On Wed, Nov 29 2000, Linus Torvalds wrote:
> I would much rather actually go back to the original setup, which did
> nothing at all if the queue wasn't plugged in the first place.
But that potentially breaks devices that either don't use plugging
or alternatively implement their own, because q->plugged will not
get set and the unplug from __get_request_wait does nothing. It's
clear that the plug/noplug is too coarse. Anyway, I don't think
there's currently a problem with the old setup for any in-kernel
drivers so I'm fine with reverting to that behaviour for now.
> I think that we should strive for a setup that calls "request_fn" only to
> start new IO, and that expects the low-level driver to be able to do the
> whole request queue until it is empty. Then we re-start it the next time
> around.
Yes agreed.
--- drivers/block/ll_rw_blk.c~ Wed Nov 29 15:17:33 2000
+++ drivers/block/ll_rw_blk.c Wed Nov 29 19:04:50 2000
@@ -347,9 +347,10 @@
*/
static inline void __generic_unplug_device(request_queue_t *q)
{
- if (!list_empty(&q->queue_head)) {
+ if (q->plugged) {
q->plugged = 0;
- q->request_fn(q);
+ if (!list_empty(&q->queue_head))
+ q->request_fn(q);
}
}
-- * Jens Axboe <axboe@suse.de> * SuSE Labs - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org Please read the FAQ at http://www.tux.org/lkml/
This archive was generated by hypermail 2b29 : Thu Nov 30 2000 - 21:00:22 EST