>locks contended in tests, have you measured things. OS development is
>never 'mathematically clean'.
Usually I do what I think will improve things. Sometime I also benchmark.
I think this time I did the wrong choice, probably because it was more fun
the finegriend way :-). The io_request_lock is a very good point.
I released now a buffer-2.2.9-L.gz that kills the per-page spinlock.
Andrea Arcangeli
-
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/