From patchwork Sun Oct 30 10:02:53 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Patchwork-Submitter: Paolo Valente X-Patchwork-Id: 13025050 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 8B378C38A02 for ; Sun, 30 Oct 2022 10:03:42 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S230018AbiJ3KDk (ORCPT ); Sun, 30 Oct 2022 06:03:40 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:50042 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S229961AbiJ3KDi (ORCPT ); Sun, 30 Oct 2022 06:03:38 -0400 Received: from mail-ej1-x62a.google.com (mail-ej1-x62a.google.com [IPv6:2a00:1450:4864:20::62a]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 9C0CC1A1 for ; Sun, 30 Oct 2022 03:03:35 -0700 (PDT) Received: by mail-ej1-x62a.google.com with SMTP id q9so22924125ejd.0 for ; Sun, 30 Oct 2022 03:03:35 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=YuQet8vAfXYjtJovtWvfi564eTZoov1XJZh14ZhEs4I=; b=MoCV288NV6piyppcD8QDHQZaPRlAEEeT7Yj6ZPnFAwtE+/2oyx/V8GC3xznHoMvVMc DPWQScX9P/d5C29d2uKSpKixlVykUHTF5KYz4NPVrh7RE97A7wMXZWKbKfuFcFZ/ei+5 hgGz1SlDtlaUBhdDKwrHRyFOGWRcw0JPdPUQlC/gHTdIg1JQUFV+om8aDgR135H7vhCN ND+LfQZOMmyForrXMkYc7o0nzxFzdat+6qogQlDI0kJRwUfC6ofGs6+x9qLmHJLu5Hmi GOJGFOffIc8GiWEwdnHjTIekdNwedmt9R+YrRAp90+ur8pInvLPZwmReXvJeU5yx56jd s8rg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=YuQet8vAfXYjtJovtWvfi564eTZoov1XJZh14ZhEs4I=; b=efvirmk5OxpHoVm6qzQ25fUv2hNks0DAtX3GVf4jELUTNJRqLVIw9YJ7pbBXIc5oDd vLZaW9o/sP5wZso+7piHgE4A9Vv/n6bEKQUxgWo5E+J5Mpzscc0OeotP/9itnTvVkl1O PHxF4Jo326rvYxqUVITA8HNSVO0cLoXqUQs4kASODEBCF7+n+lRXqVPrude4+HInyFYz Ive55CDle1JEKXvHIThsku+GVVBZ9Mb2YImK4XLXWElYr0IWt0cusvhriZQ01exlPOEG rTCs4GSdoE9TUd4OfxMpOKhZX+WNC/kKu0n4x3eiZQ2QKKCguzoS7d8fnj/b24SHqUjt WTZQ== X-Gm-Message-State: ACrzQf1v8GVqYBjqKAq684fMJzAas6sRIVhxgKTQPQV0CVtFYaCXV5T7 zp5FgyrcWSQVnVeLtWmcNg3BqQ== X-Google-Smtp-Source: AMsMyM43ZH6ZLHLreEDFiUJ+De5VDihLm7TCNHHrB53UJ2GpWRt8sGu0+9+P99bdnq0X06yre+7vdw== X-Received: by 2002:a17:907:3f85:b0:733:3f0e:2f28 with SMTP id hr5-20020a1709073f8500b007333f0e2f28mr7174254ejc.376.1667124215019; Sun, 30 Oct 2022 03:03:35 -0700 (PDT) Received: from MBP-di-Paolo.station (net-2-35-55-161.cust.vodafonedsl.it. [2.35.55.161]) by smtp.gmail.com with ESMTPSA id d27-20020a170906305b00b0073d71792c8dsm1666088ejd.180.2022.10.30.03.03.34 (version=TLS1_2 cipher=ECDHE-ECDSA-AES128-GCM-SHA256 bits=128/128); Sun, 30 Oct 2022 03:03:34 -0700 (PDT) From: Paolo Valente To: Jens Axboe Cc: linux-block@vger.kernel.org, linux-kernel@vger.kernel.org, Paolo Valente , Gabriele Felici , Carmine Zaccagnino Subject: [PATCH V5 1/8] block, bfq: split sync bfq_queues on a per-actuator basis Date: Sun, 30 Oct 2022 11:02:53 +0100 Message-Id: <20221030100300.3085-2-paolo.valente@linaro.org> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20221030100300.3085-1-paolo.valente@linaro.org> References: <20221030100300.3085-1-paolo.valente@linaro.org> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-block@vger.kernel.org Single-LUN multi-actuator SCSI drives, as well as all multi-actuator SATA drives appear as a single device to the I/O subsystem [1]. Yet they address commands to different actuators internally, as a function of Logical Block Addressing (LBAs). A given sector is reachable by only one of the actuators. For example, Seagate’s Serial Advanced Technology Attachment (SATA) version contains two actuators and maps the lower half of the SATA LBA space to the lower actuator and the upper half to the upper actuator. Evidently, to fully utilize actuators, no actuator must be left idle or underutilized while there is pending I/O for it. The block layer must somehow control the load of each actuator individually. This commit lays the ground for allowing BFQ to provide such a per-actuator control. BFQ associates an I/O-request sync bfq_queue with each process doing synchronous I/O, or with a group of processes, in case of queue merging. Then BFQ serves one bfq_queue at a time. While in service, a bfq_queue is emptied in request-position order. Yet the same process, or group of processes, may generate I/O for different actuators. In this case, different streams of I/O (each for a different actuator) get all inserted into the same sync bfq_queue. So there is basically no individual control on when each stream is served, i.e., on when the I/O requests of the stream are picked from the bfq_queue and dispatched to the drive. This commit enables BFQ to control the service of each actuator individually for synchronous I/O, by simply splitting each sync bfq_queue into N queues, one for each actuator. In other words, a sync bfq_queue is now associated to a pair (process, actuator). As a consequence of this split, the per-queue proportional-share policy implemented by BFQ will guarantee that the sync I/O generated for each actuator, by each process, receives its fair share of service. This is just a preparatory patch. If the I/O of the same process happens to be sent to different queues, then each of these queues may undergo queue merging. To handle this event, the bfq_io_cq data structure must be properly extended. In addition, stable merging must be disabled to avoid loss of control on individual actuators. Finally, also async queues must be split. These issues are described in detail and addressed in next commits. As for this commit, although multiple per-process bfq_queues are provided, the I/O of each process or group of processes is still sent to only one queue, regardless of the actuator the I/O is for. The forwarding to distinct bfq_queues will be enabled after addressing the above issues. [1] https://www.linaro.org/blog/budget-fair-queueing-bfq-linux-io-scheduler-optimizations-for-multi-actuator-sata-hard-drives/ Signed-off-by: Gabriele Felici Signed-off-by: Carmine Zaccagnino Signed-off-by: Paolo Valente --- block/bfq-cgroup.c | 95 ++++++++++++++++------------ block/bfq-iosched.c | 151 +++++++++++++++++++++++++++++--------------- block/bfq-iosched.h | 51 ++++++++++++--- 3 files changed, 194 insertions(+), 103 deletions(-) diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c index 144bca006463..d243c429d9c0 100644 --- a/block/bfq-cgroup.c +++ b/block/bfq-cgroup.c @@ -700,6 +700,48 @@ 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) +{ + 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, 1, act_idx); + } + } +} + + /** * __bfq_bic_change_cgroup - move @bic to @bfqg. * @bfqd: the queue descriptor. @@ -714,53 +756,24 @@ 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, 0); - struct bfq_queue *sync_bfqq = bic_to_bfqq(bic, 1); struct bfq_entity *entity; + unsigned int act_idx; - if (async_bfqq) { - entity = &async_bfqq->entity; - - if (entity->sched_data != &bfqg->sched_data) { - bic_set_bfqq(bic, NULL, 0); - bfq_release_process_ref(bfqd, async_bfqq); - } - } + for (act_idx = 0; act_idx < bfqd->num_actuators; act_idx++) { + struct bfq_queue *async_bfqq = bic_to_bfqq(bic, 0, act_idx); + struct bfq_queue *sync_bfqq = bic_to_bfqq(bic, 1, act_idx); - 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; + if (async_bfqq) { + entity = &async_bfqq->entity; - /* - * 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, 1); + if (entity->sched_data != &bfqg->sched_data) { + bic_set_bfqq(bic, NULL, 0, act_idx); + bfq_release_process_ref(bfqd, async_bfqq); } } + + if (sync_bfqq) + bfq_sync_bfqq_move(bfqd, sync_bfqq, bic, bfqg, act_idx); } return bfqg; diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 7ea427817f7f..5c69394bbb65 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -377,14 +377,19 @@ 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]; + return bic->bfqq[is_sync][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) { /* * If bfqq != NULL, then a non-stable queue merge between @@ -399,7 +404,7 @@ 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; + bic->bfqq[is_sync][actuator_idx] = bfqq; if (bfqq && bic->stable_merge_bfqq == bfqq) { /* @@ -672,9 +677,9 @@ 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)) { @@ -684,14 +689,21 @@ 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; act_idx < bfqd->num_actuators; act_idx++) { + struct bfq_queue *bfqq = + bic ? bic_to_bfqq(bic, op_is_sync(opf), act_idx) : NULL; + /* + * 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) @@ -2142,7 +2154,7 @@ 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 || @@ -2454,6 +2466,16 @@ static void bfq_remove_request(struct request_queue *q, } +/* 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. + */ + return 0; +} + static bool bfq_bio_merge(struct request_queue *q, struct bio *bio, unsigned int nr_segs) { @@ -2478,7 +2500,8 @@ 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; } @@ -3174,7 +3197,7 @@ 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, 1); + bic_set_bfqq(bic, new_bfqq, 1, bfqq->actuator_idx); bfq_mark_bfqq_coop(new_bfqq); /* * new_bfqq now belongs to at least two bics (it is a shared queue): @@ -4808,11 +4831,12 @@ static struct bfq_queue *bfq_select_queue(struct bfq_data *bfqd) */ if (bfq_bfqq_wait_request(bfqq) || (bfqq->dispatched != 0 && bfq_better_to_idle(bfqq))) { + unsigned int act_idx = bfqq->actuator_idx; 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; + 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 ? + bfqq->bic->bfqq[0][act_idx] : NULL; struct bfq_queue *blocked_bfqq = !hlist_empty(&bfqq->woken_list) ? container_of(bfqq->woken_list.first, @@ -4904,7 +4928,7 @@ static struct bfq_queue *bfq_select_queue(struct bfq_data *bfqd) 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 && @@ -5365,49 +5389,59 @@ 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); bfqq->bic = NULL; bfq_exit_bfqq(bfqd, bfqq); - bic_set_bfqq(bic, NULL, is_sync); - spin_unlock_irqrestore(&bfqd->lock, flags); + bic_set_bfqq(bic, NULL, is_sync, actuator_idx); } } 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; + unsigned int num_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; + } else { /* - * bfqd is NULL if scheduler already exited, and in - * that case this is the last time bfqq is accessed. + * bfqd->num_actuators not available any longer, 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. */ - if (bfqd) { - unsigned long flags; + num_actuators = BFQ_MAX_ACTUATORS; + } - 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); - } + if (bic->stable_merge_bfqq) + 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); } /* @@ -5484,23 +5518,25 @@ 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); @@ -5739,6 +5775,7 @@ static struct bfq_queue *bfq_get_queue(struct bfq_data *bfqd, struct bfq_group *bfqg; bfqg = bfq_bio_bfqg(bfqd, bio); + if (!is_sync) { async_bfqq = bfq_async_queue_prio(bfqd, bfqg, ioprio_class, ioprio); @@ -5753,7 +5790,7 @@ 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 { @@ -6068,7 +6105,8 @@ 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), 1, + bfq_actuator_index(bfqd, rq->bio)) == bfqq) bfq_merge_bfqqs(bfqd, RQ_BIC(rq), bfqq, new_bfqq); @@ -6622,7 +6660,7 @@ bfq_split_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq) return bfqq; } - bic_set_bfqq(bic, NULL, 1); + bic_set_bfqq(bic, NULL, 1, bfqq->actuator_idx); bfq_put_cooperator(bfqq); @@ -6636,7 +6674,8 @@ 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; @@ -6648,7 +6687,7 @@ 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) @@ -7090,8 +7129,10 @@ 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; @@ -7110,6 +7151,12 