Skip to content

fix: jobs can remain permanently active if final status persistence fails after three short retries #874

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

Closed
sam-saffron-jarvis wants to merge 1 commit into from
Closed

fix: jobs can remain permanently active if final status persistence fails after three short retries #874

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
43 changes: 28 additions & 15 deletions cmd/serve_jobs_v2.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -229,14 +229,15 @@ var (
)

const (
jobsV2SchedulerMinDelay = 100 * time.Millisecond
jobsV2SchedulerIdleDelay = time.Minute
jobsV2SchedulerErrorDelay = 200 * time.Millisecond
jobsV2WorkerMinDelay = 100 * time.Millisecond
jobsV2WorkerIdleDelay = time.Minute
jobsV2WorkerErrorDelay = 200 * time.Millisecond
jobsV2FinishRunAttempts = 3
jobsV2FinishRunRetryDelay = 50 * time.Millisecond
jobsV2SchedulerMinDelay = 100 * time.Millisecond
jobsV2SchedulerIdleDelay = time.Minute
jobsV2SchedulerErrorDelay = 200 * time.Millisecond
jobsV2WorkerMinDelay = 100 * time.Millisecond
jobsV2WorkerIdleDelay = time.Minute
jobsV2WorkerErrorDelay = 200 * time.Millisecond
jobsV2FinishRunRetryDelay = 50 * time.Millisecond
jobsV2FinishRunRetryMaxDelay = time.Second
jobsV2FinishRunRetryTimeout = 30 * time.Second
)

type jobsV2ProgramConfig struct {
Expand Down Expand Up @@ -1417,19 +1418,31 @@ func (m *jobsV2Manager) executeRun(run jobsV2Run) {
}

func (m *jobsV2Manager) finishRunWithRetry(runID string, status jobsV2RunStatus, result jobsV2RunResult, runErr error, policyAttempt int) {
deadline := time.Now().Add(jobsV2FinishRunRetryTimeout)
delay := jobsV2FinishRunRetryDelay
attempts := 0
var lastErr error
for attempt := 1; attempt <= jobsV2FinishRunAttempts; attempt++ {
for {
attempts++
if err := m.finishRun(runID, status, result, runErr, policyAttempt); err != nil {
lastErr = err
if attempt < jobsV2FinishRunAttempts {
time.Sleep(jobsV2FinishRunRetryDelay)
continue
remaining := time.Until(deadline)
if remaining <= 0 {
break
}
} else {
return
wait := min(delay, remaining)
select {
case <-time.After(wait):
case <-m.doneChan():
log.Printf("jobs v2: failed to finish run %q as %s after %d attempts; manager is closing and run may remain active until restart recovery: %v", runID, status, attempts, lastErr)
return
}
delay = min(delay*2, jobsV2FinishRunRetryMaxDelay)
continue
}
return
}
log.Printf("jobs v2: failed to finish run %q as %s after %d attempts; run may remain active: %v", runID, status, jobsV2FinishRunAttempts, lastErr)
log.Printf("jobs v2: failed to finish run %q as %s after %d attempts over %s; run may remain active until restart recovery: %v", runID, status, attempts, jobsV2FinishRunRetryTimeout, lastErr)
}

func (m *jobsV2Manager) finishRun(runID string, status jobsV2RunStatus, result jobsV2RunResult, runErr error, attempt int) error {
Expand Down
2 changes: 1 addition & 1 deletion cmd/serve_jobs_v2_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1748,7 +1748,7 @@ func TestJobsV2ExecuteRunRetriesFinishRunAfterTransientDBLock(t *testing.T) {
return jobsV2RunResult{}, err
}
go func() {
time.Sleep(70 * time.Millisecond)
time.Sleep(250 * time.Millisecond)
_ = tx.Rollback()
_ = lockDB.Close()
close(lockReleased)
Expand Down
Loading