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

292 lines
15 KiB
YAML

replicaCount: 3
image:
repository: quay.io/influxdb/telegraf-operator
pullPolicy: IfNotPresent
sidecarImage: "asia-southeast1-docker.pkg.dev/meesho-devops-admin-0622/admin/sre/telegraf:1.24.4"
dedicatedValue: false
schedulerName: default-scheduler
classes:
secretName: "telegraf-operator-classes"
default: "infra"
data:
infra: |
[[inputs.mem]]
[[outputs.file]]
files = ["stdout"]
[[outputs.prometheus_client]]
listen = ":9273"
metric_version = 2
path = "/metrics"
expiration_interval = "60s"
export_timestamp = false
[agent]
interval = "10s"
round_interval = true
metric_batch_size = 1000
metric_buffer_limit = 40000
collection_jitter = "0s"
flush_interval = "30s"
flush_jitter = "0s"
precision = ""
debug = true
hostname = ""
omit_hostname = true
[[aggregators.basicstats]]
period = "60s"
grace = "10s"
delay = "30s"
drop_original = false
stats = ["count", "min", "max", "mean", "sum"]
[[aggregators.histogram]]
period = "60s"
grace = "10s"
delay = "30s"
drop_original = false
[[aggregators.histogram.config]]
buckets = [5.0, 10.0, 20.0, 30.0, 40.0, 50.0, 60.0, 80.0, 100.0, 120.0, 150.0, 175.0, 200.0, 225.0, 250.0, 275.0, 300.0, 350.0, 400.0, 450.0, 500.0, 600.0, 700.0, 800.0, 900.0, 1000.0, 1200.0, 1500.0, 2000.0, 5000.0, 10000.0, 12500.0, 15000.0, 20000.0, 25000.0, 30000.0]
measurement_name = "CONTROLLER"
[[aggregators.histogram.config]]
buckets = [5.0, 10.0, 20.0, 30.0, 40.0, 50.0, 60.0, 80.0, 100.0, 120.0, 150.0, 175.0, 200.0, 225.0, 250.0, 275.0, 300.0, 350.0, 400.0, 450.0, 500.0, 600.0, 700.0, 800.0, 900.0, 1000.0, 1200.0, 1500.0, 2000.0, 5000.0, 10000.0, 12500.0, 15000.0, 20000.0, 25000.0, 30000.0]
measurement_name = "RDS"
[[aggregators.histogram.config]]
buckets = [1.0, 2.0, 3.0, 4.0, 5.0, 10.0, 20.0, 30.0, 40.0, 50.0, 60.0, 80.0, 100.0, 120.0, 150.0, 175.0, 200.0, 225.0, 250.0, 275.0, 300.0, 350.0, 400.0, 450.0, 500.0, 600.0, 700.0, 800.0, 900.0, 1000.0, 1200.0, 1500.0, 2000.0, 5000.0, 10000.0, 12500.0, 15000.0, 20000.0, 25000.0, 30000.0]
measurement_name = "REDIS"
[[aggregators.histogram.config]]
buckets = [0.0, 5.0, 10.0, 20.0, 30.0, 40.0, 50.0, 60.0, 80.0, 100.0, 120.0, 150.0, 175.0, 200.0, 225.0, 250.0, 275.0, 300.0, 350.0, 400.0, 450.0, 500.0, 600.0, 700.0, 800.0, 900.0,1000.0, 1200.0, 1500.0, 2000.0, 5000.0, 10000.0, 12500.0, 15000.0, 20000.0, 25000.0, 30000.0]
measurement_name = "HBASE"
[[aggregators.histogram.config]]
buckets = [0.0, 5.0, 10.0, 20.0, 30.0, 40.0, 50.0, 60.0, 80.0, 100.0, 120.0, 150.0, 175.0, 200.0, 225.0, 250.0, 275.0, 300.0, 350.0, 400.0, 450.0, 500.0, 600.0, 700.0, 800.0, 900.0,1000.0, 1200.0, 1500.0, 2000.0, 5000.0, 10000.0, 12500.0, 15000.0, 20000.0, 25000.0, 30000.0]
