Article: Nehalem Performance Preview
By: Henrik S (henrik.stahl.delete@this.nospam.oracle.nothanks.com), April 12, 2009 9:18 pm
Room: Moderated Discussions
EduardoS (no@spam.com) on 4/12/09 wrote:
---------------------------
>Henrik S (henrik.stahl@nospam.oracle.nothanks.com) on 4/12/09 wrote:
>---------------------------
>>Huh? Our large (== huge) pages support work on both Windows and Linux. You must
>>of course configure the OS appropriately first.
>
>My fault, I was refering to 1GB pages, apparently, the most recent JRockit submission on a system that supports them didn't used: http://www.spec.org/jbb2005/results/res2009q1/jbb2005-20090310-00665.html
No, we haven't tried 1 GB pages yet. I wasn't aware of such support being enabled in current mainstream Linux versions (such as Red Hat). Once OS support is in place, it should be trivial to add support in the JVM. But I don't think it will help SPECjbb scores much - with "normal" large pages and 4 GB of heap we don't see many TLB misses.
>>jbb creates threads at the start of each warehouse run, and then lets them terminate at the end of the warehous run. Warehouse runs are ramped up from 1 to 2xCPU count threads, with 30/240s runtime per iteration for warmup/scoring respectively. See the jbb docs on http://www.spec.org
>>
>>for more detail.
>
>I really tought JBB was creating one thread for each "business operation" (a "client
>request"?), not a few long running threads, hum... How scores would be affected if that was the case?
That would definitely change the profile. Threads are expensive to set up and tear down, so this is not a common pattern in Java apps.
Henrik
---------------------------
>Henrik S (henrik.stahl@nospam.oracle.nothanks.com) on 4/12/09 wrote:
>---------------------------
>>Huh? Our large (== huge) pages support work on both Windows and Linux. You must
>>of course configure the OS appropriately first.
>
>My fault, I was refering to 1GB pages, apparently, the most recent JRockit submission on a system that supports them didn't used: http://www.spec.org/jbb2005/results/res2009q1/jbb2005-20090310-00665.html
No, we haven't tried 1 GB pages yet. I wasn't aware of such support being enabled in current mainstream Linux versions (such as Red Hat). Once OS support is in place, it should be trivial to add support in the JVM. But I don't think it will help SPECjbb scores much - with "normal" large pages and 4 GB of heap we don't see many TLB misses.
>>jbb creates threads at the start of each warehouse run, and then lets them terminate at the end of the warehous run. Warehouse runs are ramped up from 1 to 2xCPU count threads, with 30/240s runtime per iteration for warmup/scoring respectively. See the jbb docs on http://www.spec.org
>>
>>for more detail.
>
>I really tought JBB was creating one thread for each "business operation" (a "client
>request"?), not a few long running threads, hum... How scores would be affected if that was the case?
That would definitely change the profile. Threads are expensive to set up and tear down, so this is not a common pattern in Java apps.
Henrik
Topic | Posted By | Date |
---|---|---|
Nehalem review up | David Kanter | 2009/04/07 02:43 AM |
Nehalem review up | noone | 2009/04/07 05:48 AM |
Strange jbb on Harpertown | Henrik S | 2009/04/07 07:29 AM |
Strange jbb on Harpertown | David Kanter | 2009/04/07 10:19 AM |
Strange jbb on Harpertown | Henrik S | 2009/04/07 08:33 PM |
Strange jbb on Harpertown | Chris | 2009/04/07 11:54 PM |
Strange jbb on Harpertown | Henrik S | 2009/04/08 01:40 AM |
Nehalem review up | Vincent Diepeveen | 2009/04/07 07:34 AM |
Nehalem review up | Jack | 2009/04/09 03:51 PM |
Nehalem review up | Vincent Diepeveen | 2009/04/10 12:58 AM |
Nehalem review up | Michael S | 2009/04/10 02:45 AM |
Nehalem review up | EduardoS | 2009/04/10 06:01 AM |
Nehalem review up | Michael S | 2009/04/10 06:56 AM |
Nehalem review up | Eugene Nalimov | 2009/04/10 08:12 AM |
Choice of C compiler doesn't matter much for Java... | Henrik S | 2009/04/10 09:10 AM |
Choice of C compiler doesn't matter much for Java... | EduardoS | 2009/04/10 01:49 PM |
Choice of C compiler doesn't matter much for Java... | Henrik S | 2009/04/11 06:13 AM |
Choice of C compiler doesn't matter much for Java... | EduardoS | 2009/04/11 10:30 AM |
Large pages | David Kanter | 2009/04/11 01:02 PM |
Choice of C compiler doesn't matter much for Java... | Henrik S | 2009/04/11 10:06 PM |
Choice of C compiler doesn't matter much for Java... | Paul | 2009/04/12 12:53 AM |
Choice of C compiler doesn't matter much for Java... | iz | 2009/04/12 01:59 AM |
Choice of C compiler doesn't matter much for Java... | Henrik S | 2009/04/12 06:37 AM |
Choice of C compiler doesn't matter much for Java... | EduardoS | 2009/04/12 07:08 AM |
Choice of C compiler doesn't matter much for Java... | Henrik S | 2009/04/12 08:25 AM |
Choice of C compiler doesn't matter much for Java... | EduardoS | 2009/04/12 04:24 PM |
Choice of C compiler doesn't matter much for Java... | Henrik S | 2009/04/12 09:18 PM |
Thread costs | David Kanter | 2009/04/12 11:12 PM |
Thread costs | Henrik S | 2009/04/14 01:08 PM |
Choice of C compiler doesn't matter much for Java... | Michael S | 2009/04/11 07:53 AM |
Choice of C compiler doesn't matter much for Java... | Henrik S | 2009/04/11 10:08 PM |
Nehalem review up | Vincent Diepeveen | 2009/04/11 03:50 PM |
Nehalem review up | Michael S | 2009/04/11 04:12 PM |
Nehalem review up | Vincent Diepeveen | 2009/04/12 02:01 AM |
Nehalem review up | Michael S | 2009/04/12 04:07 AM |
Nehalem review up | rwessel | 2009/04/07 01:01 PM |
Nehalem review up | slacker | 2009/04/08 08:11 AM |
Energy vs. power | David Kanter | 2009/04/08 09:11 AM |
Energy vs. power | Vincent Diepeveen | 2009/04/10 01:08 AM |
Energy vs. power | slacker | 2009/04/10 08:26 AM |
Energy vs. power | RagingDragon | 2009/04/10 09:19 AM |
Energy vs. power | David Kanter | 2009/04/10 10:47 AM |
Energy vs. power | Jack | 2009/04/10 03:44 PM |
Energy vs. power | slacker | 2009/04/10 06:00 PM |
Energy vs. power | Jack | 2009/04/10 06:31 PM |
Energy vs. power | David Kanter | 2009/04/10 11:16 PM |
Nehalem review up | rwessel | 2009/04/08 01:32 PM |
Minor font issue | gpriatko | 2009/04/07 03:35 PM |
Minor HTML issue | David Kanter | 2009/04/07 08:38 PM |
Minor HTML issue | David Kanter | 2009/04/07 08:39 PM |
Good work, i look forward to linux and SP2 numbers (NT) | PiedPiper | 2009/04/08 12:52 AM |
Nehalem review up | Joe Chang | 2009/04/10 02:59 AM |