diff options
Diffstat (limited to 'block/blk-throttle.c')
| -rw-r--r-- | block/blk-throttle.c | 1610 |
1 files changed, 493 insertions, 1117 deletions
diff --git a/block/blk-throttle.c b/block/blk-throttle.c index 16f5766620a4..397b6a410f9e 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -25,37 +25,12 @@ #define DFL_THROTL_SLICE_HD (HZ / 10) #define DFL_THROTL_SLICE_SSD (HZ / 50) #define MAX_THROTL_SLICE (HZ) -#define MAX_IDLE_TIME (5L * 1000 * 1000) /* 5 s */ -#define MIN_THROTL_BPS (320 * 1024) -#define MIN_THROTL_IOPS (10) -#define DFL_LATENCY_TARGET (-1L) -#define DFL_IDLE_THRESHOLD (0) -#define DFL_HD_BASELINE_LATENCY (4000L) /* 4ms */ -#define LATENCY_FILTERED_SSD (0) -/* - * For HD, very small latency comes from sequential IO. Such IO is helpless to - * help determine if its IO is impacted by others, hence we ignore the IO - */ -#define LATENCY_FILTERED_HD (1000L) /* 1ms */ /* A workqueue to queue throttle related work */ static struct workqueue_struct *kthrotld_workqueue; #define rb_entry_tg(node) rb_entry((node), struct throtl_grp, rb_node) -/* We measure latency for request size from <= 4k to >= 1M */ -#define LATENCY_BUCKET_SIZE 9 - -struct latency_bucket { - unsigned long total_latency; /* ns / 1024 */ - int samples; -}; - -struct avg_latency_bucket { - unsigned long latency; /* ns / 1024 */ - bool valid; -}; - struct throtl_data { /* service tree for active throtl groups */ @@ -70,19 +45,6 @@ struct throtl_data /* Work for dispatching throttled bios */ struct work_struct dispatch_work; - unsigned int limit_index; - bool limit_valid[LIMIT_CNT]; - - unsigned long low_upgrade_time; - unsigned long low_downgrade_time; - - unsigned int scale; - - struct latency_bucket tmp_buckets[2][LATENCY_BUCKET_SIZE]; - struct avg_latency_bucket avg_buckets[2][LATENCY_BUCKET_SIZE]; - struct latency_bucket __percpu *latency_buckets[2]; - unsigned long last_calculate_time; - unsigned long filtered_latency; bool track_bio_latency; }; @@ -126,89 +88,26 @@ static struct throtl_data *sq_to_td(struct throtl_service_queue *sq) return container_of(sq, struct throtl_data, service_queue); } -/* - * cgroup's limit in LIMIT_MAX is scaled if low limit is set. This scale is to - * make the IO dispatch more smooth. - * Scale up: linearly scale up according to elapsed time since upgrade. For - * every throtl_slice, the limit scales up 1/2 .low limit till the - * limit hits .max limit - * Scale down: exponentially scale down if a cgroup doesn't hit its .low limit - */ -static uint64_t throtl_adjusted_limit(uint64_t low, struct throtl_data *td) -{ - /* arbitrary value to avoid too big scale */ - if (td->scale < 4096 && time_after_eq(jiffies, - td->low_upgrade_time + td->scale * td->throtl_slice)) - td->scale = (jiffies - td->low_upgrade_time) / td->throtl_slice; - - return low + (low >> 1) * td->scale; -} - static uint64_t tg_bps_limit(struct throtl_grp *tg, int rw) { struct blkcg_gq *blkg = tg_to_blkg(tg); - struct throtl_data *td; - uint64_t ret; if (cgroup_subsys_on_dfl(io_cgrp_subsys) && !blkg->parent) return U64_MAX; - td = tg->td; - ret = tg->bps[rw][td->limit_index]; - if (ret == 0 && td->limit_index == LIMIT_LOW) { - /* intermediate node or iops isn't 0 */ - if (!list_empty(&blkg->blkcg->css.children) || - tg->iops[rw][td->limit_index]) - return U64_MAX; - else - return MIN_THROTL_BPS; - } - - if (td->limit_index == LIMIT_MAX && tg->bps[rw][LIMIT_LOW] && - tg->bps[rw][LIMIT_LOW] != tg->bps[rw][LIMIT_MAX]) { - uint64_t adjusted; - - adjusted = throtl_adjusted_limit(tg->bps[rw][LIMIT_LOW], td); - ret = min(tg->bps[rw][LIMIT_MAX], adjusted); - } - return ret; + return tg->bps[rw]; } static unsigned int tg_iops_limit(struct throtl_grp *tg, int rw) { struct blkcg_gq *blkg = tg_to_blkg(tg); - struct throtl_data *td; - unsigned int ret; if (cgroup_subsys_on_dfl(io_cgrp_subsys) && !blkg->parent) return UINT_MAX; - td = tg->td; - ret = tg->iops[rw][td->limit_index]; - if (ret == 0 && tg->td->limit_index == LIMIT_LOW) { - /* intermediate node or bps isn't 0 */ - if (!list_empty(&blkg->blkcg->css.children) || - tg->bps[rw][td->limit_index]) - return UINT_MAX; - else - return MIN_THROTL_IOPS; - } - - if (td->limit_index == LIMIT_MAX && tg->iops[rw][LIMIT_LOW] && - tg->iops[rw][LIMIT_LOW] != tg->iops[rw][LIMIT_MAX]) { - uint64_t adjusted; - - adjusted = throtl_adjusted_limit(tg->iops[rw][LIMIT_LOW], td); - if (adjusted > UINT_MAX) - adjusted = UINT_MAX; - ret = min_t(unsigned int, tg->iops[rw][LIMIT_MAX], adjusted); - } - return ret; + return tg->iops[rw]; } -#define request_bucket_index(sectors) \ - clamp_t(int, order_base_2(sectors) - 3, 0, LATENCY_BUCKET_SIZE - 1) - /** * throtl_log - log debug message via blktrace * @sq: the service_queue being reported @@ -244,7 +143,8 @@ static inline unsigned int throtl_bio_data_size(struct bio *bio) static void throtl_qnode_init(struct throtl_qnode *qn, struct throtl_grp *tg) { INIT_LIST_HEAD(&qn->node); - bio_list_init(&qn->bios); + bio_list_init(&qn->bios_bps); + bio_list_init(&qn->bios_iops); qn->tg = tg; } @@ -252,18 +152,32 @@ static void throtl_qnode_init(struct throtl_qnode *qn, struct throtl_grp *tg) * throtl_qnode_add_bio - add a bio to a throtl_qnode and activate it * @bio: bio being added * @qn: qnode to add bio to - * @queued: the service_queue->queued[] list @qn belongs to + * @sq: the service_queue @qn belongs to * - * Add @bio to @qn and put @qn on @queued if it's not already on. + * Add @bio to @qn and put @qn on @sq->queued if it's not already on. * @qn->tg's reference count is bumped when @qn is activated. See the * comment on top of throtl_qnode definition for details. */ static void throtl_qnode_add_bio(struct bio *bio, struct throtl_qnode *qn, - struct list_head *queued) + struct throtl_service_queue *sq) { - bio_list_add(&qn->bios, bio); + bool rw = bio_data_dir(bio); + + /* + * Split bios have already been throttled by bps, so they are + * directly queued into the iops path. + */ + if (bio_flagged(bio, BIO_TG_BPS_THROTTLED) || + bio_flagged(bio, BIO_BPS_THROTTLED)) { + bio_list_add(&qn->bios_iops, bio); + sq->nr_queued_iops[rw]++; + } else { + bio_list_add(&qn->bios_bps, bio); + sq->nr_queued_bps[rw]++; + } + if (list_empty(&qn->node)) { - list_add_tail(&qn->node, queued); + list_add_tail(&qn->node, &sq->queued[rw]); blkg_get(tg_to_blkg(qn->tg)); } } @@ -271,6 +185,10 @@ static void throtl_qnode_add_bio(struct bio *bio, struct throtl_qnode *qn, /** * throtl_peek_queued - peek the first bio on a qnode list * @queued: the qnode list to peek + * + * Always take a bio from the head of the iops queue first. If the queue is + * empty, we then take it from the bps queue to maintain the overall idea of + * fetching bios from the head. */ static struct bio *throtl_peek_queued(struct list_head *queued) { @@ -281,28 +199,33 @@ static struct bio *throtl_peek_queued(struct list_head *queued) return NULL; qn = list_first_entry(queued, struct throtl_qnode, node); - bio = bio_list_peek(&qn->bios); + bio = bio_list_peek(&qn->bios_iops); + if (!bio) + bio = bio_list_peek(&qn->bios_bps); WARN_ON_ONCE(!bio); return bio; } /** * throtl_pop_queued - pop the first bio form a qnode list - * @queued: the qnode list to pop a bio from + * @sq: the service_queue to pop a bio from * @tg_to_put: optional out argument for throtl_grp to put + * @rw: read/write * - * Pop the first bio from the qnode list @queued. After popping, the first - * qnode is removed from @queued if empty or moved to the end of @queued so - * that the popping order is round-robin. + * Pop the first bio from the qnode list @sq->queued. Note that we firstly + * focus on the iops list because bios are ultimately dispatched from it. + * After popping, the first qnode is removed from @sq->queued if empty or moved + * to the end of @sq->queued so that the popping order is round-robin. * * When the first qnode is removed, its associated throtl_grp should be put * too. If @tg_to_put is NULL, this function automatically puts it; * otherwise, *@tg_to_put is set to the throtl_grp to put and the caller is * responsible for putting it. */ -static struct bio *throtl_pop_queued(struct list_head *queued, - struct throtl_grp **tg_to_put) +static