diff options
-rw-r--r-- | block/bfq-cgroup.c | 91 | ||||
-rw-r--r-- | block/bfq-iosched.c | 160 | ||||
-rw-r--r-- | block/bfq-iosched.h | 51 |
3 files changed, 195 insertions, 107 deletions
diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c index 7d9b15f0dbd5..5f081f4d51fb 100644 --- a/block/bfq-cgroup.c +++ b/block/bfq-cgroup.c @@ -712,6 +712,46 @@ void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq, bfq_put_queue(bfqq); } +static void bfq_sync_bfqq_move(struct bfq_data *bfqd, + struct bfq_queue *sync_bfqq, + struct bfq_io_cq *bic, + struct bfq_group *bfqg, + unsigned int act_idx) +{ + struct bfq_queue *bfqq; + + if (!sync_bfqq->new_bfqq && !bfq_bfqq_coop(sync_bfqq)) { + /* We are the only user of this bfqq, just move it */ + if (sync_bfqq->entity.sched_data != &bfqg->sched_data) + bfq_bfqq_move(bfqd, sync_bfqq, bfqg); + return; + } + + /* + * The queue was merged to a different queue. Check + * that the merge chain still belongs to the same + * cgroup. + */ + for (bfqq = sync_bfqq; bfqq; bfqq = bfqq->new_bfqq) + if (bfqq->entity.sched_data != &bfqg->sched_data) + break; + if (bfqq) { + /* + * Some queue changed cgroup so the merge is not valid + * anymore. We cannot easily just cancel the merge (by + * clearing new_bfqq) as there may be other processes + * using this queue and holding refs to all queues + * below sync_bfqq->new_bfqq. Similarly if the merge + * already happened, we need to detach from bfqq now + * so that we cannot merge bio to a request from the + * old cgroup. + */ + bfq_put_cooperator(sync_bfqq); + bfq_release_process_ref(bfqd, sync_bfqq); + bic_set_bfqq(bic, NULL, true, act_idx); + } +} + /** * __bfq_bic_change_cgroup - move @bic to @bfqg. * @bfqd: the queue descriptor. @@ -726,53 +766,20 @@ static void __bfq_bic_change_cgroup(struct bfq_data *bfqd, struct bfq_io_cq *bic, struct bfq_group *bfqg) { - struct bfq_queue *async_bfqq = bic_to_bfqq(bic, false); - struct bfq_queue *sync_bfqq = bic_to_bfqq(bic, true); - struct bfq_entity *entity; + unsigned int act_idx; - if (async_bfqq) { - entity = &async_bfqq->entity; + for (act_idx = 0; act_idx < bfqd->num_actuators; act_idx++) { + struct bfq_queue *async_bfqq = bic_to_bfqq(bic, false, act_idx); + struct bfq_queue *sync_bfqq = bic_to_bfqq(bic, true, act_idx); - if (entity->sched_data != &bfqg->sched_data) { - bic_set_bfqq(bic, NULL, false); + if (async_bfqq && + async_bfqq->entity.sched_data != &bfqg->sched_data) { + bic_set_bfqq(bic, NULL, false, act_idx); bfq_release_process_ref(bfqd, async_bfqq); } - } - if (sync_bfqq) { - if (!sync_bfqq->new_bfqq && !bfq_bfqq_coop(sync_bfqq)) { - /* We are the only user of this bfqq, just move it */ - if (sync_bfqq->entity.sched_data != &bfqg->sched_data) - bfq_bfqq_move(bfqd, sync_bfqq, bfqg); - } else { - struct bfq_queue *bfqq; - - /* - * The queue was merged to a different queue. Check - * that the merge chain still belongs to the same - * cgroup. - */ - for (bfqq = sync_bfqq; bfqq; bfqq = bfqq->new_bfqq) - if (bfqq->entity.sched_data != - &bfqg->sched_data) - break; - if (bfqq) { - /* - * Some queue changed cgroup so the merge is - * not valid anymore. We cannot easily just - * cancel the merge (by clearing new_bfqq) as - * there may be other processes using this - * queue and holding refs to all queues below - * sync_bfqq->new_bfqq. Similarly if the merge - * already happened, we need to detach from - * bfqq now so that we cannot merge bio to a - * request from the old cgroup. - */ - bfq_put_cooperator(sync_bfqq); - bfq_release_process_ref(bfqd, sync_bfqq); - bic_set_bfqq(bic, NULL, true); - } - } + if (sync_bfqq) + bfq_sync_bfqq_move(bfqd, sync_bfqq, bic, bfqg, act_idx); } } diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index