m1.xlarge is a poorly provisioned instance type, with low PPS at the network layer. Can you try a type advertised to have "high" I/O performance?
On Wed, Jan 15, 2014 at 12:33 PM, Vladimir Rodionov <[email protected] > wrote: > This is something which needs to be definitely solved/fixed/resolved > > I am running YCSB benchmark on aws ec2 on a small HBase cluster > > 5 (m1.xlarge) as RS > 1 (m1.xlarge) hbase-master, zookeper > > Whirr 0.8.2 (with many hacks) is used to provision HBase. > > I am running 1 ycsb client (100% insert ops) throttled at 5K ops: > > ./bin/ycsb load hbase -P workloads/load20m -p columnfamily=family -s > -threads 10 -target 5000 > > OUTPUT: > > 1120 sec: 5602339 operations; 4999.7 current ops/sec; [INSERT > AverageLatency(us)=225.53] > 1130 sec: 5652117 operations; 4969.35 current ops/sec; [INSERT > AverageLatency(us)=203.31] > 1140 sec: 5665210 operations; 1309.04 current ops/sec; [INSERT > AverageLatency(us)=17.13] > 1150 sec: 5665210 operations; 0 current ops/sec; > 1160 sec: 5665210 operations; 0 current ops/sec; > 1170 sec: 5665210 operations; 0 current ops/sec; > 1180 sec: 5665210 operations; 0 current ops/sec; > 1190 sec: 5665210 operations; 0 current ops/sec; > 2014-01-15 15:19:34,139 Thread-2 WARN > [HConnectionManager$HConnectionImplementation] Failed all from > region=usertable,user6039,1389811852201.40518862106856d23b883e5d543d0b89., > hostname=ip-10-45-174-120.ec2.internal, port=60020 > java.util.concurrent.ExecutionException: java.net.SocketTimeoutException: > Call to ip-10-45-174-120.ec2.internal/10.45.174.120:60020 failed on > socket timeout exception: java.net.SocketTimeoutException: 60000 millis > timeout while waiting for channel to be ready for read. ch : > java.nio.channels.SocketChannel[connected > local=/10.180.211.173:42466remote=ip-10-45-174-120.ec2.internal/ > 10.45.174.120:60020] > at > java.util.concurrent.FutureTask$Sync.innerGet(FutureTask.java:252) > at java.util.concurrent.FutureTask.get(FutureTask.java:111) > at > org.apache.hadoop.hbase.client.HConnectionManager$HConnectionImplementation.processBatchCallback(HConnectionManager.java:1708) > at > org.apache.hadoop.hbase.client.HConnectionManager$HConnectionImplementation.processBatch(HConnectionManager.java:1560) > at > org.apache.hadoop.hbase.client.HTable.flushCommits(HTable.java:994) > at org.apache.hadoop.hbase.client.HTable.doPut(HTable.java:850) > at org.apache.hadoop.hbase.client.HTable.put(HTable.java:826) > at com.yahoo.ycsb.db.HBaseClient.update(HBaseClient.java:328) > at com.yahoo.ycsb.db.HBaseClient.insert(HBaseClient.java:357) > at com.yahoo.ycsb.DBWrapper.insert(DBWrapper.java:148) > at > com.yahoo.ycsb.workloads.CoreWorkload.doInsert(CoreWorkload.java:461) > at com.yahoo.ycsb.ClientThread.run(Client.java:269) > Caused by: java.net.SocketTimeoutException: Call to > ip-10-45-174-120.ec2.internal/10.45.174.120:60020 failed on socket > timeout exception: java.net.SocketTimeoutException: 60000 millis timeout > while waiting for channel to be ready for read. ch : > java.nio.channels.SocketChannel[connected > local=/10.180.211.173:42466remote=ip-10-45-174-120.ec2.internal/ > 10.45.174.120:60020] > at > org.apache.hadoop.hbase.ipc.HBaseClient.wrapException(HBaseClient.java:1043) > at > org.apache.hadoop.hbase.ipc.HBaseClient.call(HBaseClient.java:1016) > at > org.apache.hadoop.hbase.ipc.WritableRpcEngine$Invoker.invoke(WritableRpcEngine.java:87) > at com.sun.proxy.