DCGM-Exporter release version 3.3.7-3.5.0

.gitignore

@@ -11,7 +11,7 @@ tests.cov
 test_results.json
 .scannerwork
 dist/
-
+.run/
 ###############################################################################
 # JetBrains
 # https://github.com/github/gitignore/blob/master/Global/JetBrains.gitignore
@@ -236,4 +236,4 @@ $RECYCLE.BIN/
 *.msp
 
 # Windows shortcuts
-*.lnk
+*.lnk

Makefile

@@ -20,7 +20,7 @@ MKDIR                ?= mkdir
 GOLANGCILINT_TIMEOUT ?= 10m
 
 DCGM_VERSION   := $(NEW_DCGM_VERSION)
-GOLANG_VERSION := 1.21.5
+GOLANG_VERSION := 1.22.5
 VERSION        := $(NEW_EXPORTER_VERSION)
 FULL_VERSION   := $(DCGM_VERSION)-$(VERSION)
 OUTPUT         := type=oci,dest=/dev/null
@@ -39,7 +39,7 @@ test-main:
 	$(GO) test ./... -short
 
 install: binary
-	install -m 755 $(DIST_DIR)/dcgm-exporter /usr/bin/dcgm-exporter
+	install -m 755 cmd/dcgm-exporter/dcgm-exporter /usr/bin/dcgm-exporter
 	install -m 644 -D ./etc/default-counters.csv /etc/dcgm-exporter/default-counters.csv
 	install -m 644 -D ./etc/dcp-metrics-included.csv /etc/dcgm-exporter/dcp-metrics-included.csv
 
@@ -78,7 +78,8 @@ test-integration:
 	go test -race -count=1 -timeout 5m -v $(TEST_ARGS) ./tests/integration/
 
 test-coverage:
-	gocov test ./... | gocov report
+	sh scripts/test_coverage.sh
+	gocov convert tests.cov  | gocov report
 
 .PHONY: lint
 lint:

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:3.3.6-3.4.2-ubuntu22.04
+docker run -d --gpus all --rm -p 9400:9400 nvcr.io/nvidia/k8s/dcgm-exporter:3.3.7-3.5.0-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: "3.4.2"
+    app.kubernetes.io/version: "3.5.0"
 spec:
   updateStrategy:
     type: RollingUpdate
   selector:
     matchLabels:
       app.kubernetes.io/name: "dcgm-exporter"
-      app.kubernetes.io/version: "3.4.2"
+      app.kubernetes.io/version: "3.5.0"
   template:
     metadata:
       labels:
         app.kubernetes.io/name: "dcgm-exporter"
-        app.kubernetes.io/version: "3.4.2"
+        app.kubernetes.io/version: "3.5.0"
       name: "dcgm-exporter"
     spec:
       containers:
-      - image: "nvcr.io/nvidia/k8s/dcgm-exporter:3.3.6-3.4.2-ubuntu22.04"
+      - image: "nvcr.io/nvidia/k8s/dcgm-exporter:3.3.7-3.5.0-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: "3.4.2"
+    app.kubernetes.io/version: "3.5.0"
 spec:
   selector:
     app.kubernetes.io/name: "dcgm-exporter"
-    app.kubernetes.io/version: "3.4.2"
+    app.kubernetes.io/version: "3.5.0"
   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: "3.4.2"
+version: "3.5.0"
 kubeVersion: ">= 1.19.0-0"
-appVersion: "3.4.2"
+appVersion: "3.5.0"
 sources:
 - https://github.com/nvidia/dcgm-exporter
 home: https://github.com/nvidia/dcgm-exporter/

deployment/templates/metrics-configmap.yaml

@@ -73,13 +73,13 @@ data:
       DCGM_FI_DEV_ROW_REMAP_FAILURE,           gauge,   Whether remapping of rows has failed
 
