RE: 2.2.16 Alpha: "Fix SMP rescheduling with lock held"

["Greg Lindahl" <glindahl hpti com>]

> So, that means it's our good friend the kernel_lock again.  How
> long did the
> system hang for before you killed it?

We've left it for hours without recovery.

> Are you either doing 1) a lot of data
> transfers or 2) a lot of heavily threaded work?

It's 2 processes doing OS-bypass data transfers. So the number of syscalls
and context switches should be minimal. There is a lot of DMA going on, etc
etc.

It might have been doing disk I/O at the time, which would be 2 processes
doing a lot of NFS activity.

-- g