选择你想要的版本
镜像链接https://mirrors.aliyun.com/apache/spark/?spm=a2c6h.25603864.0.0.5d1b590eLwbWr2
sudo tar -zxvf spark-3.3.2-bin-without-hadoop.tgz -C /usr/local/
cd /usr/local/
sudo mv spark-3.3.2-bin-without-hadoop spark-3.3.2
chown -R bill:freedom spark-3.3.2
vi /etc/profile
#Spark3.3.2
export SPARK_HOME=/usr/local/spark-3.3.2
export PATH=$PATH:${SPARK_HOME}/binsource /etc/profile
下面为spark的配置，我这里为高可用集群，其中billsaifu主机为主master，其余两个主机的matser为候选
workers
#
# 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.
#
# A Spark Worker will be started on each of the machines listed below.
billsaifu
hadoop1
hadoop2Spark-defaults.conf
#
# 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.
#
# Default system properties included when running spark-submit.
# This is useful for setting default environmental settings.
# Example:
# spark.master spark://master:7077
# spark.eventLog.enabled true
# spark.eventLog.dir hdfs://namenode:8021/directory
# spark.serializer org.apache.spark.serializer.KryoSerializer
# spark.driver.memory 5g
# spark.executor.extraJavaOptions -XX:+PrintGCDetails -Dkey=value -Dnumbers="one two three"
spark.eventLog.enabled true
spark.eventLog.dir hdfs://billsaifu:9000/spark/log
spark.yarn.historyServer.address http://billsaifu:19889/jobhistory/logs
spark.history.ui.port 18080spakr-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
#
# 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.
#
# 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
# 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_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 any mode
# - SPARK_CONF_DIR, Alternate conf dir. (Default: ${SPARK_HOME}/conf)
# - 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 read in any cluster manager using HDFS
# - HADOOP_CONF_DIR, to point Spark towards Hadoop configuration files
# Options read in YARN client/cluster mode
# - YARN_CONF_DIR, to point Spark towards YARN configuration files when you use YARN
# 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_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_DAEMON_CLASSPATH, to set the classpath for all daemons
# - SPARK_PUBLIC_DNS, to set the public dns name of the master or workers
# Options for launcher
# - SPARK_LAUNCHER_OPTS, to set config properties and Java options for the launcher (e.g. "-Dx=y")
# 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_LOG_MAX_FILES Max log files of Spark daemons can rotate to. Default is 5.
# - SPARK_PID_DIR Where the pid file is stored. (Default: /tmp)
# - SPARK_IDENT_STRING A string representing this instance of spark. (Default: $USER)
# - SPARK_NICENESS The scheduling priority for daemons. (Default: 0)
# - SPARK_NO_DAEMONIZE Run the proposed command in the foreground. It will not output a PID file.
# Options for native BLAS, like Intel MKL, OpenBLAS, and so on.
# You might get better performance to enable these options if using native BLAS (see SPARK-21305).
# - MKL_NUM_THREADS=1 Disable multi-threading of Intel MKL
# - OPENBLAS_NUM_THREADS=1 Disable multi-threading of OpenBLAS
export JAVA_HOME=/usr/local/java8/jdk1.8.0_371
#SPARK_MASTER_HOST=billsaifu
#SPARK_MASTER_PORT=7077
SPARK_WORKER_PORT=7079
#export HADOOP_HOME=/usr/local/ha/hadoop-3.3.5/
SPARK_MASTER_WEBUI_PORT=8989
SPARK_WORKER_WEBUI_PORT=8020
export HADOOP_HOME=/usr/local/hadoop-3.2.4
export HADOOP_CONF_DIR=/usr/local/hadoop-3.2.4/etc/hadoop
export YARN_CONF_DIR=/usr/local/hadoop-3.2.4/etc/hadoop
export SPARK_DAEMON_JAVA_OPTS="
-Dspark.deploy.recoveryMode=ZOOKEEPER
-Dspark.deploy.zookeeper.url=billsaifu,hadoop1,hadoop2
-Dspark.deploy.zookeeper.dir=/spark"
export SPARK_DIST_CLASSPATH=$(/usr/local/hadoop-3.2.4/bin/hadoop classpath)
export SPARK_HISTORY_OPTS="
-Dspark.history.ui.port=18080
-Dspark.history.fs.logDirectory=hdfs://billsaifu:9000/spark/log
-Dspark.history.retainedApplications=30"
"start_spark")
echo " =================== 启动 spark 集群 ==================="
echo " --------------- 启动 master和workers ---------------"
ssh billsaifu "/usr/local/spark-3.3.2/sbin/start-all.sh"
echo " --------------- 启动备用master ---------------"
ssh hadoop1 "/usr/local/spark-3.3.2/sbin/start-master.sh"
ssh hadoop2 "/usr/local/spark-3.3.2/sbin/start-master.sh"
echo " --------------- 启动 historyserver ---------------"
ssh billsaifu "/usr/local/spark-3.3.2/sbin/start-history-server.sh"
;;
"stop_spark")
echo " =================== 关闭 spark 集群 ==================="
echo " --------------- 关闭 historyserver ---------------"
ssh billsaifu "/usr/local/spark-3.3.2/sbin/stop-history-server.sh"
echo " --------------- 关闭备用master ---------------"
ssh hadoop1 "/usr/local/spark-3.3.2/sbin/stop-master.sh"
ssh hadoop2 "/usr/local/spark-3.3.2/sbin/stop-master.sh"
echo " --------------- 关闭 master和workers ---------------"
ssh billsaifu "/usr/local/spark-3.3.2/sbin/stop-all.sh"
;;开启Hadoop和zookeeper后打开spark
