Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- CREATE EXTERNAL TABLE `outbound.partitioned_orc_test`(
- `id` string COMMENT '',
- `messageid` string COMMENT '',
- `streamname` string COMMENT '',
- `subscriptionname` string COMMENT '',
- `keyword` string COMMENT '',
- `messagetype` string COMMENT '',
- `unixtime` bigint COMMENT '',
- `mid` string COMMENT '',
- `createddt` string COMMENT '',
- `indexproviderid` string COMMENT '',
- `siteid` string COMMENT '',
- `domain` string COMMENT '',
- `lang` string COMMENT '',
- `country` string COMMENT '',
- `crawleddt` string COMMENT '',
- `ip` string,
- `day` int
- )
- PARTITIONED BY (
- `customerid` int,
- `providerid` int,
- `year` int,
- `month` int
- )
- stored as ORC;
- for i in {-1..543}
- do
- for y in {2015..2018}
- do
- for m in {1..12}
- do
- beeline -u "jdbc:hive2://hdp-prod-master02.boardreader.com:2181,hdp-prod-master01.boardreader.com:2181,hdp-prod-master03.boardreader.com:2181/;serviceDiscoveryMode=zooKeeper;zooKeeperNamespace=hiveserver2" -n root -p root \
- -e"
- set mapreduce.job.name='conversion job partition $i $y $m';
- set tez.task.log.level=ERROR;
- set tez.am.log.level=ERROR;
- set tez.grouping.min-size=16777216;
- set tez.grouping.max-size=512000000;
- set hive.exec.reducers.max=10000;
- set tez.am.resource.memory.mb=24000;
- set hive.exec.dynamic.partition.mode=nonstrict;
- set hive.exec.dynamic.partition=true;
- set hive.exec.max.dynamic.partitions=1000000000;
- set hive.tez.container.size=3096;
- set hive.tez.java.opts=-Xmx2500m -XX:NewRatio=8 -XX:+UseNUMA -XX:+UseG1GC -XX:+ResizeTLAB -XX:+PrintGCDetails -verbose:gc -XX:+PrintGCTimeStamps;
- INSERT OVERWRITE TABLE outbound.partitioned_orc_test PARTITION (customerid, providerid, year, month)
- SELECT id, messageid, streamname, subscriptionname, keyword, messagetype, unixtime, mid, createddt, indexproviderid, siteid, domain, lang, country, crawleddt, ip, day, customerid, providerid, year, month
- FROM outbound.partitioned
- WHERE customerid=$i AND year=$y AND month=$m
- DISTRIBUTE BY customerid, providerid, year, month;"
- done
- done
- done
- hbase org.apache.hadoop.hbase.mapreduce.RowCounter
- 2018-02-09 14:55:06,159 [INFO] [AMRM Callback Handler Thread] |rm.YarnTaskSchedulerService|: Allocated: <memory:0, vCores:0> Free: <memory:688128, vCores:143> pendingRequests: 0 delayedContainers: 0 heartbeats: 2701 lastPreemptionHeartbeat: 2700
- 2018-02-09 14:55:56,841 [WARN] [ResponseProcessor for block BP-484199763-192.168.197.14-1444236781588:blk_1125819368_52080718] |hdfs.DFSClient|: DFSOutputStream ResponseProcessor exception for block BP-484199763-192.168.197.14-1444236781588:blk_1125819368_52080718
- java.io.EOFException: Premature EOF: no length prefix available
- at org.apache.hadoop.hdfs.protocolPB.PBHelper.vintPrefixed(PBHelper.java:2464)
- at org.apache.hadoop.hdfs.protocol.datatransfer.PipelineAck.readFields(PipelineAck.java:244)
