From 7cd806a9a953f234b9865c30028f47fd738ce375 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 25 Sep 2019 16:03:09 -0700 Subject: [PATCH] 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 Signed-off-by: Jens Axboe --- block/blk-iocost.c | 19 +++++++++++-------- 1 file 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;