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 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id A3C32C433FE for ; Fri, 15 Oct 2021 02:20:59 +0000 (UTC) Received: from kanga.kvack.org (kanga.kvack.org [205.233.56.17]) by mail.kernel.org (Postfix) with ESMTP id 043E0610D1 for ; Fri, 15 Oct 2021 02:20:58 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.4.1 mail.kernel.org 043E0610D1 Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=huawei.com Authentication-Results: mail.kernel.org; spf=pass smtp.mailfrom=kvack.org Received: by kanga.kvack.org (Postfix) id 8BB466B006C; Thu, 14 Oct 2021 22:20:58 -0400 (EDT) Received: by kanga.kvack.org (Postfix, from userid 40) id 843766B0071; Thu, 14 Oct 2021 22:20:58 -0400 (EDT) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id 6BE636B0072; Thu, 14 Oct 2021 22:20:58 -0400 (EDT) X-Delivered-To: linux-mm@kvack.org Received: from forelay.hostedemail.com (smtprelay0136.hostedemail.com [216.40.44.136]) by kanga.kvack.org (Postfix) with ESMTP id 5734F6B006C for ; Thu, 14 Oct 2021 22:20:58 -0400 (EDT) Received: from smtpin13.hostedemail.com (10.5.19.251.rfc1918.com [10.5.19.251]) by forelay05.hostedemail.com (Postfix) with ESMTP id 16DCE1827E91F for ; Fri, 15 Oct 2021 02:20:58 +0000 (UTC) X-FDA: 78697068996.13.763B81C Received: from szxga02-in.huawei.com (szxga02-in.huawei.com [45.249.212.188]) by imf21.hostedemail.com (Postfix) with ESMTP id 2A0CCD04170E for ; Fri, 15 Oct 2021 02:20:56 +0000 (UTC) Received: from dggemv704-chm.china.huawei.com (unknown [172.30.72.56]) by szxga02-in.huawei.com (SkyGuard) with ESMTP id 4HVqdM43fBzbfXP; Fri, 15 Oct 2021 10:16:23 +0800 (CST) Received: from dggpemm500002.china.huawei.com (7.185.36.229) by dggemv704-chm.china.huawei.com (10.3.19.47) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.2308.8; Fri, 15 Oct 2021 10:20:49 +0800 Received: from [10.174.178.178] (10.174.178.178) by dggpemm500002.china.huawei.com (7.185.36.229) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.2308.8; Fri, 15 Oct 2021 10:20:48 +0800 Message-ID: Date: Fri, 15 Oct 2021 10:20:48 +0800 MIME-Version: 1.0 User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:91.0) Gecko/20100101 Thunderbird/91.0.3 Subject: Re: [PATCH] mm/vmalloc: fix numa spreading for large hash tables To: Uladzislau Rezki CC: , , , , , , References: <20210928121040.2547407-1-chenwandun@huawei.com> <20211014100157.GA1844@pc638.lan> From: Chen Wandun In-Reply-To: <20211014100157.GA1844@pc638.lan> Content-Type: text/plain; charset="UTF-8"; format=flowed X-Originating-IP: [10.174.178.178] X-ClientProxiedBy: dggems706-chm.china.huawei.com (10.3.19.183) To dggpemm500002.china.huawei.com (7.185.36.229) X-CFilter-Loop: Reflected X-Stat-Signature: gwqfwpsxiuyi9jua1g4j6dkcays9b66m Authentication-Results: imf21.hostedemail.com; dkim=none; spf=pass (imf21.hostedemail.com: domain of chenwandun@huawei.com designates 45.249.212.188 as permitted sender) smtp.mailfrom=chenwandun@huawei.com; dmarc=pass (policy=none) header.from=huawei.com X-Rspamd-Server: rspam05 X-Rspamd-Queue-Id: 2A0CCD04170E X-HE-Tag: 1634264456-832291 Content-Transfer-Encoding: quoted-printable X-Bogosity: Ham, tests=bogofilter, spamicity=0.000000, version=1.2.4 