ccf2204477a5..597f5a109092 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -377,16 +377,23 @@ static const unsigned long bfq_late_stable_merging = 600; #define RQ_BIC(rq) ((struct bfq_io_cq *)((rq)->elv.priv[0])) #define RQ_BFQQ(rq) ((rq)->elv.priv[1]) -struct bfq_queue *bic_to_bfqq(struct bfq_io_cq *bic, bool is_sync) +struct bfq_queue *bic_to_bfqq(struct bfq_io_cq *bic, bool is_sync, + unsigned int actuator_idx) { - return bic->bfqq[is_sync]; + if (is_sync) + return bic->bfqq[1][actuator_idx]; + + return bic->bfqq[0][actuator_idx]; } static void bfq_put_stable_ref(struct bfq_queue *bfqq); -void bic_set_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq, bool is_sync) +void bic_set_bfqq(struct bfq_io_cq *bic, + struct bfq_queue *bfqq, + bool is_sync, + unsigned int actuator_idx) { - struct bfq_queue *old_bfqq = bic->bfqq[is_sync]; + struct bfq_queue *old_bfqq = bic->bfqq[is_sync][actuator_idx]; /* Clear bic pointer if bfqq is detached from this bic */ if (old_bfqq && old_bfqq->bic == bic) @@ -405,7 +412,10 @@ void bic_set_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq, bool is_sync) * we cancel the stable merge if * bic->stable_merge_bfqq == bfqq. */ - bic->bfqq[is_sync] = bfqq; + if (is_sync) + bic->bfqq[1][actuator_idx] = bfqq; + else + bic->bfqq[0][actuator_idx] = bfqq; if (bfqq && bic->stable_merge_bfqq == bfqq) { /* @@ -678,9 +688,9 @@ static void bfq_limit_depth(blk_opf_t opf, struct blk_mq_alloc_data *data) { struct bfq_data *bfqd = data->q->elevator->elevator_data; struct bfq_io_cq *bic = bfq_bic_lookup(data->q); - struct bfq_queue *bfqq = bic ? bic_to_bfqq(bic, op_is_sync(opf)) : NULL; int depth; unsigned limit = data->q->nr_requests; + unsigned int act_idx; /* Sync reads have full depth available */ if (op_is_sync(opf) && !op_is_write(opf)) { @@ -690,14 +700,21 @@ static void bfq_limit_depth(blk_opf_t opf, struct blk_mq_alloc_data *data) limit = (limit * depth) >> bfqd->full_depth_shift; } - /* - * Does queue (or any parent entity) exceed number of requests that - * should be available to it? Heavily limit depth so that it cannot - * consume more available requests and thus starve other entities. - */ - if (bfqq && bfqq_request_over_limit(bfqq, limit)) - depth = 1; + for (act_idx = 0; bic && act_idx < bfqd->num_actuators; act_idx++) { + struct bfq_queue *bfqq = + bic_to_bfqq(bic, op_is_sync(opf), act_idx); + /* + * Does queue (or any parent entity) exceed number of + * requests that should be available to it? Heavily + * limit depth so that it cannot consume more + * available requests and thus starve other entities. + */ + if (bfqq && bfqq_request_over_limit(bfqq, limit)) { + depth = 1; + break; + } + } bfq_log(bfqd, "[%s] wr_busy %d sync %d depth %u", __func__, bfqd->wr_busy_queues, op_is_sync(opf), depth); if (depth) @@ -1766,6 +1783,18 @@ static bool bfq_bfqq_higher_class_or_weight(struct bfq_queue *bfqq, return bfqq_weight > in_serv_weight; } +/* + * Get the index of the actuator that will serve bio. + */ +static unsigned int bfq_actuator_index(struct bfq_data *bfqd, struct bio *bio) +{ + /* + * Multi-actuator support not complete yet, so always return 0 + * for the moment (to keep incomplete mechanisms off). + */ + return 0; +} + static bool bfq_better_to_idle(struct bfq_queue *bfqq); static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd, @@ -2098,7 +2127,7 @@ static void bfq_check_waker(struct bfq_data *bfqd, struct bfq_queue *bfqq, * We reset waker detection logic also if too much time has passed * since the first detection. If wakeups are rare, pointless idling * doesn't hurt throughput that much. The condition below makes sure - * we do not uselessly idle blocking waker in more than 1/64 cases. + * we do not uselessly idle blocking waker