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 9DF44C02198 for ; Mon, 10 Feb 2025 03:45:12 +0000 (UTC) Received: by kanga.kvack.org (Postfix) id 226AE6B0085; Sun, 9 Feb 2025 22:45:12 -0500 (EST) Received: by kanga.kvack.org (Postfix, from userid 40) id 1D7C96B0088; Sun, 9 Feb 2025 22:45:12 -0500 (EST) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id 09EFF6B0089; Sun, 9 Feb 2025 22:45:12 -0500 (EST) X-Delivered-To: linux-mm@kvack.org Received: from relay.hostedemail.com (smtprelay0017.hostedemail.com [216.40.44.17]) by kanga.kvack.org (Postfix) with ESMTP id E102A6B0085 for ; Sun, 9 Feb 2025 22:45:11 -0500 (EST) Received: from smtpin15.hostedemail.com (a10.router.float.18 [10.200.18.1]) by unirelay03.hostedemail.com (Postfix) with ESMTP id 9D3ECA205C for ; Mon, 10 Feb 2025 03:45:11 +0000 (UTC) X-FDA: 83102644422.15.B1C57EE Received: from mail-vs1-f44.google.com (mail-vs1-f44.google.com [209.85.217.44]) by imf12.hostedemail.com (Postfix) with ESMTP id BD0B84000D for ; Mon, 10 Feb 2025 03:45:09 +0000 (UTC) Authentication-Results: imf12.hostedemail.com; dkim=pass header.d=gmail.com header.s=20230601 header.b=DNJ1RaR0; spf=pass (imf12.hostedemail.com: domain of 21cnbao@gmail.com designates 209.85.217.44 as permitted sender) smtp.mailfrom=21cnbao@gmail.com; dmarc=pass (policy=none) header.from=gmail.com ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=hostedemail.com; s=arc-20220608; t=1739159109; h=from:from:sender:reply-to:subject:subject:date:date: message-id:message-id:to:to:cc:cc:mime-version:mime-version: content-type:content-type: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references:dkim-signature; bh=lrH3H45xGDQsKKJSfZ1ZGuXbNHSjoD6iw70B00N0f4U=; b=XehEl7D6FcpD64fiDfVZuoCG3T+EX6qw/uWq9+R4TyAbza8eKaC1XI4ypuQykgnJvtRHe0 JkxmmTHjifrSQp3BssWRUOgaULTwkeuTv+sixNIzIqIe9B0LJfraqtisCDPqihYplOmPaG 0YSnEg1XvHjQqdV80DK+00FLbDsDTDA= ARC-Authentication-Results: i=1; imf12.hostedemail.com; dkim=pass header.d=gmail.com header.s=20230601 header.b=DNJ1RaR0; spf=pass (imf12.hostedemail.com: domain of 21cnbao@gmail.com designates 209.85.217.44 as permitted sender) smtp.mailfrom=21cnbao@gmail.com; dmarc=pass (policy=none) header.from=gmail.com ARC-Seal: i=1; s=arc-20220608; d=hostedemail.com; t=1739159109; a=rsa-sha256; cv=none; b=v7C2Cbx36j+vLPISxGvQ2WPY6dIuVJfnOXLBNDvthxKsBiCjg+F/+UBfhX9TCkrPL0DZfi dwfgenu6Ub6zWdx6vmPxV+g74yxI+hR6jId5KpkHDXNWeKUTm2UCUWf84aJqMhU1logMqD 74FbXfPCDGILWraUOgwyd1yR+p+LiX0= Received: by mail-vs1-f44.google.com with SMTP id ada2fe7eead31-4ba79f6c678so1113785137.3 for ; Sun, 09 Feb 2025 19:45:09 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20230601; t=1739159109; x=1739763909; darn=kvack.org; h=content-transfer-encoding:cc:to:subject:message-id:date:from :in-reply-to:references:mime-version:from:to:cc:subject:date :message-id:reply-to; bh=lrH3H45xGDQsKKJSfZ1ZGuXbNHSjoD6iw70B00N0f4U=; b=DNJ1RaR0ZGyt7nK9dVNo/4SYMFhpd4F1bwLUFXfzMWnfYdh9GCijIy+YCocyDrw4QH okFbLHcrgJiGQhkVlrQZ+M1pHs1OY7iMw5u8fGYSqsijzCxN1InEBjG8SLEdu67LdBi8 e4TzlRY19dKyyRF+BLi+pL7EnraELJaVpEXlp7qQND2ZGk2+ClVeH6WBYkLHrYpfsid6 Q/cBlhj41IeUmcd5BJSbO170bmmvuXBYMD5SJVRPhtErHMq9On+spx6eJP8Qq7Q5vdzz QhePvyp7ru8/HAmRTkN/3s8iib0gPwqhUVbTG18mxbl2FYjsbB+BYMDU8QPwPcPMhIjR 