From: Pekka Enberg <penberg@cs.helsinki.fi>
To: Ingo Molnar <mingo@elte.hu>
Cc: Tim Blechmann <tim@klingt.org>,
linux-kernel@vger.kernel.org,
Christoph Lameter <cl@linux-foundation.org>,
Nick Piggin <npiggin@suse.de>,
David Rientjes <rientjes@google.com>
Subject: Re: [PATCH 3/5] slab.c: remove branch hint
Date: Wed, 25 Nov 2009 12:41:57 +0200 [thread overview]
Message-ID: <4B0D09F5.6020305@cs.helsinki.fi> (raw)
In-Reply-To: <20091124114218.GA24396@elte.hu>
Ingo Molnar kirjoitti:
>> That sounds odd to me. Can you see where the incorrectly predicted
>> calls are coming from? Calling kmem_cache_alloc_node() with node set
>> to -1 most of the time could be a real bug somewhere.
>
> I think it could occur in too limited tests - the branch prediction
> looks 'wrong' in certain tests - while it's OK in general.
>
> Is there some easy to run workload you consider more or less
> representative of typical SLAB patterns?
I can think of three main classes: VFS, SCSI, or network intensive
applications and benchmarks tend to bring out the worst in SLAB. There
are probably some interesting NUMA related things that I'm not really
aware of.
next prev parent reply other threads:[~2009-11-25 10:41 UTC|newest]
Thread overview: 29+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <cover.1259059549.git.tim@klingt.org>
2009-11-24 10:55 ` [PATCH 1/5] process_64: remove branch hint Tim Blechmann
2009-11-24 16:57 ` [tip:sched/core] sched, x86: Optimize branch hint in __switch_to() tip-bot for Tim Blechmann
2009-11-24 17:28 ` Brian Gerst
2009-11-25 9:03 ` Tim Blechmann
2009-11-25 15:53 ` Brian Gerst
2009-11-25 16:16 ` index 780cd92..22db86a 100644 Brian Gerst
2009-11-25 16:17 ` [PATCH] x86, 64-bit: Set data segments to null after switching to 64-bit mode Brian Gerst
2009-11-26 9:56 ` [tip:x86/asm] " tip-bot for Brian Gerst
2009-11-29 11:44 ` [PATCH] " Tim Blechmann
2009-12-02 11:32 ` [PATCH] Revert "sched, x86: Optimize branch hint in __switch_to()" Tim Blechmann
2009-12-02 13:27 ` [tip:sched/core] " tip-bot for Tim Blechmann
2009-11-24 10:55 ` [PATCH 2/5] sched.c: change branch hint Tim Blechmann
2009-11-24 16:56 ` [tip:sched/core] sched: Optimize branch hint in context_switch() tip-bot for Tim Blechmann
2009-11-24 10:55 ` [PATCH 3/5] slab.c: remove branch hint Tim Blechmann
2009-11-24 11:20 ` Ingo Molnar
2009-11-24 11:28 ` Pekka Enberg
2009-11-24 11:42 ` Ingo Molnar
2009-11-25 10:41 ` Pekka Enberg [this message]
2009-11-24 11:45 ` Tim Blechmann
2009-11-29 11:36 ` Tim Blechmann
2009-11-30 9:05 ` Pekka Enberg
2009-11-30 16:09 ` Christoph Lameter
2009-11-30 17:44 ` Pekka Enberg
2009-11-30 17:50 ` Christoph Lameter
2009-11-30 17:59 ` [PATCH] branch profiling on my nehalem machine showed 99% incorrect branch hints: Tim Blechmann
2009-12-06 8:33 ` Pekka Enberg
2009-11-24 10:55 ` [PATCH 4/5] sched_fair.c: remove branch hint Tim Blechmann
2009-11-24 16:56 ` [tip:sched/core] sched: Optimize branch hint in pick_next_task_fair() tip-bot for Tim Blechmann
2009-11-24 10:55 ` [PATCH 5/5] workqueue.c: remove branch hint Tim Blechmann
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=4B0D09F5.6020305@cs.helsinki.fi \
--to=penberg@cs.helsinki.fi \
--cc=cl@linux-foundation.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=npiggin@suse.de \
--cc=rientjes@google.com \
--cc=tim@klingt.org \
/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