summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorTejun Heo <tj@kernel.org>2019-09-25 16:03:09 -0700
committerJens Axboe <axboe@kernel.dk>2019-09-26 01:12:00 -0600
commit7cd806a9a953f234b9865c30028f47fd738ce375 (patch)
treeb1679109d6942bcc7c1649ce407195653377a9c5
parent25d41e4aadb0788b4fae8a8fca90f437b9ebd727 (diff)
iocost: improve nr_lagging handling
Some IOs may span multiple periods. As latencies are collected on completion, the inbetween periods won't register them and may incorrectly decide to increase vrate. nr_lagging tracks these IOs to avoid those situations. Currently, whenever there are IOs which are spanning from the previous period, busy_level is reset to 0 if negative thus suppressing vrate increase. This has the following two problems. * When latency target percentiles aren't set, vrate adjustment should only be governed by queue depth depletion; however, the current code keeps nr_lagging active which pulls in latency results and can keep down vrate unexpectedly. * When lagging condition is detected, it resets the entire negative busy_level. This turned out to be way too aggressive on some devices which sometimes experience extended latencies on a small subset of commands. In addition, a lagging IO will be accounted as latency target miss on completion anyway and resetting busy_level amplifies its impact unnecessarily. This patch fixes the above two problems by disabling nr_lagging counting when latency target percentiles aren't set and blocking vrate increases when there are lagging IOs while leaving busy_level as-is. Signed-off-by: Tejun Heo <tj@kernel.org> Signed-off-by: Jens Axboe <axboe@kernel.dk>
-rw-r--r--block/blk-iocost.c19
1 files changed, 11 insertions, 8 deletions
diff --git a/block/blk-iocost.c b/block/blk-iocost.c
index 32d4d6d86a99..10160de62e3b 100644
--- a/block/blk-iocost.c
+++ b/block/blk-iocost.c
@@ -1407,7 +1407,8 @@ static void ioc_timer_fn(struct timer_list *timer)
* comparing vdone against period start. If lagging behind
* IOs from past periods, don't increase vrate.
*/
- if (!atomic_read(&iocg_to_blkg(iocg)->use_delay) &&
+ if ((ppm_rthr != MILLION || ppm_wthr != MILLION) &&
+ !atomic_read(&iocg_to_blkg(iocg)->use_delay) &&
time_after64(vtime, vdone) &&
time_after64(vtime, now.vnow -
MAX_LAGGING_PERIODS * period_vtime) &&
@@ -1537,21 +1538,23 @@ skip_surplus_transfers:
missed_ppm[WRITE] > ppm_wthr) {
ioc->busy_level = max(ioc->busy_level, 0);
ioc->busy_level++;
- } else if (nr_lagging) {
- ioc->busy_level = max(ioc->busy_level, 0);
- } else if (nr_shortages && !nr_surpluses &&
- rq_wait_pct <= RQ_WAIT_BUSY_PCT * UNBUSY_THR_PCT / 100 &&
+ } else if (rq_wait_pct <= RQ_WAIT_BUSY_PCT * UNBUSY_THR_PCT / 100 &&
missed_ppm[READ] <= ppm_rthr * UNBUSY_THR_PCT / 100 &&
missed_ppm[WRITE] <= ppm_wthr * UNBUSY_THR_PCT / 100) {
- ioc->busy_level = min(ioc->busy_level, 0);
- ioc->busy_level--;
+ /* take action iff there is contention */
+ if (nr_shortages && !nr_lagging) {
+ ioc->busy_level = min(ioc->busy_level, 0);
+ /* redistribute surpluses first */
+ if (!nr_surpluses)
+ ioc->busy_level--;
+ }
} else {
ioc->busy_level = 0;
}
ioc->busy_level = clamp(ioc->busy_level, -1000, 1000);
- if (ioc->busy_level) {
+ if (ioc->busy_level > 0 || (ioc->busy_level < 0 && !nr_lagging)) {
u64 vrate = atomic64_read(&ioc->vtime_rate);
u64 vrate_min = ioc->vrate_min, vrate_max = ioc->vrate_max;