Subject: Re: 160 GB HD on PWS
To: None <port-alpha@netbsd.org>
From: Ray Phillips <r.phillips@jkmrc.uq.edu.au>
List: port-alpha
Date: 06/10/2003 17:48:39
I managed to borrow that disk one last time.

>Bechmarks? (bonnie?)

# ./Bonnie -m 160GB -s 5120
File './Bonnie.275', size: 5368709120
Writing with putc()...done
Rewriting...done
Writing intelligently...done
Reading with getc()...done
Reading intelligently...done
Seeker 2...Seeker 3...Seeker 1...start 'em...done...done...done...
               -------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
160GB    5120 13447 90.2 14146 19.1  5930 12.5 13958 93.6 14034 16.4  76.3  2.5


>What CPU load do you get on heavy IDE activity compared to SCSI?

When copying a 5 GB file from one directory to another (in the same 
partition) on the 160 GB IDE drive, top said cp used ~ 10% of the CPU 
all the time the copying was in process.

Doing the same thing on a ccd volume spread across two SCSI disks, 
cp's share of the CPU time went from 3% up to 25%, down to 3%, and up 
to 25% over a period of about seven minutes, then went down to 3% 
where it stayed until the copy was completed.

Bonnie's output for the SCSI ccd volume was:

# ./Bonnie -m ccd0 -s 5120
File './Bonnie.330', size: 5368709120
Writing with putc()...done
Rewriting...done
Writing intelligently...done
Reading with getc()...done
Reading intelligently...done
Seeker 1...Seeker 2...Seeker 3...start 'em...done...done...done...
               -------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
ccd0     5120 14632 96.6 22078 30.4  3429  7.2 14463 95.5 23919 27.5  92.3  2.8


Ray