centos安装集群笔记

时间同步

服务端内网主机

yum install ntpdate ntp -y

systemctl start ntpdate
systemctl start ntpd

客户端同步内网主机时间

yum install ntpdate

ntpdate 192.168.0.123
18 Sep 09:17:38 ntpdate[9284]: step time server 192.168.0.123 offset -682.947247 sec

解压rar包

wget http://www.rarsoft.com/rar/rarlinux-x64-5.4.0.tar.gz

tar -xvf rarlinux-x64-5.4.0.tar.gz

cd rar
make

看见下面这些信息就是安装成功了
mkdir -p /usr/local/bin
mkdir -p /usr/local/lib
cp rar unrar /usr/local/bin
cp rarfiles.lst /etc
cp default.sfx /usr/local/lib

解压rar包

rar x tianyiyun.rar

ES配置内存大小

不要超过32G

Elasticsearch默认安装后设置的内存是1GB，对于任何一个业务部署来说，这个都太小了。如果你正在使用这些默认堆内存配置，你的集群配置可能有点问题
这里有另外一个原因不分配大内存给Elasticsearch，事实上jvm在内存小于32G的时候会采用一个内存对象指针压缩技术。
在java中，所有的对象都分配在堆上，然后有一个指针引用它。指向这些对象的指针大小通常是CPU的字长的大小，不是32bit就是64bit，这取决于你的处理器，指针指向了你的值的精确位置。
对于32位系统，你的内存最大可使用4G。对于64系统可以使用更大的内存。但是64位的指针意味着更大的浪费，因为你的指针本身大了。浪费内存不算，更糟糕的是，更大的指针在主内存和缓存器（例如LLC, L1等）之间移动数据的时候，会占用更多的带宽。
java 使用一个叫内存指针压缩的技术来解决这个问题。它的指针不再表示对象在内存中的精确位置，而是表示偏移量。这意味着32位的指针可以引用40亿个对象，而不是40亿个字节。最终，也就是说堆内存长到32G的物理内存，也可以用32bit的指针表示。
一旦你越过那个神奇的30-32G的边界,指针就会切回普通对象的指针,每个对象的指针都变长了,就会使用更多的CPU内存带宽,也就是说你实际上失去了更多的内存,事实上当内存到达40-50GB的时候,有效内存才相当于使用内存对象指针压缩技术时候的32G内存
这段描述的意思就是说：即便你有足够的内存，也尽量不要超过32G，因为它浪费了内存，降低了CPU的性能，还要让GC应对大内存

Ansible过滤特定组的主机

Flink Jobmanager(Master HA)高可用

################################################################################
#  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: 192.168.0.195

# The RPC port where the JobManager is reachable.

jobmanager.rpc.port: 6123

#taskmanager.memory.jvm-metaspace.size: 1024m

# The total process memory size for the JobManager.
#
# Note this accounts for all memory usage within the JobManager process, including JVM metaspace and other overhead.

#jobmanager.memory.process.size: 1600m
jobmanager.memory.process.size: 4096m
jobmanager.memory.jvm-metaspace.size: 2048m

# The total process memory size for the TaskManager.
#
# Note this accounts for all memory usage within the TaskManager process, including JVM metaspace and other overhead.

taskmanager.memory.task.heap.size: 2048m
taskmanager.memory.managed.size: 1024m
taskmanager.memory.framework.off-heap.size: 2048m
taskmanager.memory.jvm-metaspace.size: 2048m
#taskmanager.memory.process.size: 1728m
# 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.
#
# taskmanager.memory.flink.size: 1280m

# The number of task slots that each TaskManager offers. Each slot runs one parallel pipeline.

taskmanager.numberOfTaskSlots: 300

# 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: /data/tianyiyun/nfsdata/flink/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)
#
high-availability.zookeeper.quorum: 192.168.0.232:32181,192.168.0.125:32181,192.168.0.40:32181/flinkha


# 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: filesystem

# Directory for checkpoints filesystem, when using any of the default bundled
# state backends.
#
# state.checkpoints.dir: hdfs://namenode-host:port/flink-checkpoints

# Default target directory for savepoints, optional.
#
# 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).
#
# state.backend.incremental: false
state.checkpoints.num-retained: 2

# 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
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
io.tmp.dirs: /data/tianyiyun/nfsdata/flink/flink-temp
# 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.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: file:///data/tianyiyun/nfsdata/flink/flink-history

# 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: 8882

# Comma separated list of directories to monitor for completed jobs.
historyserver.archive.fs.dir: file:///data/tianyiyun/nfsdata/flink/flink-history
# Interval in milliseconds for refreshing the monitored directories.
#historyserver.archive.fs.refresh-interval: 10000

env.java.home: /usr/lib/java/jdk1.8.0_191
web.upload.dir: /data/tianyiyun/nfsdata/flink/flink-web-jar


metrics.reporters: prom
metrics.reporter.prom.class: org.apache.flink.metrics.prometheus.PrometheusReporter
metrics.reporter.prom.port: 9213-9214

flink-conf.yaml

192.168.0.195:8081
192.168.0.170:8081

masters

192.168.0.75
192.168.0.7

workers

flink 集群重启宕机服务

jobmanager.sh start cluster jobmanager-01

zk常用命令

#1.连接zk命令

[root@raid2t shell]# zkCli.sh -server localhost:2181

#2.创建zk节点

[zk: localhost:2181(CONNECTED) 1] create /master myData

#3. 获取master节点数据

[zk: localhost:2181(CONNECTED) 1] get /master

#4. 给master节点赋值data123456

[zk: localhost:2181(CONNECTED) 1] set /master data123456

#5. 删除master节点

[zk: localhost:2181(CONNECTED) 1] delete /master deleteall /master 删除非空节点