       # DCP metrics
-      DCGM_FI_PROF_GR_ENGINE_ACTIVE,   gauge, Ratio of time the graphics engine is active (in %).
-      # DCGM_FI_PROF_SM_ACTIVE,          gauge, The ratio of cycles an SM has at least 1 warp assigned (in %).
-      # DCGM_FI_PROF_SM_OCCUPANCY,       gauge, The ratio of number of warps resident on an SM (in %).
-      DCGM_FI_PROF_PIPE_TENSOR_ACTIVE, gauge, Ratio of cycles the tensor (HMMA) pipe is active (in %).
-      DCGM_FI_PROF_DRAM_ACTIVE,        gauge, Ratio of cycles the device memory interface is active sending or receiving data (in %).
-      # DCGM_FI_PROF_PIPE_FP64_ACTIVE,   gauge, Ratio of cycles the fp64 pipes are active (in %).
-      # DCGM_FI_PROF_PIPE_FP32_ACTIVE,   gauge, Ratio of cycles the fp32 pipes are active (in %).
-      # DCGM_FI_PROF_PIPE_FP16_ACTIVE,   gauge, Ratio of cycles the fp16 pipes are active (in %).
+      DCGM_FI_PROF_GR_ENGINE_ACTIVE,   gauge, Ratio of time the graphics engine is active.
+      # DCGM_FI_PROF_SM_ACTIVE,          gauge, The ratio of cycles an SM has at least 1 warp assigned.
+      # DCGM_FI_PROF_SM_OCCUPANCY,       gauge, The ratio of number of warps resident on an SM.
+      DCGM_FI_PROF_PIPE_TENSOR_ACTIVE, gauge, Ratio of cycles the tensor (HMMA) pipe is active.
+      DCGM_FI_PROF_DRAM_ACTIVE,        gauge, Ratio of cycles the device memory interface is active sending or receiving data.
+      # DCGM_FI_PROF_PIPE_FP64_ACTIVE,   gauge, Ratio of cycles the fp64 pipes are active.
+      # DCGM_FI_PROF_PIPE_FP32_ACTIVE,   gauge, Ratio of cycles the fp32 pipes are active.
+      # DCGM_FI_PROF_PIPE_FP16_ACTIVE,   gauge, Ratio of cycles the fp16 pipes are active.
       DCGM_FI_PROF_PCIE_TX_BYTES,      counter, The number of bytes of active pcie tx data including both header and payload.
       DCGM_FI_PROF_PCIE_RX_BYTES,      counter, The number of bytes of active pcie rx data including both header and payload.

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: 3.3.6-3.4.2-ubuntu22.04
+  tag: 3.3.7-3.5.0-ubuntu22.04
 
 # Change the following reference to "/etc/dcgm-exporter/default-counters.csv"
 # to stop profiling metrics from DCGM

docker/Dockerfile.ubi9

@@ -1,5 +1,5 @@
-FROM nvcr.io/nvidia/cuda:12.4.1-base-ubi9 AS builder
-ARG GOLANG_VERSION
+FROM nvcr.io/nvidia/cuda:12.5.1-base-ubi9 AS builder
+ARG GOLANG_VERSION=1.22.4
 WORKDIR /go/src/github.com/NVIDIA/dcgm-exporter
 RUN set -eux; \
 	dnf clean expire-cache; \
@@ -40,7 +40,7 @@ COPY . .
 
 RUN make binary check-format
 
-FROM nvcr.io/nvidia/cuda:12.4.1-base-ubi9
+FROM nvcr.io/nvidia/cuda:12.5.1-base-ubi9
 ARG DCGM_VERSION
 ARG VERSION
 ARG DIST_DIR
@@ -53,9 +53,17 @@ LABEL release="N/A"
 LABEL summary="Exports GPU Metrics to Prometheus"
 LABEL description="See summary"
 
