From: "Paolo Ciarrocchi" <ciarrocchi@linuxmail.org>
To: "Martin J. Bligh" <mbligh@aracnet.com>,
ciarrocchi@linuxmail.org, linux-kernel@vger.kernel.org
Cc: akpm@digeo.com
Subject: Re: [BENCHMARK] AIM9 results. 2.4.19 vs 2.5.58 vs 2.5.63
Date: Sat, 01 Mar 2003 20:47:59 +0800 [thread overview]
Message-ID: <20030301124759.10054.qmail@linuxmail.org> (raw)
From: "Martin J. Bligh" <mbligh@aracnet.com>
Date: Thu, 27 Feb 2003 14:16:16 -0800
To: Paolo Ciarrocchi <ciarrocchi@linuxmail.org>, linux-kernel@vger.kernel.org
Subject: Re: [BENCHMARK] AIM9 results. 2.4.19 vs 2.5.58 vs 2.5.63
[...]
> Could you compare 63 mainline to -mjb or -mm with objrmap patches in?
> I think you'll get significant improvements on the tests above.
Of course I can.
And here it goes the results:
2.4.19
2.5.63
2.5.63-mjb2
creat-clo 10040 19.4223 19422.31 File Creations and Closes/second
creat-clo 10010 84.3157 84315.68 File Creations and Closes/second
creat-clo 10000 87.4 87400.00 File Creations and Closes/second
^^^mjb2 is faster than 2.5.63
brk_test 10010 48.951 832167.83 System Memory Allocations/second
brk_test 10020 41.018 697305.39 System Memory Allocations/second
brk_test 10000 41.3 702100.00 System Memory Allocations/second
^^^Still slower than 2.4.19
signal_test 10000 166.1 166100.00 Signal Traps/second
signal_test 10000 148.3 148300.00 Signal Traps/second
signal_test 10010 151.748 151748.25 Signal Traps/second
^^^Still slower than 2.4.19
exec_test 10000 13.8 69.00 Program Loads/second
exec_test 10020 12.7745 63.87 Program Loads/second
exec_test 10010 12.987 64.94 Program Loads/second
^^^Still slower than 2.4.19
fork_test 10000 44.8 4480.00 Task Creations/second
fork_test 10000 23.2 2320.00 Task Creations/second
fork_test 10020 30.0399 3003.99 Task Creations/second
^^^mjb2 is faster than 2.5.63
link_test 10000 155.3 9783.90 Link/Unlink Pairs/second
link_test 10010 160.739 10126.57 Link/Unlink Pairs/second
link_test 10010 150.25 9465.73 Link/Unlink Pairs/second
^^^mmh... strange
array_rtns 10010 13.6863 273.73 Linear Systems Solved/second
array_rtns 10020 11.2774 225.55 Linear Systems Solved/second
array_rtns 10050 13.5323 270.65 Linear Systems Solved/second
^^^^^^mjb2 is faster than 2.5.63
mem_rtns_1 10000 27.7 831000.00 Dynamic Memory Operations/second
mem_rtns_1 10020 22.7545 682634.73 Dynamic Memory Operations/second
mem_rtns_1 10020 25.0499 751497.01 Dynamic Memory Operations/second
^^^mjb2 is faster than 2.5.63
misc_rtns_1 10000 782.2 7822.00 Auxiliary Loops/second
misc_rtns_1 10000 686.9 6869.00 Auxiliary Loops/second
misc_rtns_1 10000 709.7 7097.00 Auxiliary Loops/second
^^^mjb2 is faster than 2.5.63
dgram_pipe 10000 2357.8 235780.00 DataGram Pipe Messages/second
dgram_pipe 10000 1978 197800.00 DataGram Pipe Messages/second
dgram_pipe 10000 2078.1 207810.00 DataGram Pipe Messages/second
^^^mjb2 is faster than 2.5.63
Let me know if you need further tests/information.
Ciao,
Paolo
--
______________________________________________
http://www.linuxmail.org/
Now with e-mail forwarding for only US$5.95/yr
Powered by Outblaze
next reply other threads:[~2003-03-01 12:37 UTC|newest]
Thread overview: 3+ messages / expand[flat|nested] mbox.gz Atom feed top
2003-03-01 12:47 Paolo Ciarrocchi [this message]
-- strict thread matches above, loose matches on Subject: below --
2003-02-27 21:39 [BENCHMARK] AIM9 results. 2.4.19 vs 2.5.58 vs 2.5.63 Paolo Ciarrocchi
2003-02-27 22:16 ` Martin J. Bligh
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=20030301124759.10054.qmail@linuxmail.org \
--to=ciarrocchi@linuxmail.org \
--cc=akpm@digeo.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mbligh@aracnet.com \
/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.