From: Ingo Molnar <mingo@elte.hu>
To: Jie Chen <chen@jlab.org>
Cc: Simon Holm Th??gersen <odie@cs.aau.dk>,
Eric Dumazet <dada1@cosmosbay.com>,
linux-kernel@vger.kernel.org,
Peter Zijlstra <a.p.zijlstra@chello.nl>
Subject: Re: Possible bug from kernel 2.6.22 and above, 2.6.24-rc4
Date: Thu, 6 Dec 2007 11:43:18 +0100 [thread overview]
Message-ID: <20071206104318.GB30838@elte.hu> (raw)
In-Reply-To: <47572353.4040606@jlab.org>
* Jie Chen <chen@jlab.org> wrote:
>> not "BARRIER time". I've re-read the discussion and found no hint
>> about how to build and run a barrier test. Either i missed it or it's
>> so obvious to you that you didnt mention it :-)
>>
>> Ingo
>
> Hi, Ingo:
>
> Did you do configure --enable-public-release? My qmt is for qcd
> calculation (one type of physics code) [...]
yes, i did exactly as instructed.
> [...]. Without the above flag one can only test PARALLEL overhead.
> Actually the PARALLEL benchmark has the same behavior as the BARRIER.
> Thanks.
hm, but PARALLEL does not seem to do that much context switching. So
basically you create the threads and do a few short runs to establish
overhead? Threads do not get fork-balanced at the moment - but turning
it on would be easy. Could you try the patch below - how does it impact
your results? (and please keep affinity setting off)
Ingo
----------->
Subject: sched: reactivate fork balancing
From: Ingo Molnar <mingo@elte.hu>
reactivate fork balancing.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
include/linux/topology.h | 3 +++
1 file changed, 3 insertions(+)
Index: linux/include/linux/topology.h
===================================================================
--- linux.orig/include/linux/topology.h
+++ linux/include/linux/topology.h
@@ -103,6 +103,7 @@
.forkexec_idx = 0, \
.flags = SD_LOAD_BALANCE \
| SD_BALANCE_NEWIDLE \
+ | SD_BALANCE_FORK \
| SD_BALANCE_EXEC \
| SD_WAKE_AFFINE \
| SD_WAKE_IDLE \
@@ -134,6 +135,7 @@
.forkexec_idx = 1, \
.flags = SD_LOAD_BALANCE \
| SD_BALANCE_NEWIDLE \
+ | SD_BALANCE_FORK \
| SD_BALANCE_EXEC \
| SD_WAKE_AFFINE \
| SD_WAKE_IDLE \
@@ -165,6 +167,7 @@
.forkexec_idx = 1, \
.flags = SD_LOAD_BALANCE \
| SD_BALANCE_NEWIDLE \
+ | SD_BALANCE_FORK \
| SD_BALANCE_EXEC \
| SD_WAKE_AFFINE \
| BALANCE_FOR_PKG_POWER,\
next prev parent reply other threads:[~2007-12-06 10:44 UTC|newest]
Thread overview: 35+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-11-21 20:34 Possible bug from kernel 2.6.22 and above Jie Chen
2007-11-21 22:14 ` Eric Dumazet
2007-11-22 1:52 ` Jie Chen
2007-11-22 2:32 ` Simon Holm Thøgersen
2007-11-22 2:58 ` Jie Chen
2007-11-22 20:19 ` Matt Mackall
2007-12-04 13:17 ` Possible bug from kernel 2.6.22 and above, 2.6.24-rc4 Ingo Molnar
2007-12-04 15:41 ` Jie Chen
2007-12-05 15:29 ` Jie Chen
2007-12-05 15:40 ` Ingo Molnar
2007-12-05 16:16 ` Eric Dumazet
2007-12-05 16:25 ` Ingo Molnar
2007-12-05 16:29 ` Eric Dumazet
2007-12-05 16:22 ` Jie Chen
2007-12-05 16:47 ` Ingo Molnar
2007-12-05 17:47 ` Jie Chen
2007-12-05 20:03 ` Ingo Molnar
2007-12-05 20:23 ` Jie Chen
2007-12-05 20:46 ` Ingo Molnar
2007-12-05 20:52 ` Jie Chen
2007-12-05 21:02 ` Ingo Molnar
2007-12-05 22:16 ` Jie Chen
2007-12-06 10:43 ` Ingo Molnar [this message]
2007-12-06 16:29 ` Jie Chen
2007-12-10 10:59 ` Ingo Molnar
2007-12-10 20:04 ` Jie Chen
2007-12-11 10:51 ` Ingo Molnar
2007-12-11 15:28 ` Jie Chen
2007-12-11 15:52 ` Ingo Molnar
2007-12-11 16:39 ` Jie Chen
2007-12-11 21:23 ` Ingo Molnar
2007-12-11 22:11 ` Jie Chen
2007-12-12 12:49 ` Peter Zijlstra
2007-12-05 20:36 ` Possible bug from kernel 2.6.22 and above Peter Zijlstra
2007-12-05 20:53 ` Jie Chen
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20071206104318.GB30838@elte.hu \
--to=mingo@elte.hu \
--cc=a.p.zijlstra@chello.nl \
--cc=chen@jlab.org \
--cc=dada1@cosmosbay.com \
--cc=linux-kernel@vger.kernel.org \
--cc=odie@cs.aau.dk \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).