Sender: owner-linux-mm@kvack.org Precedence: bulk X-Loop: owner-majordomo@kvack.org List-ID: =E5=9C=A8 2021/10/14 18:01, Uladzislau Rezki =E5=86=99=E9=81=93: > On Tue, Sep 28, 2021 at 08:10:40PM +0800, Chen Wandun wrote: >> Eric Dumazet reported a strange numa spreading info in [1], and found >> commit 121e6f3258fe ("mm/vmalloc: hugepage vmalloc mappings") introduc= ed >> this issue [2]. >> >> Dig into the difference before and after this patch, page allocation h= as >> some difference: >> >> before: >> alloc_large_system_hash >> __vmalloc >> __vmalloc_node(..., NUMA_NO_NODE, ...) >> __vmalloc_node_range >> __vmalloc_area_node >> alloc_page /* because NUMA_NO_NODE, so choose all= oc_page branch */ >> alloc_pages_current >> alloc_page_interleave /* can be proved by= print policy mode */ >> >> after: >> alloc_large_system_hash >> __vmalloc >> __vmalloc_node(..., NUMA_NO_NODE, ...) >> __vmalloc_node_range >> __vmalloc_area_node >> alloc_pages_node /* choose nid by nuam_mem_id() *= / >> __alloc_pages_node(nid, ....) >> >> So after commit 121e6f3258fe ("mm/vmalloc: hugepage vmalloc mappings")= , >> it will allocate memory in current node instead of interleaving alloca= te >> memory. >> >> [1] >> https://lore.kernel.org/linux-mm/CANn89iL6AAyWhfxdHO+jaT075iOa3XcYn9k6= JJc7JR2XYn6k_Q@mail.gmail.com/ >> >> [2] >> https://lore.kernel.org/linux-mm/CANn89iLofTR=3DAK-QOZY87RdUZENCZUT4O6= a0hvhu3_EwRMerOg@mail.gmail.com/ >> >> Fixes: 121e6f3258fe ("mm/vmalloc: hugepage vmalloc mappings") >> Reported-by: Eric Dumazet >> Signed-off-by: Chen Wandun >> --- >> mm/vmalloc.c | 33 ++++++++++++++++++++++++++------- >> 1 file changed, 26 insertions(+), 7 deletions(-) >> >> diff --git a/mm/vmalloc.c b/mm/vmalloc.c >> index f884706c5280..48e717626e94 100644 >> --- a/mm/vmalloc.c >> +++ b/mm/vmalloc.c >> @@ -2823,6 +2823,8 @@ vm_area_alloc_pages(gfp_t gfp, int nid, >> unsigned int order, unsigned int nr_pages, struct page **pages) >> { >> unsigned int nr_allocated =3D 0; >> + struct page *page; >> + int i; >> =20 >> /* >> * For order-0 pages we make use of bulk allocator, if >> @@ -2833,6 +2835,7 @@ vm_area_alloc_pages(gfp_t gfp, int nid, >> if (!order) { >> while (nr_allocated < nr_pages) { >> unsigned int nr, nr_pages_request; >> + page =3D NULL; >> =20 >> /* >> * A maximum allowed request is hard-coded and is 100 >> @@ -2842,9 +2845,23 @@ vm_area_alloc_pages(gfp_t gfp, int nid, >> */ >> nr_pages_request =3D min(100U, nr_pages - nr_allocated); >> =20 >> - nr =3D alloc_pages_bulk_array_node(gfp, nid, >> - nr_pages_request, pages + nr_allocated); >> - >> + if (nid =3D=3D NUMA_NO_NODE) { >> > > void *vmalloc(unsigned long size) > { > return __vmalloc_node(size, 1, GFP_KERNEL, NUMA_NO_NODE, > __builtin_return_address(0)); > } > EXPORT_SYMBOL(vmalloc); > >=20 > vmalloc() uses NUMA_NO_NODE, so all vmalloc calls will be reverted to a= single > page allocator for NUMA and non-NUMA systems. Is it intentional to bypa= ss the > optimized bulk allocator for non-NUMA systems? I sent a patch, it will help to solve this. [PATCH] mm/vmalloc: introduce alloc_pages_bulk_array_mempolicy to=20 accelerate memory allocation Thanks, Wandun >=20 > Thanks! >=20 > -- > Vlad Rezki > . >=20