All of lore.kernel.org
 help / color / mirror / Atom feed
From: Michal Piotrowski <michal.k.k.piotrowski@gmail.com>
To: Peter Williams <pwil3058@bigpond.net.au>
Cc: LKML <linux-kernel@vger.kernel.org>
Subject: Re: [ANNOUNCE][RFC] PlugSched-5.2.4 for 2.6.12 and 2.6.13-rc6
Date: Tue, 16 Aug 2005 14:54:35 +0200	[thread overview]
Message-ID: <6bffcb0e050816055437477aaf@mail.gmail.com> (raw)
In-Reply-To: <4301330B.3070400@bigpond.net.au>

Hi,

On 8/16/05, Peter Williams <pwil3058@bigpond.net.au> wrote:
> Peter Williams wrote:
> > Michal Piotrowski wrote:
> >
> >> Hi,
> >> here are my benchmarks (part1):
> >
> >
> > Would you mind doing a few extra runs when you do Zaphod with different
> > configuration parameters?  Namely:
> >
> > 1. default value for max_ia_bonus and max_tpt_bonus set to zero
> > 2. default value for max_tpt_bonus and max_ia_bonus set to zero
> > 3. both max_tpt_bonus and max_ia_bonus set to zero
> >
> > in addition to the run you've already done with them both set to their
> > defaults.
> >
> > These parameters can be set via the files:
> >
> > /sys/cpusched/zaphod/max_ia_bonus
> > /sys/cpusched/zaphod/max_tpt_bonus
> 
> Also, could you print the schedstat data immediately before each run as
> well as after?  This will enable the amount of cpu consumed by other
> activity on the computer during the run.
> 
> Thanks
> Peter
> --
> Peter Williams                                   pwil3058@bigpond.net.au
> 
> "Learning, n. The kind of ignorance distinguishing the studious."
>   -- Ambrose Bierce
> 

here are additional tests of Zaphod scheduler (part1+).

1 max_ia_bonus=default max_tpt_bonus=1 (<- sorry, my big mistake, I
can rerun it if You think that it is necesery)

ng02:~# cat /proc/schedstat
version 12
timestamp 4294828669
cpu0 6 0 0 50 0 27581 11365 7805 6518 12028 9490 16216
domain0 3 74615 74286 213 10011 369 35 0 74286 813 652 2 5536 718 7 0
652 5898 5392 89 12115 1236 25 0 5392 0 0 0 0 0 0 0 0 0 2765 854 0
cpu1 9 0 0 43 0 23815 9899 6639 3872 9024 8916 13916
domain0 3 75250 74902 17 12551 823 2 0 74902 764 635 1 5312 651 0 0
635 3892 3436 107 10030 924 0 0 3436 1 0 1 0 0 0 0 0 0 1287 557 0

ng02:/usr/src/linux-2.6.12# time make all -j8
[..]
real    53m50.308s
user    73m41.361s
sys     5m47.309s

ng02:/usr/src/linux-2.6.12# cat /proc/scheduler
zaphod
ng02:/usr/src/linux-2.6.12# cat /proc/schedstat
version 12
timestamp 3333744
cpu0 6 0 0 50 0 704151 369300 155105 115309 2553853 9337517 334851
domain0 3 442011 416564 237 2659989 240011 35 0 416564 275875 85866 4
14144768 1493106 7 0 85866 69758 41638 105 2004639 224561 28 0 41638 0
0 0 0 0 0 0 0 0 61856 26188 0
cpu1 9 0 0 43 0 692905 432937 111840 49982 2503830 10233772 259968
domain0 3 444424 413562 138 3196551 288515 6 0 413562 276354 88926 12
14168673 1479753 0 0 88926 43605 18661 135 1513860 191772 1 0 18661 1
0 1 0 0 0 0 0 0 39796 15220 0

(make clean, reboot)

2 max_tpt_bonus=default max_ia_bonus=0

ng02:~# cat /proc/schedstat
version 12
timestamp 4294736329
cpu0 6 0 0 45 0 24443 9581 6929 5524 8469 7482 14862
domain0 3 29996 29706 6 7644 434 1 0 29706 606 463 2 5365 638 0 0 463 4831 4253
129 12121 1189 2 0 4253 0 0 0 0 0 0 0 0 0 2152 943 0
cpu1 9 0 0 47 0 21331 8444 5946 3792 7270 7520 12887
domain0 3 30319 29993 5 10291 652 1 0 29993 583 459 1 4207 545 0 0 459
3709 3135 128 11252 1040 0 0 3135 1 0 1 0 0 0 0 0 0 1405 623 0

ng02:/usr/src/linux-2.6.12# time make all -j8
[..]
real    51m6.564s
user    76m54.454s
sys     6m25.822s

ng02:/usr/src/linux-2.6.12# cat /proc/scheduler
zaphod
ng02:/usr/src/linux-2.6.12# cat /proc/schedstat
version 12
timestamp 2952618
cpu0 6 0 0 45 0 320718 57175 139391 101798 2959644 9817575 263543
domain0 3 152057 151673 11 14914 1062 1 0 151673 270770 97767 2
15285427 1592321 0 0 97767 55159 33566 142 1764130 187626 2 0 33566 0
0 0 0 0 0 0 0 0 64980 23518 0
cpu1 9 0 0 47 0 279159 42693 127159 62177 2367418 11675673 236466
domain0 3 447572 447107 55 18429 1277 12 0 447107 233998 60674 2
15481677 1604012 0 0 60674 42247 20848 156 1733831 187162 0 0 20848 4
0 4 0 0 0 0 0 0 37593 12259 0