- at org.apache.hadoop.hdfs.DFSOutputStream$DataStreamer$ResponseProcessor.run(DFSOutputStream.java:843)
- 2018-02-09 14:55:56,841 [WARN] [ResponseProcessor for block BP-484199763-192.168.197.14-1444236781588:blk_1125819369_52080719] |hdfs.DFSClient|: DFSOutputStream ResponseProcessor exception for block BP-484199763-192.168.197.14-1444236781588:blk_1125819369_52080719
- java.io.EOFException: Premature EOF: no length prefix available
- at org.apache.hadoop.hdfs.protocolPB.PBHelper.vintPrefixed(PBHelper.java:2464)
- at org.apache.hadoop.hdfs.protocol.datatransfer.PipelineAck.readFields(PipelineAck.java:244)
- at org.apache.hadoop.hdfs.DFSOutputStream$DataStreamer$ResponseProcessor.run(DFSOutputStream.java:843)
- 2018-02-09 14:55:56,844 [WARN] [DataStreamer for file /tmp/hive/hive/_tez_session_dir/720c7ac5-05b0-4f6d-b77a-be573ac27a1e/.tez/application_1518203762012_0005/recovery/1/summary block BP-484199763-192.168.197.14-1444236781588:blk_1125819368_52080718] |hdfs.DFSClient|: Error Recovery for block BP-484199763-192.168.197.14-1444236781588:blk_1125819368_52080718 in pipeline DatanodeInfoWithStorage[192.168.197.122:50010,DS-8c7c32b6-1df8-4f98-8c34-e0d5b98dfd53,DISK], DatanodeInfoWithStorage[192.168.197.114:50010,DS-64c48141-a07b-46ff-b272-1002c405a618,DISK], DatanodeInfoWithStorage[192.168.197.111:50010,DS-d132aa58-e22d-4d0c-804d-f03097c3496a,DISK]: bad datanode DatanodeInfoWithStorage[192.168.197.122:50010,DS-8c7c32b6-1df8-4f98-8c34-e0d5b98dfd53,DISK]
- 2018-02-09 14:55:56,844 [WARN] [DataStreamer for file /tmp/hive/hive/_tez_session_dir/720c7ac5-05b0-4f6d-b77a-be573ac27a1e/.tez/application_1518203762012_0005/recovery/1/dag_1518203762012_0005_1.recovery block BP-484199763-192.168.197.14-1444236781588:blk_1125819369_52080719] |hdfs.DFSClient|: Error Recovery for block BP-484199763-192.168.197.14-1444236781588:blk_1125819369_52080719 in pipeline DatanodeInfoWithStorage[192.168.197.122:50010,DS-8c7c32b6-1df8-4f98-8c34-e0d5b98dfd53,DISK], DatanodeInfoWithStorage[192.168.197.121:50010,DS-aa3c6c78-b9be-4cf3-b77c-847acdff008d,DISK], DatanodeInfoWithStorage[192.168.197.120:50010,DS-56de098a-13c2-4f66-b3a4-a5546371d5dd,DISK]: bad datanode DatanodeInfoWithStorage[192.168.197.122:50010,DS-8c7c32b6-1df8-4f98-8c34-e0d5b98dfd53,DISK]
- 2018-02-09 14:55:59,095 [INFO] [AMRM Callback Handler Thread] |rm.YarnTaskSchedulerService|: Allocated: <memory:0, vCores:0> Free: <memory:688128, vCores:143> pendingRequests: 0 delayedContainers: 0 heartbeats: 2751 lastPreemptionHeartbeat: 2750
- 2018-02-09 14:57:23,873 [INFO] [AMRM Callback Handler Thread] |rm.YarnTaskSchedulerService|: Allocated: <memory:0, vCores:0> Free: <memory:688128, vCores:143> pendingRequests: 0 delayedContainers: 0 heartbeats: 2801 lastPreemptionHeartbeat: 2800
- 2018-02-09 14:55:56,841 [WARN] [ResponseProcessor for block BP-484199763-192.168.197.14-1444236781588:blk_1125819368_52080718] |hdfs.DFSClient|: DFSOutputStream ResponseProcessor exception for block BP-484199763-192.168.197.14-1444236781588:blk_1125819368_52080718
