You are viewing a plain text version of this content. The canonical link for it is here.

Posted to dev@hbase.apache.org by Jean-Marc Spaggiari <je...@spaggiari.org> on 2013/04/18 17:13:19 UTC

Re: [VOTE] The 1st hbase 0.94.7 release candidate is available for download

Here is the PerformanceEvaluation comparison report:
http://www.spaggiari.org/media/blogs/hbase/pdf/performances_20130418.pdf

Summary:
- Filtered scan performances and sequential reads are consistant with
previous 0.94 releases;
- Scan range are about 3% slower;
- Random read are 7% faster;
- But random writes are 7% slower.


Basically, here is what I did:
- Downloaded the file, checked signature for both security and "regular"
distribution. Both fine.
- Decompressed regular distribution and checked the CHANGES.txt and
documentation content (few random pages).
- Ran it in standalone; checked the UI, the logs and ran all performance
evaluation scenarios.
- Ran HBCK few times before and after.
- Ran IntegrationTestLoadAndVerify (ROWS_WRITTEN=0;
REFERENCES_CHECKED=9855322). Not sure how to validate the results but I
will have expected REFERENCES_CHECKED to be 10000000.
- Ran IntegrationTestBigLinkedList (REFERENCED=6000000), sound right based
on the command line (Loop 2 1 3000000)
- Ran the test suite (org.apache.hadoop.hbase.catalog.TestMetaReaderEditor
failed the first time, I re-ran alone it and it passed. Re-ran the entire
test suite, failed at the same place.)


- Deployed it on 9 servers (8 RS, 1 master) and did a rolling-restart.
- Checked the logs, status, UI;
- Changed balancer to default balancer, stop hbase, merged all regions into
a single one, restarted;
- Checked HBCK, table status, logs, table regions (should have ony one),
etc.
- Ran major compaction on the small table from the shell, ran balancer,
checked the logs, checked the splits.
- Stopped the cluster, restored custom balancer, restarted, rebalanced,
checked transitions and logs.
- From shell, created a table; did few put, scan on the new and existing
tables, dropped table;
- Ran few different MR Job overnight, checked the results and logs.
- Ran IntegrationTestLoadAndVerify (ROWS_WRITTEN=0;
REFERENCES_CHECKED=9855185). Not sure how to validate the results but I
will have expected REFERENCES_CHECKED to be 10000000.
- Ran IntegrationTestBigLinkedList (REFERENCED=6000000), sound right based
on the command line (Loop 2 1 3000000)

Overall, +1 for me. All the comments are in the Google Spreadsheet.

But I think we should take a look at the random writes performances
degradation and to IntegrationTestLoadAnVerify results.

JM


2013/4/17 lars hofhansl <la...@apache.org>

> The 1st 0.94.7 RC is available for download at
> http://people.apache.org/~larsh/hbase-0.94.7-rc0/
>
> Signed with my code signing key: C7CFE328
>
> This RC has 71 issues resolved against it, contributed by 27 individuals.
> 0.94.7 is primarily a bug fix release. Notable exceptions include:
> HBASE-8176 Dynamic Schema Configurations
> HBASE-7801 Allow a deferred sync option per Mutation
>
> The full list of changes is available here:
> https://issues.apache.org/jira/browse/HBASE/fixforversion/12324039
>
> Please try out the RC, check out the doc, take it for a spin, etc, and
> vote +1/-1 by April 24th on whether we should release this as 0.94.7.
>
> The release testing spreadsheet is available here:
>
> https://docs.google.com/spreadsheet/ccc?key=0AvLqcVIqNtlTdG9jbVNmWmhyeGJZeUo4MUdIMEEweEE#gid=0
>
> Thanks.
>
> -- Lars

Re: [VOTE] The 1st hbase 0.94.7 release candidate is available for download

Posted by Jean-Marc Spaggiari <je...@spaggiari.org>.

Hi Lars,

I used the tarballs from the distributions. I did not build them myself.

I directly used
http://people.apache.org/~larsh/hbase-0.94.7-rc0/hbase-0.94.7.tar.gz
and http://apache.mirror.rafal.ca/hbase/hbase-0.94.6.1/hbase-0.94.6.1.tar.gz

I used them without any modification. I simply exported the JAVA_HOME
variable, started HBase and ran the PE application.

I tried with more lines (128M instead of 1M) but it failed on timeout
(most probably because of GC). I will retry today with only 2M and
increase slowly to see if I see any difference.

