1.我打包好Flink docker镜像文件flink 配置文件如下:
################################################################################
# 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 <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/Mesos
# automatically configure the host name based on the hostname of the node where the
# JobManager runs.
jobmanager.rpc.address: localhost
# The RPC port where the JobManager is reachable.
jobmanager.rpc.port: 6123
# The heap size for the JobManager JVM
jobmanager.heap.size: 1024m
# The heap size for the TaskManager JVM
taskmanager.heap.size: 1024m
# The number of task slots that each TaskManager offers. Each slot runs one parallel pipeline.
taskmanager.numberOfTaskSlots: 1
# The parallelism used for programs that did not specify and other parallelism.
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'
#
# fs.default-scheme
#==============================================================================
# High Availability
#==============================================================================
# The high-availability mode. Possible options are 'NONE' or '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, ...)
#
high-availability.storageDir: hdfs:///hadoop:9000/ha/hdfs
# 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)
#
high-availability.zookeeper.quorum: zookeeper: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
#
# 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
# <class-name-of-factory>.
#
state.backend: rocksdb
# Directory for checkpoints filesystem, when using any of the default bundled
# state backends.
#
state.checkpoints.dir: file:///data/flink/checkpoints
# Default target directory for savepoints, optional.
#
state.savepoints.dir: file:///data/flink/checkpoints
# 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.
#
#rest.port: 8081
# The address to which the REST client will connect to
#
#rest.address: 0.0.0.0
# Port range for the REST and web server to bind to.
#
#rest.bind-port: 8080-8090
# The address that the REST & web server binds to
#
#rest.bind-address: 0.0.0.0
# Flag to specify whether job submission is enabled from the web-based
# runtime monitor. Uncomment to disable.
#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
web.upload.dir: /opt/flink/jars
# 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.
#
# 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.
#
# 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.
#
# 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.
# 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
2.部署镜像这里我zooker放在了hadoop里，大家可以换一下,我就懒得换了
version: "3"
services:
jobmanager:
image: majiajue/flink:1.9.0-scala_2.12
ports:
- "18081:8081"
networks:
- flink-net
volumes:
- flink-config:/opt/flink/jars:rw
- flink-config:/data/flink/checkpoints
logging:
driver: "json-file"
options:
max-size: "10m"
command: jobmanager
environment:
- JOB_MANAGER_RPC_ADDRESS=jobmanager
deploy:
mode: replicated
replicas: 1
update_config:
parallelism: 3
delay: 2s
resources:
limits:
cpus: '0.1'
memory: 2048M
reservations:
cpus: '0.1'
memory: 2048M
taskmanager:
image: majiajue/flink:1.9.0-scala_2.12
networks:
- flink-net
logging:
driver: "json-file"
options:
max-size: "10m"
depends_on:
- jobmanager
volumes:
- flink-config:/opt/flink/jars:rw
command: taskmanager
depends_on:
- "jobmanager:jobmanager"
environment:
- JOB_MANAGER_RPC_ADDRESS=jobmanager
deploy:
mode: replicated
replicas: 3
update_config:
parallelism: 3
delay: 2s
resources:
limits:
cpus: '0.1'
memory: 2048M
reservations:
cpus: '0.1'
memory: 2048M
zookeeper:
image: majiajue/zookeeper:latest
networks:
- flink-net
ports:
- "2181:2181"
hadoop:
image: majiajue/hadoop:2.7.1
deploy:
mode: replicated
replicas: 1
update_config:
parallelism: 3
delay: 2s
resources:
limits:
cpus: '0.1'
memory: 2048M
reservations:
cpus: '0.1'
memory: 2048M
networks:
- flink-net
ports:
- "50070:50070"
- "8088:8088"
- "9000:9000"
- "8020:8020"
#存放在nfs 上文件共享，这样转移到其他节点也不怕了
volumes:
flink-config:
driver: local
driver_opts:
type: "nfs"
o: "addr=172.40.1.29,rw"
device: ":/dockershare/flink"
networks:
flink-net:
3.部署
docker stack deploy -c flink.yml flink
4.访问控制台 http://ip:18081 即可看到flink界面
网友评论