#
# Licensed to the Apache Software Foundation (ASF) under one or more
# contributor license agreements.  See the NOTICE file distributed with
# this work for additional information regarding copyright ownership.
# The ASF licenses this file to You under the Apache License, Version 2.0
# (the "License"); you may not use this file except in compliance with
# the License.  You may obtain a copy of the License at
#
#    http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#

# Default values for celeborn.
# This is a YAML-formatted file.
# Declare variables to be passed into your templates.

# we provide a default celeborn image, you can also replace to your image
# TODO rebuild celeborn official image
image:
  repository: public.ecr.aws/myang-poc/celeborn-rss
  pullPolicy: Always
  tag: spark3.2_server0.2

nodeSelector: 
  app: css

# master replicas should not less than 3
masterReplicas: 3
# worker replicas set on demand, should less than node number
workerReplicas: 3

securityContext:
  # celeborn user created in docker
  fsGroup: 10006
# configure the shuffle service volume owner as Celeborn user
volumeUser: 10006
volumeGroup: 10006
# celeborn configurations
celeborn:
  # celeborn.ha.enabled: true
  # celeborn.master.endpoints: celeborn-master-0.celeborn-master-svc.celeborn:9097,celeborn-master-1.celeborn-master-svc.celeborn:9097,celeborn-master-2.celeborn-master-svc.celeborn:9097
  celeborn.ha.master.ratis.raft.server.storage.dir: /rss1/rss_ratis/
  celeborn.worker.storage.dirs: /rss1/data,/rss2/data
  celeborn.volumes.hostpath: /local1,/local2
  celeborn.metrics.enabled: true
  celeborn.master.metrics.prometheus.port: 9098
  celeborn.worker.metrics.prometheus.port: 9096
  celeborn.worker.monitor.disk.enabled: false

  celeborn.push.io.numConnectionsPerPeer: 8
  celeborn.replicate.io.numConnectionsPerPeer: 24
  celeborn.worker.flusher.buffer.size: 128k
  celeborn.worker.flusher.threads: 64
  celeborn.worker.fetch.io.threads: 256                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      
  celeborn.worker.push.io.threads: 128
  # celeborn.master.heartbeat.application.timeout: 300s
  # celeborn.master.heartbeat.worker.timeout: 120s
  celeborn.network.timeout: 2000s
  celeborn.worker.replicate.io.threads: 128
  celeborn.worker.commit.threads: 128
  celeborn.worker.closeIdleConnections: true

environments:
  CELEBORN_MASTER_MEMORY: 16g
  CELEBORN_MASTER_JAVA_OPTS: "-XX:-PrintGC -XX:+PrintGCDetails -XX:+PrintGCTimeStamps -XX:+PrintGCDateStamps -Xloggc:gc-master.out -Dio.netty.leakDetectionLevel=advanced"
  CELEBORN_WORKER_MEMORY: 8g
  CELEBORN_WORKER_OFFHEAP_MEMORY: 20g
  CELEBORN_WORKER_JAVA_OPTS: "-XX:-PrintGC -XX:+PrintGCDetails -XX:+PrintGCTimeStamps -XX:+PrintGCDateStamps -Xloggc:gc-worker.out -Dio.netty.leakDetectionLevel=advanced"
  CELEBORN_NO_DAEMONIZE: 1
  TZ: "Australia/Melbourne"

podMonitor:
  enable: true
  podMetricsEndpoint:
    scheme: http
    interval: 5s
    portName: metrics

service:
  type: ClusterIP
  port: 9097

cluster:
  name: cluster

configmap: celeborn-conf

# resources:
resources: {}
  # We usually recommend not to specify default resources and to leave this as a conscious
  # choice for the user. This also increases chances charts run on environments with little
  # resources, such as Minikube. If you do want to specify resources, uncomment the following
  # lines, adjust them as necessary, and remove the curly braces after 'resources:'.
  # master:
  #  limits:
  #    cpu: 100m
  #    memory: 128Mi
  #  requests:
  #    cpu: 100m
  #    memory: 128Mi
  # worker:
  #  limits: #i3en.6xl
  #    cpu: 24
  #    memory: 192G
  #  requests:
  #    cpu: 21.6
  #    memory: 176G

podAnnotations: {}

affinity:
  master:
    podAntiAffinity:
      requiredDuringSchedulingIgnoredDuringExecution:
        - labelSelector:
            matchExpressions:
              - key: app.kubernetes.io/name
                operator: In
                values:
                  - celeborn
              - key: app.kubernetes.io/role
                operator: In
                values:
                  - master
          topologyKey: kubernetes.io/hostname
  worker:
    podAntiAffinity:
      requiredDuringSchedulingIgnoredDuringExecution:
        - labelSelector:
            matchExpressions:
              - key: app.kubernetes.io/name
                operator: In
                values:
                  - celeborn
              - key: app.kubernetes.io/role
                operator: In
                values:
                  - worker
          topologyKey: "kubernetes.io/hostname"

tolerations: []