JM

2013/4/20 lars hofhansl <la...@apache.org>:
> I checked with a profile. Nothing sticks out.
> Did you build the tarballs in both cases?
>
> -- Lars
>
> ________________________________
> From: lars hofhansl <la...@apache.org>
> To: Jean-Marc Spaggiari <je...@spaggiari.org>; "dev@hbase.apache.org"
> <de...@hbase.apache.org>
> Sent: Saturday, April 20, 2013 2:56 PM
>
> Subject: Re: [VOTE] The 1st hbase 0.94.7 release candidate is available for
> download
>
> Hmm... Does a profile run point to anything?
>
> -- Lars
>
>
>
> ________________________________
> From: Jean-Marc Spaggiari <je...@spaggiari.org>
> To: dev@hbase.apache.org; lars hofhansl <la...@apache.org>
> Sent: Saturday, April 20, 2013 7:35 AM
> Subject: Re: [VOTE] The 1st hbase 0.94.7 release candidate is available for
> download
>
>
> So, here are the new results.
>
> I re-ran the RandomWriteTest with JDK 1.6 and JDK 1.7 on the same
> computer. I also re-ran it on another one on a SSD with 32GB ram and 8
> cores with JDK 1.6. All giving the same trend.
>
> I will re-run again with more rows and then retry with more than 1
> client and compare.
>
> JM
>
> Summary:
>                                     Average rows/seconds
> Computer1    JDK 1.7    0.94.6.1    30112
> Computer1    JDK 1.7    0.94.7    28431
>
> Computer1    JDK 1.6    0.94.6.1    26384
> Computer1    JDK 1.6    0.94.7    24293
>
> Computer2    JDK 1.6    0.94.6.1    24548
> Computer2    JDK 1.6    0.94.7    22568
>
> Details:
> Machine 1 - JDK 1.7
> jmspaggi@hbasetest:~/hbase$ cat hbase-0.94.6.1/output.txt  | grep
> Finished | grep RandomWriteTest
> 13/04/19 20:58:13 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 34481
> at offset 0 for 1048576 rows
> 13/04/19 21:00:06 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 35055
> at offset 0 for 1048576 rows
> 13/04/19 21:02:00 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 35890
> at offset 0 for 1048576 rows
> 13/04/19 21:03:52 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 34207
> at offset 0 for 1048576 rows
> 13/04/19 21:05:42 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 34898
> at offset 0 for 1048576 rows
> 13/04/19 21:07:36 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 36355
> at offset 0 for 1048576 rows
> 13/04/19 21:09:28 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 34613
> at offset 0 for 1048576 rows
> 13/04/19 21:11:22 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 34398
> at offset 0 for 1048576 rows
> 13/04/19 21:13:15 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 35092
> at offset 0 for 1048576 rows
> 13/04/19 21:15:08 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 33852
> at offset 0 for 1048576 rows
> jmspaggi@hbasetest:~/hbase$ cat hbase-0.94.7/output.txt  | grep
> Finished | grep RandomWriteTest
> 13/04/19 17:10:26 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 36443
> at offset 0 for 1048576 rows
> 13/04/19 17:12:21 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 37071
> at offset 0 for 1048576 rows
> 13/04/19 17:14:17 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 37143
> at offset 0 for 1048576 rows
> 13/04/19 17:16:11 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 37561
> at offset 0 for 1048576 rows
> 13/04/19 17:18:05 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 37082
> at offset 0 for 1048576 rows
> 13/04/19 17:20:01 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 36667
> at offset 0 for 1048576 rows
> 13/04/19 17:21:55 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 36580
> at offset 0 for 1048576 rows
> 13/04/19 17:23:48 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 36708
> at offset 0 for 1048576 rows
> 13/04/19 17:25:42 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 36773
> at offset 0 for 1048576 rows
> 13/04/19 17:27:35 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 37035
> at offset 0 for 1048576 rows
>
> Machine 1 - JDK 1.6
> jmspaggi@hbasetest:~/hbase$ cat hbase-0.94.6.1/output.txt  | grep
> Finished | grep RandomWriteTest
> 13/04/20 08:24:03 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 39531
> at offset 0 for 1048576 rows
> 13/04/20 08:26:01 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 42207
> at offset 0 for 1048576 rows
> 13/04/20 08:27:57 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 39840
> at offset 0 for 1048576 rows
> 13/04/20 08:29:53 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 39202
> at offset 0 for 1048576 rows
> 13/04/20 08:31:50 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 40973
> at offset 0 for 1048576 rows
> 13/04/20 08:33:50 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 40906
> at offset 0 for 1048576 rows
> 13/04/20 08:35:49 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 39333
> at offset 0 for 1048576 rows
> 13/04/20 08:37:44 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 39185
> at offset 0 for 1048576 rows
> 13/04/20 08:39:41 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 39071
> at offset 0 for 1048576 rows
> 13/04/20 08:41:36 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 38693
> at offset 0 for 1048576 rows
> jmspaggi@hbasetest:~/hbase$ cat hbase-0.94.7/output.txt  | grep
> Finished | grep RandomWriteTest
> 13/04/20 08:43:37 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 43526
> at offset 0 for 1048576 rows
> 13/04/20 08:45:39 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 43593
> at offset 0 for 1048576 rows
> 13/04/20 08:47:40 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 42576
> at offset 0 for 1048576 rows
> 13/04/20 08:49:39 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 43450
> at offset 0 for 1048576 rows
> 13/04/20 08:51:41 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 43436
> at offset 0 for 1048576 rows
> 13/04/20 08:53:44 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 44171
> at offset 0 for 1048576 rows
> 13/04/20 08:55:44 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 42831
> at offset 0 for 1048576 rows
> 13/04/20 08:57:43 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 42931
> at offset 0 for 1048576 rows
> 13/04/20 08:59:42 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 42686
> at offset 0 for 1048576 rows
> 13/04/20 09:01:40 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 42879
> at offset 0 for 1048576 rows
>
>
> Machine 2 - JDK 1.6
> jmspaggi@buldo:~/foo$ cat hbase-0.94.6.1/output.txt  | grep Finished |
> grep RandomWriteTest
> 13/04/20 08:32:18 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 47083
> at offset 0 for 1048576 rows
> 13/04/20 08:34:18 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 42673
> at offset 0 for 1048576 rows
> 13/04/20 08:36:19 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 43062
> at offset 0 for 1048576 rows
> 13/04/20 08:38:15 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 41960
> at offset 0 for 1048576 rows
> 13/04/20 08:40:15 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 42788
> at offset 0 for 1048576 rows
> 13/04/20 08:42:13 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 42635
> at offset 0 for 1048576 rows
> 13/04/20 08:44:13 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 43223
> at offset 0 for 1048576 rows
> 13/04/20 08:46:10 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 42467
> at offset 0 for 1048576 rows
> 13/04/20 08:48:07 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 42322
> at offset 0 for 1048576 rows
> 13/04/20 08:50:02 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 42570
> at offset 0 for 1048576 rows
> jmspaggi@buldo:~/foo$ cat hbase-0.94.7/output.txt  | grep Finished |
> grep RandomWriteTest
> 13/04/20 08:52:04 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 47490
> at offset 0 for 1048576 rows
> 13/04/20 08:54:02 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 46620
> at offset 0 for 1048576 rows
> 13/04/20 08:56:04 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 46709
> at offset 0 for 1048576 rows
> 13/04/20 08:58:01 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 46191
> at offset 0 for 1048576 rows
> 13/04/20 09:00:01 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 47665
> at offset 0 for 1048576 rows
> 13/04/20 09:01:57 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 45665
> at offset 0 for 1048576 rows
> 13/04/20 09:03:56 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 47238
> at offset 0 for 1048576 rows
> 13/04/20 09:06:00 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 46762
> at offset 0 for 1048576 rows
> 13/04/20 09:07:56 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 45124
> at offset 0 for 1048576 rows
> 13/04/20 09:09:54 INFO hbase.PerformanceEvaluation: Finished class
> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 44909
> at offset 0 for 1048576 rows
>
>
> 2013/4/20 Jean-Marc Spaggiari <je...@spaggiari.org>
>>
>> Hi Lars,
>>
>> I just re-ran both of them again. Here are the results:
>> jmspaggi@hbasetest:~/hbase$ cat hbase-0.94.6.1/output.txt  | grep Finished
>> | grep RandomWriteTest
>> 13/04/19 20:58:13 INFO hbase.PerformanceEvaluation: Finished class
>> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 34481ms at
>> offset 0 for 1048576 rows
>> 13/04/19 21:00:06 INFO hbase.PerformanceEvaluation: Finished class
>> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 35055ms at
>> offset 0 for 1048576 rows
>> 13/04/19 21:02:00 INFO hbase.PerformanceEvaluation: Finished class
>> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 35890ms at
>> offset 0 for 1048576 rows
>> 13/04/19 21:03:52 INFO hbase.PerformanceEvaluation: Finished class
>> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 34207ms at
>> offset 0 for 1048576 rows
>> 13/04/19 21:05:42 INFO hbase.PerformanceEvaluation: Finished class
>> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 34898ms at
>> offset 0 for 1048576 rows
>> 13/04/19 21:07:36 INFO hbase.PerformanceEvaluation: Finished class
>> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 36355ms at
>> offset 0 for 1048576 rows
>> 13/04/19 21:09:28 INFO hbase.PerformanceEvaluation: Finished class
>> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 34613ms at
>> offset 0 for 1048576 rows
>> 13/04/19 21:11:22 INFO hbase.PerformanceEvaluation: Finished class
>> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 34398ms at
>> offset 0 for 1048576 rows
>> 13/04/19 21:13:15 INFO hbase.PerformanceEvaluation: Finished class
>> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 35092ms at
>> offset 0 for 1048576 rows
>> 13/04/19 21:15:08 INFO hbase.PerformanceEvaluation: Finished class
>> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 33852ms at
>> offset 0 for 1048576 rows
>> jmspaggi@hbasetest:~/hbase$ cat hbase-0.94.7/output.txt  | grep Finished |
>> grep RandomWriteTest
>> 13/04/19 17:10:26 INFO hbase.PerformanceEvaluation: Finished class
>> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 36443ms at
>> offset 0 for 1048576 rows
>> 13/04/19 17:12:21 INFO hbase.PerformanceEvaluation: Finished class
>> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 37071ms at
>> offset 0 for 1048576 rows
>> 13/04/19 17:14:17 INFO hbase.PerformanceEvaluation: Finished class
>> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 37143ms at
>> offset 0 for 1048576 rows
>> 13/04/19 17:16:11 INFO hbase.PerformanceEvaluation: Finished class
>> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 37561ms at
>> offset 0 for 1048576 rows
>> 13/04/19 17:18:05 INFO hbase.PerformanceEvaluation: Finished class
>> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 37082ms at
>> offset 0 for 1048576 rows
>> 13/04/19 17:20:01 INFO hbase.PerformanceEvaluation: Finished class
>> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 36667ms at
>> offset 0 for 1048576 rows
>> 13/04/19 17:21:55 INFO hbase.PerformanceEvaluation: Finished class
>> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 36580ms at
>> offset 0 for 1048576 rows
>> 13/04/19 17:23:48 INFO hbase.PerformanceEvaluation: Finished class
>> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 36708ms at
>> offset 0 for 1048576 rows
>> 13/04/19 17:25:42 INFO hbase.PerformanceEvaluation: Finished class
>> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 36773ms at
>> offset 0 for 1048576 rows
>> 13/04/19 17:27:35 INFO hbase.PerformanceEvaluation: Finished class
>> org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 37035ms at
>> offset 0 for 1048576 rows
>>
>> I copied the log4j config from one to the other one to make sure they are
>> logging the same thing. They are both ran on a single node standalone
>> dedicated computer. Here is the command line I used:
>> echo Test starting for randomWrite
>> for i in {1..10}; do echo; echo -n $i ; rm -rf /tmp/*; bin/start-hbase.sh;
>> sleep 60; bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation
>> randomWrite 1; bin/stop-hbase.sh; done &>> output.txt
>>
>> Computer is a 4 cores 4.2Ghz 16G with 60GB regular SATA-I hard drive.
>>
>> I will re-run the tests on another computer with different specs to figure
>> if the hard drive is impacting the results.
>>
>> But so far, 0.94.7 is still slower for me.
>>
>> JM
>>
>>
>> 2013/4/19 lars hofhansl <la...@apache.org>
>>>
>>> Thanks JM.
>>>
>>> I ran PE locally, and between 0.94.6.1 and 0.94.7 I do not see any
>>> systematic slowdown for the random write test.
>>> In fact I had the fastest run in 0.94.7 (32.6s) and the slowest one in
>>> 0.94.6.1 (39.5s).
>>>
>>> Variance of that test is very high (both in 0.94.6.1 and 0.94.7).
>>>
>>>
>>> My test setup is single node install of HBase/Hadoop/ZK.
>>>
>>> -- Lars
>>>
>>>
>>>
>>> ________________________________
>>>  From: Jean-Marc Spaggiari <je...@spaggiari.org>
>>> To: dev@hbase.apache.org; lars hofhansl <la...@apache.org>
>>> Sent: Thursday, April 18, 2013 8:13 AM
>>> Subject: Re: [VOTE] The 1st hbase 0.94.7 release candidate is available
>>> for download
>>>
>>>
>>> Here is the PerformanceEvaluation comparison report:
>>> http://www.spaggiari.org/media/blogs/hbase/pdf/performances_20130418.pdf
>>>
>>> Summary:
>>> - Filtered scan performances and sequential reads are consistant with
>>> previous 0.94 releases;
>>> - Scan range are about 3% slower;
>>> - Random read are 7% faster;
>>> - But random writes are 7% slower.
>>>
>>>
>>> Basically, here is what I did:
>>> - Downloaded the file, checked signature for both security and "regular"
>>> distribution. Both fine.
>>> - Decompressed regular distribution and checked the CHANGES.txt and
>>> documentation content (few random pages).
>>> - Ran it in standalone; checked the UI, the logs and ran all performance
>>> evaluation scenarios.
>>> - Ran HBCK few times before and after.
>>> - Ran IntegrationTestLoadAndVerify (ROWS_WRITTEN=0;
>>> REFERENCES_CHECKED=9855322). Not sure how to validate the results but I
>>> will have expected REFERENCES_CHECKED to be 10000000.
>>> - Ran IntegrationTestBigLinkedList (REFERENCED=6000000), sound right
>>> based
>>> on the command line (Loop 2 1 3000000)
>>> - Ran the test suite
>>> (org.apache.hadoop.hbase.catalog.TestMetaReaderEditor
>>> failed the first time, I re-ran alone it and it passed. Re-ran the entire
>>> test suite, failed at the same place.)
>>>
>>>
>>> - Deployed it on 9 servers (8 RS, 1 master) and did a rolling-restart.
>>> - Checked the logs, status, UI;
>>> - Changed balancer to default balancer, stop hbase, merged all regions
>>> into
>>> a single one, restarted;
>>> - Checked HBCK, table status, logs, table regions (should have ony one),
>>> etc.
>>> - Ran major compaction on the small table from the shell, ran balancer,
>>> checked the logs, checked the splits.
>>> - Stopped the cluster, restored custom balancer, restarted, rebalanced,
>>> checked transitions and logs.
>>> - From shell, created a table; did few put, scan on the new and existing
>>> tables, dropped table;
>>> - Ran few different MR Job overnight, checked the results and logs.
>>> - Ran IntegrationTestLoadAndVerify (ROWS_WRITTEN=0;
>>> REFERENCES_CHECKED=9855185). Not sure how to validate the results but I
>>> will have expected REFERENCES_CHECKED to be 10000000.
>>> - Ran IntegrationTestBigLinkedList (REFERENCED=6000000), sound right
>>> based
>>> on the command line (Loop 2 1 3000000)
>>>
>>> Overall, +1 for me. All the comments are in the Google Spreadsheet.
>>>
>>> But I think we should take a look at the random writes performances
>>> degradation and to IntegrationTestLoadAnVerify results.
>>>
>>> JM
>>>
>>>
>>> 2013/4/17 lars hofhansl <la...@apache.org>
>>>
>>> > The 1st 0.94.7 RC is available for download at
>>> > http://people.apache.org/~larsh/hbase-0.94.7-rc0/
>>> >
>>> > Signed with my code signing key: C7CFE328
>>> >
>>> > This RC has 71 issues resolved against it, contributed by 27
>>> > individuals.
>>> > 0.94.7 is primarily a bug fix release. Notable exceptions include:
>>> > HBASE-8176 Dynamic Schema Configurations
>>> > HBASE-7801 Allow a deferred sync option per Mutation
>>> >
>>> > The full list of changes is available here:
>>> > https://issues.apache.org/jira/browse/HBASE/fixforversion/12324039
>>> >
>>> > Please try out the RC, check out the doc, take it for a spin, etc, and
>>> > vote +1/-1 by April 24th on whether we should release this as 0.94.7.
>>> >
>>> > The release testing spreadsheet is available here:
>>> >
>>> >
>>> > https://docs.google.com/spreadsheet/ccc?key=0AvLqcVIqNtlTdG9jbVNmWmhyeGJZeUo4MUdIMEEweEE#gid=0
>>> >
>>> > Thanks.
>>> >
>>> > -- Lars
>>
>>
>

