flink-conf.yaml 配置文件详解

如果错误请留言……

################################################################################
#  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.
################################################################################


#==============================================================================
# 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  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/Mesos
# automatically configure the host name based on the hostname of the node where the
# JobManager runs.
# JobManager 的IP地址
jobmanager.rpc.address: localhost
# The RPC port where the JobManager is reachable.
# JobManager的端口号
jobmanager.rpc.port: 6123
# The heap size for the JobManager JVM
# JobManager JVM heap的内存大小
jobmanager.heap.size: 1024m
# The heap size for the TaskManager JVM
# TaskManager JVM Heap的内存大小
taskmanager.heap.size: 1024m
# The number of task slots that each TaskManager offers. Each slot runs one parallel pipeline.
#每个TaskManager 提供的任务Slots数量大小
taskmanager.numberOfTaskSlots: 1
# The parallelism used for programs that did not specify and other parallelism.
#程序默认并行计算的个数
parallelism.default: 1

# The default file system scheme and authority.
# 
# By default file paths without scheme are interpreted relative to the local
# 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'
# 文件系统来源
# fs.default-scheme

#==============================================================================
# High Availability
#==============================================================================

# The high-availability mode. Possible options are 'NONE' or 'zookeeper'.

#可以选择none或者zookeeper
# high-availability: zookeeper
# 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.
# Must be a durable file system that is accessible from all nodes
# (like HDFS, S3, Ceph, nfs, ...) 
#
# 文件系统路径，让flink在高可用性设置中持久保存元数据
# high-availability.storageDir: hdfs:///flink/ha/
# 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)

# zookeeper集群中仲裁者的机器ip和port端口号
# high-availability.zookeeper.quorum: localhost:2181


# ACL options are based on https://zookeeper.apache.org/doc/r3.1.2/zookeeperProgrammers.html#sc_BuiltinACLSchemes
# 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
#
# 默认是open，如果zookeeper security启用了该值会更改creator
# high-availability.zookeeper.client.acl: open

#==============================================================================
# Fault tolerance and checkpointing
#==============================================================================

# The backend that will be used to store operator state checkpoints if
# checkpointing is enabled.
#
# Supported backends are 'jobmanager', 'filesystem', 'rocksdb', or the
# .
# 用于存储和检查点状态
# state.backend: filesystem

# Directory for checkpoints filesystem, when using any of the default bundled
# state backends.
# 存储检查点的数据文件和元数据的默认目录
# state.checkpoints.dir: hdfs://namenode-host:port/flink-checkpoints

# Default target directory for savepoints, optional.
# savepoints的默认目标目录（可选）
# state.savepoints.dir: hdfs://namenode-host:port/flink-checkpoints

# Flag to enable/disable incremental checkpoints for backends that
# support incremental checkpoints (like the RocksDB state backend). 
# 用于启用/禁止增量checkpoints的标志
# state.backend.incremental: false

# 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.
# 故障转移策略
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.
#
# client链接port
#rest.port: 8081

# The address to which the REST client will connect to
# client 链接ip
#rest.address: 0.0.0.0

# Port range for the REST and web server to bind to.
# server  绑定port
#rest.bind-port: 8080-8090

# The address that the REST & web server binds to
# web 绑定ip
#rest.bind-address: 0.0.0.0

# Flag to specify whether job submission is enabled from the web-based
# runtime monitor. Uncomment to disable.
# 是否启动web提交
#web.submit.enable: false

#==============================================================================
# Advanced
#==============================================================================

# Override the directories for temporary files. If not specified, the
# system-specific Java temporary directory (java.io.tmpdir property) is taken.
#
# For framework setups on Yarn or Mesos, Flink will automatically pick up the
# 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
# high-throughput RAIDs.
#
# io.tmp.dirs: /tmp

# Specify whether TaskManager's managed memory should be allocated when starting
# up (true) or when memory is requested.
#
# We recommend to set this value to 'true' only in setups for pure batch
# processing (DataSet API). Streaming setups currently do not use the TaskManager's
# managed memory: The 'rocksdb' state backend uses RocksDB's own memory management,
# while the 'memory' and 'filesystem' backends explicitly keep data as objects
# to save on serialization cost.
# 是否应在TaskManager启动时预先分配TaskManager管理的内存
# taskmanager.memory.preallocate: false

# 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.
# 类加载解析顺序，是先检查用户代码jar（child-first）还是应用程序类路径（parent-first）默认设置指示首先从用户用户代码jar加载类
# classloader.resolve-order: child-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.
# 用于网络缓冲区的JVM的分配。这决定了TaskManager可以同时用友多少流数据交换通道及通道缓冲的程度。
# 如果作业被拒绝或者收到收到系统没有足够缓冲区的警告，请增加下面的最小值/最大值。
# 另外注意 taskmanager.network.memory.min 和 taskmanager.network.memory.max 可能会被覆盖。
# taskmanager.network.memory.fraction: 0.1
# taskmanager.network.memory.min: 64mb
# taskmanager.network.memory.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.
# 是否从Kerberos ticket缓存中读取
# security.kerberos.login.use-ticket-cache: true
# 包含用户凭据的Kerberos秘钥表文件的绝对路径
# security.kerberos.login.keytab: /path/to/kerberos/keytab
# 与keytab关联的Kerberos主体名称
# security.kerberos.login.principal: flink-user

# The configuration below defines which JAAS login contexts
# 以逗号分隔的登录上下文列表，用于提供Kerberos凭据（例如Client，KafkaClient使用凭证进行zookeeper身份验证kafka身份验证）
# 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
# 覆盖一下配置以提供自定义的zk服务名称
# zookeeper.sasl.service-name: zookeeper

# The configuration below must match one of the values set in "security.kerberos.login.contexts"
# 该配置必须匹配security.kerberos.login.contexts中的列表（含有一个）
# zookeeper.sasl.login-context-name: Client

#==============================================================================
# HistoryServer
#==============================================================================

# The HistoryServer is started and stopped via bin/historyserver.sh (start|stop)
# 可以通过 bin/historyserver.sh (start|stop) 命令启动和关闭 HistoryServer
#
# Directory to upload completed jobs to. Add this directory to the list of
# monitored directories of the HistoryServer as well (see below).
# 将已完成的作业上传到的目录
#jobmanager.archive.fs.dir: hdfs:///completed-jobs/

# The address under which the web-based HistoryServer listens.
# 基于web的historyserver的地址
#historyserver.web.address: 0.0.0.0

# The port under which the web-based HistoryServer listens.
# 基于web的historyweb的端口
#historyserver.web.port: 8082

# Comma separated list of directories to monitor for completed jobs.
# 以逗号分隔的目录列表，用于监视已完成的作业
#historyserver.archive.fs.dir: hdfs:///completed-jobs/

# Interval in milliseconds for refreshing the monitored directories.
# 刷新受监控的目录的事件间隔（以毫秒为单位）
#historyserver.archive.fs.refresh-interval: 10000