Home » Mailing list archives » linux-kernel » 2007 » November » 9

iozone write 50% regression in kernel 2.6.24-rc1

Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]
[view in full thread]
From: Zhang, Yanmin
Subject: iozone write 50% regression in kernel 2.6.24-rc1
Date: Friday, November 9, 2007 - 2:47 am

Comparing with 2.6.23, iozone sequential write/rewrite (512M) has 50% regression
in kernel 2.6.24-rc1. 2.6.24-rc2 has the same regression.

My machine has 8 processor cores and 8GB memory.

By bisect, I located patch
http://git.kernel.org/?p=linux/kernel/git/torvalds/linux-2.6.git;a=commitdiff;h=04fbfd....


Another behavior: with kernel 2.6.23, if I run iozone for many times after rebooting machine,
the result looks stable. But with 2.6.24-rc1, the first run of iozone got a very small result and
following run has 4Xorig_result.

What I reported is the regression of 2nd/3rd run, because first run has bigger regression.

I also tried to change /proc/sys/vm/dirty_ratio,dirty_backgroud_ratio and didn't get improvement.

-yanmin
-
Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]
Messages in current thread:
iozone write 50% regression in kernel 2.6.24-rc1, Zhang, Yanmin, (Fri Nov 9, 2:47 am)
Re: iozone write 50% regression in kernel 2.6.24-rc1, Peter Zijlstra, (Fri Nov 9, 2:54 am)
Re: iozone write 50% regression in kernel 2.6.24-rc1, Zhang, Yanmin, (Sun Nov 11, 7:14 pm)
Re: iozone write 50% regression in kernel 2.6.24-rc1, Peter Zijlstra, (Mon Nov 12, 2:45 am)
Re: iozone write 50% regression in kernel 2.6.24-rc1, Zhang, Yanmin, (Mon Nov 12, 2:51 am)
Re: iozone write 50% regression in kernel 2.6.24-rc1, Peter Zijlstra, (Mon Nov 12, 6:26 am)
Re: iozone write 50% regression in kernel 2.6.24-rc1, Mark Lord, (Mon Nov 12, 10:25 am)
Re: iozone write 50% regression in kernel 2.6.24-rc1, Zhang, Yanmin, (Mon Nov 12, 6:49 pm)