-RUN dnf update --disablerepo=* --enablerepo=ubi-9-appstream-rpms --enablerepo=ubi-9-baseos-rpms -y && rm -rf /var/cache/yum \
-	&& dnf clean expire-cache && dnf install -y datacenter-gpu-manager-${DCGM_VERSION} libcap \
-	&& rm -rfd /usr/local/dcgm/bindings /usr/local/dcgm/sdk_samples /usr/share/nvidia-validation-suite
+RUN dnf update --disablerepo=* --enablerepo=ubi-9-appstream-rpms --enablerepo=ubi-9-baseos-rpms -y \
+	&& dnf install --nodocs --setopt=install_weak_deps=False -y datacenter-gpu-manager-${DCGM_VERSION} libcap \
+	&& dnf -y clean all\
+	&& rm -rf /var/cache/yum\
+	&& rm -rfd /usr/local/dcgm/bindings /usr/local/dcgm/sdk_samples /usr/share/nvidia-validation-suite \
+	# DCGM exporter doesn't use libdcgm_cublas_proxy*.so.
+	&& rm -rf /usr/lib64/libdcgm_cublas_proxy*.so \
+	&& rm -rf /usr/local/dcgm/scripts \
+	&& rm -f /usr/include/*.h /usr/bin/DcgmProfTesterKernels.ptx /usr/bin/dcgmproftester* \
+	&& rm -rf /var/lib/rpm/rpmdb.sqlite /var/cache/* /var/lib/dnf/history.* /var/log/* /tmp/* /var/tmp/* \
+	&& rm -rf /usr/share/doc && rm -rf /usr/share/man
 
 COPY ./LICENSE ./licenses/LICENSE
 COPY --from=builder /go/src/github.com/NVIDIA/dcgm-exporter/cmd/dcgm-exporter/dcgm-exporter /usr/bin/

docker/Dockerfile.ubuntu22.04

@@ -1,5 +1,5 @@
-FROM nvcr.io/nvidia/cuda:12.4.1-base-ubuntu22.04 AS builder
-ARG GOLANG_VERSION=1.21.5
+FROM nvcr.io/nvidia/cuda:12.5.1-base-ubuntu22.04 AS builder
+ARG GOLANG_VERSION=1.22.4
 WORKDIR /go/src/github.com/NVIDIA/dcgm-exporter
 RUN set -eux; \
 	apt-get update; \
@@ -45,7 +45,7 @@ COPY . .
 
 RUN make binary check-format
 
-FROM nvcr.io/nvidia/cuda:12.4.1-base-ubuntu22.04
+FROM nvcr.io/nvidia/cuda:12.5.1-base-ubuntu22.04
 
 ARG VERSION
 ARG DCGM_VERSION
@@ -65,9 +65,16 @@ COPY etc /etc/dcgm-exporter
 
 RUN apt-get update && apt-get install -y --no-install-recommends \
 	datacenter-gpu-manager=1:${DCGM_VERSION} libcap2-bin && apt-get purge --autoremove -y openssl \
+	&& apt-get -y clean \
+	&& apt-get -y autoclean \
 	&& apt-get autoremove -y \
-	&& rm -rf /var/lib/apt/lists/* \
-	&& rm -rfd /usr/local/dcgm/bindings /usr/local/dcgm/sdk_samples /usr/share/nvidia-validation-suite
+	&& rm -rfd /usr/local/dcgm/bindings /usr/local/dcgm/sdk_samples /usr/share/nvidia-validation-suite \
+	# DCGM exporter doesn't use libdcgm_cublas_proxy*.so.
+	&& rm -rf /usr/lib/x86_64-linux-gnu/libdcgm_cublas_proxy*.so \
+	&& rm -rf /usr/local/dcgm/scripts \
+	&& rm -f /usr/include/*.h /usr/bin/DcgmProfTesterKernels.ptx /usr/bin/dcgmproftester* \
+	&& rm -rf /var/cache/debconf/* /var/lib/apt/lists/* /var/log/* /tmp/* /var/tmp/* \
+	&& rm -rf /usr/share/doc && rm -rf /usr/share/man
 # Required for DCP metrics
 ENV NVIDIA_DRIVER_CAPABILITIES=compute,utility,compat32
 # disable all constraints on the configurations required by NVIDIA container toolkit

etc/dcp-metrics-included.csv

@@ -77,14 +77,14 @@ DCGM_FI_DRIVER_VERSION,        label, Driver Version
 # DCGM_FI_DEV_VBIOS_VERSION,     label, VBIOS version of the device
 
