From 957b7799fa08de8a84561c7c3299c05b695bb19d Mon Sep 17 00:00:00 2001 From: Mauro Andreolini Date: Fri, 5 Jun 2015 17:45:40 +0200 Subject: [PATCH 3/3] block, bfq: add Early Queue Merge (EQM) to BFQ-v7r8 for 3.18.0 A set of processes may happen to perform interleaved reads, i.e.,requests whose union would give rise to a sequential read pattern. There are two typical cases: in the first case, processes read fixed-size chunks of data at a fixed distance from each other, while in the second case processes may read variable-size chunks at variable distances. The latter case occurs for example with QEMU, which splits the I/O generated by the guest into multiple chunks, and lets these chunks be served by a pool of cooperating processes, iteratively assigning the next chunk of I/O to the first available process. CFQ uses actual queue merging for the first type of rocesses, whereas it uses preemption to get a sequential read pattern out of the read requests performed by the second type of processes. In the end it uses two different mechanisms to achieve the same goal: boosting the throughput with interleaved I/O. This patch introduces Early Queue Merge (EQM), a unified mechanism to get a sequential read pattern with both types of processes. The main idea is checking newly arrived requests against the next request of the active queue both in case of actual request insert and in case of request merge. By doing so, both the types of processes can be handled by just merging their queues. EQM is then simpler and more compact than the pair of mechanisms used in CFQ. Finally, EQM also preserves the typical low-latency properties of BFQ, by properly restoring the weight-raising state of a queue when it gets back to a non-merged state. Signed-off-by: Mauro Andreolini Signed-off-by: Arianna Avanzini Signed-off-by: Paolo Valente --- block/bfq-iosched.c | 750 +++++++++++++++++++++++++++++++++++++--------------- block/bfq-sched.c | 28 -- block/bfq.h | 54 +++- 3 files changed, 580 insertions(+), 252 deletions(-) diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 773b2ee..71b51c1 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -573,6 +573,57 @@ static inline unsigned int bfq_wr_duration(struct bfq_data *bfqd) return dur; } +static inline unsigned +bfq_bfqq_cooperations(struct bfq_queue *bfqq) +{ + return bfqq->bic ? bfqq->bic->cooperations : 0; +} + +static inline void +bfq_bfqq_resume_state(struct bfq_queue *bfqq, struct bfq_io_cq *bic) +{ + if (bic->saved_idle_window) + bfq_mark_bfqq_idle_window(bfqq); + else + bfq_clear_bfqq_idle_window(bfqq); + if (bic->saved_IO_bound) + bfq_mark_bfqq_IO_bound(bfqq); + else + bfq_clear_bfqq_IO_bound(bfqq); + /* Assuming that the flag in_large_burst is already correctly set */ + if (bic->wr_time_left && bfqq->bfqd->low_latency && + !bfq_bfqq_in_large_burst(bfqq) && + bic->cooperations < bfqq->bfqd->bfq_coop_thresh) { + /* + * Start a weight raising period with the duration given by + * the raising_time_left snapshot. + */ + if (bfq_bfqq_busy(bfqq)) + bfqq->bfqd->wr_busy_queues++; + bfqq->wr_coeff = bfqq->bfqd->bfq_wr_coeff; + bfqq->wr_cur_max_time = bic->wr_time_left; + bfqq->last_wr_start_finish = jiffies; + bfqq->entity.ioprio_changed = 1; + } + /* + * Clear wr_time_left to prevent bfq_bfqq_save_state() from + * getting confused about the queue's need of a weight-raising + * period. + */ + bic->wr_time_left = 0; +} + +/* Must be called with the queue_lock held. */ +static int bfqq_process_refs(struct bfq_queue *bfqq) +{ + int process_refs, io_refs; + + io_refs = bfqq->allocated[READ] + bfqq->allocated[WRITE]; + process_refs = atomic_read(&bfqq->ref) - io_refs - bfqq->entity.on_st; + BUG_ON(process_refs < 0); + return process_refs; +} + /* Empty burst list and add just bfqq (see comments to bfq_handle_burst) */ static inline void bfq_reset_burst_list(struct bfq_data *bfqd, struct bfq_queue *bfqq) @@ -817,7 +868,7 @@ static void bfq_add_request(struct request *rq) bfq_rq_pos_tree_add(bfqd, bfqq); if (!bfq_bfqq_busy(bfqq)) { - bool soft_rt, + bool soft_rt, coop_or_in_burst, idle_for_long_time = time_is_before_jiffies( bfqq->budget_timeout + bfqd->bfq_wr_min_idle_time); @@ -841,11 +892,12 @@ static void bfq_add_request(struct request *rq) bfqd->last_ins_in_burst = jiffies; } + coop_or_in_burst = bfq_bfqq_in_large_burst(bfqq) || + bfq_bfqq_cooperations(bfqq) >= bfqd->bfq_coop_thresh; soft_rt = bfqd->bfq_wr_max_softrt_rate > 0 && - !bfq_bfqq_in_large_burst(bfqq) && + !coop_or_in_burst && time_is_before_jiffies(bfqq->soft_rt_next_start); - interactive = !bfq_bfqq_in_large_burst(bfqq) && - idle_for_long_time; + interactive = !coop_or_in_burst && idle_for_long_time; entity->budget = max_t(unsigned long, bfqq->max_budget, bfq_serv_to_charge(next_rq, bfqq)); @@ -864,11 +916,20 @@ static void bfq_add_request(struct request *rq) if (!bfqd->low_latency) goto add_bfqq_busy; + if (bfq_bfqq_just_split(bfqq)) + goto