#
# 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
#
#
# 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.
#
#==============================================================================
# Common
#==============================================================================
# The external address of the host on which the JobManager runs and can be
# reached by the TaskManagers and any clients which want to connect. This setting
# is only used in Standalone mode and may be overwritten on the JobManager side
# by specifying the --host <hostname> parameter of the bin/jobmanager.sh executable.
# In high availability mode, if you use the bin/start-cluster.sh script and setup
# the conf/masters file, this will be taken care of automatically. Yarn
# automatically configure the host name based on the hostname of the node where the
# JobManager runs.
jobmanager.rpc.address: hadoop150
# The RPC port where the JobManager is reachable.
jobmanager.rpc.port: 6123
# The total process memory size for the JobManager.
#
jobmanager.memory.process.size: 2048m
# The total process memory size for the TaskManager.
#
taskmanager.memory.process.size: 6g
# To exclude JVM metaspace and overhead, please, use total Flink memory size instead of 'taskmanager.memory.process.size'.
# It is not recommended to set both 'taskmanager.memory.process.size' and Flink memory.
#
# The number of task slots that each TaskManager offers. Each slot runs one parallel pipeline.
taskmanager.numberOfTaskSlots: 15
# The parallelism used for programs that did not specify and other parallelism.
parallelism.default: 1
# The default file system scheme and authority.
#
# root file system 'file:///'. Use this to override the default and interpret
# relative paths relative to a different file system,
# for example 'hdfs://mynamenode:12345'
#
#==============================================================================
# High Availability
#==============================================================================
# The high-availability mode. Possible options are 'NONE' or 'zookeeper'.
#
high-availability: zookeeper
high-availability.storageDir: hdfs:///flinkwb/flink14-ha/
high-availability.zookeeper.quorum: hadoop150:2181,hadoop151:2181,hadoop152:2181
high-availability.zookeeper.path.root: /data/flinkha/ha14
# The path where metadata for master recovery is persisted. While ZooKeeper stores
# the small ground truth for checkpoint and leader election, this location stores
# the larger objects, like persisted dataflow graphs.
#
# (like HDFS, S3, Ceph, nfs, ...)
#
# The list of ZooKeeper quorum peers that coordinate the high-availability
# setup. This must be a list of the form:
# "host1:clientPort,host2:clientPort,..." (default clientPort: 2181)
#
# ACL options are based on https://zookeeper.apache.org/doc/r3.1.2/zookeeperProgrammers.html
# It can be either "creator" (ZOO_CREATE_ALL_ACL) or "open" (ZOO_OPEN_ACL_UNSAFE)
# The default value is "open" and it can be changed to "creator" if ZK security is enabled
#
#==============================================================================
# Fault tolerance and checkpointing
#==============================================================================
# The backend that will be used to store operator state checkpoints if
# checkpointing is enabled. Checkpointing is enabled when execution.checkpointing.interval > 0.
#
#
# execution.checkpointing.externalized-checkpoint-retention: [DELETE_ON_CANCELLATION, RETAIN_ON_CANCELLATION]
# execution.checkpointing.max-concurrent-checkpoints: 1
# execution.checkpointing.min-pause: 0
# execution.checkpointing.mode: [EXACTLY_ONCE, AT_LEAST_ONCE]
# execution.checkpointing.timeout: 10min
# execution.checkpointing.tolerable-failed-checkpoints: 0
# execution.checkpointing.unaligned: false
#
# <class-name-of-factory>.
#
state.backend: rocksdb
state.checkpoints.dir: hdfs:///flinkwb/flink14-cp
state.savepoints.dir: hdfs:///flinkwb/flink14-sp
# Directory for checkpoints filesystem, when using any of the default bundled
# state backends.
#
# Default target directory for savepoints, optional.
#
# Flag to enable/disable incremental checkpoints for backends that
# support incremental checkpoints (like the RocksDB state backend).
#
state.backend.incremental: true
# The failover strategy, i.e., how the job computation recovers from task failures.
# Only restart tasks that may have been affected by the task failure, which typically includes
# downstream tasks and potentially upstream tasks if their produced data is no longer available for consumption.
jobmanager.execution.failover-strategy: region
#==============================================================================
# Rest & web frontend
#==============================================================================
# The port to which the REST client connects to. If rest.bind-port has
# not been specified, then the server will bind to this port as well.
#
# The address to which the REST client will connect to
#
# Port range for the REST and web server to bind to.
#
# The address that the REST & web server binds to
#
# Flag to specify whether job submission is enabled from the web-based
# runtime monitor. Uncomment to disable.
#web.submit.enable: false
# Flag to specify whether job cancellation is enabled from the web-based
# runtime monitor. Uncomment to disable.
#web.cancel.enable: false
#==============================================================================
# Advanced
#==============================================================================
# Override the directories for temporary files. If not specified, the
# system-specific Java temporary directory (java.io.tmpdir property) is taken.
#
# containers' temp directories without any need for configuration.
#
# Add a delimited list for multiple directories, using the system directory
# delimiter (colon ':' on unix) or a comma, e.g.:
# /data1/tmp:/data2/tmp:/data3/tmp
#
# Note: Each directory entry is read from and written to by a different I/O
# thread. You can include the same directory multiple times in order to create
# multiple I/O threads against that directory. This is for example relevant for
#ghigh-throughput RAIDs.