in more than 1/64 cases. */ if (bfqd->last_completed_rq_bfqq != bfqq->tentative_waker_bfqq || @@ -2418,7 +2447,8 @@ static bool bfq_bio_merge(struct request_queue *q, struct bio *bio, */ bfq_bic_update_cgroup(bic, bio); - bfqd->bio_bfqq = bic_to_bfqq(bic, op_is_sync(bio->bi_opf)); + bfqd->bio_bfqq = bic_to_bfqq(bic, op_is_sync(bio->bi_opf), + bfq_actuator_index(bfqd, bio)); } else { bfqd->bio_bfqq = NULL; } @@ -3114,7 +3144,7 @@ bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic, /* * Merge queues (that is, let bic redirect its requests to new_bfqq) */ - bic_set_bfqq(bic, new_bfqq, true); + bic_set_bfqq(bic, new_bfqq, true, bfqq->actuator_idx); bfq_mark_bfqq_coop(new_bfqq); /* * new_bfqq now belongs to at least two bics (it is a shared queue): @@ -4748,11 +4778,8 @@ check_queue: */ if (bfq_bfqq_wait_request(bfqq) || (bfqq->dispatched != 0 && bfq_better_to_idle(bfqq))) { - struct bfq_queue *async_bfqq = - bfqq->bic && bfqq->bic->bfqq[0] && - bfq_bfqq_busy(bfqq->bic->bfqq[0]) && - bfqq->bic->bfqq[0]->next_rq ? - bfqq->bic->bfqq[0] : NULL; + unsigned int act_idx = bfqq->actuator_idx; + struct bfq_queue *async_bfqq = NULL; struct bfq_queue *blocked_bfqq = !hlist_empty(&bfqq->woken_list) ? container_of(bfqq->woken_list.first, @@ -4760,6 +4787,10 @@ check_queue: woken_list_node) : NULL; + if (bfqq->bic && bfqq->bic->bfqq[0][act_idx] && + bfq_bfqq_busy(bfqq->bic->bfqq[0][act_idx]) && + bfqq->bic->bfqq[0][act_idx]->next_rq) + async_bfqq = bfqq->bic->bfqq[0][act_idx]; /* * The next four mutually-exclusive ifs decide * whether to try injection, and choose the queue to @@ -4844,7 +4875,7 @@ check_queue: icq_to_bic(async_bfqq->next_rq->elv.icq) == bfqq->bic && bfq_serv_to_charge(async_bfqq->next_rq, async_bfqq) <= bfq_bfqq_budget_left(async_bfqq)) - bfqq = bfqq->bic->bfqq[0]; + bfqq = bfqq->bic->bfqq[0][act_idx]; else if (bfqq->waker_bfqq && bfq_bfqq_busy(bfqq->waker_bfqq) && bfqq->waker_bfqq->next_rq && @@ -5305,48 +5336,54 @@ static void bfq_exit_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq) bfq_release_process_ref(bfqd, bfqq); } -static void bfq_exit_icq_bfqq(struct bfq_io_cq *bic, bool is_sync) +static void bfq_exit_icq_bfqq(struct bfq_io_cq *bic, bool is_sync, + unsigned int actuator_idx) { - struct bfq_queue *bfqq = bic_to_bfqq(bic, is_sync); + struct bfq_queue *bfqq = bic_to_bfqq(bic, is_sync, actuator_idx); struct bfq_data *bfqd; if (bfqq) bfqd = bfqq->bfqd; /* NULL if scheduler already exited */ if (bfqq && bfqd) { - unsigned long flags; - - spin_lock_irqsave(&bfqd->lock, flags); - bic_set_bfqq(bic, NULL, is_sync); + bic_set_bfqq(bic, NULL, is_sync, actuator_idx); bfq_exit_bfqq(bfqd, bfqq); - spin_unlock_irqrestore(&bfqd->lock, flags); } } static void bfq_exit_icq(struct io_cq *icq) { struct bfq_io_cq *bic = icq_to_bic(icq); + struct bfq_data *bfqd = bic_to_bfqd(bic); + unsigned long flags; + unsigned int act_idx; + /* + * If bfqd and thus bfqd->num_actuators is not available any + * longer, then cycle over all possible per-actuator bfqqs in + * next loop. We rely on bic being zeroed on creation, and + * therefore on its unused per-actuator fields being NULL. + */ + unsigned int num_actuators = BFQ_MAX_ACTUATORS; - if (bic->stable_merge_bfqq) { - struct bfq_data *bfqd = bic->stable_merge_bfqq->bfqd; + /* + * bfqd is NULL if scheduler already exited, and in that case + * this is the last time these queues are accessed. + */ + if (bfqd) { + spin_lock_irqsave(&bfqd->lock, flags); + num_actuators = bfqd->num_actuators; + } - /* - * bfqd is NULL if scheduler already exited, and in - * that case this is the last time bfqq is accessed. - */ - if (bfqd) { - unsigned long flags; + if (bic->stable_merge_bfqq) + bfq_put_stable_ref(bic->stable_merge_bfqq); - spin_lock_irqsave(&bfqd->lock, flags); - bfq_put_stable_ref(bic->stable_merge_bfqq); - spin_unlock_irqrestore(&bfqd->lock, flags); - } else { - bfq_put_stable_ref(bic->stable_merge_bfqq); - } + for (act_idx = 0; act_idx < num_actuators; act_idx++) { + bfq_exit_icq_bfqq(bic, true, act_idx); + bfq_exit_icq_bfqq(bic, false, act_idx); } - bfq_exit_icq_bfqq(bic, true); - bfq_exit_icq_bfqq(bic, false); + if (bfqd) + spin_unlock_irqrestore(&bfqd->lock, flags); } /* @@ -5423,23 +5460,25 @@ static void bfq_check_ioprio_change(struct bfq_io_cq *bic, struct bio *bio) bic->ioprio = ioprio; - bfqq = bic_to_bfqq(bic, false); + bfqq = bic_to_bfqq(bic, false, bfq_actuator_index(bfqd, bio)); if (bfqq) { bfq_release_process_ref(bfqd, bfqq); bfqq = bfq_get_queue(bfqd, bio, false, bic, true); - bic_set_bfqq(bic, bfqq, false); + bic_set_bfqq(bic, bfqq, false, bfq_actuator_index(bfqd, bio)); } - bfqq = bic_to_bfqq(bic, true); + bfqq = bic_to_bfqq(bic, true, bfq_actuator_index(bfqd, bio)); if (bfqq) bfq_set_next_ioprio_data(bfqq, bic); } static void bfq_init_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq, - struct bfq_io_cq *bic, pid_t pid, int is_sync) + struct bfq_io_cq *bic, pid_t pid, int is_sync, + unsigned int act_idx) { u64 now_ns = ktime_get_ns(); + bfqq->actuator_idx = act_idx; RB_CLEAR_NODE(&bfqq->entity.rb_node); INIT_LIST_HEAD(&bfqq->fifo); INIT_HLIST_NODE(&bfqq->burst_list_node); @@ -5692,7 +5731,7 @@ static struct bfq_queue *bfq_get_queue(struct bfq_data *bfqd, if (bfqq) { bfq_init_bfqq(bfqd, bfqq, bic, current->pid, - is_sync); + is_sync, bfq_actuator_index(bfqd, bio)); bfq_init_entity(&bfqq->entity, bfqg); bfq_log_bfqq(bfqd, bfqq, "allocated"); } else { @@ -6007,7 +6046,8 @@ static bool __bfq_insert_request(struct bfq_data *bfqd, struct request *rq) * then complete the merge and redirect it to * new_bfqq. */ - if (bic_to_bfqq(RQ_BIC(rq), 1) == bfqq) + if (bic_to_bfqq(RQ_BIC(rq), true, + bfq_actuator_index(bfqd, rq->bio)) == bfqq) bfq_merge_bfqqs(bfqd, RQ_BIC(rq), bfqq, new_bfqq); @@ -6562,7 +6602,7 @@ bfq_split_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq) return bfqq; } - bic_set_bfqq(bic, NULL, true); + bic_set_bfqq(bic, NULL, true, bfqq->actuator_idx); bfq_put_cooperator(bfqq); @@ -6576,7 +6616,8 @@ static struct bfq_queue *bfq_get_bfqq_handle_split(struct bfq_data *bfqd, bool split, bool is_sync, bool *new_queue) { - struct bfq_queue *bfqq = bic_to_bfqq(bic, is_sync); + unsigned int act_idx = bfq_actuator_index(bfqd, bio); + struct bfq_queue *bfqq = bic_to_bfqq(bic, is_sync, act_idx); if (likely(bfqq && bfqq != &bfqd->oom_bfqq)) return bfqq; @@ -6588,7 +6629,7 @@ static struct bfq_queue *bfq_get_bfqq_handle_split(struct bfq_data *bfqd, bfq_put_queue(bfqq); bfqq = bfq_get_queue(bfqd, bio, is_sync, bic, split); - bic_set_bfqq(bic, bfqq, is_sync); + bic_set_bfqq(bic, bfqq, is_sync, act_idx); if (split && is_sync) { if ((bic->was_in_burst_list && bfqd->large_burst) || bic->saved_in_large_burst) @@ -7036,8 +7077,10 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e) * Our fallback bfqq if bfq_find_alloc_queue() runs into OOM issues. * Grab a permanent reference to it, so that the normal code flow * will not attempt to free it. + * Set zero as actuator index: we will pretend that + * all I/O requests are for the same actuator. */ - bfq_init_bfqq(bfqd, &bfqd->oom_bfqq, NULL, 1, 0); + bfq_init_bfqq(bfqd, &bfqd->oom_bfqq, NULL, 1, 0, 0); bfqd->oom_bfqq.ref++; bfqd->oom_bfqq.new_ioprio = BFQ_DEFAULT_QUEUE_IOPRIO; bfqd->oom_bfqq.new_ioprio_class = IOPRIO_CLASS_BE; @@ -7056,6 +7099,13 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e) bfqd->queue = q; + /* + * Multi-actuator support not complete yet, unconditionally + * set to only one actuator for the moment (to