Re: [VOTE] The 1st hbase 0.94.7 release candidate is available for download

Posted by lars hofhansl <la...@apache.org>.

I checked with a profile. Nothing sticks out.
Did you build the tarballs in both cases?


-- Lars



________________________________
 From: lars hofhansl <la...@apache.org>
To: Jean-Marc Spaggiari <je...@spaggiari.org>; "dev@hbase.apache.org" <de...@hbase.apache.org> 
Sent: Saturday, April 20, 2013 2:56 PM
Subject: Re: [VOTE] The 1st hbase 0.94.7 release candidate is available for download
 

Hmm... Does a profile run point to anything?

-- Lars



________________________________
From: Jean-Marc Spaggiari <je...@spaggiari.org>
To: dev@hbase.apache.org; lars hofhansl <la...@apache.org> 
Sent: Saturday, April 20, 2013 7:35 AM
Subject: Re: [VOTE] The 1st hbase 0.94.7 release candidate is available for download


So, here are the new results.

I re-ran the RandomWriteTest with JDK 1.6 and JDK 1.7 on the same
computer. I also re-ran it on another one on a SSD with 32GB ram and 8
cores with JDK 1.6. All giving the same trend.

I will re-run again with more rows and then retry with more than 1
client and compare.

JM

Summary:
                                    Average rows/seconds
Computer1    JDK 1.7    0.94.6.1    30112
Computer1    JDK 1.7    0.94.7    28431
            
Computer1    JDK 1.6    0.94.6.1    26384
Computer1    JDK 1.6    0.94.7    24293
            
Computer2    JDK 1.6    0.94.6.1    24548
Computer2    JDK 1.6    0.94.7    22568

Details:
Machine 1 - JDK 1.7
jmspaggi@hbasetest:~/hbase$ cat hbase-0.94.6.1/output.txt  | grep
Finished | grep RandomWriteTest
13/04/19 20:58:13 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 34481
at offset 0 for 1048576 rows
13/04/19 21:00:06 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 35055
at offset 0 for 1048576 rows
13/04/19 21:02:00 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 35890
at offset 0 for 1048576 rows
13/04/19 21:03:52 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 34207
at offset 0 for 1048576 rows
13/04/19 21:05:42 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 34898
at offset 0 for 1048576 rows
13/04/19 21:07:36 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 36355
at offset 0 for 1048576 rows
13/04/19 21:09:28 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 34613
at offset 0 for 1048576 rows
13/04/19 21:11:22 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 34398
at offset 0 for 1048576 rows
13/04/19 21:13:15 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 35092
at offset 0 for 1048576 rows
13/04/19 21:15:08 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 33852
at offset 0 for 1048576 rows
jmspaggi@hbasetest:~/hbase$ cat hbase-0.94.7/output.txt  | grep
Finished | grep RandomWriteTest
13/04/19 17:10:26 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 36443
at offset 0 for 1048576 rows
13/04/19 17:12:21 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 37071
at offset 0 for 1048576 rows
13/04/19 17:14:17 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 37143
at offset 0 for 1048576 rows
13/04/19 17:16:11 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 37561
at offset 0 for 1048576 rows
13/04/19 17:18:05 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 37082
at offset 0 for 1048576 rows
13/04/19 17:20:01 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 36667
at offset 0 for 1048576 rows
13/04/19 17:21:55 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 36580
at offset 0 for 1048576 rows
13/04/19 17:23:48 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 36708
at offset 0 for 1048576 rows
13/04/19 17:25:42 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 36773
at offset 0 for 1048576 rows
13/04/19 17:27:35 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 37035
at offset 0 for 1048576 rows

Machine 1 - JDK 1.6
jmspaggi@hbasetest:~/hbase$ cat hbase-0.94.6.1/output.txt  | grep
Finished | grep RandomWriteTest
13/04/20 08:24:03 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 39531
at offset 0 for 1048576 rows
13/04/20 08:26:01 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 42207
at offset 0 for 1048576 rows
13/04/20 08:27:57 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 39840
at offset 0 for 1048576 rows
13/04/20 08:29:53 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 39202
at offset 0 for 1048576 rows
13/04/20 08:31:50 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 40973
at offset 0 for 1048576 rows
13/04/20 08:33:50 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 40906
at offset 0 for 1048576 rows
13/04/20 08:35:49 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 39333
at offset 0 for 1048576 rows
13/04/20 08:37:44 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 39185
at offset 0 for 1048576 rows
13/04/20 08:39:41 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 39071
at offset 0 for 1048576 rows
13/04/20 08:41:36 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 38693
at offset 0 for 1048576 rows
jmspaggi@hbasetest:~/hbase$ cat hbase-0.94.7/output.txt  | grep
Finished | grep RandomWriteTest
13/04/20 08:43:37 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 43526
at offset 0 for 1048576 rows
13/04/20 08:45:39 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 43593
at offset 0 for 1048576 rows
13/04/20 08:47:40 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 42576
at offset 0 for 1048576 rows
13/04/20 08:49:39 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 43450
at offset 0 for 1048576 rows
13/04/20 08:51:41 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 43436
at offset 0 for 1048576 rows
13/04/20 08:53:44 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 44171
at offset 0 for 1048576 rows
13/04/20 08:55:44 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 42831
at offset 0 for 1048576 rows
13/04/20 08:57:43 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 42931
at offset 0 for 1048576 rows
13/04/20 08:59:42 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 42686
at offset 0 for 1048576 rows
13/04/20 09:01:40 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 42879
at offset 0 for 1048576 rows


Machine 2 - JDK 1.6
jmspaggi@buldo:~/foo$ cat hbase-0.94.6.1/output.txt  | grep Finished |
grep RandomWriteTest
13/04/20 08:32:18 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 47083
at offset 0 for 1048576 rows
13/04/20 08:34:18 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 42673
at offset 0 for 1048576 rows
13/04/20 08:36:19 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 43062
at offset 0 for 1048576 rows
13/04/20 08:38:15 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 41960
at offset 0 for 1048576 rows
13/04/20 08:40:15 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 42788
at offset 0 for 1048576 rows
13/04/20 08:42:13 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 42635
at offset 0 for 1048576 rows
13/04/20 08:44:13 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 43223
at offset 0 for 1048576 rows
13/04/20 08:46:10 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 42467
at offset 0 for 1048576 rows
13/04/20 08:48:07 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 42322
at offset 0 for 1048576 rows
13/04/20 08:50:02 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 42570
at offset 0 for 1048576 rows
jmspaggi@buldo:~/foo$ cat hbase-0.94.7/output.txt  | grep Finished |
grep RandomWriteTest
13/04/20 08:52:04 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 47490
at offset 0 for 1048576 rows
13/04/20 08:54:02 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 46620
at offset 0 for 1048576 rows
13/04/20 08:56:04 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 46709
at offset 0 for 1048576 rows
13/04/20 08:58:01 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 46191
at offset 0 for 1048576 rows
13/04/20 09:00:01 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 47665
at offset 0 for 1048576 rows
13/04/20 09:01:57 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 45665
at offset 0 for 1048576 rows
13/04/20 09:03:56 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 47238
at offset 0 for 1048576 rows
13/04/20 09:06:00 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 46762
at offset 0 for 1048576 rows
13/04/20 09:07:56 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 45124
at offset 0 for 1048576 rows
13/04/20 09:09:54 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 44909
at offset 0 for 1048576 rows