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e) bfqd->queue = q; + /* + * Multi-actuator support not complete yet, default to single + * actuator for the moment. + */ + 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 71f721670ab6..bfcbd8ea9000 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 32 + struct bfq_entity; /** @@ -225,12 +233,14 @@ 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 */ @@ -395,6 +405,9 @@ 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; }; /** @@ -403,8 +416,17 @@ 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 @@ -768,6 +790,13 @@ 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 { @@ -964,8 +993,10 @@ 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_data *bfqd, struct bfq_queue *bfqq, From patchwork Sun Oct 30 10:02:54 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Paolo Valente X-Patchwork-Id: 13025051 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 9F390FA3740 for ; Sun, 30 Oct 2022 10:03:43 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S229792AbiJ3KDm (ORCPT ); Sun, 30 Oct 2022 06:03:42 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:50046 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S229663AbiJ3KDk (ORCPT ); Sun, 30 Oct 2022 06:03:40 -0400 Received: from mail-ej1-x629.google.com (mail-ej1-x629.google.com [IPv6:2a00:1450:4864:20::629]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id B5296BA0 for ; Sun, 30 Oct 2022 03:03:37 -0700 (PDT) Received: by mail-ej1-x629.google.com with SMTP id ud5so22856347ejc.4 for ; Sun, 30 Oct 2022 03:03:37 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=Dagqyailu11jgL84XY9XZ7ZO8PNuYsgn+9sY89yrA6U=; b=T9Fs+8e83L0bqfPmtM639a+YtCRBr5w4o65ZRTQeHdi6bOvQ2M+n9GYOuQdbiXrPx2 AM10J7h1PtP7OamKIIoXg2/E8f+KqVpVdjkQ4ksPCyM0UH6cLHxTsLuK0nwWhzJUBzQ4 m8r8BAzySbvyPVPufA8mmGAeTT688CWVKfHTy0lv43BgcLCQx7CkvFqULSHisNVXhcDZ gwDsKyBIXwXlEpf58IYHkos+NLInCv+yXoRsLyi3EwosNDDxFxPbnV+eyxja4CMvhyof XHAgfzscqrBXqmg28LYSe3ic1EgEYgadVLmeeKvS5/deKAD/pXnaLy5w0p0B2X64Mndh 7eYg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=Dagqyailu11jgL84XY9XZ7ZO8PNuYsgn+9sY89yrA6U=; b=qT7EYXXgJFj/znVnaSWP0wQes/AXGc5uBMBCVQhRW/nQWrnOJy0PISWvo0COibZiGk xMhw2cP8AmPtmNrb16F+0PWSILQk7tCIIqUM+kdKbSlBu7BUT9tgtV2Ll0g96/RwH5K7 aRj80KTlatX3XOo91/67K/2xpoamDESL+zYfDiocRrkj3BIfzXZvwJ1XNI8kcjeIE/ql XIEgl3TLYBlYMDVewtN+TmMMIDA7S8o4HXPOFCr7+amSl6YfEPX1ekYm0Bu4u3BEpUg5 PAhC7AfOvdEqYYhc3UsJkYEMisq3w1vITyxRMcTMkgRyOcOCYw2mZXu4XbeFq/nSIEuM 1PXw== X-Gm-Message-State: ACrzQf3mQH5VGwzEeAbIqyrNCkf6I6X4Q5aDGhpbe9kg+NHy/TNCSlwp QLn5aqkeD4jEg7URuzJaURmYZbVHQyoY/A== X-Google-Smtp-Source: AMsMyM6JhH0GebmdyqV1zMQdWueBXpI8e4sf8Rmo+d9zd2KAm/m5LgqKre84iBjX+YDXMMUqhGZgiw== X-Received: by 2002:a17:906:7949:b0:7ac:9917:90b9 with SMTP id l9-20020a170906794900b007ac991790b9mr7337741ejo.536.1667124216223; Sun, 30 Oct 2022 03:03:36 -0700 (PDT) Received: from MBP-di-Paolo.station (net-2-35-55-161.cust.vodafonedsl.it. [2.35.55.161]) by smtp.gmail.com with ESMTPSA id d27-20020a170906305b00b0073d71792c8dsm1666088ejd.180.2022.10.30.03.03.35 (version=TLS1_2 cipher=ECDHE-ECDSA-AES128-GCM-SHA256 bits=128/128); Sun, 30 Oct 2022 03:03:35 -0700 (PDT) From: Paolo Valente To: Jens Axboe Cc: linux-block@vger.kernel.org, linux-kernel@vger.kernel.org, Paolo Valente Subject: [PATCH V5 2/8] block, bfq: forbid stable merging of queues associated with different actuators Date: Sun, 30 Oct 2022 11:02:54 +0100 Message-Id: <20221030100300.3085-3-paolo.valente@linaro.org> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20221030100300.3085-1-paolo.valente@linaro.org> References: <20221030100300.3085-1-paolo.valente@linaro.org> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-block@vger.kernel.org If queues associated with different actuators are merged, then control is lost on each actuator. Therefore some actuator may be underutilized, and throughput may decrease. This problem cannot occur with basic queue merging, because the latter is triggered by spatial locality, and sectors for different actuators are not close to each other. Yet it may happen with stable merging. To address this issue, this commit prevents stable merging from occurring among queues associated with different actuators. Signed-off-by: Paolo Valente --- block/bfq-iosched.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 5c69394bbb65..ec4b0e70265f 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -5705,9 +5705,13 @@ static struct bfq_queue *bfq_do_or_sched_stable_merge(struct bfq_data *bfqd, * it has been set already, but too long ago, then move it * forward to bfqq. Finally, move also if bfqq belongs to a * different group than last_bfqq_created, or if bfqq has a - * different ioprio or ioprio_class. If none of these - * conditions holds true, then try an early stable merge or - * schedule a delayed stable merge. + * different ioprio, ioprio_class or actuator_idx. If none of + * these conditions holds true, then try an early stable merge + * or schedule a delayed stable merge. As for the condition on + * actuator_idx, the reason is that, if queues associated with + * different actuators are merged, then control is lost on + * each actuator. Therefore some actuator may be + * underutilized, and throughput may decrease. * * A delayed merge is scheduled (instead of performing an * early merge), in case bfqq might soon prove to be more @@ -5725,7 +5729,8 @@ static struct bfq_queue *bfq_do_or_sched_stable_merge(struct bfq_data *bfqd, bfqq->creation_time) || bfqq->entity.parent != last_bfqq_created->entity.parent || bfqq->ioprio != last_bfqq_created->ioprio || - bfqq->ioprio_class != last_bfqq_created->ioprio_class) + bfqq->ioprio_class != last_bfqq_created->ioprio_class || + bfqq->actuator_idx != last_bfqq_created->actuator_idx) *source_bfqq = bfqq; else if (time_after_eq(last_bfqq_created->creation_time + bfqd->bfq_burst_interval, From patchwork Sun Oct 30 10:02:55 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Paolo Valente X-Patchwork-Id: 13025052 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 200AFFA373D for ; Sun, 30 Oct 2022 10:03:45 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S229763AbiJ3KDn (ORCPT ); Sun, 30 Oct 2022 06:03:43 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:50090 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S229552AbiJ3KDl (ORCPT ); Sun, 30 Oct 2022 06:03:41 -0400 Received: from mail-ed1-x536.google.com (mail-ed1-x536.google.com [IPv6:2a00:1450:4864:20::536]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id EA34C1A9 for ; Sun, 30 Oct 2022 03:03:38 -0700 (PDT) Received: by mail-ed1-x536.google.com with SMTP id a13so13757529edj.0 for ; Sun, 30 Oct 2022 03:03:38 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=9tB9eObh3Vne5izy9wSWj1GaOcjX6R5NF7vt6yMovsw=; b=X+Wfh5H/RZeSi8Kt7fTrGwLqbc/NnXXmiagL5glKrMG0MZ0sGc4b8HpO/zrq//6pbb pNrzaLbzr8iudfQLhFBJd0uWvk/C1mHLx6ODggUzUnocmHQzWIEZHfoXyXI/imePL+vD cnYLO6C//y6Gy3f+AgXlrX6fj8X5JRPSdNqAKpdFs9UWCIX36fLbR5OydeAsw/Y0/uVj 3kBVgLjOUUL/eAzI9dre0itnsARyJa9a6tiGQmDPYfPegq5qNUSMF/2O6qo2rIF2OSsM FmgHEbXRqsQh5Vz9z2VdHtYHNCiD+JZj7TpU1vt2yFiMnamHaaqH37fh/5eAzD8vC6J9 rmOw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=9tB9eObh3Vne5izy9wSWj1GaOcjX6R5NF7vt6yMovsw=; b=ymkDfBmUp7vhfMEXxwSo6SBNpRhIPmBE9DAlgyPHOFl/9AQ0R2Ii+oqbl1GZM6ZZ0j faR5MOwv/bexIPUXDmqsTuUK7AddKnodR5Bz2S2ADWiS+1uX5h8qSEE4J4jnGZhxDAC1 5yEdmF1hm9lxEEHcyslj1UGO50RswQyH2F6XIog1agtctnPV8gQs+BMVtT5qQm2U6EXh +26tCBdIATsSiLVhkov7Q20147v6KX8fmkyeWXyaoNqO12shnJ+SlNabdpOwJrNZabKs kA9Ef6FlWIeo216ebwKP+q6feDYTSeWl0scsJlP6T77DeIbftcFWpkNxVOXEfuygkdDJ TqJg== X-Gm-Message-State: ACrzQf0NNfRwxZOJOePLwNbf74stJJhx7wu97vtarWCrDwGdLHC/TrwB IjgsUevLBtpLf3l8nB4YC0EgoA== X-Google-Smtp-Source: AMsMyM4gf9USHZSnDacnwPwQOiSdPyU/M1mh/FvolmY/yq9+Fvf9G3g/zWYazoUzh/qvqSz5/eVD1A== X-Received: by 2002:a05:6402:440d:b0:450:de54:3fcf with SMTP id y13-20020a056402440d00b00450de543fcfmr7914149eda.312.1667124217377; Sun, 30 Oct 2022 03:03:37 -0700 (PDT) Received: from MBP-di-Paolo.station (net-2-35-55-161.cust.vodafonedsl.it. [2.35.55.161]) by smtp.gmail.com with ESMTPSA id d27-20020a170906305b00b0073d71792c8dsm1666088ejd.180.2022.10.30.03.03.36 (version=TLS1_2 cipher=ECDHE-ECDSA-AES128-GCM-SHA256 bits=128/128); Sun, 30 Oct 2022 03:03:36 -0700 (PDT) From: Paolo Valente To: Jens Axboe Cc: linux-block@vger.kernel.org, linux-kernel@vger.kernel.org, Paolo Valente , Damien Le Moal , Gianmarco Lusvardi , Giulio Barabino , Emiliano Maccaferri Subject: [PATCH V5 3/8] block, bfq: move io_cq-persistent bfqq data into a dedicated struct Date: Sun, 30 Oct 2022 11:02:55 +0100 Message-Id: <20221030100300.3085-4-paolo.valente@linaro.org> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20221030100300.3085-1-paolo.valente@linaro.org> References: <20221030100300.3085-1-paolo.valente@linaro.org> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-block@vger.kernel.org With a multi-actuator drive, a process may get associated with multiple bfq_queues: one queue for each of the N actuators. So, the bfq_io_cq data structure must be able to accommodate its per-queue persistent information for N queues. Currently it stores this information for just one queue, in several scalar fields. This is a preparatory commit for moving to accommodating persistent information for N queues. In particular, this commit packs all the above scalar fields into a single data structure. Then there is now only one fieldi, in bfq_io_cq, that stores all the above information. This scalar field will then be turned into an array by a following commit. Suggested-by: Damien Le Moal Signed-off-by: Gianmarco Lusvardi Signed-off-by: Giulio Barabino Signed-off-by: Emiliano Maccaferri Signed-off-by: Paolo Valente --- block/bfq-iosched.c | 129 +++++++++++++++++++++++++------------------- block/bfq-iosched.h | 52 ++++++++++-------- 2 files changed, 105 insertions(+), 76 deletions(-) diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index ec4b0e70265f..139b8f1ba439 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -404,9 +404,10 @@ void bic_set_bfqq(struct bfq_io_cq *bic, * we cancel the stable merge if * bic->stable_merge_bfqq == bfqq. */ + struct bfq_iocq_bfqq_data bfqq_data = bic->bfqq_data; bic->bfqq[is_sync][actuator_idx] = bfqq; - if (bfqq && bic->stable_merge_bfqq == bfqq) { + if (bfqq && bfqq_data.stable_merge_bfqq == bfqq) { /* * Actually, these same instructions are executed also * in bfq_setup_cooperator, in case of abort or actual @@ -415,9 +416,9 @@ void bic_set_bfqq(struct bfq_io_cq *bic, * did so, we would nest even more complexity in this * function. */ - bfq_put_stable_ref(bic->stable_merge_bfqq); + bfq_put_stable_ref(bfqq_data.stable_merge_bfqq); - bic->stable_merge_bfqq = NULL; + bfqq_data.stable_merge_bfqq = NULL; } } @@ -1174,38 +1175,40 @@ static void bfq_bfqq_resume_state(struct bfq_queue *bfqq, struct bfq_data *bfqd, struct bfq_io_cq *bic, bool bfq_already_existing) { + struct bfq_iocq_bfqq_data bfqq_data = bic->bfqq_data; unsigned int old_wr_coeff = 1; bool busy = bfq_already_existing && bfq_bfqq_busy(bfqq); - if (bic->saved_has_short_ttime) + if (bfqq_data.saved_has_short_ttime) bfq_mark_bfqq_has_short_ttime(bfqq); else bfq_clear_bfqq_has_short_ttime(bfqq); - if (bic->saved_IO_bound) + if (bfqq_data.saved_IO_bound) bfq_mark_bfqq_IO_bound(bfqq); else bfq_clear_bfqq_IO_bound(bfqq); - bfqq->last_serv_time_ns = bic->saved_last_serv_time_ns; - bfqq->inject_limit = bic->saved_inject_limit; - bfqq->decrease_time_jif = bic->saved_decrease_time_jif; + bfqq->last_serv_time_ns = bfqq_data.saved_last_serv_time_ns; + bfqq->inject_limit = bfqq_data.saved_inject_limit; + bfqq->decrease_time_jif = bfqq_data.saved_decrease_time_jif; - bfqq->entity.new_weight = bic->saved_weight; - bfqq->ttime = bic->saved_ttime; - bfqq->io_start_time = bic->saved_io_start_time; - bfqq->tot_idle_time = bic->saved_tot_idle_time; + bfqq->entity.new_weight = bfqq_data.saved_weight; + bfqq->ttime = bfqq_data.saved_ttime; + bfqq->io_start_time = bfqq_data.saved_io_start_time; + bfqq->tot_idle_time = bfqq_data.saved_tot_idle_time; /* * Restore weight coefficient only if low_latency is on */ if (bfqd->low_latency) { old_wr_coeff = bfqq->wr_coeff; - bfqq->wr_coeff = bic->saved_wr_coeff; + bfqq->wr_coeff = bfqq_data.saved_wr_coeff; } - bfqq->service_from_wr = bic->saved_service_from_wr; - bfqq->wr_start_at_switch_to_srt = bic->saved_wr_start_at_switch_to_srt; - bfqq->last_wr_start_finish = bic->saved_last_wr_start_finish; - bfqq->wr_cur_max_time = bic->saved_wr_cur_max_time; + bfqq->service_from_wr = bfqq_data.saved_service_from_wr; + bfqq->wr_start_at_switch_to_srt = + bfqq_data.saved_wr_start_at_switch_to_srt; + bfqq->last_wr_start_finish = bfqq_data.saved_last_wr_start_finish; + bfqq->wr_cur_max_time = bfqq_data.saved_wr_cur_max_time; if (bfqq->wr_coeff > 1 && (bfq_bfqq_in_large_burst(bfqq) || time_is_before_jiffies(bfqq->last_wr_start_finish + @@ -1878,7 +1881,7 @@ static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd, wr_or_deserves_wr = bfqd->low_latency && (bfqq->wr_coeff > 1 || (bfq_bfqq_sync(bfqq) && - (bfqq->bic || RQ_BIC(rq)->stably_merged) && + (bfqq->bic || RQ_BIC(rq)->bfqq_data.stably_merged) && (*interactive || soft_rt))); /* @@ -2902,6 +2905,7 @@ bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq, void *io_struct, bool request, struct bfq_io_cq *bic) { struct bfq_queue *in_service_bfqq, *new_bfqq; + struct bfq_iocq_bfqq_data bfqq_data = bic->bfqq_data; /* if a merge has already been setup, then proceed with that first */ if (bfqq->new_bfqq) @@ -2923,21 +2927,21 @@ bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq, * stable merging) also if bic is associated with a * sync queue, but this bfqq is async */ - if (bfq_bfqq_sync(bfqq) && bic->stable_merge_bfqq && + if (bfq_bfqq_sync(bfqq) && bfqq_data.stable_merge_bfqq && !bfq_bfqq_just_created(bfqq) && time_is_before_jiffies(bfqq->split_time + msecs_to_jiffies(bfq_late_stable_merging)) && time_is_before_jiffies(bfqq->creation_time + msecs_to_jiffies(bfq_late_stable_merging))) { struct bfq_queue *stable_merge_bfqq = - bic->stable_merge_bfqq; + bfqq_data.stable_merge_bfqq; int proc_ref = min(bfqq_process_refs(bfqq), bfqq_process_refs(stable_merge_bfqq)); /* deschedule stable merge, because done or aborted here */ bfq_put_stable_ref(stable_merge_bfqq); - bic->stable_merge_bfqq = NULL; + bfqq_data.stable_merge_bfqq = NULL; if (!idling_boosts_thr_without_issues(bfqd, bfqq) && proc_ref > 0) { @@ -2946,10 +2950,10 @@ bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq, bfq_setup_merge(bfqq, stable_merge_bfqq); if (new_bfqq) { - bic->stably_merged = true; + bfqq_data.stably_merged = true; if (new_bfqq->bic) - new_bfqq->bic->stably_merged = - true; + new_bfqq->bic->bfqq_data.stably_merged = + true; } return new_bfqq; } else @@ -3048,6 +3052,7 @@ bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq, static void bfq_bfqq_save_state(struct bfq_queue *bfqq) { struct bfq_io_cq *bic = bfqq->bic; + struct bfq_iocq_bfqq_data bfqq_data = bic->bfqq_data; /* * If !bfqq->bic, the queue is already shared or its requests @@ -3057,18 +3062,21 @@ static void bfq_bfqq_save_state(struct bfq_queue *bfqq) if (!bic) return; - bic->saved_last_serv_time_ns = bfqq->last_serv_time_ns; - bic->saved_inject_limit = bfqq->inject_limit; - bic->saved_decrease_time_jif = bfqq->decrease_time_jif; - - bic->saved_weight = bfqq->entity.orig_weight; - bic->saved_ttime = bfqq->ttime; - bic->saved_has_short_ttime = bfq_bfqq_has_short_ttime(bfqq); - bic->saved_IO_bound = bfq_bfqq_IO_bound(bfqq); - bic->saved_io_start_time = bfqq->io_start_time; - bic->saved_tot_idle_time = bfqq->tot_idle_time; - bic->saved_in_large_burst = bfq_bfqq_in_large_burst(bfqq); - bic->was_in_burst_list = !hlist_unhashed(&bfqq->burst_list_node); + bfqq_data.saved_last_serv_time_ns = bfqq->last_serv_time_ns; + bfqq_data.saved_inject_limit = bfqq->inject_limit; + bfqq_data.saved_decrease_time_jif = bfqq->decrease_time_jif; + + bfqq_data.saved_weight = bfqq->entity.orig_weight; + bfqq_data.saved_ttime = bfqq->ttime; + bfqq_data.saved_has_short_ttime = + bfq_bfqq_has_short_ttime(bfqq); + bfqq_data.saved_IO_bound = bfq_bfqq_IO_bound(bfqq); + bfqq_data.saved_io_start_time = bfqq->io_start_time; + bfqq_data.saved_tot_idle_time = bfqq->tot_idle_time; + bfqq_data.saved_in_large_burst = bfq_bfqq_in_large_burst(bfqq); + bfqq_data.was_in_burst_list = + !hlist_unhashed(&bfqq->burst_list_node); + if (unlikely(bfq_bfqq_just_created(bfqq) && !bfq_bfqq_in_large_burst(bfqq) && bfqq->bfqd->low_latency)) { @@ -3081,17 +3089,21 @@ static void bfq_bfqq_save_state(struct bfq_queue *bfqq) * to bfqq, so that to avoid that bfqq unjustly fails * to enjoy weight raising if split soon. */ - bic->saved_wr_coeff = bfqq->bfqd->bfq_wr_coeff; - bic->saved_wr_start_at_switch_to_srt = bfq_smallest_from_now(); - bic->saved_wr_cur_max_time = bfq_wr_duration(bfqq->bfqd); - bic->saved_last_wr_start_finish = jiffies; + bfqq_data.saved_wr_coeff = bfqq->bfqd->bfq_wr_coeff; + bfqq_data.saved_wr_start_at_switch_to_srt = + bfq_smallest_from_now(); + bfqq_data.saved_wr_cur_max_time = + bfq_wr_duration(bfqq->bfqd); + bfqq_data.saved_last_wr_start_finish = jiffies; } else { - bic->saved_wr_coeff = bfqq->wr_coeff; - bic->saved_wr_start_at_switch_to_srt = + bfqq_data.saved_wr_coeff = bfqq->wr_coeff; + bfqq_data.saved_wr_start_at_switch_to_srt = bfqq->wr_start_at_switch_to_srt; - bic->saved_service_from_wr = bfqq->service_from_wr; - bic->saved_last_wr_start_finish = bfqq->last_wr_start_finish; - bic->saved_wr_cur_max_time = bfqq->wr_cur_max_time; + bfqq_data.saved_service_from_wr = + bfqq->service_from_wr; + bfqq_data.saved_last_wr_start_finish = + bfqq->last_wr_start_finish; + bfqq_data.saved_wr_cur_max_time = bfqq->wr_cur_max_time; } } @@ -5413,6 +5425,7 @@ static void bfq_exit_icq(struct io_cq *icq) unsigned long flags; unsigned int act_idx; unsigned int num_actuators; + struct bfq_iocq_bfqq_data bfqq_data = bic->bfqq_data; /* * bfqd is NULL if scheduler already exited, and in that case @@ -5432,8 +5445,8 @@ static void bfq_exit_icq(struct io_cq *icq) num_actuators = BFQ_MAX_ACTUATORS; } - if (bic->stable_merge_bfqq) - bfq_put_stable_ref(bic->stable_merge_bfqq); + if (bfqq_data.stable_merge_bfqq) + bfq_put_stable_ref(bfqq_data.stable_merge_bfqq); for (act_idx = 0; act_idx < num_actuators; act_idx++) { bfq_exit_icq_bfqq(bic, true, act_idx); @@ -5624,13 +5637,14 @@ bfq_do_early_stable_merge(struct bfq_data *bfqd, struct bfq_queue *bfqq, { struct bfq_queue *new_bfqq = bfq_setup_merge(bfqq, last_bfqq_created); + struct bfq_iocq_bfqq_data bfqq_data = bic->bfqq_data; if (!new_bfqq) return bfqq; if (new_bfqq->bic) - new_bfqq->bic->stably_merged = true; - bic->stably_merged = true; + new_bfqq->bic->bfqq_data.stably_merged = true; + bfqq_data.stably_merged = true; /* * Reusing merge functions. This implies that @@ -5699,6 +5713,7 @@ static struct bfq_queue *bfq_do_or_sched_stable_merge(struct bfq_data *bfqd, &bfqd->last_bfqq_created; struct bfq_queue *last_bfqq_created = *source_bfqq; + struct bfq_iocq_bfqq_data bfqq_data = bic->bfqq_data; /* * If last_bfqq_created has not been set yet, then init it. If @@ -5760,7 +5775,7 @@ static struct bfq_queue *bfq_do_or_sched_stable_merge(struct bfq_data *bfqd, /* * Record the bfqq to merge to. */ - bic->stable_merge_bfqq = last_bfqq_created; + bfqq_data.stable_merge_bfqq = last_bfqq_created; } } @@ -6681,6 +6696,7 @@ static struct bfq_queue *bfq_get_bfqq_handle_split(struct bfq_data *bfqd, { unsigned int act_idx = bfq_actuator_index(bfqd, bio); struct bfq_queue *bfqq = bic_to_bfqq(bic, is_sync, act_idx); + struct bfq_iocq_bfqq_data bfqq_data = bic->bfqq_data; if (likely(bfqq && bfqq != &bfqd->oom_bfqq)) return bfqq; @@ -6694,12 +6710,12 @@ static struct bfq_queue *bfq_get_bfqq_handle_split(struct bfq_data *bfqd, 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) + if ((bfqq_data.was_in_burst_list && bfqd->large_burst) || + bfqq_data.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) + if (bfqq_data.was_in_burst_list) /* * If bfqq was in the current * burst list before being @@ -6788,6 +6804,7 @@ static struct bfq_queue *bfq_init_rq(struct request *rq) struct bfq_queue *bfqq; bool new_queue = false; bool bfqq_already_existing = false, split = false; + struct bfq_iocq_bfqq_data bfqq_data; if (unlikely(!rq->elv.icq)) return NULL; @@ -6811,15 +6828,17 @@ static struct bfq_queue *bfq_init_rq(struct request *rq) bfqq = bfq_get_bfqq_handle_split(bfqd, bic, bio, false, is_sync, &new_queue); + bfqq_data = bic->bfqq_data; + if (likely(!new_queue)) { /* If the queue was seeky for too long, break it apart. */ if (bfq_bfqq_coop(bfqq) && bfq_bfqq_split_coop(bfqq) && - !bic->stably_merged) { + !bfqq_data.stably_merged) { struct bfq_queue *old_bfqq = bfqq; /* Update bic before losing reference to bfqq */ if (bfq_bfqq_in_large_burst(bfqq)) - bic->saved_in_large_burst = true; + bfqq_data.saved_in_large_burst = true; bfqq = bfq_split_bfqq(bic, bfqq); split = true; diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h index bfcbd8ea9000..f2e8ab91951c 100644 --- a/block/bfq-iosched.h +++ b/block/bfq-iosched.h @@ -411,27 +411,9 @@ struct bfq_queue { }; /** - * struct bfq_io_cq - per (request_queue, io_context) structure. - */ -struct bfq_io_cq { - /* associated io_cq structure */ - struct io_cq icq; /* must be the first member */ - /* - * 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 - uint64_t blkcg_serial_nr; /* the current blkcg serial */ -#endif +* struct bfq_data - bfqq data unique and persistent for associated bfq_io_cq +*/ +struct bfq_iocq_bfqq_data { /* * Snapshot of the has_short_time flag before merging; taken * to remember its value while the queue is merged, so as to @@ -486,6 +468,34 @@ struct bfq_io_cq { struct bfq_queue *stable_merge_bfqq; bool stably_merged; /* non splittable if true */ +}; + +/** + * struct bfq_io_cq - per (request_queue, io_context) structure. + */ +struct bfq_io_cq { + /* associated io_cq structure */ + struct io_cq icq; /* must be the first member */ + /* + * 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 + uint64_t blkcg_serial_nr; /* the current blkcg serial */ +#endif + + /* persistent data for associated synchronous process queue */ + struct bfq_iocq_bfqq_data bfqq_data; + unsigned int requests; /* Number of requests this process has in flight */ }; From patchwork Sun Oct 30 10:02:56 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Paolo Valente X-Patchwork-Id: 13025054 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 85E25FA3740 for ; Sun, 30 Oct 2022 10:03:46 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S230049AbiJ3KDn (ORCPT ); Sun, 30 Oct 2022 06:03:43 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:50090 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S230038AbiJ3KDm (ORCPT ); Sun, 30 Oct 2022 06:03:42 -0400 Received: from mail-ej1-x635.google.com (mail-ej1-x635.google.com [IPv6:2a00:1450:4864:20::635]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 