Merge pull request #386 from red-hat-storage/sync_us--devel

Syncing latest changes from upstream devel for ceph-csi
red-hat-storage · Sep 23, 2024 · 9559ebd · 9559ebd
2 parents 07681a2 + c76338c
commit 9559ebd
Show file tree

Hide file tree

Showing 45 changed files with 212 additions and 65 deletions.
diff --git a/.github/workflows/auto-assign.yaml b/.github/workflows/auto-assign.yaml
@@ -11,7 +11,8 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: take the issue
-        uses: bdougie/take-action@main
+        # yamllint disable-line rule:line-length
+        uses: bdougie/take-action@1439165ac45a7461c2d89a59952cd7d941964b87  # main
         with:
           message: >
             Thanks for taking this issue!

diff --git a/.github/workflows/build-multi-stage.yaml b/.github/workflows/build-multi-stage.yaml
@@ -13,7 +13,8 @@ jobs:
     name: multi-arch-build
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      # yamllint disable-line rule:line-length
+      - uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332  # v4.1.7
       - name: multi-arch-build
         # yamllint disable-line rule:line-length
         if: ${{ ! contains(github.event.pull_request.labels.*.name, 'ci/skip/multi-arch-build') }}

diff --git a/.github/workflows/codespell.yaml b/.github/workflows/codespell.yaml
@@ -15,6 +15,7 @@ jobs:
     name: codespell
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      # yamllint disable-line rule:line-length
+      - uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332  # v4.1.7
       - name: codespell
         run: make containerized-test TARGET=codespell
diff --git a/.github/workflows/commitlint.yaml b/.github/workflows/commitlint.yaml
@@ -14,7 +14,8 @@ jobs:
     if: ${{ github.event.pull_request.user.login != 'dependabot[bot]' }}
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      # yamllint disable-line rule:line-length
+      - uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332  # v4.1.7
         with:
           ref: ${{ github.event.pull_request.head.sha }}
       - name: commitlint

diff --git a/.github/workflows/dependency-review.yaml b/.github/workflows/dependency-review.yaml
@@ -15,8 +15,10 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: 'Checkout Repository'
-        uses: actions/checkout@v4
+        # yamllint disable-line rule:line-length
+        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332  # v4.1.7
       - name: 'Dependency Review'
-        uses: actions/dependency-review-action@v4
+        # yamllint disable-line rule:line-length
+        uses: actions/dependency-review-action@5a2ce3f5b92ee19cbb1541a4984c76d921601d7c  # v4.3.4
         with:
           allow-ghsas: GHSA-f4w6-3rh6-6q4q
diff --git a/.github/workflows/go-test.yaml b/.github/workflows/go-test.yaml
@@ -14,7 +14,8 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout the repo
-        uses: actions/checkout@v4
+        # yamllint disable-line rule:line-length
+        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332   # v4.1.7
 
       - name: Check generated deploy code
         run: make generate-deploy
@@ -29,20 +30,23 @@ jobs:
     name: e2e-build-test
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      # yamllint disable-line rule:line-length
+      - uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332  # v4.1.7
       - name: e2e-build-test
         run: make containerized-build TARGET=e2e.test
   go-test:
     name: go-test
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      # yamllint disable-line rule:line-length
+      - uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332  # v4.1.7
       - name: go-test
         run: make containerized-test TARGET=go-test
   go-test-api:
     name: go-test-api
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      # yamllint disable-line rule:line-length
+      - uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332  # v4.1.7
       - name: go-test-api
         run: make containerized-test TARGET=go-test-api
diff --git a/.github/workflows/golangci-lint.yaml b/.github/workflows/golangci-lint.yaml
@@ -13,6 +13,7 @@ jobs:
     name: golangci-lint
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      # yamllint disable-line rule:line-length
+      - uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332  # v4.1.7
       - name: golangci-lint
         run: make containerized-test TARGET=go-lint
diff --git a/.github/workflows/lint-extras.yaml b/.github/workflows/lint-extras.yaml
@@ -13,6 +13,7 @@ jobs:
     name: lint-extras
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      # yamllint disable-line rule:line-length
+      - uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332  # v4.1.7
       - name: lint-extras
         run: make containerized-test TARGET=lint-extras
diff --git a/.github/workflows/mergify-copy-labels.yaml b/.github/workflows/mergify-copy-labels.yaml
@@ -12,7 +12,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Copying labels
-        uses: Mergifyio/gha-mergify-merge-queue-labels-copier@main
+        uses: Mergifyio/gha-mergify-merge-queue-labels-copier@1d2b277f94d52987008ec05b571fb68f2357e63f  # main
         with:
           additional-labels: 'ok-to-test'
           token: ${{ secrets.CEPH_CSI_BOT_TOKEN }}
diff --git a/.github/workflows/mod-check.yaml b/.github/workflows/mod-check.yaml
@@ -13,6 +13,7 @@ jobs:
     name: mod-check
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      # yamllint disable-line rule:line-length
+      - uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332  # v4.1.7
       - name: mod-check
         run: make containerized-test TARGET=mod-check
diff --git a/.github/workflows/publish-artifacts.yaml b/.github/workflows/publish-artifacts.yaml
@@ -18,10 +18,12 @@ jobs:
     runs-on: ubuntu-latest
     if: github.repository == 'ceph/ceph-csi'
     steps:
-      - uses: actions/checkout@v4
+      # yamllint disable-line rule:line-length
+      - uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332  # v4.1.7
 
