commit 9f5ede3c01f9 ("block: throttle split bio in case of iops limit")
introduce a new problem, for example:
[root@localhost ~]# echo "8:0 1024" > /sys/fs/cgroup/blkio/blkio.throttle.write_bps_device
[root@localhost ~]# echo $$ > /sys/fs/cgroup/blkio/cgroup.procs
[root@localhost ~]# dd if=/dev/zero of=/dev/sda bs=10k count=1 oflag=direct &
[1] 620
[root@localhost ~]# dd if=/dev/zero of=/dev/sda bs=10k count=1 oflag=direct &
[2] 626
[root@localhost ~]# 1+0 records in
1+0 records out
10240 bytes (10 kB, 10 KiB) copied, 10.0038 s, 1.0 kB/s1+0 records in
1+0 records out
10240 bytes (10 kB, 10 KiB) copied, 9.23076 s, 1.1 kB/s
-> the second bio is issued after 10s instead of 20s.
This is because if some bios are already queued, current bio is queued
directly and the flag 'BIO_THROTTLED' is set. And later, when former
bios are dispatched, this bio will be dispatched without waiting at all,
this is due to tg_with_in_bps_limit() return 0 for this bio.
In order to fix the problem, don't skip flaged bio in
tg_with_in_bps_limit(), and for the problem that split bio can be
double accounted, compensate the over-accounting in __blk_throtl_bio().
Fixes: 9f5ede3c01f9 ("block: throttle split bio in case of iops limit")
Signed-off-by: Yu Kuai <yukuai3@xxxxxxxxxx>
---
block/blk-throttle.c | 24 ++++++++++++++++++------
1 file changed, 18 insertions(+), 6 deletions(-)
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 447e1b8722f7..6f69859eae23 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -811,7 +811,7 @@ static bool tg_with_in_bps_limit(struct throtl_grp *tg, struct bio *bio,
unsigned int bio_size = throtl_bio_data_size(bio);
/* no need to throttle if this bio's bytes have been accounted */
- if (bps_limit == U64_MAX || bio_flagged(bio, BIO_THROTTLED)) {
+ if (bps_limit == U64_MAX) {
if (wait)
*wait = 0;
return true;
@@ -921,11 +921,8 @@ static void throtl_charge_bio(struct throtl_grp *tg, struct bio *bio)
unsigned int bio_size = throtl_bio_data_size(bio);
/* Charge the bio to the group */
- if (!bio_flagged(bio, BIO_THROTTLED)) {
- tg->bytes_disp[rw] += bio_size;
- tg->last_bytes_disp[rw] += bio_size;
- }
-
+ tg->bytes_disp[rw] += bio_size;
+ tg->last_bytes_disp[rw] += bio_size;
tg->io_disp[rw]++;
tg->last_io_disp[rw]++;
@@ -2121,6 +2118,21 @@ bool __blk_throtl_bio(struct bio *bio)
tg->last_low_overflow_time[rw] = jiffies;
throtl_downgrade_check(tg);
throtl_upgrade_check(tg);
+
+ /*
+ * re-entered bio has accounted bytes already, so try to
+ * compensate previous over-accounting. However, if new
+ * slice is started, just forget it.
+ */
+ if (bio_flagged(bio, BIO_THROTTLED)) {
+ unsigned int bio_size = throtl_bio_data_size(bio);
+
+ if (tg->bytes_disp[rw] >= bio_size)
+ tg->bytes_disp[rw] -= bio_size;
+ if (tg->last_bytes_disp[rw] > bio_size)
+ tg->last_bytes_disp[rw] -= bio_size;
+ }
+
/* throtl is FIFO - if bios are already queued, should queue */
if (sq->nr_queued[rw])
break;
--
2.31.1
