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 kanga.kvack.org (kanga.kvack.org [205.233.56.17]) by smtp.lore.kernel.org (Postfix) with ESMTP id AAAAEC433EF for ; Tue, 30 Nov 2021 11:59:06 +0000 (UTC) Received: by kanga.kvack.org (Postfix) id 1FE246B0073; Tue, 30 Nov 2021 06:51:20 -0500 (EST) Received: by kanga.kvack.org (Postfix, from userid 40) id 187176B0074; Tue, 30 Nov 2021 06:51:20 -0500 (EST) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id 027D06B0075; Tue, 30 Nov 2021 06:51:19 -0500 (EST) X-Delivered-To: linux-mm@kvack.org Received: from forelay.hostedemail.com (smtprelay0143.hostedemail.com [216.40.44.143]) by kanga.kvack.org (Postfix) with ESMTP id EAC6E6B0073 for ; Tue, 30 Nov 2021 06:51:19 -0500 (EST) Received: from smtpin06.hostedemail.com (10.5.19.251.rfc1918.com [10.5.19.251]) by forelay02.hostedemail.com (Postfix) with ESMTP id B182F8CA53 for ; Tue, 30 Nov 2021 11:51:09 +0000 (UTC) X-FDA: 78865430658.06.7D768F4 Received: from szxga03-in.huawei.com (szxga03-in.huawei.com [45.249.212.189]) by imf24.hostedemail.com (Postfix) with ESMTP id 753C3B00009F for ; Tue, 30 Nov 2021 11:51:03 +0000 (UTC) Received: from dggemv704-chm.china.huawei.com (unknown [172.30.72.53]) by szxga03-in.huawei.com (SkyGuard) with ESMTP id 4J3L8z3nxQz8vjC; Tue, 30 Nov 2021 19:49:07 +0800 (CST) Received: from kwepemm000020.china.huawei.com (7.193.23.93) 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 15.1.2308.20; Tue, 30 Nov 2021 19:51:04 +0800 Received: from kwepemm600017.china.huawei.com (7.193.23.234) by kwepemm000020.china.huawei.com (7.193.23.93) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.2308.20; Tue, 30 Nov 2021 19:51:04 +0800 Received: from kwepemm600017.china.huawei.com ([7.193.23.234]) by kwepemm600017.china.huawei.com ([7.193.23.234]) with mapi id 15.01.2308.020; Tue, 30 Nov 2021 19:51:04 +0800 From: "liupeng (DM)" To: "david@redhat.com" , "akpm@linux-foundation.org" , "vbabka@suse.cz" , "linux-mm@kvack.org" Subject: =?Windows-1252?Q?[QUESTION]_=93place_pages_to_tail=94_regress_memory_read?= =?Windows-1252?Q?_bandwidth_about_10%_under_our_test_cases?= Thread-Topic: =?Windows-1252?Q?[QUESTION]_=93place_pages_to_tail=94_regress_memory_read?= =?Windows-1252?Q?_bandwidth_about_10%_under_our_test_cases?= Thread-Index: Adfl28wXsF2bjvCMQUqL0Xs8EvHstg== Date: Tue, 30 Nov 2021 11:51:04 +0000 Message-ID: <3c6349ddd9a34732a251467b7fa4fe93@huawei.com> Accept-Language: zh-CN, en-US Content-Language: zh-CN X-MS-Has-Attach: X-MS-TNEF-Correlator: x-originating-ip: [10.174.179.19] Content-Type: multipart/alternative; boundary="_000_3c6349ddd9a34732a251467b7fa4fe93huaweicom_" MIME-Version: 1.0 X-CFilter-Loop: Reflected X-Rspamd-Queue-Id: 753C3B00009F X-Stat-Signature: 5gthwx1fuagohm8abm9crxq5ymrhmkff Authentication-Results: imf24.hostedemail.com; dkim=none; dmarc=pass (policy=quarantine) header.from=huawei.com; spf=pass (imf24.hostedemail.com: domain of liupeng256@huawei.com designates 45.249.212.189 as permitted sender) smtp.mailfrom=liupeng256@huawei.com X-Rspamd-Server: rspam02 X-HE-Tag: 1638273063-101760 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: --_000_3c6349ddd9a34732a251467b7fa4fe93huaweicom_ Content-Type: text/plain; charset="Windows-1252" Content-Transfer-Encoding: quoted-printable Hi David, We met a performance regression(lmbench bw_mmap_rd/bw_mem) on our server wi= th patch 7fef431be9c9(mm/page_alloc: place pages to tail in __free_pages_core(= )), Case A. ./bw_mmap_rd -P 1 512m mmap_only out.file Case B. ./bw_mem -P 1 512m frd mode0: IMC Interleave =3D auto, Channel Interleave =3D auto, Rank Interleav= e =3D auto without with regression case A 10535.14 9645.02 8.4% case B 10526.88 9797.63 6.9% also we found different memory interleaving have different results mode1: IMC Interleave =3D 1-way, Channel Interleave =3D 2-way, Rank Interle= ave =3D2-way without with regressi= on case A 10543.01 10643.12 -0.9% case B 10971.33 10853.99 1% The 7fef431be9c9 changes the different memory layout, it seems that the is= sue is related with memory interleave. But the patch does lead to performance r= egression. Any suggestion about this regression? thanks. Peng Liu --_000_3c6349ddd9a34732a251467b7fa4fe93huaweicom_ Content-Type: text/html; charset="Windows-1252" Content-Transfer-Encoding: quoted-printable

Hi David,

 

We met a performance regression= (lmbench bw_mmap_rd/bw_mem) on our server with

patch 7fef431be9c9(mm/page_allo= c: place pages to tail in __free_pages_core()),

 

Case A.  ./bw_mmap_rd -P 1= 512m mmap_only out.file

Case B.  ./bw_mem -P 1 512= m frd

 

mode0: IMC Interleave =3D auto,= Channel Interleave =3D auto, Rank Interleave =3D auto

     &= nbsp;            &nb= sp;  without         = ;            &n= bsp;  with        regression

case A    &= nbsp;      10535.14     &= nbsp;           &nbs= p;     9645.02      8.4%<= /o:p>

case B    &= nbsp;      10526.88     &= nbsp;           &nbs= p;     9797.63      6.9%<= /o:p>

also we found different memory = interleaving have different results

 

mode1: IMC Interleave =3D 1-way= , Channel Interleave =3D 2-way, Rank Interleave =3D2-way<= /p>

     &= nbsp;            &nb= sp;   without        = ;            &n= bsp;   with         = regression

case A    &= nbsp;      10543.01     &= nbsp;            &nb= sp;    10643.12       -0.= 9%

case B    &= nbsp;      10971.33     &= nbsp;            &nb= sp;    10853.99       1%<= o:p>

 

The 7fef431be9c9 changes the di= fferent memory layout,  it seems that the issue

is related with memory interlea= ve. But the patch does lead to performance regression.

 

Any suggestion about this regre= ssion?

thanks.

 

Peng Liu

 

--_000_3c6349ddd9a34732a251467b7fa4fe93huaweicom_--