struct bio *throtl_pop_queued(struct throtl_service_queue *sq, + struct throtl_grp **tg_to_put, bool rw) { + struct list_head *queued = &sq->queued[rw]; struct throtl_qnode *qn; struct bio *bio; @@ -310,10 +233,17 @@ static struct bio *throtl_pop_queued(struct list_head *queued, return NULL; qn = list_first_entry(queued, struct throtl_qnode, node); - bio = bio_list_pop(&qn->bios); + bio = bio_list_pop(&qn->bios_iops); + if (bio) { + sq->nr_queued_iops[rw]--; + } else { + bio = bio_list_pop(&qn->bios_bps); + if (bio) + sq->nr_queued_bps[rw]--; + } WARN_ON_ONCE(!bio); - if (bio_list_empty(&qn->bios)) { + if (bio_list_empty(&qn->bios_bps) && bio_list_empty(&qn->bios_iops)) { list_del_init(&qn->node); if (tg_to_put) *tg_to_put = qn->tg; @@ -359,20 +289,10 @@ static struct blkg_policy_data *throtl_pd_alloc(struct gendisk *disk, } RB_CLEAR_NODE(&tg->rb_node); - tg->bps[READ][LIMIT_MAX] = U64_MAX; - tg->bps[WRITE][LIMIT_MAX] = U64_MAX; - tg->iops[READ][LIMIT_MAX] = UINT_MAX; - tg->iops[WRITE][LIMIT_MAX] = UINT_MAX; - tg->bps_conf[READ][LIMIT_MAX] = U64_MAX; - tg->bps_conf[WRITE][LIMIT_MAX] = U64_MAX; - tg->iops_conf[READ][LIMIT_MAX] = UINT_MAX; - tg->iops_conf[WRITE][LIMIT_MAX] = UINT_MAX; - /* LIMIT_LOW will have default value 0 */ - - tg->latency_target = DFL_LATENCY_TARGET; - tg->latency_target_conf = DFL_LATENCY_TARGET; - tg->idletime_threshold = DFL_IDLE_THRESHOLD; - tg->idletime_threshold_conf = DFL_IDLE_THRESHOLD; + tg->bps[READ] = U64_MAX; + tg->bps[WRITE] = U64_MAX; + tg->iops[READ] = UINT_MAX; + tg->iops[WRITE] = UINT_MAX; return &tg->pd; @@ -418,18 +338,15 @@ static void throtl_pd_init(struct blkg_policy_data *pd) static void tg_update_has_rules(struct throtl_grp *tg) { struct throtl_grp *parent_tg = sq_to_tg(tg->service_queue.parent_sq); - struct throtl_data *td = tg->td; int rw; for (rw = READ; rw <= WRITE; rw++) { tg->has_rules_iops[rw] = (parent_tg && parent_tg->has_rules_iops[rw]) || - (td->limit_valid[td->limit_index] && - tg_iops_limit(tg, rw) != UINT_MAX); + tg_iops_limit(tg, rw) != UINT_MAX; tg->has_rules_bps[rw] = (parent_tg && parent_tg->has_rules_bps[rw]) || - (td->limit_valid[td->limit_index] && - (tg_bps_limit(tg, rw) != U64_MAX)); + tg_bps_limit(tg, rw) != U64_MAX; } } @@ -443,54 +360,11 @@ static void throtl_pd_online(struct blkg_policy_data *pd) tg_update_has_rules(tg); } -#ifdef CONFIG_BLK_DEV_THROTTLING_LOW -static void blk_throtl_update_limit_valid(struct throtl_data *td) -{ - struct cgroup_subsys_state *pos_css; - struct blkcg_gq *blkg; - bool low_valid = false; - - rcu_read_lock(); - blkg_for_each_descendant_post(blkg, pos_css, td->queue->root_blkg) { - struct throtl_grp *tg = blkg_to_tg(blkg); - - if (tg->bps[READ][LIMIT_LOW] || tg->bps[WRITE][LIMIT_LOW] || - tg->iops[READ][LIMIT_LOW] || tg->iops[WRITE][LIMIT_LOW]) { - low_valid = true; - break; - } - } - rcu_read_unlock(); - - td->limit_valid[LIMIT_LOW] = low_valid; -} -#else -static inline void blk_throtl_update_limit_valid(struct throtl_data *td) -{ -} -#endif - -static void throtl_upgrade_state(struct throtl_data *td); -static void throtl_pd_offline(struct blkg_policy_data *pd) -{ - struct throtl_grp *tg = pd_to_tg(pd); - - tg->bps[READ][LIMIT_LOW] = 0; - tg->bps[WRITE][LIMIT_LOW] = 0; - tg->iops[READ][LIMIT_LOW] = 0; - tg->iops[WRITE][LIMIT_LOW] = 0; - - blk_throtl_update_limit_valid(tg->td); - - if (!tg->td->limit_valid[tg->td->limit_index]) - throtl_upgrade_state(tg->td); -} - static void throtl_pd_free(struct blkg_policy_data *pd) { struct throtl_grp *tg = pd_to_tg(pd); - del_timer_sync(&tg->service_queue.pending_timer); + timer_delete_sync(&tg->service_queue.pending_timer); blkg_rwstat_exit(&tg->stat_bytes); blkg_rwstat_exit(&tg->stat_ios); kfree(tg); @@ -635,8 +509,6 @@ static inline void throtl_start_new_slice_with_credit(struct throtl_grp *tg, { tg->bytes_disp[rw] = 0; tg->io_disp[rw] = 0; - tg->carryover_bytes[rw] = 0; - tg->carryover_ios[rw] = 0; /* * Previous slice has expired. We must have trimmed it after last @@ -655,16 +527,14 @@ static inline void throtl_start_new_slice_with_credit(struct throtl_grp *tg, } static inline void throtl_start_new_slice(struct throtl_grp *tg, bool rw, - bool clear_carryover) + bool clear) { - tg->bytes_disp[rw] = 0; - tg->io_disp[rw] = 0; + if (clear) { + tg->bytes_disp[rw] = 0; + tg->io_disp[rw] = 0; + } tg->slice_start[rw] = jiffies; tg->slice_end[rw] = jiffies + tg->td->throtl_slice; - if (clear_carryover) { - tg->carryover_bytes[rw] = 0; - tg->carryover_ios[rw] = 0; - } throtl_log(&tg->service_queue, "[%c] new slice start=%lu end=%lu jiffies=%lu", @@ -681,6 +551,9 @@ static inline void throtl_set_slice_end(struct throtl_grp *tg, bool rw, static inline void throtl_extend_slice(struct throtl_grp *tg, bool rw, unsigned long jiffy_end) { + if (!time_before(tg->slice_end[rw], jiffy_end)) + return; + throtl_set_slice_end(tg, rw, jiffy_end); throtl_log(&tg->service_queue, "[%c] extend slice start=%lu end=%lu jiffies=%lu", @@ -697,6 +570,11 @@ static bool throtl_slice_used(struct throtl_grp *tg, bool rw) return true; } +static unsigned int sq_queued(struct throtl_service_queue *sq, int type) +{ + return sq->nr_queued_bps[type] + sq->nr_queued_iops[type]; +} + static unsigned int calculate_io_allowed(u32 iops_limit, unsigned long jiffy_elapsed) { @@ -732,6 +610,48 @@ static u64 calculate_bytes_allowed(u64 bps_limit, unsigned long jiffy_elapsed) return mul_u64_u64_div_u64(bps_limit, (u64)jiffy_elapsed, (u64)HZ); } +static long long throtl_trim_bps(struct throtl_grp *tg, bool rw, + unsigned long time_elapsed) +{ + u64 bps_limit = tg_bps_limit(tg, rw); + long long bytes_trim; + + if (bps_limit == U64_MAX) + return 0; + + /* Need to consider the case of bytes_allowed overflow. */ + bytes_trim = calculate_bytes_allowed(bps_limit, time_elapsed); + if (bytes_trim <= 0 || tg->bytes_disp[rw] < bytes_trim) { + bytes_trim = tg->bytes_disp[rw]; + tg->bytes_disp[rw] = 0; + } else { + tg->bytes_disp[rw] -= bytes_trim; + } + + return bytes_trim; +} + +static int throtl_trim_iops(struct throtl_grp *tg, bool rw, + unsigned long time_elapsed) +{ + u32 iops_limit = tg_iops_limit(tg, rw); + int io_trim; + + if (iops_limit == UINT_MAX) + return 0; + + /* Need to consider the case of io_allowed overflow. */ + io_trim = calculate_io_allowed(iops_limit, time_elapsed); + if (io_trim <= 0 || tg->io_disp[rw] < io_trim) { + io_trim = tg->io_disp[rw]; + tg->io_disp[rw] = 0; + } else { + tg->io_disp[rw] -= io_trim; + } + + return io_trim; +} + /* Trim the used slices and adjust slice start accordingly */ static inline void throtl_trim_slice(struct throtl_grp *tg, bool rw) { @@ -756,34 +676,28 @@ static inline void throtl_trim_slice(struct throtl_grp *tg, bool rw) * sooner, then we need to reduce slice_end. A high bogus slice_end * is bad because it does not allow new slice to start. */ - throtl_set_slice_end(tg, rw, jiffies + tg->td->throtl_slice); time_elapsed = rounddown(jiffies - tg->slice_start[rw], tg->td->throtl_slice); - if (!time_elapsed) + /* Don't trim slice until at least 2 slices are used */ + if (time_elapsed < tg->td->throtl_slice * 2) return; - bytes_trim = calculate_bytes_allowed(tg_bps_limit(tg, rw), - time_elapsed) + - tg->carryover_bytes[rw]; - io_trim = calculate_io_allowed(tg_iops_limit(tg, rw), time_elapsed) + - tg->carryover_ios[rw]; - if (bytes_trim <= 0 && io_trim <= 0) + /* + * The bio submission time may be a few jiffies more than the expected + * waiting time, due to 'extra_bytes' can't be divided in + * tg_within_bps_limit(), and also due to timer wakeup delay. In this + * case, adjust slice_start will discard the extra wait time, causing + * lower rate than expected. Therefore, other than the above rounddown, + * one extra slice is preserved for deviation. + */ + time_elapsed -= tg->td->throtl_slice; + bytes_trim = throtl_trim_bps(tg, rw, time_elapsed); + io_trim = throtl_trim_iops(tg, rw, time_elapsed); + if (!bytes_trim && !io_trim) return; - tg->carryover_bytes[rw] = 0; - if ((long long)tg->bytes_disp[rw] >= bytes_trim) - tg->bytes_disp[rw] -= bytes_trim; - else - tg->bytes_disp[rw] = 0; - - tg->carryover_ios[rw] = 0; - if ((int)tg->io_disp[rw] >= io_trim) - tg->io_disp[rw] -= io_trim; - else - tg->io_disp[rw] = 0; - tg->slice_start[rw] += time_elapsed; throtl_log(&tg->service_queue, @@ -793,39 +707,60 @@ static inline void throtl_trim_slice(struct throtl_grp *tg, bool rw) jiffies); } -static void __tg_update_carryover(struct throtl_grp *tg, bool rw) +static void __tg_update_carryover(struct throtl_grp *tg, bool rw, + long long *bytes, int *ios) { unsigned long jiffy_elapsed = jiffies - tg->slice_start[rw]; u64 bps_limit = tg_bps_limit(tg, rw); u32 iops_limit = tg_iops_limit(tg, rw); + long long bytes_allowed; + int io_allowed; + + /* + * If the queue is empty, carryover handling is not needed. In such cases, + * tg->[bytes/io]_disp should be reset to 0 to avoid impacting the dispatch + * of subsequent bios. The same handling applies when the previous BPS/IOPS + * limit was set to max. + */ + if (sq_queued(&tg->service_queue, rw) == 0) { + tg->bytes_disp[rw] = 0; + tg->io_disp[rw] = 0; + return; + } /* * If config is updated while bios are still throttled, calculate and - * accumulate how many bytes/ios are waited across changes. And - * carryover_bytes/ios will be used to calculate new wait time under new - * configuration. + * accumulate how many bytes/ios are waited across changes. And use the + * calculated carryover (@bytes/@ios) to update [bytes/io]_disp, which + * will be used to calculate new wait time under new configuration. + * And we need to consider the case of bytes/io_allowed overflow. */ - if (bps_limit != U64_MAX) - tg->carryover_bytes[rw] += - calculate_bytes_allowed(bps_limit, jiffy_elapsed) - - tg->bytes_disp[rw]; - if (iops_limit != UINT_MAX) - tg->carryover_ios[rw] += - calculate_io_allowed(iops_limit, jiffy_elapsed) - - tg->io_disp[rw]; + if (bps_limit != U64_MAX) { + bytes_allowed = calculate_bytes_allowed(bps_limit, jiffy_elapsed); + if (bytes_allowed > 0) + *bytes = bytes_allowed - tg->bytes_disp[rw]; + } + if (iops_limit != UINT_MAX) { + io_allowed = calculate_io_allowed(iops_limit, jiffy_elapsed); + if (io_allowed > 0) + *ios = io_allowed - tg->io_disp[rw]; + } + + tg->bytes_disp[rw] = -*bytes; + tg->io_disp[rw] = -*ios; } static void tg_update_carryover(struct throtl_grp *tg) { - if (tg->service_queue.nr_queued[READ]) - __tg_update_carryover(tg, READ); - if (tg->service_queue.nr_queued[WRITE]) - __tg_update_carryover(tg, WRITE); + long long bytes[2] = {0}; + int ios[2] = {0}; - /* see comments in struct throtl_grp for meaning of these fields. */ + __tg_update_carryover(tg, READ, &bytes[READ], &ios[READ]); + __tg_update_carryover(tg, WRITE, &bytes[WRITE], &ios[WRITE]); + + /* see comments in struct throtl_grp for meaning of carryover. */ throtl_log(&tg->service_queue, "%s: %lld %lld %d %d\n", __func__, - tg->carryover_bytes[READ], tg->carryover_bytes[WRITE], - tg->carryover_ios[READ], tg->carryover_ios[WRITE]); + bytes[READ], bytes[WRITE], ios[READ], ios[WRITE]); } static unsigned long tg_within_iops_limit(struct throtl_grp *tg, struct bio *bio, @@ -835,21 +770,19 @@ static unsigned long tg_within_iops_limit(struct throtl_grp *tg, struct bio *bio int io_allowed; unsigned long jiffy_elapsed, jiffy_wait, jiffy_elapsed_rnd; - if (iops_limit == UINT_MAX) { - return 0; - } - jiffy_elapsed = jiffies - tg->slice_start[rw]; /* Round up to the next throttle slice, wait time must be nonzero */ jiffy_elapsed_rnd = roundup(jiffy_elapsed + 1, tg->td->throtl_slice); - io_allowed = calculate_io_allowed(iops_limit, jiffy_elapsed_rnd) + - tg->carryover_ios[rw]; + io_allowed = calculate_io_allowed(iops_limit, jiffy_elapsed_rnd); if (io_allowed > 0 && tg->io_disp[rw] + 1 <= io_allowed) return 0; /* Calc approx time to dispatch */ jiffy_wait = jiffy_elapsed_rnd - jiffy_elapsed; + + /* make sure at least one io can be dispatched after waiting */ + jiffy_wait = max(jiffy_wait, HZ / iops_limit + 1); return jiffy_wait; } @@ -862,11 +795,6 @@ static unsigned long tg_within_bps_limit(struct throtl_grp *tg, struct bio *bio, unsigned long jiffy_elapsed, jiffy_wait, jiffy_elapsed_rnd; unsigned int bio_size = throtl_bio_data_size(bio); - /* no need to throttle if this bio's bytes have been accounted */ - if (bps_limit == U64_MAX || bio_flagged(bio, BIO_BPS_THROTTLED)) { - return 0; - } - jiffy_elapsed = jiffy_elapsed_rnd = jiffies - tg->slice_start[rw]; /* Slice has just started. Consider one slice interval */ @@ -874,9 +802,10 @@ static unsigned long tg_within_bps_limit(struct throtl_grp *tg, struct bio *bio, jiffy_elapsed_rnd = tg->td->throtl_slice; jiffy_elapsed_rnd = roundup(jiffy_elapsed_rnd, tg->td->throtl_slice); - bytes_allowed = calculate_bytes_allowed(bps_limit, jiffy_elapsed_rnd) + - tg->carryover_bytes[rw]; - if (bytes_allowed > 0 && tg->bytes_disp[rw] + bio_size <= bytes_allowed) + bytes_allowed = calculate_bytes_allowed(bps_limit, jiffy_elapsed_rnd); + /* Need to consider the case of bytes_allowed overflow. */ + if ((bytes_allowed > 0 && tg->bytes_disp[rw] + bio_size <= bytes_allowed) + || bytes_allowed < 0) return 0; /* Calc approx time to dispatch */ @@ -894,17 +823,82 @@ static unsigned long tg_within_bps_limit(struct throtl_grp *tg, struct bio *bio, return jiffy_wait; } +static void throtl_charge_bps_bio(struct throtl_grp *tg, struct bio *bio) +{ + unsigned int bio_size = throtl_bio_data_size(bio); + + /* Charge the bio to the group */ + if (!bio_flagged(bio, BIO_BPS_THROTTLED) && + !bio_flagged(bio, BIO_TG_BPS_THROTTLED)) { + bio_set_flag(bio, BIO_TG_BPS_THROTTLED); + tg->bytes_disp[bio_data_dir(bio)] += bio_size; + } +} + +static void throtl_charge_iops_bio(struct throtl_grp *tg, struct bio *bio) +{ + bio_clear_flag(bio, BIO_TG_BPS_THROTTLED); + tg->io_disp[bio_data_dir(bio)]++; +} + /* - * Returns whether one can dispatch a bio or not. Also returns approx number - * of jiffies to wait before this bio is with-in IO rate and can be dispatched + * If previous slice expired, start a new one otherwise renew/extend existing + * slice to make sure it is at least throtl_slice interval long since now. New + * slice is started only for empty throttle group. If there is queued bio, that + * means there should be an active slice and it should be extended instead. */ -static bool tg_may_dispatch(struct throtl_grp *tg, struct bio *bio, - unsigned long *wait) +static void tg_update_slice(struct throtl_grp *tg, bool rw) +{ + if (throtl_slice_used(tg, rw) && + sq_queued(&tg->service_queue, rw) == 0) + throtl_start_new_slice(tg, rw, true); + else + throtl_extend_slice(tg, rw, jiffies + tg->td->throtl_slice); +} + +static unsigned long tg_dispatch_bps_time(struct throtl_grp *tg, struct bio *bio) { bool rw = bio_data_dir(bio); - unsigned long bps_wait = 0, iops_wait = 0, max_wait = 0; u64 bps_limit = tg_bps_limit(tg, rw); + unsigned long bps_wait; + + /* no need to throttle if this bio's bytes have been accounted */ + if (bps_limit == U64_MAX || tg->flags & THROTL_TG_CANCELING || + bio_flagged(bio, BIO_BPS_THROTTLED) || + bio_flagged(bio, BIO_TG_BPS_THROTTLED)) + return 0; + + tg_update_slice(tg, rw); + bps_wait = tg_within_bps_limit(tg, bio, bps_limit); + throtl_extend_slice(tg, rw, jiffies + bps_wait); + + return bps_wait; +} + +static unsigned long tg_dispatch_iops_time(struct throtl_grp *tg, struct bio *bio) +{ + bool rw = bio_data_dir(bio); u32 iops_limit = tg_iops_limit(tg, rw); + unsigned long iops_wait; + + if (iops_limit == UINT_MAX || tg->flags & THROTL_TG_CANCELING) + return 0; + + tg_update_slice(tg, rw); + iops_wait = tg_within_iops_limit(tg, bio, iops_limit); + throtl_extend_slice(tg, rw, jiffies + iops_wait); + + return iops_wait; +} + +/* + * Returns approx number of jiffies to wait before this bio is with-in IO rate + * and can be moved to other queue or dispatched. + */ +static unsigned long tg_dispatch_time(struct throtl_grp *tg, struct bio *bio) +{ + bool rw = bio_data_dir(bio); + unsigned long wait; /* * Currently whole state machine of group depends on first bio @@ -912,65 +906,20 @@ static bool tg_may_dispatch(struct throtl_grp *tg, struct bio *bio, * this function with a different bio if there are other bios * queued. */ - BUG_ON(tg->service_queue.nr_queued[rw] && + BUG_ON(sq_queued(&tg->service_queue, rw) && bio != throtl_peek_queued(&tg->service_queue.queued[rw])); - /* If tg->bps = -1, then BW is unlimited */ - if ((bps_limit == U64_MAX && iops_limit == UINT_MAX) || - tg->flags & THROTL_TG_CANCELING) { - if (wait) - *wait = 0; - return true; - } + wait = tg_dispatch_bps_time(tg, bio); + if (wait != 0) + return wait; /* - * If previous slice expired, start a new one otherwise renew/extend - * existing slice to make sure it is at least throtl_slice interval - * long since now. New slice is started only for empty throttle group. - * If there is queued bio, that means there should be an active - * slice and it should be extended instead. + * Charge bps here because @bio will be directly placed into the + * iops queue afterward. */ - if (throtl_slice_used(tg, rw) && !