TheArchive/tailscale
1
0
Fork 0
mirror of https://github.com/tailscale/tailscale.git synced 2025-12-15 20:12:04 +00:00
Code Issues Packages Projects Releases Wiki Activity

cmd/{containerboot,k8s-operator},k8s-operator: new options to expose user metrics (#14035)

Browse Source 
containerboot:

Adds 3 new environment variables for containerboot, `TS_LOCAL_ADDR_PORT` (default
`"${POD_IP}:9002"`), `TS_METRICS_ENABLED` (default `false`), and `TS_DEBUG_ADDR_PORT`
(default `""`), to configure metrics and debug endpoints. In a follow-up PR, the
health check endpoint will be updated to use the `TS_LOCAL_ADDR_PORT` if
`TS_HEALTHCHECK_ADDR_PORT` hasn't been set.

Users previously only had access to internal debug metrics (which are unstable
and not recommended) via passing the `--debug` flag to tailscaled, but can now
set `TS_METRICS_ENABLED=true` to expose the stable metrics documented at
https://tailscale.com/kb/1482/client-metrics at `/metrics` on the addr/port
specified by `TS_LOCAL_ADDR_PORT`.

Users can also now configure a debug endpoint more directly via the
`TS_DEBUG_ADDR_PORT` environment variable. This is not recommended for production
use, but exposes an internal set of debug metrics and pprof endpoints.

operator:

The `ProxyClass` CRD's `.spec.metrics.enable` field now enables serving the
stable user metrics documented at https://tailscale.com/kb/1482/client-metrics
at `/metrics` on the same "metrics" container port that debug metrics were
previously served on. To smooth the transition for anyone relying on the way the
operator previously consumed this field, we also _temporarily_ serve tailscaled's
internal debug metrics on the same `/debug/metrics` path as before, until 1.82.0
when debug metrics will be turned off by default even if `.spec.metrics.enable`
is set. At that point, anyone who wishes to continue using the internal debug
metrics (not recommended) will need to set the new `ProxyClass` field
`.spec.statefulSet.pod.tailscaleContainer.debug.enable`.

Users who wish to opt out of the transitional behaviour, where enabling
`.spec.metrics.enable` also enables debug metrics, can set
`.spec.statefulSet.pod.tailscaleContainer.debug.enable` to false (recommended).

Separately but related, the operator will no longer specify a host port for the
"metrics" container port definition. This caused scheduling conflicts when k8s
needs to schedule more than one proxy per node, and was not necessary for allowing
the pod's port to be exposed to prometheus scrapers.

Updates #11292

---------

Co-authored-by: Kristoffer Dalby <kristoffer@tailscale.com>
Signed-off-by: Tom Proctor <tomhjp@users.noreply.github.com>
This commit is contained in:
Tom Proctor
2024-11-22 15:41:07 +00:00
committed by GitHub
parent c59ab6baac
commit 74d4652144
14 changed files with 472 additions and 34 deletions
Download Patch File Download Diff File Expand all files Collapse all files

