From nobody Mon Dec 15 22:28:31 2025 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 vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 5CD95C05027 for ; Tue, 14 Mar 2023 19:02:03 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S231268AbjCNTCB (ORCPT ); Tue, 14 Mar 2023 15:02:01 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:49638 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S229870AbjCNTBu (ORCPT ); Tue, 14 Mar 2023 15:01:50 -0400 Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [170.10.129.124]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id A72D1CA1D for ; Tue, 14 Mar 2023 12:01:13 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1678820472; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version:content-type:content-type: references:references; bh=s8sJ/cpBUh6LGMZ+lcAYSBuSqrBbcVYVRwc+yqWmsjw=; b=Dmv4+FKvYu9muybOMmhLf97d0V9b7e7nybeZOjKrpAf5gyKe775l6qXywI7EzIz28eq1Qk enJ3pNYROmNsEgpbnmTdYZNrXgevxowuzErMs8/B2heZyAJf5gO6A2VraMaKskCQJ+IjgF pngdqyyNLvmP23JrWkJnjCJDBbnuQo0= Received: from mimecast-mx02.redhat.com (mx3-rdu2.redhat.com [66.187.233.73]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id us-mta-287-Jb4Ci1vOPbS-aOjTw-mf6g-1; Tue, 14 Mar 2023 15:01:06 -0400 X-MC-Unique: Jb4Ci1vOPbS-aOjTw-mf6g-1 Received: from smtp.corp.redhat.com (int-mx01.intmail.prod.int.rdu2.redhat.com [10.11.54.1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id 30E6128004F3; Tue, 14 Mar 2023 19:01:05 +0000 (UTC) Received: from tpad.localdomain (ovpn-112-2.gru2.redhat.com [10.97.112.2]) by smtp.corp.redhat.com (Postfix) with ESMTPS id 07BDF4042AC1; Tue, 14 Mar 2023 19:01:05 +0000 (UTC) Received: by tpad.localdomain (Postfix, from userid 1000) id 80AD44039C296; Tue, 14 Mar 2023 16:00:44 -0300 (-03) Message-ID: <20230314185951.829632491@redhat.com> User-Agent: quilt/0.67 Date: Tue, 14 Mar 2023 15:59:26 -0300 From: Marcelo Tosatti To: Christoph Lameter Cc: Aaron Tomlin , Frederic Weisbecker , Andrew Morton , linux-kernel@vger.kernel.org, linux-mm@kvack.org, Russell King , Huacai Chen , Heiko Carstens , x86@kernel.org, Vlastimil Babka , Michal Hocko , Marcelo Tosatti Subject: [PATCH v6 12/12] vmstat: add pcp remote node draining via cpu_vm_stats_fold References: <20230314185914.836510860@redhat.com> MIME-Version: 1.0 X-Scanned-By: MIMEDefang 3.1 on 10.11.54.1 Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" Large NUMA systems might have significant portions=20 of system memory to be trapped in pcp queues. The number of pcp is = =20 determined by the number of processors and nodes in a system. A system = =20 with 4 processors and 2 nodes has 8 pcps which is okay. But a system = =20 with 1024 processors and 512 nodes has 512k pcps with a high potential = =20 for large amount of memory being caught in them. Enable remote node draining for the CONFIG_HAVE_CMPXCHG_LOCAL case, where vmstat_shepherd will perform the aging and draining via cpu_vm_stats_fold. Suggested-by: Vlastimil Babka Signed-off-by: Marcelo Tosatti Index: linux-vmstat-remote/mm/vmstat.c =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D --- linux-vmstat-remote.orig/mm/vmstat.c +++ linux-vmstat-remote/mm/vmstat.c @@ -928,7 +928,7 @@ static int refresh_cpu_vm_stats(bool do_ * There cannot be any access by the offline cpu and therefore * synchronization is simplified. */ -void cpu_vm_stats_fold(int cpu) +void cpu_vm_stats_fold(int cpu, bool do_pagesets) { struct pglist_data *pgdat; struct zone *zone; @@ -938,6 +938,9 @@ void cpu_vm_stats_fold(int cpu) =20 for_each_populated_zone(zone) { struct per_cpu_zonestat *pzstats; +#ifdef CONFIG_NUMA + struct per_cpu_pages *pcp =3D per_cpu_ptr(zone->per_cpu_pageset, cpu); +#endif =20 pzstats =3D per_cpu_ptr(zone->per_cpu_zonestats, cpu); =20 @@ -948,6 +951,11 @@ void cpu_vm_stats_fold(int cpu) v =3D xchg(&pzstats->vm_stat_diff[i], 0); atomic_long_add(v, &zone->vm_stat[i]); global_zone_diff[i] +=3D v; +#ifdef CONFIG_NUMA + /* 3 seconds idle till flush */ + if (do_pagesets) + pcp->expire =3D 3; +#endif } } #ifdef CONFIG_NUMA @@ -959,6 +967,38 @@ void cpu_vm_stats_fold(int cpu) zone_numa_event_add(v, zone, i); } } + + if (do_pagesets) { + cond_resched(); + /* + * Deal with draining the remote pageset of a + * processor + * + * Check if there are pages remaining in this pageset + * if not then there is nothing to expire. + */ + if (!pcp->expire || !pcp->count) + continue; + + /* + * We never drain zones local to this processor. + */ + if (zone_to_nid(zone) =3D=3D cpu_to_node(cpu)) { + pcp->expire =3D 0; + continue; + } + + WARN_ON(pcp->expire < 0); + /* + * pcp->expire is only accessed from vmstat_shepherd context, + * therefore no locking is required. + */ + if (--pcp->expire) + continue; + + if (pcp->count) + drain_zone_pages(zone, pcp); + } #endif } =20 @@ -2060,7 +2100,7 @@ static int refresh_all_vm_stats(void) =20 cpus_read_lock(); for_each_online_cpu(cpu) { - cpu_vm_stats_fold(cpu); + cpu_vm_stats_fold(cpu, true); cond_resched(); } cpus_read_unlock(); Index: linux-vmstat-remote/include/linux/vmstat.h =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D --- linux-vmstat-remote.orig/include/linux/vmstat.h +++ linux-vmstat-remote/include/linux/vmstat.h @@ -291,7 +291,7 @@ extern void __dec_zone_state(struct zone extern void __dec_node_state(struct pglist_data *, enum node_stat_item); =20 void quiet_vmstat(void); -void cpu_vm_stats_fold(int cpu); +void cpu_vm_stats_fold(int cpu, bool do_pagesets); void refresh_zone_stat_thresholds(void); =20 struct ctl_table; Index: linux-vmstat-remote/mm/page_alloc.c =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D --- linux-vmstat-remote.orig/mm/page_alloc.c +++ linux-vmstat-remote/mm/page_alloc.c @@ -8629,7 +8629,7 @@ static int page_alloc_cpu_dead(unsigned * Zero the differential counters of the dead processor * so that the vm statistics are consistent. */ - cpu_vm_stats_fold(cpu); + cpu_vm_stats_fold(cpu, false); =20 for_each_populated_zone(zone) zone_pcp_update(zone, 0);