measurement_name = "HTTP"
[[aggregators.histogram.config]]
buckets = [0.0, 5.0, 10.0, 20.0, 30.0, 40.0, 50.0, 60.0, 80.0, 100.0, 120.0, 150.0, 175.0, 200.0, 225.0, 250.0, 275.0, 300.0, 350.0, 400.0, 450.0, 500.0, 600.0, 700.0, 800.0, 900.0,1000.0, 1200.0, 1500.0, 2000.0, 5000.0, 10000.0, 12500.0, 15000.0, 20000.0, 25000.0, 30000.0]
measurement_name = "METHOD"
[[aggregators.histogram.config]]
buckets = [0.0, 5.0, 10.0, 20.0, 30.0, 40.0, 50.0, 60.0, 80.0, 100.0, 120.0, 150.0, 175.0, 200.0, 225.0, 250.0, 275.0, 300.0, 350.0, 400.0, 450.0, 500.0, 600.0, 700.0, 800.0, 900.0,1000.0, 1200.0, 1500.0, 2000.0, 5000.0, 10000.0, 12500.0, 15000.0, 20000.0, 25000.0, 30000.0]
measurement_name = "QUERY_EXECUTION_LATENCY"
[[aggregators.histogram.config]]
buckets = [0.0, 5.0, 10.0, 20.0, 30.0, 40.0, 50.0, 60.0, 80.0, 100.0, 120.0, 150.0, 175.0, 200.0, 225.0, 250.0, 275.0, 300.0, 350.0, 400.0, 450.0, 500.0, 600.0, 700.0, 800.0, 900.0,1000.0, 1200.0, 1500.0, 2000.0, 5000.0, 10000.0, 12500.0, 15000.0, 20000.0, 25000.0, 30000.0]
measurement_name = "DOWN_STREAM_LATENCY"
[[aggregators.histogram.config]]
buckets = [0.0, 5.0, 10.0, 20.0, 30.0, 40.0, 50.0, 60.0, 80.0, 100.0, 120.0, 150.0, 175.0, 200.0, 225.0, 250.0, 275.0, 300.0, 350.0, 400.0, 450.0, 500.0, 600.0, 700.0, 800.0, 900.0,1000.0, 1200.0, 1500.0, 2000.0, 5000.0, 10000.0, 12500.0, 15000.0, 20000.0, 25000.0, 30000.0]
measurement_name = "API_LATENCY"
[[inputs.socket_listener]]
service_address = "udp://:8094"
read_buffer_size = "16MB"
[[inputs.statsd]]
protocol = "udp"
service_address = ":8125"
delete_gauges = false
delete_counters = false
percentiles = [50.0, 90.0, 99.0, 99.9, 99.95, 100.0]
datadog_extensions = true
allowed_pending_messages = 100000
infra-histogram-expiration-enabled: |
[[inputs.mem]]
[[outputs.file]]
files = ["stdout"]
[[outputs.prometheus_client]]
listen = ":9273"
metric_version = 2
path = "/metrics"
expiration_interval = "60s"
export_timestamp = false
[agent]
interval = "10s"
round_interval = true
metric_batch_size = 1000
metric_buffer_limit = 40000
collection_jitter = "0s"
flush_interval = "30s"
flush_jitter = "0s"
precision = ""
debug = true
hostname = ""
omit_hostname = true
[[aggregators.basicstats]]
period = "60s"
grace = "10s"
delay = "30s"
drop_original = false
stats = ["count", "min", "max", "mean", "sum"]
[[aggregators.histogram]]
period = "60s"
grace = "10s"
delay = "30s"
drop_original = false
expiration_interval = "2m"
[[aggregators.histogram.config]]
buckets = [5.0, 10.0, 20.0, 30.0, 40.0, 50.0, 60.0, 80.0, 100.0, 120.0, 150.0, 175.0, 200.0, 225.0, 250.0, 275.0, 300.0, 350.0, 400.0, 450.0, 500.0, 600.0, 700.0, 800.0, 900.0, 1000.0, 1200.0, 1500.0, 2000.0, 5000.0, 10000.0, 12500.0, 15000.0, 20000.0, 25000.0, 30000.0]
