Skip site navigation (1)Skip section navigation (2)
Date:      Wed, 14 Mar 2001 18:51:25 -0800
From:      Alfred Perlstein <bright@wintelcom.net>
To:        David Scheidt <dscheidt@tumbolia.com>
Cc:        chat@freebsd.org
Subject:   Re: Disk I/O problem in 4.3-BETA
Message-ID:  <20010314185125.T29888@fw.wintelcom.net>
In-Reply-To: <Pine.BSF.4.21.0103141941300.38966-100000@shell-2.enteract.com>; from dscheidt@tumbolia.com on Wed, Mar 14, 2001 at 07:44:49PM -0600
References:  <20010314154323.O29888@fw.wintelcom.net> <Pine.BSF.4.21.0103141941300.38966-100000@shell-2.enteract.com>

next in thread | previous in thread | raw e-mail | index | archive | help
* David Scheidt <dscheidt@tumbolia.com> [010314 17:44] wrote:
> On Wed, 14 Mar 2001, Alfred Perlstein wrote:
> 
> :* Iain Templeton <iain@research.canon.com.au> [010314 14:54] wrote:
> :> On Mon, 12 Mar 2001, Alfred Perlstein wrote:
> :It's a common starvation problem.
> :
> :Imagine an elevator that always goes to the nearest requested floor
> :instead of making almost complete up then down sweeps.
> :
> :At quit time there's a good chance you'll never hit the lobby
> :because the elevator keeps going to the nearest floor which is
> :unlikely to be the lobby once it gets high up enough.
> :
> :Matt explained that Linux had this "feature" to reduce disk seeking
> :for a short period, finally someone with algorithm experience stood
> :up and smacked enough people around such that it got changed to
> :the proper elevator algorithm.
> 
> HP introduced this problem (I think it was somewhat subtler than the way
> you've laid it out, though) into HP/UX 10.20 at some point.  It meant that
> ls would take minutes(!!) to produce output on one of the boxes I ran, if
> it was being pounded on in a certain way.  It's been fixed for a long time,
> though.

That's really funny, about 4-5 years ago I talked to someone who
had just finished interviewing a potential candidate who had been
working in the HPUX devel team (i think).  And talked about a
"a weird problem when we have lots of IO".

Does that even come close to the same time period?

-- 
-Alfred Perlstein - [bright@wintelcom.net|alfred@freebsd.org]


To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-chat" in the body of the message




Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20010314185125.T29888>