On Mon, Nov 12, 2001, Klavs Klavsen wrote:
>
> I read it wrong..
>
> it's not the IO that was heavily loaded.. (at approx 18.000 pr. sec) - it
> was interrupts..
>
> Do any of you know how many I can expect - before the machine stalls.. and
> what I can do to increase the ability to handle more interrupts?
>
> btw. it's a linux-2.4 kernel.
>
> I hope you have some tuning tips for me..
>
> and to Torsten.. thanks for all your help so far..
>
Uhm, if you're using iDE anywhere, make sure you've turned DMA on.
That's burnt me a few times when doing squid work under Linux.
A few lines of vmstat output when the cache is heavily loaded will
tell us where the bottleneck may be.
Adrian
Received on Mon Nov 12 2001 - 20:16:09 MST
This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 17:04:03 MST