On Wed, May 03 2000, Jeff Garzik wrote:
> Have you checked the asm to make sure the function is inlined?
> Typically the rule is you must make it 'static inline' to better ensure
> inlining.
No, and you are right I should have. But ->
> Stepping back a bit, is this function ever called with interrupts
> disabled and such? If not, you can use spin_lock_irq in certain
> [carefully considered] cases. That eliminates worrying about 'flags'
> completely and is a bit faster.
It doesn't appear to be. Andre should be able to confirm this. And in fact
the the io_request_lock is just used to protect the hwgroup so the locking
can be made a bit simpler yet. Patch attached.
-- * Jens Axboe <axboe@suse.de> * Linux CD/DVD-ROM, SuSE Labs * http://kernel.dk
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/
This archive was generated by hypermail 2b29 : Sun May 07 2000 - 21:00:13 EST