134 lines
3.1 KiB
YAML
134 lines
3.1 KiB
YAML
fullnameOverride: opentelemetry-dsgpu-prd
|
|
|
|
mode: daemonset
|
|
|
|
# priorityClassName: "system-node-critical"
|
|
# Removing since dataengg pods are going into pending state
|
|
config:
|
|
exporters:
|
|
loadbalancing:
|
|
routing_key: "traceID"
|
|
protocol:
|
|
otlp:
|
|
timeout: 5s
|
|
tls:
|
|
insecure: true
|
|
sending_queue:
|
|
num_consumers: 500
|
|
queue_size: 50000
|
|
resolver:
|
|
dns:
|
|
hostname: opentelemetry-admin-prd-headless.opentelemetry.svc.clusterset.local
|
|
processors: {}
|
|
receivers:
|
|
otlp:
|
|
protocols:
|
|
grpc:
|
|
endpoint: ${env:MY_POD_IP}:4317
|
|
http:
|
|
endpoint: ${env:MY_POD_IP}:4318
|
|
service:
|
|
telemetry:
|
|
metrics:
|
|
level: detailed
|
|
readers:
|
|
- pull:
|
|
exporter:
|
|
prometheus:
|
|
host: '0.0.0.0'
|
|
port: 8888
|
|
extensions:
|
|
- health_check
|
|
pipelines:
|
|
logs: null
|
|
metrics: null
|
|
traces:
|
|
exporters:
|
|
- loadbalancing
|
|
processors: []
|
|
receivers:
|
|
- otlp
|
|
|
|
image:
|
|
repository: asia-southeast1-docker.pkg.dev/meesho-devops-admin-0622/admin/sre/opentelemetry-collector-contrib
|
|
tag: "0.111.0"
|
|
|
|
tolerations:
|
|
- operator: Exists
|
|
|
|
affinity:
|
|
nodeAffinity:
|
|
requiredDuringSchedulingIgnoredDuringExecution:
|
|
nodeSelectorTerms:
|
|
- matchExpressions:
|
|
- key: p-dsgpu-contour-ext
|
|
operator: NotIn
|
|
values:
|
|
- dedicated
|
|
- key: p-dsgpu-contour-int-0
|
|
operator: NotIn
|
|
values:
|
|
- dedicated
|
|
- key: p-dsgpu-contour-int-1
|
|
operator: NotIn
|
|
values:
|
|
- dedicated
|
|
- key: p-dsgpu-contour-int
|
|
operator: NotIn
|
|
values:
|
|
- dedicated
|
|
- key: node_pool
|
|
operator: NotIn
|
|
values:
|
|
- np-dsgpu-default-prd-ase1
|
|
- key: cloud.google.com/compute-class
|
|
operator: NotIn
|
|
values:
|
|
- n4d-highcpu-64-vmagent-compute-class
|
|
- n4-highcpu-16-vminsert-compute-class
|
|
- c3-highcpu-44-vmselect-compute-class
|
|
- n4d-highmem-48-vmstorage-compute-class
|
|
- c3-highcpu-22-contour-internal-1-compute-class
|
|
- c4d-highcpu-16-contour-internal-1-compute-class
|
|
- c3-highcpu-22-contour-internal-0-compute-class
|
|
- c4d-highcpu-16-contour-internal-0-compute-class
|
|
|
|
extraEnvs:
|
|
- name: K8S_NODE_NAME
|
|
valueFrom:
|
|
fieldRef:
|
|
apiVersion: v1
|
|
fieldPath: spec.nodeName
|
|
- name: OTEL_RESOURCE_ATTRIBUTES
|
|
value: "k8s.node.name=$(K8S_NODE_NAME)"
|
|
|
|
ports:
|
|
metrics:
|
|
enabled: true
|
|
|
|
resources:
|
|
requests:
|
|
cpu: 100m
|
|
memory: 124Mi
|
|
limits:
|
|
cpu: 200m
|
|
memory: 256Mi
|
|
|
|
podAnnotations:
|
|
otel.io/path: "/metrics"
|
|
otel.io/scrape: "true"
|
|
otel.io/port: "8888"
|
|
|
|
podLabels:
|
|
bu: "dsgpu"
|
|
team: "sre"
|
|
service: "opentelemetry-dsgpu-prd"
|
|
env: "prd"
|
|
priority: "p0"
|
|
type: "opentelemetry"
|
|
arch: "any"
|
|
runpod: "ondemand"
|
|
|
|
rollout:
|
|
rollingUpdate:
|
|
maxUnavailable: 10% |