$Proxy5.multi(Unknown Source) > at > org.apache.hadoop.hbase.client.HConnectionManager$HConnectionImplementation$3$1.call(HConnectionManager.java:1537) > at > org.apache.hadoop.hbase.client.HConnectionManager$HConnectionImplementation$3$1.call(HConnectionManager.java:1535) > at > org.apache.hadoop.hbase.client.ServerCallable.withoutRetries(ServerCallable.java:229) > at > org.apache.hadoop.hbase.client.HConnectionManager$HConnectionImplementation$3.call(HConnectionManager.java:1544) > at > org.apache.hadoop.hbase.client.HConnectionManager$HConnectionImplementation$3.call(HConnectionManager.java:1532) > at > java.util.concurrent.FutureTask$Sync.innerRun(FutureTask.java:334) > at java.util.concurrent.FutureTask.run(FutureTask.java:166) > at > java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1146) > at > java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) > at java.lang.Thread.run(Thread.java:701) > > > SKIPPED A LOT > > > 1200 sec: 5674180 operations; 896.82 current ops/sec; [INSERT > AverageLatency(us)=7506.37] > 1210 sec: 6022326 operations; 34811.12 current ops/sec; [INSERT > AverageLatency(us)=1998.26] > 1220 sec: 6102627 operations; 8018.07 current ops/sec; [INSERT > AverageLatency(us)=395.11] > 1230 sec: 6152632 operations; 5000 current ops/sec; [INSERT > AverageLatency(us)=182.53] > 1240 sec: 6202641 operations; 4999.9 current ops/sec; [INSERT > AverageLatency(us)=201.76] > 1250 sec: 6252642 operations; 4999.6 current ops/sec; [INSERT > AverageLatency(us)=190.46] > 1260 sec: 6302653 operations; 5000.1 current ops/sec; [INSERT > AverageLatency(us)=212.31] > 1270 sec: 6352660 operations; 5000.2 current ops/sec; [INSERT > AverageLatency(us)=217.77] > 1280 sec: 6402731 operations; 5000.1 current ops/sec; [INSERT > AverageLatency(us)=195.83] > 1290 sec: 6452740 operations; 4999.9 current ops/sec; [INSERT > AverageLatency(us)=232.43] > 1300 sec: 6502743 operations; 4999.8 current ops/sec; [INSERT > AverageLatency(us)=290.52] > 1310 sec: 6552755 operations; 5000.2 current ops/sec; [INSERT > AverageLatency(us)=259.49] > > > As you can see here there is ~ 60 sec total write stall on a cluster which > I suppose 100% correlates with compactions started (minor) > > MAX_FILESIZE = 5GB > ## Regions of 'usertable' - 50 > > I would appreciate any advices on how to get rid of these stalls. 5K per > sec is quite moderate load even for 5 lousy AWS servers. Or it is not? > > Best regards, > Vladimir Rodionov > Principal Platform Engineer > Carrier IQ, www.carrieriq.com > e-mail: [email protected] > > > Confidentiality Notice: The information contained in this message, > including any attachments hereto, may be confidential and is intended to be > read only by the individual or entity to whom this message is addressed. If > the reader of this message is not the intended recipient or an agent or > designee of the intended recipient, please note that any review, use, > disclosure or distribution of this message or its attachments, in any form, > is strictly prohibited. If you have received this message in error, please > immediately notify the sender and/or [email protected] and > delete or destroy any copy of this message and its attachments. > -- Best regards, - Andy Problems worthy of attack prove their worth by hitting back. - Piet Hein (via Tom White)