 # DCP metrics
-DCGM_FI_PROF_GR_ENGINE_ACTIVE,   gauge, Ratio of time the graphics engine is active (in %).
-# DCGM_FI_PROF_SM_ACTIVE,          gauge, The ratio of cycles an SM has at least 1 warp assigned (in %).
-# DCGM_FI_PROF_SM_OCCUPANCY,       gauge, The ratio of number of warps resident on an SM (in %).
-DCGM_FI_PROF_PIPE_TENSOR_ACTIVE, gauge, Ratio of cycles the tensor (HMMA) pipe is active (in %).
-DCGM_FI_PROF_DRAM_ACTIVE,        gauge, Ratio of cycles the device memory interface is active sending or receiving data (in %).
-# DCGM_FI_PROF_PIPE_FP64_ACTIVE,   gauge, Ratio of cycles the fp64 pipes are active (in %).
-# DCGM_FI_PROF_PIPE_FP32_ACTIVE,   gauge, Ratio of cycles the fp32 pipes are active (in %).
-# DCGM_FI_PROF_PIPE_FP16_ACTIVE,   gauge, Ratio of cycles the fp16 pipes are active (in %).
+DCGM_FI_PROF_GR_ENGINE_ACTIVE,   gauge, Ratio of time the graphics engine is active.
+# DCGM_FI_PROF_SM_ACTIVE,          gauge, The ratio of cycles an SM has at least 1 warp assigned.
+# DCGM_FI_PROF_SM_OCCUPANCY,       gauge, The ratio of number of warps resident on an SM.
+DCGM_FI_PROF_PIPE_TENSOR_ACTIVE, gauge, Ratio of cycles the tensor (HMMA) pipe is active.
+DCGM_FI_PROF_DRAM_ACTIVE,        gauge, Ratio of cycles the device memory interface is active sending or receiving data.
+# DCGM_FI_PROF_PIPE_FP64_ACTIVE,   gauge, Ratio of cycles the fp64 pipes are active.
+# DCGM_FI_PROF_PIPE_FP32_ACTIVE,   gauge, Ratio of cycles the fp32 pipes are active.
+# DCGM_FI_PROF_PIPE_FP16_ACTIVE,   gauge, Ratio of cycles the fp16 pipes are active.
 DCGM_FI_PROF_PCIE_TX_BYTES,      gauge, The rate of data transmitted over the PCIe bus - including both protocol headers and data payloads - in bytes per second.
 DCGM_FI_PROF_PCIE_RX_BYTES,      gauge, The rate of data received over the PCIe bus - including both protocol headers and data payloads - in bytes per second.
 