set_ioprio_changed; + /* - * If the queue is not being boosted and has been idle - * for enough time, start a weight-raising period + * If the queue: + * - is not being boosted, + * - has been idle for enough time, + * - is not a sync queue or is linked to a bfq_io_cq (it is + * shared "for its nature" or it is not shared and its + * requests have not been redirected to a shared queue) + * start a weight-raising period. */ - if (old_wr_coeff == 1 && (interactive || soft_rt)) { + if (old_wr_coeff == 1 && (interactive || soft_rt) && + (!bfq_bfqq_sync(bfqq) || bfqq->bic != NULL)) { bfqq->wr_coeff = bfqd->bfq_wr_coeff; if (interactive) bfqq->wr_cur_max_time = bfq_wr_duration(bfqd); @@ -882,7 +943,7 @@ static void bfq_add_request(struct request *rq) } else if (old_wr_coeff > 1) { if (interactive) bfqq->wr_cur_max_time = bfq_wr_duration(bfqd); - else if (bfq_bfqq_in_large_burst(bfqq) || + else if (coop_or_in_burst || (bfqq->wr_cur_max_time == bfqd->bfq_wr_rt_max_time && !soft_rt)) { @@ -901,18 +962,18 @@ static void bfq_add_request(struct request *rq) /* * * The remaining weight-raising time is lower - * than bfqd->bfq_wr_rt_max_time, which - * means that the application is enjoying - * weight raising either because deemed soft- - * rt in the near past, or because deemed - * interactive a long ago. In both cases, - * resetting now the current remaining weight- - * raising time for the application to the - * weight-raising duration for soft rt - * applications would not cause any latency - * increase for the application (as the new - * duration would be higher than the remaining - * time). + * than bfqd->bfq_wr_rt_max_time, which means + * that the application is enjoying weight + * raising either because deemed soft-rt in + * the near past, or because deemed interactive + * a long ago. + * In both cases, resetting now the current + * remaining weight-raising time for the + * application to the weight-raising duration + * for soft rt applications would not cause any + * latency increase for the application (as the + * new duration would be higher than the + * remaining time). * * In addition, the application is now meeting * the requirements for being deemed soft rt. @@ -947,6 +1008,7 @@ static void bfq_add_request(struct request *rq) bfqd->bfq_wr_rt_max_time; } } +set_ioprio_changed: if (old_wr_coeff != bfqq->wr_coeff) entity->ioprio_changed = 1; add_bfqq_busy: @@ -1167,90 +1229,35 @@ static void bfq_end_wr(struct bfq_data *bfqd) spin_unlock_irq(bfqd->queue->queue_lock); } -static int bfq_allow_merge(struct request_queue *q, struct request *rq, - struct bio *bio) +static inline sector_t bfq_io_struct_pos(void *io_struct, bool request) { - struct bfq_data *bfqd = q->elevator->elevator_data; - struct bfq_io_cq *bic; - struct bfq_queue *bfqq; - - /* - * Disallow merge of a sync bio into an async request. - */ - if (bfq_bio_sync(bio) && !rq_is_sync(rq)) - return 0; - - /* - * Lookup the bfqq that this bio will be queued with. Allow - * merge only if rq is queued there. - * Queue lock is held here. - */ - bic = bfq_bic_lookup(bfqd, current->io_context); - if (bic == NULL) - return 0; - - bfqq = bic_to_bfqq(bic, bfq_bio_sync(bio)); - return bfqq == RQ_BFQQ(rq); -} - -static void __bfq_set_in_service_queue(struct bfq_data *bfqd, - struct bfq_queue *bfqq) -{ - if (bfqq != NULL) { - bfq_mark_bfqq_must_alloc(bfqq); - bfq_mark_bfqq_budget_new(bfqq); - bfq_clear_bfqq_fifo_expire(bfqq); - - bfqd->budgets_assigned = (bfqd->budgets_assigned*7 + 256) / 8; - - bfq_log_bfqq(bfqd, bfqq, - "set_in_service_queue, cur-budget = %lu", - bfqq->entity.budget); - } - - bfqd->in_service_queue = bfqq; -} - -/* - * Get and set a new queue for service. - */ -static struct bfq_queue *bfq_set_in_service_queue(struct bfq_data *bfqd, - struct bfq_queue *bfqq) -{ - if (!bfqq) - bfqq = bfq_get_next_queue(bfqd); + if (request) + return blk_rq_pos(io_struct); else - bfq_get_next_queue_forced(bfqd, bfqq); - - __bfq_set_in_service_queue(bfqd, bfqq); - return bfqq; + return ((struct bio *)io_struct)->bi_iter.bi_sector; } -static inline sector_t bfq_dist_from_last(struct bfq_data *bfqd, - struct request *rq) +static inline sector_t bfq_dist_from(sector_t pos1, + sector_t pos2) { - if (blk_rq_pos(rq) >= bfqd->last_position) - return blk_rq_pos(rq) - bfqd->last_position; + if (pos1 >= pos2) + return pos1 - pos2; else - return bfqd->last_position - blk_rq_pos(rq); + return pos2 - pos1; } -/* - * Return true if bfqq has no request pending and rq is close enough to - * bfqd->last_position, or if rq is closer to bfqd->last_position than - * bfqq->next_rq - */ -static inline int bfq_rq_close(struct bfq_data *bfqd, struct request *rq) +static inline int bfq_rq_close_to_sector(void *io_struct, bool request, + sector_t sector) { - return bfq_dist_from_last(bfqd, rq) <= BFQQ_SEEK_THR; + return bfq_dist_from(bfq_io_struct_pos(io_struct, request), sector) <= + BFQQ_SEEK_THR; } -static struct