From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754117AbdBARxi (ORCPT ); Wed, 1 Feb 2017 12:53:38 -0500 Received: from mx0b-00082601.pphosted.com ([67.231.153.30]:42036 "EHLO mx0b-00082601.pphosted.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753678AbdBARxU (ORCPT ); Wed, 1 Feb 2017 12:53:20 -0500 Smtp-Origin-Hostprefix: devbig From: Shaohua Li Smtp-Origin-Hostname: devbig638.prn2.facebook.com To: , CC: , , Smtp-Origin-Cluster: prn2c22 Subject: [PATCH V2 1/3] blk-mq: allocate blk_mq_tags and requests in correct node Date: Wed, 1 Feb 2017 09:53:14 -0800 Message-ID: X-Mailer: git-send-email 2.9.3 X-FB-Internal: Safe MIME-Version: 1.0 Content-Type: text/plain X-Proofpoint-Spam-Reason: safe X-FB-Internal: Safe X-Proofpoint-Virus-Version: vendor=fsecure engine=2.50.10432:,, definitions=2017-02-01_13:,, signatures=0 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org blk_mq_tags/requests of specific hardware queue are mostly used in specific cpus, which might not be in the same numa node as disk. For example, a nvme card is in node 0. half hardware queue will be used by node 0, the other node 1. Signed-off-by: Shaohua Li --- block/blk-mq.c | 21 +++++++++++++++------ 1 file changed, 15 insertions(+), 6 deletions(-) diff --git a/block/blk-mq.c b/block/blk-mq.c index 48df5fd..888077c 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1666,16 +1666,20 @@ struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set, unsigned int reserved_tags) { struct blk_mq_tags *tags; + int node; + + node = blk_mq_hw_queue_to_node(set->mq_map, hctx_idx); + if (node == NUMA_NO_NODE) + node = set->numa_node; - tags = blk_mq_init_tags(nr_tags, reserved_tags, - set->numa_node, + tags = blk_mq_init_tags(nr_tags, reserved_tags, node, BLK_MQ_FLAG_TO_ALLOC_POLICY(set->flags)); if (!tags) return NULL; tags->rqs = kzalloc_node(nr_tags * sizeof(struct request *), GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY, - set->numa_node); + node); if (!tags->rqs) { blk_mq_free_tags(tags); return NULL; @@ -1683,7 +1687,7 @@ struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set, tags->static_rqs = kzalloc_node(nr_tags * sizeof(struct request *), GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY, - set->numa_node); + node); if (!tags->static_rqs) { kfree(tags->rqs); blk_mq_free_tags(tags); @@ -1703,6 +1707,11 @@ int blk_mq_alloc_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags, { unsigned int i, j, entries_per_page, max_order = 4; size_t rq_size, left; + int node; + + node = blk_mq_hw_queue_to_node(set->mq_map, hctx_idx); + if (node == NUMA_NO_NODE) + node = set->numa_node; INIT_LIST_HEAD(&tags->page_list); @@ -1724,7 +1733,7 @@ int blk_mq_alloc_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags, this_order--; do { - page = alloc_pages_node(set->numa_node, + page = alloc_pages_node(node, GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY | __GFP_ZERO, this_order); if (page) @@ -1757,7 +1766,7 @@ int blk_mq_alloc_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags, if (set->ops->init_request) { if (set->ops->init_request(set->driver_data, rq, hctx_idx, i, - set->numa_node)) { + node)) { tags->static_rqs[i] = NULL; goto fail; } -- 2.9.3