freebsd stable - Feb 2009 - vm_thread_new: kstack allocation failed with vm.kmem_size="1536M"

So, I have a farm of machines runnign 7.1/amd64, all of which have 16 gig of
memory in them. This afternoon, as an experiment, I altered loader.conf
to have these two lines in it:

vm.kmem_size="1536M"
vm.kmem_size_max="1536M"

This is what I do on machines running ZFS - these machines are not, however
running ZFS, and do not have the zfs module loaded. I just wanted to see if
they would run OK with those kernel settings (as I may put ZFS on them in
the future)

I expected it to run fine, I just wanted to make sure. But after about
an hour I started getting the message in the subject line, and the
machines were unable to fork and needed to be reset.

Explanation anyone ? This makes no sense to me - I have actually expanded
the amount of memory available, so why is it now running out of stack
space ?! The machines are running a very simple setup of apache, mysql
and tomcat - and this runs fine with the kernel variables set as default.

I am very puzzled.

-pete.

In the last episode (Feb 28), Pete French said:
> So, I have a farm of machines runnign 7.1/amd64, all of which have 16 gig
> of memory in them.  This afternoon, as an experiment, I altered
> loader.conf to have these two lines in it:
> 
> vm.kmem_size="1536M"
> vm.kmem_size_max="1536M"
> 
> This is what I do on machines running ZFS - these machines are not,
> however running ZFS, and do not have the zfs module loaded.  I just wanted
> to see if they would run OK with those kernel settings (as I may put ZFS
> on them in the future)
You've probably reduced kmem_size from the default.  I don't set
anything on
my 6 GB amd64 system, and I get:

$ sysctl vm.kmem_size vm.kmem_size_max
vm.kmem_size: 2061496320
vm.kmem_size_max: 3865468109

I assume your 16GB system would default to even larger numbers.  What values
do you get without forcing anything in loader.conf?

-- 
	Dan Nelson
	dnelson@allantgroup.com