measurement_name = "CONTROLLER"
[[aggregators.histogram.config]]
buckets = [5.0, 10.0, 20.0, 30.0, 40.0, 50.0, 60.0, 80.0, 100.0, 120.0, 150.0, 175.0, 200.0, 225.0, 250.0, 275.0, 300.0, 350.0, 400.0, 450.0, 500.0, 600.0, 700.0, 800.0, 900.0, 1000.0, 1200.0, 1500.0, 2000.0, 5000.0, 10000.0, 12500.0, 15000.0, 20000.0, 25000.0, 30000.0]
measurement_name = "RDS"
[[aggregators.histogram.config]]
buckets = [1.0, 2.0, 3.0, 4.0, 5.0, 10.0, 20.0, 30.0, 40.0, 50.0, 60.0, 80.0, 100.0, 120.0, 150.0, 175.0, 200.0, 225.0, 250.0, 275.0, 300.0, 350.0, 400.0, 450.0, 500.0, 600.0, 700.0, 800.0, 900.0, 1000.0, 1200.0, 1500.0, 2000.0, 5000.0, 10000.0, 12500.0, 15000.0, 20000.0, 25000.0, 30000.0]
measurement_name = "REDIS"
[[aggregators.histogram.config]]
buckets = [0.0, 5.0, 10.0, 20.0, 30.0, 40.0, 50.0, 60.0, 80.0, 100.0, 120.0, 150.0, 175.0, 200.0, 225.0, 250.0, 275.0, 300.0, 350.0, 400.0, 450.0, 500.0, 600.0, 700.0, 800.0, 900.0,1000.0, 1200.0, 1500.0, 2000.0, 5000.0, 10000.0, 12500.0, 15000.0, 20000.0, 25000.0, 30000.0]
measurement_name = "HBASE"
[[aggregators.histogram.config]]
buckets = [0.0, 5.0, 10.0, 20.0, 30.0, 40.0, 50.0, 60.0, 80.0, 100.0, 120.0, 150.0, 175.0, 200.0, 225.0, 250.0, 275.0, 300.0, 350.0, 400.0, 450.0, 500.0, 600.0, 700.0, 800.0, 900.0,1000.0, 1200.0, 1500.0, 2000.0, 5000.0, 10000.0, 12500.0, 15000.0, 20000.0, 25000.0, 30000.0]
measurement_name = "HTTP"
[[aggregators.histogram.config]]
buckets = [0.0, 5.0, 10.0, 20.0, 30.0, 40.0, 50.0, 60.0, 80.0, 100.0, 120.0, 150.0, 175.0, 200.0, 225.0, 250.0, 275.0, 300.0, 350.0, 400.0, 450.0, 500.0, 600.0, 700.0, 800.0, 900.0,1000.0, 1200.0, 1500.0, 2000.0, 5000.0, 10000.0, 12500.0, 15000.0, 20000.0, 25000.0, 30000.0]
measurement_name = "METHOD"
[[aggregators.histogram.config]]
buckets = [0.0, 5.0, 10.0, 20.0, 30.0, 40.0, 50.0, 60.0, 80.0, 100.0, 120.0, 150.0, 175.0, 200.0, 225.0, 250.0, 275.0, 300.0, 350.0, 400.0, 450.0, 500.0, 600.0, 700.0, 800.0, 900.0,1000.0, 1200.0, 1500.0, 2000.0, 5000.0, 10000.0, 12500.0, 15000.0, 20000.0, 25000.0, 30000.0]
measurement_name = "QUERY_EXECUTION_LATENCY"
[[aggregators.histogram.config]]
buckets = [0.0, 5.0, 10.0, 20.0, 30.0, 40.0, 50.0, 60.0, 80.0, 100.0, 120.0, 150.0, 175.0, 200.0, 225.0, 250.0, 275.0, 300.0, 350.0, 400.0, 450.0, 500.0, 600.0, 700.0, 800.0, 900.0,1000.0, 1200.0, 1500.0, 2000.0, 5000.0, 10000.0, 12500.0, 15000.0, 20000.0, 25000.0, 30000.0]
measurement_name = "DOWN_STREAM_LATENCY"
[[aggregators.histogram.config]]
buckets = [0.0, 5.0, 10.0, 20.0, 30.0, 40.0, 50.0, 60.0, 80.0, 100.0, 120.0, 150.0, 175.0, 200.0, 225.0, 250.0, 275.0, 300.0, 350.0, 400.0, 450.0, 500.0, 600.0, 700.0, 800.0, 900.0,1000.0, 1200.0, 1500.0, 2000.0, 5000.0, 10000.0, 12500.0, 15000.0, 20000.0, 25000.0, 30000.0]
measurement_name = "API_LATENCY"
[[inputs.socket_listener]]
service_address = "udp://:8094"
read_buffer_size = "16MB"
[[inputs.statsd]]
protocol = "udp"
service_address = ":8125"
delete_gauges = false
delete_counters = false
percentiles = [50.0, 90.0, 99.0, 99.9, 99.95, 100.0]
datadog_extensions = true
allowed_pending_messages = 100000
infra-telegraf-cardinality-optimized: |
[[inputs.mem]]
[[outputs.file]]
files = ["stdout"]
[[outputs.prometheus_client]]
listen = ":9273"
metric_version = 2
path = "/metrics"
expiration_interval = "60s"
export_timestamp = false
[agent]
interval = "10s"
round_interval = true
metric_batch_size = 1000
metric_buffer_limit = 40000
collection_jitter = "0s"
flush_interval = "30s"
flush_jitter = "0s"
precision = ""
debug = true
hostname = ""
omit_hostname = true
[[aggregators.histogram]]
period = "60s"
grace = "10s"
delay = "30s"
drop_original = false
expiration_interval = "2m"
[[aggregators.histogram.config]]
buckets = [5.0, 10.0, 20.0, 30.0, 40.0, 50.0, 60.0, 80.0, 100.0, 120.0, 150.0, 175.0, 200.0, 225.0, 250.0, 275.0, 300.0, 350.0, 400.0, 450.0, 500.0, 600.0, 700.0, 800.0, 900.0, 1000.0, 1200.0, 1500.0, 2000.0, 5000.0, 10000.0, 12500.0, 15000.0, 20000.0, 25000.0, 30000.0]
measurement_name = "CONTROLLER"
[[aggregators.histogram.config]]
buckets = [5.0, 10.0, 20.0, 30.0, 40.0, 50.0, 60.0, 80.0, 100.0, 120.0, 150.0, 175.0, 200.0, 225.0, 250.0, 275.0, 300.0, 350.0, 400.0, 450.0, 500.0, 600.0, 700.0, 800.0, 900.0, 1000.0, 1200.0, 1500.0, 2000.0, 5000.0, 10000.0, 12500.0, 15000.0, 20000.0, 25000.0, 30000.0]
measurement_name = "RDS"
[[aggregators.histogram.config]]
buckets = [1.0, 2.0, 3.0, 4.0, 5.0, 10.0, 20.0, 30.0, 40.0, 50.0, 60.0, 80.0, 100.0, 120.0, 150.0, 175.0, 200.0, 225.0, 250.0, 275.0, 300.0, 350.0, 400.0, 450.0, 500.0, 600.0, 700.0, 800.0, 900.0, 1000.0, 1200.0, 1500.0, 2000.0, 5000.0, 10000.0, 12500.0, 15000.0, 20000.0, 25000.0, 30000.0]
measurement_name = "REDIS"
[[aggregators.histogram.config]]
buckets = [0.0, 5.0, 10.0, 20.0, 30.0, 40.0, 50.0, 60.0, 80.0, 100.0, 120.0, 150.0, 175.0, 200.0, 225.0, 250.0, 275.0, 300.0, 350.0, 400.0, 450.0, 500.0, 600.0, 700.0, 800.0, 900.0,1000.0, 1200.0, 1500.0, 2000.0, 5000.0, 10000.0, 12500.0, 15000.0, 20000.0, 25000.0, 30000.0]
measurement_name = "HBASE"
[[aggregators.histogram.config]]
buckets = [0.0, 5.0, 10.0, 20.0, 30.0, 40.0, 50.0, 60.0, 80.0, 100.0, 120.0, 150.0, 175.0, 200.0, 225.0, 250.0, 275.0, 300.0, 350.0, 400.0, 450.0, 500.0, 600.0, 700.0, 800.0, 900.0,1000.0, 1200.0, 1500.0, 2000.0, 5000.0, 10000.0, 12500.0, 15000.0, 20000.0, 25000.0, 30000.0]
measurement_name = "HTTP"
[[aggregators.histogram.config]]