2013/4/20 Jean-Marc Spaggiari <je...@spaggiari.org>
>
> Hi Lars,
>
> I just re-ran both of them again. Here are the results:
> jmspaggi@hbasetest:~/hbase$ cat hbase-0.94.6.1/output.txt  | grep Finished | grep RandomWriteTest
> 13/04/19 20:58:13 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 34481ms at offset 0 for 1048576 rows
> 13/04/19 21:00:06 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 35055ms at offset 0 for 1048576 rows
> 13/04/19 21:02:00 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 35890ms at offset 0 for 1048576 rows
> 13/04/19 21:03:52 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 34207ms at offset 0 for 1048576 rows
> 13/04/19 21:05:42 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 34898ms at offset 0 for 1048576 rows
> 13/04/19 21:07:36 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 36355ms at offset 0 for 1048576 rows
> 13/04/19 21:09:28 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 34613ms at offset 0 for 1048576 rows
> 13/04/19 21:11:22 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 34398ms at offset 0 for 1048576 rows
> 13/04/19 21:13:15 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 35092ms at offset 0 for 1048576 rows
> 13/04/19 21:15:08 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 33852ms at offset 0 for 1048576 rows
> jmspaggi@hbasetest:~/hbase$ cat hbase-0.94.7/output.txt  | grep Finished | grep RandomWriteTest
> 13/04/19 17:10:26 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 36443ms at offset 0 for 1048576 rows
> 13/04/19 17:12:21 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 37071ms at offset 0 for 1048576 rows
> 13/04/19 17:14:17 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 37143ms at offset 0 for 1048576 rows
> 13/04/19 17:16:11 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 37561ms at offset 0 for 1048576 rows
> 13/04/19 17:18:05 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 37082ms at offset 0 for 1048576 rows
> 13/04/19 17:20:01 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 36667ms at offset 0 for 1048576 rows
> 13/04/19 17:21:55 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 36580ms at offset 0 for 1048576 rows
> 13/04/19 17:23:48 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 36708ms at offset 0 for 1048576 rows
> 13/04/19 17:25:42 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 36773ms at offset 0 for 1048576 rows
> 13/04/19 17:27:35 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 37035ms at offset 0 for 1048576 rows
>
> I copied the log4j config from one to the other one to make sure they are logging the same thing. They are both ran on a single node standalone dedicated computer. Here is the command line I used:
> echo Test starting for randomWrite
> for i in {1..10}; do echo; echo -n $i ; rm -rf /tmp/*; bin/start-hbase.sh; sleep 60; bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation randomWrite 1; bin/stop-hbase.sh; done &>> output.txt
>
> Computer is a 4 cores 4.2Ghz 16G with 60GB regular SATA-I hard drive.
>
> I will re-run the tests on another computer with different specs to figure if the hard drive is impacting the results.
>
> But so far, 0.94.7 is still slower for me.
>
> JM
>
>
> 2013/4/19 lars hofhansl <la...@apache.org>
>>
>> Thanks JM.
>>
>> I ran PE locally, and between 0.94.6.1 and 0.94.7 I do not see any systematic slowdown for the random write test.
>> In fact I had the fastest run in 0.94.7 (32.6s) and the slowest one in 0.94.6.1 (39.5s).
>>
>> Variance of that test is very high (both in 0.94.6.1 and 0.94.7).
>>
>>
>> My test setup is single node install of HBase/Hadoop/ZK.
>>
>> -- Lars
>>
>>
>>
>> ________________________________
>>  From: Jean-Marc Spaggiari <je...@spaggiari.org>
>> To: dev@hbase.apache.org; lars hofhansl <la...@apache.org>
>> Sent: Thursday, April 18, 2013 8:13 AM
>> Subject: Re: [VOTE] The 1st hbase 0.94.7 release candidate is available for download
>>
>>
>> Here is the PerformanceEvaluation comparison report:
>> http://www.spaggiari.org/media/blogs/hbase/pdf/performances_20130418.pdf
>>
>> Summary:
>> - Filtered scan performances and sequential reads are consistant with
>> previous 0.94 releases;
>> - Scan range are about 3% slower;
>> - Random read are 7% faster;
>> - But random writes are 7% slower.
>>
>>
>> Basically, here is what I did:
>> - Downloaded the file, checked signature for both security and "regular"
>> distribution. Both fine.
>> - Decompressed regular distribution and checked the CHANGES.txt and
>> documentation content (few random pages).
>> - Ran it in standalone; checked the UI, the logs and ran all performance
>> evaluation scenarios.
>> - Ran HBCK few times before and after.
>> - Ran IntegrationTestLoadAndVerify (ROWS_WRITTEN=0;
>> REFERENCES_CHECKED=9855322). Not sure how to validate the results but I
>> will have expected REFERENCES_CHECKED to be 10000000.
>> - Ran IntegrationTestBigLinkedList (REFERENCED=6000000), sound right based
>> on the command line (Loop 2 1 3000000)
>> - Ran the test suite (org.apache.hadoop.hbase.catalog.TestMetaReaderEditor
>> failed the first time, I re-ran alone it and it passed. Re-ran the entire
>> test suite, failed at the same place.)
>>
>>
>> - Deployed it on 9 servers (8 RS, 1 master) and did a rolling-restart.
>> - Checked the logs, status, UI;
>> - Changed balancer to default balancer, stop hbase, merged all regions into
>> a single one, restarted;
>> - Checked HBCK, table status, logs, table regions (should have ony one),
>> etc.
>> - Ran major compaction on the small table from the shell, ran balancer,
>> checked the logs, checked the splits.
>> - Stopped the cluster, restored custom balancer, restarted, rebalanced,
>> checked transitions and logs.
>> - From shell, created a table; did few put, scan on the new and existing
>> tables, dropped table;
>> - Ran few different MR Job overnight, checked the results and logs.
>> - Ran IntegrationTestLoadAndVerify (ROWS_WRITTEN=0;
>> REFERENCES_CHECKED=9855185). Not sure how to validate the results but I
>> will have expected REFERENCES_CHECKED to be 10000000.
>> - Ran IntegrationTestBigLinkedList (REFERENCED=6000000), sound right based
>> on the command line (Loop 2 1 3000000)
>>
>> Overall, +1 for me. All the comments are in the Google Spreadsheet.
>>
>> But I think we should take a look at the random writes performances
>> degradation and to IntegrationTestLoadAnVerify results.
>>
>> JM
>>
>>
>> 2013/4/17 lars hofhansl <la...@apache.org>
>>
>> > The 1st 0.94.7 RC is available for download at
>> > http://people.apache.org/~larsh/hbase-0.94.7-rc0/
>> >
>> > Signed with my code signing key: C7CFE328
>> >
>> > This RC has 71 issues resolved against it, contributed by 27 individuals.
>> > 0.94.7 is primarily a bug fix release. Notable exceptions include:
>> > HBASE-8176 Dynamic Schema Configurations
>> > HBASE-7801 Allow a deferred sync option per Mutation
>> >
>> > The full list of changes is available here:
>> > https://issues.apache.org/jira/browse/HBASE/fixforversion/12324039
>> >
>> > Please try out the RC, check out the doc, take it for a spin, etc, and
>> > vote +1/-1 by April 24th on whether we should release this as 0.94.7.
>> >
>> > The release testing spreadsheet is available here:
>> >
>> > https://docs.google.com/spreadsheet/ccc?key=0AvLqcVIqNtlTdG9jbVNmWmhyeGJZeUo4MUdIMEEweEE#gid=0
>> >
>> > Thanks.
>> >
>> > -- Lars
>
>

Re: [VOTE] The 1st hbase 0.94.7 release candidate is available for download

Posted by lars hofhansl <la...@apache.org>.

Hmm... Does a profile run point to anything?

-- Lars



________________________________
 From: Jean-Marc Spaggiari <je...@spaggiari.org>
To: dev@hbase.apache.org; lars hofhansl <la...@apache.org> 
Sent: Saturday, April 20, 2013 7:35 AM
Subject: Re: [VOTE] The 1st hbase 0.94.7 release candidate is available for download
 

So, here are the new results.

I re-ran the RandomWriteTest with JDK 1.6 and JDK 1.7 on the same
computer. I also re-ran it on another one on a SSD with 32GB ram and 8
cores with JDK 1.6. All giving the same trend.

I will re-run again with more rows and then retry with more than 1
client and compare.

