From nobody Mon Feb 9 05:01:45 2026 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 965EAEB64D7 for ; Wed, 21 Jun 2023 09:21:15 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S230445AbjFUJVO (ORCPT ); Wed, 21 Jun 2023 05:21:14 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:55356 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S230148AbjFUJVL (ORCPT ); Wed, 21 Jun 2023 05:21:11 -0400 Received: from chinatelecom.cn (prt-mail.chinatelecom.cn [42.123.76.223]) by lindbergh.monkeyblade.net (Postfix) with ESMTP id 9DBF51B4 for ; Wed, 21 Jun 2023 02:21:09 -0700 (PDT) HMM_SOURCE_IP: 172.18.0.48:41464.1037017731 HMM_ATTACHE_NUM: 0000 HMM_SOURCE_TYPE: SMTP Received: from clientip-36.111.64.85 (unknown [172.18.0.48]) by chinatelecom.cn (HERMES) with SMTP id A0D352800BB; Wed, 21 Jun 2023 17:21:01 +0800 (CST) X-189-SAVE-TO-SEND: +liuq131@chinatelecom.cn Received: from ([36.111.64.85]) by app0024 with ESMTP id fa69a156f7714ae4ae7368d0327bf29c for akpm@linux-foundation.org; Wed, 21 Jun 2023 17:21:07 CST X-Transaction-ID: fa69a156f7714ae4ae7368d0327bf29c X-Real-From: liuq131@chinatelecom.cn X-Receive-IP: 36.111.64.85 X-MEDUSA-Status: 0 Sender: liuq131@chinatelecom.cn From: liuq To: akpm@linux-foundation.org Cc: ying.huang@intel.com, linux-mm@kvack.org, linux-kernel@vger.kernel.org, liuq Subject: [PATCH v3] mm/min_free_kbytes: modify min_free_kbytes calculation rules Date: Wed, 21 Jun 2023 17:20:48 +0800 Message-Id: <20230621092048.5242-1-liuq131@chinatelecom.cn> X-Mailer: git-send-email 2.27.0 MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" The current calculation of min_free_kbytes only uses ZONE_DMA and ZONE_NORMAL pages,but the ZONE_MOVABLE zone->_watermark[WMARK_MIN] will also divide part of min_free_kbytes.This will cause the min watermark of ZONE_NORMAL to be too small in the presence of ZONE_MOVEABLE. __GFP_HIGH and PF_MEMALLOC allocations usually don't need movable zone pages, so just like ZONE_HIGHMEM, cap pages_min to a small value in __setup_per_zone_wmarks. On my testing machine with 16GB of memory (transparent hugepage is turned off by default, and movablecore=3D12G is configured) The following is a comparative test data of watermark_min no patch add patch ZONE_DMA 1 8 ZONE_DMA32 151 709 ZONE_NORMAL 233 1113 ZONE_MOVABLE 1434 128 min_free_kbytes 7288 7326 Signed-off-by: liuq --- mm/page_alloc.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 47421bedc12b..590ed8725e09 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -6362,9 +6362,9 @@ static void __setup_per_zone_wmarks(void) struct zone *zone; unsigned long flags; =20 - /* Calculate total number of !ZONE_HIGHMEM pages */ + /* Calculate total number of !ZONE_HIGHMEM and !ZONE_MOVABLE pages */ for_each_zone(zone) { - if (!is_highmem(zone)) + if (!is_highmem(zone) && zone_idx(zone) !=3D ZONE_MOVABLE) lowmem_pages +=3D zone_managed_pages(zone); } =20 @@ -6374,15 +6374,15 @@ static void __setup_per_zone_wmarks(void) spin_lock_irqsave(&zone->lock, flags); tmp =3D (u64)pages_min * zone_managed_pages(zone); do_div(tmp, lowmem_pages); - if (is_highmem(zone)) { + if (is_highmem(zone) || zone_idx(zone) =3D=3D ZONE_MOVABLE) { /* * __GFP_HIGH and PF_MEMALLOC allocations usually don't - * need highmem pages, so cap pages_min to a small - * value here. + * need highmem and movable zones pages, so cap pages_min + * to a small value here. * * The WMARK_HIGH-WMARK_LOW and (WMARK_LOW-WMARK_MIN) * deltas control async page reclaim, and so should - * not be capped for highmem. + * not be capped for highmem and movable zones. */ unsigned long min_pages; =20 --=20 2.27.0