Skip to content

Add optional flag to metricbeat modules to suppress health degradation on fetch errors #49492

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
Oddly wants to merge 1 commit into from
Closed

Add optional flag to metricbeat modules to suppress health degradation on fetch errors #49492

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
10 changes: 9 additions & 1 deletion metricbeat/mb/module/wrapper.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -77,6 +77,7 @@ type metricSetWrapper struct {

periodic bool // Set to true if this metricset is a periodic fetcher
failureThreshold uint // threshold of consecutive errors needed to set the stream as degraded
optional bool // When true, fetch failures do not degrade agent health
}

// stats bundles common metricset stats.
Expand Down Expand Up @@ -119,6 +120,7 @@ func createWrapper(module mb.Module, metricSets []mb.MetricSet, monitoring beatm

var streamHealthSettings struct {
FailureThreshold *uint `config:"failure_threshold"`
Optional *bool `config:"optional"`
}

err := module.UnpackConfig(&streamHealthSettings)
Expand All @@ -131,12 +133,18 @@ func createWrapper(module mb.Module, metricSets []mb.MetricSet, monitoring beatm
failureThreshold = *streamHealthSettings.FailureThreshold
}

optional := false
if streamHealthSettings.Optional != nil {
optional = *streamHealthSettings.Optional
}

for i, metricSet := range metricSets {
wrapper.metricSets[i] = &metricSetWrapper{
MetricSet: metricSet,
module: wrapper,
stats: getMetricSetStats(monitoring, wrapper.Name(), metricSet.Name()),
failureThreshold: failureThreshold,
optional: optional,
}
}
return wrapper, nil
Expand Down Expand Up @@ -324,7 +332,7 @@ func (msw *metricSetWrapper) handleFetchError(err error, reporter mb.PushReporte
default:
reporter.Error(err)
msw.stats.consecutiveFailures.Inc()
if msw.failureThreshold > 0 && msw.stats.consecutiveFailures != nil && uint(msw.stats.consecutiveFailures.Get()) >= msw.failureThreshold {
if !msw.optional && msw.failureThreshold > 0 && msw.stats.consecutiveFailures != nil && uint(msw.stats.consecutiveFailures.Get()) >= msw.failureThreshold {
// mark it as degraded for any other issue encountered
msw.module.UpdateStatus(status.Degraded, fmt.Sprintf("Error fetching data for metricset %s.%s: %v", msw.module.Name(), msw.Name(), err))
}
Expand Down
44 changes: 44 additions & 0 deletions metricbeat/mb/module/wrapper_internal_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -270,6 +270,50 @@ func TestWrapperHandleFetchErrorSync(t *testing.T) {
}
},
},
{
name: "optional = true: status never becomes DEGRADED regardless of errors",
config: newConfig(t, map[string]interface{}{
"module": mockModuleName,
"metricsets": []string{mockMetricSetName},
"period": "100ms",
"hosts": []string{"testhost"},
"optional": true,
}),
setup: func(t *testing.T, fetcher *mockReportingFetcher, pushReporter *mockPushReporterV2, statusReporter *mockStatusReporter) {
fetcher.On("Fetch", pushReporter).Return(fetchError).Times(5)
pushReporter.On("Error", fetchError).Return(true).Times(5)
},
iterations: 5,
assertIteration: func(t *testing.T, i int, msWrapper *metricSetWrapper, fetcher *mockReportingFetcher, pushReporter *mockPushReporterV2, statusReporter *mockStatusReporter) {
t.Logf("Assertion after iteration %d", i)
assert.Truef(t, statusReporter.AssertNotCalled(t, "UpdateStatus", status.Degraded, mock.AnythingOfType("string")), "optional stream should not be degraded at iteration %d", i)
assert.Equal(t, uint64(i+1), msWrapper.stats.consecutiveFailures.Get(), "consecutive failures should be tracked even for optional metricsets")
},
},
{
name: "optional = true: status returns to Running after recovery",
config: newConfig(t, map[string]interface{}{
"module": mockModuleName,
"metricsets": []string{mockMetricSetName},
"period": "100ms",
"hosts": []string{"testhost"},
"optional": true,
}),
setup: func(t *testing.T, fetcher *mockReportingFetcher, pushReporter *mockPushReporterV2, statusReporter *mockStatusReporter) {
fetcher.On("Fetch", pushReporter).Return(fetchError).Times(3)
fetcher.On("Fetch", pushReporter).Return(nil).Once()
pushReporter.On("Error", fetchError).Return(true).Times(3)
statusReporter.On("UpdateStatus", status.Running, mock.AnythingOfType("string")).Once()
},
iterations: 4,
assertIteration: func(t *testing.T, i int, msWrapper *metricSetWrapper, fetcher *mockReportingFetcher, pushReporter *mockPushReporterV2, statusReporter *mockStatusReporter) {
t.Logf("Assertion after iteration %d", i)
assert.Truef(t, statusReporter.AssertNotCalled(t, "UpdateStatus", status.Degraded, mock.AnythingOfType("string")), "optional stream should never be degraded at iteration %d", i)
if i == 3 {
assert.Truef(t, statusReporter.AssertCalled(t, "UpdateStatus", status.Running, mock.AnythingOfType("string")), "stream should be running after recovery at iteration %d", i)
}
},
},
}

for _, tc := range testcases {
Expand Down
Loading