bfq_queue *bfqq_close(struct bfq_data *bfqd) +static struct bfq_queue *bfqq_close(struct bfq_data *bfqd, sector_t sector) { struct rb_root *root = &bfqd->rq_pos_tree; struct rb_node *parent, *node; struct bfq_queue *__bfqq; - sector_t sector = bfqd->last_position; if (RB_EMPTY_ROOT(root)) return NULL; @@ -1269,7 +1276,7 @@ static struct bfq_queue *bfqq_close(struct bfq_data *bfqd) * next_request position). */ __bfqq = rb_entry(parent, struct bfq_queue, pos_node); - if (bfq_rq_close(bfqd, __bfqq->next_rq)) + if (bfq_rq_close_to_sector(__bfqq->next_rq, true, sector)) return __bfqq; if (blk_rq_pos(__bfqq->next_rq) < sector) @@ -1280,7 +1287,7 @@ static struct bfq_queue *bfqq_close(struct bfq_data *bfqd) return NULL; __bfqq = rb_entry(node, struct bfq_queue, pos_node); - if (bfq_rq_close(bfqd, __bfqq->next_rq)) + if (bfq_rq_close_to_sector(__bfqq->next_rq, true, sector)) return __bfqq; return NULL; @@ -1289,14 +1296,12 @@ static struct bfq_queue *bfqq_close(struct bfq_data *bfqd) /* * bfqd - obvious * cur_bfqq - passed in so that we don't decide that the current queue - * is closely cooperating with itself. - * - * We are assuming that cur_bfqq has dispatched at least one request, - * and that bfqd->last_position reflects a position on the disk associated - * with the I/O issued by cur_bfqq. + * is closely cooperating with itself + * sector - used as a reference point to search for a close queue */ static struct bfq_queue *bfq_close_cooperator(struct bfq_data *bfqd, - struct bfq_queue *cur_bfqq) + struct bfq_queue *cur_bfqq, + sector_t sector) { struct bfq_queue *bfqq; @@ -1316,7 +1321,7 @@ static struct bfq_queue *bfq_close_cooperator(struct bfq_data *bfqd, * working closely on the same area of the disk. In that case, * we can group them together and don't waste time idling. */ - bfqq = bfqq_close(bfqd); + bfqq = bfqq_close(bfqd, sector); if (bfqq == NULL || bfqq == cur_bfqq) return NULL; @@ -1343,6 +1348,315 @@ static struct bfq_queue *bfq_close_cooperator(struct bfq_data *bfqd, return bfqq; } +static struct bfq_queue * +bfq_setup_merge(struct bfq_queue *bfqq, struct bfq_queue *new_bfqq) +{ + int process_refs, new_process_refs; + struct bfq_queue *__bfqq; + + /* + * If there are no process references on the new_bfqq, then it is + * unsafe to follow the ->new_bfqq chain as other bfqq's in the chain + * may have dropped their last reference (not just their last process + * reference). + */ + if (!bfqq_process_refs(new_bfqq)) + return NULL; + + /* Avoid a circular list and skip interim queue merges. */ + while ((__bfqq = new_bfqq->new_bfqq)) { + if (__bfqq == bfqq) + return NULL; + new_bfqq = __bfqq; + } + + process_refs = bfqq_process_refs(bfqq); + new_process_refs = bfqq_process_refs(new_bfqq); + /* + * If the process for the bfqq has gone away, there is no + * sense in merging the queues. + */ + if (process_refs == 0 || new_process_refs == 0) + return NULL; + + bfq_log_bfqq(bfqq->bfqd, bfqq, "scheduling merge with queue %d", + new_bfqq->pid); + + /* + * Merging is just a redirection: the requests of the process + * owning one of the two queues are redirected to the other queue. + * The latter queue, in its turn, is set as shared if this is the + * first time that the requests of some process are redirected to + * it. + * + * We redirect bfqq to new_bfqq and not the opposite, because we + * are in the context of the process owning bfqq, hence we have + * the io_cq of this process. So we can immediately configure this + * io_cq to redirect the requests of the process to new_bfqq. + * + * NOTE, even if new_bfqq coincides with the in-service queue, the + * io_cq of new_bfqq is not available, because, if the in-service + * queue is shared, bfqd->in_service_bic may not point to the + * io_cq of the in-service queue. + * Redirecting the requests of the process owning bfqq to the + * currently in-service queue is in any case the best option, as + * we feed the in-service queue with new requests close to the + * last request served and, by doing so, hopefully increase the + * throughput. + */ + bfqq->new_bfqq = new_bfqq; + atomic_add(process_refs, &new_bfqq->ref); + return new_bfqq; +} + +/* + * Attempt to schedule a merge of bfqq with the currently in-service queue + * or with a close queue among the scheduled queues. + * Return NULL if no merge was scheduled, a pointer to the shared bfq_queue + * structure otherwise. + * + * The OOM queue is not allowed to participate to cooperation: in fact, since + * the requests temporarily redirected to the OOM queue could be redirected + * again to dedicated queues at any time, the state needed to correctly + * handle merging with the OOM queue would be quite complex and expensive + * to maintain. Besides, in such a critical condition as an out of memory, + * the benefits of queue merging may be little relevant, or even negligible. + */ +static struct bfq_queue * +bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq, + void *io_struct, bool request) +{ + struct bfq_queue *in_service_bfqq, *new_bfqq; + + if (bfqq->new_bfqq) + return bfqq->new_bfqq; + + if (!io_struct || unlikely(bfqq == &bfqd->oom_bfqq)) + return NULL; + + in_service_bfqq = bfqd->in_service_queue; + + if (in_service_bfqq == NULL || in_service_bfqq == bfqq || + !bfqd->in_service_bic || + unlikely(in_service_bfqq == &bfqd->oom_bfqq)) + goto check_scheduled; + + if (bfq_class_idle(in_service_bfqq) || bfq_class_idle(bfqq)) + goto check_scheduled; + + if (bfq_class_rt(in_service_bfqq) != bfq_class_rt(bfqq)) + goto check_scheduled; + + if (in_service_bfqq->entity.parent != bfqq->entity.parent) + goto check_scheduled; + + if (bfq_rq_close_to_sector(io_struct, request, bfqd->last_position) && + bfq_bfqq_sync(in_service_bfqq) && bfq_bfqq_sync(bfqq)) { + new_bfqq = bfq_setup_merge(bfqq, in_service_bfqq); + if (new_bfqq != NULL) + return new_bfqq; /* Merge with in-service queue */ + } + + /* + * Check whether there is a cooperator among currently scheduled + * queues. The only thing we need is that the bio/request is not + * NULL, as we need it to establish whether a cooperator exists. + */ +check_scheduled: + new_bfqq = bfq_close_cooperator(bfqd, bfqq, + bfq_io_struct_pos(io_struct, request)); + if (new_bfqq && likely(new_bfqq != &bfqd->oom_bfqq)) + return bfq_setup_merge(bfqq, new_bfqq); + + return NULL; +} + +static inline void +bfq_bfqq_save_state(struct bfq_queue *bfqq) +{ + /* + * If bfqq->bic == NULL, the queue is already shared or its requests + * have already been redirected to a shared queue; both idle window + * and weight raising state have already been saved. Do nothing. + */ + if (bfqq->bic == NULL) + return; + if (bfqq->bic->wr_time_left) + /* + * This is the queue of a just-started process, and would + * deserve weight raising: we set wr_time_left to the full + * weight-raising duration to trigger weight-raising when + * and if the queue is split and the first request of the + * queue is enqueued. + */ + bfqq->bic->wr_time_left = bfq_wr_duration(bfqq->bfqd); + else if (bfqq->wr_coeff > 1) { + unsigned long wr_duration = + jiffies - bfqq->last_wr_start_finish; + /* + * It may happen that a queue's weight raising period lasts + * longer than its wr_cur_max_time, as weight raising is + * handled only when a request is enqueued or dispatched (it + * does not use any timer). If the weight raising period is + * about to end, don't save it. + */ + if (bfqq->wr_cur_max_time <= wr_duration) + bfqq->bic->wr_time_left = 0; + else + bfqq->bic->wr_time_left = + bfqq->wr_cur_max_time - wr_duration; + /* + * The bfq_queue is becoming shared or the requests of the + * process owning the queue are being redirected to a shared + * queue. Stop the weight raising period of the queue, as in + * both cases it should not be owned by an interactive or + * soft real-time application. + */ + bfq_bfqq_end_wr(bfqq); + } else + bfqq->bic->wr_time_left = 0; + bfqq->bic->saved_idle_window = bfq_bfqq_idle_window(bfqq); + bfqq->bic->saved_IO_bound = bfq_bfqq_IO_bound(bfqq); + bfqq->bic->saved_in_large_burst = bfq_bfqq_in_large_burst(bfqq); + bfqq->bic->was_in_burst_list = !hlist_unhashed(&bfqq->burst_list_node); + bfqq->bic->cooperations++; + bfqq->bic->failed_cooperations = 0; +} + +static inline void +bfq_get_bic_reference(struct bfq_queue *bfqq) +{ + /* + * If bfqq->bic has a non-NULL value, the bic to which it belongs + * is about to begin using a shared bfq_queue. + */ + if (bfqq->bic) + atomic_long_inc(&bfqq->bic->icq.ioc->refcount); +} + +static void +bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic, + struct bfq_queue *bfqq, struct bfq_queue *new_bfqq) +{ + bfq_log_bfqq(bfqd, bfqq, "merging with queue %lu", + (long unsigned)new_bfqq->pid); + /* Save weight raising and idle window of the merged queues */ + bfq_bfqq_save_state(bfqq); + bfq_bfqq_save_state(new_bfqq); + if (bfq_bfqq_IO_bound(bfqq)) + bfq_mark_bfqq_IO_bound(new_bfqq); + bfq_clear_bfqq_IO_bound(bfqq); + /* + * Grab a reference to the bic, to prevent it from being destroyed + * before being possibly touched by a bfq_split_bfqq(). + */ + bfq_get_bic_reference(bfqq); + bfq_get_bic_reference(new_bfqq); + /* + * Merge queues (that is, let bic redirect its requests to new_bfqq) + */ + bic_set_bfqq(bic, new_bfqq, 1); + bfq_mark_bfqq_coop(new_bfqq); + /* + * new_bfqq now belongs to at least two bics (it is a shared queue): + * set new_bfqq->bic to NULL. bfqq either: + * - does not belong to any bic any more, and hence bfqq->bic must + * be set to NULL, or + * - is a queue whose owning bics have already been redirected to a + * different queue, hence the queue is destined to not belong to + * any bic soon and bfqq->bic is already NULL (therefore the next + * assignment causes no harm). + */ + new_bfqq->bic = NULL; + bfqq->bic = NULL; + bfq_put_queue(bfqq); +} + +static inline void bfq_bfqq_increase_failed_cooperations(struct