System comes to a halt on heavy disk I/O

Charles Curley charlescurley at charlescurley.com
Mon Feb 1 14:15:30 MST 2010


On Mon, 1 Feb 2010 13:04:57 -0700
Charles Curley <charlescurley at charlescurley.com> wrote:

> On Mon, 01 Feb 2010 09:51:55 -0700
> Kenneth Burgener <kenneth at mail1.ttak.org> wrote:
> 

> 
> So far I've been testing by writing to sdb. I think a similar test to
> send data to sda is next. If I can't swamp the system with that, that
> will suggest that sbd is the problem.

Hmmm. To clear out some space for testing on sda, I copied a 12G file
from sda to sdb, in 2m54s, or about 68 MB/sec one way.

I also noticed a major difference in the vmstat output. Both the blocks
in and blocks out showed much larger numbers. Rarely did the wait times
go above 20%, and I don't think I saw it go over 30%.

I'm now diffing them, and seeing wait times in the low 30% range, and
lots of blocks in. The diff took 2m51.849s to read 24 G.



-- 

Charles Curley                  /"\    ASCII Ribbon Campaign
Looking for fine software       \ /    Respect for open standards
and/or writing?                  X     No HTML/RTF in email
http://www.charlescurley.com    / \    No M$ Word docs in email

Key fingerprint = CE5C 6645 A45A 64E4 94C0  809C FFF6 4C48 4ECD DFDB



More information about the PLUG mailing list