You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
139 lines
3.9 KiB
YAML
139 lines
3.9 KiB
YAML
# Copyright (c) 2020, NVIDIA CORPORATION. All rights reserved.
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
|
|
image:
|
|
repository: nvcr.io/nvidia/k8s/dcgm-exporter
|
|
pullPolicy: IfNotPresent
|
|
# Image tag defaults to AppVersion, but you can use the tag key
|
|
# for the image tag, e.g:
|
|
tag: 3.2.5-3.1.7-ubuntu20.04
|
|
|
|
# Change the following reference to "/etc/dcgm-exporter/default-counters.csv"
|
|
# to stop profiling metrics from DCGM
|
|
arguments: ["-f", "/etc/dcgm-exporter/dcp-metrics-included.csv"]
|
|
# NOTE: in general, add any command line arguments to arguments above
|
|
# and they will be passed through.
|
|
# Use "-r", "<HOST>:<PORT>" to connect to an already running hostengine
|
|
# Example arguments: ["-r", "host123:5555"]
|
|
# Use "-n" to remove the hostname tag from the output.
|
|
# Example arguments: ["-n"]
|
|
# Use "-d" to specify the devices to monitor. -d must be followed by a string
|
|
# in the following format: [f] or [g[:numeric_range][+]][i[:numeric_range]]
|
|
# Where a numeric range is something like 0-4 or 0,2,4, etc.
|
|
# Example arguments: ["-d", "g+i"] to monitor all GPUs and GPU instances or
|
|
# ["-d", "g:0-3"] to monitor GPUs 0-3.
|
|
# Use "-m" to specify the namespace and name of a configmap containing
|
|
# the watched exporter fields.
|
|
# Example arguments: ["-m", "default:exporter-metrics-config-map"]
|
|
|
|
imagePullSecrets: []
|
|
nameOverride: ""
|
|
fullnameOverride: ""
|
|
namespaceOverride: ""
|
|
|
|
runtimeClassName: ""
|
|
|
|
serviceAccount:
|
|
# Specifies whether a service account should be created
|
|
create: true
|
|
# Annotations to add to the service account
|
|
annotations: {}
|
|
# The name of the service account to use.
|
|
# If not set and create is true, a name is generated using the fullname template
|
|
name:
|
|
|
|
rollingUpdate:
|
|
# Specifies maximum number of DaemonSet pods that can be unavailable during the update
|
|
maxUnavailable: 1
|
|
# Specifies maximum number of nodes with an existing available DaemonSet pod that can have an updated DaemonSet pod during during an update
|
|
maxSurge: 0
|
|
|
|
podAnnotations: {}
|
|
# Using this annotation which is required for prometheus scraping
|
|
# prometheus.io/scrape: "true"
|
|
# prometheus.io/port: "9400"
|
|
|
|
podSecurityContext: {}
|
|
# fsGroup: 2000
|
|
|
|
securityContext:
|
|
runAsNonRoot: false
|
|
runAsUser: 0
|
|
capabilities:
|
|
add: ["SYS_ADMIN"]
|
|
# readOnlyRootFilesystem: true
|
|
|
|
service:
|
|
enable: true
|
|
type: ClusterIP
|
|
port: 9400
|
|
address: ":9400"
|
|
# Annotations to add to the service
|
|
annotations: {}
|
|
|
|
resources: {}
|
|
# limits:
|
|
# cpu: 100m
|
|
# memory: 128Mi
|
|
# requests:
|
|
# cpu: 100m
|
|
# memory: 128Mi
|
|
serviceMonitor:
|
|
enabled: true
|
|
interval: 15s
|
|
honorLabels: false
|
|
additionalLabels: {}
|
|
#monitoring: prometheus
|
|
relabelings: []
|
|
# - sourceLabels: [__meta_kubernetes_pod_node_name]
|
|
# separator: ;
|
|
# regex: ^(.*)$
|
|
# targetLabel: nodename
|
|
# replacement: $1
|
|
# action: replace
|
|
|
|
nodeSelector: {}
|
|
#node: gpu
|
|
|
|
tolerations: []
|
|
#- operator: Exists
|
|
|
|
affinity: {}
|
|
#nodeAffinity:
|
|
# requiredDuringSchedulingIgnoredDuringExecution:
|
|
# nodeSelectorTerms:
|
|
# - matchExpressions:
|
|
# - key: nvidia-gpu
|
|
# operator: Exists
|
|
|
|
extraHostVolumes: []
|
|
#- name: host-binaries
|
|
# hostPath: /opt/bin
|
|
|
|
extraConfigMapVolumes: []
|
|
#- name: exporter-metrics-volume
|
|
# configMap:
|
|
# name: exporter-metrics-config-map
|
|
|
|
extraVolumeMounts: []
|
|
#- name: host-binaries
|
|
# mountPath: /opt/bin
|
|
# readOnly: true
|
|
|
|
extraEnv: []
|
|
#- name: EXTRA_VAR
|
|
# value: "TheStringValue"
|
|
|
|
kubeletPath: "/var/lib/kubelet/pod-resources"
|