cfq-iosched: use call_rcu() instead of doing grace period stall on queue exit
authorJens Axboe <jens.axboe@oracle.com>
Sun, 6 Dec 2009 08:54:19 +0000 (09:54 +0100)
committerJens Axboe <jens.axboe@oracle.com>
Sun, 6 Dec 2009 08:54:19 +0000 (09:54 +0100)
commitbb729bc98c0f3e6a898d8730df3e2830bf68751a
treef2170f8f688a7c7f813168a6c8c757087934c094
parent846954b0a32f4ae953e082eabd178e7a98dd2efd
cfq-iosched: use call_rcu() instead of doing grace period stall on queue exit

After the merge of the IO controller patches, booting on my megaraid
box ran much slower. Vivek Goyal traced it down to megaraid discovery
creating tons of devices, each suffering a grace period when they later
kill that queue (if no device is found).

So lets use call_rcu() to batch these deferred frees, instead of taking
the grace period hit for each one.

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