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 mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 515AFC433F5 for ; Thu, 11 Nov 2021 02:44:03 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 38A236113B for ; Thu, 11 Nov 2021 02:44:03 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S234289AbhKKCqu (ORCPT ); Wed, 10 Nov 2021 21:46:50 -0500 Received: from mail.kernel.org ([198.145.29.99]:51956 "EHLO mail.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S234032AbhKKCqu (ORCPT ); Wed, 10 Nov 2021 21:46:50 -0500 Received: by mail.kernel.org (Postfix) with ESMTPSA id 9395161208; Thu, 11 Nov 2021 02:44:01 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=linux-foundation.org; s=korg; t=1636598641; bh=oDKkPx1ds5PALp6YaPKy9BmN53tmcH79sO4jjaBCqLI=; h=Date:From:To:Subject:From; b=H5S5KSetLrSantfjtGRUixQkO0hTjv9f3QRYipPbJ1xL9b9qcoYzM3FCTiEdUKrvb mdM9BS2ocmerYZsjeULGBaRS912V6HLDTGceYbTMH4UJAREhfqGOmtNeddP1CB+CJf Uv5yWDhGBhwOfcMRyKeLNolq+CDZc0+BXMDmrBR8= Date: Wed, 10 Nov 2021 18:44:01 -0800 From: akpm@linux-foundation.org To: anshuman.khandual@arm.com, bharata@amd.com, kamezawa.hiroyu@jp.fujitsu.com, krupa.ramakrishnan@amd.com, lee.schermerhorn@hp.com, mgorman@suse.de, mm-commits@vger.kernel.org, Sadagopan.Srinivasan@amd.com Subject: [merged] mm-page_alloc-use-accumulated-load-when-building-node-fallback-list.patch removed from -mm tree Message-ID: <20211111024401.I-g-gOddb%akpm@linux-foundation.org> User-Agent: s-nail v14.8.16 Precedence: bulk Reply-To: linux-kernel@vger.kernel.org List-ID: X-Mailing-List: mm-commits@vger.kernel.org The patch titled Subject: mm/page_alloc: use accumulated load when building node fallback list has been removed from the -mm tree. Its filename was mm-page_alloc-use-accumulated-load-when-building-node-fallback-list.patch This patch was dropped because it was merged into mainline or a subsystem tree ------------------------------------------------------ From: Krupa Ramakrishnan Subject: mm/page_alloc: use accumulated load when building node fallback list In build_zonelists(), when the fallback list is built for the nodes, the node load gets reinitialized during each iteration. This results in nodes with same distances occupying the same slot in different node fallback lists rather than appearing in the intended round- robin manner. This results in one node getting picked for allocation more compared to other nodes with the same distance. As an example, consider a 4 node system with the following distance matrix. Node 0 1 2 3 ---------------- 0 10 12 32 32 1 12 10 32 32 2 32 32 10 12 3 32 32 12 10 For this case, the node fallback list gets built like this: Node Fallback list --------------------- 0 0 1 2 3 1 1 0 3 2 2 2 3 0 1 3 3 2 0 1 <-- Unexpected fallback order In the fallback list for nodes 2 and 3, the nodes 0 and 1 appear in the same order which results in more allocations getting satisfied from node 0 compared to node 1. The effect of this on remote memory bandwidth as seen by stream benchmark is shown below: Case 1: Bandwidth from cores on nodes 2 & 3 to memory on nodes 0 & 1 (numactl -m 0,1 ./stream_lowOverhead ... --cores ) Case 2: Bandwidth from cores on nodes 0 & 1 to memory on nodes 2 & 3 (numactl -m 2,3 ./stream_lowOverhead ... --cores ) ---------------------------------------- BANDWIDTH (MB/s) TEST Case 1 Case 2 ---------------------------------------- COPY 57479.6 110791.8 SCALE 55372.9 105685.9 ADD 50460.6 96734.2 TRIADD 50397.6 97119.1 ---------------------------------------- The bandwidth drop in Case 1 occurs because most of the allocations get satisfied by node 0 as it appears first in the fallback order for both nodes 2 and 3. This can be fixed by accumulating the node load in build_zonelists() rather than reinitializing it during each iteration. With this the nodes with the same distance rightly get assigned in the round robin manner. In fact this was how it was originally until the commit f0c0b2b808f2 ("change zonelist order: zonelist order selection logic") dropped the load accumulation and resorted to initializing the load during each iteration. While zonelist ordering was removed by commit c9bff3eebc09 ("mm, page_alloc: rip out ZONELIST_ORDER_ZONE"), the change to the node load accumulation in build_zonelists() remained. So essentially this patch reverts back to the accumulated node load logic. After this fix, the fallback order gets built like this: Node Fallback list ------------------ 0 0 1 2 3 1 1 0 3 2 2 2 3 0 1 3 3 2 1 0 <-- Note the change here The bandwidth in Case 1 improves and matches Case 2 as shown below. ---------------------------------------- BANDWIDTH (MB/s) TEST Case 1 Case 2 ---------------------------------------- COPY 110438.9 110107.2 SCALE 105930.5 105817.5 ADD 97005.1 96159.8 TRIADD 97441.5 96757.1 ---------------------------------------- The correctness of the fallback list generation has been verified for the above node configuration where the node 3 starts as memory-less node and comes up online only during memory hotplug. [bharata@amd.com: Added changelog, review, test validation] Link: https://lkml.kernel.org/r/20210830121603.1081-3-bharata@amd.com Fixes: f0c0b2b808f2 ("change zonelist order: zonelist order selection logic") Signed-off-by: Krupa Ramakrishnan Co-developed-by: Sadagopan Srinivasan Signed-off-by: Sadagopan Srinivasan Signed-off-by: Bharata B Rao Acked-by: Mel Gorman Reviewed-by: Anshuman Khandual Cc: KAMEZAWA Hiroyuki Cc: Lee Schermerhorn Signed-off-by: Andrew Morton --- mm/page_alloc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) --- a/mm/page_alloc.c~mm-page_alloc-use-accumulated-load-when-building-node-fallback-list +++ a/mm/page_alloc.c @@ -6253,7 +6253,7 @@ static void build_zonelists(pg_data_t *p */ if (node_distance(local_node, node) != node_distance(local_node, prev_node)) - node_load[node] = load; + node_load[node] += load; node_order[nr_nodes++] = node; prev_node = node; _ Patches currently in -mm which might be from krupa.ramakrishnan@amd.com are