Re: 2.2.2: Freeze (possible kb failure)

Alan Cox (alan@lxorguk.ukuu.org.uk)
Sun, 28 Feb 1999 18:01:48 +0000 (GMT)

> >The big problem one is with the VM - its quite possible to get a heavily
> >loaded 2.2.x box to the point where it has no 8K blocks and thus cannot
>
> You mean that the VM gets fragmented? That could happen on a low memory
> machine of course, but I really dubit it's the case of high memory
> machine boxes.

I've seen it happen on a 256Mb 2.2.1 box verified with monitoring printks.
I suspect the 2.2.1 "we queue too much I/O" bug may well have had a lot to
do with how it got so fragmented, but it happens and we do need some kind
of low key defragmentation goal in the VM, just to kick in occasionally and
do the hoovering.

> even if many part of the kernel are been changed. What's the major 2.2.x
> change that impacted the stability and the performances of NFS? I never
> followed NFS development so far so I don't know... Excuse me for these

Asynchronous writeback.

Alan

-
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/