JM

Summary:
                                    Average rows/seconds
Computer1    JDK 1.7    0.94.6.1    30112
Computer1    JDK 1.7    0.94.7    28431
            
Computer1    JDK 1.6    0.94.6.1    26384
Computer1    JDK 1.6    0.94.7    24293
            
Computer2    JDK 1.6    0.94.6.1    24548
Computer2    JDK 1.6    0.94.7    22568

Details:
Machine 1 - JDK 1.7
jmspaggi@hbasetest:~/hbase$ cat hbase-0.94.6.1/output.txt  | grep
Finished | grep RandomWriteTest
13/04/19 20:58:13 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 34481
at offset 0 for 1048576 rows
13/04/19 21:00:06 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 35055
at offset 0 for 1048576 rows
13/04/19 21:02:00 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 35890
at offset 0 for 1048576 rows
13/04/19 21:03:52 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 34207
at offset 0 for 1048576 rows
13/04/19 21:05:42 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 34898
at offset 0 for 1048576 rows
13/04/19 21:07:36 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 36355
at offset 0 for 1048576 rows
13/04/19 21:09:28 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 34613
at offset 0 for 1048576 rows
13/04/19 21:11:22 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 34398
at offset 0 for 1048576 rows
13/04/19 21:13:15 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 35092
at offset 0 for 1048576 rows
13/04/19 21:15:08 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 33852
at offset 0 for 1048576 rows
jmspaggi@hbasetest:~/hbase$ cat hbase-0.94.7/output.txt  | grep
Finished | grep RandomWriteTest
13/04/19 17:10:26 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 36443
at offset 0 for 1048576 rows
13/04/19 17:12:21 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 37071
at offset 0 for 1048576 rows
13/04/19 17:14:17 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 37143
at offset 0 for 1048576 rows
13/04/19 17:16:11 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 37561
at offset 0 for 1048576 rows
13/04/19 17:18:05 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 37082
at offset 0 for 1048576 rows
13/04/19 17:20:01 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 36667
at offset 0 for 1048576 rows
13/04/19 17:21:55 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 36580
at offset 0 for 1048576 rows
13/04/19 17:23:48 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 36708
at offset 0 for 1048576 rows
13/04/19 17:25:42 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 36773
at offset 0 for 1048576 rows
13/04/19 17:27:35 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 37035
at offset 0 for 1048576 rows

Machine 1 - JDK 1.6
jmspaggi@hbasetest:~/hbase$ cat hbase-0.94.6.1/output.txt  | grep
Finished | grep RandomWriteTest
13/04/20 08:24:03 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 39531
at offset 0 for 1048576 rows
13/04/20 08:26:01 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 42207
at offset 0 for 1048576 rows
13/04/20 08:27:57 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 39840
at offset 0 for 1048576 rows
13/04/20 08:29:53 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 39202
at offset 0 for 1048576 rows
13/04/20 08:31:50 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 40973
at offset 0 for 1048576 rows
13/04/20 08:33:50 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 40906
at offset 0 for 1048576 rows
13/04/20 08:35:49 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 39333
at offset 0 for 1048576 rows
13/04/20 08:37:44 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 39185
at offset 0 for 1048576 rows
13/04/20 08:39:41 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 39071
at offset 0 for 1048576 rows
13/04/20 08:41:36 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 38693
at offset 0 for 1048576 rows
jmspaggi@hbasetest:~/hbase$ cat hbase-0.94.7/output.txt  | grep
Finished | grep RandomWriteTest
13/04/20 08:43:37 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 43526
at offset 0 for 1048576 rows
13/04/20 08:45:39 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 43593
at offset 0 for 1048576 rows
13/04/20 08:47:40 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 42576
at offset 0 for 1048576 rows
13/04/20 08:49:39 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 43450
at offset 0 for 1048576 rows
13/04/20 08:51:41 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 43436
at offset 0 for 1048576 rows
13/04/20 08:53:44 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 44171
at offset 0 for 1048576 rows
13/04/20 08:55:44 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 42831
at offset 0 for 1048576 rows
13/04/20 08:57:43 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 42931
at offset 0 for 1048576 rows
13/04/20 08:59:42 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 42686
at offset 0 for 1048576 rows
13/04/20 09:01:40 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 42879
at offset 0 for 1048576 rows


Machine 2 - JDK 1.6
jmspaggi@buldo:~/foo$ cat hbase-0.94.6.1/output.txt  | grep Finished |
grep RandomWriteTest
13/04/20 08:32:18 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 47083
at offset 0 for 1048576 rows
13/04/20 08:34:18 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 42673
at offset 0 for 1048576 rows
13/04/20 08:36:19 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 43062
at offset 0 for 1048576 rows
13/04/20 08:38:15 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 41960
at offset 0 for 1048576 rows
13/04/20 08:40:15 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 42788
at offset 0 for 1048576 rows
13/04/20 08:42:13 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 42635
at offset 0 for 1048576 rows
13/04/20 08:44:13 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 43223
at offset 0 for 1048576 rows
13/04/20 08:46:10 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 42467
at offset 0 for 1048576 rows
13/04/20 08:48:07 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 42322
at offset 0 for 1048576 rows
13/04/20 08:50:02 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 42570
at offset 0 for 1048576 rows
jmspaggi@buldo:~/foo$ cat hbase-0.94.7/output.txt  | grep Finished |
grep RandomWriteTest
13/04/20 08:52:04 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 47490
at offset 0 for 1048576 rows
13/04/20 08:54:02 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 46620
at offset 0 for 1048576 rows
13/04/20 08:56:04 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 46709
at offset 0 for 1048576 rows
13/04/20 08:58:01 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 46191
at offset 0 for 1048576 rows
13/04/20 09:00:01 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 47665
at offset 0 for 1048576 rows
13/04/20 09:01:57 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 45665
at offset 0 for 1048576 rows
13/04/20 09:03:56 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 47238
at offset 0 for 1048576 rows
13/04/20 09:06:00 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 46762
at offset 0 for 1048576 rows
13/04/20 09:07:56 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 45124
at offset 0 for 1048576 rows
13/04/20 09:09:54 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 44909
at offset 0 for 1048576 rows


2013/4/20 Jean-Marc Spaggiari <je...@spaggiari.org>
>
> Hi Lars,
>
> I just re-ran both of them again. Here are the results:
> jmspaggi@hbasetest:~/hbase$ cat hbase-0.94.6.1/output.txt  | grep Finished | grep RandomWriteTest
> 13/04/19 20:58:13 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 34481ms at offset 0 for 1048576 rows
> 13/04/19 21:00:06 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 35055ms at offset 0 for 1048576 rows
> 13/04/19 21:02:00 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 35890ms at offset 0 for 1048576 rows
> 13/04/19 21:03:52 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 34207ms at offset 0 for 1048576 rows
> 13/04/19 21:05:42 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 34898ms at offset 0 for 1048576 rows
> 13/04/19 21:07:36 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 36355ms at offset 0 for 1048576 rows
> 13/04/19 21:09:28 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 34613ms at offset 0 for 1048576 rows
> 13/04/19 21:11:22 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 34398ms at offset 0 for 1048576 rows
> 13/04/19 21:13:15 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 35092ms at offset 0 for 1048576 rows
> 13/04/19 21:15:08 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 33852ms at offset 0 for 1048576 rows
> jmspaggi@hbasetest:~/hbase$ cat hbase-0.94.7/output.txt  | grep Finished | grep RandomWriteTest
> 13/04/19 17:10:26 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 36443ms at offset 0 for 1048576 rows
> 13/04/19 17:12:21 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 37071ms at offset 0 for 1048576 rows
> 13/04/19 17:14:17 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 37143ms at offset 0 for 1048576 rows
> 13/04/19 17:16:11 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 37561ms at offset 0 for 1048576 rows
> 13/04/19 17:18:05 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 37082ms at offset 0 for 1048576 rows
> 13/04/19 17:20:01 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 36667ms at offset 0 for 1048576 rows
> 13/04/19 17:21:55 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 36580ms at offset 0 for 1048576 rows
> 13/04/19 17:23:48 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 36708ms at offset 0 for 1048576 rows
> 13/04/19 17:25:42 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 36773ms at offset 0 for 1048576 rows
> 13/04/19 17:27:35 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 37035ms at offset 0 for 1048576 rows
>
> I copied the log4j config from one to the other one to make sure they are logging the same thing. They are both ran on a single node standalone dedicated computer. Here is the command line I used:
> echo Test starting for randomWrite
> for i in {1..10}; do echo; echo -n $i ; rm -rf /tmp/*; bin/start-hbase.sh; sleep 60; bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation randomWrite 1; bin/stop-hbase.sh; done &>> output.txt
>
> Computer is a 4 cores 4.2Ghz 16G with 60GB regular SATA-I hard drive.
>
> I will re-run the tests on another computer with different specs to figure if the hard drive is impacting the results.
>
> But so far, 0.94.7 is still slower for me.
>
> JM
>
>
> 2013/4/19 lars hofhansl <la...@apache.org>
>>
>> Thanks JM.
>>
>> I ran PE locally, and between 0.94.6.1 and 0.94.7 I do not see any systematic slowdown for the random write test.
>> In fact I had the fastest run in 0.94.7 (32.6s) and the slowest one in 0.94.6.1 (39.5s).
>>
>> Variance of that test is very high (both in 0.94.6.1 and 0.94.7).
>>
>>
>> My test setup is single node install of HBase/Hadoop/ZK.
>>
>> -- Lars
>>
>>
>>
>> ________________________________
>>  From: Jean-Marc Spaggiari <je...@spaggiari.org>
>> To: dev@hbase.apache.org; lars hofhansl <la...@apache.org>
>> Sent: Thursday, April 18, 2013 8:13 AM
>> Subject: Re: [VOTE] The 1st hbase 0.94.7 release candidate is available for download
>>
>>
>> Here is the PerformanceEvaluation comparison report:
>> http://www.spaggiari.org/media/blogs/hbase/pdf/performances_20130418.pdf
>>
>> Summary:
>> - Filtered scan performances and sequential reads are consistant with
>> previous 0.94 releases;
>> - Scan range are about 3% slower;
>> - Random read are 7% faster;
>> - But random writes are 7% slower.
>>
>>
>> Basically, here is what I did:
>> - Downloaded the file, checked signature for both security and "regular"
>> distribution. Both fine.
>> - Decompressed regular distribution and checked the CHANGES.txt and
>> documentation content (few random pages).
>> - Ran it in standalone; checked the UI, the logs and ran all performance
>> evaluation scenarios.
>> - Ran HBCK few times before and after.
>> - Ran IntegrationTestLoadAndVerify (ROWS_WRITTEN=0;
>> REFERENCES_CHECKED=9855322). Not sure how to validate the results but I
>> will have expected REFERENCES_CHECKED to be 10000000.
>> - Ran IntegrationTestBigLinkedList (REFERENCED=6000000), sound right based
>> on the command line (Loop 2 1 3000000)
>> - Ran the test suite (org.apache.hadoop.hbase.catalog.TestMetaReaderEditor
>> failed the first time, I re-ran alone it and it passed. Re-ran the entire
>> test suite, failed at the same place.)
>>
>>
>> - Deployed it on 9 servers (8 RS, 1 master) and did a rolling-restart.
>> - Checked the logs, status, UI;
>> - Changed balancer to default balancer, stop hbase, merged all regions into
>> a single one, restarted;
>> - Checked HBCK, table status, logs, table regions (should have ony one),
>> etc.
>> - Ran major compaction on the small table from the shell, ran balancer,
>> checked the logs, checked the splits.
>> - Stopped the cluster, restored custom balancer, restarted, rebalanced,
>> checked transitions and logs.
>> - From shell, created a table; did few put, scan on the new and existing
>> tables, dropped table;
>> - Ran few different MR Job overnight, checked the results and logs.
>> - Ran IntegrationTestLoadAndVerify (ROWS_WRITTEN=0;
>> REFERENCES_CHECKED=9855185). Not sure how to validate the results but I
>> will have expected REFERENCES_CHECKED to be 10000000.
>> - Ran IntegrationTestBigLinkedList (REFERENCED=6000000), sound right based
>> on the command line (Loop 2 1 3000000)
>>
>> Overall, +1 for me. All the comments are in the Google Spreadsheet.
>>
>> But I think we should take a look at the random writes performances
>> degradation and to IntegrationTestLoadAnVerify results.
>>
>> JM
>>
>>
>> 2013/4/17 lars hofhansl <la...@apache.org>
>>
>> > The 1st 0.94.7 RC is available for download at
>> > http://people.apache.org/~larsh/hbase-0.94.7-rc0/
>> >
>> > Signed with my code signing key: C7CFE328
>> >
>> > This RC has 71 issues resolved against it, contributed by 27 individuals.
>> > 0.94.7 is primarily a bug fix release. Notable exceptions include:
>> > HBASE-8176 Dynamic Schema Configurations
>> > HBASE-7801 Allow a deferred sync option per Mutation
>> >
>> > The full list of changes is available here:
>> > https://issues.apache.org/jira/browse/HBASE/fixforversion/12324039
>> >
>> > Please try out the RC, check out the doc, take it for a spin, etc, and
>> > vote +1/-1 by April 24th on whether we should release this as 0.94.7.
>> >
>> > The release testing spreadsheet is available here:
>> >
>> > https://docs.google.com/spreadsheet/ccc?key=0AvLqcVIqNtlTdG9jbVNmWmhyeGJZeUo4MUdIMEEweEE#gid=0
>> >
>> > Thanks.
>> >
>> > -- Lars
>
>

