From 765b13f15aabbd8bfd9c7475cc5b20da8a768c62 Mon Sep 17 00:00:00 2001 From: Patrick Ohly Date: Tue, 15 Jun 2021 09:52:09 +0200 Subject: [PATCH] deploy: revise probe settings Containers remained in the "not ready" state for a noticable amount of time, probably because the startup probe failed and then only checked again after 10 seconds. These delays caused test failures and slowed down testing. With the previous values, `make test_e2e TEST_E2E_FOCUS=operator.*API.*switch.device.mode` ran for 1370 seconds and had one failure. With the new values, it finished successfully in 617 seconds. --- deploy/kubernetes-1.19/direct/pmem-csi.yaml | 23 +++++++++++------ .../direct/testing/pmem-csi.yaml | 23 +++++++++++------ deploy/kubernetes-1.19/lvm/pmem-csi.yaml | 23 +++++++++++------ .../kubernetes-1.19/lvm/testing/pmem-csi.yaml | 23 +++++++++++------ .../pmem-csi-direct-testing.yaml | 23 +++++++++++------ deploy/kubernetes-1.19/pmem-csi-direct.yaml | 23 +++++++++++------ .../kubernetes-1.19/pmem-csi-lvm-testing.yaml | 23 +++++++++++------ deploy/kubernetes-1.19/pmem-csi-lvm.yaml | 23 +++++++++++------ deploy/kubernetes-1.20/direct/pmem-csi.yaml | 23 +++++++++++------ .../direct/testing/pmem-csi.yaml | 23 +++++++++++------ deploy/kubernetes-1.20/lvm/pmem-csi.yaml | 23 +++++++++++------ .../kubernetes-1.20/lvm/testing/pmem-csi.yaml | 23 +++++++++++------ .../pmem-csi-direct-testing.yaml | 23 +++++++++++------ deploy/kubernetes-1.20/pmem-csi-direct.yaml | 23 +++++++++++------ .../kubernetes-1.20/pmem-csi-lvm-testing.yaml | 23 +++++++++++------ deploy/kubernetes-1.20/pmem-csi-lvm.yaml | 23 +++++++++++------ deploy/kubernetes-1.21/direct/pmem-csi.yaml | 23 +++++++++++------ .../direct/testing/pmem-csi.yaml | 23 +++++++++++------ deploy/kubernetes-1.21/lvm/pmem-csi.yaml | 23 +++++++++++------ .../kubernetes-1.21/lvm/testing/pmem-csi.yaml | 23 +++++++++++------ .../pmem-csi-direct-testing.yaml | 23 +++++++++++------ deploy/kubernetes-1.21/pmem-csi-direct.yaml | 23 +++++++++++------ .../kubernetes-1.21/pmem-csi-lvm-testing.yaml | 23 +++++++++++------ deploy/kubernetes-1.21/pmem-csi-lvm.yaml | 23 +++++++++++------ .../kustomize/patches/metrics-controller.yaml | 20 ++++++++++++--- deploy/kustomize/patches/metrics-node.yaml | 25 ++++++++----------- .../deployment/controller_driver.go | 15 +++++------ 27 files changed, 419 insertions(+), 193 deletions(-) diff --git a/deploy/kubernetes-1.19/direct/pmem-csi.yaml b/deploy/kubernetes-1.19/direct/pmem-csi.yaml index adf076557..69c572781 100644 --- a/deploy/kubernetes-1.19/direct/pmem-csi.yaml +++ b/deploy/kubernetes-1.19/direct/pmem-csi.yaml @@ -381,7 +381,7 @@ spec: image: intel/pmem-csi-driver:canary imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -399,6 +399,15 @@ spec: memory: 128Mi securityContext: readOnlyRootFilesystem: true + startupProbe: + failureThreshold: 60 + httpGet: + path: /metrics + port: metrics + scheme: HTTP + periodSeconds: 1 + successThreshold: 1 + timeoutSeconds: 5 terminationMessagePath: /dev/termination-log volumeMounts: - mountPath: /certs @@ -473,7 +482,7 @@ spec: image: intel/pmem-csi-driver:canary imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -493,12 +502,12 @@ spec: privileged: true runAsUser: 0 startupProbe: - failureThreshold: 30 + failureThreshold: 300 httpGet: path: /metrics port: metrics scheme: HTTP - periodSeconds: 10 + periodSeconds: 1 successThreshold: 1 timeoutSeconds: 5 terminationMessagePath: /tmp/termination-log @@ -562,7 +571,7 @@ spec: image: k8s.gcr.io/sig-storage/csi-provisioner:v2.2.2 imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -581,12 +590,12 @@ spec: securityContext: readOnlyRootFilesystem: true startupProbe: - failureThreshold: 30 + failureThreshold: 300 httpGet: path: /metrics port: metrics scheme: HTTP - periodSeconds: 10 + periodSeconds: 1 successThreshold: 1 timeoutSeconds: 5 volumeMounts: diff --git a/deploy/kubernetes-1.19/direct/testing/pmem-csi.yaml b/deploy/kubernetes-1.19/direct/testing/pmem-csi.yaml index 16514d9c6..5fa4ed4d9 100644 --- a/deploy/kubernetes-1.19/direct/testing/pmem-csi.yaml +++ b/deploy/kubernetes-1.19/direct/testing/pmem-csi.yaml @@ -383,7 +383,7 @@ spec: image: intel/pmem-csi-driver-test:canary imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -401,6 +401,15 @@ spec: memory: 128Mi securityContext: readOnlyRootFilesystem: true + startupProbe: + failureThreshold: 60 + httpGet: + path: /metrics + port: metrics + scheme: HTTP + periodSeconds: 1 + successThreshold: 1 + timeoutSeconds: 5 terminationMessagePath: /dev/termination-log volumeMounts: - mountPath: /certs @@ -497,7 +506,7 @@ spec: image: intel/pmem-csi-driver-test:canary imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -517,12 +526,12 @@ spec: privileged: true runAsUser: 0 startupProbe: - failureThreshold: 30 + failureThreshold: 300 httpGet: path: /metrics port: metrics scheme: HTTP - periodSeconds: 10 + periodSeconds: 1 successThreshold: 1 timeoutSeconds: 5 terminationMessagePath: /tmp/termination-log @@ -590,7 +599,7 @@ spec: image: k8s.gcr.io/sig-storage/csi-provisioner:v2.2.2 imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -609,12 +618,12 @@ spec: securityContext: readOnlyRootFilesystem: true startupProbe: - failureThreshold: 30 + failureThreshold: 300 httpGet: path: /metrics port: metrics scheme: HTTP - periodSeconds: 10 + periodSeconds: 1 successThreshold: 1 timeoutSeconds: 5 