On 13 Feb 2000, David Wragg wrote:
> Manfred Spraul <manfreds@colorfullife.com> writes:
> > The TLB flush code changed in 2.3.43 and .44. If you see corruptions
> > with 2.3.42, then the TLB changes cannot be the cause for the
> > corruptions.
>
> After playing around with .4[234], I see problems in 43 and 44,
> but 42 seems fine.
It must have been a .43 pre version then :)
> But wouldn't TLB problems be intermittent, and tend to affect
> everything rather than very speific programs? When I see a program
> SIGSEGV unusually (sometimes it's SIGILL or SIGBUS), and md5sum on
> the relevant binary, then reboot into a plain old 2.2 kernel, then
> md5sum on the binary again, I get a different result! Unless the
> TLB changes in 43 could plausibly cause these symptoms, aren't the
> changes to fs/buffer.c a more likely culprit?
It might well be fs/buffer.c (too?). A repeated md5sum on a
big file over NFS always gives the correct result, ext2fs and
isofs don't always work...
This suggests a slight bug in the read path. Did anyone do
something suspicious with that code? :)
Rik
-- The Internet is not a network of computers. It is a network of people. That is its real strength.- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/
This archive was generated by hypermail 2b29 : Tue Feb 15 2000 - 21:00:26 EST