Server lock up: kern.maxswzone relate ...

[Dmitry Morozovsky]

On Wed, 10 Jun 2009, Marc G. Fournier wrote:

MGF> 
MGF> I'm running a couple of brand new servers ... 32G of RAM, very little load
MGF> on it right now, and this morning it locked up with that 'kern.maxswzone'
MGF> error on the console ...
MGF> 
MGF> The server is running a reasonably current 7.2-STABLE:
MGF> 
MGF> FreeBSD pluto.hub.org 7.2-STABLE FreeBSD 7.2-STABLE #0: Sun May 31 14:48:04
MGF> ADT
MGF> 
MGF> And top right now, with everything running, shows no swappping, 19G of Free
MGF> memory, 9G of Inact memory ... no reason to do any serious amount of
MGF> swapping.
MGF> 
MGF> last pid: 32159;  load averages:  0.12,  0.21,  0.47    up 0+10:57:56
MGF> 11:53:39
MGF> 573 processes: 1 running, 571 sleeping, 1 zombie
MGF> CPU:  2.0% user,  0.0% nice,  1.2% system,  0.0% interrupt, 96.8% idle
MGF> Mem: 1331M Active, 9446M Inact, 659M Wired, 35M Cache, 399M Buf, 19G Free
MGF> Swap: 32G Total, 32G Free

As a workaround, if your machine is usually not going to swap, you can decrease 
swap space significally, and use otherwise unused partition for crashdumps.

For RELENG_7/amd64 with 8G RAM and 16G of swap, on stress tests with 
tmpfs to avoid such locks I had to tune kern.maxswzone up to 192M, which seems 
to be kinda overkill...

-- 
Sincerely,
D.Marck                                     [DM5020, MCK-RIPE, DM3-RIPN]
[ FreeBSD committer:                                 marck at FreeBSD.org ]
------------------------------------------------------------------------
*** Dmitry Morozovsky --- D.Marck --- Wild Woozle --- marck at rinet.ru ***
------------------------------------------------------------------------