block: do not merge requests without consulting with io scheduler

Before merging a bio into an existing request, io scheduler is called to
get its approval first. However, the requests that come from a plug
flush may get merged by block layer without consulting with io
scheduler.

In case of CFQ, this can cause fairness problems. For instance, if a
request gets merged into a low weight cgroup's request, high weight cgroup
now will depend on low weight cgroup to get scheduled. If high weigt cgroup
needs that io request to complete before submitting more requests, then it
will also lose its timeslice.

Following script demonstrates the problem. Group g1 has a low weight, g2
and g3 have equal high weights but g2's requests are adjacent to g1's
requests so they are subject to merging. Due to these merges, g2 gets
poor disk time allocation.

cat > cfq-merge-repro.sh << "EOF"
#!/bin/bash
set -e

IO_ROOT=/mnt-cgroup/io

mkdir -p $IO_ROOT

if ! mount | grep -qw $IO_ROOT; then
  mount -t cgroup none -oblkio $IO_ROOT
fi

cd $IO_ROOT

for i in g1 g2 g3; do
  if [ -d $i ]; then
    rmdir $i
  fi
done

mkdir g1 && echo 10 > g1/blkio.weight
mkdir g2 && echo 495 > g2/blkio.weight
mkdir g3 && echo 495 > g3/blkio.weight

RUNTIME=10

(echo $BASHPID > g1/cgroup.procs &&
 fio --readonly --name name1 --filename /dev/sdb \
     --rw read --size 64k --bs 64k --time_based \
     --runtime=$RUNTIME --offset=0k &> /dev/null)&

(echo $BASHPID > g2/cgroup.procs &&
 fio --readonly --name name1 --filename /dev/sdb \
     --rw read --size 64k --bs 64k --time_based \
     --runtime=$RUNTIME --offset=64k &> /dev/null)&

(echo $BASHPID > g3/cgroup.procs &&
 fio --readonly --name name1 --filename /dev/sdb \
     --rw read --size 64k --bs 64k --time_based \
     --runtime=$RUNTIME --offset=256k &> /dev/null)&

sleep $((RUNTIME+1))

for i in g1 g2 g3; do
  echo ---- $i ----
  cat $i/blkio.time
done

EOF
# ./cfq-merge-repro.sh
---- g1 ----
8:16 162
---- g2 ----
8:16 165
---- g3 ----
8:16 686

After applying the patch:

# ./cfq-merge-repro.sh
---- g1 ----
8:16 90
---- g2 ----
8:16 445
---- g3 ----
8:16 471

Signed-off-by: Tahsin Erdogan <tahsin@google.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

1 files changed, 8 insertions, 3 deletions

diff --git a/include/linux/elevator.h b/include/linux/elevator.h
index 953d28647435..e7f358d2e5fc 100644
--- a/include/linux/elevator.h
+++ b/include/linux/elevator.h
@@ -16,7 +16,11 @@ typedef void (elevator_merge_req_fn) (struct request_queue *, struct request *,
 
 typedef void (elevator_merged_fn) (struct request_queue *, struct request *, int);
 
-typedef int (elevator_allow_merge_fn) (struct request_queue *, struct request *, struct bio *);
+typedef int (elevator_allow_bio_merge_fn) (struct request_queue *,
+					   struct request *, struct bio *);
+
+typedef int (elevator_allow_rq_merge_fn) (struct request_queue *,
+					  struct request *, struct request *);
 
 typedef void (elevator_bio_merged_fn) (struct request_queue *,
 						struct request *, struct bio *);
@@ -46,7 +50,8 @@ struct elevator_ops
 	elevator_merge_fn *elevator_merge_fn;
 	elevator_merged_fn *elevator_merged_fn;
 	elevator_merge_req_fn *elevator_merge_req_fn;
-	elevator_allow_merge_fn *elevator_allow_merge_fn;
+	elevator_allow_bio_merge_fn *elevator_allow_bio_merge_fn;
+	elevator_allow_rq_merge_fn *elevator_allow_rq_merge_fn;
 	elevator_bio_merged_fn *elevator_bio_merged_fn;
 
 	elevator_dispatch_fn *elevator_dispatch_fn;
@@ -157,7 +162,7 @@ extern ssize_t elv_iosched_store(struct request_queue *, const char *, size_t);
 extern int elevator_init(struct request_queue *, char *);
 extern void elevator_exit(struct elevator_queue *);
 extern int elevator_change(struct request_queue *, const char *);
-extern bool elv_rq_merge_ok(struct request *, struct bio *);
+extern bool elv_bio_merge_ok(struct request *, struct bio *);
 extern struct elevator_queue *elevator_alloc(struct request_queue *,
 					struct elevator_type *);