go.mod

@@ -1,16 +1,18 @@
 module github.com/NVIDIA/dcgm-exporter
 
-go 1.21
+go 1.22.0
+
+toolchain go1.22.4
 
 require (
 	github.com/NVIDIA/go-dcgm v0.0.0-20240118201113-3385e277e49f
 	github.com/NVIDIA/go-nvml v0.12.0-2
 	github.com/avast/retry-go/v4 v4.5.1
 	github.com/bits-and-blooms/bitset v1.13.0
 	github.com/go-kit/log v0.2.1
-	github.com/google/uuid v1.5.0
+	github.com/google/uuid v1.6.0
 	github.com/gorilla/mux v1.8.1
-	github.com/mittwald/go-helm-client v0.12.8
+	github.com/mittwald/go-helm-client v0.12.9
 	github.com/onsi/ginkgo/v2 v2.15.0
 	github.com/onsi/gomega v1.32.0
 	github.com/prometheus/client_model v0.6.0
@@ -20,13 +22,14 @@ require (
 	github.com/stretchr/testify v1.8.4
 	github.com/urfave/cli/v2 v2.27.1
 	go.uber.org/automaxprocs v1.5.3
-	golang.org/x/sync v0.5.0
-	google.golang.org/grpc v1.61.1
-	k8s.io/api v0.29.2
-	k8s.io/apimachinery v0.29.2
-	k8s.io/client-go v0.29.2
-	k8s.io/kubelet v0.29.2
-	k8s.io/utils v0.0.0-20240102154912-e7106e64919e
+	go.uber.org/mock v0.4.0
+	golang.org/x/sync v0.7.0
+	google.golang.org/grpc v1.64.0
+	k8s.io/api v0.30.2
+	k8s.io/apimachinery v0.30.2
+	k8s.io/client-go v0.30.2
+	k8s.io/kubelet v0.30.2
+	k8s.io/utils v0.0.0-20240502163921-fe8a2dddb1d0
 )
 
