Re: Severe netbsd-6 NFS server-side performance issues

[Hauke Fath <hauke%Espresso.Rhein-Neckar.DE@localhost>]

At 16:51 Uhr -0700 30.5.2012, Brian Buhrow wrote:
>I went back and re-read your original message.  It would be
>interesting to know what those nfsd's are doing when they're in d state.
>What does ps -l show?

I'll check next time.

>   Is it possible to build a kernel with debugging
>symbols and then get things in a plugged up state, then drop into the ddb
>debugger and get a crash dump?  If you can do that, then gdb can be used on
>the crash file after the fact to determine what each process is doing at
>the time of the crash.

Frequently, the amr(4) is too upset to allow for a dump - not machine
specific, I've seen that on another machine with a 320-1 and netbsd-5, too.

>  I still think it has something to do with the raid
>controller even if it's not obvious.  Is anyone else using the crazy
>version of firmware you picked up?

I don't know. The firmware was certainly from a Fujitsu update iso; I guess
320-4X boards are not too frequent.

>       Also, what happens if you run two or more bonnie processes
>simultaneously?  That ought to stress the raid out and help demonstrate the
>problem.

I'll try that. I have a maintenance window scheduled for Friday, afternoon,
that'll give a few answers.

        hauke

--
"It's never straight up and down"     (DEVO)