From: Ingo Molnar <mingo@elte.hu>
To: Avi Kivity <avi@redhat.com>
Cc: Sasha Levin <levinsasha928@gmail.com>,
Pekka Enberg <penberg@kernel.org>,
Takuya Yoshikawa <yoshikawa.takuya@oss.ntt.co.jp>,
kvm@vger.kernel.org, asias.hejun@gmail.com, gorcunov@gmail.com,
prasadjoshi124@gmail.com,
"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>,
takuya.yoshikawa@gmail.com
Subject: Re: [PATCH v2 6/8] kvm tools: Add rwlock wrapper
Date: Mon, 30 May 2011 21:32:53 +0200 [thread overview]
Message-ID: <20110530193253.GA5707@elte.hu> (raw)
In-Reply-To: <4DE3AED3.7070405@redhat.com>
* Avi Kivity <avi@redhat.com> wrote:
> > Also, a profile of a typical kernel build shows:
> >
> > 0.69% cc1 [kernel.kallsyms] [k] clear_page_c
> > 0.49% cc1 [kernel.kallsyms] [k] page_fault
> >
> > So while we could improve it, the question is, can we do this without
> > accidentally slowing things down by more than 0.69%? And kernel
> > builds are a pretty clear_page_c() intense workload.
>
> I usually see much higher clear_page_c, but I'm using a pretty old
> system for most of my testing.
Well, clear_page_c() is still the most expensive kernel function.
I'd suggest using a modern system *and* using percise PEBS profiling
via perf record -e cycles:pp - otherwise it's easy to see profiling
artifacts, especially in and around short functions like
clear_page_c().
Thanks,
Ingo
next prev parent reply other threads:[~2011-05-30 19:33 UTC|newest]
Thread overview: 72+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-05-30 8:30 [PATCH v2 1/8] kvm tools: Use correct value for user signal base Sasha Levin
2011-05-30 8:30 ` [PATCH v2 2/8] kvm tools: Remove wrong global definition of kvm Sasha Levin
2011-05-30 8:38 ` Ingo Molnar
2011-05-30 8:59 ` Sasha Levin
2011-05-30 8:30 ` [PATCH v2 3/8] kvm tools: Allow pausing guests Sasha Levin
2011-05-30 8:39 ` Ingo Molnar
2011-05-30 8:30 ` [PATCH v2 4/8] kvm tools: Pause/resume guest using SIGUSR2 Sasha Levin
2011-05-30 8:41 ` Ingo Molnar
2011-05-30 8:30 ` [PATCH v2 5/8] kvm tools: Add a brlock Sasha Levin
2011-05-30 8:30 ` [PATCH v2 6/8] kvm tools: Add rwlock wrapper Sasha Levin
2011-05-30 8:43 ` Ingo Molnar
2011-05-30 9:29 ` Pekka Enberg
2011-05-30 9:34 ` Sasha Levin
2011-05-30 9:40 ` Pekka Enberg
2011-05-30 9:46 ` Sasha Levin
2011-05-30 9:48 ` Pekka Enberg
2011-05-30 9:54 ` Ingo Molnar
2011-05-30 11:11 ` Takuya Yoshikawa
2011-05-30 11:12 ` Sasha Levin
2011-05-30 11:26 ` Takuya Yoshikawa
2011-05-30 11:39 ` Avi Kivity
2011-05-30 11:49 ` Ingo Molnar
2011-05-30 11:55 ` Pekka Enberg
2011-05-30 11:58 ` Sasha Levin
2011-05-30 12:20 ` Ingo Molnar
2011-05-30 12:22 ` Sasha Levin
2011-05-30 12:25 ` Avi Kivity
2011-05-30 12:23 ` Avi Kivity
2011-05-30 12:30 ` Pekka Enberg
2011-05-30 12:32 ` Avi Kivity
2011-05-30 14:10 ` Ingo Molnar
2011-05-30 14:30 ` Avi Kivity
2011-05-30 14:43 ` Ingo Molnar
2011-05-30 14:50 ` Avi Kivity
2011-05-30 19:32 ` Ingo Molnar [this message]
2011-05-30 12:04 ` Avi Kivity
2011-05-30 12:36 ` Ingo Molnar
2011-05-30 12:44 ` Avi Kivity
2011-05-30 12:46 ` Pekka Enberg
2011-05-30 12:48 ` Avi Kivity
2011-05-30 13:05 ` Sasha Levin
2011-06-03 7:27 ` Sasha Levin
2011-06-03 7:34 ` Ingo Molnar
2011-06-03 7:54 ` Sasha Levin
2011-06-03 19:31 ` Paul E. McKenney
2011-06-03 19:56 ` Sasha Levin
2011-06-03 20:22 ` Paul E. McKenney
2011-06-03 21:03 ` Sasha Levin
2011-06-03 21:20 ` Paul E. McKenney
2011-06-03 22:54 ` Sasha Levin
2011-06-03 23:05 ` Paul E. McKenney
2011-06-04 6:26 ` Sasha Levin
2011-06-04 16:30 ` Paul E. McKenney
2011-06-14 22:26 ` Sasha Levin
2011-06-14 23:42 ` Paul E. McKenney
2011-06-15 1:25 ` Sasha Levin
2011-06-15 4:22 ` Paul E. McKenney
2011-06-05 12:12 ` Avi Kivity
2011-05-30 14:16 ` Takuya Yoshikawa
2011-05-30 9:56 ` Ingo Molnar
2011-05-30 10:05 ` Sasha Levin
2011-05-30 10:13 ` Ingo Molnar
2011-05-30 10:22 ` Sasha Levin
2011-05-30 10:30 ` Ingo Molnar
2011-05-30 10:41 ` Sasha Levin
2011-05-30 8:30 ` [PATCH v2 7/8] kvm tools: Add debug mode to brlock Sasha Levin
2011-05-30 8:30 ` [PATCH v2 8/8] kvm tools: Use brlock in MMIO and IOPORT Sasha Levin
2011-05-30 8:47 ` Ingo Molnar
2011-05-30 8:56 ` Sasha Levin
2011-05-30 8:35 ` [PATCH v2 1/8] kvm tools: Use correct value for user signal base Ingo Molnar
2011-05-30 8:40 ` Sasha Levin
2011-05-30 8:49 ` Ingo Molnar
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=20110530193253.GA5707@elte.hu \
--to=mingo@elte.hu \
--cc=asias.hejun@gmail.com \
--cc=avi@redhat.com \
--cc=gorcunov@gmail.com \
--cc=kvm@vger.kernel.org \
--cc=levinsasha928@gmail.com \
--cc=paulmck@linux.vnet.ibm.com \
--cc=penberg@kernel.org \
--cc=prasadjoshi124@gmail.com \
--cc=takuya.yoshikawa@gmail.com \
--cc=yoshikawa.takuya@oss.ntt.co.jp \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.