1. 准备工作
- 创建日志文件存放的目录 /export/data/logs/log,执行命令:
mkdir -p /export/data/logs/log
- 创建待上传文件存放的目录/export/data/logs/toupload,执行命令:
mkdir -p /export/data/logs/toupload
- 查看创建的目录树结构
- 先安装tree命令:
yum -y install tree
- 查看创建目录数结构:
tree /export
2. 编程实现步骤及结果
2.1 编写脚本,实现功能
- 进入/export/data/logs目录:
cd /export/data/logs
- 执行命令:
vim upload2HDFS.sh
JAVA_HOME=/usr/local/jdk1.8.0_231
export JRE_HOME=${JAVA_HOME}/jre
export CLASSPATH=.:${JAVA_HOME}/lib:${JRE_HOME}/lib
export PATH=${JAVA_HOME}/bin:$PATH
export HADOOP_HOME=/usr/local/hadoop-3.3.4/
export PATH=${HADOOP_HOME}/bin:${HADOOP_HOME}/sbin:$PATH
log_src_dir=/export/data/logs/log/
log_toupload_dir=/export/data/logs/toupload/
date1=`date +%Y_%m_%d`
hdfs_root_dir=/data/clickLog/$date1/
echo "envs: hadoop_home: $HADOOP_HOME"
echo "log_src_dir: $log_src_dir"
ls $log_src_dir | while read fileName
do
if [[ "$fileName" == access.log.* ]]; then
date=`date +%Y_%m_%d_%H_%M_%S`
echo "moving $log_src_dir$fileName to $log_toupload_dir"lzy_click_log_$fileName"$date"
mv $log_src_dir$fileName $log_toupload_dir"lzy_click_log_$fileName"$date
echo $log_toupload_dir"lzy_click_log_$fileName"$date >> $log_toupload_dir"willDoing."$date
fi
done
ls $log_toupload_dir | grep will | grep -v "_COPY_" | grep -v "_DONE_" | while read line
do
echo "toupload is in file: $line"
mv $log_toupload_dir$line $log_toupload_dir$line"_COPY_"
cat $log_toupload_dir$line"_COPY_" | while read line
do
echo "puting...$line to hdfs path...$hdfs_root_dir"
hdfs dfs -mkdir -p $hdfs_root_dir
hdfs dfs -put $line $hdfs_root_dir
done
mv $log_toupload_dir$line"_COPY_" $log_toupload_dir$line"_DONE_"
done
- 编辑权限,执行命令:
chmod u+x upload2HDFS.sh
- 查看/export目录树结构
2.2 运行脚本,查看结果
- 创建四个日志文件(必须以access.log.打头)
- 查看/export目录树结构
- 执行命令:
./upload2HDFS.sh
- 查看/export目录树结构
- 打开HDFS集群WebUI查看上传的日志文件