Revert "cfq: Remove special treatment for metadata rqs."

We have a kernel build regression since 3.1-rc1, which is about 10%
regression. The kernel source is in an ext3 filesystem.
Alex Shi bisect it to commit:
commit a07405b7802691d29ab3b23bdc76ee6d006aad0b
Author: Justin TerAvest <teravest@google.com>
Date:   Sun Jul 10 22:09:19 2011 +0200

    cfq: Remove special treatment for metadata rqs.

Apparently this is caused by lack metadata preemption, where ext3/ext4
do use READ_META. I didn't see a way to fix the issue, so suggest
reverting the patch.

This reverts commit a07405b7802691d29ab3b23bdc76ee6d006aad0b.

Reported-by: Alex Shi<alex.shi@intel.com>
Reported-by: Shaohua Li<shaohua.li@intel.com>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>

1 files changed, 18 insertions, 0 deletions

diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 65083453760..a33bd4377c6 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -130,6 +130,8 @@ struct cfq_queue {
 	unsigned long slice_end;
 	long slice_resid;
 
+	/* pending metadata requests */
+	int meta_pending;
 	/* number of requests that are on the dispatch list or inside driver */
 	int dispatched;
 
@@ -682,6 +684,9 @@ cfq_choose_req(struct cfq_data *cfqd, struct request *rq1, struct request *rq2,
 	if (rq_is_sync(rq1) != rq_is_sync(rq2))
 		return rq_is_sync(rq1) ? rq1 : rq2;
 
+	if ((rq1->cmd_flags ^ rq2->cmd_flags) & REQ_META)
+		return rq1->cmd_flags & REQ_META ? rq1 : rq2;
+
 	s1 = blk_rq_pos(rq1);
 	s2 = blk_rq_pos(rq2);
 
@@ -1607,6 +1612,10 @@ static void cfq_remove_request(struct request *rq)
 	cfqq->cfqd->rq_queued--;
 	cfq_blkiocg_update_io_remove_stats(&(RQ_CFQG(rq))->blkg,
 					rq_data_dir(rq), rq_is_sync(rq));
+	if (rq->cmd_flags & REQ_META) {
+		WARN_ON(!cfqq->meta_pending);
+		cfqq->meta_pending--;
+	}
 }
 
 static int cfq_merge(struct request_queue *q, struct request **req,
@@ -3360,6 +3369,13 @@ cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq,
 		return true;
 
 	/*
+	 * So both queues are sync. Let the new request get disk time if
+	 * it's a metadata request and the current queue is doing regular IO.
+	 */
+	if ((rq->cmd_flags & REQ_META) && !cfqq->meta_pending)
+		return true;
+
+	/*
 	 * Allow an RT request to pre-empt an ongoing non-RT cfqq timeslice.
 	 */
 	if (cfq_class_rt(new_cfqq) && !cfq_class_rt(cfqq))
@@ -3423,6 +3439,8 @@ cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 	struct cfq_io_context *cic = RQ_CIC(rq);
 
 	cfqd->rq_queued++;
+	if (rq->cmd_flags & REQ_META)
+		cfqq->meta_pending++;
 
 	cfq_update_io_thinktime(cfqd, cfqq, cic);
 	cfq_update_io_seektime(cfqd, cfqq, rq);