From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-9.0 required=3.0 tests=DKIMWL_WL_MED,DKIM_SIGNED, DKIM_VALID,HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_PATCH,MAILING_LIST_MULTI, SIGNED_OFF_BY,SPF_PASS,URIBL_BLOCKED,USER_AGENT_GIT autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 7D88EC65BAE for ; Fri, 30 Nov 2018 16:01:27 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.kernel.org (Postfix) with ESMTP id 38A7E2146D for ; Fri, 30 Nov 2018 16:01:27 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (2048-bit key) header.d=kernel-dk.20150623.gappssmtp.com header.i=@kernel-dk.20150623.gappssmtp.com header.b="giy0s/Nj" DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 38A7E2146D Authentication-Results: mail.kernel.org; dmarc=none (p=none dis=none) header.from=kernel.dk Authentication-Results: mail.kernel.org; spf=none smtp.mailfrom=linux-block-owner@vger.kernel.org Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1726702AbeLADLN (ORCPT ); Fri, 30 Nov 2018 22:11:13 -0500 Received: from mail-io1-f66.google.com ([209.85.166.66]:36926 "EHLO mail-io1-f66.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1726595AbeLADLN (ORCPT ); Fri, 30 Nov 2018 22:11:13 -0500 Received: by mail-io1-f66.google.com with SMTP id a3so4924144ioc.4 for ; Fri, 30 Nov 2018 08:01:25 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=kernel-dk.20150623.gappssmtp.com; s=20150623; h=from:to:cc:subject:date:message-id:in-reply-to:references; bh=VD7x+jCHzchNwON0o+zX+xRpZWyqbTARaQb1ekxUQbs=; b=giy0s/NjRJhEA0tNsB/3nmF8H/9pVVFPRmwPIk0krSIxqSSXMqdxh1sl5m2Hral1/a dq84jSKianSjtuByKS3L0drIuytzzZd4KKekI0xqBVR2gehNPHLXECZTfXnvIIVRa0/N SGiAMivHnen5oHes6LVkJLvd2zu860pdD3/u/mOkwvFcTw8LrU2lRUoxjFPZcCVrUfgh 4Qgs9VNb2Tv2DOLH9yLA7LhGrBSWrYjSP/al+1ghLRciPPmuTtwyz9UoVmf0TAmg9DLx 0Cd/ks5H0eQSF9x4YREK/n/sZTf0QV8gXx/Kx7nr3TaKeRqwqMy0mMnGawwr+TWdvV1J 2cuw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to :references; bh=VD7x+jCHzchNwON0o+zX+xRpZWyqbTARaQb1ekxUQbs=; b=GVP6ArF2JLSgh+OfACzCsEoJ2GLv0nweDs9StPnj0FMkaa3XxVf38maOc/wo8nqNU4 GUK7E+s+AiMJZk05RWRKqGgormQbyGbwR1NUMYxET+KttlG8do5+KqiHN2ofiOpXMaYV TyDzJTJ0vgUOHvtbUtyxKwn7ZVTpzccl4IYg4fAbhr/JKbAsKzKUUS6TXYSjJTrqXqxF J1MLifvit9m+XnSfg1FNXzIifZ40k5eMmnIN1MYESky3oa/KIy6QAJIWRK+Vh7Lo2X/Z N7tWEszjELJT7kCScfSLcmQm0/Uhd9uR5+gugzFe/E/viYUsVNLg6wuZUSYStuXJ41pA vO+Q== X-Gm-Message-State: AA+aEWbzjoFho6ONXnX322/t62GTZQAuaJCVe0I3pqgH/lPkr107HC6v 2Tb8X1tI5MGCXycjFWWJyJfDsBA+rKk= X-Google-Smtp-Source: AFSGD/VrXf9KUaDmuZbs5sqqddcnqTxLU538UMYaznNjgieFqM8qes/9oIftf8zqx+Fls+o5qjhfhQ== X-Received: by 2002:a5e:dd01:: with SMTP id t1mr5152163iop.102.1543593684639; Fri, 30 Nov 2018 08:01:24 -0800 (PST) Received: from localhost.localdomain ([216.160.245.98]) by smtp.gmail.com with ESMTPSA id m11sm2906784itb.24.2018.11.30.08.01.23 (version=TLS1_2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128/128); Fri, 30 Nov 2018 08:01:23 -0800 (PST) From: Jens Axboe To: linux-block@vger.kernel.org, osandov@osandov.com Cc: Jens Axboe Subject: [PATCH 2/2] sbitmap: optimize wakeup check Date: Fri, 30 Nov 2018 09:01:18 -0700 Message-Id: <20181130160118.24683-3-axboe@kernel.dk> X-Mailer: git-send-email 2.17.1 In-Reply-To: <20181130160118.24683-1-axboe@kernel.dk> References: <20181130160118.24683-1-axboe@kernel.dk> Sender: linux-block-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-block@vger.kernel.org Even if we have no waiters on any of the sbitmap_queue wait states, we still have to loop every entry to check. We do this for every IO, so the cost adds up. Shift a bit of the cost to the slow path, when we actually have waiters. Wrap prepare_to_wait_exclusive() and finish_wait(), so we can maintain an internal count of how many are currently active. Then we can simply check this count in sbq_wake_ptr() and not have to loop if we don't have any sleepers. Convert the two users of sbitmap with waiting, blk-mq-tag and iSCSI. Signed-off-by: Jens Axboe --- block/blk-mq-tag.c | 11 ++++---- drivers/target/iscsi/iscsi_target_util.c | 12 +++++---- include/linux/sbitmap.h | 34 ++++++++++++++++++++++++ lib/sbitmap.c | 28 +++++++++++++++++++ 4 files changed, 74 insertions(+), 11 deletions(-) diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index 87bc5df72d48..2089c6c62f44 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -110,7 +110,7 @@ unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data) struct blk_mq_tags *tags = blk_mq_tags_from_data(data); struct sbitmap_queue *bt; struct sbq_wait_state *ws; - DEFINE_WAIT(wait); + DEFINE_SBQ_WAIT(wait); unsigned int tag_offset; bool drop_ctx; int tag; @@ -154,8 +154,7 @@ unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data) if (tag != -1) break; - prepare_to_wait_exclusive(&ws->wait, &wait, - TASK_UNINTERRUPTIBLE); + sbitmap_prepare_to_wait(bt, ws, &wait, TASK_UNINTERRUPTIBLE); tag = __blk_mq_get_tag(data, bt); if (tag != -1) @@ -167,6 +166,8 @@ unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data) bt_prev = bt; io_schedule(); + sbitmap_finish_wait(bt, ws, &wait); + data->ctx = blk_mq_get_ctx(data->q); data->hctx = blk_mq_map_queue(data->q, data->cmd_flags, data->ctx->cpu); @@ -176,8 +177,6 @@ unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data) else bt = &tags->bitmap_tags; - finish_wait(&ws->wait, &wait); - /* * If destination hw queue is changed, fake wake up on * previous queue for compensating the wake up miss, so @@ -192,7 +191,7 @@ unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data) if (drop_ctx && data->ctx) blk_mq_put_ctx(data->ctx); - finish_wait(&ws->wait, &wait); + sbitmap_finish_wait(bt, ws, &wait); found_tag: return tag + tag_offset; diff --git a/drivers/target/iscsi/iscsi_target_util.c b/drivers/target/iscsi/iscsi_target_util.c index 36b742932c72..86987da86dd6 100644 --- a/drivers/target/iscsi/iscsi_target_util.c +++ b/drivers/target/iscsi/iscsi_target_util.c @@ -150,24 +150,26 @@ void iscsit_free_r2ts_from_list(struct iscsi_cmd *cmd) static int iscsit_wait_for_tag(struct se_session *se_sess, int state, int *cpup) { int tag = -1; - DEFINE_WAIT(wait); + DEFINE_SBQ_WAIT(wait); struct sbq_wait_state *ws; + struct sbitmap_queue *sbq; if (state == TASK_RUNNING) return tag; - ws = &se_sess->sess_tag_pool.ws[0]; + sbq = &se_sess->sess_tag_pool; + ws = &sbq->ws[0]; for (;;) { - prepare_to_wait_exclusive(&ws->wait, &wait, state); + sbitmap_prepare_to_wait(sbq, ws, &wait, state); if (signal_pending_state(state, current)) break; - tag = sbitmap_queue_get(&se_sess->sess_tag_pool, cpup); + tag = sbitmap_queue_get(sbq, cpup); if (tag >= 