Re: [VOTE] The 1st hbase 0.94.7 release candidate is available for download

Posted by Jean-Marc Spaggiari <je...@spaggiari.org>.

So, here are the new results.

I re-ran the RandomWriteTest with JDK 1.6 and JDK 1.7 on the same
computer. I also re-ran it on another one on a SSD with 32GB ram and 8
cores with JDK 1.6. All giving the same trend.

I will re-run again with more rows and then retry with more than 1
client and compare.

JM

Summary:
			                        Average rows/seconds
Computer1	JDK 1.7	0.94.6.1	30112
Computer1	JDK 1.7	0.94.7	28431
			
Computer1	JDK 1.6	0.94.6.1	26384
Computer1	JDK 1.6	0.94.7	24293
			
Computer2	JDK 1.6	0.94.6.1	24548
Computer2	JDK 1.6	0.94.7	22568

Details:
Machine 1 - JDK 1.7
jmspaggi@hbasetest:~/hbase$ cat hbase-0.94.6.1/output.txt  | grep
Finished | grep RandomWriteTest
13/04/19 20:58:13 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 34481
at offset 0 for 1048576 rows
13/04/19 21:00:06 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 35055
at offset 0 for 1048576 rows
13/04/19 21:02:00 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 35890
at offset 0 for 1048576 rows
13/04/19 21:03:52 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 34207
at offset 0 for 1048576 rows
13/04/19 21:05:42 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 34898
at offset 0 for 1048576 rows
13/04/19 21:07:36 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 36355
at offset 0 for 1048576 rows
13/04/19 21:09:28 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 34613
at offset 0 for 1048576 rows
13/04/19 21:11:22 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 34398
at offset 0 for 1048576 rows
13/04/19 21:13:15 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 35092
at offset 0 for 1048576 rows
13/04/19 21:15:08 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 33852
at offset 0 for 1048576 rows
jmspaggi@hbasetest:~/hbase$ cat hbase-0.94.7/output.txt  | grep
Finished | grep RandomWriteTest
13/04/19 17:10:26 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 36443
at offset 0 for 1048576 rows
13/04/19 17:12:21 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 37071
at offset 0 for 1048576 rows
13/04/19 17:14:17 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 37143
at offset 0 for 1048576 rows
13/04/19 17:16:11 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 37561
at offset 0 for 1048576 rows
13/04/19 17:18:05 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 37082
at offset 0 for 1048576 rows
13/04/19 17:20:01 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 36667
at offset 0 for 1048576 rows
13/04/19 17:21:55 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 36580
at offset 0 for 1048576 rows
13/04/19 17:23:48 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 36708
at offset 0 for 1048576 rows
13/04/19 17:25:42 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 36773
at offset 0 for 1048576 rows
13/04/19 17:27:35 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 37035
at offset 0 for 1048576 rows

Machine 1 - JDK 1.6
jmspaggi@hbasetest:~/hbase$ cat hbase-0.94.6.1/output.txt  | grep
Finished | grep RandomWriteTest
13/04/20 08:24:03 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 39531
at offset 0 for 1048576 rows
13/04/20 08:26:01 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 42207
at offset 0 for 1048576 rows
13/04/20 08:27:57 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 39840
at offset 0 for 1048576 rows
13/04/20 08:29:53 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 39202
at offset 0 for 1048576 rows
13/04/20 08:31:50 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 40973
at offset 0 for 1048576 rows
13/04/20 08:33:50 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 40906
at offset 0 for 1048576 rows
13/04/20 08:35:49 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 39333
at offset 0 for 1048576 rows
13/04/20 08:37:44 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 39185
at offset 0 for 1048576 rows
13/04/20 08:39:41 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 39071
at offset 0 for 1048576 rows
13/04/20 08:41:36 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 38693
at offset 0 for 1048576 rows
jmspaggi@hbasetest:~/hbase$ cat hbase-0.94.7/output.txt  | grep
Finished | grep RandomWriteTest
13/04/20 08:43:37 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 43526
at offset 0 for 1048576 rows
13/04/20 08:45:39 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 43593
at offset 0 for 1048576 rows
13/04/20 08:47:40 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 42576
at offset 0 for 1048576 rows
13/04/20 08:49:39 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 43450
at offset 0 for 1048576 rows
13/04/20 08:51:41 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 43436
at offset 0 for 1048576 rows
13/04/20 08:53:44 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 44171
at offset 0 for 1048576 rows
13/04/20 08:55:44 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 42831
at offset 0 for 1048576 rows
13/04/20 08:57:43 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 42931
at offset 0 for 1048576 rows
13/04/20 08:59:42 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 42686
at offset 0 for 1048576 rows
13/04/20 09:01:40 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 42879
at offset 0 for 1048576 rows


Machine 2 - JDK 1.6
jmspaggi@buldo:~/foo$ cat hbase-0.94.6.1/output.txt  | grep Finished |
grep RandomWriteTest
13/04/20 08:32:18 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 47083
at offset 0 for 1048576 rows
13/04/20 08:34:18 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 42673
at offset 0 for 1048576 rows
13/04/20 08:36:19 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 43062
at offset 0 for 1048576 rows
13/04/20 08:38:15 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 41960
at offset 0 for 1048576 rows
13/04/20 08:40:15 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 42788
at offset 0 for 1048576 rows
13/04/20 08:42:13 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 42635
at offset 0 for 1048576 rows
13/04/20 08:44:13 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 43223
at offset 0 for 1048576 rows
13/04/20 08:46:10 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 42467
at offset 0 for 1048576 rows
13/04/20 08:48:07 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 42322
at offset 0 for 1048576 rows
13/04/20 08:50:02 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 42570
at offset 0 for 1048576 rows
jmspaggi@buldo:~/foo$ cat hbase-0.94.7/output.txt  | grep Finished |
grep RandomWriteTest
13/04/20 08:52:04 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 47490
at offset 0 for 1048576 rows
13/04/20 08:54:02 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 46620
at offset 0 for 1048576 rows
13/04/20 08:56:04 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 46709
at offset 0 for 1048576 rows
13/04/20 08:58:01 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 46191
at offset 0 for 1048576 rows
13/04/20 09:00:01 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 47665
at offset 0 for 1048576 rows
13/04/20 09:01:57 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 45665
at offset 0 for 1048576 rows
13/04/20 09:03:56 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 47238
at offset 0 for 1048576 rows
13/04/20 09:06:00 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 46762
at offset 0 for 1048576 rows
13/04/20 09:07:56 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 45124
at offset 0 for 1048576 rows
13/04/20 09:09:54 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 44909
at offset 0 for 1048576 rows


