>Date: Thu, 25 Jan 1996 07:51:54 -0600
>From: Chris Csanady <ccsanady@friley14.res.iastate.edu>
>
>>Brad Walker writes:
>>
>>>But, they don't optimize for head actuator position.
>>
>>Huh?  That's what the disksort routine is supposed to take care of.
>
>disksort routine??  i dont know quite what the best way is, but it seems
>to me that this may also hurt performance on modern drives with variable
>sectors/track.  i know my drive certainly is not as fast as i think it
>should be, and makes very odd sounding seek patterns often.  they sound
>much less than optimal...

This was all discussed a year ago.  The result was that the defaults
for newfs(8) were changed to eliminate rotdelay (-d).  AFAIK, if
rotdelay is zero, then disksort() becomes a NOP.

If you have "modern" disks and you created your filesystems with 1.0,
or with a pre-9412 -current, then you may want to back them up and
then re-create them.  Filesystems created with the current defaults
should be much faster.

----------------------------------------------------------------------
From: mycroft@gnu.ai.mit.edu
Date: Thu, 1 Dec 94 22:38:09 est
Subject: Re: More on UFS performance

Well, I've already changed the newfs(8) defaults to the equivalent of
`-a 8 -d 0 -n 1', do I declare this discussion moot.  B-)

----------------------------------------------------------------------
-- 
Mike Long <mike.long@analog.com>           http://www.shore.net/~mikel
VLSI Design Engineer         finger mikel@shore.net for PGP public key
Analog Devices, CPD Division          CCBF225E7D3F7ECB2C8F7ABB15D9BE7B
Norwood, MA 02062 USA       (eq (opinion 'ADI) (opinion 'mike)) -> nil