52B4223E for ; Sun, 30 Oct 2022 03:03:40 -0700 (PDT) Received: by mail-ej1-x635.google.com with SMTP id f27so22836171eje.1 for ; Sun, 30 Oct 2022 03:03:40 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=5a6As9UVgwj6yXvVVDplGTtGvsy9ujSwGGjDgxJRrts=; b=eawdJckTVbzkCIQZ9+YQ2zSimtcKcyQ9pF8VtJQM5MQeCtJ8AU6l5ZV7fKJBs+Lnua Y/kn6HGxkU2gbPRz9PnUS9y7CUJJja+Y8MtP6C1gaYzXmSOKd4VIxSPRgw7CX/qADpZE oASeB/K71mfwwFI4zkqFL9xej8aAgJYn8ILBJbIcEKkU2c1lwPbVB+/u9giAPlm0Qx0o woUSqechGR57X/GeWGQQZpXuobjoXaV+paaRZBKj5I9w9UMq1b2dTu+tvFLcHBUiMtWo jVdyY2GEYUu+aP7WNBzjKvYSOEn3iEZDMZsdDggu5Ka6Ki0BaIgQ0sqJPT55zK3iEZLf 56/g== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=5a6As9UVgwj6yXvVVDplGTtGvsy9ujSwGGjDgxJRrts=; b=4zRex5S44Di7V6n37KIp4Y5gcDCTrY6ZQ8LxACcwPhiYKaPc0nZZIANFUvWXGGeuXc CXmk4o+XjTHPkoQO3WJ/Y2khHByS1hxLI5hg1mXzsQwv0bEyUsOE+7TxLkgmHFViJiJU wFdTShLa2nRTZ4uJmXVQdCpCt68ExxoxLlsOf3l5t+1AbTuu3cb+taH9v4mN6YUvnp3e mYO0ahHiDCnMmPCq0t7mpbnQYoygVF2rV35Cc8Z9q2N5uHiaSr3b0It/45dUwXhP9DQB M1W7GqUVs+trBE4bPslqZhWEtFeW8H3VwRAXZePGzEL/UDlPzu8iODAUe4HY/vbNhN3U MSxA== X-Gm-Message-State: ACrzQf1Mhn3hm88ItbA4frUS1InrmX+j9rbHkAD1x2/RMCwe2gBvIvfn RGOb8KYtsBNRAI6YwbHjJc8RNpzOcWR5ww== X-Google-Smtp-Source: AMsMyM4Xg7yIPyhOs9G3PMOkyRBM+6GNXim4zkaMqO8dHsxnSmWy+sxFCm4FMBAt+/NnbhlAjzNRGg== X-Received: by 2002:a17:907:7621:b0:741:6656:bd14 with SMTP id jy1-20020a170907762100b007416656bd14mr7416763ejc.298.1667124218755; Sun, 30 Oct 2022 03:03:38 -0700 (PDT) Received: from MBP-di-Paolo.station (net-2-35-55-161.cust.vodafonedsl.it. [2.35.55.161]) by smtp.gmail.com with ESMTPSA id d27-20020a170906305b00b0073d71792c8dsm1666088ejd.180.2022.10.30.03.03.37 (version=TLS1_2 cipher=ECDHE-ECDSA-AES128-GCM-SHA256 bits=128/128); Sun, 30 Oct 2022 03:03:38 -0700 (PDT) From: Paolo Valente To: Jens Axboe Cc: linux-block@vger.kernel.org, linux-kernel@vger.kernel.org, Paolo Valente , Gabriele Felici , Gianmarco Lusvardi , Giulio Barabino , Emiliano Maccaferri Subject: [PATCH V5 4/8] block, bfq: turn bfqq_data into an array in bfq_io_cq Date: Sun, 30 Oct 2022 11:02:56 +0100 Message-Id: <20221030100300.3085-5-paolo.valente@linaro.org> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20221030100300.3085-1-paolo.valente@linaro.org> References: <20221030100300.3085-1-paolo.valente@linaro.org> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-block@vger.kernel.org When a bfq_queue Q is merged with another queue, several pieces of information are saved about Q. These pieces are stored in the bfqq_data field in the bfq_io_cq data structure of the process associated with Q. Yet, with a multi-actuator drive, a process may get associated with multiple bfq_queues: one queue for each of the N actuators. Each of these queues may undergo a merge. So, the bfq_io_cq data structure must be able to accommodate the above information for N queues. This commit solves this problem by turning the bfqq_data scalar field into an array of N elements (and by changing code so as to handle this array). This solution is written under the assumption that bfq_queues associated with different actuators cannot be cross-merged. This assumption holds naturally with basic queue merging: the latter is triggered by spatial locality, and sectors for different actuators are not close to each other. As for stable cross-merging, the assumption here is that it is disabled. Signed-off-by: Gabriele Felici Signed-off-by: Gianmarco Lusvardi Signed-off-by: Giulio Barabino Signed-off-by: Emiliano Maccaferri Signed-off-by: Paolo Valente --- block/bfq-iosched.c | 170 ++++++++++++++++++++++++-------------------- block/bfq-iosched.h | 12 ++-- 2 files changed, 101 insertions(+), 81 deletions(-) diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 139b8f1ba439..bfdf954da5b7 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -404,10 +404,10 @@ void bic_set_bfqq(struct bfq_io_cq *bic, * we cancel the stable merge if * bic->stable_merge_bfqq == bfqq. */ - struct bfq_iocq_bfqq_data bfqq_data = bic->bfqq_data; + struct bfq_iocq_bfqq_data *bfqq_data = &bic->bfqq_data[actuator_idx]; bic->bfqq[is_sync][actuator_idx] = bfqq; - if (bfqq && bfqq_data.stable_merge_bfqq == bfqq) { + if (bfqq && bfqq_data->stable_merge_bfqq == bfqq) { /* * Actually, these same instructions are executed also * in bfq_setup_cooperator, in case of abort or actual @@ -416,9 +416,9 @@ void bic_set_bfqq(struct bfq_io_cq *bic, * did so, we would nest even more complexity in this * function. */ - bfq_put_stable_ref(bfqq_data.stable_merge_bfqq); + bfq_put_stable_ref(bfqq_data->stable_merge_bfqq); - bfqq_data.stable_merge_bfqq = NULL; + bfqq_data->stable_merge_bfqq = NULL; } } @@ -1175,40 +1175,43 @@ static void bfq_bfqq_resume_state(struct bfq_queue *bfqq, struct bfq_data *bfqd, struct bfq_io_cq *bic, bool bfq_already_existing) { - struct bfq_iocq_bfqq_data bfqq_data = bic->bfqq_data; unsigned int old_wr_coeff = 1; bool busy = bfq_already_existing && bfq_bfqq_busy(bfqq); + unsigned int a_idx = bfqq->actuator_idx; + struct bfq_iocq_bfqq_data *bfqq_data = &bic->bfqq_data[a_idx]; - if (bfqq_data.saved_has_short_ttime) + if (bfqq_data->saved_has_short_ttime) bfq_mark_bfqq_has_short_ttime(bfqq); else bfq_clear_bfqq_has_short_ttime(bfqq); - if (bfqq_data.saved_IO_bound) + if (bfqq_data->saved_IO_bound) bfq_mark_bfqq_IO_bound(bfqq); else bfq_clear_bfqq_IO_bound(bfqq); - bfqq->last_serv_time_ns = bfqq_data.saved_last_serv_time_ns; - bfqq->inject_limit = bfqq_data.saved_inject_limit; - bfqq->decrease_time_jif = bfqq_data.saved_decrease_time_jif; - - bfqq->entity.new_weight = bfqq_data.saved_weight; - bfqq->ttime = bfqq_data.saved_ttime; - bfqq->io_start_time = bfqq_data.saved_io_start_time; - bfqq->tot_idle_time = bfqq_data.saved_tot_idle_time; + bfqq->last_serv_time_ns = + bfqq_data->saved_last_serv_time_ns; + bfqq->inject_limit = bfqq_data->saved_inject_limit; + bfqq->decrease_time_jif = + bfqq_data->saved_decrease_time_jif; + bfqq->entity.new_weight = bfqq_data->saved_weight; + bfqq->ttime = bfqq_data->saved_ttime; + bfqq->io_start_time = bfqq_data->saved_io_start_time; + bfqq->tot_idle_time = bfqq_data->saved_tot_idle_time; /* * Restore weight coefficient only if low_latency is on */ if (bfqd->low_latency) { old_wr_coeff = bfqq->wr_coeff; - bfqq->wr_coeff = bfqq_data.saved_wr_coeff; + bfqq->wr_coeff = bfqq_data->saved_wr_coeff; } - bfqq->service_from_wr = bfqq_data.saved_service_from_wr; + bfqq->service_from_wr = bfqq_data->saved_service_from_wr; bfqq->wr_start_at_switch_to_srt = - bfqq_data.saved_wr_start_at_switch_to_srt; - bfqq->last_wr_start_finish = bfqq_data.saved_last_wr_start_finish; - bfqq->wr_cur_max_time = bfqq_data.saved_wr_cur_max_time; + bfqq_data->saved_wr_start_at_switch_to_srt; + bfqq->last_wr_start_finish = + bfqq_data->saved_last_wr_start_finish; + bfqq->wr_cur_max_time = bfqq_data->saved_wr_cur_max_time; if (bfqq->wr_coeff > 1 && (bfq_bfqq_in_large_burst(bfqq) || time_is_before_jiffies(bfqq->last_wr_start_finish + @@ -1827,6 +1830,16 @@ 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. + */ + return 0; +} + static bool bfq_better_to_idle(struct bfq_queue *bfqq); static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd, @@ -1881,7 +1894,9 @@ static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd, wr_or_deserves_wr = bfqd->low_latency && (bfqq->wr_coeff > 1 || (bfq_bfqq_sync(bfqq) && - (bfqq->bic || RQ_BIC(rq)->bfqq_data.stably_merged) && + (bfqq->bic || + RQ_BIC(rq)->bfqq_data[bfq_actuator_index(bfqd, rq->bio)] + .stably_merged) && (*interactive || soft_rt))); /* @@ -2469,16 +2484,6 @@ static void bfq_remove_request(struct request_queue *q, } -/* 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. - */ - return 0; -} - static bool bfq_bio_merge(struct request_queue *q, struct bio *bio, unsigned int nr_segs) { @@ -2905,7 +2910,8 @@ bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq, void *io_struct, bool request, struct bfq_io_cq *bic) { struct bfq_queue *in_service_bfqq, *new_bfqq; - struct bfq_iocq_bfqq_data bfqq_data = bic->bfqq_data; + unsigned int a_idx = bfqq->actuator_idx; + struct bfq_iocq_bfqq_data *bfqq_data = &bic->bfqq_data[a_idx]; /* if a merge has already been setup, then proceed with that first */ if (bfqq->new_bfqq) @@ -2927,21 +2933,22 @@ bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq, * stable merging) also if bic is associated with a * sync queue, but this bfqq is async */ - if (bfq_bfqq_sync(bfqq) && bfqq_data.stable_merge_bfqq && + if (bfq_bfqq_sync(bfqq) && + bfqq_data->stable_merge_bfqq && !bfq_bfqq_just_created(bfqq) && time_is_before_jiffies(bfqq->split_time + msecs_to_jiffies(bfq_late_stable_merging)) && time_is_before_jiffies(bfqq->creation_time + msecs_to_jiffies(bfq_late_stable_merging))) { struct bfq_queue *stable_merge_bfqq = - bfqq_data.stable_merge_bfqq; + bfqq_data->stable_merge_bfqq; int proc_ref = min(bfqq_process_refs(bfqq), bfqq_process_refs(stable_merge_bfqq)); /* deschedule stable merge, because done or aborted here */ bfq_put_stable_ref(stable_merge_bfqq); - bfqq_data.stable_merge_bfqq = NULL; + bfqq_data->stable_merge_bfqq = NULL; if (!idling_boosts_thr_without_issues(bfqd, bfqq) && proc_ref > 0) { @@ -2950,10 +2957,11 @@ bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq, bfq_setup_merge(bfqq, stable_merge_bfqq); if (new_bfqq) { - bfqq_data.stably_merged = true; + bfqq_data->stably_merged = true; if (new_bfqq->bic) - new_bfqq->bic->bfqq_data.stably_merged = - true; + new_bfqq->bic->bfqq_data + [new_bfqq->actuator_idx] + .stably_merged = true; } return new_bfqq; } else @@ -3052,7 +3060,9 @@ bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq, static void bfq_bfqq_save_state(struct bfq_queue *bfqq) { struct bfq_io_cq *bic = bfqq->bic; - struct bfq_iocq_bfqq_data bfqq_data = bic->bfqq_data; + /* State must be saved for the right queue index. */ + unsigned int a_idx = bfqq->actuator_idx; + struct bfq_iocq_bfqq_data *bfqq_data = &bic->bfqq_data[a_idx]; /* * If !bfqq->bic, the queue is already shared or its requests @@ -3062,19 +3072,23 @@ static void bfq_bfqq_save_state(struct bfq_queue *bfqq) if (!bic) return; - bfqq_data.saved_last_serv_time_ns = bfqq->last_serv_time_ns; - bfqq_data.saved_inject_limit = bfqq->inject_limit; - bfqq_data.saved_decrease_time_jif = bfqq->decrease_time_jif; + bfqq_data->saved_last_serv_time_ns = + bfqq->last_serv_time_ns; + bfqq_data->saved_inject_limit = + bfqq->inject_limit; + bfqq_data->saved_decrease_time_jif = + bfqq->decrease_time_jif; - bfqq_data.saved_weight = bfqq->entity.orig_weight; - bfqq_data.saved_ttime = bfqq->ttime; - bfqq_data.saved_has_short_ttime = + bfqq_data->saved_weight = bfqq->entity.orig_weight; + bfqq_data->saved_ttime = bfqq->ttime; + bfqq_data->saved_has_short_ttime = bfq_bfqq_has_short_ttime(bfqq); - bfqq_data.saved_IO_bound = bfq_bfqq_IO_bound(bfqq); - bfqq_data.saved_io_start_time = bfqq->io_start_time; - bfqq_data.saved_tot_idle_time = bfqq->tot_idle_time; - bfqq_data.saved_in_large_burst = bfq_bfqq_in_large_burst(bfqq); - bfqq_data.was_in_burst_list = + bfqq_data->saved_IO_bound = bfq_bfqq_IO_bound(bfqq); + bfqq_data->saved_io_start_time = bfqq->io_start_time; + bfqq_data->saved_tot_idle_time = bfqq->tot_idle_time; + bfqq_data->saved_in_large_burst = + bfq_bfqq_in_large_burst(bfqq); + bfqq_data->was_in_burst_list = !hlist_unhashed(&bfqq->burst_list_node); if (unlikely(bfq_bfqq_just_created(bfqq) && @@ -3089,21 +3103,23 @@ static void bfq_bfqq_save_state(struct bfq_queue *bfqq) * to bfqq, so