summaryrefslogtreecommitdiffstats
path: root/block/blk-merge.c
diff options
context:
space:
mode:
authorTahsin Erdogan <tahsin@google.com>2016-07-07 11:48:22 -0700
committerJens Axboe <axboe@fb.com>2016-07-20 21:35:12 -0600
commit72ef799b3f14f4cb4c56ba3af6e6bdcbae6df368 (patch)
treecb511d5616fa5119a4f0e8f9fd8c693f8a7ecd21 /block/blk-merge.c
parent68bdf1ac2aa6318198adfe12407173bc60248b4e (diff)
downloadlinux-0-day-72ef799b3f14f4cb4c56ba3af6e6bdcbae6df368.tar.gz
linux-0-day-72ef799b3f14f4cb4c56ba3af6e6bdcbae6df368.tar.xz
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>
Diffstat (limited to 'block/blk-merge.c')
-rw-r--r--block/blk-merge.c6
1 files changed, 6 insertions, 0 deletions
diff --git a/block/blk-merge.c b/block/blk-merge.c
index c265348b75d1a..e7c2fbc3f6564 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -744,6 +744,12 @@ int attempt_front_merge(struct request_queue *q, struct request *rq)
int blk_attempt_req_merge(struct request_queue *q, struct request *rq,
struct request *next)
{
+ struct elevator_queue *e = q->elevator;
+
+ if (e->type->ops.elevator_allow_rq_merge_fn)
+ if (!e->type->ops.elevator_allow_rq_merge_fn(q, rq, next))
+ return 0;
+
return attempt_merge(q, rq, next);
}