> The only time I've seen the slowdowns, they've occurred during a read
> from the 4k filesystem. I'm not sure if the WCHAN reported by ps is
> accurate or not, but it was reporting 1261d9, which is in the middle
> of try_to_free_buffers, according to my System.map.
There aren't supposed to be any blocking operations in
try_to_free_buffer. Could the task perhaps be stuck in a tight loop
repeatedly calling try_to_free_buffer()? The next time it gets stuck,
try hitting alt-scroll-lock a few times to get the current address, and
then look this up your System.map. If the address is changing but
usually in try_to_free_buffer(), the system is probably looking for
memory and repeatedly trying to free buffers.
Regards,
Bill