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 60CAFC47258 for ; Wed, 17 Jan 2024 22:15:03 +0000 (UTC) Received: by kanga.kvack.org (Postfix) id 971C96B0078; Wed, 17 Jan 2024 17:15:02 -0500 (EST) Received: by kanga.kvack.org (Postfix, from userid 40) id 9225E6B007B; Wed, 17 Jan 2024 17:15:02 -0500 (EST) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id 7E9736B0087; Wed, 17 Jan 2024 17:15:02 -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 6CFC86B0078 for ; Wed, 17 Jan 2024 17:15:02 -0500 (EST) Received: from smtpin18.hostedemail.com (a10.router.float.18 [10.200.18.1]) by unirelay10.hostedemail.com (Postfix) with ESMTP id E7B72C0553 for ; Wed, 17 Jan 2024 22:15:01 +0000 (UTC) X-FDA: 81690209202.18.88FFFD6 Received: from mgamail.intel.com (mgamail.intel.com [198.175.65.11]) by imf27.hostedemail.com (Postfix) with ESMTP id AAA514000D for ; Wed, 17 Jan 2024 22:14:58 +0000 (UTC) Authentication-Results: imf27.hostedemail.com; dkim=pass header.d=intel.com header.s=Intel header.b=c7hcR09s; spf=none (imf27.hostedemail.com: domain of tim.c.chen@linux.intel.com has no SPF policy when checking 198.175.65.11) smtp.mailfrom=tim.c.chen@linux.intel.com; dmarc=pass (policy=none) header.from=intel.com ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=hostedemail.com; s=arc-20220608; t=1705529700; 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=chvb3TFTw0boKPp+bWGKodBMB09MQ2Mob+IdGpm9b3w=; b=OXnKp7ZUsVX17otqdd6yTduSPgiaQnnuR84KPH3j0C3pHGaTyG4ZVyS987++4SGQxfN+VA fjhPqm7g0+HEy7Y2upZSX81UzlHJ5//3uc7/XVfoJf1UBbRQ7o3AqGZJuq/tzQuYF0yXz2 FQSph7Oe6D1rJWq6iZtHeB6AbkN7zEc= ARC-Seal: i=1; s=arc-20220608; d=hostedemail.com; t=1705529700; a=rsa-sha256; cv=none; b=gj9bM4PfBfQdFRCNN1ouEgpC68prwD2XllDCWHukzboF8NWJgmG+btTyuOBa5a1cYmw2eM N2gc/Jb3+yC17YERyI1G99BOkTr9UntIlJdHl91UW6LXnrqV9fZuPWXKMxyZfD383CIq81 GMQh9HKu6egtZH+4im7O+lOq8rv1374= ARC-Authentication-Results: i=1; imf27.hostedemail.com; dkim=pass header.d=intel.com header.s=Intel header.b=c7hcR09s; spf=none (imf27.hostedemail.com: domain of tim.c.chen@linux.intel.com has no SPF policy when checking 198.175.65.11) smtp.mailfrom=tim.c.chen@linux.intel.com; dmarc=pass (policy=none) header.from=intel.com DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1705529699; x=1737065699; h=message-id:subject:from:to:cc:date:in-reply-to: references:content-transfer-encoding:mime-version; bh=NkvEXTpBfoUpi2iXajrBKt8X8S/DHNktsJvGm0GzI0E=; b=c7hcR09sutj8rmozEGnh93XoEJ68vzIRlf0iUAqLmz29xgner97t6OHx yNVYscR4Q+/vZPqqpQTvNkNr1XFKKHYzF1RB4bgYr3eR5xN0NFwr9jUgm kNnQWy//6qoSiJu9S35wsYOWCYlSWAUjLOq9lpPPYqta445cfemcHsucl JE3tOju7egRraBssBjZ5IoOxKH2O8mluh7IL3YOuDVkxeQEfKYww0pv5L EZhNgPYnUBAkunITzLyzC481UZ2IsrSSJsjTHSgwRPUEhdm813GRp6wrE Nh56HwyGexpuqKLv+f+K4GvPPIQq239c8Hwh1EQWQn9qUYuSaWR0zGKW+ A==; X-IronPort-AV: E=McAfee;i="6600,9927,10956"; a="6987200" X-IronPort-AV: E=Sophos;i="6.05,201,1701158400"; d="scan'208";a="6987200" Received: from orviesa003.jf.intel.com ([10.64.159.143]) by orvoesa103.