opensource/coder
3
0
Fork 0
mirror of https://github.com/coder/coder.git synced 2026-09-24 15:04:27 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix(coderd): poll for metrics in TestWorkspaceProvisionerdServerMetrics (#22644)

Browse Source 
## Problem

`TestWorkspaceProvisionerdServerMetrics` flakes because metric
assertions run immediately after
`AwaitWorkspaceBuildJobCompleted` returns, but metrics are updated
**asynchronously after the
DB transaction commits** in `completeWorkspaceBuildJob`.

The timeline in the provisioner server:
1. DB transaction commits (`provisionerdserver.go:~2362`) — job marked
completed
2. Audit logging, notifications, DB queries (`~2370-2427`)
3. **Metric `.Observe()`** (`~2463`) — happens ~100 lines later

The test synchronization (`AwaitWorkspaceBuildJobCompleted`) polls for
`CompletedAt != nil`,
which fires at step 1. The metric assertion then executes before step 3,
causing the flake.

## Fix

Wrap all three metric assertions (prebuild creation, prebuild claim,
regular workspace
creation) in `require.Eventually` to poll until the metric appears, then
assert on the value.

## Test

- `go test -run TestWorkspaceProvisionerdServerMetrics -count=5` — all
pass
- `go test -race -run TestWorkspaceProvisionerdServerMetrics -count=1` —
clean
This commit is contained in:
Kyle Carberry
2026-03-04 22:30:36 -05:00
committed by GitHub
parent 5630390d94
commit 219d02bdc3
1 changed files with 27 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files
enterprise/coderd/workspaces_test.go
+27 -12
View File
@@ -3022,14 +3022,19 @@ func TestWorkspaceProvisionerdServerMetrics(t *testing.T) {
runningPrebuilds := coderdenttest.GetRunningPrebuilds(ctx, t, db, 1)
require.Len(t, runningPrebuilds, 1)
// Then: the histogram value for prebuilt workspace creation should be updated
prebuildCreationHistogram := promhelp.HistogramValue(t, reg, "coderd_workspace_creation_duration_seconds", prometheus.Labels{
// Then: the histogram value for prebuilt workspace creation should be updated.
// The metric is updated asynchronously after the DB transaction commits,
// so we need to poll for it.
prebuildCreationLabels := prometheus.Labels{
"organization_name": organizationName.Name,
"template_name": templatePrebuild.Name,
"preset_name": presetsPrebuild[0].Name,
"type": "prebuild",
})
require.NotNil(t, prebuildCreationHistogram)
}
require.Eventually(t, func() bool {
return promhelp.MetricValue(t, reg, "coderd_workspace_creation_duration_seconds", prebuildCreationLabels) != nil
}, testutil.WaitShort, testutil.IntervalFast)
prebuildCreationHistogram := promhelp.HistogramValue(t, reg, "coderd_workspace_creation_duration_seconds", prebuildCreationLabels)
require.Equal(t, uint64(1), prebuildCreationHistogram.GetSampleCount())
// Given: a running prebuilt workspace, ready to be claimed
@@ -3050,13 +3055,18 @@ func TestWorkspaceProvisionerdServerMetrics(t *testing.T) {
workspace := coderdenttest.MustClaimPrebuild(ctx, t, client, userClient, user.Username, versionPrebuild, presetsPrebuild[0].ID)
require.Equal(t, prebuild.ID, workspace.ID)
// Then: the histogram value for prebuilt workspace claim should be updated
prebuildClaimHistogram := promhelp.HistogramValue(t, reg, "coderd_prebuilt_workspace_claim_duration_seconds", prometheus.Labels{
// Then: the histogram value for prebuilt workspace claim should be updated.
// The metric is updated asynchronously after the DB transaction commits,
// so we need to poll for it.
prebuildClaimLabels := prometheus.Labels{
"organization_name": organizationName.Name,
"template_name": templatePrebuild.Name,
"preset_name": presetsPrebuild[0].Name,
})
require.NotNil(t, prebuildClaimHistogram)
}
require.Eventually(t, func() bool {
return promhelp.MetricValue(t, reg, "coderd_prebuilt_workspace_claim_duration_seconds", prebuildClaimLabels) != nil
}, testutil.WaitShort, testutil.IntervalFast)
prebuildClaimHistogram := promhelp.HistogramValue(t, reg, "coderd_prebuilt_workspace_claim_duration_seconds", prebuildClaimLabels)
require.Equal(t, uint64(1), prebuildClaimHistogram.GetSampleCount())
// Given: no histogram value for regular workspaces creation
@@ -3077,14 +3087,19 @@ func TestWorkspaceProvisionerdServerMetrics(t *testing.T) {
require.NoError(t, err)
coderdtest.AwaitWorkspaceBuildJobCompleted(t, client, regularWorkspace.LatestBuild.ID)
// Then: the histogram value for regular workspace creation should be updated
regularWorkspaceHistogram := promhelp.HistogramValue(t, reg, "coderd_workspace_creation_duration_seconds", prometheus.Labels{
// Then: the histogram value for regular workspace creation should be updated.
// The metric is updated asynchronously after the DB transaction commits,
// so we need to poll for it.
regularWorkspaceLabels := prometheus.Labels{
"organization_name": organizationName.Name,
"template_name": templateNoPrebuild.Name,
"preset_name": presetsNoPrebuild[0].Name,
"type": "regular",
})
require.NotNil(t, regularWorkspaceHistogram)
}
require.Eventually(t, func() bool {
return promhelp.MetricValue(t, reg, "coderd_workspace_creation_duration_seconds", regularWorkspaceLabels) != nil
}, testutil.WaitShort, testutil.IntervalFast)
regularWorkspaceHistogram := promhelp.HistogramValue(t, reg, "coderd_workspace_creation_duration_seconds", regularWorkspaceLabels)
require.Equal(t, uint64(1), regularWorkspaceHistogram.GetSampleCount())
}