keep incomplete + * mechanisms off). + */ + bfqd->num_actuators = 1; + INIT_LIST_HEAD(&bfqd->dispatch); hrtimer_init(&bfqd->idle_slice_timer, CLOCK_MONOTONIC, diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h index 466e4865ace6..645bc0138a16 100644 --- a/block/bfq-iosched.h +++ b/block/bfq-iosched.h @@ -33,6 +33,14 @@ */ #define BFQ_SOFTRT_WEIGHT_FACTOR 100 +/* + * Maximum number of actuators supported. This constant is used simply + * to define the size of the static array that will contain + * per-actuator data. The current value is hopefully a good upper + * bound to the possible number of actuators of any actual drive. + */ +#define BFQ_MAX_ACTUATORS 8 + struct bfq_entity; /** @@ -227,12 +235,14 @@ struct bfq_ttime { * struct bfq_queue - leaf schedulable entity. * * A bfq_queue is a leaf request queue; it can be associated with an - * io_context or more, if it is async or shared between cooperating - * processes. @cgroup holds a reference to the cgroup, to be sure that it - * does not disappear while a bfqq still references it (mostly to avoid - * races between request issuing and task migration followed by cgroup - * destruction). - * All the fields are protected by the queue lock of the containing bfqd. + * io_context or more, if it is async or shared between cooperating + * processes. Besides, it contains I/O requests for only one actuator + * (an io_context is associated with a different bfq_queue for each + * actuator it generates I/O for). @cgroup holds a reference to the + * cgroup, to be sure that it does not disappear while a bfqq still + * references it (mostly to avoid races between request issuing and + * task migration followed by cgroup destruction). All the fields are + * protected by the queue lock of the containing bfqd. */ struct bfq_queue { /* reference counter */ @@ -397,6 +407,9 @@ struct bfq_queue { * the woken queues when this queue exits. */ struct hlist_head woken_list; + + /* index of the actuator this queue is associated with */ + unsigned int actuator_idx; }; /** @@ -405,8 +418,17 @@ struct bfq_queue { struct bfq_io_cq { /* associated io_cq structure */ struct io_cq icq; /* must be the first member */ - /* array of two process queues, the sync and the async */ - struct bfq_queue *bfqq[2]; + /* + * Matrix of associated process queues: first row for async + * queues, second row sync queues. Each row contains one + * column for each actuator. An I/O request generated by the + * process is inserted into the queue pointed by bfqq[i][j] if + * the request is to be served by the j-th actuator of the + * drive, where i==0 or i==1, depending on whether the request + * is async or sync. So there is a distinct queue for each + * actuator. + */ + struct bfq_queue *bfqq[2][BFQ_MAX_ACTUATORS]; /* per (request_queue, blkcg) ioprio */ int ioprio; #ifdef CONFIG_BFQ_GROUP_IOSCHED @@ -772,6 +794,13 @@ struct bfq_data { */ unsigned int word_depths[2][2]; unsigned int full_depth_shift; + + /* + * Number of independent actuators. This is equal to 1 in + * case of single-actuator drives. + */ + unsigned int num_actuators; + }; enum bfqq_state_flags { @@ -969,8 +998,10 @@ struct bfq_group { extern const int bfq_timeout; -struct bfq_queue *bic_to_bfqq(struct bfq_io_cq *bic, bool is_sync); -void bic_set_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq, bool is_sync); +struct bfq_queue *bic_to_bfqq(struct bfq_io_cq *bic, bool is_sync, + unsigned int actuator_idx); +void bic_set_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq, bool is_sync, + unsigned int actuator_idx); struct bfq_data *bic_to_bfqd(struct bfq_io_cq *bic); void bfq_pos_tree_add_move(struct bfq_data *bfqd, struct bfq_queue *bfqq); void bfq_weights_tree_add(struct bfq_queue *bfqq); |