From 0f5fcdb996cb03ca7b2693d07f129b98039a42de Mon Sep 17 00:00:00 2001 From: Evan Lezar Date: Sun, 28 Jan 2024 18:15:14 +0100 Subject: [PATCH 1/4] Bump version in deployments Signed-off-by: Evan Lezar --- deployments/helm/nvidia-device-plugin/Chart.yaml | 4 ++-- .../static/extensions-v1beta1-nvidia-device-plugin.yml | 2 +- .../static/nvidia-device-plugin-compat-with-cpumanager.yml | 2 +- .../nvidia-device-plugin-privileged-with-service-account.yml | 2 +- nvidia-device-plugin.yml | 2 +- 5 files changed, 6 insertions(+), 6 deletions(-) diff --git a/deployments/helm/nvidia-device-plugin/Chart.yaml b/deployments/helm/nvidia-device-plugin/Chart.yaml index ab37f00e0..c7670c7e2 100644 --- a/deployments/helm/nvidia-device-plugin/Chart.yaml +++ b/deployments/helm/nvidia-device-plugin/Chart.yaml @@ -2,8 +2,8 @@ apiVersion: v2 name: nvidia-device-plugin type: application description: A Helm chart for the nvidia-device-plugin on Kubernetes -version: "0.14.3" -appVersion: "0.14.3" +version: "0.14.4" +appVersion: "0.14.4" kubeVersion: ">= 1.10.0-0" home: https://github.com/NVIDIA/k8s-device-plugin diff --git a/deployments/static/extensions-v1beta1-nvidia-device-plugin.yml b/deployments/static/extensions-v1beta1-nvidia-device-plugin.yml index 6dfecc702..956ccb8ae 100644 --- a/deployments/static/extensions-v1beta1-nvidia-device-plugin.yml +++ b/deployments/static/extensions-v1beta1-nvidia-device-plugin.yml @@ -35,7 +35,7 @@ spec: # See https://kubernetes.io/docs/tasks/administer-cluster/guaranteed-scheduling-critical-addon-pods/ priorityClassName: "system-node-critical" containers: - - image: nvcr.io/nvidia/k8s-device-plugin:v0.14.3 + - image: nvcr.io/nvidia/k8s-device-plugin:v0.14.4 name: nvidia-device-plugin-ctr env: - name: FAIL_ON_INIT_ERROR diff --git a/deployments/static/nvidia-device-plugin-compat-with-cpumanager.yml b/deployments/static/nvidia-device-plugin-compat-with-cpumanager.yml index 9554376d5..15ad02695 100644 --- a/deployments/static/nvidia-device-plugin-compat-with-cpumanager.yml +++ b/deployments/static/nvidia-device-plugin-compat-with-cpumanager.yml @@ -38,7 +38,7 @@ spec: # See https://kubernetes.io/docs/tasks/administer-cluster/guaranteed-scheduling-critical-addon-pods/ priorityClassName: "system-node-critical" containers: - - image: nvcr.io/nvidia/k8s-device-plugin:v0.14.3 + - image: nvcr.io/nvidia/k8s-device-plugin:v0.14.4 name: nvidia-device-plugin-ctr env: - name: FAIL_ON_INIT_ERROR diff --git a/deployments/static/nvidia-device-plugin-privileged-with-service-account.yml b/deployments/static/nvidia-device-plugin-privileged-with-service-account.yml index 8b9a3c011..8341c6987 100644 --- a/deployments/static/nvidia-device-plugin-privileged-with-service-account.yml +++ b/deployments/static/nvidia-device-plugin-privileged-with-service-account.yml @@ -124,7 +124,7 @@ spec: - env: - name: PASS_DEVICE_SPECS value: "true" - image: nvcr.io/nvidia/k8s-device-plugin:v0.14.3 + image: nvcr.io/nvidia/k8s-device-plugin:v0.14.4 name: nvidia-device-plugin-ctr securityContext: privileged: true diff --git a/nvidia-device-plugin.yml b/nvidia-device-plugin.yml index 50cc905cd..c798799d4 100644 --- a/nvidia-device-plugin.yml +++ b/nvidia-device-plugin.yml @@ -38,7 +38,7 @@ spec: # See https://kubernetes.io/docs/tasks/administer-cluster/guaranteed-scheduling-critical-addon-pods/ priorityClassName: "system-node-critical" containers: - - image: nvcr.io/nvidia/k8s-device-plugin:v0.14.3 + - image: nvcr.io/nvidia/k8s-device-plugin:v0.14.4 name: nvidia-device-plugin-ctr env: - name: FAIL_ON_INIT_ERROR From d50ca9f55f9d8e125207d6e82cec1c5041e9c72f Mon Sep 17 00:00:00 2001 From: Evan Lezar Date: Sun, 28 Jan 2024 18:15:28 +0100 Subject: [PATCH 2/4] Bump version in versions.mk Signed-off-by: Evan Lezar --- versions.mk | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/versions.mk b/versions.mk index b7457699f..e8aedcdf1 100644 --- a/versions.mk +++ b/versions.mk @@ -14,7 +14,7 @@ MODULE := github.com/NVIDIA/k8s-device-plugin -VERSION ?= v0.14.3 +VERSION ?= v0.14.4 # vVERSION represents the version with a guaranteed v-prefix vVERSION := v$(VERSION:v%=%) From 5acd0599d24e03edd54e1ad21894566800ced057 Mon Sep 17 00:00:00 2001 From: Evan Lezar Date: Sun, 28 Jan 2024 18:17:06 +0100 Subject: [PATCH 3/4] Bump version in README Signed-off-by: Evan Lezar --- README.md | 45 +++++++++++++++++++++++++-------------------- RELEASE.md | 2 +- 2 files changed, 26 insertions(+), 21 deletions(-) diff --git a/README.md b/README.md index 0dd12e35d..389706d88 100644 --- a/README.md +++ b/README.md @@ -124,7 +124,7 @@ Once you have configured the options above on all the GPU nodes in your cluster, you can enable GPU support by deploying the following Daemonset: ```shell -$ kubectl create -f https://raw.githubusercontent.com/NVIDIA/k8s-device-plugin/v0.14.3/nvidia-device-plugin.yml +$ kubectl create -f https://raw.githubusercontent.com/NVIDIA/k8s-device-plugin/v0.14.4/nvidia-device-plugin.yml ``` **Note:** This is a simple static daemonset meant to demonstrate the basic @@ -462,11 +462,11 @@ $ helm repo add nvdp https://nvidia.github.io/k8s-device-plugin $ helm repo update ``` -Then verify that the latest release (`v0.14.3`) of the plugin is available: +Then verify that the latest release (`v0.14.4`) of the plugin is available: ``` $ helm search repo nvdp --devel NAME CHART VERSION APP VERSION DESCRIPTION -nvdp/nvidia-device-plugin 0.14.3 0.14.3 A Helm chart for ... +nvdp/nvidia-device-plugin 0.14.4 0.14.4 A Helm chart for ... ``` Once this repo is updated, you can begin installing packages from it to deploy @@ -477,7 +477,7 @@ The most basic installation command without any options is then: helm upgrade -i nvdp nvdp/nvidia-device-plugin \ --namespace nvidia-device-plugin \ --create-namespace \ - --version 0.14.3 + --version 0.14.4 ``` **Note:** You only need the to pass the `--devel` flag to `helm search repo` @@ -486,7 +486,7 @@ version (e.g. `-rc.1`). Full releases will be listed without this. ### Configuring the device plugin's `helm` chart -The `helm` chart for the latest release of the plugin (`v0.14.3`) includes +The `helm` chart for the latest release of the plugin (`v0.14.4`) includes a number of customizable values. Prior to `v0.12.0` the most commonly used values were those that had direct @@ -496,7 +496,7 @@ case of the original values is then to override an option from the `ConfigMap` if desired. Both methods are discussed in more detail below. The full set of values that can be set are found here: -[here](https://github.com/NVIDIA/k8s-device-plugin/blob/v0.14.3/deployments/helm/nvidia-device-plugin/values.yaml). +[here](https://github.com/NVIDIA/k8s-device-plugin/blob/v0.14.4/deployments/helm/nvidia-device-plugin/values.yaml). #### Passing