74
cmd/k8s-operator/sts_test.go
View File

@@ -125,10 +125,26 @@ func Test_applyProxyClassToStatefulSet(t *testing.T) {
},
},
}
proxyClassMetrics := &tsapi.ProxyClass{
Spec: tsapi.ProxyClassSpec{
Metrics: &tsapi.Metrics{Enable: true},
},
proxyClassWithMetricsDebug := func(metrics bool, debug *bool) *tsapi.ProxyClass {
return &tsapi.ProxyClass{
Spec: tsapi.ProxyClassSpec{
Metrics: &tsapi.Metrics{Enable: metrics},
StatefulSet: func() *tsapi.StatefulSet {
if debug == nil {
return nil
}
return &tsapi.StatefulSet{
Pod: &tsapi.Pod{
TailscaleContainer: &tsapi.Container{
Debug: &tsapi.Debug{Enable: *debug},
},
},
}
}(),
},
}
}
var userspaceProxySS, nonUserspaceProxySS appsv1.StatefulSet
@@ -184,7 +200,7 @@ func Test_applyProxyClassToStatefulSet(t *testing.T) {
gotSS := applyProxyClassToStatefulSet(proxyClassAllOpts, nonUserspaceProxySS.DeepCopy(), new(tailscaleSTSConfig), zl.Sugar())
if diff := cmp.Diff(gotSS, wantSS); diff != "" {
t.Fatalf("Unexpected result applying ProxyClass with all fields set to a StatefulSet for non-userspace proxy (-got +want):\n%s", diff)
t.Errorf("Unexpected result applying ProxyClass with all fields set to a StatefulSet for non-userspace proxy (-got +want):\n%s", diff)
}
// 2. Test that a ProxyClass with custom labels and annotations for
@@ -197,7 +213,7 @@ func Test_applyProxyClassToStatefulSet(t *testing.T) {
wantSS.Spec.Template.Annotations = proxyClassJustLabels.Spec.StatefulSet.Pod.Annotations
gotSS = applyProxyClassToStatefulSet(proxyClassJustLabels, nonUserspaceProxySS.DeepCopy(), new(tailscaleSTSConfig), zl.Sugar())
if diff := cmp.Diff(gotSS, wantSS); diff != "" {
t.Fatalf("Unexpected result applying ProxyClass with custom labels and annotations to a StatefulSet for non-userspace proxy (-got +want):\n%s", diff)
t.Errorf("Unexpected result applying ProxyClass with custom labels and annotations to a StatefulSet for non-userspace proxy (-got +want):\n%s", diff)
}
// 3. Test that a ProxyClass with all fields set gets correctly applied
@@ -221,7 +237,7 @@ func Test_applyProxyClassToStatefulSet(t *testing.T) {
wantSS.Spec.Template.Spec.Containers[0].Image = "ghcr.io/my-repo/tailscale:v0.01testsomething"
gotSS = applyProxyClassToStatefulSet(proxyClassAllOpts, userspaceProxySS.DeepCopy(), new(tailscaleSTSConfig), zl.Sugar())
if diff := cmp.Diff(gotSS, wantSS); diff != "" {
t.Fatalf("Unexpected result applying ProxyClass with all options to a StatefulSet for a userspace proxy (-got +want):\n%s", diff)
t.Errorf("Unexpected result applying ProxyClass with all options to a StatefulSet for a userspace proxy (-got +want):\n%s", diff)
}
// 4. Test that a ProxyClass with custom labels and annotations gets correctly applied
@@ -233,16 +249,48 @@ func Test_applyProxyClassToStatefulSet(t *testing.T) {
wantSS.Spec.Template.Annotations = proxyClassJustLabels.Spec.StatefulSet.Pod.Annotations
gotSS = applyProxyClassToStatefulSet(proxyClassJustLabels, userspaceProxySS.DeepCopy(), new(tailscaleSTSConfig), zl.Sugar())
if diff := cmp.Diff(gotSS, wantSS); diff != "" {
t.Fatalf("Unexpected result applying ProxyClass with custom labels and annotations to a StatefulSet for a userspace proxy (-got +want):\n%s", diff)
t.Errorf("Unexpected result applying ProxyClass with custom labels and annotations to a StatefulSet for a userspace proxy (-got +want):\n%s", diff)
