On closer inspection this means that we've run out of KVA. In principle it should be handled more gracefully, but the 1GB KVA limitation is really a 32-bit artifact. It might be worth wading through the kernel memory allocations to see if a subsystem has gone beserk.
-Kip On 9/1/06, Kip Macy <[EMAIL PROTECTED]> wrote:
I've seen this when running stress2 with a large number of incarnations. Why don't we return an error to the user? -Kip On 9/1/06, Julian Elischer <[EMAIL PROTECTED]> wrote: > Vyacheslav Vovk wrote: > > can you see how many threads thre are in the system? > I think you will have to extract this information frome the zone allocator. > > I just realised there is no effective limit on kernel threads in the system. > probably one could cause this with a fork bomb appoach using forks and > thread creation. > > >Unread portion of the kernel message buffer: > >panic: vm_thread_new: kstack allocation failed > >cpuid = 3 > >Uptime: 7d4h30m58s > > > > > > > _______________________________________________ > freebsd-stable@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-stable > To unsubscribe, send any mail to "[EMAIL PROTECTED]" >
_______________________________________________ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to "[EMAIL PROTECTED]"