that to avoid that bfqq unjustly fails * to enjoy weight raising if split soon. */ - bfqq_data.saved_wr_coeff = bfqq->bfqd->bfq_wr_coeff; - bfqq_data.saved_wr_start_at_switch_to_srt = + bfqq_data->saved_wr_coeff = + bfqq->bfqd->bfq_wr_coeff; + bfqq_data->saved_wr_start_at_switch_to_srt = bfq_smallest_from_now(); - bfqq_data.saved_wr_cur_max_time = + bfqq_data->saved_wr_cur_max_time = bfq_wr_duration(bfqq->bfqd); - bfqq_data.saved_last_wr_start_finish = jiffies; + bfqq_data->saved_last_wr_start_finish = jiffies; } else { - bfqq_data.saved_wr_coeff = bfqq->wr_coeff; - bfqq_data.saved_wr_start_at_switch_to_srt = + bfqq_data->saved_wr_coeff = bfqq->wr_coeff; + bfqq_data->saved_wr_start_at_switch_to_srt = bfqq->wr_start_at_switch_to_srt; - bfqq_data.saved_service_from_wr = + bfqq_data->saved_service_from_wr = bfqq->service_from_wr; - bfqq_data.saved_last_wr_start_finish = + bfqq_data->saved_last_wr_start_finish = bfqq->last_wr_start_finish; - bfqq_data.saved_wr_cur_max_time = bfqq->wr_cur_max_time; + bfqq_data->saved_wr_cur_max_time = + bfqq->wr_cur_max_time; } } @@ -5425,7 +5441,7 @@ static void bfq_exit_icq(struct io_cq *icq) unsigned long flags; unsigned int act_idx; unsigned int num_actuators; - struct bfq_iocq_bfqq_data bfqq_data = bic->bfqq_data; + struct bfq_iocq_bfqq_data *bfqq_data = bic->bfqq_data; /* * bfqd is NULL if scheduler already exited, and in that case @@ -5445,10 +5461,10 @@ static void bfq_exit_icq(struct io_cq *icq) num_actuators = BFQ_MAX_ACTUATORS; } - if (bfqq_data.stable_merge_bfqq) - bfq_put_stable_ref(bfqq_data.stable_merge_bfqq); - for (act_idx = 0; act_idx < num_actuators; act_idx++) { + if (bfqq_data[act_idx].stable_merge_bfqq) + bfq_put_stable_ref(bfqq_data[act_idx].stable_merge_bfqq); + bfq_exit_icq_bfqq(bic, true, act_idx); bfq_exit_icq_bfqq(bic, false, act_idx); } @@ -5635,16 +5651,16 @@ bfq_do_early_stable_merge(struct bfq_data *bfqd, struct bfq_queue *bfqq, struct bfq_io_cq *bic, struct bfq_queue *last_bfqq_created) { + unsigned int a_idx = last_bfqq_created->actuator_idx; struct bfq_queue *new_bfqq = bfq_setup_merge(bfqq, last_bfqq_created); - struct bfq_iocq_bfqq_data bfqq_data = bic->bfqq_data; if (!new_bfqq) return bfqq; if (new_bfqq->bic) - new_bfqq->bic->bfqq_data.stably_merged = true; - bfqq_data.stably_merged = true; + new_bfqq->bic->bfqq_data[a_idx].stably_merged = true; + bic->bfqq_data[a_idx].stably_merged = true; /* * Reusing merge functions. This implies that @@ -5713,7 +5729,6 @@ static struct bfq_queue *bfq_do_or_sched_stable_merge(struct bfq_data *bfqd, &bfqd->last_bfqq_created; struct bfq_queue *last_bfqq_created = *source_bfqq; - struct bfq_iocq_bfqq_data bfqq_data = bic->bfqq_data; /* * If last_bfqq_created has not been set yet, then init it. If @@ -5775,7 +5790,8 @@ static struct bfq_queue *bfq_do_or_sched_stable_merge(struct bfq_data *bfqd, /* * Record the bfqq to merge to. */ - bfqq_data.stable_merge_bfqq = last_bfqq_created; + bic->bfqq_data[last_bfqq_created->actuator_idx].stable_merge_bfqq = + last_bfqq_created; } } @@ -6696,7 +6712,7 @@ static struct bfq_queue *bfq_get_bfqq_handle_split(struct bfq_data *bfqd, { unsigned int act_idx = bfq_actuator_index(bfqd, bio); struct bfq_queue *bfqq = bic_to_bfqq(bic, is_sync, act_idx); - struct bfq_iocq_bfqq_data bfqq_data = bic->bfqq_data; + struct bfq_iocq_bfqq_data *bfqq_data = &bic->bfqq_data[act_idx]; if (likely(bfqq && bfqq != &bfqd->oom_bfqq)) return bfqq; @@ -6710,12 +6726,13 @@ static struct bfq_queue *bfq_get_bfqq_handle_split(struct bfq_data *bfqd, bic_set_bfqq(bic, bfqq, is_sync, act_idx); if (split && is_sync) { - if ((bfqq_data.was_in_burst_list && bfqd->large_burst) || - bfqq_data.saved_in_large_burst) + if ((bfqq_data->was_in_burst_list && + bfqd->large_burst) || + bfqq_data->saved_in_large_burst) bfq_mark_bfqq_in_large_burst(bfqq); else { bfq_clear_bfqq_in_large_burst(bfqq); - if (bfqq_data.was_in_burst_list) + if (bfqq_data->was_in_burst_list) /* * If bfqq was in the current * burst list before being @@ -6804,7 +6821,7 @@ static struct bfq_queue *bfq_init_rq(struct request *rq) struct bfq_queue *bfqq; bool new_queue = false; bool bfqq_already_existing = false, split = false; - struct bfq_iocq_bfqq_data bfqq_data; + unsigned int a_idx = bfq_actuator_index(bfqd, bio); if (unlikely(!rq->elv.icq)) return NULL; @@ -6828,17 +6845,16 @@ static struct bfq_queue *bfq_init_rq(struct request *rq) bfqq = bfq_get_bfqq_handle_split(bfqd, bic, bio, false, is_sync, &new_queue); - bfqq_data = bic->bfqq_data; - if (likely(!new_queue)) { /* If the queue was seeky for too long, break it apart. */ if (bfq_bfqq_coop(bfqq) && bfq_bfqq_split_coop(bfqq) && - !bfqq_data.stably_merged) { + !bic->bfqq_data[a_idx].stably_merged) { struct bfq_queue *old_bfqq = bfqq; /* Update bic before losing reference to bfqq */ if (bfq_bfqq_in_large_burst(bfqq)) - bfqq_data.saved_in_large_burst = true; + bic->bfqq_data[a_idx].saved_in_large_burst = + true; bfqq = bfq_split_bfqq(bic, bfqq); split = true; diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h index f2e8ab91951c..e27897d66a0f 100644 --- a/block/bfq-iosched.h +++ b/block/bfq-iosched.h @@ -416,7 +416,7 @@ struct bfq_queue { struct bfq_iocq_bfqq_data { /* * Snapshot of the has_short_time flag before merging; taken - * to remember its value while the queue is merged, so as to + * to remember its values while the queue is merged, so as to * be able to restore it in case of split. */ bool saved_has_short_ttime; @@ -430,7 +430,7 @@ struct bfq_iocq_bfqq_data { u64 saved_tot_idle_time; /* - * Same purpose as the previous fields for the value of the + * Same purpose as the previous fields for the values of the * field keeping the queue's belonging to a large burst */ bool saved_in_large_burst; @@ -493,8 +493,12 @@ struct bfq_io_cq { uint64_t blkcg_serial_nr; /* the current blkcg serial */ #endif - /* persistent data for associated synchronous process queue */ - struct bfq_iocq_bfqq_data bfqq_data; + /* + * Persistent data for associated synchronous process queues + * (one queue per actuator, see field bfqq above). In + * particular, each of these queues may undergo a merge. + */ + struct bfq_iocq_bfqq_data bfqq_data[BFQ_MAX_ACTUATORS]; unsigned int requests; /* Number of requests this process has in flight */ }; From patchwork Sun Oct 30 10:02:57 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Paolo Valente X-Patchwork-Id: 13025053 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 8B616FA3744 for ; Sun, 30 Oct 2022 10:03:47 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S230037AbiJ3KDp (ORCPT ); Sun, 30 Oct 2022 06:03:45 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:50124 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S229744AbiJ3KDm (ORCPT ); Sun, 30 Oct 2022 06:03:42 -0400 Received: from mail-ed1-x52f.google.com (mail-ed1-x52f.google.com [IPv6:2a00:1450:4864:20::52f]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 4E3C5194 for ; Sun, 30 Oct 2022 03:03:41 -0700 (PDT) Received: by mail-ed1-x52f.google.com with SMTP id z18so8698841edb.9 for ; Sun, 30 Oct 2022 03:03:41 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=krwG5u3iMnmu3ZPyM320ApdNLoJb3oY0Z8Dtz0r35Fs=; b=jNOSzmpHJBbkT5huF8E1SaX7WqMvDB9fnJk8W0LOrGS3g1NReJYWh0CfxzZP6B8bEj H53Z44w1dPVbv7h4NXh7OELX2CXFUPjDOieVp8BQ6a4LsfOL53LOPIdOS+TrN6bi3yQi YBwiA6nrFVunL51D8WHcgOuKbdoGp6MCEQ3zUcrO60xqZ1Rr145kG57RHRZPwGmi87nu x23zHyot3FHmvhOUzOqYXYADqUCGiyaIqogjHLGOrOzT6GCrlXpHOpVrWDlsX0G5e6aM tw9v+EPKCUd9VewrDVtDzTB6W3bLWTm6MDvdK7YftEMta16k4YzGwLuIVX57kbXsHRLT YUYQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=krwG5u3iMnmu3ZPyM320ApdNLoJb3oY0Z8Dtz0r35Fs=; b=iBOtG2zWZVZVFso3/xXLJuDT3AC8YKSYhB/q0MZ1ykWAqvtGG2E2H/2fsc1t78kGy9 pN0CmkWUfhR7sjeJ2ApATR1h6nUTp7Iam9I/O8vxTXDc9up+TvPXDSvMSdjW0DX1G8Wu uNjzv6QGSzMHAJd/Jn0cF2YEeiCymciSroOj91lSsZvxvm/zhYvqiThdB19SGfR6+JRT Il44FqLctxLDv8qeQVNYZxoxemQhIYJc7l/xXH8+GG97Glo5RPmeXWDdK0ZdojGpP7bv VTEVEHqIS7IfLpupUbdAH2lnNuhJpFpueTQjreSWewxoCuVboF0oUUj0X8M48kHBM22F Lp/Q== X-Gm-Message-State: ACrzQf2DesFpiQIg36J3xbYddjRd9tI5o83jwJcehNYUF1zGzg442rXo SiqiNmAy7oSbKOaNsNNUQ5ltLw== X-Google-Smtp-Source: AMsMyM7O3y2RUM57lY78LybjEjVVtWXjRLMP3Zukd5ONnJbN2wZgsI9LyPREXvo/nhhv2TvdFsfsNw== X-Received: by 2002:a05:6402:5187:b0:461:ac01:7512 with SMTP id q7-20020a056402518700b00461ac017512mr8011937edd.327.1667124219916; Sun, 30 Oct 2022 03:03:39 -0700 (PDT) Received: from MBP-di-Paolo.station (net-2-35-55-161.cust.vodafonedsl.it. [2.35.55.161]) by smtp.gmail.com with ESMTPSA id d27-20020a170906305b00b0073d71792c8dsm1666088ejd.180.2022.10.30.03.03.38 (version=TLS1_2 cipher=ECDHE-ECDSA-AES128-GCM-SHA256 bits=128/128); Sun, 30 Oct 2022 03:03:39 -0700 (PDT) From: Paolo Valente To: Jens Axboe Cc: linux-block@vger.kernel.org, linux-kernel@vger.kernel.org, Davide Zini , Paolo Valente Subject: [PATCH V5 5/8] block, bfq: split also async bfq_queues on a per-actuator basis Date: Sun, 30 Oct 2022 11:02:57 +0100 Message-Id: <20221030100300.3085-6-paolo.valente@linaro.org> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20221030100300.3085-1-paolo.valente@linaro.org> References: <20221030100300.3085-1-paolo.valente@linaro.org> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-block@vger.kernel.org From: Davide Zini Similarly to sync bfq_queues, also async bfq_queues need to be split on a per-actuator basis. Signed-off-by: Paolo Valente Signed-off-by: Davide Zini --- block/bfq-iosched.c | 41 +++++++++++++++++++++++------------------ block/bfq-iosched.h | 8 ++++---- 2 files changed, 27 insertions(+), 22 deletions(-) diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index bfdf954da5b7..f1ea24775d90 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -2675,14 +2675,16 @@ static void bfq_bfqq_end_wr(struct bfq_queue *bfqq) void bfq_end_wr_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg) { - int i, j; - - for (i = 0; i < 2; i++) - for (j = 0; j < IOPRIO_NR_LEVELS; j++) - if (bfqg->async_bfqq[i][j]) - bfq_bfqq_end_wr(bfqg->async_bfqq[i][j]); - if (bfqg->async_idle_bfqq) - bfq_bfqq_end_wr(bfqg->async_idle_bfqq); + int i, j, k; + + for (k = 0; k < bfqd->num_actuators; k++) { + for (i = 0; i < 2; i++) + for (j = 0; j < IOPRIO_NR_LEVELS; j++) + if (bfqg->async_bfqq[i][j][k]) + bfq_bfqq_end_wr(bfqg->async_bfqq[i][j][k]); + if (bfqg->async_idle_bfqq[k]) + bfq_bfqq_end_wr(bfqg->async_idle_bfqq[k]); + } } static void bfq_end_wr(struct bfq_data *bfqd) @@ -5629,18 +5631,18 @@ static void bfq_init_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq, static struct bfq_queue **bfq_async_queue_prio(struct bfq_data *bfqd, struct bfq_group *bfqg, - int ioprio_class, int ioprio) + int ioprio_class, int ioprio, int act_idx) { switch (ioprio_class) { case IOPRIO_CLASS_RT: - return &bfqg->async_bfqq[0][ioprio]; + return &bfqg->async_bfqq[0][ioprio][act_idx]; case IOPRIO_CLASS_NONE: ioprio = IOPRIO_BE_NORM; fallthrough; case IOPRIO_CLASS_BE: - return &bfqg->async_bfqq[1][ioprio]; + return &bfqg->async_bfqq[1][ioprio][act_idx]; case IOPRIO_CLASS_IDLE: - return &bfqg->async_idle_bfqq; + return &bfqg->async_idle_bfqq[act_idx]; default: return NULL; } @@ -5814,7 +5816,8 @@ static struct bfq_queue *bfq_get_queue(struct bfq_data *bfqd, if (!is_sync) { async_bfqq = bfq_async_queue_prio(bfqd, bfqg, ioprio_class, - ioprio); + ioprio, + bfq_actuator_index(bfqd, bio)); bfqq = *async_bfqq; if (bfqq) goto out; @@ -7032,13 +7035,15 @@ static void __bfq_put_async_bfqq(struct bfq_data *bfqd, */ void bfq_put_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg) { - int