gitea_admin/sientia-dataops-laborious_temporal
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
5e883d45302b29a475e82d9dbcfc0b2a39bab9cf
sientia-dataops-laborious_t…/values.yaml
vitor-aignosi 59dd6078b0 SIENTIAPDE-1712 
Update values.yaml to adjust workflow and activity poller configurations for improved performance, increasing minimum, initial, and maximum values. Additionally, add new minimal retrain parameters to enhance retraining capabilities.
2026-03-31 16:21:32 -03:00

316 lines
10 KiB
YAML
Raw Blame History

# Default values for sientia-module.
# This is a YAML-formatted file.
# Declare variables to be passed into your templates.
# This will set the replicaset count more information can be found here: https://kubernetes.io/docs/concepts/workloads/controllers/replicaset/
replicaCount: 1
# This sets the container image more information can be found here: https://kubernetes.io/docs/concepts/containers/images/
image:
repository: aignosi.azurecr.io/sientia-module
# This sets the pull policy for images.
pullPolicy: Always
# Overrides the image tag whose default is the chart appVersion.
tag: "1.1.2"
# This is for the secrets for pulling an image from a private repository more information can be found here: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/
imagePullSecrets:
- name: docker-hub-secret
# This is to override the chart name.
nameOverride: "sientia-laborious-worker"
fullnameOverride: "sientia-laborious-worker"
namespace: sientia
# This section builds out the service account more information can be found here: https://kubernetes.io/docs/concepts/security/service-accounts/
serviceAccount:
# Specifies whether a service account should be created
create: true
# Automatically mount a ServiceAccount's API credentials?
automount: 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: "sientia-laborious-worker"
# This is for setting Kubernetes Annotations to a Pod.
# For more information checkout: https://kubernetes.io/docs/concepts/overview/working-with-objects/annotations/
podAnnotations: {}
# This is for setting Kubernetes Labels to a Pod.
# For more information checkout: https://kubernetes.io/docs/concepts/overview/working-with-objects/labels/
podLabels: {}
podSecurityContext: {}
# fsGroup: 2000
securityContext: {}
# capabilities:
# drop:
# - ALL
# readOnlyRootFilesystem: true
# runAsNonRoot: true
# runAsUser: 1000
resources:
# Resource limits and requests are important for ResourceBasedTuner to work correctly.
# The tuner monitors system CPU and memory usage, so proper resource limits must be set.
limits:
cpu: 2000m # 2 CPU cores
memory: 20Gi # 20 GB memory
requests:
cpu: 1000m # 1 CPU core
memory: 2Gi # 2 GB memory
# This is to setup the liveness and readiness probes more information can be found here: https://kubernetes.io/docs/tasks/configure-pod-container/configure-liveness-readiness-startup-probes/
# This is to setup the liveness and readiness probes more information can be found here: https://kubernetes.io/docs/tasks/configure-pod-container/configure-liveness-readiness-startup-probes/
livenessProbe:
exec:
command:
- sh
- -c
- |
curl -sf http://localhost:9090/metrics | grep -q '^app_up{.*} 1'
initialDelaySeconds: 1260
periodSeconds: 15
timeoutSeconds: 5
failureThreshold: 3
readinessProbe:
exec:
command:
- sh
- -c
- |
curl -sf http://localhost:9090/metrics | grep -q '^app_up{.*} 1'
initialDelaySeconds: 1200
periodSeconds: 10
timeoutSeconds: 3
failureThreshold: 2
# This section is for setting up autoscaling more information can be found here: https://kubernetes.io/docs/concepts/workloads/autoscaling/
autoscaling:
enabled: false
minReplicas: 1
maxReplicas: 100
targetCPUUtilizationPercentage: 80
# targetMemoryUtilizationPercentage: 80
# Additional volumes on the output Deployment definition.
volumes: []