0) break; schedule(); } - finish_wait(&ws->wait, &wait); + sbitmap_finish_wait(sbq, ws, &wait); return tag; } diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h index 07f117ee19dc..f0f49bbb2617 100644 --- a/include/linux/sbitmap.h +++ b/include/linux/sbitmap.h @@ -135,6 +135,11 @@ struct sbitmap_queue { */ struct sbq_wait_state *ws; + /* + * @ws_active: count of currently active ws waitqueues + */ + atomic_t ws_active; + /** * @round_robin: Allocate bits in strict round-robin order. */ @@ -554,4 +559,33 @@ void sbitmap_queue_wake_up(struct sbitmap_queue *sbq); */ void sbitmap_queue_show(struct sbitmap_queue *sbq, struct seq_file *m); +struct sbq_wait { + int accounted; + struct wait_queue_entry wait; +}; + +#define DEFINE_SBQ_WAIT(name) \ + struct sbq_wait name = { \ + .accounted = 0, \ + .wait = { \ + .private = current, \ + .func = autoremove_wake_function, \ + .entry = LIST_HEAD_INIT((name).wait.entry), \ + } \ + } + +/* + * Wrapper around prepare_to_wait_exclusive(), which maintains some extra + * internal state. + */ +void sbitmap_prepare_to_wait(struct sbitmap_queue *sbq, + struct sbq_wait_state *ws, + struct sbq_wait *sbq_wait, int state); + +/* + * Must be paired with sbitmap_prepare_to_wait(). + */ +void sbitmap_finish_wait(struct sbitmap_queue *sbq, struct sbq_wait_state *ws, + struct sbq_wait *sbq_wait); + #endif /* __LINUX_SCALE_BITMAP_H */ diff --git a/lib/sbitmap.c b/lib/sbitmap.c index f6a9553617bd..90a295cc782c 100644 --- a/lib/sbitmap.c +++ b/lib/sbitmap.c @@ -395,6 +395,7 @@ int sbitmap_queue_init_node(struct sbitmap_queue *sbq, unsigned int depth, sbq->min_shallow_depth = UINT_MAX; sbq->wake_batch = sbq_calc_wake_batch(sbq, depth); atomic_set(&sbq->wake_index, 0); + atomic_set(&sbq->ws_active, 0); sbq->ws = kzalloc_node(SBQ_WAIT_QUEUES * sizeof(*sbq->ws), flags, node); if (!sbq->ws) { @@ -510,6 +511,9 @@ static struct sbq_wait_state *sbq_wake_ptr(struct sbitmap_queue *sbq) { int i, wake_index; + if (!atomic_read(&sbq->ws_active)) + return NULL; + wake_index = atomic_read(&sbq->wake_index); for (i = 0; i < SBQ_WAIT_QUEUES; i++) { struct sbq_wait_state *ws = &sbq->ws[wake_index]; @@ -635,6 +639,7 @@ void sbitmap_queue_show(struct sbitmap_queue *sbq, struct seq_file *m) seq_printf(m, "wake_batch=%u\n", sbq->wake_batch); seq_printf(m, "wake_index=%d\n", atomic_read(&sbq->wake_index)); + seq_printf(m, "ws_active=%d\n", atomic_read(&sbq->ws_active)); seq_puts(m, "ws={\n"); for (i = 0; i < SBQ_WAIT_QUEUES; i++) { @@ -650,3 +655,26 @@ void sbitmap_queue_show(struct sbitmap_queue *sbq, struct seq_file *m) seq_printf(m, "min_shallow_depth=%u\n", sbq->min_shallow_depth); } EXPORT_SYMBOL_GPL(sbitmap_queue_show); + +void sbitmap_prepare_to_wait(struct sbitmap_queue *sbq, + struct sbq_wait_state *ws, + struct sbq_wait *sbq_wait, int state) +{ + if (!sbq_wait->accounted) { + atomic_inc(&sbq->ws_active); + sbq_wait->accounted = 1; + } + prepare_to_wait_exclusive(&ws->wait, &sbq_wait->wait, state); +} +EXPORT_SYMBOL_GPL(sbitmap_prepare_to_wait); + +void sbitmap_finish_wait(struct sbitmap_queue *sbq, struct sbq_wait_state *ws, + struct sbq_wait *sbq_wait) +{ + finish_wait(&ws->wait, &sbq_wait->wait); + if (sbq_wait->accounted) { + atomic_dec(&sbq->ws_active); + sbq_wait->accounted = 0; + } +} +EXPORT_SYMBOL_GPL(sbitmap_finish_wait); -- 2.17.1