 7 additions & 6 deletions pkg/controller/periodic/job.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -107,9 +107,9 @@ func (j *JobController) CreateGathererJob(ctx context.Context, dataGatherName, i
}

// WaitForJobCompletion listen the Kubernetes events to check if job finished.
func (j *JobController) WaitForJobCompletion(ctx context.Context, job *batchv1.Job) error {
func (j *JobController) WaitForJobCompletion(ctx context.Context, jobName string) error {
watcher, err := j.kubeClient.BatchV1().Jobs(insightsNamespace).
Watch(ctx, metav1.ListOptions{FieldSelector: fmt.Sprintf("metadata.name=%s", job.Name)})
Watch(ctx, metav1.ListOptions{FieldSelector: fmt.Sprintf("metadata.name=%s", jobName)})
if err != nil {
return err
}
Expand All @@ -123,19 +123,20 @@ func (j *JobController) WaitForJobCompletion(ctx context.Context, job *batchv1.J
if !ok {
return fmt.Errorf("watcher channel was closed unexpectedly")
}
if event.Type == watch.Error {
return fmt.Errorf("watcher received error event: %v", event.Object)

if event.Type != watch.Modified {
continue
}

job := event.Object.(*batchv1.Job)
rluders marked this conversation as resolved.
Show resolved Hide resolved
if job == nil {
return fmt.Errorf("cannot cast event objeto into job: %v", event.Object)
return fmt.Errorf("failed to cast job event: %v", event.Object)
}
if job.Status.Succeeded > 0 {
return nil
}
if job.Status.Failed > 0 {
return fmt.Errorf("job %s failed", job.Name)
return fmt.Errorf("job %s failed: %s", job.Name, job.Status.Conditions[0].Message)
rluders marked this conversation as resolved.
Show resolved Hide resolved
}
}
}
Expand Down
4 changes: 2 additions & 2 deletions pkg/controller/periodic/periodic.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -346,15 +346,15 @@ func (c *Controller) runJobAndCheckResults(ctx context.Context, dataGather *insi
}

klog.Infof("Created new gathering job %v", gj.Name)
err = c.jobController.WaitForJobCompletion(ctx, gj)
err = c.jobController.WaitForJobCompletion(ctx, gj.Name)
if err != nil {
if errors.Is(err, context.DeadlineExceeded) {
klog.Errorf("Failed to read job status: %v", err)
return
}
klog.Error(err)
}
klog.Infof("Job completed %s", gj.Name)
klog.Infof("Job completed %s", "")
rluders marked this conversation as resolved.
Show resolved Hide resolved
dataGatherFinished, err := c.dataGatherClient.DataGathers().Get(ctx, dataGather.Name, metav1.GetOptions{})
if err != nil {
klog.Errorf("Failed to get DataGather resource %s: %v", dataGather.Name, err)
Expand Down