}
// 5. Test that a ProxyClass with metrics enabled gets correctly applied to a StatefulSet.
// 5. Metrics enabled defaults to enabling both metrics and debug.
wantSS = nonUserspaceProxySS.DeepCopy()
wantSS.Spec.Template.Spec.Containers[0].Env = append(wantSS.Spec.Template.Spec.Containers[0].Env, corev1.EnvVar{Name: "TS_TAILSCALED_EXTRA_ARGS", Value: "--debug=$(POD_IP):9001"})
wantSS.Spec.Template.Spec.Containers[0].Ports = []corev1.ContainerPort{{Name: "metrics", Protocol: "TCP", ContainerPort: 9001, HostPort: 9001}}
gotSS = applyProxyClassToStatefulSet(proxyClassMetrics, nonUserspaceProxySS.DeepCopy(), new(tailscaleSTSConfig), zl.Sugar())
wantSS.Spec.Template.Spec.Containers[0].Env = append(wantSS.Spec.Template.Spec.Containers[0].Env,
corev1.EnvVar{Name: "TS_DEBUG_ADDR_PORT", Value: "$(POD_IP):9001"},
corev1.EnvVar{Name: "TS_TAILSCALED_EXTRA_ARGS", Value: "--debug=$(TS_DEBUG_ADDR_PORT)"},
corev1.EnvVar{Name: "TS_LOCAL_ADDR_PORT", Value: "$(POD_IP):9002"},
corev1.EnvVar{Name: "TS_METRICS_ENABLED", Value: "true"},
)
wantSS.Spec.Template.Spec.Containers[0].Ports = []corev1.ContainerPort{
{Name: "debug", Protocol: "TCP", ContainerPort: 9001},
{Name: "metrics", Protocol: "TCP", ContainerPort: 9002},
}
gotSS = applyProxyClassToStatefulSet(proxyClassWithMetricsDebug(true, nil), nonUserspaceProxySS.DeepCopy(), new(tailscaleSTSConfig), zl.Sugar())
if diff := cmp.Diff(gotSS, wantSS); diff != "" {
t.Fatalf("Unexpected result applying ProxyClass with metrics enabled to a StatefulSet (-got +want):\n%s", diff)
t.Errorf("Unexpected result applying ProxyClass with metrics enabled to a StatefulSet (-got +want):\n%s", diff)
}
// 6. Enable _just_ metrics by explicitly disabling debug.
wantSS = nonUserspaceProxySS.DeepCopy()
wantSS.Spec.Template.Spec.Containers[0].Env = append(wantSS.Spec.Template.Spec.Containers[0].Env,
corev1.EnvVar{Name: "TS_LOCAL_ADDR_PORT", Value: "$(POD_IP):9002"},
corev1.EnvVar{Name: "TS_METRICS_ENABLED", Value: "true"},
)
wantSS.Spec.Template.Spec.Containers[0].Ports = []corev1.ContainerPort{{Name: "metrics", Protocol: "TCP", ContainerPort: 9002}}
gotSS = applyProxyClassToStatefulSet(proxyClassWithMetricsDebug(true, ptr.To(false)), nonUserspaceProxySS.DeepCopy(), new(tailscaleSTSConfig), zl.Sugar())
if diff := cmp.Diff(gotSS, wantSS); diff != "" {
t.Errorf("Unexpected result applying ProxyClass with metrics enabled to a StatefulSet (-got +want):\n%s", diff)
}
// 7. Enable _just_ debug without metrics.
wantSS = nonUserspaceProxySS.DeepCopy()
wantSS.Spec.Template.Spec.Containers[0].Env = append(wantSS.Spec.Template.Spec.Containers[0].Env,
corev1.EnvVar{Name: "TS_DEBUG_ADDR_PORT", Value: "$(POD_IP):9001"},
corev1.EnvVar{Name: "TS_TAILSCALED_EXTRA_ARGS", Value: "--debug=$(TS_DEBUG_ADDR_PORT)"},
)
wantSS.Spec.Template.Spec.Containers[0].Ports = []corev1.ContainerPort{{Name: "debug", Protocol: "TCP", ContainerPort: 9001}}
gotSS = applyProxyClassToStatefulSet(proxyClassWithMetricsDebug(false, ptr.To(true)), nonUserspaceProxySS.DeepCopy(), new(tailscaleSTSConfig), zl.Sugar())
if diff := cmp.Diff(gotSS, wantSS); diff != "" {
t.Errorf("Unexpected result applying ProxyClass with metrics enabled to a StatefulSet (-got +want):\n%s", diff)
}
}