(make clean, reboot)

3 max_tpt_bonus=0 max_ia_bonus=0

ng02:/usr/src/linux-2.6.12# cat /proc/schedstat
version 12
timestamp 11675
cpu0 5 0 0 47 0 71540 28537 29644 27894 20805 9048 43003
domain0 3 148153 147803 4 10552 646 0 0 147803 1002 876 2 4529 563 0 0
876 22990 22404 122 12815 1211 2 0 22404 0 0 0 0 0 0 0 0 0 4906 1101 0
cpu1 10 0 0 60 0 31563 12992 9851 4943 17957 7986 18571
domain0 3 147104 146655 141 10768 437 5 0 146655 1160 1021 2 5429 666
0 0 1021 7517 6962 133 12439 1211 1 0 6962 2 0 2 0 0 0 0 0 0 1750 566
0

ng02:/usr/src/linux-2.6.12# time make all -j8
[..]
real    51m6.603s
user    76m52.540s
sys     6m23.543s

ng02:/usr/src/linux-2.6.12# cat /proc/scheduler
zaphod
ng02:/usr/src/linux-2.6.12# cat /proc/schedstat
version 12
timestamp 3115369
cpu0 5 0 0 47 0 374548 76035 167205 128963 2979961 10874604 298513
domain0 3 226463 225988 13 22104 1676 2 0 225988 278776 91526 2
16756230 1738221 0 0 91526 72724 51543 154 1688685 184528 2 0 51543 2
0 2 0 0 0 0 0 0 66687 22160 0
cpu1 10 0 0 60 0 287129 47253 129103 62414 2359157 10725845 239876
domain0 3 533436 532838 197 20068 1159 13 0 532838 240341 53220 3
16822420 1740549 0 0 53220 46356 24486 156 1771913 191086 1 0 24486 4
0 4 0 0 0 0 0 0 38242 12689 0

Regards,
Michal Piotrowski

  parent reply	other threads:[~2005-08-16 12:54 UTC|newest]

Thread overview: 34+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2005-08-15  4:46 [ANNOUNCE][RFC] PlugSched-5.2.4 for 2.6.12 and 2.6.13-rc6 Peter Williams
2005-08-15 12:29 ` Michal Piotrowski
     [not found]   ` <43012427.9080406@bigpond.net.au>
     [not found]     ` <4301330B.3070400@bigpond.net.au>
2005-08-16 12:54       ` Michal Piotrowski [this message]
2005-08-17  8:00   ` Con Kolivas
2005-08-17 11:23     ` Michal Piotrowski
2005-08-17 12:31       ` Con Kolivas
2005-08-16 21:49 ` Schedulers benchmark - Was: " Michal Piotrowski
2005-08-17  8:10   ` Peter Williams
2005-08-17  9:03     ` Con Kolivas
2005-08-17 18:04       ` Michal Piotrowski
2005-08-17 21:35         ` Con Kolivas
2005-08-17 23:15       ` Peter Williams
2005-08-17 23:16         ` Con Kolivas
2005-08-17 23:48           ` Peter Williams
2005-08-17 23:45             ` Con Kolivas
2005-08-19  3:09               ` Michal Piotrowski
2005-08-19  3:28                 ` Lee Revell
2005-08-19  3:41                   ` Con Kolivas
2005-08-19  4:41                     ` Peter Williams
2005-08-19  4:36                       ` Con Kolivas
2005-08-19 20:13                         ` Lee Revell
2005-08-20  0:31                           ` Con Kolivas
2005-08-20  3:04                             ` Lee Revell
2005-08-20 18:52                             ` Lee Revell
2005-08-19  4:26                   ` Peter Williams
2005-08-17 11:59     ` Michal Piotrowski
2005-08-21  1:34   ` Michal Piotrowski
2005-08-21  1:47     ` Con Kolivas
2005-08-21  4:16       ` Michal Piotrowski
2005-08-21  4:22         ` Con Kolivas
2005-08-21  4:44           ` Michal Piotrowski
2005-08-21  4:49             ` Con Kolivas
2005-08-21  1:37   ` Michal Piotrowski
     [not found]     ` <4309125B.4020707@bigpond.net.au>
2005-08-22 11:39       ` Michal Piotrowski

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=6bffcb0e050816055437477aaf@mail.gmail.com \
    --to=michal.k.k.piotrowski@gmail.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=pwil3058@bigpond.net.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.