Skip to content

chore: reduce chance of flakiness on the migrate integration test #2674

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
josephschorr wants to merge 1 commit into from
Closed

chore: reduce chance of flakiness on the migrate integration test #2674

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
104 changes: 59 additions & 45 deletions cmd/spicedb/migrate_integration_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -43,57 +43,71 @@ func TestMigrate(t *testing.T) {
}

t.Run(engineKey, func(t *testing.T) {
engineKey := engineKey
for retryCount := range 5 {
engineKey := engineKey

r := testdatastore.RunDatastoreEngineWithBridge(t, engineKey, bridgeNetworkName)
db := r.NewDatabase(t)
r := testdatastore.RunDatastoreEngineWithBridge(t, engineKey, bridgeNetworkName)
db := r.NewDatabase(t)

envVars := []string{}
if wev, ok := r.(testdatastore.RunningEngineForTestWithEnvVars); ok {
envVars = wev.ExternalEnvVars()
}

// Run the migrate command and wait for it to complete.
resource, err := pool.RunWithOptions(&dockertest.RunOptions{
Repository: "authzed/spicedb",
Tag: "ci",
Cmd: []string{"migrate", "head", "--datastore-engine", engineKey, "--datastore-conn-uri", db},
NetworkID: bridgeNetworkName,
Env: envVars,
}, func(config *docker.HostConfig) {
config.RestartPolicy = docker.RestartPolicy{
Name: "no",
envVars := []string{}
if wev, ok := r.(testdatastore.RunningEngineForTestWithEnvVars); ok {
envVars = wev.ExternalEnvVars()
}
})
require.NoError(t, err)

waitCtx, cancel := context.WithTimeout(context.Background(), 3*time.Second)
defer cancel()

// Ensure the command completed successfully.
status, err := pool.Client.WaitContainerWithContext(resource.Container.ID, waitCtx)
require.NoError(t, err)

if status != 0 {
stream := new(bytes.Buffer)

lerr := pool.Client.Logs(docker.LogsOptions{
Context: waitCtx,
OutputStream: stream,
ErrorStream: stream,
Stdout: true,
Stderr: true,
Container: resource.Container.ID,

// Run the migrate command and wait for it to complete.
resource, err := pool.RunWithOptions(&dockertest.RunOptions{
Repository: "authzed/spicedb",
Tag: "ci",
Cmd: []string{"migrate", "head", "--datastore-engine", engineKey, "--datastore-conn-uri", db},
NetworkID: bridgeNetworkName,
Env: envVars,
}, func(config *docker.HostConfig) {
config.RestartPolicy = docker.RestartPolicy{
Name: "no",
}
})
require.NoError(t, lerr)
if err != nil && retryCount < 4 {
// On error, retry a few times before failing
t.Logf("retrying migration for engine %s due to error: %v", engineKey, err)
continue
}

require.Fail(t, "Got non-zero exit code", stream.String())
}
require.NoError(t, err)

waitCtx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
Copy link
Contributor

@miparnisari miparnisari Nov 7, 2025 •
edited
Loading

Choose a reason for hiding this comment

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

why do we even have a timeout here..? i say let the thing take as long as it wants: remove the retry stuff and the waitCtx.

Copy link
Member Author

@josephschorr josephschorr Nov 10, 2025

Choose a reason for hiding this comment

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

I don't want the test to hang

Copy link
Contributor

@miparnisari miparnisari Nov 10, 2025 •
edited
Loading

Choose a reason for hiding this comment

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

it won't hang, that's what go test -timeout XXX is for: https://github.com/authzed/actions/blob/main/go-test/action.yaml#L11

ugh we don't use that action for these. can you add -timeout 20m to

spicedb/magefiles/util.go

Lines 42 to 51 in 03a31da

func testWithArgs(ctx context.Context, args ...string) ([]string, error) {
testArgs := append([]string{
"test",
"-failfast",
"-count=1",
"-race",
}, args...)
return testArgs, nil
}
?

Also FYI, github actions have a default timeout of 360 minutes per step.

defer cancel()

// Ensure the command completed successfully.
status, err := pool.Client.WaitContainerWithContext(resource.Container.ID, waitCtx)
if err != nil && retryCount < 4 {
// On error, retry a few times before failing
t.Logf("retrying migration for engine %s due to error: %v", engineKey, err)
continue
}

t.Cleanup(func() {
// When you're done, kill and remove the container
_ = pool.Purge(resource)
})
require.NoError(t, err)

if status != 0 {
stream := new(bytes.Buffer)

lerr := pool.Client.Logs(docker.LogsOptions{
Context: waitCtx,
OutputStream: stream,
ErrorStream: stream,
Stdout: true,
Stderr: true,
Container: resource.Container.ID,
})
require.NoError(t, lerr)

require.Fail(t, "Got non-zero exit code", stream.String())
}

t.Cleanup(func() {
// When you're done, kill and remove the container
_ = pool.Purge(resource)
})
}
})
}
}
Loading