HDFS数据压缩&解压缩

hadoop jar /data/hadoop/hadoop-yum/share/hadoop/tools/lib/hadoop-streaming-2.7.2.jar \
    -Dmapred.reduce.tasks=6 \
    -Dmapred.map.tasks=25 \
    -Dmapred.output.compress=true \
    -Dmapred.compress.map.output=true \
    -Dmapred.output.compression.codec=org.apache.hadoop.io.compress.SnappyCodec \
    -input /apps/hive/archive/all/tracking/analytics/flume/FlumeData.1672585476778 \
    -output /apps/hive/archive/all/tracking/analytics/flume/lz4 \
    -mapper /bin/cat \
    -reducer /bin/cat \
    -inputformat org.apache.hadoop.mapred.TextInputFormat \
    -outputformat org.apache.hadoop.mapred.TextOutputFormat

hadoop jar /data/hadoop/hadoop-yum/share/hadoop/tools/lib/hadoop-streaming-2.7.2.jar \
    -Dmapred.reduce.tasks=6 \
    -Dmapred.map.tasks=25 \
    -Dmapred.output.compress=true \
    -Dmapred.uncompress.map.output=true \
    -Dmapred.output.uncompression.codec=org.apache.hadoop.io.compress.SnappyCodec \
    -input /apps/hive/archive/all/tracking/analytics/flume/FlumeData.1672585476778 \
    -output /apps/hive/archive/all/tracking/analytics/flume/lz4 \
    -mapper /bin/cat \
    -reducer /bin/cat \
    -inputformat org.apache.hadoop.mapred.TextInputFormat \
    -outputformat org.apache.hadoop.mapred.TextOutputFormat