# - name: foo
# secret:
# secretName: mysecret
# optional: false
# Additional volumeMounts on the output Deployment definition.
volumeMounts: []
# - name: foo
# mountPath: "/etc/foo"
# readOnly: true
nodeSelector: {}
tolerations: []
affinity: {}
services:
sdk-metrics:
enabled: true
type: ClusterIP
port: 9091
targetPort: 9091
name: sdk-metrics
metrics:
enabled: true
type: ClusterIP
port: 9090
targetPort: 9090
name: metrics
# Configuração do ServiceMonitor para o Prometheus Operator
# ref: https://github.com/prometheus-operator/prometheus-operator
serviceMonitor:
# Se true, um recurso ServiceMonitor será criado.
enabled: true
# O intervalo no qual as métricas devem ser coletadas (ex: 30s, 1m).
endpoints:
- port: metrics
path: /metrics
interval: 30s
relabelings: []
- port: sdk-metrics
path: /metrics
interval: 30s
relabelings: []
additionalLabels:
release: kube-prometheus-stack
env:
# Entrypoint variables
- name: GITHUB_REPO_URL
value: "git@github.com:Aignosi/sientia-dataops-laborious_temporal.git"
- name: GITHUB_BRANCH
value: "feature/SIENTIAPDE-1712"
- name: PYTHON_APP
value: "laborious.worker.worker"
# Application variables
- name: POSTGRES_HOST
value: "paradedb-rw.paradedb.svc.cluster.local"
- name: POSTGRES_PORT
value: "5432"
- name: POSTGRES_USER
value: "postgres"
- name: POSTGRES_PASSWORD
value: "nFqc81y6kwmr2zuAIx43DhiOosFCVPpeEfTtTWZflkNjB2j1KtEeIANkhFR9mAX3"
- name: POSTGRES_DBNAME
value: "sientia"
- name: POSTGRES_MIN_CONNECTIONS
value: "20"
# max_connections = number_of_workers * max_concurrent_activities * safety_factor
# Example: 4 workers * 50 activities * 0.5 = 100 connections
- name: POSTGRES_MAX_CONNECTIONS
value: "100"
- name: MLFLOW_HOST
value: "http://sientia-tracker-mlflow-tracking.sientia-tracker.svc.cluster.local"
- name: MLFLOW_PORT
value: "80"
- name: MLFLOW_USERNAME
value: "aignosi"
- name: MLFLOW_PASSWORD
value: "1L0FP50j3ncp123"
- name: OPC_ID
value: "1"
- name: OPC_SERVER_NAME
value: "default_server"
- name: OPC_URL
value: "opc.tcp://sientia-opc-simulator-opc.sientia.svc.cluster.local:4840"
- name: LOG_LEVEL
value: "DEBUG"
- name: HTTP_METRICS_PORT
value: "9090"
- name: HTTP_SDK_METRICS_PORT
value: "9091"
- name: PROJECT_NAME
value: "sientia-laborious"
- name: TEMPORAL_HOST
value: "temporal-frontend.temporal.svc.cluster.local:7233"
- name: TEMPORAL_NAMESPACE
value: "laborious"
- name: MONGODB_USERNAME
value: "root"
- name: MONGODB_PASSWORD
value: "wKZDbMNU1c"
- name: MONGODB_URL
value: "my-release-mongodb.mongodb.svc.cluster.local:27017"
- name: MONGODB_DATABASE
value: "sientia"
- name: MONGODB_TTL_INDEX_HOURS
value: "1"
- name: MINIO_ENDPOINT_URL
value: "minio.minio.svc.cluster.local:9000"
- name: MINIO_ACCESS_KEY
value: "admin"
- name: MINIO_SECRET_KEY
value: "LiArt4eNmJ"
- name: MINIO_DEFAULT_BUCKET
value: "sientia"
- name: MINIO_RETENTION_HOURS
value: "24"
- name: SIENTIA_MINIO_OFFLOAD_THRESHOLD_MEGABYTES
value: "0.5"
# Temporal worker tuning for PredictionsBatch.
# IMPORTANT: prefix must be PREDICTIONSBATCH_ (from class name PredictionsBatch).
# Keep workflow-task concurrency moderate to reduce task completion races under load.
- name: PREDICTIONSBATCH_MAX_CONCURRENT_WORKFLOW_TASKS
value: "20"
