From cba13a1fee97971dc5753dadb852ea659d8dc611 Mon Sep 17 00:00:00 2001 From: baoliang Date: Wed, 10 Apr 2019 16:21:58 +0800 Subject: [PATCH] fix bug, update action would change the user of definition. --- docs/zh_CN/后端部署文档.md | 431 +++---------------------------- install.sh | 2 +- 2 files changed, 38 insertions(+), 395 deletions(-) diff --git a/docs/zh_CN/后端部署文档.md b/docs/zh_CN/后端部署文档.md index 4559e4b817..a07effbf49 100644 --- a/docs/zh_CN/后端部署文档.md +++ b/docs/zh_CN/后端部署文档.md @@ -86,370 +86,11 @@ escheduler ALL=(ALL) NOPASSWD: NOPASSWD: ALL #Default requiretty ``` -## 配置文件说明 - -``` -说明：配置文件位于 target/escheduler-{version}/conf 下面 -``` - -### escheduler-alert - -配置邮件告警信息 - - -* alert.properties - -``` -#以qq邮箱为例，如果是别的邮箱，请更改对应配置 -#alert type is EMAIL/SMS -alert.type=EMAIL - -# mail server configuration -mail.protocol=SMTP -mail.server.host=smtp.exmail.qq.com -mail.server.port=25 -mail.sender=xxxxxxx@qq.com -mail.passwd=xxxxxxx - -# xls file path, need manually create it before use if not exist -xls.file.path=/opt/xls -``` - - - - -### escheduler-common - -通用配置文件配置，队列选择及地址配置，通用文件目录配置 - -- common/common.properties - -``` -#task queue implementation, default "zookeeper" -escheduler.queue.impl=zookeeper - -# user data directory path, self configuration, please make sure the directory exists and have read write permissions -data.basedir.path=/tmp/escheduler - -# directory path for user data download. self configuration, please make sure the directory exists and have read write permissions -data.download.basedir.path=/tmp/escheduler/download - -# process execute directory. self configuration, please make sure the directory exists and have read write permissions -process.exec.basepath=/tmp/escheduler/exec - -# data base dir, resource file will store to this hadoop hdfs path, self configuration, please make sure the directory exists on hdfs and have read write permissions。"/escheduler" is recommended -data.store2hdfs.basepath=/escheduler - -# whether hdfs starts -hdfs.startup.state=true - -# system env path. self configuration, please make sure the directory and file exists and have read write execute permissions -escheduler.env.path=/opt/.escheduler_env.sh -escheduler.env.py=/opt/escheduler_env.py - -#resource.view.suffixs -resource.view.suffixs=txt,log,sh,conf,cfg,py,java,sql,hql,xml - -# is development state? default "false" -development.state=false -``` - - - -SHELL任务 环境变量配置 - -``` -说明：配置文件位于 target/escheduler-{version}/conf/env 下面，这个会是Worker执行任务时加载的环境 -``` - -.escheduler_env.sh -``` -export HADOOP_HOME=/opt/soft/hadoop -export HADOOP_CONF_DIR=/opt/soft/hadoop/etc/hadoop -export SPARK_HOME1=/opt/soft/spark1 -export SPARK_HOME2=/opt/soft/spark2 -export PYTHON_HOME=/opt/soft/python -export JAVA_HOME=/opt/soft/java -export HIVE_HOME=/opt/soft/hive - -export PATH=$HADOOP_HOME/bin:$SPARK_HOME1/bin:$SPARK_HOME2/bin:$PYTHON_HOME/bin:$JAVA_HOME/bin:$HIVE_HOME/bin:$PATH -``` - - -​ - -Python任务 环境变量配置 - -``` -说明：配置文件位于 target/escheduler-{version}/conf/env 下面 -``` - -escheduler_env.py -``` -import os - -HADOOP_HOME="/opt/soft/hadoop" -SPARK_HOME1="/opt/soft/spark1" -SPARK_HOME2="/opt/soft/spark2" -PYTHON_HOME="/opt/soft/python" -JAVA_HOME="/opt/soft/java" -HIVE_HOME="/opt/soft/hive" -PATH=os.environ['PATH'] -PATH="%s/bin:%s/bin:%s/bin:%s/bin:%s/bin:%s/bin:%s"%(HIVE_HOME,HADOOP_HOME,SPARK_HOME1,SPARK_HOME2,JAVA_HOME,PYTHON_HOME,PATH) - -os.putenv('PATH','%s'%PATH) -``` - - - -hadoop 配置文件 - -- common/hadoop/hadoop.properties - -``` -# ha or single namenode,If namenode ha needs to copy core-site.xml and hdfs-site.xml to the conf directory -fs.defaultFS=hdfs://mycluster:8020 - -#resourcemanager ha note this need ips , this empty if single -yarn.resourcemanager.ha.rm.ids=192.168.xx.xx,192.168.xx.xx - -# If it is a single resourcemanager, you only need to configure one host name. If it is resourcemanager HA, the default configuration is fine -yarn.application.status.address=http://ark1:8088/ws/v1/cluster/apps/%s - -``` - - - -定时器配置文件 - -- quartz.properties - -``` -#============================================================================ -# Configure Main Scheduler Properties -#============================================================================ -org.quartz.scheduler.instanceName = EasyScheduler -org.quartz.scheduler.instanceId = AUTO -org.quartz.scheduler.makeSchedulerThreadDaemon = true -org.quartz.jobStore.useProperties = false - -#============================================================================ -# Configure ThreadPool -#============================================================================ - -org.quartz.threadPool.class = org.quartz.simpl.SimpleThreadPool -org.quartz.threadPool.makeThreadsDaemons = true -org.quartz.threadPool.threadCount = 25 -org.quartz.threadPool.threadPriority = 5 - -#============================================================================ -# Configure JobStore -#============================================================================ - -org.quartz.jobStore.class = org.quartz.impl.jdbcjobstore.JobStoreTX -org.quartz.jobStore.driverDelegateClass = org.quartz.impl.jdbcjobstore.StdJDBCDelegate -org.quartz.jobStore.tablePrefix = QRTZ_ -org.quartz.jobStore.isClustered = true -org.quartz.jobStore.misfireThreshold = 60000 -org.quartz.jobStore.clusterCheckinInterval = 5000 -org.quartz.jobStore.dataSource = myDs - -#============================================================================ -# Configure Datasources -#============================================================================ - -org.quartz.dataSource.myDs.driver = com.mysql.jdbc.Driver -org.quartz.dataSource.myDs.URL = jdbc:mysql://192.168.xx.xx:3306/escheduler?characterEncoding=utf8&useSSL=false -org.quartz.dataSource.myDs.user = xx -org.quartz.dataSource.myDs.password = xx -org.quartz.dataSource.myDs.maxConnections = 10 -org.quartz.dataSource.myDs.validationQuery = select 1 -``` - - - -zookeeper 配置文件 - - -- zookeeper.properties - -``` -#zookeeper cluster -zookeeper.quorum=192.168.xx.xx:2181,192.168.xx.xx:2181,192.168.xx.xx:2181 - -#escheduler root directory -zookeeper.escheduler.root=/escheduler - -#zookeeper server dirctory -zookeeper.escheduler.dead.servers=/escheduler/dead-servers -zookeeper.escheduler.masters=/escheduler/masters -zookeeper.escheduler.workers=/escheduler/workers - -#zookeeper lock dirctory -zookeeper.escheduler.lock.masters=/escheduler/lock/masters -zookeeper.escheduler.lock.workers=/escheduler/lock/workers - -#escheduler failover directory -zookeeper.escheduler.lock.masters.failover=/escheduler/lock/failover/masters -zookeeper.escheduler.lock.workers.failover=/escheduler/lock/failover/workers - -#escheduler failover directory -zookeeper.session.timeout=300 -zookeeper.connection.timeout=300 -zookeeper.retry.sleep=1000 -zookeeper.retry.maxtime=5 - -``` - - - -### escheduler-dao - -dao数据源配置 - -- dao/data_source.properties - -``` -# base spring data source configuration -spring.datasource.type=com.alibaba.druid.pool.DruidDataSource -spring.datasource.driver-class-name=com.mysql.jdbc.Driver -spring.datasource.url=jdbc:mysql://192.168.xx.xx:3306/escheduler?characterEncoding=UTF-8 -spring.datasource.username=xx -spring.datasource.password=xx - -# connection configuration -spring.datasource.initialSize=5 -# min connection number -spring.datasource.minIdle=5 -# max connection number -spring.datasource.maxActive=50 - -# max wait time for get a connection in milliseconds. if configuring maxWait, fair locks are enabled by default and concurrency efficiency decreases. -# If necessary, unfair locks can be used by configuring the useUnfairLock attribute to true. -spring.datasource.maxWait=60000 - -# milliseconds for check to close free connections -spring.datasource.timeBetweenEvictionRunsMillis=60000 - -# the Destroy thread detects the connection interval and closes the physical connection in milliseconds if the connection idle time is greater than or equal to minEvictableIdleTimeMillis. -spring.datasource.timeBetweenConnectErrorMillis=60000 - -# the longest time a connection remains idle without being evicted, in milliseconds -spring.datasource.minEvictableIdleTimeMillis=300000 - -#the SQL used to check whether the connection is valid requires a query statement. If validation Query is null, testOnBorrow, testOnReturn, and testWhileIdle will not work. -spring.datasource.validationQuery=SELECT 1 -#check whether the connection is valid for timeout, in seconds -spring.datasource.validationQueryTimeout=3 - -# when applying for a connection, if it is detected that the connection is idle longer than time Between Eviction Runs Millis, -# validation Query is performed to check whether the connection is valid -spring.datasource.testWhileIdle=true - -#execute validation to check if the connection