7dXA== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1739159109; x=1739763909; h=content-transfer-encoding:cc:to:subject:message-id:date:from :in-reply-to:references:mime-version:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=lrH3H45xGDQsKKJSfZ1ZGuXbNHSjoD6iw70B00N0f4U=; b=lMozLOwZi3RMA6ucxqe462cpfOiZprHsDJRcEhWflzXokpb8r7SlJUBzEAJfvGRRoH JP++6wY1rfgviVWTUSWXs1EgTztHJFX0a7dtcUhFJMLEbvthcYtMFLQC9L7BheClYJ2U oUtlRAlotJKcqKNhjj9YHjFs3/3OOcaIw/oU2BTO6i+7b3+ZZX1+3z10tUDM5kRFm4NQ uzyPY5j942t0tL1BxtcqREMYjtsHNZ6HLsV2LKw/uWyqpor02LEAFkHiEXqYFrVF8IYA TS3Rj2izCF6UeUTHbWJiSGMaP1fMBGNYTrixMHE2UMfvUacRqVJhcXIzIuwWQg1sXvIm taUA== X-Forwarded-Encrypted: i=1; AJvYcCVeSF6c+0Fr3Fn75hVvgYBeJykiUN9kDU1M6gastOH2XARwqohxJ8KPmJqNygIyUq55aOZJgEsQwg==@kvack.org X-Gm-Message-State: AOJu0YymPTUMeADinCTVB9tgubp2QhIgw2IqAVzdF6lGv/FdJjV+7yZh PU9Kem7CMUWqGrfIWD4duhZ0B3+Np4fymOQMhhrvjEUcypqxgCkaQDNcA4i5UO/4ybifA8asooN 8aK1ihRZAFzNOZruMFluL4rl+g+k= X-Gm-Gg: ASbGncsKCHxWlyq2wirP/I91/X/mRHEHvrlSsnMU9+Ff1t4K9QOh9ln1k6fvvRu0JF5 Dvy9Qyddt+/QVoYhwrzGvMz5XiI0ovVoEPYFigfEU3bnuZ/IzvLHnVNkrh9khKxmLvuw6QNoEbs 1LvHTpmFmda9mWPYynk7A+zQdUoVlHZgI= X-Google-Smtp-Source: AGHT+IEL/vT0c2/JjpJIapWwelliCNO8zWyTPXIfAdpD+v+MEPdjpOqc0GvFXRyd23qTFM1E2q1jL7qZ2Tmv4zPg7mo= X-Received: by 2002:a05:6102:809d:b0:4b2:485b:e151 with SMTP id ada2fe7eead31-4ba85e1929emr7564766137.10.1739159108739; Sun, 09 Feb 2025 19:45:08 -0800 (PST) MIME-Version: 1.0 References: <1739152566-744-1-git-send-email-yangge1116@126.com> In-Reply-To: <1739152566-744-1-git-send-email-yangge1116@126.com> From: Barry Song <21cnbao@gmail.com> Date: Mon, 10 Feb 2025 16:44:58 +1300 X-Gm-Features: AWEUYZmJvDQL6PxmjmgrcMCGRqvblJVkLUq-BAD3C8C-jcdLwPdnVbLWcnB6LAg Message-ID: Subject: Re: [PATCH V2] mm/cma: using per-CMA locks to improve concurrent allocation performance To: yangge1116@126.com Cc: akpm@linux-foundation.org, linux-mm@kvack.org, linux-kernel@vger.kernel.org, david@redhat.com, baolin.wang@linux.alibaba.com, aisheng.dong@nxp.com, liuzixing@hygon.cn Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable X-Rspam-User: X-Rspamd-Queue-Id: BD0B84000D X-Stat-Signature: u688ibkfz4jcm75wuse7b5zgus654azr X-Rspamd-Server: rspam03 X-HE-Tag: 1739159109-409136 X-HE-Meta: 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 SPXZt9VK hr9v9axt3+AE6Z+8Bofh+vu/mbgUr9JQCOGEsEPle/lyEcjbRkPhz6U53l/F120FI6q/4CCgstSzkFmVwGkW8wKNPVsr6EbYvLro2Cjoj/LgnXqx6RCEw5bVr3h6Nv1prd/offj0c34HEKKWNmQdmaXrZ8BDWnM83/iDQq6PoM7WGRg1xcoJxJ3nB/KRJWYXh0XPoN/qfD3DIvsSPBP22yH4iEbkhsaaeWhu3q6Gqg3bj6LptbqibYwAGvAUNQxMFgmhGP/yLIWzMLNDlxYDA5Sruyy1+lVH6Quy3iEuIGIIOkqa/bY8qIwNCJVkJ7tX+knxshrnC7GMiJ+UsSET3lBWMBwYPvmjBYR09KYMkSG2QcSkaD/RDINbb/iUOiRGfN3jQ1HauuhzhFCO2/ghMNJc6Zw== 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: List-Subscribe: List-Unsubscribe: On Mon, Feb 10, 2025 at 2:56=E2=80=AFPM wrote: > > From: yangge > > For different CMAs, concurrent allocation of CMA memory ideally should no= t > require synchronization using locks. Currently, a global cma_mutex lock i= s > employed to synchronize all CMA allocations, which can impact the > performance of concurrent allocations across different CMAs. > > To