       - name: Login to Quay
-        uses: docker/login-action@v3
+        # yamllint disable-line rule:line-length
+        uses: docker/login-action@9780b0c442fbb1117ed29e0efdff1e18412f7567  # v3.3.0
         with:
           registry: quay.io
           username: ${{ secrets.QUAY_IO_USERNAME }}

diff --git a/.github/workflows/pull-request-commentor.yaml b/.github/workflows/pull-request-commentor.yaml
@@ -51,7 +51,8 @@ jobs:
           Add comment to trigger external storage tests for Kubernetes
           ${{ matrix.k8s }}
         if: ${{ github.base_ref == matrix.branch }}
-        uses: peter-evans/create-or-update-comment@v4
+        # yamllint disable-line rule:line-length
+        uses: peter-evans/create-or-update-comment@71345be0265236311c031f5c7866368bd1eff043  # v4.0.0
         with:
           token: ${{ secrets.CEPH_CSI_BOT_TOKEN }}
           issue-number: ${{ github.event.pull_request.number }}
@@ -62,15 +63,17 @@ jobs:
           Add comment to trigger helm E2E tests for Kubernetes
           ${{ matrix.k8s }}
         if: ${{ github.base_ref == matrix.branch }}
-        uses: peter-evans/create-or-update-comment@v4
+        # yamllint disable-line rule:line-length
+        uses: peter-evans/create-or-update-comment@71345be0265236311c031f5c7866368bd1eff043  # v4.0.0
         with:
           token: ${{ secrets.CEPH_CSI_BOT_TOKEN }}
           issue-number: ${{ github.event.pull_request.number }}
           body: |
             /test ci/centos/mini-e2e-helm/k8s-${{ matrix.k8s }}
 
       - name: Add comment to trigger E2E tests for Kubernetes ${{ matrix.k8s }}
-        uses: peter-evans/create-or-update-comment@v4
+        # yamllint disable-line rule:line-length
+        uses: peter-evans/create-or-update-comment@71345be0265236311c031f5c7866368bd1eff043  # v4.0.0
         if: ${{ github.base_ref == matrix.branch }}
         with:
           token: ${{ secrets.CEPH_CSI_BOT_TOKEN }}
@@ -87,15 +90,17 @@ jobs:
 
     steps:
       - name: Add comment to trigger cephfs upgrade tests
-        uses: peter-evans/create-or-update-comment@v4
+        # yamllint disable-line rule:line-length
+        uses: peter-evans/create-or-update-comment@71345be0265236311c031f5c7866368bd1eff043  # v4.0.0
         with:
           token: ${{ secrets.CEPH_CSI_BOT_TOKEN }}
           issue-number: ${{ github.event.pull_request.number }}
           body: |
             /test ci/centos/upgrade-tests-cephfs
 
