Skip to content

Use unambiguous retry suffix to prevent job name collisions #799

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

Open
hoxhaeris wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Use unambiguous retry suffix to prevent job name collisions #799

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
2 changes: 1 addition & 1 deletion cmd/release-controller/sync_verify.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -69,7 +69,7 @@ func (c *Controller) ensureVerificationJobs(release *releasecontroller.Release,
}
jobNameSuffix := ""
if jobRetries > 0 {
jobNameSuffix = fmt.Sprintf("%d", jobRetries)
jobNameSuffix = fmt.Sprintf("retry-%d", jobRetries)
}
jobLabels := map[string]string{
releasecontroller.ProwJobLabelCapability: "rce",
Expand Down
8 changes: 5 additions & 3 deletions cmd/release-controller/sync_verify_prow.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,9 +39,11 @@ func (c *Controller) ensureProwJobForReleaseTag(release *releasecontroller.Relea
jobName = defaultAggregateProwJobName
}
aggregatorSuffix := "aggregator"
if retry, err := strconv.Atoi(verifySuffix); err == nil {
klog.V(6).Infof("Aggregator job has failed. Retry count: %d", retry)
aggregatorSuffix = aggregatorSuffix + fmt.Sprintf("-%s", verifySuffix)
if after, ok := strings.CutPrefix(verifySuffix, "retry-"); ok {
if retry, err := strconv.Atoi(after); err == nil {
klog.V(6).Infof("Aggregator job has failed. Retry count: %d", retry)
aggregatorSuffix = aggregatorSuffix + fmt.Sprintf("-%s", verifySuffix)
}
}
// Postfix the name to differentiate it from the analysis jobs
prowJobName = prow.GenerateSafeProwJobName(fullProwJobName, aggregatorSuffix)

@bradmwilliams bradmwilliams Jul 20, 2026

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

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

Can you make sure that this function has tests for this new suffix? Specifically on really long job names because this is literally adding 6 more characters and we need to make sure they resolve properly (which they should, but warrants a test).

@hoxhaeris hoxhaeris Jul 20, 2026

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

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

Added a test.

Expand Down
20 changes: 16 additions & 4 deletions cmd/release-controller/sync_verify_prow_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -111,14 +111,26 @@ func TestGenerateSafeProwJobName(t *testing.T) {
{
name: "AggregatorJobWithRetry",
jobName: "4.16.0-0.nightly-2024-02-07-125310-aggregated-hypershift-ovn-conformance-4.16",
suffix: "aggregator-2",
expected: "4.16.0-0.nightly-2024-02-07-125310-aggrega-44j0w6k-aggregator-2",
suffix: "aggregator-retry-2",
expected: "4.16.0-0.nightly-2024-02-07-125310-a-44j0w6k-aggregator-retry-2",
},
{
name: "TruncationResultsInInvalidJobName",
jobName: "4.19.0-0.nightly-2025-06-19-224840-aws-ovn-upgrade-4.19-micro-fips",
suffix: "1",
expected: "4.19.0-0.nightly-2025-06-19-224840-aws-ovn-upgrade-4-mzdcpq2-1",
suffix: "retry-1",
expected: "4.19.0-0.nightly-2025-06-19-224840-aws-ovn-upgr-mzdcpq2-retry-1",
},
{
name: "RetryWithLongJobNameTriggersProperTruncation",
jobName: "5.0.0-0.nightly-2026-07-20-081439-driver-toolkit-rhel10",
suffix: "retry-2",
expected: "5.0.0-0.nightly-2026-07-20-081439-driver-toolkit-rhel10-retry-2",
},
{
name: "RetryWithMaxLengthJobNameTruncates",
jobName: "5.0.0-0.nightly-2026-07-20-081439-some-very-long-job-name-here",
suffix: "retry-10",
expected: "5.0.0-0.nightly-2026-07-20-081439-some-very-lo-jn7w8wk-retry-10",
},
}

Expand Down
10 changes: 5 additions & 5 deletions pkg/releasepayload/utils/release-verification-job-details.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,11 +17,11 @@ const (
var (
candidates = regexp.MustCompile(`[efr]c.\d+`)
expressions = []*regexp.Regexp{
regexp.MustCompile(`^(?P<prerelease>[\d-]+)\.(?P<stream>okd-scos|okd|\w+)-(?P<architecture>\w+)?-?(?P<timestamp>\d{4}-\d{2}-\d{2}-\d{6})-(?P<job>[\w-\\.]+?)(?:-(?P<count>\d+))?$`),
regexp.MustCompile(`^(?P<prerelease>[efr]c\.\d+)?-?upgrade-from-(?P<upgrade_from>[\d\\.]+(?:-[efr]c.\d+)?)-?(?P<job>\w+)-?(?P<count>\d+)?$`),
regexp.MustCompile(`^(?P<stream>okd-scos|okd)\.(?P<prerelease>(?:[erf]c\.\d+)+|\d+)-(?P<job>[\w-\\.]+?)(?:-(?P<count>\d+))?$`),
regexp.MustCompile(`^(?P<prerelease>(?:[erf]c|okd-scos|okd)\.\d+)-(?P<job>[\w-\\.]+?)(?:-(?P<count>\d+))?$`),
regexp.MustCompile(`^(?P<job>[\w-\\.]+?)(?:-(?P<count>\d+))?$`),
regexp.MustCompile(`^(?P<prerelease>[\d-]+)\.(?P<stream>okd-scos|okd|\w+)-(?P<architecture>\w+)?-?(?P<timestamp>\d{4}-\d{2}-\d{2}-\d{6})-(?P<job>[\w-\\.]+?)(?:-(?:retry-)?(?P<count>\d+))?$`),
regexp.MustCompile(`^(?P<prerelease>[efr]c\.\d+)?-?upgrade-from-(?P<upgrade_from>[\d\\.]+(?:-[efr]c.\d+)?)-?(?P<job>\w+)-?(?:retry-)?(?P<count>\d+)?$`),
regexp.MustCompile(`^(?P<stream>okd-scos|okd)\.(?P<prerelease>(?:[erf]c\.\d+)+|\d+)-(?P<job>[\w-\\.]+?)(?:-(?:retry-)?(?P<count>\d+))?$`),
regexp.MustCompile(`^(?P<prerelease>(?:[erf]c|okd-scos|okd)\.\d+)-(?P<job>[\w-\\.]+?)(?:-(?:retry-)?(?P<count>\d+))?$`),
regexp.MustCompile(`^(?P<job>[\w-\\.]+?)(?:-(?:retry-)?(?P<count>\d+))?$`),
}
)

Expand Down
Loading