Re: Warning, user cutting in: Kernel 2.2.14, dirty buffers, stalls in performance ...

From: Bryan -TheBS- Smith (thebs@theseus.com)
Date: Tue Mar 28 2000 - 14:45:03 EST


On Tue, 28 Mar 2000, Daniel J Blueman wrote:
> Do a 'cat /proc/interrupts' and see what devices are sharing any
> interrupts - I'm not saying this is causing a problem, but eg if the network
> and RAID SCSI cards were sharing an interrupt line, that would hurt
> performance a bit.

[root@thor /root]# cat /proc/interrupts
           CPU0
  0: 78030234 XT-PIC timer
  1: 5517 XT-PIC keyboard
  2: 0 XT-PIC cascade
  8: 1 XT-PIC rtc
 10: 31594636 XT-PIC gdth
 12: 621 XT-PIC PS/2 Mouse
 13: 1 XT-PIC fpu
 15: 234737971 XT-PIC eth0
NMI: 0

Whoa! Does eth0 on Int15h raise a big flag in anyone else's
book?!?!?!

> Just a guess but, it could be the NFSv2 locking issues?

Er, maybe. I mean, my first instinct when coming to the company
mid-last year was NOT to use Linux to serve out Solaris clients
(and I'm a _huge_ Linux advocate) because of NFS issues/performance.

But I hope someone can confirm (solid, i.e. no doubts -- because I
have to take our sole fileserver down when I do this -- in a 24x7
production environment) that I will have problems if my NIC is on
Int 15h?

-- TheBS

-- 
 Bryan "TheBS" Smith -- Engineer, IT Professional and Hacker
      E-mail:  mailto:thebs@theseus.com,b.j.smith@ieee.org
  Disclaimer:  http://www.SmithConcepts.com/legal.html
*************************************************************
  TheBS ... Serving E-mail filters to /dev/null since 1989

- 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/



This archive was generated by hypermail 2b29 : Fri Mar 31 2000 - 21:00:22 EST