Skip to content

✨ added reconciles_total metric #239

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
merged 1 commit into from
Dec 19, 2018
Merged

✨ added reconciles_total metric #239

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
5 changes: 4 additions & 1 deletion pkg/internal/controller/controller.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -214,13 +214,15 @@ func (c *Controller) processNextWorkItem() bool {
c.Queue.AddRateLimited(req)
log.Error(err, "Reconciler error", "controller", c.Name, "request", req)
ctrlmetrics.ReconcileErrors.WithLabelValues(c.Name).Inc()

ctrlmetrics.ReconcileTotal.WithLabelValues(c.Name, "error").Inc()
return false
} else if result.RequeueAfter > 0 {
c.Queue.AddAfter(req, result.RequeueAfter)
ctrlmetrics.ReconcileTotal.WithLabelValues(c.Name, "requeue_after").Inc()
return true
} else if result.Requeue {
c.Queue.AddRateLimited(req)
ctrlmetrics.ReconcileTotal.WithLabelValues(c.Name, "requeue").Inc()
return true
}

Expand All @@ -231,6 +233,7 @@ func (c *Controller) processNextWorkItem() bool {
// TODO(directxman12): What does 1 mean? Do we want level constants? Do we want levels at all?
log.V(1).Info("Successfully Reconciled", "controller", c.Name, "request", req)

ctrlmetrics.ReconcileTotal.WithLabelValues(c.Name, "success").Inc()
// Return true, don't take a break
return true
}
Expand Down
130 changes: 127 additions & 3 deletions pkg/internal/controller/controller_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -408,14 +408,138 @@ var _ = Describe("controller", func() {
// TODO(community): write this test
})

Context("prometheus metric reconcile_total", func() {
var reconcileTotal dto.Metric

BeforeEach(func() {
ctrlmetrics.ReconcileTotal.Reset()
reconcileTotal.Reset()
})

It("should get updated on successful reconciliation", func(done Done) {
Expect(func() error {
ctrlmetrics.ReconcileTotal.WithLabelValues(ctrl.Name, "success").Write(&reconcileTotal)
if reconcileTotal.GetCounter().GetValue() != 0.0 {
return fmt.Errorf("metric reconcile total not reset")
}
return nil
}()).Should(Succeed())

go func() {
defer GinkgoRecover()
Expect(ctrl.Start(stop)).NotTo(HaveOccurred())
}()
By("Invoking Reconciler which will succeed")
ctrl.Queue.Add(request)

Expect(<-reconciled).To(Equal(request))
Eventually(func() error {
ctrlmetrics.ReconcileTotal.WithLabelValues(ctrl.Name, "success").Write(&reconcileTotal)
if actual := reconcileTotal.GetCounter().GetValue(); actual != 1.0 {
return fmt.Errorf("metric reconcile total expected: %v and got: %v", 1.0, actual)
}
return nil
}, 2.0).Should(Succeed())

close(done)
}, 2.0)

It("should get updated on reconcile errors", func(done Done) {
Expect(func() error {
ctrlmetrics.ReconcileTotal.WithLabelValues(ctrl.Name, "error").Write(&reconcileTotal)
if reconcileTotal.GetCounter().GetValue() != 0.0 {
return fmt.Errorf("metric reconcile total not reset")
}
return nil
}()).Should(Succeed())

fakeReconcile.Err = fmt.Errorf("expected error: reconcile")
go func() {
defer GinkgoRecover()
Expect(ctrl.Start(stop)).NotTo(HaveOccurred())
}()
By("Invoking Reconciler which will give an error")
ctrl.Queue.Add(request)

Expect(<-reconciled).To(Equal(request))
Eventually(func() error {
ctrlmetrics.ReconcileTotal.WithLabelValues(ctrl.Name, "error").Write(&reconcileTotal)
if actual := reconcileTotal.GetCounter().GetValue(); actual != 1.0 {
return fmt.Errorf("metric reconcile total expected: %v and got: %v", 1.0, actual)
}
return nil
}, 2.0).Should(Succeed())

close(done)
}, 2.0)

It("should get updated when reconcile returns with retry enabled", func(done Done) {
Expect(func() error {
ctrlmetrics.ReconcileTotal.WithLabelValues(ctrl.Name, "retry").Write(&reconcileTotal)
if reconcileTotal.GetCounter().GetValue() != 0.0 {
return fmt.Errorf("metric reconcile total not reset")
}
return nil
}()).Should(Succeed())

fakeReconcile.Result.Requeue = true
go func() {
defer GinkgoRecover()
Expect(ctrl.Start(stop)).NotTo(HaveOccurred())
}()
By("Invoking Reconciler which will return result with Requeue enabled")
ctrl.Queue.Add(request)

