Re: 2.1.125 filesystem corruption under extreme load

Gregory Maxwell (linker@z.ml.org)
Sun, 29 Nov 1998 15:39:57 -0500 (EST)


On 29 Nov 1998, Linus Torvalds wrote:

> In article <Pine.LNX.3.96.981129131222.20862F-100000@z.ml.org>,
> Gregory Maxwell <linker@z.ml.org> wrote:
> >
> >No just bad, very very very bad. 8k is the smallest unit that can have
> >frag problems, and it's very important that we can fork.
> >
> >If this is happening to people then perhaps we need to delay 2.2 and wait
> >for the 2.3 big MM changes. How trivial is an emergency defragmenter?
>
> Stop blaming the memory management!
>
> People blamed the memory management last time too, and ran around in
> circles shouting that it needed to be rewritten. They were wrong then,
> they are wrong now. The error reported was EAGAIN, not ENOMEM. Big
> difference.

Sorry.. :( I didn't read.. Why can't people write programs that respond
correctly to EAGAIN? Sigh.

> People have fragmentation on their brains, PLEASE STOP IT!
>
> Linus

-
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/