Recent VFS locking vs kqueue

[Jiawei Ye]

On 6/16/05, Xin LI <delphij at frontfree.net> wrote:
> Hi, Jeff and -current@,
> 
> With a fresh -CURRENT kernel (today's source) I got the following
> messages from console and /var/log/messages on my laptop, with a "cvs -R
> up -PdA 2>/dev/null" running on one console (which results in disk/fs
> activities) and "tail -F /var/log/messages" (which uses kqueue events).
> 
> The kernel is built with ULE scheduler, PREEMPTION+FULL_PREEMPTION
> enabled, and all debugging options, like INVARIANTS and WITESS turned
> on.
> 
> BTW.  I have found something that can lead to panic: Negative nice
> count, which indicates that there are some races in our code, but it
> seems that the bug is not easy to exercise.  Will report more
> information/patches once I got some findings.
> 
> Thanks in advance!
Perhaps you could try compling Apache2 with KQUEUE and THREADS
support, then try exercise the httpd server with 'webbench -c 1000'. I
got several panics (alas, not dump available) during the last week
with such setup. After turning off KQUEUE and THREADS support in
Apache2, things calmed down.

Jiawei
-- 
"Without the userland, the kernel is useless."
               --inspired by The Tao of Programming