someone is eating massive menory
pluknet
pluknet at gmail.com
Wed Apr 8 01:15:23 PDT 2009
2009/4/8 Randy Bush <randy at psg.com>:
> amd64, 4g ram, geom mirror and zfs
>
> another amd64 4g system is not crashing but is being very sloggish for
> 3-5 minutes.
>
> work0.psg.com:/root# uname -a
> FreeBSD work0.psg.com 8.0-CURRENT FreeBSD 8.0-CURRENT #22: Mon Apr 6 01:41:51 UTC 2009
> root at work0.psg.com:/usr/obj/usr/src/sys/WORK0 amd64
>
> when midnight crons run, it's death. this is from serial console
>
> swap_pager_getswapspace(9): failed
> swap_pager_getswapspace(3): failed
> swap_pager_getswapspace(3): failed
> swap_pager_getswapspace(3): failed
> swap_pager_getswapspace(3): failed
> swap_pager_getswapspace(3): failed
> swap_pager_getswapspace(3): failed
> swap_pager_getswapspace(3): failed
> swap_pager_getswapspace(3): failed
> swap_pager_getswapspace(3): failed
> swap_pager_getswapspace(3): failed
> swap_pager_getswapspace(3): failed
> swap_pager_getswapspace(16): failed
> swap_pager_getswapspace(3): failed
> swap_pager_getswapspace(16): failed
> swap_pager_getswapspace(3): failed
> swap_pager_getswapspace(3): failed
> swap_pager_getswapspace(3): failed
> swap_pager_getswapspace(3): failed
>
If your system survived you could grep /var/log/messages
for processes killed by kernel.
That'd help you to find the guilty procs eating all memory.
Look at vm_pageout.c.
--
wbr,
pluknet
More information about the freebsd-current
mailing list