lkml.org 
[lkml]   [1999]   [Oct]   [31]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
Subjectide performance in 2.2
Hi all -- I was recently trying to record a high bandwidth signal & ran
into the bandwidth limit of my ultra-dma drive.

I've hacked the program & also bonnie-big to write alternate blocks to two
files on different ide interfaces, with the idea that I'd get more bandwidth
writing to two disks.

I get the odd result that this actually slows down the data rate.

Anyone know what's going on here? Is there some other bottleneck? Is
software raid going to give me the same result (slower than one drive)?

I'm running an ASUS P2B-D, 2.2 kernel. hdparm for both drives are set to
"-d 1 -m 16 -u 1 -c 1".



This result is basically the same for either drive. One is primary master,
the other secondary slave. The secondary master is a cd burner which is
not accessed during the test:

-------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
1* 600 5402 79.8 10464 14.7 4073 10.7 6708 94.8 11492 12.5 83.0 1.7


This is the result for writing to two disks:

-------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
2* 300 5355 79.4 9913 13.7 4058 10.4 6218 85.5 10983 12.4 70.8 1.9


b.c.

-
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 13:54    [W:0.117 / U:0.016 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site