Expect(<-reconciled).To(Equal(request))
Eventually(func() error {
ctrlmetrics.ReconcileTotal.WithLabelValues(ctrl.Name, "requeue").Write(&reconcileTotal)
if actual := reconcileTotal.GetCounter().GetValue(); actual != 1.0 {
return fmt.Errorf("metric reconcile total expected: %v and got: %v", 1.0, actual)
}
return nil
}, 2.0).Should(Succeed())

close(done)
}, 2.0)

It("should get updated when reconcile returns with retryAfter enabled", func(done Done) {
Expect(func() error {
ctrlmetrics.ReconcileTotal.WithLabelValues(ctrl.Name, "retry_after").Write(&reconcileTotal)
if reconcileTotal.GetCounter().GetValue() != 0.0 {
return fmt.Errorf("metric reconcile total not reset")
}
return nil
}()).Should(Succeed())

fakeReconcile.Result.RequeueAfter = 5 * time.Hour
go func() {
defer GinkgoRecover()
Expect(ctrl.Start(stop)).NotTo(HaveOccurred())
}()
By("Invoking Reconciler which will return result with requeueAfter enabled")
ctrl.Queue.Add(request)

Expect(<-reconciled).To(Equal(request))
Eventually(func() error {
ctrlmetrics.ReconcileTotal.WithLabelValues(ctrl.Name, "requeue_after").Write(&reconcileTotal)
if actual := reconcileTotal.GetCounter().GetValue(); actual != 1.0 {
return fmt.Errorf("metric reconcile total expected: %v and got: %v", 1.0, actual)
}
return nil
}, 2.0).Should(Succeed())

close(done)
}, 2.0)
})

Context("should update prometheus metrics", func() {
It("should requeue a Request if there is an error and continue processing items", func(done Done) {
var queueLength, reconcileErrs dto.Metric
ctrlmetrics.QueueLength.Reset()
Expect(func() error {
ctrlmetrics.QueueLength.WithLabelValues(ctrl.Name).Write(&queueLength)
if queueLength.GetGauge().GetValue() != 0.0 {
return fmt.Errorf("metrics not reset")
return fmt.Errorf("metric queue length not reset")
}
return nil
}()).Should(Succeed())
Expand All @@ -424,7 +548,7 @@ var _ = Describe("controller", func() {
Expect(func() error {
ctrlmetrics.ReconcileErrors.WithLabelValues(ctrl.Name).Write(&reconcileErrs)
if reconcileErrs.GetCounter().GetValue() != 0.0 {
return fmt.Errorf("metrics not reset")
return fmt.Errorf("metric reconcile errors not reset")
}
return nil
}()).Should(Succeed())
Expand All @@ -444,7 +568,7 @@ var _ = Describe("controller", func() {
Eventually(func() error {
ctrlmetrics.QueueLength.WithLabelValues(ctrl.Name).Write(&queueLength)
if queueLength.GetGauge().GetValue() != 1.0 {
return fmt.Errorf("metrics not updated")
return fmt.Errorf("metric queue length not updated")
}
return nil
}, 2.0).Should(Succeed())
Expand Down
16 changes: 13 additions & 3 deletions pkg/internal/controller/metrics/metrics.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,24 +29,34 @@ var (
Help: "Length of reconcile queue per controller",
}, []string{"controller"})

// ReconcileTotal is a prometheus counter metrics which holds the total
// number of reconciliations per controller. It has two labels. controller label refers
// to the controller name and result label refers to the reconcile result i.e
// success, error, requeue, requeue_after
ReconcileTotal = prometheus.NewCounterVec(prometheus.CounterOpts{
Name: "controller_runtime_reconcile_total",
Help: "Total number of reconciliations per controller",
}, []string{"controller", "result"})

// ReconcileErrors is a prometheus counter metrics which holds the total
// number of errors from the Reconciler
ReconcileErrors = prometheus.NewCounterVec(prometheus.CounterOpts{
Name: "controller_runtime_reconcile_errors_total",
Help: "Total number of reconcile errors per controller",
Help: "Total number of reconciliation errors per controller",
}, []string{"controller"})

// ReconcileTime is a prometheus metric which keeps track of the duration
// of reconciles
// of reconciliations
ReconcileTime = prometheus.NewHistogramVec(prometheus.HistogramOpts{
Name: "controller_runtime_reconcile_time_seconds",
Help: "Length of time per reconcile per controller",
Help: "Length of time per reconciliation per controller",
}, []string{"controller"})
)

func init() {
metrics.Registry.MustRegister(
QueueLength,
ReconcileTotal,
ReconcileErrors,
Copy link
Member

Choose a reason for hiding this comment

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

Will ReconcileErrors still be useful if we have ReconcileTotal with label result=error?

Copy link
Member

Choose a reason for hiding this comment

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

Are these 2 identical actually?

Copy link
Contributor Author

Choose a reason for hiding this comment

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

Yes, they will be identical. Will do a separate PR where we drop support for ReconcileErrors.

ReconcileTime,
// expose process metrics like CPU, Memory, file descriptor usage etc.
Expand Down