(tg->service_queue.nr_queued[rw])) - throtl_start_new_slice(tg, rw, true); - else { - if (time_before(tg->slice_end[rw], - jiffies + tg->td->throtl_slice)) - throtl_extend_slice(tg, rw, - jiffies + tg->td->throtl_slice); - } + throtl_charge_bps_bio(tg, bio); - bps_wait = tg_within_bps_limit(tg, bio, bps_limit); - iops_wait = tg_within_iops_limit(tg, bio, iops_limit); - if (bps_wait + iops_wait == 0) { - if (wait) - *wait = 0; - return true; - } - - max_wait = max(bps_wait, iops_wait); - - if (wait) - *wait = max_wait; - - if (time_before(tg->slice_end[rw], jiffies + max_wait)) - throtl_extend_slice(tg, rw, jiffies + max_wait); - - return false; -} - -static void throtl_charge_bio(struct throtl_grp *tg, struct bio *bio) -{ - bool rw = bio_data_dir(bio); - unsigned int bio_size = throtl_bio_data_size(bio); - - /* Charge the bio to the group */ - if (!bio_flagged(bio, BIO_BPS_THROTTLED)) { - tg->bytes_disp[rw] += bio_size; - tg->last_bytes_disp[rw] += bio_size; - } - - tg->io_disp[rw]++; - tg->last_io_disp[rw]++; + return tg_dispatch_iops_time(tg, bio); } /** @@ -997,28 +946,36 @@ static void throtl_add_bio_tg(struct bio *bio, struct throtl_qnode *qn, * dispatched. Mark that @tg was empty. This is automatically * cleared on the next tg_update_disptime(). */ - if (!sq->nr_queued[rw]) + if (sq_queued(sq, rw) == 0) tg->flags |= THROTL_TG_WAS_EMPTY; - throtl_qnode_add_bio(bio, qn, &sq->queued[rw]); + throtl_qnode_add_bio(bio, qn, sq); + + /* + * Since we have split the queues, when the iops queue is + * previously empty and a new @bio is added into the first @qn, + * we also need to update the @tg->disptime. + */ + if (bio_flagged(bio, BIO_BPS_THROTTLED) && + bio == throtl_peek_queued(&sq->queued[rw])) + tg->flags |= THROTL_TG_IOPS_WAS_EMPTY; - sq->nr_queued[rw]++; throtl_enqueue_tg(tg); } static void tg_update_disptime(struct throtl_grp *tg) { struct throtl_service_queue *sq = &tg->service_queue; - unsigned long read_wait = -1, write_wait = -1, min_wait = -1, disptime; + unsigned long read_wait = -1, write_wait = -1, min_wait, disptime; struct bio *bio; bio = throtl_peek_queued(&sq->queued[READ]); if (bio) - tg_may_dispatch(tg, bio, &read_wait); + read_wait = tg_dispatch_time(tg, bio); bio = throtl_peek_queued(&sq->queued[WRITE]); if (bio) - tg_may_dispatch(tg, bio, &write_wait); + write_wait = tg_dispatch_time(tg, bio); min_wait = min(read_wait, write_wait); disptime = jiffies + min_wait; @@ -1030,6 +987,7 @@ static void tg_update_disptime(struct throtl_grp *tg) /* see throtl_add_bio_tg() */ tg->flags &= ~THROTL_TG_WAS_EMPTY; + tg->flags &= ~THROTL_TG_IOPS_WAS_EMPTY; } static void start_parent_slice_with_credit(struct throtl_grp *child_tg, @@ -1056,10 +1014,9 @@ static void tg_dispatch_one_bio(struct throtl_grp *tg, bool rw) * getting released prematurely. Remember the tg to put and put it * after @bio is transferred to @parent_sq. */ - bio = throtl_pop_queued(&sq->queued[rw], &tg_to_put); - sq->nr_queued[rw]--; + bio = throtl_pop_queued(sq, &tg_to_put, rw); - throtl_charge_bio(tg, bio); + throtl_charge_iops_bio(tg, bio); /* * If our parent is another tg, we just need to transfer @bio to @@ -1074,7 +1031,7 @@ static void tg_dispatch_one_bio(struct throtl_grp *tg, bool rw) } else { bio_set_flag(bio, BIO_BPS_THROTTLED); throtl_qnode_add_bio(bio, &tg->qnode_on_parent[rw], - &parent_sq->queued[rw]); + parent_sq); BUG_ON(tg->td->nr_queued[rw] <= 0); tg->td->nr_queued[rw]--; } @@ -1096,9 +1053,9 @@ static int throtl_dispatch_tg(struct throtl_grp *tg) /* Try to dispatch 75% READS and 25% WRITES */ while ((bio = throtl_peek_queued(&sq->queued[READ])) && - tg_may_dispatch(tg, bio, NULL)) { + tg_dispatch_time(tg, bio) == 0) { - tg_dispatch_one_bio(tg, bio_data_dir(bio)); + tg_dispatch_one_bio(tg, READ); nr_reads++; if (nr_reads >= max_nr_reads) @@ -1106,9 +1063,9 @@ static int throtl_dispatch_tg(struct throtl_grp *tg) } while ((bio = throtl_peek_queued(&sq->queued[WRITE])) && - tg_may_dispatch(tg, bio, NULL)) { + tg_dispatch_time(tg, bio) == 0) { - tg_dispatch_one_bio(tg, bio_data_dir(bio)); + tg_dispatch_one_bio(tg, WRITE); nr_writes++; if (nr_writes >= max_nr_writes) @@ -1139,7 +1096,7 @@ static int throtl_select_dispatch(struct throtl_service_queue *parent_sq) nr_disp += throtl_dispatch_tg(tg); sq = &tg->service_queue; - if (sq->nr_queued[READ] || sq->nr_queued[WRITE]) + if (sq_queued(sq, READ) || sq_queued(sq, WRITE)) tg_update_disptime(tg); else throtl_dequeue_tg(tg); @@ -1151,8 +1108,6 @@ static int throtl_select_dispatch(struct throtl_service_queue *parent_sq) return nr_disp; } -static bool throtl_can_upgrade(struct throtl_data *td, - struct throtl_grp *this_tg); /** * throtl_pending_timer_fn - timer function for service_queue->pending_timer * @t: the pending_timer member of the throtl_service_queue being serviced @@ -1170,7 +1125,8 @@ static bool throtl_can_upgrade(struct throtl_data *td, */ static void throtl_pending_timer_fn(struct timer_list *t) { - struct throtl_service_queue *sq = from_timer(sq, t, pending_timer); + struct throtl_service_queue *sq = timer_container_of(sq, t, + pending_timer); struct throtl_grp *tg = sq_to_tg(sq); struct throtl_data *td = sq_to_td(sq); struct throtl_service_queue *parent_sq; @@ -1189,17 +1145,16 @@ static void throtl_pending_timer_fn(struct timer_list *t) if (!q->root_blkg) goto out_unlock; - if (throtl_can_upgrade(td, NULL)) - throtl_upgrade_state(td); - again: parent_sq = sq->parent_sq; dispatched = false; while (true) { + unsigned int __maybe_unused bio_cnt_r = sq_queued(sq, READ); + unsigned int __maybe_unused bio_cnt_w = sq_queued(sq, WRITE); + throtl_log(sq, "dispatch nr_queued=%u read=%u write=%u", - sq->nr_queued[READ] + sq->nr_queued[WRITE], - sq->nr_queued[READ], sq->nr_queued[WRITE]); + bio_cnt_r + bio_cnt_w, bio_cnt_r, bio_cnt_w); ret = throtl_select_dispatch(sq); if (ret) { @@ -1221,7 +1176,8 @@ again: if (parent_sq) { /* @parent_sq is another throl_grp, propagate dispatch */ - if (tg->flags & THROTL_TG_WAS_EMPTY) { + if (tg->flags & THROTL_TG_WAS_EMPTY || + tg->flags & THROTL_TG_IOPS_WAS_EMPTY) { tg_update_disptime(tg); if (!throtl_schedule_next_dispatch(parent_sq, false)) { /* window is already open, repeat dispatching */ @@ -1261,7 +1217,7 @@ static void blk_throtl_dispatch_work_fn(struct work_struct *work) spin_lock_irq(&q->queue_lock); for (rw = READ; rw <= WRITE; rw++) - while ((bio = throtl_pop_queued(&td_sq->queued[rw], NULL))) + while ((bio = throtl_pop_queued(td_sq, NULL, rw))) bio_list_add(&bio_list_on_stack, bio); spin_unlock_irq(&q->queue_lock); @@ -1331,22 +1287,12 @@ static void tg_conf_updated(struct throtl_grp *tg, bool global) blkg_for_each_descendant_pre(blkg, pos_css, global ? tg->td->queue->root_blkg : tg_to_blkg(tg)) { struct throtl_grp *this_tg = blkg_to_tg(blkg); - struct throtl_grp *parent_tg; tg_update_has_rules(this_tg); /* ignore root/second level */ if (!cgroup_subsys_on_dfl(io_cgrp_subsys) || !blkg->parent || !blkg->parent->parent) continue; - parent_tg = blkg_to_tg(blkg->parent); - /* - * make sure all children has lower idle time threshold and - * higher latency target - */ - this_tg->idletime_threshold = min(this_tg->idletime_threshold, - parent_tg->idletime_threshold); - this_tg->latency_target = max(this_tg->latency_target, - parent_tg->latency_target); } rcu_read_unlock(); @@ -1367,6 +1313,54 @@ static void tg_conf_updated(struct throtl_grp *tg, bool global) } } +static int blk_throtl_init(struct