Re: File corruption in 2.2.12*

Stephen C. Tweedie (sct@redhat.com)
Mon, 4 Oct 1999 11:14:28 +0100 (BST)


Hi,

On Fri, 1 Oct 1999 09:36:16 -0500, "Nicholas R LeRoy"
<nick.leroy@norland.com> said:

>< extern int do_sigaltstack(const stack_t *ss, stack_t *oss, unsigned long sp);
> ---
>> extern int do_sigaltstack(const stack_ö *ss, sDack_t *Mss, unsIgned long sp);

> As you can see, exactly two bytes were corrupt in the bufferred version
> of the file, and thus copied to the file in /tmp, but the original ON DISK
> version of the file is fine. Something rotten in China.

No, there are four bytes corrupt, at 8 byte offsets from each other.
In other words, we are getting garbage in offsets which represent the
same byte offset within each word of a 32-byte cache line burst
transfer. This looks very much like a hardware problem to me, I'm
afraid.

--Stephen

-
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/