lkml.org 
[lkml]   [1999]   [Jan]   [9]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: Drastic performance issue in ext2 v ffs
Hi,

On Tue, 05 Jan 1999 12:41:59 -0700, Tom Christiansen
<tchrist@jhereg.perl.com> said:

> I believe there is something dramatically wrong here, probably in either
> the ext2 filesystems or the SCSI driver, or both. Here's the story.

Are these results from a hot cache, by the way?

> My first test was du on that directory tree. Here are the timing results
> of "du -s >/dev/null".

> linux 0.080u 11.400s 0:11.51
> bsd 0.030u 0.462s 0:00.49

On a 75MB tree (the kernel source tree, compiled):
Linux-2.2.0pre5 0.11u 0.66s 0:08.66 (from cold)
Subsequent runs: 0.05u 0.09s 0:00.39 (from cache)

> Here are timings on "find . -ls >/dev/null":

> linux 1.050u 12.130s 0:13.35
> bsd 0.739u 0.445s 0:01.18

Linux-2.2.0pre5 0.76u 0.15s 0:00.91 (again, from cache)

> So, what might account for this embarrassingly dramatic disparity?

The fact that you are using such an old Linux kernel? :)

> Does BSD have an incedibly better inode cache? Is this a known
> bug? Is it fixed in the next release? :-)

Not a bug: it is mainly a property of the directory entry caching
implemented in 2.1/2.2 kernels.

--Stephen

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/

\
 
 \ /
  Last update: 2005-03-22 13:49    [from the cache]
©2003-2011 Jasper Spaans