       - name: Add comment to trigger rbd upgrade tests
-        uses: peter-evans/create-or-update-comment@v4
+        # yamllint disable-line rule:line-length
+        uses: peter-evans/create-or-update-comment@71345be0265236311c031f5c7866368bd1eff043  # v4.0.0
         with:
           token: ${{ secrets.CEPH_CSI_BOT_TOKEN }}
           issue-number: ${{ github.event.pull_request.number }}
@@ -116,7 +121,8 @@ jobs:
 
     steps:
       - name: remove ok-to-test-label after commenting
-        uses: actions/github-script@v7
+        # yamllint disable-line rule:line-length
+        uses: actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea  # v7.0.1
         with:
           github-token: ${{ secrets.CEPH_CSI_BOT_TOKEN }}
           script: |

diff --git a/.github/workflows/retest.yaml b/.github/workflows/retest.yaml
@@ -15,7 +15,8 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       # path to the retest action
-      - uses: ceph/ceph-csi/actions/retest@devel
+      # yamllint disable-line rule:line-length
+      - uses: ceph/ceph-csi/actions/retest@28dc64dcae3cec8d11d84bdf525bda0ef757c688  # devel
         with:
           GITHUB_TOKEN: ${{ secrets.CEPH_CSI_BOT_TOKEN }}
           required-label: "ci/retry/e2e"

diff --git a/.github/workflows/snyk-container-image.yaml b/.github/workflows/snyk-container-image.yaml
@@ -26,18 +26,21 @@ jobs:
     if: github.repository == 'ceph/ceph-csi'
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      # yamllint disable-line rule:line-length
+      - uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332  # v4.1.7
       - name: Build a Docker image
         run: make image-cephcsi
       - name: Run Snyk to check Docker image for vulnerabilities
         continue-on-error: true
-        uses: snyk/actions/docker@master
+        # yamllint disable-line rule:line-length
+        uses: snyk/actions/docker@cdb760004ba9ea4d525f2e043745dfe85bb9077e  # master
         env:
           SNYK_TOKEN: ${{ secrets.SYNK_TOKEN }}
         with:
           image: quay.io/cephcsi/cephcsi:${{ github.base_ref }}
           args: --file=Dockerfilei
       - name: Upload result to GitHub Code Scanning
-        uses: github/codeql-action/upload-sarif@v3
+        # yamllint disable-line rule:line-length
+        uses: github/codeql-action/upload-sarif@8214744c546c1e5c8f03dde8fab3a7353211988d  # v3.26.7
         with:
           sarif_file: snyk.sarif
diff --git a/.github/workflows/snyk.yaml b/.github/workflows/snyk.yaml
@@ -20,11 +20,13 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: checkout
-        uses: actions/checkout@v4
+        # yamllint disable-line rule:line-length
+        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332  # v4.1.7
         with:
           fetch-depth: 0
 
       - name: run Snyk to check for code vulnerabilities
-        uses: snyk/actions/golang@master
+        # yamllint disable-line rule:line-length
+        uses: snyk/actions/golang@cdb760004ba9ea4d525f2e043745dfe85bb9077e  # master
         env:
           SNYK_TOKEN: ${{ secrets.SYNK_TOKEN }}
diff --git a/.github/workflows/stale.yaml b/.github/workflows/stale.yaml
@@ -18,7 +18,8 @@ jobs:
     runs-on: ubuntu-latest
     if: github.repository == 'ceph/ceph-csi'
     steps:
-      - uses: actions/stale@v9
+      # yamllint disable-line rule:line-length
+      - uses: actions/stale@28ca1036281a5e5922ead5184a1bbf96e5fc984e  # v9.0.0
         with:
           repo-token: ${{ secrets.GITHUB_TOKEN }}
           days-before-issue-stale: 30

diff --git a/.github/workflows/test-retest-action.yaml b/.github/workflows/test-retest-action.yaml
@@ -15,7 +15,8 @@ jobs:
   build:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      # yamllint disable-line rule:line-length
+      - uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332  # v4.1.7
 
