On Sun, 21 Jan 2007 15:31:59 -0800
buhrow@lothlorien.nfbcal.org (Brian Buhrow) wrote:

> 	Hello.  Here is, perhaps, a sily suggestion.  What if you try
> breaking into ddb when the machine seems particularly sluggish and
> running a back trace?  I may not know what I'm talking about here,
> but perhaps in this way you can catch the machine red-handed and
> somehow divine where the problem is, or, at least, get closer?
> I assume the behavior is easy to reproduce, so if you don't want to
> run with a broken kernel all of the time, you can quicly do the test,
> and then go back to your normal everyday system.

It doesn't last long enough; besides, I'm in X, which makes entering
ddb more difficult.

		--Steve Bellovin, http://www.cs.columbia.edu/~smb