Re: 2.1.125 filesystem corruption under extreme load

Neil Conway (nconway.list@ukaea.org.uk)
Mon, 30 Nov 1998 10:28:42 +0000

Messages sorted by: [ date ][ thread ][ subject ][ author ]
Next message: Frode L. Odegard: "using sockets in kernel threads"
Previous message: Matthew Kirkwood: "Re: /dev/winchester reporting their size"
Maybe in reply to: Arjan van de Ven: "2.1.125 filesystem corruption under extreme load"

Linus Torvalds wrote:
>
> In article <98Nov29.133059met.140554-3@colin.muc.de>,
> Andi Kleen <ak@muc.de> wrote:
> >>On Sat, 28 Nov 1998, Neil Conway DID NOT write:
> >>
> >>[dump question] what resource wasn't available? [/dump]
> >
> >Memory. Probably memory fragmentation, a fork needs a continuous 8K
> >block (2 pages).
>
> Nope. If it was memory, you'd see "out of memory".
>
> "Resource temporarily unavailable" implies fork() returned EAGAIN, which
> is basically returned for process limit overflows (and I noticed that

Ouch. The attributions have got mixed up - I didn't say either of those
things. (I wouldn't dream of blaming the memory management routines
:-)) In fact I *replied* to this question suggesting the same as you
(!)

Neil

-
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/

Next message: Frode L. Odegard: "using sockets in kernel threads"
Previous message: Matthew Kirkwood: "Re: /dev/winchester reporting their size"
Maybe in reply to: Arjan van de Ven: "2.1.125 filesystem corruption under extreme load"