volumeMounts: diff --git a/deploy/kubernetes-1.19/lvm/pmem-csi.yaml b/deploy/kubernetes-1.19/lvm/pmem-csi.yaml index 791f9c1c7..ed6404946 100644 --- a/deploy/kubernetes-1.19/lvm/pmem-csi.yaml +++ b/deploy/kubernetes-1.19/lvm/pmem-csi.yaml @@ -381,7 +381,7 @@ spec: image: intel/pmem-csi-driver:canary imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -399,6 +399,15 @@ spec: memory: 128Mi securityContext: readOnlyRootFilesystem: true + startupProbe: + failureThreshold: 60 + httpGet: + path: /metrics + port: metrics + scheme: HTTP + periodSeconds: 1 + successThreshold: 1 + timeoutSeconds: 5 terminationMessagePath: /dev/termination-log volumeMounts: - mountPath: /certs @@ -473,7 +482,7 @@ spec: image: intel/pmem-csi-driver:canary imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -493,12 +502,12 @@ spec: privileged: true runAsUser: 0 startupProbe: - failureThreshold: 30 + failureThreshold: 300 httpGet: path: /metrics port: metrics scheme: HTTP - periodSeconds: 10 + periodSeconds: 1 successThreshold: 1 timeoutSeconds: 5 terminationMessagePath: /tmp/termination-log @@ -562,7 +571,7 @@ spec: image: k8s.gcr.io/sig-storage/csi-provisioner:v2.2.2 imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -581,12 +590,12 @@ spec: securityContext: readOnlyRootFilesystem: true startupProbe: - failureThreshold: 30 + failureThreshold: 300 httpGet: path: /metrics port: metrics scheme: HTTP - periodSeconds: 10 + periodSeconds: 1 successThreshold: 1 timeoutSeconds: 5 volumeMounts: diff --git a/deploy/kubernetes-1.19/lvm/testing/pmem-csi.yaml b/deploy/kubernetes-1.19/lvm/testing/pmem-csi.yaml index 4bf1f411c..4ae9f86f0 100644 --- a/deploy/kubernetes-1.19/lvm/testing/pmem-csi.yaml +++ b/deploy/kubernetes-1.19/lvm/testing/pmem-csi.yaml @@ -383,7 +383,7 @@ spec: image: intel/pmem-csi-driver-test:canary imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -401,6 +401,15 @@ spec: memory: 128Mi securityContext: readOnlyRootFilesystem: true + startupProbe: + failureThreshold: 60 + httpGet: + path: /metrics + port: metrics + scheme: HTTP + periodSeconds: 1 + successThreshold: 1 + timeoutSeconds: 5 terminationMessagePath: /dev/termination-log volumeMounts: - mountPath: /certs @@ -497,7 +506,7 @@ spec: image: intel/pmem-csi-driver-test:canary imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -517,12 +526,12 @@ spec: privileged: true runAsUser: 0 startupProbe: - failureThreshold: 30 + failureThreshold: 300 httpGet: path: /metrics port: metrics scheme: HTTP - periodSeconds: 10 + periodSeconds: 1 successThreshold: 1 timeoutSeconds: 5 terminationMessagePath: /tmp/termination-log @@ -590,7 +599,7 @@ spec: image: k8s.gcr.io/sig-storage/csi-provisioner:v2.2.2 imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -609,12 +618,12 @@ spec: securityContext: readOnlyRootFilesystem: true startupProbe: - failureThreshold: 30 + failureThreshold: 300 httpGet: path: /metrics port: metrics scheme: HTTP - periodSeconds: 10 + periodSeconds: 1 successThreshold: 1 timeoutSeconds: 5 volumeMounts: diff --git a/deploy/kubernetes-1.19/pmem-csi-direct-testing.yaml b/deploy/kubernetes-1.19/pmem-csi-direct-testing.yaml index 16514d9c6..5fa4ed4d9 100644 --- a/deploy/kubernetes-1.19/pmem-csi-direct-testing.yaml +++ b/deploy/kubernetes-1.19/pmem-csi-direct-testing.yaml @@ -383,7 +383,7 @@ spec: image: intel/pmem-csi-driver-test:canary imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -401,6 +401,15 @@ spec: memory: 128Mi securityContext: readOnlyRootFilesystem: true + startupProbe: + failureThreshold: 60 + httpGet: + path: /metrics + port: metrics + scheme: HTTP + periodSeconds: 1 + successThreshold: 1 + timeoutSeconds: 5 terminationMessagePath: /dev/termination-log volumeMounts: - mountPath: /certs @@ -497,7 +506,7 @@ spec: image: intel/pmem-csi-driver-test:canary imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -517,12 +526,12 @@ spec: privileged: true runAsUser: 0 startupProbe: - failureThreshold: 30 + failureThreshold: 300 httpGet: path: /metrics port: metrics scheme: HTTP - periodSeconds: 10 + periodSeconds: 1 successThreshold: 1 timeoutSeconds: 5 terminationMessagePath: /tmp/termination-log @@ -590,7 +599,7 @@ spec: image: k8s.gcr.io/sig-storage/csi-provisioner:v2.2.2 imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -609,12 +618,12 @@ spec: securityContext: readOnlyRootFilesystem: true startupProbe: - failureThreshold: 30 + failureThreshold: 300 httpGet: path: /metrics port: metrics scheme: HTTP - periodSeconds: 10 + periodSeconds: 1 successThreshold: 1 timeoutSeconds: 5 volumeMounts: diff --git a/deploy/kubernetes-1.19/pmem-csi-direct.yaml b/deploy/kubernetes-1.19/pmem-csi-direct.yaml index adf076557..69c572781 100644 --- a/deploy/kubernetes-1.19/pmem-csi-direct.yaml +++ b/deploy/kubernetes-1.19/pmem-csi-direct.yaml @@ -381,7 +381,7 @@ spec: image: intel/pmem-csi-driver:canary imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -399,6 +399,15 @@ spec: memory: 128Mi securityContext: readOnlyRootFilesystem: true + startupProbe: + failureThreshold: 60 + httpGet: + path: /metrics + port: metrics + scheme: HTTP + periodSeconds: 1 + successThreshold: 1 + timeoutSeconds: 5 terminationMessagePath: /dev/termination-log volumeMounts: - mountPath: /certs @@ -473,7 +482,7 @@ spec: image: intel/pmem-csi-driver:canary imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -493,12 +502,12 @@ spec: privileged: true runAsUser: 