values.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: 4.1.1-4.0.4-ubuntu22.04

# Change the following reference to "/etc/dcgm-exporter/default-counters.csv"
# to stop profiling metrics from DCGM
arguments: ["-f", "/etc/dcgm-exporter/default-counters.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"]

# Image pull secrets for container images
imagePullSecrets: []

# Overrides the chart's name
nameOverride: ""

# Overrides the chart's computed fullname
fullnameOverride: ""

# Overrides the deployment namespace
namespaceOverride: ""

# Defines the runtime class that will be used by the pod
runtimeClassName: ""
# Defines serviceAccount names for components.
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

# Labels to be added to dcgm-exporter pods
podLabels: {}

# Annotations to be added to dcgm-exporter pods
podAnnotations: {}
# Using this annotation which is required for prometheus scraping
  # prometheus.io/scrape: "true"
  # prometheus.io/port: "9400"

# The SecurityContext for the dcgm-exporter pods
podSecurityContext: {}
  # fsGroup: 2000

# The SecurityContext for the dcgm-exporter containers
securityContext:
  runAsNonRoot: false
  runAsUser: 0
  capabilities:
    add: ["SYS_ADMIN"]
  # readOnlyRootFilesystem: true

# Defines the dcgm-exporter service
service:
  # When enabled, the helm chart will create service
  enable: true
  type: ClusterIP
  clusterIP: ""
  port: 9400
  address: ":9400"
  # Annotations to add to the service
  annotations: {}

# Allows to control pod resources
resources: {}
  # limits:
  #   cpu: 100m
  #   memory: 128Mi
  # requests:
  #   cpu: 100m
  #   memory: 128Mi
serviceMonitor:
  apiVersion: "monitoring.coreos.com/v1"
  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
      items:
      - key: metrics
        path: default-counters.csv

extraVolumeMounts:
  - name: exporter-metrics-volume
    mountPath: /etc/dcgm-exporter/default-counters.csv
    subPath: default-counters.csv

extraEnv: []
#- name: EXTRA_VAR
#  value: "TheStringValue"

# Path to the kubelet socket for /pod-resources
kubeletPath: "/var/lib/kubelet/pod-resources"

# HTTPS configuration
tlsServerConfig:
  # Enable or disable HTTPS configuration
  enabled: false
  # Use autogenerated self-signed TLS certificates. Not recommended for production environments.
  autoGenerated: true
  # Existing secret containing your own server key and certificate
  existingSecret: ""
  # Certificate file name
  certFilename: "tls.crt"
  # Key file name
  keyFilename: "tls.key"
  # CA certificate file name
  caFilename: "ca.crt"
  # Server policy for client authentication. Maps to ClientAuth Policies.
  # For more detail on clientAuth options:
  # https://golang.org/pkg/crypto/tls/#ClientAuthType
  #
  # NOTE: If you want to enable client authentication, you need to use
  # RequireAndVerifyClientCert. Other values are insecure.
  clientAuthType: ""
  # TLS Key for HTTPS - ignored if existingSecret is provided
  key: ""
  # TLS Certificate for HTTPS - ignored if existingSecret is provided
  cert: ""
  # CA Certificate for HTTPS - ignored if existingSecret is provided
  ca: ""

basicAuth:
  #Object containing <user>:<passwords> key-value pairs for each user that will have access via basic authentication
  users: {}

# Customized list of metrics to emit. Expected to be in the same format (CSV) as the default list.
# Must be the complete list and is not additive. If unset, the default list will take effect.
# customMetrics: |
  # Format
  # If line starts with a '#' it is considered a comment
  # DCGM FIELD, Prometheus metric type, help message
  
  # Clocks
  # DCGM_FI_DEV_SM_CLOCK,  gauge, SM clock frequency (in MHz).
  # DCGM_FI_DEV_MEM_CLOCK, gauge, Memory clock frequency (in MHz).
  
  # Temperature
  # DCGM_FI_DEV_MEMORY_TEMP, gauge, Memory temperature (in C).
  # DCGM_FI_DEV_GPU_TEMP,    gauge, GPU temperature (in C).
  
  # Power
  # DCGM_FI_DEV_POWER_USAGE,              gauge, Power draw (in W).
  # DCGM_FI_DEV_TOTAL_ENERGY_CONSUMPTION, counter, Total energy consumption since boot (in mJ).
  