gendisk *disk) +{ + struct request_queue *q = disk->queue; + struct throtl_data *td; + unsigned int memflags; + int ret; + + td = kzalloc_node(sizeof(*td), GFP_KERNEL, q->node); + if (!td) + return -ENOMEM; + + INIT_WORK(&td->dispatch_work, blk_throtl_dispatch_work_fn); + throtl_service_queue_init(&td->service_queue); + + /* + * Freeze queue before activating policy, to synchronize with IO path, + * which is protected by 'q_usage_counter'. + */ + memflags = blk_mq_freeze_queue(disk->queue); + blk_mq_quiesce_queue(disk->queue); + + q->td = td; + td->queue = q; + + /* activate policy */ + ret = blkcg_activate_policy(disk, &blkcg_policy_throtl); + if (ret) { + q->td = NULL; + kfree(td); + goto out; + } + + if (blk_queue_nonrot(q)) + td->throtl_slice = DFL_THROTL_SLICE_SSD; + else + td->throtl_slice = DFL_THROTL_SLICE_HD; + td->track_bio_latency = !queue_is_mq(q); + if (!td->track_bio_latency) + blk_stat_enable_accounting(q); + +out: + blk_mq_unquiesce_queue(disk->queue); + blk_mq_unfreeze_queue(disk->queue, memflags); + + return ret; +} + + static ssize_t tg_set_conf(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off, bool is_u64) { @@ -1378,6 +1372,16 @@ static ssize_t tg_set_conf(struct kernfs_open_file *of, blkg_conf_init(&ctx, buf); + ret = blkg_conf_open_bdev(&ctx); + if (ret) + goto out_finish; + + if (!blk_throtl_activated(ctx.bdev->bd_queue)) { + ret = blk_throtl_init(ctx.bdev->bd_disk); + if (ret) + goto out_finish; + } + ret = blkg_conf_prep(blkcg, &blkcg_policy_throtl, &ctx); if (ret) goto out_finish; @@ -1444,25 +1448,25 @@ static int tg_print_rwstat_recursive(struct seq_file *sf, void *v) static struct cftype throtl_legacy_files[] = { { .name = "throttle.read_bps_device", - .private = offsetof(struct throtl_grp, bps[READ][LIMIT_MAX]), + .private = offsetof(struct throtl_grp, bps[READ]), .seq_show = tg_print_conf_u64, .write = tg_set_conf_u64, }, { .name = "throttle.write_bps_device", - .private = offsetof(struct throtl_grp, bps[WRITE][LIMIT_MAX]), + .private = offsetof(struct throtl_grp, bps[WRITE]), .seq_show = tg_print_conf_u64, .write = tg_set_conf_u64, }, { .name = "throttle.read_iops_device", - .private = offsetof(struct throtl_grp, iops[READ][LIMIT_MAX]), + .private = offsetof(struct throtl_grp, iops[READ]), .seq_show = tg_print_conf_uint, .write = tg_set_conf_uint, }, { .name = "throttle.write_iops_device", - .private = offsetof(struct throtl_grp, iops[WRITE][LIMIT_MAX]), + .private = offsetof(struct throtl_grp, iops[WRITE]), .seq_show = tg_print_conf_uint, .write = tg_set_conf_uint, }, @@ -1494,61 +1498,43 @@ static u64 tg_prfill_limit(struct seq_file *sf, struct blkg_policy_data *pd, { struct throtl_grp *tg = pd_to_tg(pd); const char *dname = blkg_dev_name(pd->blkg); - char bufs[4][21] = { "max", "max", "max", "max" }; u64 bps_dft; unsigned int iops_dft; - char idle_time[26] = ""; - char latency_time[26] = ""; if (!dname) return 0; - if (off == LIMIT_LOW) { - bps_dft = 0; - iops_dft = 0; - } else { - bps_dft = U64_MAX; - iops_dft = UINT_MAX; - } + bps_dft = U64_MAX; + iops_dft = UINT_MAX; - if (tg->bps_conf[READ][off] == bps_dft && - tg->bps_conf[WRITE][off] == bps_dft && - tg->iops_conf[READ][off] == iops_dft && - tg->iops_conf[WRITE][off] == iops_dft && - (off != LIMIT_LOW || - (tg->idletime_threshold_conf == DFL_IDLE_THRESHOLD && - tg->latency_target_conf == DFL_LATENCY_TARGET))) + if (tg->bps[READ] == bps_dft && + tg->bps[WRITE] == bps_dft && + tg->iops[READ] == iops_dft && + tg->iops[WRITE] == iops_dft) return 0; - if (tg->bps_conf[READ][off] != U64_MAX) - snprintf(bufs[0], sizeof(bufs[0]), "%llu", - tg->bps_conf[READ][off]); - if (tg->bps_conf[WRITE][off] != U64_MAX) - snprintf(bufs[1], sizeof(bufs[1]), "%llu", - tg->bps_conf[WRITE][off]); - if (tg->iops_conf[READ][off] != UINT_MAX) - snprintf(bufs[2], sizeof(bufs[2]), "%u", - tg->iops_conf[READ][off]); - if (tg->iops_conf[WRITE][off] != UINT_MAX) - snprintf(bufs[3], sizeof(bufs[3]), "%u", - tg->iops_conf[WRITE][off]); - if (off == LIMIT_LOW) { - if (tg->idletime_threshold_conf == ULONG_MAX) - strcpy(idle_time, " idle=max"); - else - snprintf(idle_time, sizeof(idle_time), " idle=%lu", - tg->idletime_threshold_conf); + seq_printf(sf, "%s", dname); + if (tg->bps[READ] == U64_MAX) + seq_printf(sf, " rbps=max"); + else + seq_printf(sf, " rbps=%llu", tg->bps[READ]); - if (tg->latency_target_conf == ULONG_MAX) - strcpy(latency_time, " latency=max"); - else - snprintf(latency_time, sizeof(latency_time), - " latency=%lu", tg->latency_target_conf); - } + if (tg->bps[WRITE] == U64_MAX) + seq_printf(sf, " wbps=max"); + else + seq_printf(sf, " wbps=%llu", tg->bps[WRITE]); - seq_printf(sf, "%s rbps=%s wbps=%s riops=%s wiops=%s%s%s\n", - dname, bufs[0], bufs[1], bufs[2], bufs[3], idle_time, - latency_time); + if (tg->iops[READ] == UINT_MAX) + seq_printf(sf, " riops=max"); + else + seq_printf(sf, " riops=%u", tg->iops[READ]); + + if (tg->iops[WRITE] == UINT_MAX) + seq_printf(sf, " wiops=max"); + else + seq_printf(sf, " wiops=%u", tg->iops[WRITE]); + + seq_printf(sf, "\n"); return 0; } @@ -1566,13 +1552,20 @@ static ssize_t tg_set_limit(struct kernfs_open_file *of, struct blkg_conf_ctx ctx; struct throtl_grp *tg; u64 v[4]; - unsigned long idle_time; - unsigned long latency_time; int ret; - int index = of_cft(of)->private; blkg_conf_init(&ctx, buf); + ret = blkg_conf_open_bdev(&ctx); + if (ret) + goto out_finish; + + if (!blk_throtl_activated(ctx.bdev->bd_queue)) { + ret = blk_throtl_init(ctx.bdev->bd_disk); + if (ret) + goto out_finish; + } + ret = blkg_conf_prep(blkcg, &blkcg_policy_throtl, &ctx); if (ret) goto out_finish; @@ -1580,13 +1573,11 @@ static ssize_t tg_set_limit(struct kernfs_open_file *of, tg = blkg_to_tg(ctx.blkg); tg_update_carryover(tg); - v[0] = tg->bps_conf[READ][index]; - v[1] = tg->bps_conf[WRITE][index]; - v[2] = tg->iops_conf[READ][index]; - v[3] = tg->iops_conf[WRITE][index]; + v[0] = tg->bps[READ]; + v[1] = tg->bps[WRITE]; + v[2] = tg->iops[READ]; + v[3] = tg->iops[WRITE]; - idle_time = tg->idletime_threshold_conf; - latency_time = tg->latency_target_conf; while (true) { char tok[27]; /* wiops=18446744073709551616 */ char *p; @@ -1610,68 +1601,24 @@ static ssize_t tg_set_limit(struct kernfs_open_file *of, goto out_finish; ret = -EINVAL; - if (!strcmp(tok, "rbps") && val > 1) + if (!strcmp(tok, "rbps")) v[0] = val; - else if (!strcmp(tok, "wbps") && val > 1) + else if (!strcmp(tok, "wbps")) v[1] = val; - else if (!strcmp(tok, "riops") && val > 1) + else if (!strcmp(tok, "riops")) v[2] = min_t(u64, val, UINT_MAX); - else if (!strcmp(tok, "wiops") && val > 1) + else if (!strcmp(tok, "wiops")) v[3] = min_t(u64, val, UINT_MAX); - else if (off == LIMIT_LOW && !strcmp(tok, "idle")) - idle_time = val; - else if (off == LIMIT_LOW && !strcmp(tok, "latency")) - latency_time = val; else goto out_finish; } - tg->bps_conf[READ][index] = v[0]; - tg->bps_conf[WRITE][index] = v[1]; - tg->iops_conf[READ][index] = v[2]; - tg->iops_conf[WRITE][index] = v[3]; + tg->bps[READ] = v[0]; + tg->bps[WRITE] = v[1]; + tg->iops[READ] = v[2]; + tg->iops[WRITE] = v[3]; - if (index == LIMIT_MAX) { - tg->bps[READ][index] = v[0]; - tg->bps[WRITE][index] = v[1]; - tg->iops[READ][index] = v[2]; - tg->iops[WRITE][index] = v[3]; - } - tg->bps[READ][LIMIT_LOW] = min(tg->bps_conf[READ][LIMIT_LOW], - tg->bps_conf[READ][LIMIT_MAX]); - tg->bps[WRITE][LIMIT_LOW] = min(tg->bps_conf[WRITE][LIMIT_LOW], - tg->bps_conf[WRITE][LIMIT_MAX]); - tg->iops[READ][LIMIT_LOW] = min(tg->iops_conf[READ][LIMIT_LOW], - tg->iops_conf[READ][LIMIT_MAX]); - tg->iops[WRITE][LIMIT_LOW] = min(tg->iops_conf[WRITE][LIMIT_LOW], - tg->iops_conf[WRITE][LIMIT_MAX]); - tg->idletime_threshold_conf = idle_time; - tg->latency_target_conf = latency_time; - - /* force user to configure all settings for low limit */ - if (!