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=-8.7 required=3.0 tests=DKIM_INVALID,DKIM_SIGNED, HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_PATCH,MAILING_LIST_MULTI,SIGNED_OFF_BY, SPF_PASS,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 C22DFC67869 for ; Tue, 11 Dec 2018 10:50:06 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.kernel.org (Postfix) with ESMTP id 884E72084A for ; Tue, 11 Dec 2018 10:50:06 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=fail reason="signature verification failed" (2048-bit key) header.d=infradead.org header.i=@infradead.org header.b="CJ3tcibv" DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 884E72084A Authentication-Results: mail.kernel.org; dmarc=none (p=none dis=none) header.from=grimberg.me 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 S1726437AbeLKKuF (ORCPT ); Tue, 11 Dec 2018 05:50:05 -0500 Received: from bombadil.infradead.org ([198.137.202.133]:58356 "EHLO bombadil.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1726439AbeLKKuF (ORCPT ); Tue, 11 Dec 2018 05:50:05 -0500 DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=infradead.org; s=bombadil.20170209; h=References:In-Reply-To:Message-Id: Date:Subject:Cc:To:From:Sender:Reply-To:MIME-Version:Content-Type: Content-Transfer-Encoding:Content-ID:Content-Description:Resent-Date: Resent-From:Resent-Sender:Resent-To:Resent-Cc:Resent-Message-ID:List-Id: List-Help:List-Unsubscribe:List-Subscribe:List-Post:List-Owner:List-Archive; bh=BGXGAtLJ071y3udVrUEE3he2KIN4yUu10pMvRzrD4Ts=; b=CJ3tcibvD6f+YT4220UHw0Zdd 1Q1RUlYWAsIfB2RMAYhSLGSeWX+TRWkTDO2DEkcREj+krSVxZ2rK/LR8vNcqYlCHM7oImca5H4piL gafSIErmbGkdi6Vx/GaD54I2XmW+9kMX3P/GJtFSiG40eGbDur61v4QvE+iUsPXcPUYAoOe5UCHDt TXV01AYrwKVU6zUgizcec/htw4VIzIMtqfPZgDh57ggWh93t15tyim0Ac6Lz8b0DRvBtDE5mVaypF THB0S0c2B4gT2oJhyNmP6PoDbd3E+TOCeRdjPJn/qId57+tkMYHs/n05zwD1KQ5X0hbwwxtf322IU v8NPYpn8A==; Received: from [2601:647:4800:973f:7888:b13c:bff:87b0] (helo=bombadil.infradead.org) by bombadil.infradead.org with esmtpsa (Exim 4.90_1 #2 (Red Hat Linux)) id 1gWfbe-0004p6-4k; Tue, 11 Dec 2018 10:49:38 +0000 From: Sagi Grimberg To: linux-nvme@lists.infradead.org Cc: Christoph Hellwig , Keith Busch , linux-block@vger.kernel.org, Jens Axboe Subject: [PATCH 4/5] nvme-tcp: support separate queue maps for read and write Date: Tue, 11 Dec 2018 02:49:34 -0800 Message-Id: <20181211104936.25333-5-sagi@grimberg.me> X-Mailer: git-send-email 2.17.1 In-Reply-To: <20181211104936.25333-1-sagi@grimberg.me> References: <20181211104936.25333-1-sagi@grimberg.me> Sender: linux-block-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-block@vger.kernel.org Signed-off-by: Sagi Grimberg --- drivers/nvme/host/tcp.c | 53 ++++++++++++++++++++++++++++++++++++----- 1 file changed, 47 insertions(+), 6 deletions(-) diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 15543358e245..5c0ba99fb105 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -1215,7 +1215,7 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl); struct nvme_tcp_queue *queue = &ctrl->queues[qid]; struct linger sol = { .l_onoff = 1, .l_linger = 0 }; - int ret, opt, rcv_pdu_size; + int ret, opt, rcv_pdu_size, n; queue->ctrl = ctrl; INIT_LIST_HEAD(&queue->send_list); @@ -1271,7 +1271,8 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, } queue->sock->sk->sk_allocation = GFP_ATOMIC; - queue->io_cpu = (qid == 0) ? 