----- Original Message ----- 
From: "Mark Cullen" <mark.r.cullen@gmail.com>
To: <netbsd-users@NetBSD.org>
Sent: Friday, July 21, 2006 11:27 AM
Subject: Re: 3.0.1: softdep + ffsv2 + 'heavy' load = pauses


> Mark Cullen wrote:
>
> LCDProc was still running fine, and the LCD on the machine was showing 
> ~70% idle CPU at the time, so perhaps processes were getting wedged 
> waiting for the disk or something? Perhaps it is something to do with 
> RAIDFrame? The test machine is not running on a RAID-1 array like this 
> box, and only has one 'fxp' card as opposed to two. Who knows! The 
> hardware configurations differ quite a lot, and the test box (which 
> doesn't hang, even with 400 clients) doesn't have all of the stuff the 
> home server has running. It just runs the same kernel.

This matches exactly a reoccuring problem I've suffered from since 1.6 IIRC. 
I thought it went away when I upgraded to 3.0 (GENERIC.MP from Dec 19, '05), 
but it came back...coincidentally about the same time I turned on softdeps.

My machine is a 4-way PPRo box with 512MB ram, 6 disks on 2 aha(4) busses. 
The only ata device is the cdrom, it's rarely mounted. Three disks are 
configured as a raid 5 drive mounted as /export and /home/www and /tmp is 
mfs. fxp0 is up and bound to both an IPv4 and IPv6 address, although only 
IPv4 addressing is in use. fxp1 and fea0 are currently unused.

>
> I have disabled softdep on all mounts now and I am giving BUFQ_PRIOCSCAN a 
> try. Hopefully it won't hang this time, but I shalln't be able to test 
> until tonight.

I'll try turning off softdeps and see if the problem goes away.

-- 
Bob

>
> -- 
> Mark Cullen <mark.r.cullen@gmail.com>
>