Home | About | Sematext search-lucene.com search-hadoop.com
 Search Hadoop and all its subprojects:

Switch to Threaded View
HBase, mail # dev - [ANNOUNCE] The 1st hbase 0.94.9 release candidate is available for download


Copy link to this message
-
Re: [ANNOUNCE] The 1st hbase 0.94.9 release candidate is available for download
lars hofhansl 2013-07-06, 16:50
Are these times or ops/sec, or something else?
----- Original Message -----
From: Jean-Marc Spaggiari <[EMAIL PROTECTED]>
To: [EMAIL PROTECTED]; lars hofhansl <[EMAIL PROTECTED]>
Cc:
Sent: Friday, July 5, 2013 8:24 PM
Subject: Re: [ANNOUNCE] The 1st hbase 0.94.9 release candidate is available
 for download

I have redo the tests and it's now all very consistent between all the
recent versions

Min    Max    Average    Min80%    Max80%    Variance    Precision
hbase-0.94.5    914    1175    929    920    944    172    18.46%
hbase-0.94.6    913    1176    927    915    954    174    18.80%
hbase-0.94.7    913    1295    930    919    946    170    18.30%
hbase-0.94.8    914    947    935    914    945    166    17.78%
hbase-0.94.9    921    947    936    933    940    164    17.55%

I will try to make the tests last longer to get more precise results...

If we think a few nodes clusters is way beter for the performances
tracking, then let's work that way. But if we think PE can do the job,
it's even better ;) I just want to make sure we have accurate results
and that we performance test the right things...

I will re-run that, update the pdf and upload it again...

JM

2013/7/4 lars hofhansl <[EMAIL PROTECTED]>:
> Thanks for doing all this work!
>
> I did find a pretty high variance between the runs, which may be at issue here.
>
> Maybe there are effects that only show on certain setups (disk drives, ram, jvm version, etc).
>
> Maybe we can compare setups offline.
>
> -- Lars
>
>
>
> ----- Original Message -----
> From: Jean-Marc Spaggiari <[EMAIL PROTECTED]>
> To: [EMAIL PROTECTED]
> Cc:
> Sent: Thursday, July 4, 2013 9:25 AM
> Subject: Re: [ANNOUNCE] The 1st hbase 0.94.9 release candidate is available
>  for download
>
> Ok. I get similar performances between 0.94.7 and 0.94.9 for the randomRead
>
> 0.94.7 => 1124179.9ms
> 0.94.9 => 1110489.3ms
>
> I will re-run the tests one by one for all the 0.94.x versions and
> update my charts...
>
> 2013/7/3 Jean-Marc Spaggiari <[EMAIL PROTECTED]>:
>> Ok. Test pass if I run it alone:
>>
>> mvn clean test -P runSmallTests -Djava.net.preferIPv4Stack=true
>> -Dtest=org.apache.hadoop.hbase.coprocessor.TestRegionObserverScannerOpenHook
>>
>> -------------------------------------------------------
>>  T E S T S
>> -------------------------------------------------------
>> Running org.apache.hadoop.hbase.coprocessor.TestRegionObserverScannerOpenHook
>> Tests run: 3, Failures: 0, Errors: 0, Skipped: 0, Time elapsed: 11.642 sec
>>
>> Results :
>>
>> Tests run: 3, Failures: 0, Errors: 0, Skipped: 0
>>
>>
>>
>> And finally passed on another one:
>> Results :
>>
>> Tests run: 1359, Failures: 0, Errors: 0, Skipped: 13
>>
>> [INFO] ------------------------------------------------------------------------
>> [INFO] BUILD SUCCESS
>> [INFO] ------------------------------------------------------------------------
>> [INFO] Total time: 1:33:34.925s
>> [INFO] Finished at: Tue Jul 02 16:37:59 EDT 2013
>> [INFO] Final Memory: 44M/594M
>> [INFO] ------------------------------------------------------------------------
>>
>>
>> So it's all +1 for me.
>>
>> JM
>>
>> 2013/7/2 Elliott Clark <[EMAIL PROTECTED]>:
>>> +1
>>>
>>> untared.
>>> Checked the sig.
>>> Ran Ycsb.
>>> Ran PE.
>>> upgraded from 94.8.
>>>
>>> On Tue, Jul 2, 2013 at 11:32 AM, lars hofhansl <[EMAIL PROTECTED]> wrote:
>>>> passes fine here too
>>>>
>>>>
>>>>
>>>> ----- Original Message -----
>>>> From: Jean-Daniel Cryans <[EMAIL PROTECTED]>
>>>> To: "[EMAIL PROTECTED]" <[EMAIL PROTECTED]>
>>>> Cc:
>>>> Sent: Tuesday, July 2, 2013 11:22 AM
>>>> Subject: Re: [ANNOUNCE] The 1st hbase 0.94.9 release candidate is available
>>>>  for download
>>>>
>>>> Yup:
>>>>
>>>> Running org.apache.hadoop.hbase.coprocessor.TestRegionObserverScannerOpenHook
>>>> Tests run: 3, Failures: 0, Errors: 0, Skipped: 0, Time elapsed: 22.756 sec
>>>>
>>>> Have you looked at the log to see on what error it fails?
>>>>
>>>> J-D
>>>>
>>>> On Tue, Jul 2, 2013 at 11:08 AM, Jean-Marc Spaggiari