From: Tao Cui The existing iocost tracepoints are state-change driven: vrate_adj fires only when the adjustment logic runs, inuse_* only on surplus state transitions, activate/idle only on cgroup state changes. In a steady state none of them fire. The only other way to observe the controller (period length, vrate, busy level, active cgroup count, device utilization) is iocost_monitor.py, which reads kernel memory through drgn and is not usable in most production environments. Add iocost_ioc_tick, emitted once per period from the tail of ioc_timer_fn() with the overall controller state: period_us, vrate, busy_level, active iocg count, usage percentage and running state. It fires every period the controller runs, including steady states, plus one final tick before the controller goes idle, which makes dormancy (e.g. a device saturated entirely by uncharged IO) directly visible. At the default period this is a couple of events per second per device; the cost is zero while the static key is off. Signed-off-by: Tao Cui --- block/blk-iocost.c | 5 +++++ include/trace/events/iocost.h | 40 +++++++++++++++++++++++++++++++++++ 2 files changed, 45 insertions(+) diff --git a/block/blk-iocost.c b/block/blk-iocost.c index 2745bffcd5eef..c24daa9d72ee9 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -2238,6 +2238,7 @@ 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; @@ -2274,6 +2275,8 @@ static void ioc_timer_fn(struct timer_list *timer) u64 vdone, vtime, usage_us; u32 hw_active, hw_inuse; + nr_active++; + /* * Collect unused and wind vtime closer to vnow to prevent * iocgs from accumulating a large amount of budget. @@ -2460,6 +2463,8 @@ static void ioc_timer_fn(struct timer_list *timer) ioc_refresh_vrate(ioc, &now); } + trace_iocost_ioc_tick(ioc, nr_active, usage_us_sum); + spin_unlock_irq(&ioc->lock); } diff --git a/include/trace/events/iocost.h b/include/trace/events/iocost.h index e772b1bc60d60..2b9ff348a4f51 100644 --- a/include/trace/events/iocost.h +++ b/include/trace/events/iocost.h @@ -178,6 +178,46 @@ TRACE_EVENT(iocost_ioc_vrate_adj, ) ); +/* + * Periodic per-device summary, emitted once per period from the tail of + * 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, int nr_active, u64 usage_us_sum), + + TP_ARGS(ioc, nr_active, usage_us_sum), + + TP_STRUCT__entry ( + __string(devname, ioc_name(ioc)) + __field(u32, period_us) + __field(u64, vrate) + __field(int, busy_level) + __field(int, nr_active) + __field(u32, usage_pct) + __field(int, running) + ), + + TP_fast_assign( + __assign_str(devname); + __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 = ioc->period_us ? + div_u64(usage_us_sum * 100, ioc->period_us) : 0; + __entry->running = ioc->running; + ), + + TP_printk("[%s] period=%uus vrate=%llu busy=%d active=%d usage=%u%% running=%d", + __get_str(devname), __entry->period_us, __entry->vrate, + __entry->busy_level, __entry->nr_active, __entry->usage_pct, + __entry->running + ) +); + TRACE_EVENT(iocost_iocg_forgive_debt, TP_PROTO(struct ioc_gq *iocg, const char *path, struct ioc_now *now, -- 2.43.0