       - name: Docker build
         # Run cd to avoid loading complete cephcsi directory in docker context

diff --git a/.github/workflows/tickgit.yaml b/.github/workflows/tickgit.yaml
@@ -14,5 +14,6 @@ jobs:
     name: tickgit
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      # yamllint disable-line rule:line-length
+      - uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332  # v4.1.7
       - run: make containerized-test TARGET=tickgit
diff --git a/PendingReleaseNotes.md b/PendingReleaseNotes.md
@@ -12,5 +12,7 @@
 - deploy: radosNamespaceCephFS can be configured for ceph-csi-cephfs chart in [PR](https://github.com/ceph/ceph-csi/pull/4652)
 - build: update ceph release to squid in [PR](https://github.com/ceph/ceph-csi/pull/4735)
 - build: CentOS Stream 9 is used as OS in the container-images [PR](https://github.com/ceph/ceph-csi/pull/4735)
+- util: a log message "Slow GRPC" is now emitted when
+  CSI GRPC call outlives its deadline [PR](https://github.com/ceph/ceph-csi/pull/4847)
 
 ## NOTE
diff --git a/charts/ceph-csi-cephfs/README.md b/charts/ceph-csi-cephfs/README.md
@@ -118,6 +118,7 @@ charts and their default values.
 | `commonLabels`                                 | Labels to apply to all resources                                                               | `{}`                                                  |
 | `logLevel`                                     | Set logging level for csi containers. Supported values from 0 to 5. 0 for general useful logs, 5 for trace level verbosity.                          | `5`                                                |
 | `sidecarLogLevel`                              | Set logging level for csi sidecar containers. Supported values from 0 to 5. 0 for general useful logs, 5 for trace level verbosity.                  | `1`                                                |
+| `logSlowOperationInterval`                     | Log slow operations at the specified rate. Operation is considered slow if it outlives its deadline.                                                 | `30s`                                              |
 | `nodeplugin.name`                              | Specifies the nodeplugin name                                                                                                                        | `nodeplugin`                                       |
 | `nodeplugin.updateStrategy`                    | Specifies the update Strategy. If you are using ceph-fuse client set this value to OnDelete                                                          | `RollingUpdate`                                    |
 | `nodeplugin.priorityClassName`                 | Set user created priorityClassName for csi plugin pods. default is system-node-critical which is highest priority                                    | `system-node-critical`                             |

diff --git a/charts/ceph-csi-cephfs/templates/nodeplugin-daemonset.yaml b/charts/ceph-csi-cephfs/templates/nodeplugin-daemonset.yaml
@@ -72,6 +72,7 @@ spec:
 {{- if and .Values.readAffinity .Values.readAffinity.enabled }}
             - "--crush-location-labels={{ .Values.readAffinity.crushLocationLabels | join "," }}"
 {{- end }}
+            - "--logslowopinterval={{ .Values.logSlowOperationInterval }}"
           env:
             - name: POD_IP
               valueFrom:

diff --git a/charts/ceph-csi-cephfs/templates/provisioner-deployment.yaml b/charts/ceph-csi-cephfs/templates/provisioner-deployment.yaml
@@ -92,6 +92,7 @@ spec:
             - "--clustername={{ .Values.provisioner.clustername }}"
 {{- end }}
             - "--setmetadata={{ .Values.provisioner.setmetadata }}"
+            - "--logslowopinterval={{ .Values.logSlowOperationInterval }}"
           env:
             - name: POD_IP
               valueFrom:

diff --git a/charts/ceph-csi-cephfs/values.yaml b/charts/ceph-csi-cephfs/values.yaml
@@ -40,6 +40,9 @@ commonLabels: {}
 logLevel: 5
 # sidecarLogLevel is the variable for Kubernetes sidecar container's log level
 sidecarLogLevel: 1
+# Log slow operations at the specified rate.
+# Operation is considered slow if it outlives its deadline.
+logSlowOperationInterval: 30s
 
