[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20110204165839.GA2630@redhat.com>
Date: Fri, 4 Feb 2011 11:58:39 -0500
From: Mike Snitzer <snitzer@...hat.com>
To: Jens Axboe <jaxboe@...ionio.com>
Cc: Tejun Heo <tj@...nel.org>, Vivek Goyal <vgoyal@...hat.com>,
"tytso@....edu" <tytso@....edu>,
"djwong@...ibm.com" <djwong@...ibm.com>,
"shli@...nel.org" <shli@...nel.org>,
"neilb@...e.de" <neilb@...e.de>,
"adilger.kernel@...ger.ca" <adilger.kernel@...ger.ca>,
"jack@...e.cz" <jack@...e.cz>,
"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
"kmannth@...ibm.com" <kmannth@...ibm.com>,
"cmm@...ibm.com" <cmm@...ibm.com>,
"linux-ext4@...r.kernel.org" <linux-ext4@...r.kernel.org>,
"rwheeler@...hat.com" <rwheeler@...hat.com>,
"hch@....de" <hch@....de>, "josef@...hat.com" <josef@...hat.com>,
"jmoyer@...hat.com" <jmoyer@...hat.com>
Subject: [PATCH v5 1/2] block: skip elevator data initialization for flush
requests
Skip elevator initialization for flush requests by passing priv=0 to
blk_alloc_request() in get_request(). As such elv_set_request() is
never called for flush requests.
Signed-off-by: Mike Snitzer <snitzer@...hat.com>
---
block/blk-core.c | 29 +++++++++++++++++++++++++----
1 file changed, 25 insertions(+), 4 deletions(-)
v5: introduces blk_rq_should_init_elevator() to abstract the elevator
initialization decision to promote future reuse and clarity.
Index: linux-2.6/block/blk-core.c
===================================================================
--- linux-2.6.orig/block/blk-core.c
+++ linux-2.6/block/blk-core.c
@@ -753,6 +753,25 @@ static void freed_request(struct request
}
/*
+ * Determine if elevator data should be initialized when allocating the
+ * request associated with @bio.
+ */
+static bool blk_rq_should_init_elevator(struct bio *bio)
+{
+ if (!bio)
+ return true;
+
+ /*
+ * Flush requests do not use the elevator so skip initialization.
+ * This allows a request to share the flush and elevator data.
+ */
+ if (bio->bi_rw & (REQ_FLUSH | REQ_FUA))
+ return false;
+
+ return true;
+}
+
+/*
* Get a free request, queue_lock must be held.
* Returns NULL on failure, with queue_lock held.
* Returns !NULL on success, with queue_lock *not held*.
@@ -764,7 +783,7 @@ static struct request *get_request(struc
struct request_list *rl = &q->rq;
struct io_context *ioc = NULL;
const bool is_sync = rw_is_sync(rw_flags) != 0;
- int may_queue, priv;
+ int may_queue, priv = 0;
may_queue = elv_may_queue(q, rw_flags);
if (may_queue == ELV_MQUEUE_NO)
@@ -808,9 +827,11 @@ static struct request *get_request(struc
rl->count[is_sync]++;
rl->starved[is_sync] = 0;
- priv = !test_bit(QUEUE_FLAG_ELVSWITCH, &q->queue_flags);
- if (priv)
- rl->elvpriv++;
+ if (blk_rq_should_init_elevator(bio)) {
+ priv = !test_bit(QUEUE_FLAG_ELVSWITCH, &q->queue_flags);
+ if (priv)
+ rl->elvpriv++;
+ }
if (blk_queue_io_stat(q))
rw_flags |= REQ_IO_STAT;
--
To unsubscribe from this list: send the line "unsubscribe linux-ext4" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists