The PriorityClasses exist in the repository but no pod uses them, so every platform pod still evicts at priority 0. Attach platform-critical to Keycloak (CR spec.scheduling) and Gitea (chart priorityClassName), and platform-low to Loki (singleBinary) and Tempo. The Keycloak CR also gets spec.image at the running 26.7.0 digest with startOptimized: false: with spec.image the operator otherwise assumes a pre-built optimized image, and this is the stock one. Grafana and pgAdmin have no top-level priorityClassName in their charts and are left for later; platform-postgres is W1's file and tech-log belongs to its deploy/ directory. Risk: applying restarts Keycloak, Gitea, Loki and Tempo once, so it belongs in the k3s restart window, after the PriorityClasses exist (a pod that names a missing class is rejected). The accepted-drift list holds these objects until 2026-11-30. Verification (desktop): render-phase1/2 and render-observability-core pass with the four priorityClassName values; kubectl diff (server dry-run) against live shows only these fields.
129 lines
2.7 KiB
YAML
129 lines
2.7 KiB
YAML
global:
|
|
commonLabels:
|
|
observability.hyeonworks.com/instance: home
|
|
|
|
replicas: 1
|
|
|
|
# services/priority-classes: traces can be lost first under node pressure.
|
|
priorityClassName: platform-low
|
|
|
|
config: |
|
|
stream_over_http_enabled: false
|
|
memberlist:
|
|
cluster_label: "{{ .Release.Name }}.{{ .Release.Namespace }}"
|
|
multitenancy_enabled: false
|
|
usage_report:
|
|
reporting_enabled: false
|
|
compactor:
|
|
compaction:
|
|
block_retention: 168h
|
|
distributor:
|
|
receivers:
|
|
otlp:
|
|
protocols:
|
|
grpc:
|
|
endpoint: 0.0.0.0:4317
|
|
ingester:
|
|
trace_idle_period: 10s
|
|
max_block_duration: 5m
|
|
max_block_bytes: 100000000
|
|
complete_block_timeout: 15m
|
|
flush_all_on_shutdown: true
|
|
server:
|
|
http_listen_port: 3200
|
|
storage:
|
|
trace:
|
|
backend: s3
|
|
s3:
|
|
bucket: tempo
|
|
endpoint: minio.object-storage.svc.cluster.local:80
|
|
insecure: true
|
|
forcepathstyle: true
|
|
access_key: ${AWS_ACCESS_KEY_ID}
|
|
secret_key: ${AWS_SECRET_ACCESS_KEY}
|
|
wal:
|
|
path: /var/tempo/wal
|
|
querier: {}
|
|
query_frontend: {}
|
|
overrides:
|
|
defaults:
|
|
ingestion:
|
|
rate_limit_bytes: 5000000
|
|
burst_size_bytes: 10000000
|
|
max_traces_per_user: 5000
|
|
global:
|
|
max_bytes_per_trace: 5000000
|
|
|
|
tempo:
|
|
registry: docker.io
|
|
repository: grafana/tempo
|
|
tag: 2.10.7
|
|
resources:
|
|
requests:
|
|
cpu: 250m
|
|
memory: 512Mi
|
|
limits:
|
|
cpu: "1"
|
|
memory: 1Gi
|
|
memBallastSizeMbs: 0
|
|
reportingEnabled: false
|
|
metricsGenerator:
|
|
enabled: false
|
|
extraArgs:
|
|
config.expand-env: true
|
|
extraEnv:
|
|
- name: AWS_ACCESS_KEY_ID
|
|
valueFrom:
|
|
secretKeyRef:
|
|
name: tempo-object-storage
|
|
key: access-key-id
|
|
- name: AWS_SECRET_ACCESS_KEY
|
|
valueFrom:
|
|
secretKeyRef:
|
|
name: tempo-object-storage
|
|
key: secret-access-key
|
|
securityContext:
|
|
runAsNonRoot: true
|
|
allowPrivilegeEscalation: false
|
|
readOnlyRootFilesystem: true
|
|
capabilities:
|
|
drop:
|
|
- ALL
|
|
seccompProfile:
|
|
type: RuntimeDefault
|
|
|
|
tempoQuery:
|
|
enabled: false
|
|
|
|
securityContext:
|
|
runAsUser: 10001
|
|
runAsGroup: 10001
|
|
runAsNonRoot: true
|
|
fsGroup: 10001
|
|
fsGroupChangePolicy: OnRootMismatch
|
|
seccompProfile:
|
|
type: RuntimeDefault
|
|
|
|
serviceAccount:
|
|
automountServiceAccountToken: false
|
|
|
|
service:
|
|
type: ClusterIP
|
|
|
|
serviceMonitor:
|
|
enabled: true
|
|
interval: 30s
|
|
additionalLabels:
|
|
observability.hyeonworks.com/instance: home
|
|
|
|
persistence:
|
|
enabled: true
|
|
enableStatefulSetAutoDeletePVC: false
|
|
storageClassName: ssd-local-observability-tempo-retain
|
|
accessModes:
|
|
- ReadWriteOnce
|
|
size: 5Gi
|
|
|
|
podLabels:
|
|
platform.hyeonworks.com/aistor-client: "true"
|