0 startupProbe: - failureThreshold: 30 + failureThreshold: 300 httpGet: path: /metrics port: metrics scheme: HTTP - periodSeconds: 10 + periodSeconds: 1 successThreshold: 1 timeoutSeconds: 5 terminationMessagePath: /tmp/termination-log @@ -562,7 +571,7 @@ spec: image: k8s.gcr.io/sig-storage/csi-provisioner:v2.2.2 imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -581,12 +590,12 @@ spec: securityContext: readOnlyRootFilesystem: true startupProbe: - failureThreshold: 30 + failureThreshold: 300 httpGet: path: /metrics port: metrics scheme: HTTP - periodSeconds: 10 + periodSeconds: 1 successThreshold: 1 timeoutSeconds: 5 volumeMounts: diff --git a/deploy/kubernetes-1.19/pmem-csi-lvm-testing.yaml b/deploy/kubernetes-1.19/pmem-csi-lvm-testing.yaml index 4bf1f411c..4ae9f86f0 100644 --- a/deploy/kubernetes-1.19/pmem-csi-lvm-testing.yaml +++ b/deploy/kubernetes-1.19/pmem-csi-lvm-testing.yaml @@ -383,7 +383,7 @@ spec: image: intel/pmem-csi-driver-test:canary imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -401,6 +401,15 @@ spec: memory: 128Mi securityContext: readOnlyRootFilesystem: true + startupProbe: + failureThreshold: 60 + httpGet: + path: /metrics + port: metrics + scheme: HTTP + periodSeconds: 1 + successThreshold: 1 + timeoutSeconds: 5 terminationMessagePath: /dev/termination-log volumeMounts: - mountPath: /certs @@ -497,7 +506,7 @@ spec: image: intel/pmem-csi-driver-test:canary imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -517,12 +526,12 @@ spec: privileged: true runAsUser: 0 startupProbe: - failureThreshold: 30 + failureThreshold: 300 httpGet: path: /metrics port: metrics scheme: HTTP - periodSeconds: 10 + periodSeconds: 1 successThreshold: 1 timeoutSeconds: 5 terminationMessagePath: /tmp/termination-log @@ -590,7 +599,7 @@ spec: image: k8s.gcr.io/sig-storage/csi-provisioner:v2.2.2 imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -609,12 +618,12 @@ spec: securityContext: readOnlyRootFilesystem: true startupProbe: - failureThreshold: 30 + failureThreshold: 300 httpGet: path: /metrics port: metrics scheme: HTTP - periodSeconds: 10 + periodSeconds: 1 successThreshold: 1 timeoutSeconds: 5 volumeMounts: diff --git a/deploy/kubernetes-1.19/pmem-csi-lvm.yaml b/deploy/kubernetes-1.19/pmem-csi-lvm.yaml index 791f9c1c7..ed6404946 100644 --- a/deploy/kubernetes-1.19/pmem-csi-lvm.yaml +++ b/deploy/kubernetes-1.19/pmem-csi-lvm.yaml @@ -381,7 +381,7 @@ spec: image: intel/pmem-csi-driver:canary imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -399,6 +399,15 @@ spec: memory: 128Mi securityContext: readOnlyRootFilesystem: true + startupProbe: + failureThreshold: 60 + httpGet: + path: /metrics + port: metrics + scheme: HTTP + periodSeconds: 1 + successThreshold: 1 + timeoutSeconds: 5 terminationMessagePath: /dev/termination-log volumeMounts: - mountPath: /certs @@ -473,7 +482,7 @@ spec: image: intel/pmem-csi-driver:canary imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -493,12 +502,12 @@ spec: privileged: true runAsUser: 0 startupProbe: - failureThreshold: 30 + failureThreshold: 300 httpGet: path: /metrics port: metrics scheme: HTTP - periodSeconds: 10 + periodSeconds: 1 successThreshold: 1 timeoutSeconds: 5 terminationMessagePath: /tmp/termination-log @@ -562,7 +571,7 @@ spec: image: k8s.gcr.io/sig-storage/csi-provisioner:v2.2.2 imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -581,12 +590,12 @@ spec: securityContext: readOnlyRootFilesystem: true startupProbe: - failureThreshold: 30 + failureThreshold: 300 httpGet: path: /metrics port: metrics scheme: HTTP - periodSeconds: 10 + periodSeconds: 1 successThreshold: 1 timeoutSeconds: 5 volumeMounts: diff --git a/deploy/kubernetes-1.20/direct/pmem-csi.yaml b/deploy/kubernetes-1.20/direct/pmem-csi.yaml index adf076557..69c572781 100644 --- a/deploy/kubernetes-1.20/direct/pmem-csi.yaml +++ b/deploy/kubernetes-1.20/direct/pmem-csi.yaml @@ -381,7 +381,7 @@ spec: image: intel/pmem-csi-driver:canary imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -399,6 +399,15 @@ spec: memory: 128Mi securityContext: readOnlyRootFilesystem: true + startupProbe: + failureThreshold: 60 + httpGet: + path: /metrics + port: metrics + scheme: HTTP + periodSeconds: 1 + successThreshold: 1 + timeoutSeconds: 5 terminationMessagePath: /dev/termination-log volumeMounts: - mountPath: /certs @@ -473,7 +482,7 @@ spec: image: intel/pmem-csi-driver:canary imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -493,12 +502,12 @@ spec: privileged: true runAsUser: 0 startupProbe: - failureThreshold: 30 + failureThreshold: 300 httpGet: path: /metrics port: metrics scheme: HTTP - periodSeconds: 10 + periodSeconds: 1 successThreshold: 1 timeoutSeconds: 5 terminationMessagePath: /tmp/termination-log @@ -562,7 +571,7 @@ spec: image: k8s.gcr.io/sig-storage/csi-provisioner:v2.2.2 imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -581,12 +590,12 @@ spec: securityContext: readOnlyRootFilesystem: true startupProbe: - failureThreshold: 30 + failureThreshold: 300 httpGet: path: /metrics port: metrics scheme: HTTP - periodSeconds: 10 + periodSeconds: 1 successThreshold: 1 timeoutSeconds: 5 volumeMounts: diff --git a/deploy/kubernetes-1.20/direct/testing/pmem-csi.yaml b/deploy/kubernetes-1.20/direct/testing/pmem-csi.yaml index 16514d9c6..5fa4ed4d9 100644 --- a/deploy/kubernetes-1.20/direct/testing/pmem-csi.yaml +++ b/deploy/kubernetes-1.20/direct/testing/pmem-csi.yaml @@ -383,7 +383,7 @@ spec: image: intel/pmem-csi-driver-test:canary imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -401,6 +401,15 @@ spec: memory: 128Mi securityContext: readOnlyRootFilesystem: true + startupProbe: + failureThreshold: 60 + httpGet: + path: /metrics + port: metrics + scheme: HTTP + periodSeconds: 1 + successThreshold: 1 + timeoutSeconds: 5 terminationMessagePath: /dev/termination-log volumeMounts: - mountPath: /certs @@ -497,7 +506,7 @@ spec: image: intel/pmem-csi-driver-test:canary imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -517,12 +526,12 @@ spec: privileged: true runAsUser: 0 startupProbe: - failureThreshold: 30 + failureThreshold: 300 httpGet: path: /metrics port: metrics scheme: HTTP - periodSeconds: 10 + periodSeconds: 1 successThreshold: 1 timeoutSeconds: 5 terminationMessagePath: /tmp/termination-log @@ -590,7 +599,7 @@ spec: image: k8s.gcr.io/sig-storage/csi-provisioner:v2.2.2 imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -609,12 +618,12 @@ spec: securityContext: readOnlyRootFilesystem: true startupProbe: - failureThreshold: 30 + failureThreshold: 300 httpGet: path: /metrics port: metrics scheme: HTTP - periodSeconds: 10 + periodSeconds: 1 successThreshold: 1 timeoutSeconds: 5 volumeMounts: diff --git a/deploy/kubernetes-1.20/lvm/pmem-csi.yaml b/deploy/kubernetes-1.20/lvm/pmem-csi.yaml index 791f9c1c7..ed6404946 100644 --- a/deploy/kubernetes-1.20/lvm/pmem-csi.yaml +++ b/deploy/kubernetes-1.20/lvm/pmem-csi.yaml @@ -381,7 +381,7 @@ spec: image: intel/pmem-csi-driver:canary imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -399,6 +399,15 @@ spec: memory: 128Mi securityContext: readOnlyRootFilesystem: true + startupProbe: + failureThreshold: 60 + httpGet: + path: /metrics + port: metrics + scheme: HTTP + periodSeconds: 1 + successThreshold: 1 + timeoutSeconds: 5 terminationMessagePath: /dev/termination-log volumeMounts: - mountPath: /certs @@ -473,7 +482,7 @@ spec: image: intel/pmem-csi-driver:canary imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -493,12 +502,12 @@ spec: privileged: true runAsUser: 0 startupProbe: - failureThreshold: 30 + failureThreshold: 300 httpGet: path: /metrics port: metrics scheme: HTTP - periodSeconds: 10 + periodSeconds: 1 successThreshold: 1 timeoutSeconds: 5 terminationMessagePath: /tmp/termination-log @@ -562,7 +571,7 @@ spec: image: k8s.gcr.io/sig-storage/csi-provisioner:v2.2.2 imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -581,12 +590,12 @@ spec: securityContext: readOnlyRootFilesystem: true startupProbe: - failureThreshold: 30 + failureThreshold: 300 httpGet: path: /metrics port: metrics scheme: HTTP - periodSeconds: 10 + periodSeconds: 1 successThreshold: 1 timeoutSeconds: 5 volumeMounts: diff --git a/deploy/kubernetes-1.20/lvm/testing/pmem-csi.yaml b/deploy/kubernetes-1.20/lvm/testing/pmem-csi.yaml index 4bf1f411c..4ae9f86f0 100644 --- a/deploy/kubernetes-1.20/lvm/testing/pmem-csi.yaml +++ b/deploy/kubernetes-1.20/lvm/testing/pmem-csi.yaml @@ -383,7 +383,7 @@ spec: image: intel/pmem-csi-driver-test:canary imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -401,6 +401,15 @@ spec: memory: 128Mi securityContext: readOnlyRootFilesystem: true + startupProbe: + failureThreshold: 60 + httpGet: + path: /metrics + port: metrics + scheme: HTTP + periodSeconds: 1 + successThreshold: 1 + timeoutSeconds: 5 terminationMessagePath: /dev/termination-log volumeMounts: - mountPath: /certs @@ -497,7 +506,7 @@ spec: image: intel/pmem-csi-driver-test:canary imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -517,12 +526,12 @@ spec: privileged: true runAsUser: 0 startupProbe: - failureThreshold: 30 + failureThreshold: 300 httpGet: path: /metrics port: metrics scheme: HTTP - periodSeconds: 10 + periodSeconds: 1 successThreshold: 1 timeoutSeconds: 5 terminationMessagePath: /tmp/termination-log @@ -590,7 +599,7 @@ spec: image: k8s.gcr.io/sig-storage/csi-provisioner:v2.2.2 imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -609,12 +618,12 @@ spec: securityContext: readOnlyRootFilesystem: true startupProbe: - failureThreshold: 30 + failureThreshold: 300 httpGet: path: /metrics port: metrics scheme: HTTP - periodSeconds: 10 + periodSeconds: 1 successThreshold: 1 timeoutSeconds: 5 volumeMounts: diff --git a/deploy/kubernetes-1.20/pmem-csi-direct-testing.yaml b/deploy/kubernetes-1.20/pmem-csi-direct-testing.yaml index 16514d9c6..5fa4ed4d9 100644 --- a/deploy/kubernetes-1.20/pmem-csi-direct-testing.yaml +++ b/deploy/kubernetes-1.20/pmem-csi-direct-testing.yaml @@ -383,7 +383,7 @@ spec: image: intel/pmem-csi-driver-test:canary imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -401,6 +401,15 @@ spec: memory: 128Mi securityContext: readOnlyRootFilesystem: true + startupProbe: + failureThreshold: 60 + httpGet: + path: /metrics + port: metrics + scheme: HTTP + periodSeconds: 1 + successThreshold: 1 + timeoutSeconds: 5 terminationMessagePath: /dev/termination-log volumeMounts: - mountPath: /certs @@ -497,7 +506,7 @@ spec: image: intel/pmem-csi-driver-test:canary imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -517,12 +526,12 @@ spec: privileged: true runAsUser: 0 startupProbe: - failureThreshold: 30 + failureThreshold: 300 httpGet: path: /metrics port: metrics scheme: HTTP - periodSeconds: 10 + periodSeconds: 1 successThreshold: 1 timeoutSeconds: 5 terminationMessagePath: /tmp/termination-log @@ -590,7 +599,7 @@ spec: image: k8s.gcr.io/sig-storage/csi-provisioner:v2.2.2 imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -609,12 +618,12 @@ spec: securityContext: readOnlyRootFilesystem: true startupProbe: - failureThreshold: 30 + failureThreshold: 300 httpGet: path: /metrics port: metrics scheme: HTTP - periodSeconds: 10 + periodSeconds: 1 successThreshold: 1 timeoutSeconds: 5 volumeMounts: diff --git a/deploy/kubernetes-1.20/pmem-csi-direct.yaml b/deploy/kubernetes-1.20/pmem-csi-direct.yaml index adf076557..69c572781 100644 --- a/deploy/kubernetes-1.20/pmem-csi-direct.yaml +++ b/deploy/kubernetes-1.20/pmem-csi-direct.yaml @@ -381,7 +381,7 @@ spec: image: intel/pmem-csi-driver:canary imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -399,6 +399,15 @@ spec: memory: 128Mi securityContext: readOnlyRootFilesystem: true + startupProbe: + failureThreshold: 60 + httpGet: + path: /metrics + port: metrics + scheme: HTTP + periodSeconds: 1 + successThreshold: 1 + timeoutSeconds: 5 terminationMessagePath: /dev/termination-log volumeMounts: - mountPath: /certs @@ -473,7 +482,7 @@ spec: image: intel/pmem-csi-driver:canary imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -493,12 +502,12 @@ spec: privileged: true runAsUser: 0 startupProbe: - failureThreshold: 30 + failureThreshold: 300 httpGet: path: /metrics port: metrics scheme: HTTP - periodSeconds: 10 + periodSeconds: 1 successThreshold: 1 timeoutSeconds: 5 terminationMessagePath: /tmp/termination-log @@ -562,7 +571,7 @@ spec: image: k8s.gcr.io/sig-storage/csi-provisioner:v2.2.2 imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -581,12 +590,12 @@ spec: securityContext: readOnlyRootFilesystem: true startupProbe: - failureThreshold: 30 + failureThreshold: 300 httpGet: path: /metrics port: metrics scheme: HTTP - periodSeconds: 10 + periodSeconds: 1 successThreshold: 1 timeoutSeconds: 5 volumeMounts: diff --git a/deploy/kubernetes-1.20/pmem-csi-lvm-testing.yaml b/deploy/kubernetes-1.20/pmem-csi-lvm-testing.yaml index 4bf1f411c..4ae9f86f0 100644 --- a/deploy/kubernetes-1.20/pmem-csi-lvm-testing.yaml +++ b/deploy/kubernetes-1.20/pmem-csi-lvm-testing.yaml @@ -383,7 +383,7 @@ spec: image: intel/pmem-csi-driver-test:canary imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -401,6 +401,15 @@ spec: memory: 128Mi securityContext: readOnlyRootFilesystem: true + startupProbe: + failureThreshold: 60 + httpGet: + path: /metrics + port: metrics + scheme: HTTP + periodSeconds: 1 + successThreshold: 1 + timeoutSeconds: 5 terminationMessagePath: /dev/termination-log volumeMounts: - mountPath: /certs @@ -497,7 +506,7 @@ spec: image: intel/pmem-csi-driver-test:canary imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -517,12 +526,12 @@ spec: privileged: true runAsUser: 0 startupProbe: - failureThreshold: 30 + failureThreshold: 300 httpGet: path: /metrics port: metrics scheme: HTTP - periodSeconds: 10 + periodSeconds: 1 successThreshold: 1 timeoutSeconds: 5 terminationMessagePath: /tmp/termination-log @@ -590,7 +599,7 @@ spec: image: k8s.gcr.io/sig-storage/csi-provisioner:v2.2.2 imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -609,12 +618,12 @@ spec: securityContext: readOnlyRootFilesystem: true startupProbe: - failureThreshold: 30 + failureThreshold: 300 httpGet: path: /metrics port: metrics scheme: HTTP - periodSeconds: 10 + periodSeconds: 1 successThreshold: 1 timeoutSeconds: 5 volumeMounts: diff --git a/deploy/kubernetes-1.20/pmem-csi-lvm.yaml b/deploy/kubernetes-1.20/pmem-csi-lvm.yaml index 791f9c1c7..ed6404946 100644 --- a/deploy/kubernetes-1.20/pmem-csi-lvm.yaml +++ b/deploy/kubernetes-1.20/pmem-csi-lvm.yaml @@ -381,7 +381,7 @@ spec: image: intel/pmem-csi-driver:canary imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -399,6 +399,15 @@ spec: memory: 128Mi securityContext: readOnlyRootFilesystem: true + startupProbe: + failureThreshold: 60 + httpGet: + path: /metrics + port: metrics + scheme: HTTP + periodSeconds: 1 + successThreshold: 1 + timeoutSeconds: 5 terminationMessagePath: /dev/termination-log volumeMounts: - mountPath: /certs @@ -473,7 +482,7 @@ spec: image: intel/pmem-csi-driver:canary imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -493,12 +502,12 @@ spec: privileged: true runAsUser: 0 startupProbe: - failureThreshold: 30 + failureThreshold: 300 httpGet: path: /metrics port: metrics scheme: HTTP - periodSeconds: 10 + periodSeconds: 1 successThreshold: 1 timeoutSeconds: 5 terminationMessagePath: /tmp/termination-log @@ -562,7 +571,7 @@ spec: image: k8s.gcr.io/sig-storage/csi-provisioner:v2.2.2 imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -581,12 +590,12 @@ spec: securityContext: readOnlyRootFilesystem: true startupProbe: - failureThreshold: 30 + failureThreshold: 300 httpGet: path: /metrics port: metrics scheme: HTTP - periodSeconds: 10 + periodSeconds: 1 successThreshold: 1 timeoutSeconds: 5 volumeMounts: diff --git a/deploy/kubernetes-1.21/direct/pmem-csi.yaml b/deploy/kubernetes-1.21/direct/pmem-csi.yaml index 56dbfc4a6..8641b709c 100644 --- a/deploy/kubernetes-1.21/direct/pmem-csi.yaml +++ b/deploy/kubernetes-1.21/direct/pmem-csi.yaml @@ -381,7 +381,7 @@ spec: image: intel/pmem-csi-driver:canary imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -399,6 +399,15 @@ spec: memory: 128Mi securityContext: readOnlyRootFilesystem: true + startupProbe: + failureThreshold: 