lkml.org 
[lkml]   [2000]   [Jan]   [17]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRAID1 slow reads
Here are some results from Bonnie on dual WD 10G UDMA/66 drives, separate
HPT366 controllers on an ABIT BP6 dual Celeron-433 motherboard running
Linux kernel 2.2.14 + ide.2.2.14.20000108.patch + raid0145-19990824-2.2.11

-------Sequential Output-------- ---Sequential Input-- --Random--
-Per Char- --Block--- -Rewrite-- -Per Char- --Block--- --Seeks---
Machine MB K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU /sec %CPU
wd-dma66 500 3339 99.7 21572 61.7 8626 52.2 3605 97.8 19586 27.6 113.1 3.5
raid0 500 3334 99.4 29952 92.7 11636 75.9 3643 99.0 38183 69.5 123.2 4.9
raid1 500 3288 99.5 21253 72.8 7064 47.0 3561 97.8 11974 19.3 113.9 4.4

The first line is a single drive to establish a baseline. The second line
is running two drives striped with 8k chunks, which shows the expected
performance improvement. However when running the two drives mirrored
there is a significant performance degradation - not just on writes, which
is expected, but also on reads which should still be faster, not slower!
Any ideas? (l-k readers, please copy replies to my email address)

Cheers,
*** Xanni ***
--
mailto:xanni@xanadu.net Andrew Pam
http://www.xanadu.com.au/ Chief Scientist, Xanadu
http://www.glasswings.com.au/ Technology Manager, Glass Wings
http://www.sericyb.com.au/sc/ Manager, Serious Cybernetics
P.O. Box 26, East Melbourne VIC 8002 Australia Phone +61 3 9419-2989

-
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 13:55    [W:0.030 / U:0.488 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site