Files
devops-infra-helm-charts-gcp/helm-overrides/k8s-admin-prd-ase1/opentelemetry-deployment/custom-values.yaml
T
2026-08-26 03:39:42 +05:30

111 lines
2.7 KiB
YAML

config:
receivers:
otlp:
protocols:
grpc:
endpoint: ${env:MY_POD_IP}:4317
max_recv_msg_size_mib: 50
processors:
batch:
send_batch_size: 256
timeout: 200ms
send_batch_max_size: 512
filter/drop-noisy-services:
error_mode: ignore
traces:
span:
- IsMatch(resource.attributes["service.name"], ".*consumer.*|.*scheduler.*|.*cron.*|.*worker.*|.*inhouse-ingestion.*|.*.messaging-api-internal*|.*cis.*")
tail_sampling:
decision_wait: 10s # avg latency across services
num_traces: 25000000 # expected_new_traces_per_sec * decision_wait + some buffer
expected_new_traces_per_sec: 1500000 # combined span rate across all business units
decision_cache:
sampled_cache_size: 6000000 # sampling rate * num_traces + some buffer
policies:
[
{
name: errors-policy,
type: status_code,
status_code: {status_codes: [ERROR]}
},
# {
# name: latency-policy,
# type: latency,
# latency: {threshold_ms: 1000}
# },
{
name: probablistic-policy,
type: probabilistic,
probabilistic: {sampling_percentage: 1}
}
]
exporters:
otlp/elastic:
endpoint: "946ece6f7b344005aa1e5c273b1a886f.apm.psc.asia-southeast1.gcp.elastic-cloud.com:443"
timeout: 15s
sending_queue:
num_consumers: 50
queue_size: 10000
headers:
Authorization: "Bearer ehllv9fQQ7GGMOjE79"
service:
telemetry:
metrics:
level: detailed
readers:
- pull:
exporter:
prometheus:
host: '0.0.0.0'
port: 8888
extensions:
- health_check
pipelines:
traces:
receivers: [otlp]
processors: [filter/drop-noisy-services, tail_sampling, batch]
exporters: [otlp/elastic]
metrics: null
logs: null
fullnameOverride: "opentelemetry-admin-prd"
mode: "deployment"
podAnnotations:
otel.io/path: '/metrics'
otel.io/port: '8888'
otel.io/scrape: 'true'
image:
repository: asia-southeast1-docker.pkg.dev/meesho-devops-admin-0622/admin/sre/opentelemetry-collector-contrib
pullPolicy: IfNotPresent
tag: "0.114.0"
nodeSelector:
dedicated: "opentelemetry-std"
tolerations:
- key: "dedicated"
operator: "Equal"
value: "opentelemetry-std"
effect: "NoSchedule"
resources:
requests:
cpu: '45'
memory: 175Gi
limits:
cpu: '45'
memory: 175Gi
autoscaling:
enabled: true
minReplicas: 15
maxReplicas: 50
targetCPUUtilizationPercentage: 75
targetMemoryUtilizationPercentage: 75