i, j; + int i, j, k; - for (i = 0; i < 2; i++) - for (j = 0; j < IOPRIO_NR_LEVELS; j++) - __bfq_put_async_bfqq(bfqd, &bfqg->async_bfqq[i][j]); + for (k = 0; k < bfqd->num_actuators; k++) { + for (i = 0; i < 2; i++) + for (j = 0; j < IOPRIO_NR_LEVELS; j++) + __bfq_put_async_bfqq(bfqd, &bfqg->async_bfqq[i][j][k]); - __bfq_put_async_bfqq(bfqd, &bfqg->async_idle_bfqq); + __bfq_put_async_bfqq(bfqd, &bfqg->async_idle_bfqq[k]); + } } /* diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h index e27897d66a0f..f1c2e77cbf9a 100644 --- a/block/bfq-iosched.h +++ b/block/bfq-iosched.h @@ -976,8 +976,8 @@ struct bfq_group { void *bfqd; - struct bfq_queue *async_bfqq[2][IOPRIO_NR_LEVELS]; - struct bfq_queue *async_idle_bfqq; + struct bfq_queue *async_bfqq[2][IOPRIO_NR_LEVELS][BFQ_MAX_ACTUATORS]; + struct bfq_queue *async_idle_bfqq[BFQ_MAX_ACTUATORS]; struct bfq_entity *my_entity; @@ -993,8 +993,8 @@ struct bfq_group { struct bfq_entity entity; struct bfq_sched_data sched_data; - struct bfq_queue *async_bfqq[2][IOPRIO_NR_LEVELS]; - struct bfq_queue *async_idle_bfqq; + struct bfq_queue *async_bfqq[2][IOPRIO_NR_LEVELS][BFQ_MAX_ACTUATORS]; + struct bfq_queue *async_idle_bfqq[BFQ_MAX_ACTUATORS]; struct rb_root rq_pos_tree; }; From patchwork Sun Oct 30 10:02:58 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Paolo Valente X-Patchwork-Id: 13025055 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 1E1DFFA3745 for ; Sun, 30 Oct 2022 10:03:47 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S229761AbiJ3KDp (ORCPT ); Sun, 30 Oct 2022 06:03:45 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:50128 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S230042AbiJ3KDm (ORCPT ); Sun, 30 Oct 2022 06:03:42 -0400 Received: from mail-ej1-x629.google.com (mail-ej1-x629.google.com [IPv6:2a00:1450:4864:20::629]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id A37CC23F for ; Sun, 30 Oct 2022 03:03:41 -0700 (PDT) Received: by mail-ej1-x629.google.com with SMTP id ud5so22856641ejc.4 for ; Sun, 30 Oct 2022 03:03:41 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=w0jpEUiIStstn+cz9/9ycvh0etWYQc/7Lgp1ggYo6Sw=; b=Pkc1XWViIueLswGPwN/I3OqzS7h/cpEacd6eJo4Ox3Jaj4auWsLxY8H+eHhQbfZwRD XOHTF0roKn+zZoEmsuyC6vkLOz8mEgN0JQshN6I1VxjapsOrLnNL7mm1/Y4OmCxXj+Qk L7gm1cthaMVcLQlHjVdf6lqZvSjYpp63pN0nuvpM1Ifck3HVrDqDucK7+J3rZCUbN1S7 nvpo5hagUfc+/DgMLJtVHcs/jdIaushxUGwrjwDK4hLX0f5HJGnnhgUMIpQ1ZpcUXxR1 0ElKUXESHZyiyad1V7csYj3tfFXyORTkbtVstwkjCMAP6z7H2qiVkH40GCPbqMG9BaO8 Hnow== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=w0jpEUiIStstn+cz9/9ycvh0etWYQc/7Lgp1ggYo6Sw=; b=rnKbBWhgZqMBEzc0JwVoGDhrpTxS9/PmqstCZyoUV5cA6VjfjdjnynLREMC/kmcmBR ZcbTxUBzfPeC+gHN4dF1U4wYb7K1QXN1wOUaHdtE3rCq4tloCqMcXCFm8ww+i+paZI1S igWs3gP0HtPk2kuGCCBhHAullPVUfbiut5v7Kq/XVJXjLTW6cS6kaZLyQz5HElqblqJ1 veyI1ePyET2I+waJ1PErHTq5vemHVBSOaGplOK2ka3/9mPtL9wC6PcXXXz3Rns3QO1yT ifLhixplBXzo3/K90UBg8WMe7QVzYv7hV44gmmXrtjZzY0pjhqflF1HsSRX4e3iNtE+B 0Srw== X-Gm-Message-State: ACrzQf3yAqcApqvNDYgc/iOncvQ447f4Sx5ynMVd2+DRsmOR5Of0vq2S fFMtM5Chfb2MtH1F1SPWVdv2yA== X-Google-Smtp-Source: AMsMyM6e8rNz8OtmSdbJsYu4hPjyGmD3JUoWOtWMIIiIiWQk09CHvwBZmvrYZmT5jKSoZE9xWAtm/Q== X-Received: by 2002:a17:907:6e03:b0:78e:1c82:1f2a with SMTP id sd3-20020a1709076e0300b0078e1c821f2amr7190243ejc.611.1667124221217; Sun, 30 Oct 2022 03:03:41 -0700 (PDT) Received: from MBP-di-Paolo.station (net-2-35-55-161.cust.vodafonedsl.it. [2.35.55.161]) by smtp.gmail.com with ESMTPSA id d27-20020a170906305b00b0073d71792c8dsm1666088ejd.180.2022.10.30.03.03.40 (version=TLS1_2 cipher=ECDHE-ECDSA-AES128-GCM-SHA256 bits=128/128); Sun, 30 Oct 2022 03:03:40 -0700 (PDT) From: Paolo Valente To: Jens Axboe Cc: linux-block@vger.kernel.org, linux-kernel@vger.kernel.org, Federico Gavioli , Rory Chen , Paolo Valente Subject: [PATCH V5 6/8] block, bfq: retrieve independent access ranges from request queue Date: Sun, 30 Oct 2022 11:02:58 +0100 Message-Id: <20221030100300.3085-7-paolo.valente@linaro.org> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20221030100300.3085-1-paolo.valente@linaro.org> References: <20221030100300.3085-1-paolo.valente@linaro.org> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-block@vger.kernel.org From: Federico Gavioli This patch implements the code to gather the content of the independent_access_ranges structure from the request_queue and copy it into the queue's bfq_data. This copy is done at queue initialization. We copy the access ranges into the bfq_data to avoid taking the queue lock each time we access the ranges. This implementation, however, puts a limit to the maximum independent ranges supported by the scheduler. Such a limit is equal to the constant BFQ_MAX_ACTUATORS. This limit was placed to avoid the allocation of dynamic memory. Co-developed-by: Rory Chen Signed-off-by: Rory Chen Signed-off-by: Federico Gavioli Signed-off-by: Paolo Valente --- block/bfq-iosched.c | 54 ++++++++++++++++++++++++++++++++++++++------- block/bfq-iosched.h | 5 +++++ 2 files changed, 51 insertions(+), 8 deletions(-) diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index f1ea24775d90..6f464d422098 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -1833,10 +1833,26 @@ static bool bfq_bfqq_higher_class_or_weight(struct bfq_queue *bfqq, /* 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. - */ + struct blk_independent_access_range *iar; + unsigned int i; + sector_t end; + + /* no search needed if one or zero ranges present */ + if (bfqd->num_actuators < 2) + return 0; + + /* bio_end_sector(bio) gives the sector after the last one */ + end = bio_end_sector(bio) - 1; + + for (i = 0; i < bfqd->num_actuators; i++) { + iar = &(bfqd->ia_ranges[i]); + if (end >= iar->sector && end < iar->sector + iar->nr_sectors) + return i; + } + + WARN_ONCE(true, + "bfq_actuator_index: bio sector out of ranges: end=%llu\n", + end); return 0; } @@ -2481,7 +2497,6 @@ static void bfq_remove_request(struct request_queue *q, if (rq->cmd_flags & REQ_META) bfqq->meta_pending--; - } static bool bfq_bio_merge(struct request_queue *q, struct bio *bio, @@ -7154,6 +7169,8 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e) { struct bfq_data *bfqd; struct elevator_queue *eq; + unsigned int i; + struct blk_independent_access_ranges *ia_ranges = q->disk->ia_ranges; eq = elevator_alloc(q, e); if (!eq) @@ -7197,10 +7214,31 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e) bfqd->queue = q; /* - * Multi-actuator support not complete yet, default to single - * actuator for the moment. + * If the disk supports multiple actuators, we copy the independent + * access ranges from the request queue structure. */ - bfqd->num_actuators = 1; + spin_lock_irq(&q->queue_lock); + if (ia_ranges) { + /* + * Check if the disk ia_ranges size exceeds the current bfq + * actuator limit. + */ + if (ia_ranges->nr_ia_ranges > BFQ_MAX_ACTUATORS) { + pr_crit("nr_ia_ranges higher than act limit: iars=%d, max=%d.\n", + ia_ranges->nr_ia_ranges, BFQ_MAX_ACTUATORS); + pr_crit("Falling back to single actuator mode.\n"); + bfqd->num_actuators = 0; + } else { + bfqd->num_actuators = ia_ranges->nr_ia_ranges; + + for (i = 0; i < bfqd->num_actuators; i++) + bfqd->ia_ranges[i] = ia_ranges->ia_range[i]; + } + } else { + bfqd->num_actuators = 0; + } + + spin_unlock_irq(&q->queue_lock); INIT_LIST_HEAD(&bfqd->dispatch); diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h index f1c2e77cbf9a..90130a893c8f 100644 --- a/block/bfq-iosched.h +++ b/block/bfq-iosched.h @@ -811,6 +811,11 @@ struct bfq_data { */ unsigned int num_actuators; + /* + * Disk independent access ranges for each actuator + * in this device. + */ + struct blk_independent_access_range ia_ranges[BFQ_MAX_ACTUATORS]; }; enum bfqq_state_flags { From patchwork Sun Oct 30 10:02:59 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Paolo Valente X-Patchwork-Id: 13025057 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 67016C38A02 for ; Sun, 30 Oct 2022 10:03:50 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S230088AbiJ3KDs (ORCPT ); Sun, 30 Oct 2022 06:03:48 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:50216 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S230054AbiJ3KDq (ORCPT ); Sun, 30 Oct 2022 06:03:46 -0400 Received: from mail-ed1-x52e.google.com (mail-ed1-x52e.google.com [IPv6:2a00:1450:4864:20::52e]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id DF59EC0B for ; Sun, 30 Oct 2022 03:03:43 -0700 (PDT) Received: by mail-ed1-x52e.google.com with SMTP id i21so13697009edj.10 for ; Sun, 30 Oct 2022 03:03:43 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=mNQDX/3BgflPUItKLMTHQsd/7uDvCbPOZxZcndPgzvw=; b=l9tnIuhrO2XBhtPnHth7rTlh9rNNG+b9pCqDVZJV1jO8CDfCBbimoVhZ35guCGE8pa m5EE5zndcKtq5KmsGSSOdV1e1uEtTdgPIqTEmf38q9jwS7DhoU0NUp4Hb9Y0SpDl0urY OVN4613EwLpbPolpRYw4T8G5H3PD3czjsK7ebHQuk1LKNZtLHQ30sFHusNrRb6nnE7wa SnGLQ9OqsrLP7R4HGgwnV0ZocBxoOYDUkUv/WzCGaBVD/ZnP+O+7HRMAhZjLyru51Cwi QAUfJ1qmxvGQMwaQQ5BiceLDErcoGjkSth/8QO2vvjxsE1yy8FFWzAqngEZIiKoN4lR/ f2cw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=mNQDX/3BgflPUItKLMTHQsd/7uDvCbPOZxZcndPgzvw=; b=bTzgNXQQ1FPEozm4SctR1qd6dYycquC6lWPTjC1hb4EXUivjtpp78EOuUOO900YIoU lO+6rMamjSCpg5jYOt9m1aHmL+OuV34onONBezy06snv10GHekUuqdGvfbRqqnGXB+G7 /beCdy+b7suetAVTkbJ++/XiQ8tx56r8GhEaZpCyHfqycqwQtgsGMCYChOY+mcjLj0UE Har8BUMkniWcGDFO/2GJJNvw+b+fLWgGrWQPOQiJXORc38e4IhpFXqYgj4bqUbDezhz9 ifvMnsf78tflouQDWqvZ4a1PsdopRDE4XyWmBNyPxxSk7fvudrceZu77a30a4eNl61UD Osug== X-Gm-Message-State: ACrzQf0AmvZJk1AqWMeWZ9kjKLXE0e1pOtoMch20Iml7jASRXtqGtHM3 XEymML23PjiYDi1l/BUjfGQTJw== X-Google-Smtp-Source: AMsMyM5iT4Gki0pnI3XZkB5061kBXRKYpRikZne599FPtV9NcXMRm9RNhMA0ZTCFRrbtP8elXUU9yQ== X-Received: by 2002:a50:fe85:0:b0:458:5562:bf1e with SMTP id d5-20020a50fe85000000b004585562bf1emr7843570edt.167.1667124222229; Sun, 30 Oct 2022 03:03:42 -0700 (PDT) Received: from MBP-di-Paolo.station (net-2-35-55-161.cust.vodafonedsl.it. [2.35.55.161]) by smtp.gmail.com with ESMTPSA id d27-20020a170906305b00b0073d71792c8dsm1666088ejd.180.2022.10.30.03.03.41 (version=TLS1_2 cipher=ECDHE-ECDSA-AES128-GCM-SHA256 bits=128/128); Sun, 30 Oct 2022 03:03:41 -0700 (PDT) From: Paolo Valente To: Jens Axboe Cc: linux-block@vger.kernel.org, linux-kernel@vger.kernel.org, Davide Zini , Paolo Valente Subject: [PATCH V5 7/8] block, bfq: inject I/O to underutilized actuators Date: Sun, 30 Oct 2022 11:02:59 +0100 Message-Id: <20221030100300.3085-8-paolo.valente@linaro.org> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20221030100300.3085-1-paolo.valente@linaro.org> References: <20221030100300.3085-1-paolo.valente@linaro.org> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-block@vger.kernel.org From: Davide Zini The main service scheme of BFQ for sync I/O is serving one sync bfq_queue at a time, for a while. In particular, BFQ enforces this scheme when it deems the latter necessary to boost throughput or to preserve service guarantees. Unfortunately, when BFQ enforces this policy, only one actuator at a time gets served for a while, because each bfq_queue contains I/O only for one actuator. The other actuators may remain underutilized. Actually, BFQ may serve (inject) extra I/O, taken from other bfq_queues, in parallel with that of the in-service queue. This injection mechanism may provide the ground for dealing also with the above actuator-underutilization problem. Yet BFQ does not take the actuator load into account when choosing which queue to pick extra I/O from. In