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

NO-JIRA: delete all active jobs during restart #920

Merged
merged 1 commit into from
Mar 26, 2024
Merged

NO-JIRA: delete all active jobs during restart #920

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
26 changes: 26 additions & 0 deletions pkg/controller/operator.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,7 @@ import (
"context"
"fmt"
"os"
"strings"
"time"

v1 "github.com/openshift/api/config/v1"
Expand Down Expand Up @@ -141,6 +142,7 @@ func (s *Operator) Run(ctx context.Context, controller *controllercmd.Controller
var insightsDataGatherObserver configobserver.InsightsDataGatherObserver
var dgInformer periodic.DataGatherInformer
if insightsConfigAPIEnabled {
deleteAllRunningGatheringsPods(ctx, kubeClient)
configInformersForTechPreview := configv1informers.NewSharedInformerFactory(configClient, 10*time.Minute)
insightsDataGatherObserver, err = configobserver.NewInsightsDataGatherObserver(gatherKubeConfig,
controller.EventRecorder, configInformersForTechPreview)
Expand Down Expand Up @@ -316,3 +318,27 @@ func isRunning(kubeConfig *rest.Config) wait.ConditionWithContextFunc {
return true, nil
}
}

// deleteAllRunningGatheringsPods deletes all the active jobs (and their Pods) with the "periodic-gathering-"
// prefix in the openshift-insights namespace
func deleteAllRunningGatheringsPods(ctx context.Context, cli kubernetes.Interface) {
jobList, err := cli.BatchV1().Jobs("openshift-insights").List(ctx, metav1.ListOptions{})
if err != nil {
klog.Warningf("Failed to list jobs in the Insights namespace: %v ", err)
}

orphan := metav1.DeletePropagationBackground
for i := range jobList.Items {
j := jobList.Items[i]
if j.Status.Active > 0 && strings.HasPrefix(j.Name, "periodic-gathering-") {
err := cli.BatchV1().Jobs("openshift-insights").Delete(ctx, j.Name, metav1.DeleteOptions{
PropagationPolicy: &orphan,
})
if err != nil {
klog.Warningf("Failed to delete job %s: %v", j.Name, err)
} else {
klog.Infof("Job %s was deleted due to container restart", j.Name)
}
}
}
}
4 changes: 4 additions & 0 deletions pkg/controller/periodic/job.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -131,6 +131,10 @@ func (j *JobController) WaitForJobCompletion(ctx context.Context, job *batchv1.J
return fmt.Errorf("watcher channel was closed unexpectedly")
}

if event.Type == apiWatch.Deleted {
return nil
}
Copy link
Contributor Author

Choose a reason for hiding this comment

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

This is also pretty import, because one can delete the job and in that case it would end up in infinite loop (never ending watch)


if event.Type != apiWatch.Modified {
continue
}
Expand Down