添加如下信息
######### spark ############ export SPARK_HOME=http://www.likecs.com/usr/local/spark-2.0.2 export PATH=$PATH:$SPARK_HOME/bin:$SPARK_HOME/sbin 2.3 刷新配置文件： source /etc/profile 2.4 修改spark配置文件 cd /usr/local/spark-2.0.2/conf mv spark-env.sh.template spark-env.sh [root@spark-master conf]# ll 总用量 36 -rw-r--r--. 1 500 500 987 11月 8 09:58 docker.properties.template -rw-r--r--. 1 500 500 1105 11月 8 09:58 fairscheduler.xml.template -rw-r--r--. 1 500 500 2025 11月 8 09:58 log4j.properties.template -rw-r--r--. 1 500 500 7239 11月 8 09:58 metrics.properties.template -rw-r--r--. 1 500 500 912 12月 21 16:55 slaves -rw-r--r--. 1 500 500 1292 11月 8 09:58 spark-defaults.conf.template -rwxr-xr-x. 1 root root 3969 12月 21 15:50 spark-env.sh -rwxr-xr-x. 1 500 500 3861 11月 8 09:58 spark-env.sh.template 2.4.1 spark关联jdk vim spark-env.sh #!/usr/bin/env bash # # 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 # # # # 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. # # This file is sourced when running various Spark programs. # Copy it as spark-env.sh and edit that to configure Spark for your site. # Options read when launching programs locally with # ./bin/run-example or ./bin/spark-submit # - HADOOP_CONF_DIR, to point Spark towards Hadoop configuration files # - SPARK_LOCAL_IP, to set the IP address Spark binds to on this node # - SPARK_PUBLIC_DNS, to set the public dns name of the driver program # - SPARK_CLASSPATH, default classpath entries to append # Options read by executors and drivers running inside the cluster # - SPARK_LOCAL_IP, to set the IP address Spark binds to on this node # - SPARK_PUBLIC_DNS, to set the public DNS name of the driver program # - SPARK_CLASSPATH, default classpath entries to append # - SPARK_LOCAL_DIRS, storage directories to use on this node for shuffle and RDD data # - MESOS_NATIVE_JAVA_LIBRARY, to point to your libmesos.so if you use Mesos # Options read in YARN client mode # - HADOOP_CONF_DIR, to point Spark towards Hadoop configuration files # - SPARK_EXECUTOR_INSTANCES, Number of executors to start (Default: 2) # - SPARK_EXECUTOR_CORES, Number of cores for the executors (Default: 1). # - SPARK_EXECUTOR_MEMORY, Memory per Executor (e.g. 1000M, 2G) (Default: 1G) # - SPARK_DRIVER_MEMORY, Memory for Driver (e.g. 1000M, 2G) (Default: 1G) # Options for the daemons used in the standalone deploy mode # - SPARK_MASTER_HOST, to bind the master to a different IP address or hostname # - SPARK_MASTER_PORT / SPARK_MASTER_WEBUI_PORT, to use non-default ports for the master # - SPARK_MASTER_OPTS, to set config properties only for the master (e.g. "-Dx=y") # - SPARK_WORKER_CORES, to set the number of cores to use on this machine # - SPARK_WORKER_MEMORY, to set how much total memory workers have to give executors (e.g. 1000m, 2g) # - SPARK_WORKER_PORT / SPARK_WORKER_WEBUI_PORT, to use non-default ports for the worker # - SPARK_WORKER_INSTANCES, to set the number of worker processes per node # - SPARK_WORKER_DIR, to set the working directory of worker processes # - SPARK_WORKER_OPTS, to set config properties only for the worker (e.g. "-Dx=y") # - SPARK_DAEMON_MEMORY, to allocate to the master, worker and history server themselves (default: 1g). # - SPARK_HISTORY_OPTS, to set config properties only for the history server (e.g. "-Dx=y") # - SPARK_SHUFFLE_OPTS, to set config properties only for the external shuffle service (e.g. "-Dx=y") # - SPARK_DAEMON_JAVA_OPTS, to set config properties for all daemons (e.g. "-Dx=y") # - SPARK_PUBLIC_DNS, to set the public dns name of the master or workers # Generic options for the daemons used in the standalone deploy mode # - SPARK_CONF_DIR Alternate conf dir. (Default: ${SPARK_HOME}/conf) # - SPARK_LOG_DIR Where log files are stored. (Default: ${SPARK_HOME}/logs) # - SPARK_PID_DIR Where the pid file is stored. (Default: /tmp) # - SPARK_IDENT_STRING A string representing this instance of spark. (Default: $USER) # - SPARK_NICENESS The scheduling priority for daemons. (Default: 0) #java的环境变量 export JAVA_HOME=http://www.likecs.com/usr/local/jdk1.8.0_111 #spark主节点的ip export SPARK_MASTER_IP=172.16.200.81 #spark主节点的端口号 export SPARK_MASTER_PORT=7077 2.4.2 配置slaves vim slaves # # 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 # # # # 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. # # A Spark Worker will be started on each of the machines listed below. 172.16.200.81 172.16.200.82 172.16.200.83 172.16.200.84 3. 安装scala cd /usr/loca/src/ tar zxvf scala-2.12.1.tgz mv scala-2.12.1 /usr/local 3.1 配置scala环境变量（只master安装） vim /etc/profile