addition, BFQ may happen to inject extra I/O only when the in-service queue is temporarily empty. In view of these facts, this commit extends the injection mechanism in such a way that the latter: (1) takes into account also the actuator load; (2) checks such a load on each dispatch, and injects I/O for an underutilized actuator, if there is one and there is I/O for it. To perform the check in (2), this commit introduces a load threshold, currently set to 4. A linear scan of each actuator is performed, until an actuator is found for which the following two conditions hold: the load of the actuator is below the threshold, and there is at least one non-in-service queue that contains I/O for that actuator. If such a pair (actuator, queue) is found, then the head request of that queue is returned for dispatch, instead of the head request of the in-service queue. We have set the threshold, empirically, to the minimum possible value for which an actuator is fully utilized, or close to be fully utilized. By doing so, injected I/O 'steals' as few drive-queue slots as possibile to the in-service queue. This reduces as much as possible the probability that the service of I/O from the in-service bfq_queue gets delayed because of slot exhaustion, i.e., because all the slots of the drive queue are filled with I/O injected from other queues (NCQ provides for 32 slots). This new mechanism also counters actuator underutilization in the case of asymmetric configurations of bfq_queues. Namely if there are few bfq_queues containing I/O for some actuators and many bfq_queues containing I/O for other actuators. Or if the bfq_queues containing I/O for some actuators have lower weights than the other bfq_queues. Signed-off-by: Paolo Valente Signed-off-by: Davide Zini --- block/bfq-cgroup.c | 2 +- block/bfq-iosched.c | 139 +++++++++++++++++++++++++++++++++----------- block/bfq-iosched.h | 39 ++++++++++++- block/bfq-wf2q.c | 2 +- 4 files changed, 143 insertions(+), 39 deletions(-) diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c index d243c429d9c0..38ccfe55ad46 100644 --- a/block/bfq-cgroup.c +++ b/block/bfq-cgroup.c @@ -694,7 +694,7 @@ void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq, bfq_activate_bfqq(bfqd, bfqq); } - if (!bfqd->in_service_queue && !bfqd->rq_in_driver) + if (!bfqd->in_service_queue && !bfqd->tot_rq_in_driver) bfq_schedule_dispatch(bfqd); /* release extra ref taken above, bfqq may happen to be freed now */ bfq_put_queue(bfqq); diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 6f464d422098..c9af17a36219 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -2254,6 +2254,7 @@ static void bfq_add_request(struct request *rq) bfq_log_bfqq(bfqd, bfqq, "add_request %d", rq_is_sync(rq)); bfqq->queued[rq_is_sync(rq)]++; + /* * Updating of 'bfqd->queued' is protected by 'bfqd->lock', however, it * may be read without holding the lock in bfq_has_work(). @@ -2299,9 +2300,9 @@ static void bfq_add_request(struct request *rq) * elapsed. */ if (bfqq == bfqd->in_service_queue && - (bfqd->rq_in_driver == 0 || + (bfqd->tot_rq_in_driver == 0 || (bfqq->last_serv_time_ns > 0 && - bfqd->rqs_injected && bfqd->rq_in_driver > 0)) && + bfqd->rqs_injected && bfqd->tot_rq_in_driver > 0)) && time_is_before_eq_jiffies(bfqq->decrease_time_jif + msecs_to_jiffies(10))) { bfqd->last_empty_occupied_ns = ktime_get_ns(); @@ -2325,7 +2326,7 @@ static void bfq_add_request(struct request *rq) * will be set in case injection is performed * on bfqq before rq is completed). */ - if (bfqd->rq_in_driver == 0) + if (bfqd->tot_rq_in_driver == 0) bfqd->rqs_injected = false; } } @@ -2423,15 +2424,18 @@ static sector_t get_sdist(sector_t last_pos, struct request *rq) static void bfq_activate_request(struct request_queue *q, struct request *rq) { struct bfq_data *bfqd = q->elevator->elevator_data; + unsigned int act_idx = bfq_actuator_index(bfqd, rq->bio); - bfqd->rq_in_driver++; + bfqd->tot_rq_in_driver++; + bfqd->rq_in_driver[act_idx]++; } static void bfq_deactivate_request(struct request_queue *q, struct request *rq) { struct bfq_data *bfqd = q->elevator->elevator_data; - bfqd->rq_in_driver--; + bfqd->tot_rq_in_driver--; + bfqd->rq_in_driver[bfq_actuator_index(bfqd, rq->bio)]--; } #endif @@ -2705,11 +2709,14 @@ void bfq_end_wr_async_queues(struct bfq_data *bfqd, static void bfq_end_wr(struct bfq_data *bfqd) { struct bfq_queue *bfqq; + int i; spin_lock_irq(&bfqd->lock); - list_for_each_entry(bfqq, &bfqd->active_list, bfqq_list) - bfq_bfqq_end_wr(bfqq); + for (i = 0; i < bfqd->num_actuators; i++) { + list_for_each_entry(bfqq, &bfqd->active_list[i], bfqq_list) + bfq_bfqq_end_wr(bfqq); + } list_for_each_entry(bfqq, &bfqd->idle_list, bfqq_list) bfq_bfqq_end_wr(bfqq); bfq_end_wr_async(bfqd); @@ -3660,13 +3667,13 @@ static void bfq_update_peak_rate(struct bfq_data *bfqd, struct request *rq) * - start a new observation interval with this dispatch */ if (now_ns - bfqd->last_dispatch > 100*NSEC_PER_MSEC && - bfqd->rq_in_driver == 0) + bfqd->tot_rq_in_driver == 0) goto update_rate_and_reset; /* Update sampling information */ bfqd->peak_rate_samples++; - if ((bfqd->rq_in_driver > 0 || + if ((bfqd->tot_rq_in_driver > 0 || now_ns - bfqd->last_completion < BFQ_MIN_TT) && !BFQ_RQ_SEEKY(bfqd, bfqd->last_position, rq)) bfqd->sequential_samples++; @@ -3933,7 +3940,7 @@ static bool idling_needed_for_service_guarantees(struct bfq_data *bfqd, return (bfqq->wr_coeff > 1 && (bfqd->wr_busy_queues < tot_busy_queues || - bfqd->rq_in_driver >= + bfqd->tot_rq_in_driver >= bfqq->dispatched + 4)) || bfq_asymmetric_scenario(bfqd, bfqq) || tot_busy_queues == 1; @@ -4705,6 +4712,7 @@ bfq_choose_bfqq_for_injection(struct bfq_data *bfqd) { struct bfq_queue *bfqq, *in_serv_bfqq = bfqd->in_service_queue; unsigned int limit = in_serv_bfqq->inject_limit; + int i; /* * If * - bfqq is not weight-raised and therefore does not carry @@ -4736,7 +4744,7 @@ bfq_choose_bfqq_for_injection(struct bfq_data *bfqd) ) limit = 1; - if (bfqd->rq_in_driver >= limit) + if (bfqd->tot_rq_in_driver >= limit) return NULL; /* @@ -4751,11 +4759,12 @@ bfq_choose_bfqq_for_injection(struct bfq_data *bfqd) * (and re-added only if it gets new requests, but then it * is assigned again enough budget for its new backlog). */ - list_for_each_entry(bfqq, &bfqd->active_list, bfqq_list) - if (!RB_EMPTY_ROOT(&bfqq->sort_list) && - (in_serv_always_inject || bfqq->wr_coeff > 1) && - bfq_serv_to_charge(bfqq->next_rq, bfqq) <= - bfq_bfqq_budget_left(bfqq)) { + for (i = 0; i < bfqd->num_actuators; i++) { + list_for_each_entry(bfqq, &bfqd->active_list[i], bfqq_list) + if (!RB_EMPTY_ROOT(&bfqq->sort_list) && + (in_serv_always_inject || bfqq->wr_coeff > 1) && + bfq_serv_to_charge(bfqq->next_rq, bfqq) <= + bfq_bfqq_budget_left(bfqq)) { /* * Allow for only one large in-flight request * on non-rotational devices, for the @@ -4780,22 +4789,69 @@ bfq_choose_bfqq_for_injection(struct bfq_data *bfqd) else limit = in_serv_bfqq->inject_limit; - if (bfqd->rq_in_driver < limit) { + if (bfqd->tot_rq_in_driver < limit) { bfqd->rqs_injected = true; return bfqq; } } + } + + return NULL; +} + +static struct bfq_queue * +bfq_find_active_bfqq_for_actuator(struct bfq_data *bfqd, + int idx) +{ + struct bfq_queue *bfqq = NULL; + + if (bfqd->in_service_queue && + bfqd->in_service_queue->actuator_idx == idx) + return bfqd->in_service_queue; + + list_for_each_entry(bfqq, &bfqd->active_list[idx], bfqq_list) { + if (!RB_EMPTY_ROOT(&bfqq->sort_list) && + bfq_serv_to_charge(bfqq->next_rq, bfqq) <= + bfq_bfqq_budget_left(bfqq)) { + return bfqq; + } + } return NULL; } +/* + * Perform a linear scan of each actuator, until an actuator is found + * for which the following two conditions hold: the load of the + * actuator is below the threshold (see comments on actuator_load_threshold + * for details), and there is a queue that contains I/O for that + * actuator. On success, return that queue. + */ +static struct bfq_queue * +bfq_find_bfqq_for_underused_actuator(struct bfq_data *bfqd) +{ + int i; + + for (i = 0 ; i < bfqd->num_actuators; i++) + if (bfqd->rq_in_driver[i] < bfqd->actuator_load_threshold) { + struct bfq_queue *bfqq = + bfq_find_active_bfqq_for_actuator(bfqd, i); + + if (bfqq) + return bfqq; + } + + return NULL; +} + + /* * Select a queue for service. If we have a current queue in service, * check whether to continue servicing it, or retrieve and set a new one. */ static struct bfq_queue *bfq_select_queue(struct bfq_data *bfqd) { - struct bfq_queue *bfqq; + struct bfq_queue *bfqq, *inject_bfqq; struct request *next_rq; enum bfqq_expiration reason = BFQQE_BUDGET_TIMEOUT; @@ -4817,6 +4873,15 @@ static struct bfq_queue *bfq_select_queue(struct bfq_data *bfqd) goto expire; check_queue: + /* + * If some actuator is underutilized, but the in-service + * queue does not contain I/O for that actuator, then try to + * inject I/O for that actuator. + */ + inject_bfqq = bfq_find_bfqq_for_underused_actuator(bfqd); + if (inject_bfqq && inject_bfqq != bfqq) + return inject_bfqq; + /* * This loop is rarely executed more than once. Even when it * happens, it is much more convenient to re-execute this loop @@ -5172,11 +5237,11 @@ static struct request *__bfq_dispatch_request(struct blk_mq_hw_ctx *hctx) /* * We exploit the bfq_finish_requeue_request hook to - * decrement rq_in_driver, but + * decrement tot_rq_in_driver, but * bfq_finish_requeue_request will not be invoked on * this request. So, to avoid unbalance, just start - * this request, without incrementing rq_in_driver. As - * a negative consequence, rq_in_driver is deceptively + * this request, without incrementing tot_rq_in_driver. As + * a negative consequence, tot_rq_in_driver is deceptively * lower than it should be while this request is in * service. This may cause bfq_schedule_dispatch to be * invoked uselessly. @@ -5185,7 +5250,7 @@ static struct request *__bfq_dispatch_request(struct blk_mq_hw_ctx *hctx) * bfq_finish_requeue_request hook, if defined, is * probably invoked also on this request. So, by * exploiting this hook, we could 1) increment - * rq_in_driver here, and 2) decrement it in + * tot_rq_in_driver here, and 2) decrement it in * bfq_finish_requeue_request. Such a solution would * let the value of the counter be always accurate, * but it would entail using an extra interface @@ -5214,7 +5279,7 @@ static struct request *__bfq_dispatch_request(struct blk_mq_hw_ctx *hctx) * Of course, serving one request at a time may cause loss of * throughput. */ - if (bfqd->strict_guarantees && bfqd->rq_in_driver > 0) + if (bfqd->strict_guarantees && bfqd->tot_rq_in_driver > 0) goto exit; bfqq = bfq_select_queue(bfqd); @@ -5225,7 +5290,8 @@ static struct request *__bfq_dispatch_request(struct blk_mq_hw_ctx *hctx) if (rq) { inc_in_driver_start_rq: - bfqd->rq_in_driver++; + bfqd->rq_in_driver[bfqq->actuator_idx]++; + bfqd->tot_rq_in_driver++; start_rq: rq->rq_flags |= RQF_STARTED; } @@ -6298,7 +6364,7 @@ static void bfq_update_hw_tag(struct bfq_data *bfqd) struct bfq_queue *bfqq = bfqd->in_service_queue; bfqd->max_rq_in_driver = max_t(int, bfqd->max_rq_in_driver, - bfqd->rq_in_driver); + bfqd->tot_rq_in_driver); if (bfqd->hw_tag == 1) return; @@ -6309,7 +6375,7 @@ static void bfq_update_hw_tag(struct bfq_data *bfqd) * sum is not exact, as it's not taking into account deactivated * requests. */ - if (bfqd->rq_in_driver + bfqd->queued <= BFQ_HW_QUEUE_THRESHOLD) + if (bfqd->tot_rq_in_driver + bfqd->queued <= BFQ_HW_QUEUE_THRESHOLD) return; /* @@ -6320,7 +6386,7 @@ static void bfq_update_hw_tag(struct bfq_data *bfqd) if (bfqq && bfq_bfqq_has_short_ttime(bfqq) && bfqq->dispatched + bfqq->queued[0] + bfqq->queued[1] < BFQ_HW_QUEUE_THRESHOLD && - bfqd->rq_in_driver < BFQ_HW_QUEUE_THRESHOLD) + bfqd->tot_rq_in_driver < BFQ_HW_QUEUE_THRESHOLD) return; if (bfqd->hw_tag_samples++ < BFQ_HW_QUEUE_SAMPLES) @@ -6341,7 +6407,8 @@ static void bfq_completed_request(struct bfq_queue *bfqq, struct bfq_data *bfqd) bfq_update_hw_tag(bfqd); - bfqd->rq_in_driver--; + bfqd->rq_in_driver[bfqq->actuator_idx]--; + bfqd->tot_rq_in_driver--; bfqq->dispatched--; if (!bfqq->dispatched && !bfq_bfqq_busy(bfqq)) { @@ -6460,7 +6527,7 @@ static void bfq_completed_request(struct bfq_queue *bfqq, struct bfq_data *bfqd) BFQQE_NO_MORE_REQUESTS); } - if (!bfqd->rq_in_driver) + if (!bfqd->tot_rq_in_driver) bfq_schedule_dispatch(bfqd); } @@ -6591,13 +6658,13 @@ static void bfq_update_inject_limit(struct bfq_data *bfqd, * conditions to do it, or we can lower the last base value * computed. * - * NOTE: (bfqd->rq_in_driver == 1) means that there is no I/O + * NOTE: (bfqd->tot_rq_in_driver == 1) means that there is no I/O * request in flight, because this function is in the code * path that handles the completion of a request of bfqq, and, * in particular, this function is executed before - * bfqd->rq_in_driver is decremented in such a code path. + * bfqd->tot_rq_in_driver is decremented in such a code path. */ - if ((bfqq->last_serv_time_ns == 0 && bfqd->rq_in_driver == 1) || + if ((bfqq->last_serv_time_ns == 0 && bfqd->tot_rq_in_driver == 1) || tot_time_ns < bfqq->last_serv_time_ns) { if (bfqq->last_serv_time_ns == 0) { /* @@ -6607,7 +6674,7 @@ static void bfq_update_inject_limit(struct bfq_data *bfqd, bfqq->inject_limit = max_t(unsigned int, 1, old_limit); } bfqq->last_serv_time_ns = tot_time_ns; - } else if (!bfqd->rqs_injected && bfqd->rq_in_driver == 1) + } else if (!bfqd->rqs_injected && bfqd->tot_rq_in_driver == 1) /* * No I/O injected and no request still in service in * the drive: these are the exact conditions for @@ -7249,7 +7316,8 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e) bfqd->queue_weights_tree = RB_ROOT_CACHED; bfqd->num_groups_with_pending_reqs = 0; - INIT_LIST_HEAD(&bfqd->active_list); + INIT_LIST_HEAD(&bfqd->active_list[0]); + INIT_LIST_HEAD(&bfqd->active_list[1]); INIT_LIST_HEAD(&bfqd->idle_list); INIT_HLIST_HEAD(&bfqd->burst_list); @@ -7294,6 +7362,9 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e) ref_wr_duration[blk_queue_nonrot(bfqd->queue)]; bfqd->peak_rate = ref_rate[blk_queue_nonrot(bfqd->queue)] * 2 / 3; + /* see comments on the definition of next field inside bfq_data */ + bfqd->actuator_load_threshold = 4; + spin_lock_init(&bfqd->lock); /* diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h index 90130a893c8f..adb3ba6a9d90 100644 --- a/block/bfq-iosched.h +++ b/block/bfq-iosched.h @@ -586,7 +586,12 @@ struct bfq_data { /* number of queued requests */ int queued; /* number of requests dispatched and waiting for completion */ - int rq_in_driver; + int tot_rq_in_driver; + /* + * number of requests dispatched and waiting for completion + * for each actuator + */ + int rq_in_driver[BFQ_MAX_ACTUATORS]; /* true if the device is non rotational and performs queueing */ bool nonrot_with_queueing; @@ -680,8 +685,13 @@ struct bfq_data { /* maximum budget allotted to a bfq_queue before rescheduling */ int bfq_max_budget; - /* list of all the bfq_queues active on the device */ - struct list_head active_list; + /* + * List of all the bfq_queues active for a specific actuator + * on the device. Keeping active queues separate on a + * per-actuator basis helps implementing per-actuator + * injection more efficiently. + */ + struct list_head active_list[BFQ_MAX_ACTUATORS]; /* list of all the bfq_queues idle on the device */ struct list_head idle_list; @@ -816,6 +826,29 @@ struct bfq_data { * in this device. */ struct blk_independent_access_range ia_ranges[BFQ_MAX_ACTUATORS]; + + /* + * If the number of I/O requests queued in the device for a + * given actuator is below next threshold, then the actuator + * is deemed as underutilized. If this condition is found to + * hold for some actuator upon a dispatch, but (i) the + * in-service queue does not contain I/O for that actuator, + * while (ii) some other queue does contain I/O for that + * actuator, then the head I/O request of the latter queue is + * returned (injected), instead of the head request of the + * currently in-service queue. + * + * We set the threshold, empirically, to the minimum possible + * value for which an actuator is fully utilized, or close to + * be fully utilized. By doing so, injected I/O 'steals' as + * few drive-queue slots as possibile to the in-service + * queue. This reduces as much as possible the probability + * that the service of I/O from the in-service bfq_queue gets + * delayed because of slot exhaustion, i.e., because all the + * slots of the drive queue are filled with I/O injected from + * other queues (NCQ provides for 32 slots). + */ + unsigned int actuator_load_threshold; }; enum bfqq_state_flags { diff --git a/block/bfq-wf2q.c b/block/bfq-wf2q.c index 8fc3da4c23bb..ec0273e2cd07 100644 --- a/block/bfq-wf2q.c +++ b/block/bfq-wf2q.c @@ -477,7 +477,7 @@ static void bfq_active_insert(struct bfq_service_tree *st, bfqd = (struct bfq_data *)bfqg->bfqd; #endif if (bfqq) - list_add(&bfqq->bfqq_list, &bfqq->bfqd->active_list); + list_add(&bfqq->bfqq_list, &bfqq->bfqd->active_list[bfqq->actuator_idx]); #ifdef CONFIG_BFQ_GROUP_IOSCHED if (bfqg != bfqd->root_group) bfqg->active_entities++; From patchwork Sun Oct 30 10:03:00 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Paolo Valente X-Patchwork-Id: 13025056 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 523B4FA373D for ; Sun, 30 Oct 2022 10:03:49 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S229682AbiJ3KDs (ORCPT ); Sun, 30 Oct 2022 06:03:48 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:50220 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S230062AbiJ3KDq (ORCPT ); Sun, 30 Oct 2022 06:03:46 -0400 Received: from mail-ej1-x62a.google.com (mail-ej1-x62a.google.com [IPv6:2a00:1450:4864:20::62a]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id A04942B8 for ; Sun, 30 Oct 2022 03:03:44 -0700 (PDT) Received: by mail-ej1-x62a.google.com with SMTP id b2so22853887eja.6 for ; Sun, 30 Oct 2022 03:03:44 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=jM3QRj1EVjuG2HTGTPAAvacJgPBGfkkz821afQrSz+o=; b=PbgYJjGDH30zX4rdDzg7LxIyS9IvehyrFKlkCIMb7d38wicDPUuQlJrs0rlAyP5U5e gF2SvDn3urpigL1xA5RxlXjyWPOb8UoVzphOzXCUHrUdDoFVoc/hmGnszls6M1uxXFgr Beu4AjvpK5w1rgouIZ/uj4IBPDJkajcSKV90jRKzTRKOEgshyukaP6xnaFU20bw5DUnh lQnkNUR2CkKgR/utbea9eMQDriAxG5DFHGumBuVHbJfAXR3yzws9cA+NZgkib7aIOfOy I+7kNFs35qV3dXazGpwls6/22scL8c5Bwqmypqnvt5o5KODldohefOy5FkcF8RSNnunE OBTg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=jM3QRj1EVjuG2HTGTPAAvacJgPBGfkkz821afQrSz+o=; b=AkcUYonEWP/S8nWz9VbEDxjDyTIhP4GTIb0DrmQ+efXEKBfXSyPa0Ez1pfIcO+0ovx TYHT7nUvXo/+4Mc/G2vnaLXLJq03BYa/0nUmfiD8q5IGIdru7zcVRXHdMbAdyE31QlBX jpkB+V/AJ1YyZ5xIlaasgf7Oj1uBoFuLSedxdYZnTBy0omEMjnorYHiZ/fEZXBQ6688p IQDedAba9Gl4axf/ITJz7wjeaY0smSigw5dv5BTFz8j0W74Y4eIcEdovW9YGG773IfQD IBWLWwBU5nsIcWHAoSJ1doP56mkiU1BaI9/eTaTe5Lxz4S4sJXc/Ip+xXEA+rcvhuiVS n7GA== X-Gm-Message-State: ACrzQf0P/S4iREEOkYS3AZAxajPiROF+f26Der7yDs4nNGMLUpP6Y9eN OFyCCSMFt8kfOuXMtNREeByG7nzcf5r3dg== X-Google-Smtp-Source: AMsMyM6fbaBOfBdgC1p/YVbYOgFLA6QW5gQGUIuMqKBDjre6T8fNB3ltyv24Cap3GQEC5UX5mFb8IA== X-Received: by 2002:a17:907:761b:b0:7a3:86dd:d330 with SMTP id jx27-20020a170907761b00b007a386ddd330mr7454455ejc.34.1667124223196; Sun, 30 Oct 2022 03:03:43 -0700 (PDT) Received: from MBP-di-Paolo.station (net-2-35-55-161.cust.vodafonedsl.it. [2.35.55.161]) by smtp.gmail.com with ESMTPSA id d27-20020a170906305b00b0073d71792c8dsm1666088ejd.180.2022.10.30.03.03.42 (version=TLS1_2 cipher=ECDHE-ECDSA-AES128-GCM-SHA256 bits=128/128); Sun, 30 Oct 2022 03:03:42 -0700 (PDT) From: Paolo Valente To: Jens Axboe Cc: linux-block@vger.kernel.org, linux-kernel@vger.kernel.org, Davide Zini , Paolo Valente Subject: [PATCH V5 8/8] block, bfq: balance I/O injection among underutilized actuators Date: Sun, 30 Oct 2022 11:03:00 +0100 Message-Id: <20221030100300.3085-9-paolo.valente@linaro.org> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20221030100300.3085-1-paolo.valente@linaro.org> References: <20221030100300.3085-1-paolo.valente@linaro.org> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-block@vger.kernel.org From: Davide Zini Upon the invocation of its dispatch function, BFQ returns the next I/O request of the in-service bfq_queue, unless some exception holds. One such exception is that there is some underutilized actuator, different from the actuator for which the in-service queue contains I/O, and that some other bfq_queue happens to contain I/O for such an actuator. In this case, the next I/O request of the latter bfq_queue, and not of the in-service bfq_queue, is returned (I/O is injected from that bfq_queue). To find such an actuator, a linear scan, in increasing index order, is performed among actuators. Performing a linear scan entails a prioritization among actuators: an underutilized actuator may be considered for injection only if all actuators with a lower index are currently fully utilized, or if there is no pending I/O for any lower-index actuator that happens to be underutilized. This commits breaks this prioritization and tends to distribute injection uniformly across actuators. This is obtained by adding the following condition to the linear scan: even if an actuator A is underutilized, A is however skipped if its load is higher than that of the next actuator. Signed-off-by: Paolo Valente Signed-off-by: Davide Zini --- block/bfq-iosched.c | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index c9af17a36219..77002ebcab39 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -4822,10 +4822,16 @@ bfq_find_active_bfqq_for_actuator(struct bfq_data *bfqd, /* * Perform a linear scan of each actuator, until an actuator is found - * for which the following two conditions hold: the load of the - * actuator is below the threshold (see comments on actuator_load_threshold - * for details), and there is a queue that contains I/O for that - * actuator. On success, return that queue. + * for which the following three conditions hold: the load of the + * actuator is below the threshold (see comments on + * actuator_load_threshold for details) and lower than that of the + * next actuator (comments on this extra condition below), and there + * is a queue that contains I/O for that actuator. On success, return + * that queue. + * + * Performing a plain linear scan entails a prioritization among + * actuators. The extra condition above breaks this prioritization and + * tends to distribute injection uniformly across actuators. */ static struct bfq_queue * bfq_find_bfqq_for_underused_actuator(struct bfq_data *bfqd) @@ -4833,7 +4839,9 @@ bfq_find_bfqq_for_underused_actuator(struct bfq_data *bfqd) int i; for (i = 0 ; i < bfqd->num_actuators; i++) - if (bfqd->rq_in_driver[i] < bfqd->actuator_load_threshold) { + if (bfqd->rq_in_driver[i] < bfqd->actuator_load_threshold && + (i == bfqd->num_actuators - 1 || + bfqd->rq_in_driver[i] < bfqd->rq_in_driver[i+1])) { struct bfq_queue *bfqq = bfq_find_active_bfqq_for_actuator(bfqd, i);