0 : qid - 1; + n = (qid ? qid - 1 : 0) % num_online_cpus(); + queue->io_cpu = cpumask_next_wrap(n - 1, cpu_online_mask, -1, false); queue->request = NULL; queue->data_remaining = 0; queue->ddgst_remaining = 0; @@ -1433,6 +1434,7 @@ static struct blk_mq_tag_set *nvme_tcp_alloc_tagset(struct nvme_ctrl *nctrl, set->driver_data = ctrl; set->nr_hw_queues = nctrl->queue_count - 1; set->timeout = NVME_IO_TIMEOUT; + set->nr_maps = 2 /* default + read */; } ret = blk_mq_alloc_tag_set(set); @@ -1527,7 +1529,12 @@ static int nvme_tcp_alloc_io_queues(struct nvme_ctrl *ctrl) static unsigned int nvme_tcp_nr_io_queues(struct nvme_ctrl *ctrl) { - return min(ctrl->queue_count - 1, num_online_cpus()); + unsigned int nr_io_queues; + + nr_io_queues = min(ctrl->opts->nr_io_queues, num_online_cpus()); + nr_io_queues += min(ctrl->opts->nr_write_queues, num_online_cpus()); + + return nr_io_queues; } static int nvme_alloc_io_queues(struct nvme_ctrl *ctrl) @@ -2052,6 +2059,38 @@ static blk_status_t nvme_tcp_queue_rq(struct blk_mq_hw_ctx *hctx, return BLK_STS_OK; } +static int nvme_tcp_map_queues(struct blk_mq_tag_set *set) +{ + struct nvme_tcp_ctrl *ctrl = set->driver_data; + struct blk_mq_queue_map *map; + + if (ctrl->ctrl.opts->nr_write_queues) { + /* separate read/write queues */ + map = &set->map[HCTX_TYPE_DEFAULT]; + map->queue_offset = 0; + map->nr_queues = ctrl->ctrl.opts->nr_write_queues; + blk_mq_map_queues(map); + + map = &set->map[HCTX_TYPE_READ]; + map->nr_queues = ctrl->ctrl.opts->nr_io_queues; + map->queue_offset = ctrl->ctrl.opts->nr_write_queues; + blk_mq_map_queues(map); + } else { + /* mixed read/write queues */ + map = &set->map[HCTX_TYPE_DEFAULT]; + map->queue_offset = 0; + map->nr_queues = ctrl->ctrl.opts->nr_io_queues; + blk_mq_map_queues(map); + + map = &set->map[HCTX_TYPE_READ]; + map->queue_offset = 0; + map->nr_queues = ctrl->ctrl.opts->nr_io_queues; + blk_mq_map_queues(map); + } + + return 0; +} + static struct blk_mq_ops nvme_tcp_mq_ops = { .queue_rq = nvme_tcp_queue_rq, .complete = nvme_complete_rq, @@ -2059,6 +2098,7 @@ static struct blk_mq_ops nvme_tcp_mq_ops = { .exit_request = nvme_tcp_exit_request, .init_hctx = nvme_tcp_init_hctx, .timeout = nvme_tcp_timeout, + .map_queues = nvme_tcp_map_queues, }; static struct blk_mq_ops nvme_tcp_admin_mq_ops = { @@ -2113,7 +2153,7 @@ static struct nvme_ctrl *nvme_tcp_create_ctrl(struct device *dev, INIT_LIST_HEAD(&ctrl->list); ctrl->ctrl.opts = opts; - ctrl->ctrl.queue_count = opts->nr_io_queues + 1; /* +1 for admin queue */ + ctrl->ctrl.queue_count = opts->nr_io_queues + opts->nr_write_queues + 1; ctrl->ctrl.sqsize = opts->queue_size - 1; ctrl->ctrl.kato = opts->kato; @@ -2155,7 +2195,7 @@ static struct nvme_ctrl *nvme_tcp_create_ctrl(struct device *dev, goto out_free_ctrl; } - ctrl->queues = kcalloc(opts->nr_io_queues + 1, sizeof(*ctrl->queues), + ctrl->queues = kcalloc(ctrl->ctrl.queue_count, sizeof(*ctrl->queues), GFP_KERNEL); if (!ctrl->queues) { ret = -ENOMEM; @@ -2206,7 +2246,8 @@ static struct nvmf_transport_ops nvme_tcp_transport = { .required_opts = NVMF_OPT_TRADDR, .allowed_opts = NVMF_OPT_TRSVCID | NVMF_OPT_RECONNECT_DELAY | NVMF_OPT_HOST_TRADDR | NVMF_OPT_CTRL_LOSS_TMO | - NVMF_OPT_HDR_DIGEST | NVMF_OPT_DATA_DIGEST, + NVMF_OPT_HDR_DIGEST | NVMF_OPT_DATA_DIGEST | + NVMF_OPT_NR_IO_QUEUES, .create_ctrl = nvme_tcp_create_ctrl, }; -- 2.17.1 From mboxrd@z Thu Jan 1 00:00:00 1970 From: sagi@grimberg.me (Sagi Grimberg) Date: Tue, 11 Dec 2018 02:49:34 -0800 Subject: [PATCH 4/5] nvme-tcp: support separate queue maps for read and write In-Reply-To: <20181211104936.25333-1-sagi@grimberg.me> References: <20181211104936.25333-1-sagi@grimberg.me> Message-ID: <20181211104936.25333-5-sagi@grimberg.me> Signed-off-by: Sagi Grimberg --- drivers/nvme/host/tcp.c | 53 ++++++++++++++++++++++++++++++++++++----- 1 file changed, 47 insertions(+), 6 deletions(-) diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 15543358e245..5c0ba99fb105 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -1215,7 +1215,7 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl); struct nvme_tcp_queue *queue = &ctrl->queues[qid]; struct linger sol = { .l_onoff = 1, .l_linger = 0 }; - int ret, opt, rcv_pdu_size; + int ret, opt, rcv_pdu_size, n; queue->ctrl = ctrl; INIT_LIST_HEAD(&queue->send_list); @@ -1271,7 +1271,8 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, } queue->sock->sk->sk_allocation = GFP_ATOMIC; - queue->io_cpu = (qid == 0) ? 