configuration to the plugin via a `ConfigMap`. @@ -535,7 +535,7 @@ EOF And deploy the device plugin via helm (pointing it at this config file and giving it a name): ``` $ helm upgrade -i nvdp nvdp/nvidia-device-plugin \ - --version=0.14.3 \ + --version=0.14.4 \ --namespace nvidia-device-plugin \ --create-namespace \ --set-file config.map.config=/tmp/dp-example-config0.yaml @@ -557,7 +557,7 @@ $ kubectl create cm -n nvidia-device-plugin nvidia-plugin-configs \ ``` ``` $ helm upgrade -i nvdp nvdp/nvidia-device-plugin \ - --version=0.14.3 \ + --version=0.14.4 \ --namespace nvidia-device-plugin \ --create-namespace \ --set config.name=nvidia-plugin-configs @@ -585,7 +585,7 @@ EOF And redeploy the device plugin via helm (pointing it at both configs with a specified default). ``` $ helm upgrade -i nvdp nvdp/nvidia-device-plugin \ - --version=0.14.3 \ + --version=0.14.4 \ --namespace nvidia-device-plugin \ --create-namespace \ --set config.default=config0 \ @@ -604,7 +604,7 @@ $ kubectl create cm -n nvidia-device-plugin nvidia-plugin-configs \ ``` ``` $ helm upgrade -i nvdp nvdp/nvidia-device-plugin \ - --version=0.14.3 \ + --version=0.14.4 \ --namespace nvidia-device-plugin \ --create-namespace \ --set config.default=config0 \ @@ -690,7 +690,7 @@ chart values that are commonly overridden are: ``` Please take a look in the -[`values.yaml`](https://github.com/NVIDIA/k8s-device-plugin/blob/v0.14.3/deployments/helm/nvidia-device-plugin/values.yaml) +[`values.yaml`](https://github.com/NVIDIA/k8s-device-plugin/blob/v0.14.4/deployments/helm/nvidia-device-plugin/values.yaml) file to see the full set of overridable parameters for the device plugin. Examples of setting these options include: @@ -699,7 +699,7 @@ Enabling compatibility with the `CPUManager` and running with a request for 100ms of CPU time and a limit of 512MB of memory. ```shell $ helm upgrade -i nvdp nvdp/nvidia-device-plugin \ - --version=0.14.3 \ + --version=0.14.4 \ --namespace nvidia-device-plugin \ --create-namespace \ --set compatWithCPUManager=true \ @@ -710,7 +710,7 @@ $ helm upgrade -i nvdp nvdp/nvidia-device-plugin \ Using the legacy Daemonset API (only available on Kubernetes < `v1.16`): ```shell $ helm upgrade -i nvdp nvdp/nvidia-device-plugin \ - --version=0.14.3 \ + --version=0.14.4 \ --namespace nvidia-device-plugin \ --create-namespace \ --set legacyDaemonsetAPI=true @@ -719,7 +719,7 @@ $ helm upgrade -i nvdp nvdp/nvidia-device-plugin \ Enabling compatibility with the `CPUManager` and the `mixed` `migStrategy` ```shell $ helm upgrade -i nvdp nvdp/nvidia-device-plugin \ - --version=0.14.3 \ + --version=0.14.4 \ --namespace nvidia-device-plugin \ --create-namespace \ --set compatWithCPUManager=true \ @@ -738,7 +738,7 @@ Discovery to perform this labeling. To enable it, simply set `gfd.enabled=true` during helm install. ``` helm upgrade -i nvdp nvdp/nvidia-device-plugin \ - --version=0.14.3 \ + --version=0.14.4 \ --namespace nvidia-device-plugin \ --create-namespace \ --set gfd.enabled=true @@ -793,14 +793,14 @@ Using the default values for the flags: $ helm upgrade -i nvdp \ --namespace nvidia-device-plugin \ --create-namespace \ - https://nvidia.github.io/k8s-device-plugin/stable/nvidia-device-plugin-0.14.3.tgz + https://nvidia.github.io/k8s-device-plugin/stable/nvidia-device-plugin-0.14.4.tgz ``` ## Building and Running Locally The next sections are focused on building the device plugin locally and running it. It is intended purely for development and testing, and not required by most users. -It assumes you are pinning to the latest release tag (i.e. `v0.14.3`), but can +It assumes you are pinning to the latest release tag (i.e. `v0.14.4`), but can easily be modified to work with any available tag or branch. ### With Docker @@ -808,8 +808,8 @@ easily be modified to work with any available tag or branch. #### Build Option 1, pull the prebuilt image from [Docker Hub](https://hub.docker.com/r/nvidia/k8s-device-plugin): ```shell -$ docker pull nvcr.io/nvidia/k8s-device-plugin:v0.14.3 -$ docker tag nvcr.io/nvidia/k8s-device-plugin:v0.14.3 nvcr.io/nvidia/k8s-device-plugin:devel +$ docker pull nvcr.io/nvidia/k8s-device-plugin:v0.14.4 +$ docker tag nvcr.io/nvidia/k8s-device-plugin:v0.14.4 nvcr.io/nvidia/k8s-device-plugin:devel ``` Option 2, build without cloning the repository: @@ -817,7 +817,7 @@ Option 2, build without cloning the repository: $ docker build \ -t nvcr.io/nvidia/k8s-device-plugin:devel \ -f deployments/container/Dockerfile.ubuntu \ - https://github.com/NVIDIA/k8s-device-plugin.git#v0.14.3 + https://github.com/NVIDIA/k8s-device-plugin.git#v0.14.4 ``` Option 3, if you want to modify the code: @@ -871,6 +871,11 @@ $ ./k8s-device-plugin --pass-device-specs ## Changelog +### Version v0.14.4 + +- Update to refactored go-gpuallocator code. This permanently fixes the NVML_NVLINK_MAX_LINKS value addressed in a + hotfix in v0.14.3. This also addresses a bug due to uninitialized NVML when calling go-gpuallocator. + ### Version v0.14.3 - Patch vendored code for new NVML_NVLINK_MAX_LINKS value diff --git a/RELEASE.md b/RELEASE.md index 4f2cb2cc9..84996e219 100644 --- a/RELEASE.md +++ b/RELEASE.md @@ -9,7 +9,7 @@ Publishing the helm chart is currently manual, and we should move to an automate # Release Process Checklist - [ ] Update the README changelog -- [ ] Update the README to change occurances of the old version (e.g: `v0.14.3`) with the new version +- [ ] Update the README to change occurances of the old version (e.g: `v0.14.4`) with the new version - [ ] Commit, Tag and Push to Gitlab - [ ] Build a new helm package with `helm package ./deployments/helm/nvidia-device-plugin` - [ ] Switch to the `gh-pages` branch and move the newly generated package to the `stable` helm repo From 082426cc473208c557720051ad41a911eff4dff4 Mon Sep 17 00:00:00 2001 From: Evan Lezar Date: Sun, 28 Jan 2024 18:52:21 +0100 Subject: [PATCH 4/4] Fix typo in github action Signed-off-by: Evan Lezar --- .github/workflows/image.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.github/workflows/image.yaml b/.github/workflows/image.yaml index a678ffd91..7c2fc75df 100644 --- a/.github/workflows/image.yaml +++ b/.github/workflows/image.yaml @@ -56,7 +56,7 @@ jobs: fi echo "PUSH_ON_BUILD=${GENERATE_ARTIFACTS}" >> $GITHUB_ENV echo "BUILD_MULTI_ARCH_IMAGES=${GENERATE_ARTIFACTS}" >> $GITHUB_ENV - s- name: Set up QEMU + - name: Set up QEMU uses: docker/setup-qemu-action@v3 - name: Set up Docker Buildx uses: docker/setup-buildx-action@v3