Skip to content

Fix two flaky Windows unit tests in jobsupervisor #440

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

Merged
aramprice merged 2 commits into from
Oct 30, 2026
Merged

Fix two flaky Windows unit tests in jobsupervisor #440

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
4180051
Fix two flaky Windows unit tests in jobsupervisor
neddp Jun 15, 2026
e4de29b
Use WaitForNWatchersAndIncrement for atomic clock advance in StopAndW…
neddp Oct 30, 2026
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
15 changes: 4 additions & 11 deletions jobsupervisor/monit_job_supervisor_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -353,7 +353,7 @@ var _ = Describe("monitJobSupervisor", func() {

failureMessage := "Timed out waiting for services 'foo' to no longer be pending after 5 minutes"

advanceTime(timeService, 10*time.Minute, 2)
timeService.WaitForNWatchersAndIncrement(10*time.Minute, 2)
Eventually(timeService.WatcherCount).Should(Equal(0))
Eventually(errchan).Should(Receive(Equal(errors.New(failureMessage))))
Expect(len(runner.RunCommands)).To(Equal(0)) // never called 'monit stop'
Expand All @@ -371,18 +371,16 @@ var _ = Describe("monitJobSupervisor", func() {
errchan <- monit.StopAndWait()
}()

Eventually(timeService.WatcherCount).Should(Equal(2)) // we hit the pending sleep
Eventually(timeService.WatcherCount).Should(Equal(2)) // wait for pending sleep

client.StatusStatus = fakemonit.FakeMonitStatus{
Services: []boshmonit.Service{
{Monitored: true, Name: "foo", Status: "unknown", Pending: false},
},
}
timeService.Increment(3 * time.Minute)

Eventually(timeService.WatcherCount).Should(Equal(2)) // we hit the stop sleep

timeService.Increment(3 * time.Minute)
timeService.WaitForNWatchersAndIncrement(3*time.Minute, 2) // wait for stop sleep, then advance

Eventually(errchan).Should(Receive(Equal(errors.New("Timed out waiting for services 'foo' to stop after 5 minutes"))))
})
Expand Down Expand Up @@ -555,7 +553,7 @@ var _ = Describe("monitJobSupervisor", func() {

failureMessage := "Timed out waiting for services 'unmonitored-start-pending, initializing, running, running-stop-pending, unmonitored-stop-pending, failing' to stop after 5 minutes"

advanceTime(timeService, 5*time.Minute, 2)
timeService.WaitForNWatchersAndIncrement(5*time.Minute, 2)
Eventually(timeService.WatcherCount).Should(Equal(0))
Eventually(errchan).Should(Receive(Equal(errors.New(failureMessage))))
Expect(statusRequests).To(Equal(3))
Expand Down Expand Up @@ -894,8 +892,3 @@ var _ = Describe("monitJobSupervisor", func() {
})
})
})

func advanceTime(timeService *fakeclock.FakeClock, duration time.Duration, watcherCount int) {
Eventually(timeService.WatcherCount).Should(Equal(watcherCount))
timeService.Increment(duration)
}
10 changes: 6 additions & 4 deletions jobsupervisor/windows_job_supervisor_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -64,8 +64,7 @@ var (
)

var _ = AfterSuite(func() {
err := os.RemoveAll(TempDir)
Expect(err).NotTo(HaveOccurred())
Eventually(func() error { return os.RemoveAll(TempDir) }, 2*time.Minute, time.Second).Should(Succeed())
gexec.CleanupBuildArtifacts()

match := func(s string) bool {
Expand Down Expand Up @@ -486,8 +485,11 @@ var _ = Describe("WindowsJobSupervisor", func() {
AfterEach(func() {
Expect(jobSupervisor.Stop()).To(Succeed())
Expect(jobSupervisor.RemoveAllJobs()).To(Succeed())
Eventually(func() error { return fs.RemoveAll(jobDir) }, 60*time.Second).Should(Succeed())
Expect(fs.RemoveAll(logDir)).To(Succeed())
// Windows releases file handles on the service wrapper exe and log
// files asynchronously after the SCM reports services as deleted.
// Use a long timeout with a slow poll to avoid spinning on busy CI.
Eventually(func() error { return fs.RemoveAll(jobDir) }, 2*time.Minute, time.Second).Should(Succeed())
Eventually(func() error { return fs.RemoveAll(logDir) }, 2*time.Minute, time.Second).Should(Succeed())
})

Describe("AddJob", func() {
Expand Down
Loading