From: "Jeff V. Merkey" <jmerkey@wolfmountaingroup.com>
To: Lennart Sorensen <lsorense@csclub.uwaterloo.ca>
Cc: Bernd Eckenfels <be-news06@lina.inka.de>, linux-kernel@vger.kernel.org
Subject: Re: [PATCH] Re: 2G memory split
Date: Tue, 10 Jan 2006 10:13:46 -0700 [thread overview]
Message-ID: <43C3EB4A.6000606@wolfmountaingroup.com> (raw)
In-Reply-To: <20060110185030.GB26581@csclub.uwaterloo.ca>
Lennart Sorensen wrote:
>On Tue, Jan 10, 2006 at 09:30:58AM -0700, Jeff V. Merkey wrote:
>
>
>>Bernd Eckenfels wrote:
>>
>>Here are the patches I use for the splitting. They work well. The
>>methods employed in Red Hat ES are far better and I am surprised
>>no one has simply integrated those patches into the kernel which are 4GB
>>/ 4GB kernel/user.
>>
>>
>
>I was under the impression the 4G/4G split had some non negligable
>performance penalties compared to the other options.
>
>
It does, but from my testing, I/O performance and app performance seems
negligible. I run the highest performing app/driver
on Linux for disk and network I/O loading and ES3 and ES4 are just as
performant with 4:4 as FC2, FC3, and FC4 with
3:1.
I am now able to capture 4 x gigabit segments with 3:1 at sustained
stream to disk rates of 497 MB/S
and 1 x 10Gbe at 517 MB/S stream to disk. I see no appreciable
performance differences 3:1 vs. 4:4. Modern Xeon
processors have gotten a lot better dealing with TLB invalidation. I
suppose applications that remap
memory all over the place or that do tons of swapping would see some
penalty, and I do see some
performance degredation when user space apps start swapping, but it's
difficult to quantify how much is related
to disk I/O latency vs. TLB overhear. Most TLB flushes will cost you 150
clocks over time as the TLB reloads
itself.
Jeff
>Len Sorensen
>
>
>
next prev parent reply other threads:[~2006-01-10 18:58 UTC|newest]
Thread overview: 87+ messages / expand[flat|nested] mbox.gz Atom feed top
2006-01-10 12:58 2G memory split Jens Axboe
2006-01-10 13:29 ` Ingo Molnar
2006-01-10 13:37 ` Jens Axboe
2006-01-10 13:43 ` Byron Stanoszek
2006-01-10 13:47 ` Jens Axboe
2006-01-10 14:39 ` Jens Axboe
2006-01-10 14:44 ` Ingo Molnar
2006-01-10 15:03 ` [PATCH] Address space split configuration Jens Axboe
2006-01-10 15:11 ` Mark Lord
2006-01-10 15:24 ` Mikael Pettersson
2006-01-10 16:14 ` 2G memory split Linus Torvalds
2006-01-10 16:40 ` Mark Lord
2006-01-10 16:52 ` Linus Torvalds
2006-01-10 18:33 ` Coywolf Qi Hunt
2006-01-10 17:07 ` Mark Lord
2006-01-10 17:28 ` Linus Torvalds
2006-01-10 17:32 ` Jens Axboe
2006-01-10 17:37 ` Mark Lord
2006-01-10 18:58 ` Mark Lord
2006-01-10 19:16 ` [PATCH ] VMSPLIT config options (with default config fixed) Mark Lord
2006-01-10 17:37 ` Jeff V. Merkey
2006-01-10 19:27 ` Jens Axboe
2006-01-11 1:13 ` J.A. Magallon
2006-01-11 10:15 ` Jens Axboe
2006-01-11 16:00 ` Greg Norris
2006-01-11 17:13 ` Mark Lord
2006-01-11 17:44 ` Greg Norris
2006-02-05 18:42 ` Barry K. Nathan
2006-02-01 22:23 ` Herbert Poetzl
2006-02-02 11:04 ` Ulrich Mueller
2006-02-02 20:55 ` Jan Engelhardt
2006-02-03 22:39 ` Mark Lord
2006-02-04 10:23 ` Ulrich Mueller
2006-02-04 11:06 ` Jan Engelhardt
2006-02-04 10:36 ` Jens Axboe
2006-02-04 11:05 ` Jan Engelhardt
2006-02-04 13:57 ` Mark Lord
2006-02-05 15:32 ` J.A. Magallon
2006-02-05 15:38 ` Arjan van de Ven
2006-02-05 21:14 ` Jan Engelhardt
2006-02-05 21:19 ` Arjan van de Ven
2006-02-06 14:56 ` Jan Engelhardt
2006-02-07 0:41 ` Herbert Poetzl
2006-02-07 2:51 ` Mark Rustad
2006-02-07 9:38 ` Bernd Petrovitsch
2006-02-07 12:19 ` RFC: add an ADVANCED_USER option Adrian Bunk
2006-02-07 14:05 ` Ulrich Mueller
2006-02-07 14:42 ` Adrian Bunk
2006-02-09 16:06 ` Jan Engelhardt
2006-01-10 17:48 ` 2G memory split Bernd Eckenfels
2006-01-10 16:30 ` [PATCH] " Jeff V. Merkey
2006-01-10 18:50 ` Lennart Sorensen
2006-01-10 17:13 ` Jeff V. Merkey [this message]
2006-01-10 19:42 ` Jens Axboe
2006-01-10 20:17 ` Bernd Eckenfels
2006-01-10 20:28 ` Jens Axboe
2006-01-11 8:39 ` Bernd Eckenfels
2006-01-11 10:06 ` Jens Axboe
2006-01-10 18:14 ` Martin Bligh
2006-01-10 18:34 ` Linus Torvalds
2006-01-10 16:56 ` Jeff V. Merkey
2006-01-10 17:01 ` Jeff V. Merkey
2006-01-10 18:45 ` Mark Lord
2006-01-10 18:46 ` Martin Bligh
2006-01-10 18:58 ` Jens Axboe
2006-01-10 17:17 ` Jeff V. Merkey
2006-01-10 20:55 ` Alan Cox
2006-01-10 19:12 ` Jeff V. Merkey
2006-01-10 21:02 ` Jens Axboe
2006-01-10 19:30 ` Jeff V. Merkey
2006-01-10 18:39 ` Martin Bligh
2006-01-10 18:55 ` Dave Hansen
2006-01-10 19:01 ` Mark Lord
2006-01-10 19:05 ` Dave Hansen
2006-01-10 17:07 ` Sergey Vlasov
2006-04-10 14:11 ` Kirill Korotaev
2006-04-10 14:39 ` Mark Lord
2006-01-10 18:28 ` Coywolf Qi Hunt
2006-01-10 13:47 ` Mikael Pettersson
2006-01-10 13:54 ` Jens Axboe
2006-01-10 14:09 ` Gerd Hoffmann
2006-01-10 14:21 ` Jens Axboe
2006-01-10 14:25 ` Jens Axboe
2006-01-10 20:42 ` Jan Engelhardt
2006-01-11 0:25 ` Con Kolivas
2006-01-10 14:12 ` Mark Lord
2006-01-10 14:22 ` Jens Axboe
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=43C3EB4A.6000606@wolfmountaingroup.com \
--to=jmerkey@wolfmountaingroup.com \
--cc=be-news06@lina.inka.de \
--cc=linux-kernel@vger.kernel.org \
--cc=lsorense@csclub.uwaterloo.ca \
/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).