Date: Fri, 11 Jun 2004 21:50:03 -0400 (EDT)
From: Rik van Riel <riel@redhat.com>
To: =?iso-8859-1?Q?J=F6rn?= Engel <joern@wohnheim.fh-wedel.de>
cc: John Bradford <john@grabjohn.com>, Matt Mackall <mpm@selenic.com>,
       Christian Borntraeger <linux-kernel@borntraeger.net>,
       <linux-kernel@vger.kernel.org>,
       Lasse K?rkk?inen / Tronic <tronic2@sci.fi>
Subject: Re: Some thoughts about cache and swap
In-Reply-To: <20040611140721.GB7369@wohnheim.fh-wedel.de>
Message-ID: <Pine.LNX.4.44.0406112148420.13607-100000@chimarrao.boston.redhat.com>
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; charset=ISO-8859-1
Content-Transfer-Encoding: 8BIT
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 1336
Lines: 34

On Fri, 11 Jun 2004, J?rn Engel wrote:
> On Wed, 9 June 2004 15:32:41 -0400, Rik van Riel wrote:
> > 
> > Haven't seen many of those, to be honest.  The majority
> > of the VM problems I get to see are people running a
> > workload the kernel didn't expect - a workload the kernel
> > wasn't prepared to handle...
> 
> Is there a list of those different workloads somewhere?  And I don't
> mean in your head. ;)

That's the point.  If there was such a list, we could put
appropriate kludges in place for all of them.

> All I notive in my personal use is the cache flushing effect from
> use-once data.  If that was the whole list, it should be easy enough to
> fix.

I wish it were that easy.  Users keep surprising us with
new and unexpected workloads, though.

Part of it is that every time Linux is improved, people are
encouraged to try out stranger, newer, heavier workloads ;)

-- 
"Debugging is twice as hard as writing the code in the first place.
Therefore, if you write the code as cleverly as possible, you are,
by definition, not smart enough to debug it." - Brian W. Kernighan

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/