bfq_queue *bfqq) +{ + struct bfq_io_cq *bic = bfqq->bic; + struct bfq_data *bfqd = bfqq->bfqd; + + if (bic && bfq_bfqq_cooperations(bfqq) >= bfqd->bfq_coop_thresh) { + bic->failed_cooperations++; + if (bic->failed_cooperations >= bfqd->bfq_failed_cooperations) + bic->cooperations = 0; + } +} + +static int bfq_allow_merge(struct request_queue *q, struct request *rq, + struct bio *bio) +{ + struct bfq_data *bfqd = q->elevator->elevator_data; + struct bfq_io_cq *bic; + struct bfq_queue *bfqq, *new_bfqq; + + /* + * Disallow merge of a sync bio into an async request. + */ + if (bfq_bio_sync(bio) && !rq_is_sync(rq)) + return 0; + + /* + * Lookup the bfqq that this bio will be queued with. Allow + * merge only if rq is queued there. + * Queue lock is held here. + */ + bic = bfq_bic_lookup(bfqd, current->io_context); + if (bic == NULL) + return 0; + + bfqq = bic_to_bfqq(bic, bfq_bio_sync(bio)); + /* + * We take advantage of this function to perform an early merge + * of the queues of possible cooperating processes. + */ + if (bfqq != NULL) { + new_bfqq = bfq_setup_cooperator(bfqd, bfqq, bio, false); + if (new_bfqq != NULL) { + bfq_merge_bfqqs(bfqd, bic, bfqq, new_bfqq); + /* + * If we get here, the bio will be queued in the + * shared queue, i.e., new_bfqq, so use new_bfqq + * to decide whether bio and rq can be merged. + */ + bfqq = new_bfqq; + } else + bfq_bfqq_increase_failed_cooperations(bfqq); + } + + return bfqq == RQ_BFQQ(rq); +} + +static void __bfq_set_in_service_queue(struct bfq_data *bfqd, + struct bfq_queue *bfqq) +{ + if (bfqq != NULL) { + bfq_mark_bfqq_must_alloc(bfqq); + bfq_mark_bfqq_budget_new(bfqq); + bfq_clear_bfqq_fifo_expire(bfqq); + + bfqd->budgets_assigned = (bfqd->budgets_assigned*7 + 256) / 8; + + bfq_log_bfqq(bfqd, bfqq, + "set_in_service_queue, cur-budget = %lu", + bfqq->entity.budget); + } + + bfqd->in_service_queue = bfqq; +} + +/* + * Get and set a new queue for service. + */ +static struct bfq_queue *bfq_set_in_service_queue(struct bfq_data *bfqd) +{ + struct bfq_queue *bfqq = bfq_get_next_queue(bfqd); + + __bfq_set_in_service_queue(bfqd, bfqq); + return bfqq; +} + /* * If enough samples have been computed, return the current max budget * stored in bfqd, which is dynamically updated according to the @@ -1488,61 +1802,6 @@ static struct request *bfq_check_fifo(struct bfq_queue *bfqq) return rq; } -/* Must be called with the queue_lock held. */ -static int bfqq_process_refs(struct bfq_queue *bfqq) -{ - int process_refs, io_refs; - - io_refs = bfqq->allocated[READ] + bfqq->allocated[WRITE]; - process_refs = atomic_read(&bfqq->ref) - io_refs - bfqq->entity.on_st; - BUG_ON(process_refs < 0); - return process_refs; -} - -static void bfq_setup_merge(struct bfq_queue *bfqq, struct bfq_queue *new_bfqq) -{ - int process_refs, new_process_refs; - struct bfq_queue *__bfqq; - - /* - * If there are no process references on the new_bfqq, then it is - * unsafe to follow the ->new_bfqq chain as other bfqq's in the chain - * may have dropped their last reference (not just their last process - * reference). - */ - if (!bfqq_process_refs(new_bfqq)) - return; - - /* Avoid a circular list and skip interim queue merges. */ - while ((__bfqq = new_bfqq->new_bfqq)) { - if (__bfqq == bfqq) - return; - new_bfqq = __bfqq; - } - - process_refs = bfqq_process_refs(bfqq); - new_process_refs = bfqq_process_refs(new_bfqq); - /* - * If the process for the bfqq has gone away, there is no - * sense in merging the queues. - */ - if (process_refs == 0 || new_process_refs == 0) - return; - - /* - * Merge in the direction of the lesser amount of work. - */ - if (new_process_refs >= process_refs) { - bfqq->new_bfqq = new_bfqq; - atomic_add(process_refs, &new_bfqq->ref); - } else { - new_bfqq->new_bfqq = bfqq; - atomic_add(new_process_refs, &bfqq->ref); - } - bfq_log_bfqq(bfqq->bfqd, bfqq, "scheduling merge with queue %d", - new_bfqq->pid); -} - static inline unsigned long bfq_bfqq_budget_left(struct bfq_queue *bfqq) { struct bfq_entity *entity = &bfqq->entity; @@ -2269,7 +2528,7 @@ static inline bool bfq_bfqq_must_idle(struct bfq_queue *bfqq) */ static struct bfq_queue *bfq_select_queue(struct bfq_data *bfqd) { - struct bfq_queue *bfqq, *new_bfqq = NULL; + struct bfq_queue *bfqq; struct request *next_rq; enum bfqq_expiration reason = BFQ_BFQQ_BUDGET_TIMEOUT; @@ -2279,17 +2538,6 @@ static struct bfq_queue *bfq_select_queue(struct bfq_data *bfqd) bfq_log_bfqq(bfqd, bfqq, "select_queue: already in-service queue"); - /* - * If another queue has a request waiting within our mean seek - * distance, let it run. The expire code will check for close - * cooperators and put the close queue at the front of the - * service tree. If possible, merge the expiring queue with the - * new bfqq. - */ - new_bfqq = bfq_close_cooperator(bfqd, bfqq); - if (new_bfqq != NULL && bfqq->new_bfqq == NULL) - bfq_setup_merge(bfqq, new_bfqq); - if (bfq_may_expire_for_budg_timeout(bfqq) && !timer_pending(&bfqd->idle_slice_timer) && !bfq_bfqq_must_idle(bfqq)) @@ -2328,10 +2576,7 @@ static struct bfq_queue *bfq_select_queue(struct bfq_data *bfqd) bfq_clear_bfqq_wait_request(bfqq); del_timer(&bfqd->idle_slice_timer); } - if (new_bfqq == NULL) - goto keep_queue; - else - goto expire; + goto keep_queue; } } @@ -2340,40 +2585,30 @@ static struct bfq_queue *bfq_select_queue(struct bfq_data *bfqd) * for a new request, or has requests waiting for a completion and * may idle after their completion, then keep it anyway. */ - if (new_bfqq == NULL && (timer_pending(&bfqd->idle_slice_timer) || - (bfqq->dispatched != 0 && bfq_bfqq_must_not_expire(bfqq)))) { + if (timer_pending(&bfqd->idle_slice_timer) || + (bfqq->dispatched != 0 && bfq_bfqq_must_not_expire(bfqq))) { bfqq = NULL; goto keep_queue; - } else if (new_bfqq != NULL && timer_pending(&bfqd->idle_slice_timer)) { - /* - * Expiring the queue because there is a close cooperator, - * cancel timer. - */ - bfq_clear_bfqq_wait_request(bfqq); - del_timer(&bfqd->idle_slice_timer); } reason = BFQ_BFQQ_NO_MORE_REQUESTS; expire: bfq_bfqq_expire(bfqd, bfqq, 0, reason); new_queue: - bfqq = bfq_set_in_service_queue(bfqd, new_bfqq); + bfqq = bfq_set_in_service_queue(bfqd); bfq_log(bfqd, "select_queue: new queue %d returned", bfqq != NULL ? bfqq->pid : 0); keep_queue: return bfqq; } -static void bfq_update_wr_data(struct bfq_data *bfqd, - struct bfq_queue *bfqq) +static void bfq_update_wr_data(struct bfq_data *bfqd, struct bfq_queue *bfqq) { - if (bfqq->wr_coeff > 1) { /* queue is being boosted */ - struct bfq_entity *entity = &bfqq->entity; - + struct bfq_entity *entity = &bfqq->entity; + if (bfqq->wr_coeff > 1) { /* queue is being weight-raised */ bfq_log_bfqq(bfqd, bfqq, "raising period dur %u/%u msec, old coeff %u, w %d(%d)", - jiffies_to_msecs(jiffies - - bfqq->last_wr_start_finish), + jiffies_to_msecs(jiffies - bfqq->last_wr_start_finish), jiffies_to_msecs(bfqq->wr_cur_max_time), bfqq->wr_coeff, bfqq->entity.weight, bfqq->entity.orig_weight); @@ -2382,12 +2617,16 @@ static void bfq_update_wr_data(struct bfq_data *bfqd, entity->orig_weight * bfqq->wr_coeff); if (entity->ioprio_changed) bfq_log_bfqq(bfqd, bfqq, "WARN: pending prio change"); + /* * If the queue was activated in a burst, or * too much time has elapsed from the beginning - * of this weight-raising, then end weight raising. + * of this weight-raising period, or the queue has + * exceeded the acceptable number of cooperations, + * then end weight raising. */ if (bfq_bfqq_in_large_burst(bfqq) || + bfq_bfqq_cooperations(bfqq) >= bfqd->bfq_coop_thresh || time_is_before_jiffies(bfqq->last_wr_start_finish + bfqq->wr_cur_max_time)) { bfqq->last_wr_start_finish = jiffies; @@ -2396,11 +2635,13 @@ static void bfq_update_wr_data(struct bfq_data *bfqd, bfqq->last_wr_start_finish, jiffies_to_msecs(bfqq->wr_cur_max_time)); bfq_bfqq_end_wr(bfqq); - __bfq_entity_update_weight_prio( - bfq_entity_service_tree(entity), - entity); } } + /* Update weight both if it must be raised and if it must be lowered */ + if ((entity->weight > entity->orig_weight) != (bfqq->wr_coeff > 1)) + __bfq_entity_update_weight_prio( + bfq_entity_service_tree(entity), + entity); } /* @@ -2647,6 +2888,25 @@ static inline void bfq_init_icq(struct io_cq *icq) struct bfq_io_cq *bic = icq_to_bic(icq); bic->ttime.last_end_request = jiffies; + /* + * A newly created bic indicates that the process has just + * started doing I/O, and is probably mapping into memory its + * executable and libraries: it definitely needs weight raising. + * There is however the possibility that the process performs, + * for a while, I/O close to some other process. EQM intercepts + * this behavior and may merge the queue corresponding to the + * process with some other queue, BEFORE the weight of the queue + * is raised. Merged queues are not weight-raised (they are assumed + * to belong to processes that benefit only from high throughput). + * If the merge is basically the consequence of an accident, then + * the queue will be split soon and will get back its old weight. + * It is then important to write down somewhere that this queue + * does need weight raising, even if it did not make it to get its + * weight raised before being merged. To this purpose, we overload + * the field raising_time_left and assign 1 to it, to mark the queue + * as needing weight raising. + */ + bic->wr_time_left = 1; } static void bfq_exit_icq(struct io_cq *icq) @@ -2660,6 +2920,13 @@ static void bfq_exit_icq(struct io_cq *icq) } if (bic->bfqq[BLK_RW_SYNC]) { + /* + * If the bic is using a shared queue, put the reference + * taken on the io_context when the bic started using a + * shared bfq_queue. + */ + if (bfq_bfqq_coop(bic->bfqq[BLK_RW_SYNC])) + put_io_context(icq->ioc); bfq_exit_bfqq(bfqd, bic->bfqq[BLK_RW_SYNC]); bic->bfqq[BLK_RW_SYNC] = NULL; } @@ -2952,6 +3219,10 @@ static void bfq_update_idle_window(struct