(tg->bps[READ][LIMIT_LOW] || tg->iops[READ][LIMIT_LOW] || - tg->bps[WRITE][LIMIT_LOW] || tg->iops[WRITE][LIMIT_LOW]) || - tg->idletime_threshold_conf == DFL_IDLE_THRESHOLD || - tg->latency_target_conf == DFL_LATENCY_TARGET) { - tg->bps[READ][LIMIT_LOW] = 0; - tg->bps[WRITE][LIMIT_LOW] = 0; - tg->iops[READ][LIMIT_LOW] = 0; - tg->iops[WRITE][LIMIT_LOW] = 0; - tg->idletime_threshold = DFL_IDLE_THRESHOLD; - tg->latency_target = DFL_LATENCY_TARGET; - } else if (index == LIMIT_LOW) { - tg->idletime_threshold = tg->idletime_threshold_conf; - tg->latency_target = tg->latency_target_conf; - } - - blk_throtl_update_limit_valid(tg->td); - if (tg->td->limit_valid[LIMIT_LOW]) { - if (index == LIMIT_LOW) - tg->td->limit_index = LIMIT_LOW; - } else - tg->td->limit_index = LIMIT_MAX; - tg_conf_updated(tg, index == LIMIT_LOW && - tg->td->limit_valid[LIMIT_LOW]); + tg_conf_updated(tg, false); ret = 0; out_finish: blkg_conf_exit(&ctx); @@ -1679,21 +1626,11 @@ out_finish: } static struct cftype throtl_files[] = { -#ifdef CONFIG_BLK_DEV_THROTTLING_LOW - { - .name = "low", - .flags = CFTYPE_NOT_ON_ROOT, - .seq_show = tg_print_limit, - .write = tg_set_limit, - .private = LIMIT_LOW, - }, -#endif { .name = "max", .flags = CFTYPE_NOT_ON_ROOT, .seq_show = tg_print_limit, .write = tg_set_limit, - .private = LIMIT_MAX, }, { } /* terminate */ }; @@ -1705,6 +1642,42 @@ static void throtl_shutdown_wq(struct request_queue *q) cancel_work_sync(&td->dispatch_work); } +static void tg_flush_bios(struct throtl_grp *tg) +{ + struct throtl_service_queue *sq = &tg->service_queue; + + if (tg->flags & THROTL_TG_CANCELING) + return; + /* + * Set the flag to make sure throtl_pending_timer_fn() won't + * stop until all throttled bios are dispatched. + */ + tg->flags |= THROTL_TG_CANCELING; + + /* + * Do not dispatch cgroup without THROTL_TG_PENDING or cgroup + * will be inserted to service queue without THROTL_TG_PENDING + * set in tg_update_disptime below. Then IO dispatched from + * child in tg_dispatch_one_bio will trigger double insertion + * and corrupt the tree. + */ + if (!(tg->flags & THROTL_TG_PENDING)) + return; + + /* + * Update disptime after setting the above flag to make sure + * throtl_select_dispatch() won't exit without dispatching. + */ + tg_update_disptime(tg); + + throtl_schedule_pending_timer(sq, jiffies + 1); +} + +static void throtl_pd_offline(struct blkg_policy_data *pd) +{ + tg_flush_bios(pd_to_tg(pd)); +} + struct blkcg_policy blkcg_policy_throtl = { .dfl_cftypes = throtl_files, .legacy_cftypes = throtl_legacy_files, @@ -1722,6 +1695,9 @@ void blk_throtl_cancel_bios(struct gendisk *disk) struct cgroup_subsys_state *pos_css; struct blkcg_gq *blkg; + if (!blk_throtl_activated(q)) + return; + spin_lock_irq(&q->queue_lock); /* * queue_lock is held, rcu lock is not needed here technically. @@ -1730,449 +1706,48 @@ void blk_throtl_cancel_bios(struct gendisk *disk) */ rcu_read_lock(); blkg_for_each_descendant_post(blkg, pos_css, q->root_blkg) { - struct throtl_grp *tg = blkg_to_tg(blkg); - struct throtl_service_queue *sq = &tg->service_queue; - - /* - * Set the flag to make sure throtl_pending_timer_fn() won't - * stop until all throttled bios are dispatched. - */ - tg->flags |= THROTL_TG_CANCELING; - - /* - * Do not dispatch cgroup without THROTL_TG_PENDING or cgroup - * will be inserted to service queue without THROTL_TG_PENDING - * set in tg_update_disptime below. Then IO dispatched from - * child in tg_dispatch_one_bio will trigger double insertion - * and corrupt the tree. - */ - if (!(tg->flags & THROTL_TG_PENDING)) - continue; - /* - * Update disptime after setting the above flag to make sure - * throtl_select_dispatch() won't exit without dispatching. + * disk_release will call pd_offline_fn to cancel bios. + * However, disk_release can't be called if someone get + * the refcount of device and issued bios which are + * inflight after del_gendisk. + * Cancel bios here to ensure no bios are inflight after + * del_gendisk. */ - tg_update_disptime(tg); - - throtl_schedule_pending_timer(sq, jiffies + 1); + tg_flush_bios(blkg_to_tg(blkg)); } rcu_read_unlock(); spin_unlock_irq(&q->queue_lock); } -#ifdef CONFIG_BLK_DEV_THROTTLING_LOW -static unsigned long __tg_last_low_overflow_time(struct throtl_grp *tg) -{ - unsigned long rtime = jiffies, wtime = jiffies; - - if (tg->bps[READ][LIMIT_LOW] || tg->iops[READ][LIMIT_LOW]) - rtime = tg->last_low_overflow_time[READ]; - if (tg->bps[WRITE][LIMIT_LOW] || tg->iops[WRITE][LIMIT_LOW]) - wtime = tg->last_low_overflow_time[WRITE]; - return min(rtime, wtime); -} - -static unsigned long tg_last_low_overflow_time(struct throtl_grp *tg) -{ - struct throtl_service_queue *parent_sq; - struct throtl_grp *parent = tg; - unsigned long ret = __tg_last_low_overflow_time(tg); - - while (true) { - parent_sq = parent->service_queue.parent_sq; - parent = sq_to_tg(parent_sq); - if (!parent) - break; - - /* - * The parent doesn't have low limit, it always reaches low - * limit. Its overflow time is useless for children - */ - if (!parent->bps[READ][LIMIT_LOW] && - !parent->iops[READ][LIMIT_LOW] && - !parent->bps[WRITE][LIMIT_LOW] && - !parent->iops[WRITE][LIMIT_LOW]) - continue; - if (time_after(__tg_last_low_overflow_time(parent), ret)) - ret = __tg_last_low_overflow_time(parent); - } - return ret; -} - -static bool throtl_tg_is_idle(struct throtl_grp *tg) -{ - /* - * cgroup is idle if: - * - single idle is too long, longer than a fixed value (in case user - * configure a too big threshold) or 4 times of idletime threshold - * - average think time is more than threshold - * - IO latency is largely below threshold - */ - unsigned long time; - bool ret; - - time = min_t(unsigned long, MAX_IDLE_TIME, 4 * tg->idletime_threshold); - ret = tg->latency_target == DFL_LATENCY_TARGET || - tg->idletime_threshold == DFL_IDLE_THRESHOLD || - (ktime_get_ns() >> 10) - tg->last_finish_time > time || - tg->avg_idletime > tg->idletime_threshold || - (tg->latency_target && tg->bio_cnt && - tg->bad_bio_cnt * 5 < tg->bio_cnt); - throtl_log(&tg->service_queue, - "avg_idle=%ld, idle_threshold=%ld, bad_bio=%d, total_bio=%d, is_idle=%d, scale=%d", - tg->avg_idletime, tg->idletime_threshold, tg->bad_bio_cnt, - tg->bio_cnt, ret, tg->td->scale); - return ret; -} - -static bool throtl_low_limit_reached(struct throtl_grp *tg, int rw) +static bool tg_within_limit(struct throtl_grp *tg, struct bio *bio, bool rw) { struct throtl_service_queue *sq = &tg->service_queue; - bool limit = tg->bps[rw][LIMIT_LOW] || tg->iops[rw][LIMIT_LOW]; /* - * if low limit is zero, low limit is always reached. - * if low limit is non-zero, we can check if there is any request - * is queued to determine if low limit is reached as we throttle - * request according to limit. + * For a split bio, we need to specifically distinguish whether the + * iops queue is empty. */ - return !limit || sq->nr_queued[rw]; -} + if (bio_flagged(bio, BIO_BPS_THROTTLED)) + return sq->nr_queued_iops[rw] == 0 && + tg_dispatch_iops_time(tg, bio) == 0; -static bool throtl_tg_can_upgrade(struct throtl_grp *tg) -{ /* - * cgroup reaches low limit when low limit of READ and WRITE are - * both reached, it's ok to upgrade to next limit if cgroup reaches - * low limit + * Throtl is FIFO - if bios are already queued, should queue. + * If the bps queue is empty and @bio is within the bps limit, charge + * bps here for direct placement into the iops queue. */ - if (throtl_low_limit_reached(tg, READ) && - throtl_low_limit_reached(tg, WRITE)) - return true; - - if (time_after_eq(jiffies, - tg_last_low_overflow_time(tg) + tg->td->throtl_slice) && - throtl_tg_is_idle(tg)) - return true; - return false; -} + if (sq_queued(&tg->service_queue, rw)) { + if (sq->nr_queued_bps[rw] == 0 && + tg_dispatch_bps_time(tg, bio) == 0) + throtl_charge_bps_bio(tg, bio); -static bool throtl_hierarchy_can_upgrade(struct throtl_grp *tg) -{ - while (true) { - if (throtl_tg_can_upgrade(tg)) - return true; - tg = sq_to_tg(tg->service_queue.parent_sq); - if (!tg || !tg_to_blkg(tg)->parent) - return false; - } - return false; -} - -static bool throtl_can_upgrade(struct throtl_data *td, - struct throtl_grp *this_tg) -{ - struct cgroup_subsys_state *pos_css; - struct blkcg_gq *blkg; - - if (td->limit_index != LIMIT_LOW) - return false; - - if (time_before(jiffies, td->low_downgrade_time + td->throtl_slice)) return false; - - rcu_read_lock(); - blkg_for_each_descendant_post(blkg, pos_css, td->queue->root_blkg) { - struct throtl_grp *tg = blkg_to_tg(blkg); - - if (tg == this_tg) - continue; - if (!list_empty(&tg_to_blkg(tg)->blkcg->css.children)) - continue; - if (!throtl_hierarchy_can_upgrade(tg)) { - rcu_read_unlock(); - return false; - } - } - rcu_read_unlock(); - return true; -} - -static void throtl_upgrade_check(struct throtl_grp *tg) -{ - unsigned long now = jiffies; - - if (tg->td->limit_index != LIMIT_LOW) - return; - - if (time_after(tg->last_check_time + tg->td->throtl_slice, now)) - return; - - tg->last_check_time = now; - - if (!time_after_eq(now, - __tg_last_low_overflow_time(tg) + tg->td->throtl_slice)) - return; - - if (throtl_can_upgrade(tg->td, NULL)) - throtl_upgrade_state(tg->td); -} - -static void throtl_upgrade_state(struct throtl_data *td) -{ - struct cgroup_subsys_state *pos_css; - struct blkcg_gq *blkg; - - throtl_log(&td->service_queue, "upgrade to max"); - td->limit_index = LIMIT_MAX; - td->low_upgrade_time = jiffies; - td->scale = 0; - rcu_read_lock(); - blkg_for_each_descendant_post(blkg, pos_css, td->queue->root_blkg) { - struct throtl_grp *tg = blkg_to_tg(blkg); - struct throtl_service_queue *sq = &tg->service_queue; - - tg->disptime = jiffies - 1; - throtl_select_dispatch(sq); - throtl_schedule_next_dispatch(sq, true); - } - rcu_read_unlock(); - throtl_select_dispatch(&td->service_queue); - throtl_schedule_next_dispatch(&td->service_queue, true); - queue_work(kthrotld_workqueue, &td->dispatch_work); -} - -static void throtl_downgrade_state(struct throtl_data *td) -{ - td->scale /= 2; - - throtl_log(&td->service_queue, "downgrade, scale %d", td->scale); - if (td->scale) { - td->low_upgrade_time = jiffies - td->scale * td->throtl_slice; - return; - } - - td->limit_index = LIMIT_LOW; - td->low_downgrade_time = jiffies; -} - -static bool throtl_tg_can_downgrade(struct throtl_grp *tg) -{ - struct throtl_data *td = tg->td; - unsigned long now = jiffies; - - /* - * If cgroup is below low limit, consider downgrade and throttle other - * cgroups - */ - if (time_after_eq(now, tg_last_low_overflow_time(tg) + - td->throtl_slice) && - (!throtl_tg_is_idle(tg) || - !list_empty(&tg_to_blkg(tg)->blkcg->css.children))) - return true; - return false; -} - -static bool throtl_hierarchy_can_downgrade(struct throtl_grp *tg) -{ - struct throtl_data *td = tg->td; - - if (time_before(jiffies, td->low_upgrade_time + td->throtl_slice)) - return false; - - while (true) { - if (!throtl_tg_can_downgrade(tg)) - return false; - tg = sq_to_tg(tg->service_queue.parent_sq); - if (!tg || !tg_to_blkg(tg)->parent) - break; - } - return true; -} - -static void throtl_downgrade_check(struct throtl_grp *tg) -{ - uint64_t bps; - unsigned int iops; - unsigned long elapsed_time; - unsigned long now = jiffies; - - if (tg->td->limit_index != LIMIT_MAX || - !tg->td->limit_valid[LIMIT_LOW]) - return; - if (!list_empty(&tg_to_blkg(tg)->blkcg->css.children)) - return; - if (time_after(tg->last_check_time + tg->td->throtl_slice, now)) - return; - - elapsed_time = now - tg->last_check_time; - tg->last_check_time = now; - - if (time_before(now, tg_last_low_overflow_time(tg) + - tg->td->throtl_slice)) - return; - - if (tg->bps[READ][LIMIT_LOW]) { - bps = tg->last_bytes_disp[READ] * HZ; - do_div(bps, elapsed_time); - if (bps >= tg->bps[READ][LIMIT_LOW]) - tg->last_low_overflow_time[READ] = now; - } - - if (tg->bps[WRITE][LIMIT_LOW]) { - bps = tg->last_bytes_disp[WRITE] * HZ; - do_div(bps, elapsed_time); - if (bps >= tg->bps[WRITE][LIMIT_LOW]) - tg->last_low_overflow_time[WRITE] = now; - } - - if (tg->iops[READ][LIMIT_LOW]) { - iops = tg->last_io_disp[READ] * HZ / elapsed_time; - if (iops >= tg->iops[READ][LIMIT_LOW]) - tg->last_low_overflow_time[READ] = now; - } - - if (tg->iops[WRITE][LIMIT_LOW]) { - iops = tg->last_io_disp[WRITE] * HZ / elapsed_time; - if (iops >= tg->iops[WRITE][LIMIT_LOW]) - tg->last_low_overflow_time[WRITE] = now; - } - - /* - * If cgroup is below low limit, consider downgrade and throttle other - * cgroups - */ - if (throtl_hierarchy_can_downgrade(tg)) - throtl_downgrade_state(tg->td); - - tg->last_bytes_disp[READ] = 0; - tg->last_bytes_disp[WRITE] = 0; - tg->last_io_disp[READ] = 0; - tg->last_io_disp[WRITE] = 0; -} - -static void blk_throtl_update_idletime(struct throtl_grp *tg) -{ - unsigned long now; - unsigned long last_finish_time = tg->last_finish_time; - - if (last_finish_time == 0) - return; - - now = ktime_get_ns() >> 10; - if (now <= last_finish_time || - last_finish_time == tg->checked_last_finish_time) - return; - - tg->avg_idletime = (tg->avg_idletime * 7 + now - last_finish_time) >> 3; - tg->checked_last_finish_time = last_finish_time; -} - -static void throtl_update_latency_buckets(struct throtl_data *td) -{ - struct avg_latency_bucket avg_latency[2][LATENCY_BUCKET_SIZE]; - int i, cpu, rw; - unsigned long last_latency[2] = { 0 }; - unsigned long latency[2]; - - if (!blk_queue_nonrot(td->queue) || !td->limit_valid[LIMIT_LOW]) - return; - if (time_before(jiffies, td->last_calculate_time + HZ)) - return; - td->last_calculate_time = jiffies; - - memset(avg_latency, 0, sizeof(avg_latency)); - for (rw = READ; rw <= WRITE; rw++) { - for (i = 0; i < LATENCY_BUCKET_SIZE; i++) { - struct latency_bucket *tmp = &td->tmp_buckets[rw][i]; - - for_each_possible_cpu(cpu) { - struct latency_bucket *bucket; - - /* this isn't race free, but ok in practice */ - bucket = per_cpu_ptr(td->latency_buckets[rw], - cpu); - tmp->total_latency += bucket[i].total_latency; - tmp->samples += bucket[i].samples; - bucket[i].total_latency = 0; - bucket[i].samples = 0; - } - - if (tmp->samples >= 32) { - int samples = tmp->samples; - - latency[rw] = tmp->total_latency; - - tmp->total_latency = 0; - tmp->samples = 0; - latency[rw] /= samples; - if (latency[rw] == 0) - continue; - avg_latency[rw][i].latency = latency[rw]; - } - } } - for (rw = READ; rw <= WRITE; rw++) { - for (i = 0; i < LATENCY_BUCKET_SIZE; i++) { - if (!avg_latency[rw][i].latency) { - if (td->avg_buckets[rw][i].latency < last_latency[rw]) - td->avg_buckets[rw][i].latency = - last_latency[rw]; - continue; - } - - if (!td->avg_buckets[rw][i].valid) - latency[rw] = avg_latency[rw][i].latency; - else - latency[rw] = (td->avg_buckets[rw][i].latency * 7 + - avg_latency[rw][i].latency) >> 3; - - td->avg_buckets[rw][i].latency = max(latency[rw], - last_latency[rw]); - td->avg_buckets[rw][i].valid = true; - last_latency[rw] = td->avg_buckets[rw][i].latency; - } - } - - for (i = 0; i < LATENCY_BUCKET_SIZE; i++) - throtl_log(&td->service_queue, - "Latency bucket %d: read latency=%ld, read valid=%d, " - "write latency=%ld, write valid=%d", i, - td->avg_buckets[READ][i].latency, - td->avg_buckets[READ][i].valid, - td->avg_buckets[WRITE][i].latency, - td->avg_buckets[WRITE][i].valid); -} -#else -static inline void throtl_update_latency_buckets(struct throtl_data *td) -{ -} - -static void blk_throtl_update_idletime(struct throtl_grp *tg) -{ + return tg_dispatch_time(tg, bio) == 0; } -static void throtl_downgrade_check(struct throtl_grp *tg) -{ -} - -static void throtl_upgrade_check(struct throtl_grp *tg) -{ -} - -static bool throtl_can_upgrade(struct throtl_data *td, - struct throtl_grp *this_tg) -{ - return false; -} - -static void throtl_upgrade_state(struct throtl_data *td) -{ -} -#endif - bool __blk_throtl_bio(struct bio *bio) { struct request_queue *q = bdev_get_queue(bio->bi_bdev); @@ -2185,51 +1760,42 @@ bool __blk_throtl_bio(struct bio *bio) struct throtl_data *td = tg->td; rcu_read_lock(); - spin_lock_irq(&q->queue_lock); - - throtl_update_latency_buckets(td); - - blk_throtl_update_idletime(tg); - sq = &tg->service_queue; -again: while (true) { - if (tg->last_low_overflow_time[rw] == 0) - tg->last_low_overflow_time[rw] = jiffies; - throtl_downgrade_check(tg); - throtl_upgrade_check(tg); - /* throtl is FIFO - if bios are already queued, should queue */ - if (sq->nr_queued[rw]) - break; - - /* if above limits, break to queue */ - if (!tg_may_dispatch(tg, bio, NULL)) { - tg->last_low_overflow_time[rw] = jiffies; - if (throtl_can_upgrade(td, tg)) { - throtl_upgrade_state(td); - goto again; - } + if (tg_within_limit(tg, bio, rw)) { + /* within limits, let's charge and dispatch directly */ + throtl_charge_iops_bio(tg, bio); + + /* + * We need to trim slice even when