60 + httpGet: + path: /metrics + port: metrics + scheme: HTTP + periodSeconds: 1 + successThreshold: 1 + timeoutSeconds: 5 terminationMessagePath: /dev/termination-log volumeMounts: - mountPath: /certs @@ -473,7 +482,7 @@ spec: image: intel/pmem-csi-driver:canary imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -493,12 +502,12 @@ spec: privileged: true runAsUser: 0 startupProbe: - failureThreshold: 30 + failureThreshold: 300 httpGet: path: /metrics port: metrics scheme: HTTP - periodSeconds: 10 + periodSeconds: 1 successThreshold: 1 timeoutSeconds: 5 terminationMessagePath: /tmp/termination-log @@ -571,7 +580,7 @@ spec: image: k8s.gcr.io/sig-storage/csi-provisioner:v2.2.2 imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -590,12 +599,12 @@ spec: securityContext: readOnlyRootFilesystem: true startupProbe: - failureThreshold: 30 + failureThreshold: 300 httpGet: path: /metrics port: metrics scheme: HTTP - periodSeconds: 10 + periodSeconds: 1 successThreshold: 1 timeoutSeconds: 5 volumeMounts: diff --git a/deploy/kubernetes-1.21/direct/testing/pmem-csi.yaml b/deploy/kubernetes-1.21/direct/testing/pmem-csi.yaml index b6907fe5b..b09e28644 100644 --- a/deploy/kubernetes-1.21/direct/testing/pmem-csi.yaml +++ b/deploy/kubernetes-1.21/direct/testing/pmem-csi.yaml @@ -383,7 +383,7 @@ spec: image: intel/pmem-csi-driver-test:canary imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -401,6 +401,15 @@ spec: memory: 128Mi securityContext: readOnlyRootFilesystem: true + startupProbe: + failureThreshold: 60 + httpGet: + path: /metrics + port: metrics + scheme: HTTP + periodSeconds: 1 + successThreshold: 1 + timeoutSeconds: 5 terminationMessagePath: /dev/termination-log volumeMounts: - mountPath: /certs @@ -497,7 +506,7 @@ spec: image: intel/pmem-csi-driver-test:canary imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -517,12 +526,12 @@ spec: privileged: true runAsUser: 0 startupProbe: - failureThreshold: 30 + failureThreshold: 300 httpGet: path: /metrics port: metrics scheme: HTTP - periodSeconds: 10 + periodSeconds: 1 successThreshold: 1 timeoutSeconds: 5 terminationMessagePath: /tmp/termination-log @@ -599,7 +608,7 @@ spec: image: k8s.gcr.io/sig-storage/csi-provisioner:v2.2.2 imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -618,12 +627,12 @@ spec: securityContext: readOnlyRootFilesystem: true startupProbe: - failureThreshold: 30 + failureThreshold: 300 httpGet: path: /metrics port: metrics scheme: HTTP - periodSeconds: 10 + periodSeconds: 1 successThreshold: 1 timeoutSeconds: 5 volumeMounts: diff --git a/deploy/kubernetes-1.21/lvm/pmem-csi.yaml b/deploy/kubernetes-1.21/lvm/pmem-csi.yaml index 3e8fbdbae..325010fed 100644 --- a/deploy/kubernetes-1.21/lvm/pmem-csi.yaml +++ b/deploy/kubernetes-1.21/lvm/pmem-csi.yaml @@ -381,7 +381,7 @@ spec: image: intel/pmem-csi-driver:canary imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -399,6 +399,15 @@ spec: memory: 128Mi securityContext: readOnlyRootFilesystem: true + startupProbe: + failureThreshold: 60 + httpGet: + path: /metrics + port: metrics + scheme: HTTP + periodSeconds: 1 + successThreshold: 1 + timeoutSeconds: 5 terminationMessagePath: /dev/termination-log volumeMounts: - mountPath: /certs @@ -473,7 +482,7 @@ spec: image: intel/pmem-csi-driver:canary imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -493,12 +502,12 @@ spec: privileged: true runAsUser: 0 startupProbe: - failureThreshold: 30 + failureThreshold: 300 httpGet: path: /metrics port: metrics scheme: HTTP - periodSeconds: 10 + periodSeconds: 1 successThreshold: 1 timeoutSeconds: 5 terminationMessagePath: /tmp/termination-log @@ -571,7 +580,7 @@ spec: image: k8s.gcr.io/sig-storage/csi-provisioner:v2.2.2 imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -590,12 +599,12 @@ spec: securityContext: readOnlyRootFilesystem: true startupProbe: - failureThreshold: 30 + failureThreshold: 300 httpGet: path: /metrics port: metrics scheme: HTTP - periodSeconds: 10 + periodSeconds: 1 successThreshold: 1 timeoutSeconds: 5 volumeMounts: diff --git a/deploy/kubernetes-1.21/lvm/testing/pmem-csi.yaml b/deploy/kubernetes-1.21/lvm/testing/pmem-csi.yaml index 5e4c8b1d9..6d5002d65 100644 --- a/deploy/kubernetes-1.21/lvm/testing/pmem-csi.yaml +++ b/deploy/kubernetes-1.21/lvm/testing/pmem-csi.yaml @@ -383,7 +383,7 @@ spec: image: intel/pmem-csi-driver-test:canary imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -401,6 +401,15 @@ spec: memory: 128Mi securityContext: readOnlyRootFilesystem: true + startupProbe: + failureThreshold: 60 + httpGet: + path: /metrics + port: metrics + scheme: HTTP + periodSeconds: 1 + successThreshold: 1 + timeoutSeconds: 5 terminationMessagePath: /dev/termination-log volumeMounts: - mountPath: /certs @@ -497,7 +506,7 @@ spec: image: intel/pmem-csi-driver-test:canary imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -517,12 +526,12 @@ spec: privileged: true runAsUser: 0 startupProbe: - failureThreshold: 30 + failureThreshold: 300 httpGet: path: /metrics port: metrics scheme: HTTP - periodSeconds: 10 + periodSeconds: 1 successThreshold: 1 timeoutSeconds: 5 terminationMessagePath: /tmp/termination-log @@ -599,7 +608,7 @@ spec: image: k8s.gcr.io/sig-storage/csi-provisioner:v2.2.2 imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -618,12 +627,12 @@ spec: securityContext: readOnlyRootFilesystem: true startupProbe: - failureThreshold: 