0 : qid - 1; + n = (qid ? qid - 1 : 0) % num_online_cpus(); + queue->io_cpu = cpumask_next_wrap(n - 1, cpu_online_mask, -1, false); queue->request = NULL; queue->data_remaining = 0; queue->ddgst_remaining = 0; @@ -1433,6 +1434,7 @@ static struct blk_mq_tag_set *nvme_tcp_alloc_tagset(struct nvme_ctrl *nctrl, set->driver_data = ctrl; set->nr_hw_queues = nctrl->queue_count - 1; set->timeout = NVME_IO_TIMEOUT; + set->nr_maps = 2 /* default + read */; } ret = blk_mq_alloc_tag_set(set); @@ -1527,7 +1529,12 @@ static int nvme_tcp_alloc_io_queues(struct nvme_ctrl *ctrl) static unsigned int nvme_tcp_nr_io_queues(struct nvme_ctrl *ctrl) { - return min(ctrl->queue_count - 1, num_online_cpus()); + unsigned int nr_io_queues; + + nr_io_queues = min(ctrl->opts->nr_io_queues, num_online_cpus()); + nr_io_queues += min(ctrl->opts->nr_write_queues, num_online_cpus()); + + return nr_io_queues; } static int nvme_alloc_io_queues(struct nvme_ctrl *ctrl) @@ -2052,6 +2059,38 @@ static blk_status_t nvme_tcp_queue_rq(struct blk_mq_hw_ctx *hctx, return BLK_STS_OK; } +static int nvme_tcp_map_queues(struct blk_mq_tag_set *set) +{ + struct nvme_tcp_ctrl *ctrl = set->driver_data; + struct blk_mq_queue_map *map; + + if (ctrl->ctrl.opts->nr_write_queues) { + /* separate read/write queues */ + map = &set->map[HCTX_TYPE_DEFAULT]; + map->queue_offset = 0; + map->nr_queues = ctrl->ctrl.opts->nr_write_queues; + blk_mq_map_queues(map); + + map = &set->map[HCTX_TYPE_READ]; + map->nr_queues = ctrl->ctrl.opts->nr_io_queues; + map->queue_offset = ctrl->ctrl.opts->nr_write_queues; + blk_mq_map_queues(map); + } else { + /* mixed read/write queues */ + map = &set->map[HCTX_TYPE_DEFAULT]; + map->queue_offset = 0; + map->nr_queues = ctrl->ctrl.opts->nr_io_queues; + blk_mq_map_queues(map); + + map = &set->map[HCTX_TYPE_READ]; + map->queue_offset = 0; + map->nr_queues = ctrl->ctrl.opts->nr_io_queues; + blk_mq_map_queues(map); + } + + return 0; +} + static struct blk_mq_ops nvme_tcp_mq_ops = { .queue_rq = nvme_tcp_queue_rq, .complete = nvme_complete_rq, @@ -2059,6 +2098,7 @@ static struct blk_mq_ops nvme_tcp_mq_ops = { .exit_request = nvme_tcp_exit_request, .init_hctx = nvme_tcp_init_hctx, .timeout = nvme_tcp_timeout, + .map_queues = nvme_tcp_map_queues, }; static struct blk_mq_ops nvme_tcp_admin_mq_ops = { @@ -2113,7 +2153,7 @@ static struct nvme_ctrl *nvme_tcp_create_ctrl(struct device *dev, INIT_LIST_HEAD(&ctrl->list); ctrl->ctrl.opts = opts; - ctrl->ctrl.queue_count = opts->nr_io_queues + 1; /* +1 for admin queue */ + ctrl->ctrl.queue_count = opts->nr_io_queues + opts->nr_write_queues + 1; ctrl->ctrl.sqsize = opts->queue_size - 1; ctrl->ctrl.kato = opts->kato; @@ -2155,7 +2195,7 @@ static struct nvme_ctrl *nvme_tcp_create_ctrl(struct device *dev, goto out_free_ctrl; } - ctrl->queues = kcalloc(opts->nr_io_queues + 1, sizeof(*ctrl->queues), + ctrl->queues = kcalloc(ctrl->ctrl.queue_count, sizeof(*ctrl->queues), GFP_KERNEL); if (!ctrl->queues) { ret = -ENOMEM; @@ -2206,7 +2246,8 @@ static struct nvmf_transport_ops nvme_tcp_transport = { .required_opts = NVMF_OPT_TRADDR, .allowed_opts = NVMF_OPT_TRSVCID | NVMF_OPT_RECONNECT_DELAY | NVMF_OPT_HOST_TRADDR | NVMF_OPT_CTRL_LOSS_TMO | - NVMF_OPT_HDR_DIGEST | NVMF_OPT_DATA_DIGEST, + NVMF_OPT_HDR_DIGEST | NVMF_OPT_DATA_DIGEST | + NVMF_OPT_NR_IO_QUEUES, .create_ctrl = nvme_tcp_create_ctrl, }; -- 2.17.1