Mark Cullen wrote:
> 
> On a side note, I tried running `dbench` on the home server with just 20 
> clients and it totally hung the machine when it got to the "executing" 
> stage of the test. I'm not terribly sure why either. It'd been up for 20 
> days, was using BUFQ_NEW_STATEGY (=BUFQ_PRIOREAD?) and had softupdates 
> enabled. I couldn't get this to happen again on the test machine with 
> the same kernel. I can't even get it to happen again on the same 
> machine, with the same kernel, after rebooting it!
> 

It appears I may have lied about this one. I just managed to make it 
hang again, this time it appeared to need 50 clients running and it hung 
in the 'cleaning up' stage of the test. I hit the power button and it 
responded, and the serial console showed it trying to sync the disk's 
buffers, it gave up on '8'.

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.

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.

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