30 + failureThreshold: 300 httpGet: path: /metrics port: metrics scheme: HTTP - periodSeconds: 10 + periodSeconds: 1 successThreshold: 1 timeoutSeconds: 5 volumeMounts: diff --git a/deploy/kubernetes-1.21/pmem-csi-direct-testing.yaml b/deploy/kubernetes-1.21/pmem-csi-direct-testing.yaml index b6907fe5b..b09e28644 100644 --- a/deploy/kubernetes-1.21/pmem-csi-direct-testing.yaml +++ b/deploy/kubernetes-1.21/pmem-csi-direct-testing.yaml @@ -383,7 +383,7 @@ spec: image: intel/pmem-csi-driver-test:canary imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -401,6 +401,15 @@ spec: memory: 128Mi securityContext: readOnlyRootFilesystem: true + startupProbe: + failureThreshold: 60 + httpGet: + path: /metrics + port: metrics + scheme: HTTP + periodSeconds: 1 + successThreshold: 1 + timeoutSeconds: 5 terminationMessagePath: /dev/termination-log volumeMounts: - mountPath: /certs @@ -497,7 +506,7 @@ spec: image: intel/pmem-csi-driver-test:canary imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -517,12 +526,12 @@ spec: privileged: true runAsUser: 0 startupProbe: - failureThreshold: 30 + failureThreshold: 300 httpGet: path: /metrics port: metrics scheme: HTTP - periodSeconds: 10 + periodSeconds: 1 successThreshold: 1 timeoutSeconds: 5 terminationMessagePath: /tmp/termination-log @@ -599,7 +608,7 @@ spec: image: k8s.gcr.io/sig-storage/csi-provisioner:v2.2.2 imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -618,12 +627,12 @@ spec: securityContext: readOnlyRootFilesystem: true startupProbe: - failureThreshold: 30 + failureThreshold: 300 httpGet: path: /metrics port: metrics scheme: HTTP - periodSeconds: 10 + periodSeconds: 1 successThreshold: 1 timeoutSeconds: 5 volumeMounts: diff --git a/deploy/kubernetes-1.21/pmem-csi-direct.yaml b/deploy/kubernetes-1.21/pmem-csi-direct.yaml index 56dbfc4a6..8641b709c 100644 --- a/deploy/kubernetes-1.21/pmem-csi-direct.yaml +++ b/deploy/kubernetes-1.21/pmem-csi-direct.yaml @@ -381,7 +381,7 @@ spec: image: intel/pmem-csi-driver:canary imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -399,6 +399,15 @@ spec: memory: 128Mi securityContext: readOnlyRootFilesystem: true + startupProbe: + failureThreshold: 60 + httpGet: + path: /metrics + port: metrics + scheme: HTTP + periodSeconds: 1 + successThreshold: 1 + timeoutSeconds: 5 terminationMessagePath: /dev/termination-log volumeMounts: - mountPath: /certs @@ -473,7 +482,7 @@ spec: image: intel/pmem-csi-driver:canary imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -493,12 +502,12 @@ spec: privileged: true runAsUser: 0 startupProbe: - failureThreshold: 30 + failureThreshold: 300 httpGet: path: /metrics port: metrics scheme: HTTP - periodSeconds: 10 + periodSeconds: 1 successThreshold: 1 timeoutSeconds: 5 terminationMessagePath: /tmp/termination-log @@ -571,7 +580,7 @@ spec: image: k8s.gcr.io/sig-storage/csi-provisioner:v2.2.2 imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -590,12 +599,12 @@ spec: securityContext: readOnlyRootFilesystem: true startupProbe: - failureThreshold: 30 + failureThreshold: 300 httpGet: path: /metrics port: metrics scheme: HTTP - periodSeconds: 10 + periodSeconds: 1 successThreshold: 1 timeoutSeconds: 5 volumeMounts: diff --git a/deploy/kubernetes-1.21/pmem-csi-lvm-testing.yaml b/deploy/kubernetes-1.21/pmem-csi-lvm-testing.yaml index 5e4c8b1d9..6d5002d65 100644 --- a/deploy/kubernetes-1.21/pmem-csi-lvm-testing.yaml +++ b/deploy/kubernetes-1.21/pmem-csi-lvm-testing.yaml @@ -383,7 +383,7 @@ spec: image: intel/pmem-csi-driver-test:canary imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -401,6 +401,15 @@ spec: memory: 128Mi securityContext: readOnlyRootFilesystem: true + startupProbe: + failureThreshold: 60 + httpGet: + path: /metrics + port: metrics + scheme: HTTP + periodSeconds: 1 + successThreshold: 1 + timeoutSeconds: 5 terminationMessagePath: /dev/termination-log volumeMounts: - mountPath: /certs @@ -497,7 +506,7 @@ spec: image: intel/pmem-csi-driver-test:canary imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -517,12 +526,12 @@ spec: privileged: true runAsUser: 0 startupProbe: - failureThreshold: 30 + failureThreshold: 300 httpGet: path: /metrics port: metrics scheme: HTTP - periodSeconds: 10 + periodSeconds: 1 successThreshold: 1 timeoutSeconds: 5 terminationMessagePath: /tmp/termination-log @@ -599,7 +608,7 @@ spec: image: k8s.gcr.io/sig-storage/csi-provisioner:v2.2.2 imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -618,12 +627,12 @@ spec: securityContext: readOnlyRootFilesystem: true startupProbe: - failureThreshold: 30 + failureThreshold: 300 httpGet: path: /metrics port: metrics scheme: HTTP - periodSeconds: 10 + periodSeconds: 1 successThreshold: 1 timeoutSeconds: 5 volumeMounts: diff --git a/deploy/kubernetes-1.21/pmem-csi-lvm.yaml b/deploy/kubernetes-1.21/pmem-csi-lvm.yaml index 3e8fbdbae..325010fed 100644 --- a/deploy/kubernetes-1.21/pmem-csi-lvm.yaml +++ b/deploy/kubernetes-1.21/pmem-csi-lvm.yaml @@ -381,7 +381,7 @@ spec: image: intel/pmem-csi-driver:canary imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -399,6 +399,15 @@ spec: memory: 128Mi securityContext: readOnlyRootFilesystem: true + startupProbe: + failureThreshold: 60 + httpGet: + path: /metrics + port: metrics + scheme: HTTP + periodSeconds: 1 + successThreshold: 1 + timeoutSeconds: 5 terminationMessagePath: /dev/termination-log volumeMounts: - mountPath: /certs @@ -473,7 +482,7 @@ spec: image: intel/pmem-csi-driver:canary imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -493,12 +502,12 @@ spec: privileged: true runAsUser: 0 startupProbe: - failureThreshold: 30 + failureThreshold: 300 httpGet: path: /metrics port: metrics scheme: HTTP - periodSeconds: 10 + periodSeconds: 1 successThreshold: 1 timeoutSeconds: 5 terminationMessagePath: /tmp/termination-log @@ -571,7 +580,7 @@ spec: image: k8s.gcr.io/sig-storage/csi-provisioner:v2.2.2 imagePullPolicy: IfNotPresent livenessProbe: - failureThreshold: 5 + failureThreshold: 6 httpGet: path: /metrics port: metrics @@ -590,12 +599,12 @@ spec: securityContext: readOnlyRootFilesystem: true startupProbe: - failureThreshold: 30 + failureThreshold: 300 httpGet: path: /metrics port: metrics scheme: HTTP - periodSeconds: 10 + periodSeconds: 1 successThreshold: 1 timeoutSeconds: 5 volumeMounts: diff --git a/deploy/kustomize/patches/metrics-controller.yaml b/deploy/kustomize/patches/metrics-controller.yaml index b87d02574..d3293a0ca 100644 --- a/deploy/kustomize/patches/metrics-controller.yaml +++ b/deploy/kustomize/patches/metrics-controller.yaml @@ -23,10 +23,22 @@ scheme: HTTP path: /metrics port: metrics - # Allow it to fail 5 times. This is conservative - # because the probe is new. It might get reduced - # to 1 later. - failureThreshold: 5 + # Allow it to for a total duration of one minute. + # This is conservative because the probe is new. + failureThreshold: 6 periodSeconds: 10 successThreshold: 1 timeoutSeconds: 5 +- op: add + path: /spec/template/spec/containers/0/startupProbe + value: + httpGet: + scheme: HTTP + path: /metrics + port: metrics + # Check more frequently while the container starts up + # to get it into a ready state quickly. + failureThreshold: 60 + periodSeconds: 1 + successThreshold: 1 + timeoutSeconds: 5 diff --git a/deploy/kustomize/patches/metrics-node.yaml b/deploy/kustomize/patches/metrics-node.yaml index fc9a55f6f..94ac74060 100644 --- a/deploy/kustomize/patches/metrics-node.yaml +++ b/deploy/kustomize/patches/metrics-node.yaml @@ -24,10 +24,9 @@ scheme: HTTP path: /metrics port: metrics - # Allow it to fail 5 times. This is conservative - # because the probe is new. It might get reduced - # to 1 later. - failureThreshold: 5 + # Allow it to for a total duration of one minute. + # This is conservative because the probe is new. + failureThreshold: 6 periodSeconds: 10 successThreshold: 1 timeoutSeconds: 5 @@ -39,8 +38,9 @@ path: /metrics port: metrics # Startup may be slower when LVM needs to be set up first. - failureThreshold: 30 - periodSeconds: 10 + # Check more frequently to get it into a ready state quickly. + failureThreshold: 300 + periodSeconds: 1 successThreshold: 1 timeoutSeconds: 5 @@ -68,10 +68,9 @@ scheme: HTTP path: /metrics port: metrics - # Allow it to fail 5 times. This is conservative - # because the probe is new. It might get reduced - # to 1 later. - failureThreshold: 5 + # Same settings as for driver because the provisioner + # waits for the driver. + failureThreshold: 6 periodSeconds: 10 successThreshold: 1 timeoutSeconds: 5 @@ -82,9 +81,7 @@ scheme: HTTP path: /metrics port: metrics - # The provisioner waits for the driver, so startup - # may be slower when LVM needs to be set up first. - failureThreshold: 30 - periodSeconds: 10 + failureThreshold: 300 + periodSeconds: 1 successThreshold: 1 timeoutSeconds: 5 diff --git a/pkg/pmem-csi-operator/controller/deployment/controller_driver.go b/pkg/pmem-csi-operator/controller/deployment/controller_driver.go index 3ef9116eb..e5f56b9f6 100644 --- a/pkg/pmem-csi-operator/controller/deployment/controller_driver.go +++ b/pkg/pmem-csi-operator/controller/deployment/controller_driver.go @@ -1304,7 +1304,8 @@ func (d *pmemCSIDeployment) getControllerContainer() corev1.Container { SecurityContext: &corev1.SecurityContext{ ReadOnlyRootFilesystem: &true, }, - LivenessProbe: getMetricsProbe(5), + LivenessProbe: getMetricsProbe(6, 10), + StartupProbe: getMetricsProbe(60, 1), } if d.Spec.ControllerTLSSecret != "" { @@ -1388,8 +1389,8 @@ func (d *pmemCSIDeployment) getNodeDriverContainer() corev1.Container { }, TerminationMessagePath: "/tmp/termination-log", TerminationMessagePolicy: corev1.TerminationMessageReadFile, - LivenessProbe: getMetricsProbe(5), - StartupProbe: getMetricsProbe(30), + LivenessProbe: getMetricsProbe(6, 10), + StartupProbe: getMetricsProbe(300, 1), } return c @@ -1438,8 +1439,8 @@ func (d *pmemCSIDeployment) getProvisionerContainer() corev1.Container { }, TerminationMessagePath: corev1.TerminationMessagePathDefault, TerminationMessagePolicy: corev1.TerminationMessageReadFile, - LivenessProbe: getMetricsProbe(5), - StartupProbe: getMetricsProbe(30), + LivenessProbe: getMetricsProbe(6, 10), + StartupProbe: getMetricsProbe(300, 1), } if d.withStorageCapacity() { @@ -1675,7 +1676,7 @@ func (d *pmemCSIDeployment) getObjectMeta(name string, isClusterResource bool) m return meta } -func getMetricsProbe(failureThreshold int32) *corev1.Probe { +func getMetricsProbe(failureThreshold int32, periodSeconds int32) *corev1.Probe { return &corev1.Probe{ Handler: corev1.Handler{ HTTPGet: &corev1.HTTPGetAction{ @@ -1686,7 +1687,7 @@ func getMetricsProbe(failureThreshold int32) *corev1.Probe { }, SuccessThreshold: 1, TimeoutSeconds: 5, - PeriodSeconds: 10, + PeriodSeconds: periodSeconds, FailureThreshold: failureThreshold, } }