Jason A. Diegmueller wrote:
> The main goal here was to get the system stable. I feel it is. But
> if anyone has any ideas as to why SMP would cause the hardlockups,
> or if there is anything I can try to help out the community and track
> down what would cause this problem, be sure to let me know.
A number of us are having similar problems currently with 2.2.1? with many
ide disks and SMP. It is probably worth sending linux-kernel a summary of
your difficulty, as the topic is being discussed. What Alan would really
like is if you could run 2.2.13pre11 without the raid code, and get a
similar lockup... perhaps just by keying heavy disk activity on each disk at
the same time.. at least this works for the many-ide-SMP lockups (something
like dd if=/dev/sdX of=/dev/null count=500000 & running on each drive at the
same time
I appreciate this is a production box... the one I am having a problem is
too. But these kinds of tests may help them resolve the problem... and then
we'll all buy you a beer ;)
Tom