buckets = [0.0, 5.0, 10.0, 20.0, 30.0, 40.0, 50.0, 60.0, 80.0, 100.0, 120.0, 150.0, 175.0, 200.0, 225.0, 250.0, 275.0, 300.0, 350.0, 400.0, 450.0, 500.0, 600.0, 700.0, 800.0, 900.0,1000.0, 1200.0, 1500.0, 2000.0, 5000.0, 10000.0, 12500.0, 15000.0, 20000.0, 25000.0, 30000.0]
measurement_name = "METHOD"
[[aggregators.histogram.config]]
buckets = [0.0, 5.0, 10.0, 20.0, 30.0, 40.0, 50.0, 60.0, 80.0, 100.0, 120.0, 150.0, 175.0, 200.0, 225.0, 250.0, 275.0, 300.0, 350.0, 400.0, 450.0, 500.0, 600.0, 700.0, 800.0, 900.0,1000.0, 1200.0, 1500.0, 2000.0, 5000.0, 10000.0, 12500.0, 15000.0, 20000.0, 25000.0, 30000.0]
measurement_name = "QUERY_EXECUTION_LATENCY"
[[aggregators.histogram.config]]
buckets = [0.0, 5.0, 10.0, 20.0, 30.0, 40.0, 50.0, 60.0, 80.0, 100.0, 120.0, 150.0, 175.0, 200.0, 225.0, 250.0, 275.0, 300.0, 350.0, 400.0, 450.0, 500.0, 600.0, 700.0, 800.0, 900.0,1000.0, 1200.0, 1500.0, 2000.0, 5000.0, 10000.0, 12500.0, 15000.0, 20000.0, 25000.0, 30000.0]
measurement_name = "DOWN_STREAM_LATENCY"
[[aggregators.histogram.config]]
buckets = [0.0, 5.0, 10.0, 20.0, 30.0, 40.0, 50.0, 60.0, 80.0, 100.0, 120.0, 150.0, 175.0, 200.0, 225.0, 250.0, 275.0, 300.0, 350.0, 400.0, 450.0, 500.0, 600.0, 700.0, 800.0, 900.0,1000.0, 1200.0, 1500.0, 2000.0, 5000.0, 10000.0, 12500.0, 15000.0, 20000.0, 25000.0, 30000.0]
measurement_name = "API_LATENCY"
[[inputs.socket_listener]]
service_address = "udp://:8094"
read_buffer_size = "16MB"
[[inputs.statsd]]
protocol = "udp"
service_address = ":8125"
delete_gauges = false
delete_counters = false
percentiles = [50.0, 90.0, 99.0, 99.9, 99.95]
datadog_extensions = true
allowed_pending_messages = 100000
certManager:
enable: false
imagePullSecrets: []
nameOverride: ""
fullnameOverride: ""
serviceAccount:
# Annotations to add to the service account
annotations: {}
podSecurityContext: {}
# fsGroup: 2000
securityContext: {}
# capabilities:
# drop:
# - ALL
# readOnlyRootFilesystem: true
# runAsNonRoot: true
# runAsUser: 1000
resources:
limits:
cpu: 200m
memory: 256Mi
requests:
cpu: 50m
memory: 64Mi
sidecarResources:
requests:
cpu: 200m
memory: 200Mi
topologySpreadConstraints:
- maxSkew: 1
topologyKey: topology.kubernetes.io/zone
whenUnsatisfiable: ScheduleAnyway
labelSelector:
matchLabels:
type: exporter
- maxSkew: 1
topologyKey: kubernetes.io/hostname
whenUnsatisfiable: DoNotSchedule
labelSelector:
matchLabels:
type: exporter
labels:
bu: "demand"
team: "demand-sre"
service: "telegraf-operator-demand-prd"
env: "prd"
priority: "p0"
type: "exporter"
nodeSelector:
dedicated: "vmselect-mds"
tolerations:
- key: "dedicated"
operator: "Equal"
value: "vmselect-mds"
effect: "NoSchedule"
affinity: {}
requireAnnotationsForSecret: false
# allow hot reload ; disabled by default to support versions of telegraf
# that do not support hot-reload and --watch-config flag
hotReload: false