2013/4/20 Jean-Marc Spaggiari <je...@spaggiari.org>
>
> Hi Lars,
>
> I just re-ran both of them again. Here are the results:
> jmspaggi@hbasetest:~/hbase$ cat hbase-0.94.6.1/output.txt  | grep Finished | grep RandomWriteTest
> 13/04/19 20:58:13 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 34481ms at offset 0 for 1048576 rows
> 13/04/19 21:00:06 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 35055ms at offset 0 for 1048576 rows
> 13/04/19 21:02:00 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 35890ms at offset 0 for 1048576 rows
> 13/04/19 21:03:52 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 34207ms at offset 0 for 1048576 rows
> 13/04/19 21:05:42 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 34898ms at offset 0 for 1048576 rows
> 13/04/19 21:07:36 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 36355ms at offset 0 for 1048576 rows
> 13/04/19 21:09:28 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 34613ms at offset 0 for 1048576 rows
> 13/04/19 21:11:22 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 34398ms at offset 0 for 1048576 rows
> 13/04/19 21:13:15 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 35092ms at offset 0 for 1048576 rows
> 13/04/19 21:15:08 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 33852ms at offset 0 for 1048576 rows
> jmspaggi@hbasetest:~/hbase$ cat hbase-0.94.7/output.txt  | grep Finished | grep RandomWriteTest
> 13/04/19 17:10:26 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 36443ms at offset 0 for 1048576 rows
> 13/04/19 17:12:21 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 37071ms at offset 0 for 1048576 rows
> 13/04/19 17:14:17 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 37143ms at offset 0 for 1048576 rows
> 13/04/19 17:16:11 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 37561ms at offset 0 for 1048576 rows
> 13/04/19 17:18:05 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 37082ms at offset 0 for 1048576 rows
> 13/04/19 17:20:01 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 36667ms at offset 0 for 1048576 rows
> 13/04/19 17:21:55 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 36580ms at offset 0 for 1048576 rows
> 13/04/19 17:23:48 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 36708ms at offset 0 for 1048576 rows
> 13/04/19 17:25:42 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 36773ms at offset 0 for 1048576 rows
> 13/04/19 17:27:35 INFO hbase.PerformanceEvaluation: Finished class org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 37035ms at offset 0 for 1048576 rows
>
> I copied the log4j config from one to the other one to make sure they are logging the same thing. They are both ran on a single node standalone dedicated computer. Here is the command line I used:
> echo Test starting for randomWrite
> for i in {1..10}; do echo; echo -n $i ; rm -rf /tmp/*; bin/start-hbase.sh; sleep 60; bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation randomWrite 1; bin/stop-hbase.sh; done &>> output.txt
>
> Computer is a 4 cores 4.2Ghz 16G with 60GB regular SATA-I hard drive.
>
> I will re-run the tests on another computer with different specs to figure if the hard drive is impacting the results.
>
> But so far, 0.94.7 is still slower for me.
>
> JM
>
>
> 2013/4/19 lars hofhansl <la...@apache.org>
>>
>> Thanks JM.
>>
>> I ran PE locally, and between 0.94.6.1 and 0.94.7 I do not see any systematic slowdown for the random write test.
>> In fact I had the fastest run in 0.94.7 (32.6s) and the slowest one in 0.94.6.1 (39.5s).
>>
>> Variance of that test is very high (both in 0.94.6.1 and 0.94.7).
>>
>>
>> My test setup is single node install of HBase/Hadoop/ZK.
>>
>> -- Lars
>>
>>
>>
>> ________________________________
>>  From: Jean-Marc Spaggiari <je...@spaggiari.org>
>> To: dev@hbase.apache.org; lars hofhansl <la...@apache.org>
>> Sent: Thursday, April 18, 2013 8:13 AM
>> Subject: Re: [VOTE] The 1st hbase 0.94.7 release candidate is available for download
>>
>>
>> Here is the PerformanceEvaluation comparison report:
>> http://www.spaggiari.org/media/blogs/hbase/pdf/performances_20130418.pdf
>>
>> Summary:
>> - Filtered scan performances and sequential reads are consistant with
>> previous 0.94 releases;
>> - Scan range are about 3% slower;
>> - Random read are 7% faster;
>> - But random writes are 7% slower.
>>
>>
>> Basically, here is what I did:
>> - Downloaded the file, checked signature for both security and "regular"
>> distribution. Both fine.
>> - Decompressed regular distribution and checked the CHANGES.txt and
>> documentation content (few random pages).
>> - Ran it in standalone; checked the UI, the logs and ran all performance
>> evaluation scenarios.
>> - Ran HBCK few times before and after.
>> - Ran IntegrationTestLoadAndVerify (ROWS_WRITTEN=0;
>> REFERENCES_CHECKED=9855322). Not sure how to validate the results but I
>> will have expected REFERENCES_CHECKED to be 10000000.
>> - Ran IntegrationTestBigLinkedList (REFERENCED=6000000), sound right based
>> on the command line (Loop 2 1 3000000)
>> - Ran the test suite (org.apache.hadoop.hbase.catalog.TestMetaReaderEditor
>> failed the first time, I re-ran alone it and it passed. Re-ran the entire
>> test suite, failed at the same place.)
>>
>>
>> - Deployed it on 9 servers (8 RS, 1 master) and did a rolling-restart.
>> - Checked the logs, status, UI;
>> - Changed balancer to default balancer, stop hbase, merged all regions into
>> a single one, restarted;
>> - Checked HBCK, table status, logs, table regions (should have ony one),
>> etc.
>> - Ran major compaction on the small table from the shell, ran balancer,
>> checked the logs, checked the splits.
>> - Stopped the cluster, restored custom balancer, restarted, rebalanced,
>> checked transitions and logs.
>> - From shell, created a table; did few put, scan on the new and existing
>> tables, dropped table;
>> - Ran few different MR Job overnight, checked the results and logs.
>> - Ran IntegrationTestLoadAndVerify (ROWS_WRITTEN=0;
>> REFERENCES_CHECKED=9855185). Not sure how to validate the results but I
>> will have expected REFERENCES_CHECKED to be 10000000.
>> - Ran IntegrationTestBigLinkedList (REFERENCED=6000000), sound right based
>> on the command line (Loop 2 1 3000000)
>>
>> Overall, +1 for me. All the comments are in the Google Spreadsheet.
>>
>> But I think we should take a look at the random writes performances
>> degradation and to IntegrationTestLoadAnVerify results.
>>
>> JM
>>
>>
>> 2013/4/17 lars hofhansl <la...@apache.org>
>>
>> > The 1st 0.94.7 RC is available for download at
>> > http://people.apache.org/~larsh/hbase-0.94.7-rc0/
>> >
>> > Signed with my code signing key: C7CFE328
>> >
>> > This RC has 71 issues resolved against it, contributed by 27 individuals.
>> > 0.94.7 is primarily a bug fix release. Notable exceptions include:
>> > HBASE-8176 Dynamic Schema Configurations
>> > HBASE-7801 Allow a deferred sync option per Mutation
>> >
>> > The full list of changes is available here:
>> > https://issues.apache.org/jira/browse/HBASE/fixforversion/12324039
>> >
>> > Please try out the RC, check out the doc, take it for a spin, etc, and
>> > vote +1/-1 by April 24th on whether we should release this as 0.94.7.
>> >
>> > The release testing spreadsheet is available here:
>> >
>> > https://docs.google.com/spreadsheet/ccc?key=0AvLqcVIqNtlTdG9jbVNmWmhyeGJZeUo4MUdIMEEweEE#gid=0
>> >
>> > Thanks.
>> >
>> > -- Lars
>
>

Re: [VOTE] The 1st hbase 0.94.7 release candidate is available for download

Posted by Jean-Marc Spaggiari <je...@spaggiari.org>.

Hi Lars,

I just re-ran both of them again. Here are the results:
jmspaggi@hbasetest:~/hbase$ cat hbase-0.94.6.1/output.txt  | grep Finished
| grep RandomWriteTest
13/04/19 20:58:13 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 34481ms at
offset 0 for 1048576 rows
13/04/19 21:00:06 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 35055ms at
offset 0 for 1048576 rows
13/04/19 21:02:00 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 35890ms at
offset 0 for 1048576 rows
13/04/19 21:03:52 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 34207ms at
offset 0 for 1048576 rows
13/04/19 21:05:42 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 34898ms at
offset 0 for 1048576 rows
13/04/19 21:07:36 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 36355ms at
offset 0 for 1048576 rows
13/04/19 21:09:28 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 34613ms at
offset 0 for 1048576 rows
13/04/19 21:11:22 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 34398ms at
offset 0 for 1048576 rows
13/04/19 21:13:15 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 35092ms at
offset 0 for 1048576 rows
13/04/19 21:15:08 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 33852ms at
offset 0 for 1048576 rows
jmspaggi@hbasetest:~/hbase$ cat hbase-0.94.7/output.txt  | grep Finished |
grep RandomWriteTest
13/04/19 17:10:26 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 36443ms at
offset 0 for 1048576 rows
13/04/19 17:12:21 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 37071ms at
offset 0 for 1048576 rows
13/04/19 17:14:17 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 37143ms at
offset 0 for 1048576 rows
13/04/19 17:16:11 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 37561ms at
offset 0 for 1048576 rows
13/04/19 17:18:05 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 37082ms at
offset 0 for 1048576 rows
13/04/19 17:20:01 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 36667ms at
offset 0 for 1048576 rows
13/04/19 17:21:55 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 36580ms at
offset 0 for 1048576 rows
13/04/19 17:23:48 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 36708ms at
offset 0 for 1048576 rows
13/04/19 17:25:42 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 36773ms at
offset 0 for 1048576 rows
13/04/19 17:27:35 INFO hbase.PerformanceEvaluation: Finished class
org.apache.hadoop.hbase.PerformanceEvaluation$RandomWriteTest in 37035ms at
offset 0 for 1048576 rows

I copied the log4j config from one to the other one to make sure they are
logging the same thing. They are both ran on a single node standalone
dedicated computer. Here is the command line I used:
echo Test starting for randomWrite
for i in {1..10}; do echo; echo -n $i ; rm -rf /tmp/*; bin/start-hbase.sh;
sleep 60; bin/hbase org.apache.hadoop.hbase.PerformanceEvaluation
randomWrite 1; bin/stop-hbase.sh; done &>> output.txt

Computer is a 4 cores 4.2Ghz 16G with 60GB regular SATA-I hard drive.