bfq_data *bfqd, if (!bfq_bfqq_sync(bfqq) || bfq_class_idle(bfqq)) return; + /* Idle window just restored, statistics are meaningless. */ + if (bfq_bfqq_just_split(bfqq)) + return; + enable_idle = bfq_bfqq_idle_window(bfqq); if (atomic_read(&bic->icq.ioc->active_ref) == 0 || @@ -2999,6 +3270,7 @@ static void bfq_rq_enqueued(struct bfq_data *bfqd, struct bfq_queue *bfqq, if (bfqq->entity.service > bfq_max_budget(bfqd) / 8 || !BFQQ_SEEKY(bfqq)) bfq_update_idle_window(bfqd, bfqq, bic); + bfq_clear_bfqq_just_split(bfqq); bfq_log_bfqq(bfqd, bfqq, "rq_enqueued: idle_window=%d (seeky %d, mean %llu)", @@ -3059,12 +3331,47 @@ static void bfq_rq_enqueued(struct bfq_data *bfqd, struct bfq_queue *bfqq, static void bfq_insert_request(struct request_queue *q, struct request *rq) { struct bfq_data *bfqd = q->elevator->elevator_data; - struct bfq_queue *bfqq = RQ_BFQQ(rq); + struct bfq_queue *bfqq = RQ_BFQQ(rq), *new_bfqq; assert_spin_locked(bfqd->queue->queue_lock); + /* + * An unplug may trigger a requeue of a request from the device + * driver: make sure we are in process context while trying to + * merge two bfq_queues. + */ + if (!in_interrupt()) { + new_bfqq = bfq_setup_cooperator(bfqd, bfqq, rq, true); + if (new_bfqq != NULL) { + if (bic_to_bfqq(RQ_BIC(rq), 1) != bfqq) + new_bfqq = bic_to_bfqq(RQ_BIC(rq), 1); + /* + * Release the request's reference to the old bfqq + * and make sure one is taken to the shared queue. + */ + new_bfqq->allocated[rq_data_dir(rq)]++; + bfqq->allocated[rq_data_dir(rq)]--; + atomic_inc(&new_bfqq->ref); + bfq_put_queue(bfqq); + if (bic_to_bfqq(RQ_BIC(rq), 1) == bfqq) + bfq_merge_bfqqs(bfqd, RQ_BIC(rq), + bfqq, new_bfqq); + rq->elv.priv[1] = new_bfqq; + bfqq = new_bfqq; + } else + bfq_bfqq_increase_failed_cooperations(bfqq); + } + bfq_add_request(rq); + /* + * Here a newly-created bfq_queue has already started a weight-raising + * period: clear raising_time_left to prevent bfq_bfqq_save_state() + * from assigning it a full weight-raising period. See the detailed + * comments about this field in bfq_init_icq(). + */ + if (bfqq->bic != NULL) + bfqq->bic->wr_time_left = 0; rq->fifo_time = jiffies + bfqd->bfq_fifo_expire[rq_is_sync(rq)]; list_add_tail(&rq->queuelist, &bfqq->fifo); @@ -3226,18 +3533,6 @@ static void bfq_put_request(struct request *rq) } } -static struct bfq_queue * -bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic, - struct bfq_queue *bfqq) -{ - bfq_log_bfqq(bfqd, bfqq, "merging with queue %lu", - (long unsigned)bfqq->new_bfqq->pid); - bic_set_bfqq(bic, bfqq->new_bfqq, 1); - bfq_mark_bfqq_coop(bfqq->new_bfqq); - bfq_put_queue(bfqq); - return bic_to_bfqq(bic, 1); -} - /* * Returns NULL if a new bfqq should be allocated, or the old bfqq if this * was the last process referring to said bfqq. @@ -3246,6 +3541,9 @@ static struct bfq_queue * bfq_split_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq) { bfq_log_bfqq(bfqq->bfqd, bfqq, "splitting queue"); + + put_io_context(bic->icq.ioc); + if (bfqq_process_refs(bfqq) == 1) { bfqq->pid = current->pid; bfq_clear_bfqq_coop(bfqq); @@ -3274,6 +3572,7 @@ static int bfq_set_request(struct request_queue *q, struct request *rq, struct bfq_queue *bfqq; struct bfq_group *bfqg; unsigned long flags; + bool split = false; might_sleep_if(gfp_mask & __GFP_WAIT); @@ -3291,25 +3590,26 @@ new_queue: if (bfqq == NULL || bfqq == &bfqd->oom_bfqq) { bfqq = bfq_get_queue(bfqd, bfqg, is_sync, bic, gfp_mask); bic_set_bfqq(bic, bfqq, is_sync); + if (split && is_sync) { + if ((bic->was_in_burst_list && bfqd->large_burst) || + bic->saved_in_large_burst) + bfq_mark_bfqq_in_large_burst(bfqq); + else { + bfq_clear_bfqq_in_large_burst(bfqq); + if (bic->was_in_burst_list) + hlist_add_head(&bfqq->burst_list_node, + &bfqd->burst_list); + } + } } else { - /* - * If the queue was seeky for too long, break it apart. - */ + /* If the queue was seeky for too long, break it apart. */ if (bfq_bfqq_coop(bfqq) && bfq_bfqq_split_coop(bfqq)) { bfq_log_bfqq(bfqd, bfqq, "breaking apart bfqq"); bfqq = bfq_split_bfqq(bic, bfqq); + split = true; if (!bfqq) goto new_queue; } - - /* - * Check to see if this queue is scheduled to merge with - * another closely cooperating queue. The merging of queues - * happens here as it must be done in process context. - * The reference on new_bfqq was taken in merge_bfqqs. - */ - if (bfqq->new_bfqq != NULL) - bfqq = bfq_merge_bfqqs(bfqd, bic, bfqq); } bfqq->allocated[rw]++; @@ -3320,6 +3620,26 @@ new_queue: rq->elv.priv[0] = bic; rq->elv.priv[1] = bfqq; + /* + * If a bfq_queue has only one process reference, it is owned + * by only one bfq_io_cq: we can set the bic field of the + * bfq_queue to the address of that structure. Also, if the + * queue has just been split, mark a flag so that the + * information is available to the other scheduler hooks. + */ + if (likely(bfqq != &bfqd->oom_bfqq) && bfqq_process_refs(bfqq) == 1) { + bfqq->bic = bic; + if (split) { + bfq_mark_bfqq_just_split(bfqq); + /* + * If the queue has just been split from a shared + * queue, restore the idle window and the possible + * weight raising period. + */ + bfq_bfqq_resume_state(bfqq, bic); + } + } + spin_unlock_irqrestore(q->queue_lock, flags); return 0; diff --git a/block/bfq-sched.c b/block/bfq-sched.c index c343099..d0890c6 100644 --- a/block/bfq-sched.c +++ b/block/bfq-sched.c @@ -1085,34 +1085,6 @@ static struct bfq_queue *bfq_get_next_queue(struct bfq_data *bfqd) return bfqq; } -/* - * Forced extraction of the given queue. - */ -static void bfq_get_next_queue_forced(struct bfq_data *bfqd, - struct bfq_queue *bfqq) -{ - struct bfq_entity *entity; - struct bfq_sched_data *sd; - - BUG_ON(bfqd->in_service_queue != NULL); - - entity = &bfqq->entity; - /* - * Bubble up extraction/update from the leaf to the root. - */ - for_each_entity(entity) { - sd = entity->sched_data; - bfq_update_budget(entity); - bfq_update_vtime(bfq_entity_service_tree(entity)); - bfq_active_extract(bfq_entity_service_tree(entity), entity); - sd->in_service_entity = entity; - sd->next_in_service = NULL; - entity->service = 0; - } - - return; -} - static void __bfq_bfqd_reset_in_service(struct bfq_data *bfqd) { if (bfqd->in_service_bic != NULL) { diff --git a/block/bfq.h b/block/bfq.h index 3173b35..629c413 100644 --- a/block/bfq.h +++ b/block/bfq.h @@ -218,18 +218,21 @@ struct bfq_group; * idle @bfq_queue with no outstanding requests, then * the task associated with the queue it is deemed as * soft real-time (see the comments to the function - * bfq_bfqq_softrt_next_start()). + * bfq_bfqq_softrt_next_start()) * @last_idle_bklogged: time of the last transition of the @bfq_queue from * idle to backlogged * @service_from_backlogged: cumulative service received from the @bfq_queue * since the last transition from idle to * backlogged + * @bic: pointer to the bfq_io_cq owning the bfq_queue, set to %NULL if the + * queue is shared * - * 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). + * 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. */ struct bfq_queue { @@ -269,6 +272,7 @@ struct bfq_queue { unsigned int requests_within_timer; pid_t pid; + struct bfq_io_cq *bic; /* weight-raising fields */ unsigned long wr_cur_max_time; @@ -298,12 +302,42 @@ struct bfq_ttime { * @icq: associated io_cq structure * @bfqq: array of two process queues, the sync and the async * @ttime: associated @bfq_ttime struct + * @wr_time_left: snapshot of the time left before weight raising ends + * for the sync queue associated to this process; this + * snapshot is taken to remember this value while the weight + * raising is suspended because the queue is merged with a + * shared queue, and is used to set @raising_cur_max_time + * when the queue is split from the shared queue and its + * weight is raised again + * @saved_idle_window: same purpose as the previous field for the idle + * window + * @saved_IO_bound: same purpose as the previous two fields for the I/O + * bound classification of a queue + * @saved_in_large_burst: same purpose as the previous fields for the + * value of the field keeping the queue's belonging + * to a large burst + * @was_in_burst_list: true if the queue belonged to a burst list + * before its merge with another cooperating queue + * @cooperations: counter of consecutive successful queue merges underwent + * by any of the process' @bfq_queues + * @failed_cooperations: counter of consecutive failed queue merges of any + * of the process' @bfq_queues */ struct bfq_io_cq { struct io_cq icq; /* must be the first member */ struct bfq_queue *bfqq[2]; struct bfq_ttime ttime; int ioprio; + + unsigned int wr_time_left; + bool saved_idle_window; + bool saved_IO_bound; + + bool saved_in_large_burst; + bool was_in_burst_list; + + unsigned int cooperations; + unsigned int failed_cooperations; }; enum bfq_device_speed { @@ -536,7 +570,7 @@ enum bfqq_state_flags { BFQ_BFQQ_FLAG_idle_window, /* slice idling enabled */ BFQ_BFQQ_FLAG_sync, /* synchronous queue */ BFQ_BFQQ_FLAG_budget_new, /* no completion with this budget */ - BFQ_BFQQ_FLAG_IO_bound, /* + BFQ_BFQQ_FLAG_IO_bound, /* * bfqq has timed-out at least once * having consumed at most 2/10 of * its budget @@ -549,12 +583,13 @@ enum bfqq_state_flags { * bfqq has proved to be slow and * seeky until budget timeout */ - BFQ_BFQQ_FLAG_softrt_update, /* + BFQ_BFQQ_FLAG_softrt_update, /* * may need softrt-next-start * update */ BFQ_BFQQ_FLAG_coop, /* bfqq is shared */ - BFQ_BFQQ_FLAG_split_coop, /* shared bfqq will be splitted */ + BFQ_BFQQ_FLAG_split_coop, /* shared bfqq will be split */ + BFQ_BFQQ_FLAG_just_split, /* queue has just been split */ }; #define BFQ_BFQQ_FNS(name) \ @@ -583,6 +618,7 @@ BFQ_BFQQ_FNS(in_large_burst); BFQ_BFQQ_FNS(constantly_seeky); BFQ_BFQQ_FNS(coop); BFQ_BFQQ_FNS(split_coop); +BFQ_BFQQ_FNS(just_split); BFQ_BFQQ_FNS(softrt_update); #undef BFQ_BFQQ_FNS -- 2.1.4