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=-16.5 required=3.0 tests=BAYES_00,DKIMWL_WL_HIGH, DKIM_SIGNED,DKIM_VALID,DKIM_VALID_AU,HEADER_FROM_DIFFERENT_DOMAINS, INCLUDES_CR_TRAILER,INCLUDES_PATCH,MAILING_LIST_MULTI,SPF_HELO_NONE,SPF_PASS autolearn=unavailable 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 746E6C4338F for ; Wed, 18 Aug 2021 09:31:52 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 57AE660F39 for ; Wed, 18 Aug 2021 09:31:52 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S232569AbhHRJcY (ORCPT ); Wed, 18 Aug 2021 05:32:24 -0400 Received: from us-smtp-delivery-124.mimecast.com ([170.10.133.124]:24660 "EHLO us-smtp-delivery-124.mimecast.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S232769AbhHRJaH (ORCPT ); Wed, 18 Aug 2021 05:30:07 -0400 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1629278952; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=jEAum1p+Sq90qsNOW7FriDcJ9zjYOTdm8PupmSbR43g=; b=BSqGSj+Mktc04IuFzrm6RdPvZuWCR7hcFZ8KtgJ6Q9lbewPoxwUtx6L/p8XDAsjOcfC5xx inlDtBO+mHrN13DMf6lM5mf29eyEWCR44WrbjdISNlnOJ1zre5JwbS7Dvaky3b0j9VmDJJ 0AUMZSOtY0PRaGxBYbGXxpx7eJXGX3E= Received: from mimecast-mx01.redhat.com (mimecast-mx01.redhat.com [209.132.183.4]) (Using TLS) by relay.mimecast.com with ESMTP id us-mta-220-2yZnqJbiOvmmht-C1BXRvg-1; Wed, 18 Aug 2021 05:29:11 -0400 X-MC-Unique: 2yZnqJbiOvmmht-C1BXRvg-1 Received: from smtp.corp.redhat.com (int-mx06.intmail.prod.int.phx2.redhat.com [10.5.11.16]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx01.redhat.com (Postfix) with ESMTPS id 3F36E1009600; Wed, 18 Aug 2021 09:29:10 +0000 (UTC) Received: from localhost (ovpn-8-40.pek2.redhat.com [10.72.8.40]) by smtp.corp.redhat.com (Postfix) with ESMTP id 981CF5C1D1; Wed, 18 Aug 2021 09:29:05 +0000 (UTC) From: Ming Lei To: Thomas Gleixner , Jens Axboe Cc: linux-kernel@vger.kernel.org, linux-block@vger.kernel.org, Christoph Hellwig , Ming Lei Subject: [PATCH V2 7/7] blk-mq: build default queue map via group_cpus_evenly() Date: Wed, 18 Aug 2021 17:28:12 +0800 Message-Id: <20210818092812.787558-8-ming.lei@redhat.com> In-Reply-To: <20210818092812.787558-1-ming.lei@redhat.com> References: <20210818092812.787558-1-ming.lei@redhat.com> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Scanned-By: MIMEDefang 2.79 on 10.5.11.16 Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org The default queue mapping builder of blk_mq_map_queues doesn't take NUMA topo into account, so the built mapping is pretty bad, since CPUs belonging to different NUMA node are assigned to same queue. It is observed that IOPS drops by ~30% when running two jobs on same hctx of null_blk from two CPUs belonging to two NUMA nodes compared with from same NUMA node. Address the issue by reusing group_cpus_evenly() for addressing the issue since group_cpus_evenly() does group cpus according to CPU/NUMA locality. Lots of drivers may benefit from the change, such as nvme pci poll, nvme tcp, ... Signed-off-by: Ming Lei --- block/blk-mq-cpumap.c | 65 ++++++++++--------------------------------- 1 file changed, 14 insertions(+), 51 deletions(-) diff --git a/block/blk-mq-cpumap.c b/block/blk-mq-cpumap.c index 3db84d3197f1..b610a55eea66 100644 --- a/block/blk-mq-cpumap.c +++ b/block/blk-mq-cpumap.c @@ -10,67 +10,30 @@ #include #include #include +#include #include #include "blk.h" #include "blk-mq.h" -static int queue_index(struct blk_mq_queue_map *qmap, - unsigned int nr_queues, const int q) -{ - return qmap->queue_offset + (q % nr_queues); -} - -static int get_first_sibling(unsigned int cpu) -{ - unsigned int ret; - - ret = cpumask_first(topology_sibling_cpumask(cpu)); - if (ret < nr_cpu_ids) - return ret; - - return cpu; -} - int blk_mq_map_queues(struct blk_mq_queue_map *qmap) { - unsigned int *map = qmap->mq_map; - unsigned int nr_queues = qmap->nr_queues; - unsigned int cpu, first_sibling, q = 0; - - for_each_possible_cpu(cpu) - map[cpu] = -1; + const struct cpumask *masks; + unsigned int queue, cpu; - /* - * Spread queues among present CPUs first for minimizing - * count of dead queues which are mapped by all un-present CPUs - */ - for_each_present_cpu(cpu) { - if (q >= nr_queues) - break; - map[cpu] = queue_index(qmap, nr_queues, q++); - } + masks = group_cpus_evenly(qmap->nr_queues); + if (!masks) + goto fallback; - for_each_possible_cpu(cpu) { - if (map[cpu] != -1) - continue; - /* - * First do sequential mapping between CPUs and queues. - * In case we still have CPUs to map, and we have some number of - * threads per cores then map sibling threads to the same queue - * for performance optimizations. - */ - if (q < nr_queues) { - map[cpu] = queue_index(qmap, nr_queues, q++); - } else { - first_sibling = get_first_sibling(cpu); - if (first_sibling == cpu) - map[cpu] = queue_index(qmap, nr_queues, q++); - else - map[cpu] = map[first_sibling]; - } + for (queue = 0; queue < qmap->nr_queues; queue++) { + for_each_cpu(cpu, &masks[queue]) + qmap->mq_map[cpu] = qmap->queue_offset + queue; } - + kfree(masks); + return 0; + fallback: + for_each_possible_cpu(cpu) + qmap->mq_map[cpu] = qmap->queue_offset; return 0; } EXPORT_SYMBOL_GPL(blk_mq_map_queues); -- 2.31.1