I will re-run the tests on another computer with different specs to figure
if the hard drive is impacting the results.

But so far, 0.94.7 is still slower for me.

JM

2013/4/19 lars hofhansl <la...@apache.org>

> Thanks JM.
>
> I ran PE locally, and between 0.94.6.1 and 0.94.7 I do not see any
> systematic slowdown for the random write test.
> In fact I had the fastest run in 0.94.7 (32.6s) and the slowest one in
> 0.94.6.1 (39.5s).
>
> Variance of that test is very high (both in 0.94.6.1 and 0.94.7).
>
>
> My test setup is single node install of HBase/Hadoop/ZK.
>
> -- Lars
>
>
>
> ________________________________
>  From: Jean-Marc Spaggiari <je...@spaggiari.org>
> To: dev@hbase.apache.org; lars hofhansl <la...@apache.org>
> Sent: Thursday, April 18, 2013 8:13 AM
> Subject: Re: [VOTE] The 1st hbase 0.94.7 release candidate is available
> for download
>
>
> Here is the PerformanceEvaluation comparison report:
> http://www.spaggiari.org/media/blogs/hbase/pdf/performances_20130418.pdf
>
> Summary:
> - Filtered scan performances and sequential reads are consistant with
> previous 0.94 releases;
> - Scan range are about 3% slower;
> - Random read are 7% faster;
> - But random writes are 7% slower.
>
>
> Basically, here is what I did:
> - Downloaded the file, checked signature for both security and "regular"
> distribution. Both fine.
> - Decompressed regular distribution and checked the CHANGES.txt and
> documentation content (few random pages).
> - Ran it in standalone; checked the UI, the logs and ran all performance
> evaluation scenarios.
> - Ran HBCK few times before and after.
> - Ran IntegrationTestLoadAndVerify (ROWS_WRITTEN=0;
> REFERENCES_CHECKED=9855322). Not sure how to validate the results but I
> will have expected REFERENCES_CHECKED to be 10000000.
> - Ran IntegrationTestBigLinkedList (REFERENCED=6000000), sound right based
> on the command line (Loop 2 1 3000000)
> - Ran the test suite (org.apache.hadoop.hbase.catalog.TestMetaReaderEditor
> failed the first time, I re-ran alone it and it passed. Re-ran the entire
> test suite, failed at the same place.)
>
>
> - Deployed it on 9 servers (8 RS, 1 master) and did a rolling-restart.
> - Checked the logs, status, UI;
> - Changed balancer to default balancer, stop hbase, merged all regions into
> a single one, restarted;
> - Checked HBCK, table status, logs, table regions (should have ony one),
> etc.
> - Ran major compaction on the small table from the shell, ran balancer,
> checked the logs, checked the splits.
> - Stopped the cluster, restored custom balancer, restarted, rebalanced,
> checked transitions and logs.
> - From shell, created a table; did few put, scan on the new and existing
> tables, dropped table;
> - Ran few different MR Job overnight, checked the results and logs.
> - Ran IntegrationTestLoadAndVerify (ROWS_WRITTEN=0;
> REFERENCES_CHECKED=9855185). Not sure how to validate the results but I
> will have expected REFERENCES_CHECKED to be 10000000.
> - Ran IntegrationTestBigLinkedList (REFERENCED=6000000), sound right based
> on the command line (Loop 2 1 3000000)
>
> Overall, +1 for me. All the comments are in the Google Spreadsheet.
>
> But I think we should take a look at the random writes performances
> degradation and to IntegrationTestLoadAnVerify results.
>
> JM
>
>
> 2013/4/17 lars hofhansl <la...@apache.org>
>
> > The 1st 0.94.7 RC is available for download at
> > http://people.apache.org/~larsh/hbase-0.94.7-rc0/
> >
> > Signed with my code signing key: C7CFE328
> >
> > This RC has 71 issues resolved against it, contributed by 27 individuals.
> > 0.94.7 is primarily a bug fix release. Notable exceptions include:
> > HBASE-8176 Dynamic Schema Configurations
> > HBASE-7801 Allow a deferred sync option per Mutation
> >
> > The full list of changes is available here:
> > https://issues.apache.org/jira/browse/HBASE/fixforversion/12324039
> >
> > Please try out the RC, check out the doc, take it for a spin, etc, and
> > vote +1/-1 by April 24th on whether we should release this as 0.94.7.
> >
> > The release testing spreadsheet is available here:
> >
> >
> https://docs.google.com/spreadsheet/ccc?key=0AvLqcVIqNtlTdG9jbVNmWmhyeGJZeUo4MUdIMEEweEE#gid=0
> >
> > Thanks.
> >
> > -- Lars
>

Re: [VOTE] The 1st hbase 0.94.7 release candidate is available for download

Posted by lars hofhansl <la...@apache.org>.

Thanks JM.

I ran PE locally, and between 0.94.6.1 and 0.94.7 I do not see any systematic slowdown for the random write test.
In fact I had the fastest run in 0.94.7 (32.6s) and the slowest one in 0.94.6.1 (39.5s).

Variance of that test is very high (both in 0.94.6.1 and 0.94.7).


My test setup is single node install of HBase/Hadoop/ZK.

-- Lars



________________________________
 From: Jean-Marc Spaggiari <je...@spaggiari.org>
To: dev@hbase.apache.org; lars hofhansl <la...@apache.org> 
Sent: Thursday, April 18, 2013 8:13 AM
Subject: Re: [VOTE] The 1st hbase 0.94.7 release candidate is available for download
 

Here is the PerformanceEvaluation comparison report:
http://www.spaggiari.org/media/blogs/hbase/pdf/performances_20130418.pdf

Summary:
- Filtered scan performances and sequential reads are consistant with
previous 0.94 releases;
- Scan range are about 3% slower;
- Random read are 7% faster;
- But random writes are 7% slower.


Basically, here is what I did:
- Downloaded the file, checked signature for both security and "regular"
distribution. Both fine.
- Decompressed regular distribution and checked the CHANGES.txt and
documentation content (few random pages).
- Ran it in standalone; checked the UI, the logs and ran all performance
evaluation scenarios.
- Ran HBCK few times before and after.
- Ran IntegrationTestLoadAndVerify (ROWS_WRITTEN=0;
REFERENCES_CHECKED=9855322). Not sure how to validate the results but I
will have expected REFERENCES_CHECKED to be 10000000.
- Ran IntegrationTestBigLinkedList (REFERENCED=6000000), sound right based
on the command line (Loop 2 1 3000000)
- Ran the test suite (org.apache.hadoop.hbase.catalog.TestMetaReaderEditor
failed the first time, I re-ran alone it and it passed. Re-ran the entire
test suite, failed at the same place.)


- Deployed it on 9 servers (8 RS, 1 master) and did a rolling-restart.
- Checked the logs, status, UI;
- Changed balancer to default balancer, stop hbase, merged all regions into
a single one, restarted;
- Checked HBCK, table status, logs, table regions (should have ony one),
etc.
- Ran major compaction on the small table from the shell, ran balancer,
checked the logs, checked the splits.
- Stopped the cluster, restored custom balancer, restarted, rebalanced,
checked transitions and logs.
- From shell, created a table; did few put, scan on the new and existing
tables, dropped table;
- Ran few different MR Job overnight, checked the results and logs.
- Ran IntegrationTestLoadAndVerify (ROWS_WRITTEN=0;
REFERENCES_CHECKED=9855185). Not sure how to validate the results but I
will have expected REFERENCES_CHECKED to be 10000000.
- Ran IntegrationTestBigLinkedList (REFERENCED=6000000), sound right based
on the command line (Loop 2 1 3000000)

Overall, +1 for me. All the comments are in the Google Spreadsheet.

But I think we should take a look at the random writes performances
degradation and to IntegrationTestLoadAnVerify results.

JM


2013/4/17 lars hofhansl <la...@apache.org>

> The 1st 0.94.7 RC is available for download at
> http://people.apache.org/~larsh/hbase-0.94.7-rc0/
>
> Signed with my code signing key: C7CFE328
>
> This RC has 71 issues resolved against it, contributed by 27 individuals.
> 0.94.7 is primarily a bug fix release. Notable exceptions include:
> HBASE-8176 Dynamic Schema Configurations
> HBASE-7801 Allow a deferred sync option per Mutation
>
> The full list of changes is available here:
> https://issues.apache.org/jira/browse/HBASE/fixforversion/12324039
>
> Please try out the RC, check out the doc, take it for a spin, etc, and
> vote +1/-1 by April 24th on whether we should release this as 0.94.7.
>
> The release testing spreadsheet is available here:
>
> https://docs.google.com/spreadsheet/ccc?key=0AvLqcVIqNtlTdG9jbVNmWmhyeGJZeUo4MUdIMEEweEE#gid=0
>
> Thanks.
>
> -- Lars