From owner-freebsd-hackers  Mon Aug 18 06:18:05 1997
Return-Path: <owner-freebsd-hackers>
Received: (from root@localhost)
          by hub.freebsd.org (8.8.5/8.8.5) id GAA21235
          for hackers-outgoing; Mon, 18 Aug 1997 06:18:05 -0700 (PDT)
Received: from dg-rtp.dg.com (dg-rtp.rtp.dg.com [128.222.1.2])
          by hub.freebsd.org (8.8.5/8.8.5) with SMTP id GAA21229
          for <freebsd-hackers@freefall.FreeBSD.org>; Mon, 18 Aug 1997 06:17:55 -0700 (PDT)
Received: by dg-rtp.dg.com (5.4R3.10/dg-rtp-v02)
	id AA03390; Mon, 18 Aug 1997 09:16:51 -0400
Received: from ponds by dg-rtp.dg.com.rtp.dg.com; Mon, 18 Aug 1997 09:16 EDT
Received: from lakes.dignus.com (lakes [10.0.0.3]) by ponds.dignus.com (8.8.5/8.7.3) with ESMTP id JAA00218; Mon, 18 Aug 1997 09:03:53 -0400 (EDT)
Received: (from rivers@localhost) by lakes.dignus.com (8.8.5/8.6.9) id IAA05973; Mon, 18 Aug 1997 08:57:33 -0400 (EDT)
Date: Mon, 18 Aug 1997 08:57:33 -0400 (EDT)
From: Thomas David Rivers <ponds!rivers@dg-rtp.dg.com>
Message-Id: <199708181257.IAA05973@lakes.dignus.com>
To: ponds!root.com!dg, ponds!freefall.cdrom.com!freebsd-hackers,
        ponds!lakes.dignus.com!rivers
Subject: Re: "rm" speeds (2.1.7.1 vs. 2.2.1)
Content-Type: text
Sender: owner-freebsd-hackers@FreeBSD.ORG
X-Loop: FreeBSD.org
Precedence: bulk

> 
> > 
> > > Again, f.y.i. - this is a 486dx66 with 24meg of RAM, a typical IDE
> > >drive (1+gig)...  The 2.2.1 kernel has NBUF defined at 128; to see 
> > >if that's the problem... where the 2.1.7 kernel was from the boot floppy
> > >off of a 2.1.7 CDROM.
> > 
> >    That is the problem. Take out the NBUF= thing from your kernel config file
> > and rebuild/install the kernel. A system with 24MB of RAM will have about
> > 600 buffers if it is allowed to dynamically calculate the amount.
> >    What's happening is that the directory is getting pushed out of the cache,
> > forcing the system to re-read much of it and the inode blocks each time.
> > 
> > -DG
> > 
> > David Greenman
> > Core-team/Principal Architect, The FreeBSD Project
> > 
> 
>  I'll give it a try!   Thanks for pointing it out..
> 
>  I've still got a directory to try it on - the box has been working
> overnight (about 9+ hours now) trying to delete it...
> 

 That seems to have been the ticket!!!

 I'm doing an 'rm' right now of that troublesome directory, and I
don't hear the tale-tell disk I/O pattern I heard before.  It's just
merrily spinning along deleteing things... (there was a *big* pause
when it started; presumably skipping through those deleted entries...)

 Thanks everyone!  

	- Dave Rivers -