Hi Adrian,
btw. I wrote some other mails - with other subjects - but in regards to the
same basic problem..
here you can also see vmstat output and output from squid - while it was
loaded.. and you can also see what i'm running squid on..
it's a 2xPIII-1ghz, 1gb ram, 2x18gb (in raid 1) 10k rpm scsi disks, 160mb/s
Hardware Raid controller.
-------------| This mail has been sent to you by: |------------
Klavs Klavsen, IT-coordinator and Systems Administrator at
Metropol Online - http://www.metropol.dk
Tlf. 33752700, Fax 33752720, Email ktk@metropol.dk
Private- Email klavs@klavsen.net - http://www.vsen.dk
--------------------[ I believe that... ]-----------------------
It is a myth that people resist change. People resist what other
people make them do, not what they themselves choose to do...
That's why companies that innovate successfully year after year
seek their peopl's ideas, let them initiate new projects and
encourage more experiments. -- Rosabeth Moss Kanter
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 Tue Nov 13 2001 - 00:15:05 MST
This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 17:04:04 MST