summaryrefslogtreecommitdiffstats
path: root/block/blk-throttle.c
diff options
context:
space:
mode:
authorShaohua Li <shli@fb.com>2017-03-27 15:19:43 -0700
committerJens Axboe <axboe@fb.com>2017-03-28 08:02:20 -0600
commit53696b8d212f4a0f0e5dcdb3df64558dcdf03d1a (patch)
tree843090a882b03bbaa9731b1bab546be79f7a79c5 /block/blk-throttle.c
parentb9147dd1bae2b15d6931ecd42f8606c775fecbc9 (diff)
downloadlinux-53696b8d212f4a0f0e5dcdb3df64558dcdf03d1a.tar.bz2
blk-throttle: add latency target support
One hard problem adding .low limit is to detect idle cgroup. If one cgroup doesn't dispatch enough IO against its low limit, we must have a mechanism to determine if other cgroups dispatch more IO. We added the think time detection mechanism before, but it doesn't work for all workloads. Here we add a latency based approach. We already have mechanism to calculate latency threshold for each IO size. For every IO dispatched from a cgorup, we compare its latency against its threshold and record the info. If most IO latency is below threshold (in the code I use 75%), the cgroup could be treated idle and other cgroups can dispatch more IO. Currently this latency target check is only for SSD as we can't calcualte the latency target for hard disk. And this is only for cgroup leaf node so far. Signed-off-by: Shaohua Li <shli@fb.com> Signed-off-by: Jens Axboe <axboe@fb.com>
Diffstat (limited to 'block/blk-throttle.c')
-rw-r--r--block/blk-throttle.c39
1 files changed, 35 insertions, 4 deletions
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 140da29f5800..c82bf9b1fe72 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -165,6 +165,10 @@ struct throtl_grp {
unsigned long checked_last_finish_time; /* ns / 1024 */
unsigned long avg_idletime; /* ns / 1024 */
unsigned long idletime_threshold; /* us */
+
+ unsigned int bio_cnt; /* total bios */
+ unsigned int bad_bio_cnt; /* bios exceeding latency threshold */
+ unsigned long bio_cnt_reset_time;
};
/* We measure latency for request size from <= 4k to >= 1M */
@@ -1720,12 +1724,15 @@ static bool throtl_tg_is_idle(struct throtl_grp *tg)
* - single idle is too long, longer than a fixed value (in case user
* configure a too big threshold) or 4 times of slice
* - average think time is more than threshold
+ * - IO latency is largely below threshold
*/
unsigned long time = jiffies_to_usecs(4 * tg->td->throtl_slice);
time = min_t(unsigned long, MAX_IDLE_TIME, time);
return (ktime_get_ns() >> 10) - tg->last_finish_time > time ||
- tg->avg_idletime > tg->idletime_threshold;
+ tg->avg_idletime > tg->idletime_threshold ||
+ (tg->latency_target && tg->bio_cnt &&
+ tg->bad_bio_cnt * 5 < tg->bio_cnt);
}
static bool throtl_tg_can_upgrade(struct throtl_grp *tg)
@@ -2194,12 +2201,36 @@ void blk_throtl_bio_endio(struct bio *bio)
start_time = blk_stat_time(&bio->bi_issue_stat) >> 10;
finish_time = __blk_stat_time(finish_time_ns) >> 10;
+ if (!start_time || finish_time <= start_time)
+ return;
+
+ lat = finish_time - start_time;
/* this is only for bio based driver */
- if (start_time && finish_time > start_time &&
- !(bio->bi_issue_stat.stat & SKIP_LATENCY)) {
- lat = finish_time - start_time;
+ if (!(bio->bi_issue_stat.stat & SKIP_LATENCY))
throtl_track_latency(tg->td, blk_stat_size(&bio->bi_issue_stat),
bio_op(bio), lat);
+
+ if (tg->latency_target) {
+ int bucket;
+ unsigned int threshold;
+
+ bucket = request_bucket_index(
+ blk_stat_size(&bio->bi_issue_stat));
+ threshold = tg->td->avg_buckets[bucket].latency +
+ tg->latency_target;
+ if (lat > threshold)
+ tg->bad_bio_cnt++;
+ /*
+ * Not race free, could get wrong count, which means cgroups
+ * will be throttled
+ */
+ tg->bio_cnt++;
+ }
+
+ if (time_after(jiffies, tg->bio_cnt_reset_time) || tg->bio_cnt > 1024) {
+ tg->bio_cnt_reset_time = tg->td->throtl_slice + jiffies;
+ tg->bio_cnt /= 2;
+ tg->bad_bio_cnt /= 2;
}
}
#endif