On Tue, Apr 11 2000, Dimitris Michailidis wrote:
> case). The real bottleneck under disk I/O load is the single request array,
> IMO.
It tends to be, especially for more than one active device. I have
experimented with per-queue request tables here, but haven't yet
done any profiling to see what improvements it gets us. The goal
was also to limit contention on the io_request_lock, but that lock
is being used so incestuously throughout the I/O layer that it is
non trivial to fix.
I'll return with numbers when I have something worthwhile.
-- * 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 : Sat Apr 15 2000 - 21:00:19 EST