cfq: merge cooperating cfq_queues
authorJeff Moyer <jmoyer@redhat.com>
Fri, 23 Oct 2009 21:14:50 +0000 (17:14 -0400)
committerJens Axboe <jens.axboe@oracle.com>
Mon, 26 Oct 2009 13:34:47 +0000 (14:34 +0100)
commitdf5fe3e8e13883f58dc97489076bbcc150789a21
treeb05ce6760cd2b52e42dca22e3659a0255f4a4e4a
parentb2c18e1e08a5a9663094d57bb4be2f02226ee61c
cfq: merge cooperating cfq_queues

When cooperating cfq_queues are detected currently, they are allowed to
skip ahead in the scheduling order.  It is much more efficient to
automatically share the cfq_queue data structure between cooperating processes.
Performance of the read-test2 benchmark (which is written to emulate the
dump(8) utility) went from 12MB/s to 90MB/s on my SATA disk.  NFS servers
with multiple nfsd threads also saw performance increases.

Signed-off-by: Jeff Moyer <jmoyer@redhat.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
block/cfq-iosched.c