blk-iocost: decouple vrate adjustment from surplus transfers

Budget donations are inaccurate and could take multiple periods to converge.
To prevent triggering vrate adjustments while surplus transfers were
catching up, vrate adjustment was suppressed if donations were increasing,
which was indicated by non-zero nr_surpluses.

This entangling won't be necessary with the scheduled rewrite of donation
mechanism which will make it precise and immediate. Let's decouple the two
in preparation.

Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

diff --git a/block/blk-iocost.c b/block/blk-iocost.c
index c1cd66c..a3889a8 100644 (file)
--- a/block/blk-iocost.c
+++ b/block/blk-iocost.c
@@ -1508,7 +1508,7 @@ static void ioc_timer_fn(struct timer_list *timer)
        struct ioc_gq *iocg, *tiocg;
        struct ioc_now now;
        LIST_HEAD(surpluses);
-       int nr_surpluses = 0, nr_shortages = 0, nr_lagging = 0;
+       int nr_shortages = 0, nr_lagging = 0;
        u32 ppm_rthr = MILLION - ioc->params.qos[QOS_RPPM];
        u32 ppm_wthr = MILLION - ioc->params.qos[QOS_WPPM];
        u32 missed_ppm[2], rq_wait_pct;
@@ -1640,10 +1640,8 @@ static void ioc_timer_fn(struct timer_list *timer)
                        atomic64_add(delta, &iocg->vtime);
                        atomic64_add(delta, &iocg->done_vtime);
                        /* if usage is sufficiently low, maybe it can donate */
-                       if (surplus_adjusted_hweight_inuse(usage, hw_inuse)) {
+                       if (surplus_adjusted_hweight_inuse(usage, hw_inuse))
                                list_add(&iocg->surplus_list, &surpluses);
-                               nr_surpluses++;
-                       }
                } else if (hw_inuse < hw_active) {
                        u32 new_hwi, new_inuse;
 
@@ -1673,7 +1671,7 @@ static void ioc_timer_fn(struct timer_list *timer)
                }
        }
 
-       if (!nr_shortages || !nr_surpluses)
+       if (!nr_shortages || list_empty(&surpluses))
                goto skip_surplus_transfers;
 
        /* there are both shortages and surpluses, transfer surpluses */
@@ -1738,11 +1736,9 @@ skip_surplus_transfers:
 
                        /*
                         * If there are IOs spanning multiple periods, wait
-                        * them out before pushing the device harder.  If
-                        * there are surpluses, let redistribution work it
-                        * out first.
+                        * them out before pushing the device harder.
                         */
-                       if (!nr_lagging && !nr_surpluses)
+                       if (!nr_lagging)
                                ioc->busy_level--;
                } else {
                        /*
@@ -1796,15 +1792,14 @@ skip_surplus_transfers:
                }
 
                trace_iocost_ioc_vrate_adj(ioc, vrate, missed_ppm, rq_wait_pct,
-                                          nr_lagging, nr_shortages,
-                                          nr_surpluses);
+                                          nr_lagging, nr_shortages);
 
                atomic64_set(&ioc->vtime_rate, vrate);
                ioc_refresh_margins(ioc);
        } else if (ioc->busy_level != prev_busy_level || nr_lagging) {
                trace_iocost_ioc_vrate_adj(ioc, atomic64_read(&ioc->vtime_rate),
                                           missed_ppm, rq_wait_pct, nr_lagging,
-                                          nr_shortages, nr_surpluses);
+                                          nr_shortages);
        }
 
        ioc_refresh_params(ioc, false);

diff --git a/include/trace/events/iocost.h b/include/trace/events/iocost.h
index a905ecc..ee024fe 100644 (file)
--- a/include/trace/events/iocost.h
+++ b/include/trace/events/iocost.h
@@ -128,11 +128,9 @@ DEFINE_EVENT(iocg_inuse_update, iocost_inuse_reset,
 TRACE_EVENT(iocost_ioc_vrate_adj,
 
        TP_PROTO(struct ioc *ioc, u64 new_vrate, u32 *missed_ppm,
-               u32 rq_wait_pct, int nr_lagging, int nr_shortages,
-               int nr_surpluses),
+               u32 rq_wait_pct, int nr_lagging, int nr_shortages),
 
-       TP_ARGS(ioc, new_vrate, missed_ppm, rq_wait_pct, nr_lagging, nr_shortages,
-               nr_surpluses),
+       TP_ARGS(ioc, new_vrate, missed_ppm, rq_wait_pct, nr_lagging, nr_shortages),
 
        TP_STRUCT__entry (
                __string(devname, ioc_name(ioc))
@@ -144,7 +142,6 @@ TRACE_EVENT(iocost_ioc_vrate_adj,
                __field(u32, rq_wait_pct)
                __field(int, nr_lagging)
                __field(int, nr_shortages)
-               __field(int, nr_surpluses)
        ),
 
        TP_fast_assign(
@@ -157,15 +154,13 @@ TRACE_EVENT(iocost_ioc_vrate_adj,
                __entry->rq_wait_pct = rq_wait_pct;
                __entry->nr_lagging = nr_lagging;
                __entry->nr_shortages = nr_shortages;
-               __entry->nr_surpluses = nr_surpluses;
        ),
 
-       TP_printk("[%s] vrate=%llu->%llu busy=%d missed_ppm=%u:%u rq_wait_pct=%u lagging=%d shortages=%d surpluses=%d",
+       TP_printk("[%s] vrate=%llu->%llu busy=%d missed_ppm=%u:%u rq_wait_pct=%u lagging=%d shortages=%d",
                __get_str(devname), __entry->old_vrate, __entry->new_vrate,
                __entry->busy_level,
                __entry->read_missed_ppm, __entry->write_missed_ppm,
-               __entry->rq_wait_pct, __entry->nr_lagging, __entry->nr_shortages,
-               __entry->nr_surpluses
+               __entry->rq_wait_pct, __entry->nr_lagging, __entry->nr_shortages
        )
 );