【大数据】SmallFile-Analysis-Script

1.root账号先在namenode节点上配置一个定时任务，将fsimage定时传到其他客户机上进行操作

whereis hadoop命令确定安装目录，然后去配置文件找到namenode节点（data-93 emr-header-1）

0 1 * * * sh /root/fsimage.sh 每晚一点将fsimage文件发送到集群其他机器上，fsimage.sh如下

#!/bin/bash
TARGET_HOST=192.168.11.130
SCP_PORT=
IMAGE_DIR=/mnt/disk1/hdfs/name/current
TARGET_DIR=/data/hdfs
DAY=`date +%Y%m%d`
echo "day=$DAY"

cd $IMAGE_DIR
fsname=`ls fsimage* | head -`
echo $fsname

scp -P $SCP_PORT $fsname ${TARGET_HOST}:${TARGET_DIR}/fsimage.${DAY}

echo "done"

脚本在/mnt/disk1/hdfs/name/current下执行【scp -P 58422 fsimage_0000000007741688997 192.168.11.130:/data/hdfs/fsimage.20190920】,将namenode上的fsimage镜像文件传递到data130（192.168.11.130）上的文件夹里

2.切换账号gobblin，在data-130的机子上配置crontab 任务，每天2点执行分析脚本

small_file_analysis.sh如下

#!/bin/bash
source /etc/profile

basepath=$(cd `dirname $`; pwd)
cd $basepath
IMAGE_DIR="/data/hdfs"
IMAGE_PREFIX="fsimage"

# . 解析日期
cur_date="`date +%Y%m%d`"
cur_month="`date +%Y%m`"
cur_day="`date +%d`"
echo "cur month = $cur_month"
echo "cur day = $cur_day"
echo "cur date = $cur_date"
IMAGE_NAME=$IMAGE_PREFIX.$cur_date
echo "fsimage name is $IMAGE_NAME"

# . 解析 fsimage 镜像文件，生成txt 文件
export HADOOP_HEAPSIZE=
hdfs oiv -i $IMAGE_NAME -o $IMAGE_NAME.txt -p Delimited

# . 将 txt 文件load进 hive 表中
hive -e "load data local inpath '$IMAGE_DIR/$IMAGE_NAME.txt' overwrite into table dataplatform.fsimage  partition (month='$cur_month',day='$cur_day');"

# . sql
hive -hivevar CUR_MONTH=$cur_month -hivevar CUR_DAY=$cur_day -f small_file_analysis.hql

rm -f fsimage*
echo "done"

脚本逻辑很简单：使用image分析工具iov将image转为txt格式的文件，然后将文件导入hive 表（dataplatform.fsimage），再通过hive命令执行sql，将sql查询结果插入分析结果表（dataplatform.small_file_report_day），最后删除fsimage开头的2个文件即可

注意：export HADOOP_HEAPSIZE=10240 要加上，不然会报堆内存溢出

设置堆内存大小之后执行：

small_file_analysis.hql 如下：

set mapreduce.job.queuename=root.production.gobblin;
set mapreduce.job.name=small_file_analysis;
set hive.exec.parallel=true;
set hive.exec.parallel.thread.number=4;
set mapreduce.map.memory.mb=1024;
set mapreduce.reduce.memory.mb=1024;

INSERT OVERWRITE TABLE dataplatform.small_file_report_day PARTITION (month='${CUR_MONTH}', day='${CUR_DAY}')
SELECT b.path as path, b.total_num as total_num  FROM (
SELECT path, total_num, root_path
FROM
(
SELECT
  SUBSTRING_INDEX(path, '/', 4) AS path,
  COUNT(1) AS total_num,
  SUBSTRING_INDEX(path, '/', 2) AS root_path
FROM
  dataplatform.fsimage
WHERE
  file_size < 1048576
  AND month='${CUR_MONTH}' AND day='${CUR_DAY}'
  AND SUBSTRING_INDEX(path, '/', 2) in ('/warehouse', '/tmp')
  GROUP BY SUBSTRING_INDEX(path, '/', 4),SUBSTRING_INDEX(path, '/', 2)
  UNION
SELECT
  SUBSTRING_INDEX(path, '/', 5) AS path,
  COUNT(1) as total_num,
  SUBSTRING_INDEX(path, '/', 3) AS root_path
FROM
  dataplatform.fsimage
WHERE
  file_size < 1048576
  AND month='${CUR_MONTH}' AND day='${CUR_DAY}'
  AND SUBSTRING_INDEX(path, '/', 3) = '/gobblin/source'
GROUP BY SUBSTRING_INDEX(path, '/', 5),SUBSTRING_INDEX(path, '/', 3)
) a

dataplatform.fsimage建表语句

CREATE TABLE `fsimage`(
  `path` string,
  `block_num` int,
  `create_time` string,
  `update_time` string,
  `block_size` bigint,
  `unknown1` int,
  `file_size` bigint,
  `unknown2` int,
  `unknown3` int,
  `permission` string,
  `user` string,
  `group` string)
PARTITIONED BY (
  `month` string,
  `day` string)
ROW FORMAT SERDE
  'org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe'
WITH SERDEPROPERTIES (
  'field.delim'='\t',
  'serialization.format'='\t')
STORED AS INPUTFORMAT
  'org.apache.hadoop.mapred.TextInputFormat'
OUTPUTFORMAT
  'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'
LOCATION
  'hdfs://emr-cluster/warehouse/dataplatform.db/fsimage'

dataplatform.small_file_report_day建表语句：

CREATE TABLE `dataplatform.small_file_report_day`(
  `path` string,
  `total_num` bigint)
PARTITIONED BY (
  `month` string,
  `day` string)
ROW FORMAT SERDE
  'org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe'
STORED AS INPUTFORMAT
  'org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat'
OUTPUTFORMAT
  'org.apache.hadoop.hive.ql.io.parquet.MapredParquetOutputFormat'
LOCATION
  'hdfs://emr-cluster/warehouse/dataplatform.db/small_file_report_day'
TBLPROPERTIES
  'parquet.compression'='SNAPPY'