test the performance impact, follow these steps: > 1. Boot the kernel with the command line argument hugetlb_cma=3D30G to > allocate a 30GB CMA area specifically for huge page allocations. (note= : > on my machine, which has 3 nodes, each node is initialized with 10G of > CMA) > 2. Use the dd command with parameters if=3D/dev/zero of=3D/dev/shm/file b= s=3D1G > count=3D30 to fully utilize the CMA area by writing zeroes to a file i= n > /dev/shm. > 3. Open three terminals and execute the following commands simultaneously= : > (Note: Each of these commands attempts to allocate 10GB [2621440 * 4KB > pages] of CMA memory.) > On Terminal 1: time echo 2621440 > /sys/kernel/debug/cma/hugetlb1/allo= c > On Terminal 2: time echo 2621440 > /sys/kernel/debug/cma/hugetlb2/allo= c > On Terminal 3: time echo 2621440 > /sys/kernel/debug/cma/hugetlb3/allo= c > > We attempt to allocate pages through the CMA debug interface and use the > time command to measure the duration of each allocation. > Performance comparison: > Without this patch With this patch > Terminal1 ~7s ~7s > Terminal2 ~14s ~8s > Terminal3 ~21s ~7s > > To slove problem above, we could use per-CMA locks to improve concurrent > allocation performance. This would allow each CMA to be managed > independently, reducing the need for a global lock and thus improving > scalability and performance. > > Signed-off-by: yangge An allocation from one CMA region should not be blocked by an allocation fr= om another CMA region, especially since we may have multiple CMA regions or even per-NUMA CMA regions. Reviewed-by: Barry Song > --- > > V2: > - update code and message suggested by Barry. > > mm/cma.c | 7 ++++--- > mm/cma.h | 1 + > 2 files changed, 5 insertions(+), 3 deletions(-) > > diff --git a/mm/cma.c b/mm/cma.c > index 34a4df2..a0d4d2f 100644 > --- a/mm/cma.c > +++ b/mm/cma.c > @@ -34,7 +34,6 @@ > > struct cma cma_areas[MAX_CMA_AREAS]; > unsigned int cma_area_count; > -static DEFINE_MUTEX(cma_mutex); > > static int __init __cma_declare_contiguous_nid(phys_addr_t base, > phys_addr_t size, phys_addr_t limit, > @@ -175,6 +174,8 @@ static void __init cma_activate_area(struct cma *cma) > > spin_lock_init(&cma->lock); > > + mutex_init(&cma->alloc_mutex); > + > #ifdef CONFIG_CMA_DEBUGFS > INIT_HLIST_HEAD(&cma->mem_head); > spin_lock_init(&cma->mem_head_lock); > @@ -813,9 +814,9 @@ static int cma_range_alloc(struct cma *cma, struct cm= a_memrange *cmr, > spin_unlock_irq(&cma->lock); > > pfn =3D cmr->base_pfn + (bitmap_no << cma->order_per_bit)= ; > - mutex_lock(&cma_mutex); > + mutex_lock(&cma->alloc_mutex); > ret =3D alloc_contig_range(pfn, pfn + count, MIGRATE_CMA,= gfp); > - mutex_unlock(&cma_mutex); > + mutex_unlock(&cma->alloc_mutex); > if (ret =3D=3D 0) { > page =3D pfn_to_page(pfn); > break; > diff --git a/mm/cma.h b/mm/cma.h > index df7fc62..41a3ab0 100644 > --- a/mm/cma.h > +++ b/mm/cma.h > @@ -39,6 +39,7 @@ struct cma { > unsigned long available_count; > unsigned int order_per_bit; /* Order of pages represented by one = bit */ > spinlock_t lock; > + struct mutex alloc_mutex; > #ifdef CONFIG_CMA_DEBUGFS > struct hlist_head mem_head; > spinlock_t mem_head_lock; > -- > 2.7.4 > > Thanks Barry