From: vx 8400 <vx8400@gmail.com>
To: community@lists.altlinux.org
Subject: [Comm] p5: ложки дёгтя
Date: Tue, 13 Oct 2009 17:47:37 +0200
Message-ID: <89eb42f0910130847q4acb4c13of1ec4220600ab9c8@mail.gmail.com> (raw)
[-- Attachment #1: Type: text/plain, Size: 353 bytes --]
Добрый день,
После обновлении ядра 2.6.18 -> 2.6.30 на вчерашнем Sisyphus
обнаружилась потеря производительности в тестах unixbench-5.1.2.
Тест сделан после сравнения на глаз "шустрости" школьных ALT 4.0.* и
ALT 5.0.0beta, последний был субъективно медленнее первого при всех
прочих равных.
Таблица с результатами unixbench прилагается.
WBR,
Oleg.
[-- Attachment #2: ubench-2618-2630.txt --]
[-- Type: text/plain, Size: 4139 bytes --]
óÅÇÏÄÎÑÛÎÉÊ Sisyphus, unixbench-5.1.2
Machine: i686 (unknown)
CPU 0: Pentium III (Coppermine) (1862.2 bogomips)
MMX, Physical Address Ext, SYSENTER/SYSEXIT
--------------------------------------------------------------------------------+-------------------------------------
|
2.6.30-std-def-alt14 | 2.6.18-std-smp-alt12.M40.3
|
--------------------------------------------------------------------------------+-------------------------------------
Dhrystone 2 using register variables 2904437.4 lps (10.0 s, 7 samples) | 2908725.4 lps (10.0 s, 7 samples)
Double-Precision Whetstone 715.9 MWIPS (10.1 s, 7 samples) | 720.0 MWIPS (10.1 s, 7 samples)
--------------------------------------------------------------------------------+-------------------------------------
Execl Throughput 978.5 lps (30.0 s, 2 samples) | 1352.5 lps (29.9 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 76218.4 KBps (30.0 s, 2 samples) | 90831.9 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 27673.0 KBps (30.0 s, 2 samples) | 34464.9 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 131056.0 KBps (30.0 s, 2 samples) | 151142.7 KBps (30.0 s, 2 samples)
Pipe Throughput 289973.2 lps (10.0 s, 7 samples) | 350222.1 lps (10.0 s, 7 samples)
Pipe-based Context Switching 67133.6 lps (10.0 s, 7 samples) | 124194.3 lps (10.0 s, 7 samples)
Process Creation 3742.1 lps (30.0 s, 2 samples) | 6554.9 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 871.1 lpm (60.0 s, 2 samples) | 961.9 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 116.1 lpm (60.5 s, 2 samples) | 129.1 lpm (60.4 s, 2 samples)
System Call Overhead 541854.0 lps (10.0 s, 7 samples) | 527148.6 lps (10.0 s, 7 samples)
|
System Benchmarks Index Values BASELINE RESULT INDEX | BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 2904437.4 248.9 | 116700.0 2908725.4 249.2
Double-Precision Whetstone 55.0 715.9 130.2 | 55.0 720.0 130.9
--------------------------------------------------------------------------------+-------------------------------------
Execl Throughput 43.0 978.5 227.6 | 43.0 1352.5 314.5
File Copy 1024 bufsize 2000 maxblocks 3960.0 76218.4 192.5 | 3960.0 90831.9 229.4
File Copy 256 bufsize 500 maxblocks 1655.0 27673.0 167.2 | 1655.0 34464.9 208.2
File Copy 4096 bufsize 8000 maxblocks 5800.0 131056.0 226.0 | 5800.0 151142.7 260.6
Pipe Throughput 12440.0 289973.2 233.1 | 12440.0 350222.1 281.5
Pipe-based Context Switching 4000.0 67133.6 167.8 | 4000.0 124194.3 310.5
Process Creation 126.0 3742.1 297.0 | 126.0 6554.9 520.2
Shell Scripts (1 concurrent) 42.4 871.1 205.4 | 42.4 961.9 226.9
Shell Scripts (8 concurrent) 6.0 116.1 193.4 | 6.0 129.1 215.1
System Call Overhead 15000.0 541854.0 361.2 | 15000.0 527148.6 351.4
======== | ========
System Benchmarks Index Score 213.4 | 260.9
next reply other threads:[~2009-10-13 15:47 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-10-13 15:47 vx 8400 [this message]
2009-10-13 19:58 ` Michael Shigorin
2009-10-13 22:39 ` vx 8400
2009-10-14 8:12 ` Michael Shigorin
2009-10-14 8:22 ` Dmitriy Kruglikov
2009-10-14 8:49 ` Владимир Гусев
2009-10-14 9:00 ` vx 8400
2009-10-14 11:41 ` Michael Shigorin
2009-10-14 11:39 ` Michael Shigorin
2009-10-14 11:47 ` alisher
2009-10-14 19:57 ` Michael Shigorin
2009-10-16 4:22 ` alisher
2009-10-14 9:55 ` [Comm] p5: ложки дёгтя [slower kernel] Michael Shigorin
2009-10-15 21:14 ` vx 8400
2009-10-15 21:38 ` Michael Shigorin
2009-10-15 22:15 ` vx 8400
2009-10-16 9:44 ` alisher
2009-10-16 10:02 ` Michael Shigorin
2009-10-16 10:04 ` alisher
2009-10-16 10:18 ` Andrey Rahmatullin
2009-10-16 10:15 ` Michael Shigorin
2009-10-14 10:04 ` [Comm] p5: ложки дёгтя Владимир Гусев
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=89eb42f0910130847q4acb4c13of1ec4220600ab9c8@mail.gmail.com \
--to=vx8400@gmail.com \
--cc=community@lists.altlinux.org \
/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
ALT Linux Community general discussions
This inbox may be cloned and mirrored by anyone:
git clone --mirror http://lore.altlinux.org/community/0 community/git/0.git
# If you have public-inbox 1.1+ installed, you may
# initialize and index your mirror using the following commands:
public-inbox-init -V2 community community/ http://lore.altlinux.org/community \
mandrake-russian@linuxteam.iplabs.ru community@lists.altlinux.org community@lists.altlinux.ru community@lists.altlinux.com
public-inbox-index community
Example config snippet for mirrors.
Newsgroup available over NNTP:
nntp://lore.altlinux.org/org.altlinux.lists.community
AGPL code for this site: git clone https://public-inbox.org/public-inbox.git