#
# io.tmp.dirs: /tmp
# The classloading resolve order. Possible values are 'child-first' (Flink's default)
# and 'parent-first' (Java's default).
#
# Child first classloading allows users to use different dependency/library
# versions in their application than those in the classpath. Switching back
# to 'parent-first' may help with debugging dependency issues.
#
# classloader.resolve-order: child-first
classloader.resolve-order: parent-first
# The amount of memory going to the network stack. These numbers usually need
# no tuning. Adjusting them may be necessary in case of an "Insufficient number
# of network buffers" error. The default min is 64MB, the default max is 1GB.
#
# taskmanager.memory.network.fraction: 0.1
# taskmanager.memory.network.min: 64mb
# taskmanager.memory.network.max: 1gb
#==============================================================================
# Flink Cluster Security Configuration
#==============================================================================
# Kerberos authentication for various components - Hadoop, ZooKeeper, and connectors -
# may be enabled in four steps:
# 1. configure the local krb5.conf file
# 2. provide Kerberos credentials (either a keytab or a ticket cache w/ kinit)
# 3. make the credentials available to various JAAS login contexts
# 4. configure the connector to use JAAS/SASL
# The below configure how Kerberos credentials are provided. A keytab will be used instead of
# a ticket cache if the keytab path and principal are set.
# security.kerberos.login.use-ticket-cache: true
# security.kerberos.login.keytab: /path/to/kerberos/keytab
# security.kerberos.login.principal: flink-user
# The configuration below defines which JAAS login contexts
# security.kerberos.login.contexts: Client,KafkaClient
#==============================================================================
# ZK Security Configuration
#==============================================================================
# Below configurations are applicable if ZK ensemble is configured for security
# Override below configuration to provide custom ZK service name if configured
# zookeeper.sasl.service-name: zookeeper
# The configuration below must match one of the values set in "security.kerberos.login.contexts"
# zookeeper.sasl.login-context-name: Client
#==============================================================================
# HistoryServer
#==============================================================================
# The HistoryServer is started and stopped via bin/historyserver.sh (start|stop)
# Directory to upload completed jobs to. Add this directory to the list of
# monitored directories of the HistoryServer as well (see below).
#jobmanager.archive.fs.dir: hdfs:///completed-jobs/
# The address under which the web-based HistoryServer listens.
#historyserver.web.address: 0.0.0.0
# The port under which the web-based HistoryServer listens.
#historyserver.web.port: 8082
# Comma separated list of directories to monitor for completed jobs.
#historyserver.archive.fs.dir: hdfs:///completed-jobs/
# Interval in milliseconds for refreshing the monitored directories.
#historyserver.archive.fs.refresh-interval: 10000
# 重启次数，不能超过yarn的最大次数，目前yarn设置的是8
yarn.application-attempts: 7
# job dir
jobmanager.web.tmpdir: /data/flinkwb/tmp/dir
jobmanager.web.upload.dir: /data/flinkwb/upload/jar/dir
#心跳超时
heartbeat.timeout: 120000
# 历史记录
jobmanager.archive.fs.dir: hdfs:///flinkwb/flink14-completed-jobs/
# # The address under which the web-based HistoryServer listens.
historyserver.web.address: 172.20.0.151
# # The port under which the web-based HistoryServer listens.
historyserver.web.port: 14440
# # Comma separated list of directories to monitor for completed jobs.
historyserver.archive.fs.dir: hdfs:///flinkwb/flink14-completed-jobs/
# # Interval in milliseconds for refreshing the monitored directories.
historyserver.archive.fs.refresh-interval: 180000
# #查找到的归档文件会下载并缓存到本地存储路径，默认/tmp目录下面，默认路径为System.getProperty("java.io.tmpdir") + File.separator + "flink-web-history-" + UUID.randomUUID()
historyserver.web.tmpdir: /tmp/flinkhistoryservertmp/
# 尽可能将负载分散到所有当前可用的 TaskManage
cluster.evenly-spread-out-slots: true
taskmanager.memory.managed.fraction : 0.8
# 网络内存
taskmanager.memory.network.min: 128m
taskmanager.memory.network.max: 128m
# 元空间内存
taskmanager.memory.jvm-metaspace.size: 512m
jobmanager.memory.jvm-metaspace.size: 512m
# 启用访问状态的性能监控
state.backend.latency-track.keyed-state-enabled: true
# 采样间隔
state.backend.latency-track.sample-interval: 100
# 保留的采样数据个数，越大越精确
state.backend.latency-track.history-size: 128
# 将状态名作为变量
state.backend.latency-track.state-name-as-variable: true
# RocksDB
# block cache 默认 8m
state.backend.rocksdb.block.cache-size: 64m
# write buffer 和 level
state.backend.rocksdb.writebuffer.size: 128m
state.backend.rocksdb.compaction.level.max-size-level-base: 320m
# write buffer 数量
state.backend.rocksdb.writebuffer.count: 5
# 后台线程数和 write buffer 合并数
state.backend.rocksdb.thread.num: 4
state.backend.rocksdb.writebuffer.number-to-merge: 3
# 开启火焰图
rest.flamegraph.enabled : true
# GC 情况
#env.java.opts: -XX:+PrintGCDetails -XX:+PrintGCDateStamps
# 编码设置
env.java.opts: -Dfile.encoding=UTF-8
