All of lore.kernel.org
 help / color / mirror / Atom feed
From: rwhron@earthlink.net
To: piggin@cyberone.com.au
Cc: linux-kernel@vger.kernel.org
Subject: Re: [BENCHMARK] I/O regression after 2.6.0-test5
Date: Thu, 23 Oct 2003 20:10:58 -0400	[thread overview]
Message-ID: <20031024001035.GA13840@rushmore> (raw)

> Randy can reproduce regressions, so I'll work on his first.

Below is test8 and test8 with the test5 as-iosched.c (2.6.0-test8-as).
Jobs/minute is way up, and total runtime is way down with the test5
as-iosched.c.   

The machine (quad P3 xeon) locked up during a bonnie++ run.  I can't
compare that to vanilla test8 because I stopped the test8 to run the
test5 as-iosched.   Both of these were compiled with gcc-3.3.1 because
of the RedHat gcc-2.96 bug in test8.  (In case the compiler was part
of the instability).

Earlier I ran 2.6.0-test3-mm2 compiled with gcc-3.3.1, and it
was stable on this box.

AIM7 dbase workload
kernel                   Tasks   Jobs/Min       Real    CPU
2.6.0-test8-as           32	601.0	       316.3	134.0
2.6.0-test8              32	299.8	       634.0	128.6

2.6.0-test8-as           64	782.6	       485.8	259.2
2.6.0-test8              64	450.5	       843.9	246.5

2.6.0-test8-as           96	869.1	       656.1	387.6
2.6.0-test8              96	549.7	       1037.4	366.0

2.6.0-test8-as           128	919.3	       827.0	522.8
2.6.0-test8              128	558.7	       1360.8	497.6

2.6.0-test8-as           160	955.0	       995.2	650.3
2.6.0-test8              160	522.1	       1820.2	612.2

2.6.0-test8-as           192	981.9	       1161.5	790.9
2.6.0-test8              192	515.5	       2212.4	742.7

2.6.0-test8-as           224	1002.3	       1327.5	910.2
2.6.0-test8              224	529.9	       2510.8	859.5

2.6.0-test8-as           256	1009.9	       1505.7	1027.7
2.6.0-test8              256	552.4	       2753.0	980.4


AIM7 fserver workload
kernel                   Tasks   Jobs/Min       Real    CPU
2.6.0-test8-as           4	80.5	       301.0	37.0
2.6.0-test8              4	42.3	       573.6	40.9

2.6.0-test8-as           8	133.0	       364.6	64.0
2.6.0-test8              8	63.3	       765.7	71.6

2.6.0-test8-as           12	166.7	       436.3	93.4
2.6.0-test8              12	83.2	       874.2	95.0

2.6.0-test8-as           16	175.9	       551.2	111.5
2.6.0-test8              16	87.5	       1108.4	102.5

2.6.0-test8-as           20	186.3	       650.7	133.8
2.6.0-test8              20	105.0	       1154.6	136.7

2.6.0-test8-as           24	202.8	       717.3	161.2
2.6.0-test8              24	111.2	       1308.1	162.2

2.6.0-test8-as           28	207.1	       819.3	200.0
2.6.0-test8              28	130.7	       1297.9	185.8

2.6.0-test8-as           32	210.6	       920.7	226.5
2.6.0-test8              32	134.2	       1444.5	212.9


AIM7 shared workload
kernel                   Tasks   Jobs/Min       Real    CPU
2.6.0-test8-as           64	1949.6	       191.1	170.8
2.6.0-test8              64	829.1	       449.3	167.8

2.6.0-test8-as           128	2148.3	       346.8	339.2
2.6.0-test8              128	1105.2	       674.1	330.5

2.6.0-test8-as           192	2265.7	       493.2	507.1
2.6.0-test8              192	1320.0	       846.6	504.7

2.6.0-test8-as           256	2382.9	       625.3	678.0
2.6.0-test8              256	1462.1	       1019.0	672.7

2.6.0-test8-as           320	2450.5	       760.0	853.7
2.6.0-test8              320	1573.0	       1184.0	845.2

2.6.0-test8-as           384	2517.4	       887.8	1030.6
2.6.0-test8              384	1601.1	       1395.9	1028.7

2.6.0-test8-as           448	2547.5	       1023.5	1214.4
2.6.0-test8              448	1659.7	       1571.0	1205.2

2.6.0-test8-as           512	2594.6	       1148.5	1389.7
2.6.0-test8              512	1614.4	       1845.8	1381.5

I'm running Nick's patch
http://marc.theaimsgroup.com/?l=linux-kernel&m=106688130229337&w=2
on test8 at the moment.  I should have some comparison numbers 
within 24 hours.

-- 
Randy Hron
http://home.earthlink.net/~rwhron/kernel/bigbox.html


             reply	other threads:[~2003-10-24  0:07 UTC|newest]

Thread overview: 25+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2003-10-24  0:10 rwhron [this message]
  -- strict thread matches above, loose matches on Subject: below --
2003-10-29  0:38 [BENCHMARK] I/O regression after 2.6.0-test5 rwhron
2003-10-27 23:33 John Hawkes
2003-10-26 10:38 rwhron
2003-10-27 23:49 ` Dave Olien
2003-10-24 23:43 rwhron
2003-10-24 12:46 rwhron
2003-10-21 13:05 rwhron
2003-10-21 15:57 ` Nick Piggin
2003-10-21 21:07 ` venom
2003-10-22  9:54 ` Nick Piggin
2003-10-22 18:30   ` Dave Olien
2003-10-22 19:08     ` Dave Olien
2003-10-23  2:24     ` Nick Piggin
2003-10-23  3:48       ` Nick Piggin
2003-10-23 20:35       ` Dave Olien
2003-10-23 23:07         ` Nick Piggin
2003-10-20  0:37 rwhron
2003-10-20  1:35 ` Nick Piggin
2003-10-20  4:52   ` Andrew Morton
2003-10-20  8:12     ` Nick Piggin
2003-10-20  4:51 ` Dave Olien
2003-10-20  7:55   ` venom
2003-10-21  4:49     ` Nick Piggin
2003-10-24 13:52 ` Magnus Andersson

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=20031024001035.GA13840@rushmore \
    --to=rwhron@earthlink.net \
    --cc=linux-kernel@vger.kernel.org \
    --cc=piggin@cyberone.com.au \
    /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.