From: Theodore Tso <tytso@mit.edu>
To: Peter Zijlstra <peterz@infradead.org>
Cc: edwin <edwintorok@gmail.com>, Ingo Molnar <mingo@elte.hu>,
rml@tech9.net, Linux Kernel <linux-kernel@vger.kernel.org>,
"Thomas Gleixner mingo@redhat.com" <tglx@linutronix.de>,
"H. Peter Anvin" <hpa@zytor.com>
Subject: Re: Quad core CPUs loaded at only 50% when running a CPU and mmap intensive multi-threaded task
Date: Mon, 25 Aug 2008 09:48:01 -0400 [thread overview]
Message-ID: <20080825134801.GN1408@mit.edu> (raw)
In-Reply-To: <1219664477.8515.54.camel@twins>
On Mon, Aug 25, 2008 at 01:41:17PM +0200, Peter Zijlstra wrote:
>
> I would certainly consider this for small (< 1M?) files. With mmap the
> faults and pte overhead aren't free either, and the extra memcpy from
> pread() isn't that much.
>
Even for very big files, if you're only doing a single sequential pass
over a very large file (for example when converting a Canon raw image
file to TIFF format --- I know because I was trying to optimize dcraw
a while aback), you take the page fault for each 4k page, and so
simply using read/pread is faster. And that's on a single-threded
program. With a multithreaded program, the locking issues come on top
of that.
Maybe if I had used hugepages it would have been a win, I suppose, but
I never tried the experiment. And this was several years ago, on much
older hardware, so maybe the relative times of doing the memory copy
versus the page fault, but I wouldn't be surprised if it's even more
expensive to do the mmap, relatively speaking.
- Ted
next prev parent reply other threads:[~2008-08-25 13:48 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <48B1CC15.2040006@gmail.com>
2008-08-25 5:51 ` Quad core CPUs loaded at only 50% when running a CPU and mmap intensive multi-threaded task Peter Zijlstra
2008-08-25 7:04 ` edwin
2008-08-25 9:23 ` Peter Zijlstra
2008-08-25 9:49 ` Török Edwin
2008-08-25 10:02 ` Peter Zijlstra
2008-08-25 10:22 ` Török Edwin
2008-08-25 10:36 ` Peter Zijlstra
2008-08-25 11:00 ` edwin
2008-08-25 11:30 ` edwin
2008-08-25 11:41 ` Peter Zijlstra
2008-08-25 13:48 ` Theodore Tso [this message]
2008-08-26 8:12 ` Andi Kleen
2008-09-08 19:10 ` Török Edwin
2008-09-12 19:16 ` mmap/munmap latency on multithreaded apps, because pagefaults hold mmap_sem during disk read Török Edwin
2008-09-12 19:16 ` Török Edwin
2008-09-12 19:35 ` Mike Waychison
2008-09-12 19:35 ` Mike Waychison
2008-09-12 20:10 ` Török Edwin
2008-09-12 20:10 ` Török Edwin
2008-08-25 10:37 ` Quad core CPUs loaded at only 50% when running a CPU and mmap intensive multi-threaded task Peter Zijlstra
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=20080825134801.GN1408@mit.edu \
--to=tytso@mit.edu \
--cc=edwintorok@gmail.com \
--cc=hpa@zytor.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=peterz@infradead.org \
--cc=rml@tech9.net \
--cc=tglx@linutronix.de \
/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.