Bump dcgm-exporter to 2.1.1 with fixes to allow it to work with < r45…

…0 drivers.

Signed-off-by: Shiva Krishna, Merla <[email protected]>

Makefile

@@ -18,7 +18,7 @@ REGISTRY ?= nvidia
 
 DCGM_VERSION   := 2.0.13
 GOLANG_VERSION := 1.14.2
-VERSION        := 2.1.0
+VERSION        := 2.1.1
 FULL_VERSION   := $(DCGM_VERSION)-$(VERSION)
 
 .PHONY: all binary install check-format

README.md

@@ -18,7 +18,7 @@ The repository also contains DCGM-Exporter. It exposes GPU metrics exporter for
 
 To gather metrics on a GPU node, simply start the `dcgm-exporter` container:
 ```
-$ docker run -d --gpus all --rm -p 9400:9400 nvidia/dcgm-exporter:2.0.13-2.1.0-ubuntu18.04
+$ docker run -d --gpus all --rm -p 9400:9400 nvidia/dcgm-exporter:2.0.13-2.1.1-ubuntu18.04
 $ 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: "2.1.0"
+    app.kubernetes.io/version: "2.1.1"
 spec:
   updateStrategy:
     type: RollingUpdate
   selector:
     matchLabels:
       app.kubernetes.io/name: "dcgm-exporter"
-      app.kubernetes.io/version: "2.1.0"
+      app.kubernetes.io/version: "2.1.1"
   template:
     metadata:
       labels:
         app.kubernetes.io/name: "dcgm-exporter"
-        app.kubernetes.io/version: "2.1.0"
+        app.kubernetes.io/version: "2.1.1"
       name: "dcgm-exporter"
     spec:
       containers:
-      - image: "nvidia/dcgm-exporter:2.0.13-2.1.0-ubuntu18.04"
+      - image: "nvidia/dcgm-exporter:2.0.13-2.1.1-ubuntu18.04"
         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: "2.1.0"
+    app.kubernetes.io/version: "2.1.1"
 spec:
   selector:
     app.kubernetes.io/name: "dcgm-exporter"
-    app.kubernetes.io/version: "2.1.0"
+    app.kubernetes.io/version: "2.1.1"
   ports:
   - name: "metrics"
     port: 9400

deployment/dcgm-exporter/Chart.yaml

@@ -1,9 +1,9 @@
 apiVersion: v2
 name: dcgm-exporter
 description: A Helm chart for DCGM exporter
-version: "2.1.0"
+version: "2.1.1"
 kubeVersion: ">= 1.13.0"
-appVersion: "2.1.0"
+appVersion: "2.1.1"
 sources:
 - https://gitlab.com/nvidia/container-toolkit/gpu-monitoring-tools
 home: https://github.com/nvidia/gpu-monitoring-tools/

deployment/dcgm-exporter/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: 2.0.13-2.1.0-ubuntu18.04
+  tag: 2.0.13-2.1.1-ubuntu18.04
 
 # Comment the following line to stop profiling metrics from DCGM
 arguments: ["-f", "/etc/dcgm-exporter/dcp-metrics-included.csv"]

service-monitor.yaml

@@ -18,12 +18,12 @@ metadata:
   name: "dcgm-exporter"
   labels:
     app.kubernetes.io/name: "dcgm-exporter"
-    app.kubernetes.io/version: "2.1.0"
+    app.kubernetes.io/version: "2.1.1"
 spec:
   selector:
     matchLabels:
       app.kubernetes.io/name: "dcgm-exporter"
-      app.kubernetes.io/version: "2.1.0"
+      app.kubernetes.io/version: "2.1.1"
   endpoints:
   - port: "metrics"
     path: "/metrics"