Subject: Re: timewarps
To: matthew green <mrg@eterna.com.au>
From: enami tsugutomo <enami@but-b.or.jp>
List: tech-kern
Date: 03/17/2002 10:57:11
matthew green <mrg@eterna.com.au> writes:

> seen this on sparc64 a lot and pmax sometimes.  you can really
> notice it when processes start having (unsigned)-2^31 time used.

I've noticed that some ports like pmax and alpha have guard against to
return warped value (within a very small amount).  But unlike alpha's,
it looks like pmax's one fails to fix when current and last time
across second.

enami.