  # PCIE
  # DCGM_FI_DEV_PCIE_TX_THROUGHPUT,  counter, Total number of bytes transmitted through PCIe TX (in KB) via NVML.
  # DCGM_FI_DEV_PCIE_RX_THROUGHPUT,  counter, Total number of bytes received through PCIe RX (in KB) via NVML.
  # DCGM_FI_DEV_PCIE_REPLAY_COUNTER, counter, Total number of PCIe retries.
  
  # Utilization (the sample period varies depending on the product)
  # DCGM_FI_DEV_GPU_UTIL,      gauge, GPU utilization (in %).
  # DCGM_FI_DEV_MEM_COPY_UTIL, gauge, Memory utilization (in %).
  # DCGM_FI_DEV_ENC_UTIL,      gauge, Encoder utilization (in %).
  # DCGM_FI_DEV_DEC_UTIL ,     gauge, Decoder utilization (in %).
  
  # Errors and violations
  # DCGM_FI_DEV_XID_ERRORS,            gauge,   Value of the last XID error encountered.
  # DCGM_FI_DEV_POWER_VIOLATION,       counter, Throttling duration due to power constraints (in us).
  # DCGM_FI_DEV_THERMAL_VIOLATION,     counter, Throttling duration due to thermal constraints (in us).
  # DCGM_FI_DEV_SYNC_BOOST_VIOLATION,  counter, Throttling duration due to sync-boost constraints (in us).
  # DCGM_FI_DEV_BOARD_LIMIT_VIOLATION, counter, Throttling duration due to board limit constraints (in us).
  # DCGM_FI_DEV_LOW_UTIL_VIOLATION,    counter, Throttling duration due to low utilization (in us).
  # DCGM_FI_DEV_RELIABILITY_VIOLATION, counter, Throttling duration due to reliability constraints (in us).
  
  # Memory usage
  # DCGM_FI_DEV_FB_FREE, gauge, Framebuffer memory free (in MiB).
  # DCGM_FI_DEV_FB_USED, gauge, Framebuffer memory used (in MiB).
  
  # ECC
  # DCGM_FI_DEV_ECC_SBE_VOL_TOTAL, counter, Total number of single-bit volatile ECC errors.
  # DCGM_FI_DEV_ECC_DBE_VOL_TOTAL, counter, Total number of double-bit volatile ECC errors.
  # DCGM_FI_DEV_ECC_SBE_AGG_TOTAL, counter, Total number of single-bit persistent ECC errors.
  # DCGM_FI_DEV_ECC_DBE_AGG_TOTAL, counter, Total number of double-bit persistent ECC errors.
  
  # Retired pages
  # DCGM_FI_DEV_RETIRED_SBE,     counter, Total number of retired pages due to single-bit errors.
  # DCGM_FI_DEV_RETIRED_DBE,     counter, Total number of retired pages due to double-bit errors.
  # DCGM_FI_DEV_RETIRED_PENDING, counter, Total number of pages pending retirement.
  
  # NVLink
  # DCGM_FI_DEV_NVLINK_CRC_FLIT_ERROR_COUNT_TOTAL, counter, Total number of NVLink flow-control CRC errors.
  # DCGM_FI_DEV_NVLINK_CRC_DATA_ERROR_COUNT_TOTAL, counter, Total number of NVLink data CRC errors.
  # DCGM_FI_DEV_NVLINK_REPLAY_ERROR_COUNT_TOTAL,   counter, Total number of NVLink retries.
  # DCGM_FI_DEV_NVLINK_RECOVERY_ERROR_COUNT_TOTAL, counter, Total number of NVLink recovery errors.
  # DCGM_FI_DEV_NVLINK_BANDWIDTH_TOTAL,            counter, Total number of NVLink bandwidth counters for all lanes.
  # DCGM_FI_DEV_NVLINK_BANDWIDTH_L0,               counter, The number of bytes of active NVLink rx or tx data including both header and payload.
  
  # VGPU License status
  # DCGM_FI_DEV_VGPU_LICENSE_STATUS, gauge, vGPU License status
  
  # Remapped rows
  # DCGM_FI_DEV_UNCORRECTABLE_REMAPPED_ROWS, counter, Number of remapped rows for uncorrectable errors
  # DCGM_FI_DEV_CORRECTABLE_REMAPPED_ROWS,   counter, Number of remapped rows for correctable errors
  # 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.
  # 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.