is valid when applying for a connection -spring.datasource.testOnBorrow=true -#execute validation to check if the connection is valid when the connection is returned -spring.datasource.testOnReturn=false -spring.datasource.defaultAutoCommit=true -spring.datasource.keepAlive=true - -# open PSCache, specify count PSCache for every connection -spring.datasource.poolPreparedStatements=true -spring.datasource.maxPoolPreparedStatementPerConnectionSize=20 -``` - - - -### escheduler-server - -master配置文件 - -- master.properties - -``` -# master execute thread num -master.exec.threads=100 - -# master execute task number in parallel -master.exec.task.number=20 - -# master heartbeat interval -master.heartbeat.interval=10 - -# master commit task retry times -master.task.commit.retryTimes=5 - -# master commit task interval -master.task.commit.interval=100 - - -# only less than cpu avg load, master server can work. default value : the number of cpu cores * 2 -master.max.cpuload.avg=10 - -# only larger than reserved memory, master server can work. default value : physical memory * 1/10, unit is G. -master.reserved.memory=1 -``` - - - -worker配置文件 - -- worker.properties - -``` -# worker execute thread num -worker.exec.threads=100 - -# worker heartbeat interval -worker.heartbeat.interval=10 - -# submit the number of tasks at a time -worker.fetch.task.num = 10 - - -# only less than cpu avg load, worker server can work. default value : the number of cpu cores * 2 -worker.max.cpuload.avg=10 - -# only larger than reserved memory, worker server can work. default value : physical memory * 1/6, unit is G. -worker.reserved.memory=1 -``` - - - -### escheduler-api - -web配置文件 - -- application.properties - -``` -# server port -server.port=12345 - -# session config -server.session.timeout=7200 - -server.context-path=/escheduler/ - -# file size limit for upload -spring.http.multipart.max-file-size=1024MB -spring.http.multipart.max-request-size=1024MB - -# post content -server.max-http-post-size=5000000 -``` - - - ## 伪分布式部署 -### 1，创建部署用户 - -​ 如上 **创建部署用户** - ### 2，根据实际需求来创建HDFS根路径 -​ 根据 **common/common.properties** 中 **hdfs.startup.state** 的配置来判断是否启动HDFS，如果启动，则需要创建HDFS根路径，并将 **owner** 修改为**部署用户**，否则忽略此步骤 +​ 根据 **common/common.properties** 中 **hdf.startup.states** 的配置来判断是否启动HDFS，如果启动，则需要创建HDFS根路径，并将 **owner** 修改为**部署用户**，否则忽略此步骤 ### 3，项目编译 @@ -465,40 +106,6 @@ server.max-http-post-size=5000000 - 将**.escheduler_env.sh** 和 **escheduler_env.py** 两个环境变量文件复制到 **common/common.properties**配置的**escheduler.env.path** 和 **escheduler.env.py** 的目录下，并将 **owner** 修改为**部署用户** -### 6，启停服务 - -* 启停Master - -```启动master -sh ./bin/escheduler-daemon.sh start master-server -sh ./bin/escheduler-daemon.sh stop master-server -``` - -* 启停Worker - -``` -sh ./bin/escheduler-daemon.sh start worker-server -sh ./bin/escheduler-daemon.sh stop worker-server -``` - -* 启停Api - -``` -sh ./bin/escheduler-daemon.sh start api-server -sh ./bin/escheduler-daemon.sh stop api-server -``` -* 启停Logger - -``` -sh ./bin/escheduler-daemon.sh start logger-server -sh ./bin/escheduler-daemon.sh stop logger-server -``` -* 启停Alert - -``` -sh ./bin/escheduler-daemon.sh start alert-server -sh ./bin/escheduler-daemon.sh stop alert-server -``` @@ -546,6 +153,42 @@ sh ./bin/escheduler-daemon.sh stop alert-server - 注意：scp_hosts.sh 里 `tar -zxvf $workDir/../escheduler-1.0.0.tar.gz -C $installPath` 中的版本号(1.0.0)需要执行前手动替换成对应的版本号 + +### 7，启停服务 + +* 启停Master + +```启动master +sh ./bin/escheduler-daemon.sh start master-server +sh ./bin/escheduler-daemon.sh stop master-server +``` + +* 启停Worker + +``` +sh ./bin/escheduler-daemon.sh start worker-server +sh ./bin/escheduler-daemon.sh stop worker-server +``` + +* 启停Api + +``` +sh ./bin/escheduler-daemon.sh start api-server +sh ./bin/escheduler-daemon.sh stop api-server +``` +* 启停Logger + +``` +sh ./bin/escheduler-daemon.sh start logger-server +sh ./bin/escheduler-daemon.sh stop logger-server +``` +* 启停Alert + +``` +sh ./bin/escheduler-daemon.sh start alert-server +sh ./bin/escheduler-daemon.sh stop alert-server +``` + ## 服务监控 monitor_server.py 脚本是监听，master和worker服务挂掉重启的脚本 diff --git a/install.sh b/install.sh index 81772729de..515dfe20ea 100644 --- a/install.sh +++ b/install.sh @@ -211,7 +211,7 @@ mailPassword="xxxxxxxxxx" xlsFilePath="/opt/xls" # conf/config/install_config.conf配置 -# 安装路径 +# 安装路径,不要当前路径(pwd)一样 installPath="/data1_1T/escheduler" # 部署用户