- java.io.EOFException: Premature EOF: no length prefix available
- at org.apache.hadoop.hdfs.protocolPB.PBHelper.vintPrefixed(PBHelper.java:2464)
- at org.apache.hadoop.hdfs.protocol.datatransfer.PipelineAck.readFields(PipelineAck.java:244)
- at org.apache.hadoop.hdfs.DFSOutputStream$DataStreamer$ResponseProcessor.run(DFSOutputStream.java:843)
- 2018-02-09 14:55:56,841 [WARN] [ResponseProcessor for block BP-484199763-192.168.197.14-1444236781588:blk_1125819369_52080719] |hdfs.DFSClient|: DFSOutputStream ResponseProcessor exception for block BP-484199763-192.168.197.14-1444236781588:blk_1125819369_52080719
- java.io.EOFException: Premature EOF: no length prefix available
- at org.apache.hadoop.hdfs.protocolPB.PBHelper.vintPrefixed(PBHelper.java:2464)
- at org.apache.hadoop.hdfs.protocol.datatransfer.PipelineAck.readFields(PipelineAck.java:244)
- at org.apache.hadoop.hdfs.DFSOutputStream$DataStreamer$ResponseProcessor.run(DFSOutputStream.java:843)
- 2018-02-09 14:55:56,844 [WARN] [DataStreamer for file /tmp/hive/hive/_tez_session_dir/720c7ac5-05b0-4f6d-b77a-be573ac27a1e/.tez/application_1518203762012_0005/recovery/1/summary block BP-484199763-192.168.197.14-1444236781588:blk_1125819368_52080718] |hdfs.DFSClient|: Error Recovery for block BP-484199763-192.168.197.14-1444236781588:blk_1125819368_52080718 in pipeline DatanodeInfoWithStorage[192.168.197.122:50010,DS-8c7c32b6-1df8-4f98-8c34-e0d5b98dfd53,DISK], DatanodeInfoWithStorage[192.168.197.114:50010,DS-64c48141-a07b-46ff-b272-1002c405a618,DISK], DatanodeInfoWithStorage[192.168.197.111:50010,DS-d132aa58-e22d-4d0c-804d-f03097c3496a,DISK]: bad datanode DatanodeInfoWithStorage[192.168.197.122:50010,DS-8c7c32b6-1df8-4f98-8c34-e0d5b98dfd53,DISK]
- 2018-02-09 14:55:56,844 [WARN] [DataStreamer for file /tmp/hive/hive/_tez_session_dir/720c7ac5-05b0-4f6d-b77a-be573ac27a1e/.tez/application_1518203762012_0005/recovery/1/dag_1518203762012_0005_1.recovery block BP-484199763-192.168.197.14-1444236781588:blk_1125819369_52080719] |hdfs.DFSClient|: Error Recovery for block BP-484199763-192.168.197.14-1444236781588:blk_1125819369_52080719 in pipeline DatanodeInfoWithStorage[192.168.197.122:50010,DS-8c7c32b6-1df8-4f98-8c34-e0d5b98dfd53,DISK], DatanodeInfoWithStorage[192.168.197.121:50010,DS-aa3c6c78-b9be-4cf3-b77c-847acdff008d,DISK], DatanodeInfoWithStorage[192.168.197.120:50010,DS-56de098a-13c2-4f66-b3a4-a5546371d5dd,DISK]: bad datanode DatanodeInfoWithStorage[192.168.197.122:50010,DS-8c7c32b6-1df8-4f98-8c34-e0d5b98dfd53,DISK]
- 2018-02-09 14:55:59,095 [INFO] [AMRM Callback Handler Thread] |rm.YarnTaskSchedulerService|: Allocated: <memory:0, vCores:0> Free: <memory:688128, vCores:143> pendingRequests: 0 delayedContainers: 0 heartbeats: 2751 lastPreemptionHeartbeat: 2750
Add Comment
Please, Sign In to add comment