 # Set fsGroupPolicy for CSI Driver object spec
 # https://kubernetes-csi.github.io/docs/support-fsgroup.html

diff --git a/charts/ceph-csi-rbd/README.md b/charts/ceph-csi-rbd/README.md
@@ -120,6 +120,7 @@ charts and their default values.
 | `commonLabels`                                 | Labels to apply to all resources                                                                  | `{}`                                                  |
 | `logLevel`                                     | Set logging level for csi containers. Supported values from 0 to 5. 0 for general useful logs, 5 for trace level verbosity.                          | `5`                                                |
 | `sidecarLogLevel`                              | Set logging level for csi sidecar containers. Supported values from 0 to 5. 0 for general useful logs, 5 for trace level verbosity.                  | `1`                                                |
+| `logSlowOperationInterval`                     | Log slow operations at the specified rate. Operation is considered slow if it outlives its deadline.                                                 | `30s`                                              |
 | `nodeplugin.name`                              | Specifies the nodeplugins name                                                                                                                       | `nodeplugin`                                       |
 | `nodeplugin.updateStrategy`                    | Specifies the update Strategy. If you are using ceph-fuse client set this value to OnDelete                                                          | `RollingUpdate`                                    |
 | `nodeplugin.priorityClassName`                 | Set user created priorityclassName for csi plugin pods. default is system-node-critical which is highest priority                                    | `system-node-critical`                             |

diff --git a/charts/ceph-csi-rbd/templates/nodeplugin-daemonset.yaml b/charts/ceph-csi-rbd/templates/nodeplugin-daemonset.yaml
@@ -70,6 +70,7 @@ spec:
 {{- if and .Values.readAffinity .Values.readAffinity.enabled }}
             - "--crush-location-labels={{ .Values.readAffinity.crushLocationLabels | join "," }}"
 {{- end }}
+            - "--logslowopinterval={{ .Values.logSlowOperationInterval }}"
           env:
             - name: POD_IP
               valueFrom:

diff --git a/charts/ceph-csi-rbd/templates/provisioner-deployment.yaml b/charts/ceph-csi-rbd/templates/provisioner-deployment.yaml
@@ -97,6 +97,7 @@ spec:
             - "--clustername={{ .Values.provisioner.clustername }}"
             {{- end }}
             - "--setmetadata={{ .Values.provisioner.setmetadata }}"
+            - "--logslowopinterval={{ .Values.logSlowOperationInterval }}"
           env:
             - name: POD_IP
               valueFrom:

diff --git a/charts/ceph-csi-rbd/values.yaml b/charts/ceph-csi-rbd/values.yaml
@@ -69,6 +69,9 @@ commonLabels: {}
 logLevel: 5
 # sidecarLogLevel is the variable for Kubernetes sidecar container's log level
 sidecarLogLevel: 1
+# Log slow operations at the specified rate.
+# Operation is considered slow if it outlives its deadline.
+logSlowOperationInterval: 30s
 
 # Set fsGroupPolicy for CSI Driver object spec
 # https://kubernetes-csi.github.io/docs/support-fsgroup.html

diff --git a/cmd/cephcsi.go b/cmd/cephcsi.go
@@ -120,6 +120,11 @@ func init() {
 		"path of prometheus endpoint where metrics will be available")
 	flag.DurationVar(&conf.PollTime, "polltime", time.Second*pollTime, "time interval in seconds between each poll")
 	flag.DurationVar(&conf.PoolTimeout, "timeout", time.Second*probeTimeout, "probe timeout in seconds")
+	flag.DurationVar(
+		&conf.LogSlowOpInterval,
+		"logslowopinterval",
+		time.Second*30,
+		"how often to inform about slow gRPC calls")
 
 	flag.UintVar(
 		&conf.RbdHardMaxCloneDepth,

diff --git a/docs/deploy-cephfs.md b/docs/deploy-cephfs.md
@@ -50,6 +50,7 @@ make image-cephcsi
 | `--enable-read-affinity` | `false`                       | enable read affinity                                                                                                                                                                                                                                                                 |
 | `--crush-location-labels`| _empty_                       | Kubernetes node labels that determine the CRUSH location the node belongs to, separated by ','.<br>`Note: These labels will be replaced if crush location labels are defined in the ceph-csi-config ConfigMap for the specific cluster.`                                                                                                                                                                                       |
 | `--radosnamespacecephfs`| _empty_                       | CephFS RadosNamespace used to store CSI specific objects and keys.                                                                                                                               |
+| `--logslowopinterval`   | `30s`                         | Log slow operations at the specified rate. Operation is considered slow if it outlives its deadline.                                                                                             |
 
 **NOTE:** The parameter `-forcecephkernelclient` enables the Kernel
 CephFS mounter on kernels < 4.17.