marty wrote:
> Faster to do what?  OS A is faster at handling character-at-a-time 
data,
> OS B is faster at handling block-at-a-time data.

I could be wrong, but given the big difference in read performance, I 
suspect bonny maybe getting confused about filesystem block sizes. I'd 
be pretty impressed to get even 20Mb sustained off an 8Gb disk (probably 
SCSI II uw? - were you fsyncing Kevin?)....but then I'd have gone with 
'time cp severallargefiles somewhere' to measure performance.

(yes I know that seek time is more important for database access than 
overall throughput, but setting up 'real world' testing is _so_ much 
more difficult).

Colin
-----Original Message-----
From:   marty [SMTP:[EMAIL PROTECTED]]
Sent:   Monday, June 24, 2002 3:46 PM
To:     scottish
Subject:        Re: [scottish] Benchmarking...how to interpet Bonnie++ 
output?

> Of the following two sets of data, which is faster?

Faster to do what?  OS A is faster at handling character-at-a-time data,
OS B is faster at handling block-at-a-time data.

The one that is faster for you depends on whether your applications are
going to do more getc/putc or more read/write.

Cheers,
Martin
-- 
Martin McCarthy                 /</         http://www.non-prophet.org
[EMAIL PROTECTED]    \>\  http://www.ancient-scotland.co.uk
--------------------------------------------------------------------
http://www.lug.org.uk                   http://www.linuxportal.co.uk
http://www.linuxjob.co.uk               http://www.linuxshop.co.uk
--------------------------------------------------------------------


--------------------------------------------------------------------
http://www.lug.org.uk                   http://www.linuxportal.co.uk
http://www.linuxjob.co.uk               http://www.linuxshop.co.uk
--------------------------------------------------------------------

Reply via email to