So - after a while I've made some observations. My problem is actually connected to arp.
My config is very static so basically I want to turn off arp requests. Somewhere in the startup scripts I did > sysctl -w net.link.ether.inet.max_age=2147483647 (max accepted value) Which on freebsd-6.x worked fine. In freebsd-8.1 this makes the kernel arp functionality go bezerk - probably an integer overflow somewhere. arp requests were sent countinously from my freebsd-8.1 node to others, flooding the network. I tried to lower this value and found that 500000000s works fine 1000000000s does not. 500000000s is OK to me so I won't try to narrow it down more. The reason I was suspecting swapping problems was that after a while with the flooding going on I got a kernel panic saying 'page fault', which I would guess is a another bug, but, with a sensible setting on the arp timeout the kernel panic does not show itself any longer. I've googled for my arp-setting problem but not found anything on it. So - maybe I'm the first to see this. Should I enter a bug report somewhere? I guess this forum is not the place. /Mats 2011/3/14 Mark Tinguely <marktingu...@gmail.com> > > You are running out of physical memory, there is no swap backstore and the > kernel is killing off other programs to claim memory. > > Compare the /etc/login.conf on both systems. I bet in the FreeBSD 6.3 > system, the memory limit is set to a limit (8M) and on the FreeBSD 8.1 it > is much higher or is "unlimited". With a set memory limit, the "dd" is > killed before the kernel starts killing off the other program. > > > On 3/14/2011 6:41 AM, Mats Lindberg wrote: > > No - not from what I understand > in the vmware it looks like a real disk device /dev/ad0s1e > in the nfsroot'ed system I actually have 'of=/opt/something' which is > definately to the nfs disk. > > > 2011/3/14 Mark Tinguely <marktingu...@gmail.com> > >> On 3/14/2011 6:17 AM, Mats Lindberg wrote: >> >>> All >>> I am migrating from FreeBSD 6.3 to FreeBSD 8.1 And I have noticed some, >>> what >>> I think is, strange behaviour. >>> >>> In FreeBSD 6.3 when I do >>> >>>> swapoff -a >>>> dd if=/dev/zero of=/tmp/whatever bs=1G count=1 >>>> >>> I get something like "out of memory - killed" >>> >>> In FreeBSD 8.1 doing the same - processes around start to die, e.g. all >>> getty's are killed and finally devfs goes the same way. >>> >>> My target is diskless nfs mounted to a linux fileserver - hence no swap >>> partition >>> It does not seem to be relalted to the nfs root however - I get the same >>> behaviour running FBSD-8.1 in a VMWARE server session. >>> >>> Is this a new 'feature' of FBSD or just a bug? >>> Are there some sysctl's to set to 'really' turn of swapping. >>> >>> At one instance I also got a kernel panic saying 'page fault in kernel' >>> but >>> I'm having a hard time to repeat just that. >>> >>> regards >>> Mats >>> _______________________________________________ >>> freebsd-hackers@freebsd.org mailing list >>> http://lists.freebsd.org/mailman/listinfo/freebsd-hackers >>> To unsubscribe, send any mail to " >>> freebsd-hackers-unsubscr...@freebsd.org" >>> >>> Do you have /tmp mounted on a memory filesystem? >> >> --Mark Tinguely >> >> > > _______________________________________________ freebsd-hackers@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-hackers To unsubscribe, send any mail to "freebsd-hackers-unsubscr...@freebsd.org"
