From: Tao Cui Add iocost_ioc_tick, emitted once per period from ioc_timer_fn() with the overall controller state: period_us, vrate, busy_level, active iocg count and usage percentage. busy_level, cur_period, nr_active and usage_us_sum are complete at the emission point. usage is wall time over wall time, summed over iocgs, and is not capped at 100. vrate and period_us reflect the current controller state, which an io.cost.qos write may have changed mid-period. The event fires every period the controller is running, including steady states, plus one final tick before the controller goes idle, so the transition to dormancy is directly visible. The active iocg count is only gathered when the tracepoint is enabled. Suggested-by: Tejun Heo Signed-off-by: Tao Cui --- MAINTAINERS | 1 + block/blk-iocost.c | 17 ++++++++++++++ include/trace/events/iocost.h | 43 +++++++++++++++++++++++++++++++++++ 3 files changed, 61 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index aaf2825ac945..25cd7cd4f17b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6832,6 +6832,7 @@ F: block/blk-iocost.c F: block/blk-iolatency.c F: block/blk-throttle.c F: include/linux/blk-cgroup.h +F: include/trace/events/iocost.h CONTROL GROUP - CPUSET M: Waiman Long diff --git a/block/blk-iocost.c b/block/blk-iocost.c index 22a3d7eb3b1b..8b624654992b 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -2349,6 +2349,7 @@ static void ioc_timer_fn(struct timer_list *timer) struct ioc_now now; LIST_HEAD(surpluses); int nr_debtors, nr_shortages = 0, nr_lagging = 0; + int nr_active = 0; u64 usage_us_sum = 0; u32 ppm_rthr; u32 ppm_wthr; @@ -2546,6 +2547,22 @@ static void ioc_timer_fn(struct timer_list *timer) ioc->busy_level = clamp(ioc->busy_level, -1000, 1000); + /* + * busy_level, cur_period, nr_active and usage_us_sum are complete + * here. usage is wall time over wall time, summed over iocgs, and + * is not capped at 100. vrate and period_us reflect the current + * controller state, which an io.cost.qos write may have changed + * mid-period. Emit before the refresh and the period transition. + */ + if (trace_iocost_ioc_tick_enabled()) { + struct ioc_gq *active_iocg; + + list_for_each_entry(active_iocg, &ioc->active_iocgs, + active_list) + nr_active++; + } + trace_iocost_ioc_tick(ioc, &now, nr_active, usage_us_sum); + ioc_adjust_base_vrate(ioc, rq_wait_pct, nr_lagging, nr_shortages, prev_busy_level, missed_ppm); diff --git a/include/trace/events/iocost.h b/include/trace/events/iocost.h index eb711343ce4f..fb0be4b8c629 100644 --- a/include/trace/events/iocost.h +++ b/include/trace/events/iocost.h @@ -181,6 +181,49 @@ TRACE_EVENT(iocost_ioc_vrate_adj, ) ); +/* + * Periodic per-device summary, emitted once per period before the vrate + * adjustment and the period transition in ioc_timer_fn(). Unlike the + * state-change events above, this fires every period the controller is + * running, including steady states, and carries the overall controller state + * so basic monitoring doesn't require drgn. + */ +TRACE_EVENT(iocost_ioc_tick, + + TP_PROTO(struct ioc *ioc, const struct ioc_now *now, + int nr_active, u64 usage_us_sum), + + TP_ARGS(ioc, now, nr_active, usage_us_sum), + + TP_STRUCT__entry ( + __string(devname, ioc_name(ioc)) + __field(u64, cur_period) + __field(u32, period_us) + __field(u64, vrate) + __field(int, busy_level) + __field(int, nr_active) + __field(u32, usage_pct) + ), + + TP_fast_assign( + __assign_str(devname); + __entry->cur_period = atomic64_read(&ioc->cur_period); + __entry->period_us = ioc->period_us; + __entry->vrate = ioc->vtime_base_rate; + __entry->busy_level = ioc->busy_level; + __entry->nr_active = nr_active; + __entry->usage_pct = now->now > ioc->period_at ? + div64_u64(usage_us_sum * 100, + now->now - ioc->period_at) : 0; + ), + + TP_printk("[%s] period=%llu:%uus vrate=%llu busy=%d active=%d usage=%u%%", + __get_str(devname), __entry->cur_period, __entry->period_us, + __entry->vrate, __entry->busy_level, __entry->nr_active, + __entry->usage_pct + ) +); + TRACE_EVENT(iocost_iocg_forgive_debt, TP_PROTO(struct ioc_gq *iocg, const char *path, struct ioc_now *now, -- 2.53.0