# Allow higher activity parallelism because most activities are I/O-bound, but keep headroom.
- name: PREDICTIONSBATCH_MAX_CONCURRENT_ACTIVITIES
value: "60"
# Keep local activities controlled so they do not monopolize the event loop.
- name: PREDICTIONSBATCH_MAX_CONCURRENT_LOCAL_ACTIVITIES
value: "20"
# Cache enough workflows for reuse without excessive memory growth.
- name: PREDICTIONSBATCH_MAX_CACHED_WORKFLOWS
value: "200"
# Start with one workflow poller to avoid burst contention at startup.
- name: PREDICTIONSBATCH_WORKFLOW_POLLER_BEHAVIOUR_MINIMUM
value: "3"
# Small initial poller count warms up gradually instead of spiking task fetches.
- name: PREDICTIONSBATCH_WORKFLOW_POLLER_BEHAVIOUR_INITIAL
value: "5"
# Cap workflow pollers to limit scheduling pressure and avoid over-polling.
- name: PREDICTIONSBATCH_WORKFLOW_POLLER_BEHAVIOUR_MAXIMUM
value: "15"
# Keep at least two activity pollers so activity queues do not starve during spikes.
- name: PREDICTIONSBATCH_ACTIVITY_POLLER_BEHAVIOUR_MINIMUM
value: "3"
# Moderate initial activity pollers for faster ramp-up with controlled pressure.
- name: PREDICTIONSBATCH_ACTIVITY_POLLER_BEHAVIOUR_INITIAL
value: "10"
# Limit max activity pollers to preserve CPU for workflow-task completion.
- name: PREDICTIONSBATCH_ACTIVITY_POLLER_BEHAVIOUR_MAXIMUM
value: "30"
- name: MINIMALRETRAIN_MAX_CONCURRENT_ACTIVITIES
value: "1"
- name: MINIMALRETRAIN_MAX_CONCURRENT_LOCAL_ACTIVITIES
value: "1"
- name: MINIMALRETRAIN_MAX_CACHED_WORKFLOWS
value: "1"
- name: MINIMALRETRAIN_WORKFLOW_POLLER_BEHAVIOUR_MINIMUM
value: "1"
- name: MINIMALRETRAIN_WORKFLOW_POLLER_BEHAVIOUR_INITIAL
value: "1"
- name: MINIMALRETRAIN_WORKFLOW_POLLER_BEHAVIOUR_MAXIMUM
value: "1"
- name: MINIMALRETRAIN_ACTIVITY_POLLER_BEHAVIOUR_MINIMUM
value: "1"
- name: MINIMALRETRAIN_ACTIVITY_POLLER_BEHAVIOUR_INITIAL
value: "1"
- name: MINIMALRETRAIN_ACTIVITY_POLLER_BEHAVIOUR_MAXIMUM
value: "1"
- name: PI_WEB_API_BASE_URL
value: "https://pivision.votorantimcimentos.com/piwebapi"
- name: PI_WEB_API_AUTH_TYPE
value: "basic"
- name: PI_WEB_API_AUTH_TOKEN
valueFrom:
secretKeyRef:
name: pi-web-api-auth-token
key: token
- name: PYPI_SERVER
value: "http://library-distribution-server.library.svc.cluster.local:5000"
ssh:
enabled: true
secretName: git-ssh-key-sientia-laborious-worker
sshPath: /mnt/.ssh
knownHostsPath: /mnt/known_hosts
# kubectl create secret docker-registry docker-hub-secret --namespace sientia --docker-server=http://aignosi.azurecr.io --docker-username=aignosi --docker-password=5I5zpQ6sRaHqX1hD3dr+2mo647yO3FRc359/wu6gsP+ACRDRz5mp
# helm upgrade --install sientia-laborious-worker sientia/sientia-module -n sientia --create-namespace -f ./values.yaml --version 0.6.0
# kubectl create secret generic git-ssh-key-sientia-laborious-worker \
# --namespace sientia \
# --from-file=ssh-privatekey=git_key \
# --type=kubernetes.io/ssh-auth
Reference in New Issue View Git Blame Copy Permalink