DCGM-Exporter release 3.3.8-3.6.0 (#390)

Author: glowkey

README.md

@@ -11,7 +11,7 @@ Official documentation for DCGM-Exporter can be found on [docs.nvidia.com](https
 To gather metrics on a GPU node, simply start the `dcgm-exporter` container:
 
 ```shell
-docker run -d --gpus all --rm -p 9400:9400 nvcr.io/nvidia/k8s/dcgm-exporter:3.3.7-3.5.0-ubuntu22.04
+docker run -d --gpus all --rm -p 9400:9400 nvcr.io/nvidia/k8s/dcgm-exporter:3.3.8-3.6.0-ubuntu22.04
 curl localhost:9400/metrics
 # HELP DCGM_FI_DEV_SM_CLOCK SM clock frequency (in MHz).
 # TYPE DCGM_FI_DEV_SM_CLOCK gauge

dcgm-exporter.yaml

@@ -18,23 +18,23 @@ metadata:
   name: "dcgm-exporter"
   labels:
     app.kubernetes.io/name: "dcgm-exporter"
-    app.kubernetes.io/version: "3.5.0"
+    app.kubernetes.io/version: "3.6.0"
 spec:
   updateStrategy:
     type: RollingUpdate
   selector:
     matchLabels:
       app.kubernetes.io/name: "dcgm-exporter"
-      app.kubernetes.io/version: "3.5.0"
+      app.kubernetes.io/version: "3.6.0"
   template:
     metadata:
       labels:
         app.kubernetes.io/name: "dcgm-exporter"
-        app.kubernetes.io/version: "3.5.0"
+        app.kubernetes.io/version: "3.6.0"
       name: "dcgm-exporter"
     spec:
       containers:
-      - image: "nvcr.io/nvidia/k8s/dcgm-exporter:3.3.7-3.5.0-ubuntu22.04"
+      - image: "nvcr.io/nvidia/k8s/dcgm-exporter:3.3.8-3.6.0-ubuntu22.04"
         env:
         - name: "DCGM_EXPORTER_LISTEN"
           value: ":9400"
@@ -64,11 +64,11 @@ metadata:
   name: "dcgm-exporter"
   labels:
     app.kubernetes.io/name: "dcgm-exporter"
-    app.kubernetes.io/version: "3.5.0"
+    app.kubernetes.io/version: "3.6.0"
 spec:
   selector:
     app.kubernetes.io/name: "dcgm-exporter"
-    app.kubernetes.io/version: "3.5.0"
+    app.kubernetes.io/version: "3.6.0"
   ports:
   - name: "metrics"
     port: 9400

deployment/Chart.yaml

@@ -1,9 +1,9 @@
 apiVersion: v2
 name: dcgm-exporter
 description: A Helm chart for DCGM exporter
-version: "3.5.0"
+version: "3.6.0"
 kubeVersion: ">= 1.19.0-0"
-appVersion: "3.5.0"
+appVersion: "3.6.0"
 sources:
 - https://github.com/nvidia/dcgm-exporter
 home: https://github.com/nvidia/dcgm-exporter/

deployment/values.yaml

@@ -17,7 +17,7 @@ image:
   pullPolicy: IfNotPresent
   # Image tag defaults to AppVersion, but you can use the tag key
   # for the image tag, e.g:
-  tag: 3.3.7-3.5.0-ubuntu22.04
+  tag: 3.3.8-3.6.0-ubuntu22.04
 
 # Change the following reference to "/etc/dcgm-exporter/default-counters.csv"
 # to stop profiling metrics from DCGM

docker/Dockerfile.ubi9

@@ -1,4 +1,4 @@
-FROM nvcr.io/nvidia/cuda:12.5.1-base-ubi9 AS builder
+FROM nvcr.io/nvidia/cuda:12.6.1-base-ubi9 AS builder
 ARG GOLANG_VERSION=1.22.4
 WORKDIR /go/src/github.com/NVIDIA/dcgm-exporter
 RUN set -eux; \
@@ -40,7 +40,7 @@ COPY . .
 
 RUN make binary check-format
 
-FROM nvcr.io/nvidia/cuda:12.5.1-base-ubi9
+FROM nvcr.io/nvidia/cuda:12.6.1-base-ubi9
 ARG DCGM_VERSION
 ARG VERSION
 ARG DIST_DIR

docker/Dockerfile.ubuntu22.04

@@ -1,4 +1,4 @@
-FROM nvcr.io/nvidia/cuda:12.5.1-base-ubuntu22.04 AS builder
+FROM nvcr.io/nvidia/cuda:12.6.1-base-ubuntu22.04 AS builder
 ARG GOLANG_VERSION=1.22.4
 WORKDIR /go/src/github.com/NVIDIA/dcgm-exporter
 RUN set -eux; \
@@ -45,7 +45,7 @@ COPY . .
 
 RUN make binary check-format
 
-FROM nvcr.io/nvidia/cuda:12.5.1-base-ubuntu22.04
+FROM nvcr.io/nvidia/cuda:12.6.1-base-ubuntu22.04
 
 ARG VERSION
 ARG DCGM_VERSION

hack/VERSION

@@ -1,4 +1,4 @@
-OLD_DCGM_VERSION=3.3.6
-OLD_EXPORTER_VERSION=3.4.2
-NEW_DCGM_VERSION=3.3.7
-NEW_EXPORTER_VERSION=3.5.0
+OLD_DCGM_VERSION=3.3.7
+OLD_EXPORTER_VERSION=3.5.0
+NEW_DCGM_VERSION=3.3.8
+NEW_EXPORTER_VERSION=3.6.0

service-monitor.yaml

@@ -18,12 +18,12 @@ metadata:
   name: "dcgm-exporter"
   labels:
     app.kubernetes.io/name: "dcgm-exporter"
-    app.kubernetes.io/version: "3.5.0"
+    app.kubernetes.io/version: "3.6.0"
 spec:
   selector:
     matchLabels:
       app.kubernetes.io/name: "dcgm-exporter"
-      app.kubernetes.io/version: "3.5.0"
+      app.kubernetes.io/version: "3.6.0"
   endpoints:
   - port: "metrics"
     path: "/metrics"

tests/e2e/Makefile

@@ -16,7 +16,7 @@ GO_CMD ?= go
 NAMESPACE ?= "dcgm-exporter"
 CHART ?= "./../../deployment/"
 IMAGE_REPOSITORY ?= "nvcr.io/nvidia/k8s/dcgm-exporter"
-IMAGE_TAG ?= "3.3.7-3.5.0-ubuntu22.04"
+IMAGE_TAG ?= "3.3.8-3.6.0-ubuntu22.04"
 KUBECONFIG ?= "~/.kube/config"
 
 define TEST_CMD