bios are not being + * queued otherwise it might happen that a bio is not + * queued for a long time and slice keeps on extending + * and trim is not called for a long time. Now if limits + * are reduced suddenly we take into account all the IO + * dispatched so far at new low rate and * newly queued + * IO gets a really long dispatch time. + * + * So keep on trimming slice even if bio is not queued. + */ + throtl_trim_slice(tg, rw); + } else if (bio_issue_as_root_blkg(bio)) { + /* + * IOs which may cause priority inversions are + * dispatched directly, even if they're over limit. + * + * Charge and dispatch directly, and our throttle + * control algorithm is adaptive, and extra IO bytes + * will be throttled for paying the debt + */ + throtl_charge_bps_bio(tg, bio); + throtl_charge_iops_bio(tg, bio); + } else { + /* if above limits, break to queue */ break; } - /* within limits, let's charge and dispatch directly */ - throtl_charge_bio(tg, bio); - - /* - * We need to trim slice even when bios are not being queued - * otherwise it might happen that a bio is not queued for - * a long time and slice keeps on extending and trim is not - * called for a long time. Now if limits are reduced suddenly - * we take into account all the IO dispatched so far at new - * low rate and * newly queued IO gets a really long dispatch - * time. - * - * So keep on trimming slice even if bio is not queued. - */ - throtl_trim_slice(tg, rw); - /* * @bio passed through this layer without being throttled. * Climb up the ladder. If we're already at the top, it @@ -2250,9 +1816,7 @@ again: tg->bytes_disp[rw], bio->bi_iter.bi_size, tg_bps_limit(tg, rw), tg->io_disp[rw], tg_iops_limit(tg, rw), - sq->nr_queued[READ], sq->nr_queued[WRITE]); - - tg->last_low_overflow_time[rw] = jiffies; + sq_queued(sq, READ), sq_queued(sq, WRITE)); td->nr_queued[rw]++; throtl_add_bio_tg(bio, qn, tg); @@ -2260,225 +1824,37 @@ again: /* * Update @tg's dispatch time and force schedule dispatch if @tg - * was empty before @bio. The forced scheduling isn't likely to - * cause undue delay as @bio is likely to be dispatched directly if - * its @tg's disptime is not in the future. + * was empty before @bio, or the iops queue is empty and @bio will + * add to. The forced scheduling isn't likely to cause undue + * delay as @bio is likely to be dispatched directly if its @tg's + * disptime is not in the future. */ - if (tg->flags & THROTL_TG_WAS_EMPTY) { + if (tg->flags & THROTL_TG_WAS_EMPTY || + tg->flags & THROTL_TG_IOPS_WAS_EMPTY) { tg_update_disptime(tg); throtl_schedule_next_dispatch(tg->service_queue.parent_sq, true); } out_unlock: -#ifdef CONFIG_BLK_DEV_THROTTLING_LOW - if (throttled || !td->track_bio_latency) - bio->bi_issue.value |= BIO_ISSUE_THROTL_SKIP_LATENCY; -#endif spin_unlock_irq(&q->queue_lock); rcu_read_unlock(); return throttled; } -#ifdef CONFIG_BLK_DEV_THROTTLING_LOW -static void throtl_track_latency(struct throtl_data *td, sector_t size, - enum req_op op, unsigned long time) -{ - const bool rw = op_is_write(op); - struct latency_bucket *latency; - int index; - - if (!td || td->limit_index != LIMIT_LOW || - !(op == REQ_OP_READ || op == REQ_OP_WRITE) || - !blk_queue_nonrot(td->queue)) - return; - - index = request_bucket_index(size); - - latency = get_cpu_ptr(td->latency_buckets[rw]); - latency[index].total_latency += time; - latency[index].samples++; - put_cpu_ptr(td->latency_buckets[rw]); -} - -void blk_throtl_stat_add(struct request *rq, u64 time_ns) -{ - struct request_queue *q = rq->q; - struct throtl_data *td = q->td; - - throtl_track_latency(td, blk_rq_stats_sectors(rq), req_op(rq), - time_ns >> 10); -} - -void blk_throtl_bio_endio(struct bio *bio) -{ - struct blkcg_gq *blkg; - struct throtl_grp *tg; - u64 finish_time_ns; - unsigned long finish_time; - unsigned long start_time; - unsigned long lat; - int rw = bio_data_dir(bio); - - blkg = bio->bi_blkg; - if (!blkg) - return; - tg = blkg_to_tg(blkg); - if (!tg->td->limit_valid[LIMIT_LOW]) - return; - - finish_time_ns = ktime_get_ns(); - tg->last_finish_time = finish_time_ns >> 10; - - start_time = bio_issue_time(&bio->bi_issue) >> 10; - finish_time = __bio_issue_time(finish_time_ns) >> 10; - if (!start_time || finish_time <= start_time) - return; - - lat = finish_time - start_time; - /* this is only for bio based driver */ - if (!(bio->bi_issue.value & BIO_ISSUE_THROTL_SKIP_LATENCY)) - throtl_track_latency(tg->td, bio_issue_size(&bio->bi_issue), - bio_op(bio), lat); - - if (tg->latency_target && lat >= tg->td->filtered_latency) { - int bucket; - unsigned int threshold; - - bucket = request_bucket_index(bio_issue_size(&bio->bi_issue)); - threshold = tg->td->avg_buckets[rw][bucket].latency + - tg->latency_target; - if (lat > threshold) - tg->bad_bio_cnt++; - /* - * Not race free, could get wrong count, which means cgroups - * will be throttled - */ - tg->bio_cnt++; - } - - if (time_after(jiffies, tg->bio_cnt_reset_time) || tg->bio_cnt > 1024) { - tg->bio_cnt_reset_time = tg->td->throtl_slice + jiffies; - tg->bio_cnt /= 2; - tg->bad_bio_cnt /= 2; - } -} -#endif - -int blk_throtl_init(struct gendisk *disk) -{ - struct request_queue *q = disk->queue; - struct throtl_data *td; - int ret; - - td = kzalloc_node(sizeof(*td), GFP_KERNEL, q->node); - if (!td) - return -ENOMEM; - td->latency_buckets[READ] = __alloc_percpu(sizeof(struct latency_bucket) * - LATENCY_BUCKET_SIZE, __alignof__(u64)); - if (!td->latency_buckets[READ]) { - kfree(td); - return -ENOMEM; - } - td->latency_buckets[WRITE] = __alloc_percpu(sizeof(struct latency_bucket) * - LATENCY_BUCKET_SIZE, __alignof__(u64)); - if (!td->latency_buckets[WRITE]) { - free_percpu(td->latency_buckets[READ]); - kfree(td); - return -ENOMEM; - } - - INIT_WORK(&td->dispatch_work, blk_throtl_dispatch_work_fn); - throtl_service_queue_init(&td->service_queue); - - q->td = td; - td->queue = q; - - td->limit_valid[LIMIT_MAX] = true; - td->limit_index = LIMIT_MAX; - td->low_upgrade_time = jiffies; - td->low_downgrade_time = jiffies; - - /* activate policy */ - ret = blkcg_activate_policy(disk, &blkcg_policy_throtl); - if (ret) { - free_percpu(td->latency_buckets[READ]); - free_percpu(td->latency_buckets[WRITE]); - kfree(td); - } - return ret; -} - void blk_throtl_exit(struct gendisk *disk) { struct request_queue *q = disk->queue; - BUG_ON(!q->td); - del_timer_sync(&q->td->service_queue.pending_timer); + if (!blk_throtl_activated(q)) + return; + + timer_delete_sync(&q->td->service_queue.pending_timer); throtl_shutdown_wq(q); blkcg_deactivate_policy(disk, &blkcg_policy_throtl); - free_percpu(q->td->latency_buckets[READ]); - free_percpu(q->td->latency_buckets[WRITE]); kfree(q->td); } -void blk_throtl_register(struct gendisk *disk) -{ - struct request_queue *q = disk->queue; - struct throtl_data *td; - int i; - - td = q->td; - BUG_ON(!td); - - if (blk_queue_nonrot(q)) { - td->throtl_slice = DFL_THROTL_SLICE_SSD; - td->filtered_latency = LATENCY_FILTERED_SSD; - } else { - td->throtl_slice = DFL_THROTL_SLICE_HD; - td->filtered_latency = LATENCY_FILTERED_HD; - for (i = 0; i < LATENCY_BUCKET_SIZE; i++) { - td->avg_buckets[READ][i].latency = DFL_HD_BASELINE_LATENCY; - td->avg_buckets[WRITE][i].latency = DFL_HD_BASELINE_LATENCY; - } - } -#ifndef CONFIG_BLK_DEV_THROTTLING_LOW - /* if no low limit, use previous default */ - td->throtl_slice = DFL_THROTL_SLICE_HD; - -#else - td->track_bio_latency = !queue_is_mq(q); - if (!td->track_bio_latency) - blk_stat_enable_accounting(q); -#endif -} - -#ifdef CONFIG_BLK_DEV_THROTTLING_LOW -ssize_t blk_throtl_sample_time_show(struct request_queue *q, char *page) -{ - if (!q->td) - return -EINVAL; - return sprintf(page, "%u\n", jiffies_to_msecs(q->td->throtl_slice)); -} - -ssize_t blk_throtl_sample_time_store(struct request_queue *q, - const char *page, size_t count) -{ - unsigned long v; - unsigned long t; - - if (!q->td) - return -EINVAL; - if (kstrtoul(page, 10, &v)) - return -EINVAL; - t = msecs_to_jiffies(v); - if (t == 0 || t > MAX_THROTL_SLICE) - return -EINVAL; - q->td->throtl_slice = t; - return count; -} -#endif - static int __init throtl_init(void) { kthrotld_workqueue = alloc_workqueue("kthrotld", WQ_MEM_RECLAIM, 0); |