 require (
@@ -44,20 +47,19 @@ require (
 	github.com/beorn7/perks v1.0.1 // indirect
 	github.com/cespare/xxhash/v2 v2.2.0 // indirect
 	github.com/chai2010/gettext-go v1.0.2 // indirect
-	github.com/containerd/containerd v1.7.11 // indirect
+	github.com/containerd/containerd v1.7.12 // indirect
 	github.com/containerd/log v0.1.0 // indirect
 	github.com/coreos/go-systemd/v22 v22.5.0 // indirect
 	github.com/cpuguy83/go-md2man/v2 v2.0.3 // indirect
 	github.com/cyphar/filepath-securejoin v0.2.4 // indirect
 	github.com/davecgh/go-spew v1.1.1 // indirect
 	github.com/distribution/reference v0.5.0 // indirect
-	github.com/docker/cli v24.0.7+incompatible // indirect
+	github.com/docker/cli v26.1.4+incompatible // indirect
 	github.com/docker/distribution v2.8.3+incompatible // indirect
-	github.com/docker/docker v24.0.7+incompatible // indirect
+	github.com/docker/docker v26.1.4+incompatible // indirect
 	github.com/docker/docker-credential-helpers v0.8.0 // indirect
-	github.com/docker/go-connections v0.4.0 // indirect
+	github.com/docker/go-connections v0.5.0 // indirect
 	github.com/docker/go-metrics v0.0.1 // indirect
-	github.com/docker/go-units v0.5.0 // indirect
 	github.com/emicklei/go-restful/v3 v3.11.1 // indirect
 	github.com/evanphx/json-patch v5.7.0+incompatible // indirect
 	github.com/exponent-io/jsonpath v0.0.0-20210407135951-1de76d718b3f // indirect
@@ -74,7 +76,7 @@ require (
 	github.com/go-task/slim-sprig v0.0.0-20230315185526-52ccab3ef572 // indirect
 	github.com/gobwas/glob v0.2.3 // indirect
 	github.com/gogo/protobuf v1.3.2 // indirect
-	github.com/golang/protobuf v1.5.3 // indirect
+	github.com/golang/protobuf v1.5.4 // indirect
 	github.com/google/btree v1.1.2 // indirect
 	github.com/google/gnostic-models v0.6.8 // indirect
 	github.com/google/go-cmp v0.6.0 // indirect
@@ -111,12 +113,11 @@ require (
 	github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd // indirect
 	github.com/modern-go/reflect2 v1.0.2 // indirect
 	github.com/monochromegane/go-gitignore v0.0.0-20200626010858-205db1a8cc00 // indirect
-	github.com/morikuni/aec v1.0.0 // indirect
 	github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 // indirect
 	github.com/mwitkow/go-conntrack v0.0.0-20190716064945-2f068394615f // indirect
 	github.com/mxk/go-flowrate v0.0.0-20140419014527-cca7078d478f // indirect
 	github.com/opencontainers/go-digest v1.0.0 // indirect
-	github.com/opencontainers/image-spec v1.1.0-rc5 // indirect
+	github.com/opencontainers/image-spec v1.1.0-rc6 // indirect
 	github.com/peterbourgon/diskv v2.0.1+incompatible // indirect
 	github.com/pkg/errors v0.9.1 // indirect
 	github.com/pmezard/go-difflib v1.0.0 // indirect
@@ -140,32 +141,32 @@ require (
 	go.opentelemetry.io/otel/metric v1.21.0 // indirect
 	go.opentelemetry.io/otel/trace v1.21.0 // indirect
 	go.starlark.net v0.0.0-20231121155337-90ade8b19d09 // indirect
-	go.uber.org/mock v0.4.0 // indirect
-	golang.org/x/crypto v0.18.0 // indirect
+	golang.org/x/crypto v0.24.0 // indirect
 	golang.org/x/exp v0.0.0-20240103183307-be819d1f06fc // indirect
-	golang.org/x/net v0.20.0 // indirect
-	golang.org/x/oauth2 v0.16.0 // indirect
-	golang.org/x/sys v0.16.0 // indirect
-	golang.org/x/term v0.16.0 // indirect
-	golang.org/x/text v0.14.0 // indirect
+	golang.org/x/mod v0.17.0 // indirect
+	golang.org/x/net v0.26.0 // indirect
+	golang.org/x/oauth2 v0.18.0 // indirect
+	golang.org/x/sys v0.21.0 // indirect
+	golang.org/x/term v0.21.0 // indirect
+	golang.org/x/text v0.16.0 // indirect
 	golang.org/x/time v0.5.0 // indirect
-	golang.org/x/tools v0.16.1 // indirect
+	golang.org/x/tools v0.21.1-0.20240508182429-e35e4ccd0d2d // indirect
 	google.golang.org/appengine v1.6.8 // indirect
-	google.golang.org/genproto/googleapis/rpc v0.0.0-20240102182953-50ed04b92917 // indirect
+	google.golang.org/genproto/googleapis/rpc v0.0.0-20240318140521-94a12d6c2237 // indirect
 	google.golang.org/protobuf v1.33.0 // indirect
 	gopkg.in/evanphx/json-patch.v5 v5.7.0 // indirect
 	gopkg.in/inf.v0 v0.9.1 // indirect
 	gopkg.in/yaml.v2 v2.4.0 // indirect
 	gopkg.in/yaml.v3 v3.0.1 // indirect
-	helm.sh/helm/v3 v3.14.2 // indirect
-	k8s.io/apiextensions-apiserver v0.29.0 // indirect
-	k8s.io/apiserver v0.29.2 // indirect
-	k8s.io/cli-runtime v0.29.0 // indirect
-	k8s.io/component-base v0.29.2 // indirect
-	k8s.io/klog/v2 v2.110.1 // indirect
-	k8s.io/kube-openapi v0.0.0-20240220201932-37d671a357a5 // indirect
-	k8s.io/kubectl v0.29.0 // indirect
-	oras.land/oras-go v1.2.4 // indirect
+	helm.sh/helm/v3 v3.15.2 // indirect
+	k8s.io/apiextensions-apiserver v0.30.0 // indirect
+	k8s.io/apiserver v0.30.2 // indirect
+	k8s.io/cli-runtime v0.30.0 // indirect
+	k8s.io/component-base v0.30.2 // indirect
+	k8s.io/klog/v2 v2.120.1 // indirect
+	k8s.io/kube-openapi v0.0.0-20240228011516-70dd3763d340 // indirect
+	k8s.io/kubectl v0.30.0 // indirect
+	oras.land/oras-go v1.2.5 // indirect
 	sigs.k8s.io/json v0.0.0-20221116044647-bc3834ca7abd // indirect
 	sigs.k8s.io/kustomize/api v0.16.0 // indirect
 	sigs.k8s.io/kustomize/kyaml v0.16.0 // indirect