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 17 Jan 2024 14:14:57 -0800 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.05,201,1701158400"; d="scan'208";a="157140" Received: from kappusam-mobl.amr.corp.intel.com (HELO [10.212.188.217]) ([10.212.188.217]) by ORVIESA003-auth.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 17 Jan 2024 14:14:57 -0800 Message-ID: Subject: Re: [PATCH v3 3/7] padata: dispatch works on different nodes From: Tim Chen To: Gang Li Cc: linux-mm@kvack.org, Andrew Morton , Mike Kravetz , David Rientjes , linux-kernel@vger.kernel.org, ligang.bdlg@bytedance.com, David Hildenbrand , Muchun Song Date: Wed, 17 Jan 2024 14:14:56 -0800 In-Reply-To: References: <20240102131249.76622-1-gang.li@linux.dev> <20240102131249.76622-4-gang.li@linux.dev> <1d9074955618ea0b4b155701f7c1b8b18a43fa8d.camel@linux.intel.com> <1bd6ee64a600daad58866ce684b591d39879c470.camel@linux.intel.com> Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable User-Agent: Evolution 3.44.4 (3.44.4-2.fc36) MIME-Version: 1.0 X-Rspamd-Queue-Id: AAA514000D X-Rspam-User: X-Rspamd-Server: rspam11 X-Stat-Signature: aq6wqqfikegq6h4jsuk3j8wuhcjwcxcd X-HE-Tag: 1705529698-51592 X-HE-Meta: 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 7g4d22g8 /KBUpqXo6YVsA502MHocEz493FKUCSo6Fy7XwDdEl6R/4qQ/c3IMDP44S121fI6yae3+025SVs5/3BPaURHSmOvU22FjXY+DMr7WEK1ime2Ip09bFyHyFXmOaM4ex5mWcmLf6 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, 2024-01-15 at 16:57 +0800, Gang Li wrote: >=20 > On 2024/1/13 02:27, Tim Chen wrote: > > On Fri, 2024-01-12 at 15:09 +0800, Gang Li wrote: > > > On 2024/1/12 01:50, Tim Chen wrote: > > > > On Tue, 2024-01-02 at 21:12 +0800, Gang Li wrote: > > > > > When a group of tasks that access different nodes are scheduled o= n the > > > > > same node, they may encounter bandwidth bottlenecks and access la= tency. > > > > >=20 > > > > > Thus, numa_aware flag is introduced here, allowing tasks to be > > > > > distributed across different nodes to fully utilize the advantage= of > > > > > multi-node systems. > > > > >=20 > > > > > Signed-off-by: Gang Li > > > > > --- > > > > > include/linux/padata.h | 3 +++ > > > > > kernel/padata.c | 8 ++++++-- > > > > > mm/mm_init.c | 1 + > > > > > 3 files changed, 10 insertions(+), 2 deletions(-) > > > > >=20 > > > > > diff --git a/include/linux/padata.h b/include/linux/padata.h > > > > > index 495b16b6b4d72..f79ccd50e7f40 100644 > > > > > --- a/include/linux/padata.h > > > > > +++ b/include/linux/padata.h > > > > > @@ -137,6 +137,8 @@ struct padata_shell { > > > > > * appropriate for one worker thread to do at once= . > > > > > * @max_threads: Max threads to use for the job, actual number= may be less > > > > > * depending on task size and minimum chunk size= . > > > > > + * @numa_aware: Dispatch jobs to different nodes. If a node only= has memory but > > > > > + * no CPU, dispatch its jobs to a random CPU. > > > > > */ > > > > > struct padata_mt_job { > > > > > void (*thread_fn)(unsigned long start, unsigned long end, voi= d *arg); > > > > > @@ -146,6 +148,7 @@ struct padata_mt_job { > > > > > unsigned long align; > > > > > unsigned long min_chunk; > > > > > int max_threads; > > > > > + bool numa_aware; > > > > > }; > > > > > =20 > > > > > /** > > > > > diff --git a/kernel/padata.c b/kernel/padata.c > > > > > index 179fb1518070c..1c2b3a337479e 100644 > > > > > --- a/kernel/padata.c > > > > > +++ b/kernel/padata.c > > > > > @@ -485,7 +485,7 @@ void __init padata_do_multithreaded(struct pa= data_mt_job *job) > > > > > struct padata_work my_work, *pw; > > > > > struct padata_mt_job_state ps; > > > > > LIST_HEAD(works); > > > > > - int nworks; > > > > > + int nworks, nid =3D 0; > > > >=20 > > > > If we always start from 0, we may be biased towards the low numbere= d node, > > > > and not use high numbered nodes at all. Suggest you do > > > > static nid =3D 0; > > > >=20 > > >=20 > > > When we use `static`, if there are multiple parallel calls to > > > `padata_do_multithreaded`, it may result in an uneven distribution of > > > tasks for each padata_do_multithreaded. > > >=20 > > > We can make the following modifications to address this issue. > > >=20 > > > ``` > > > diff --git a/kernel/padata.c b/kernel/padata.c > > > index 1c2b3a337479e..925e48df6dd8d 100644 > > > --- a/kernel/padata.c > > > +++ b/kernel/padata.c > > > @@ -485,7 +485,8 @@ void __init padata_do_multithreaded(struct > > > padata_mt_job *job) > > > struct padata_work my_work, *pw; > > > struct padata_mt_job_state ps; > > > LIST_HEAD(works); > > > - int nworks, nid =3D 0; > > > + int nworks, nid; > > > + static volatile int global_nid =3D 0; > > >=20 > > > if (job->size =3D=3D 0) > > > return; > > > @@ -516,12 +517,15 @@ void __init padata_do_multithreaded(struct > > > padata_mt_job *job) > > > ps.chunk_size =3D max(ps.chunk_size, job->min_chunk); > > > ps.chunk_size =3D roundup(ps.chunk_size, job->align); > > >=20 > > > + nid =3D global_nid; > > > list_for_each_entry(pw, &works, pw_list) > > > - if (job->numa_aware) > > > - queue_work_node((++nid % num_node_state(N_MEM= ORY)), > > > - system_unbound_wq, &pw->pw_wo= rk); > > > - else > > > + if (job->numa_aware) { > > > + queue_work_node(nid, system_unbound_wq, > > > &pw->pw_work); > > > + nid =3D next_node(nid, node_states[N_CPU]); > > > + } else > > > queue_work(system_unbound_wq, &pw->pw_work)= ; > > > + if (job->numa_aware) > > > + global_nid =3D nid; > >=20 > > Thinking more about it, there could still be multiple threads working > > at the same time with stale global_nid. We should probably do a compar= e > > exchange of global_nid with new nid only if the global nid was unchange= d. > > Otherwise we should go to the next node with the changed global nid bef= ore > > we queue the job. > >=20 > > Tim > >=20 > How about: > ``` > nid =3D global_nid; > list_for_each_entry(pw, &works, pw_list) > if (job->numa_aware) { > int old_node =3D nid; > queue_work_node(nid, system_unbound_wq, &pw->pw_work); > nid =3D next_node(nid, node_states[N_CPU]); > cmpxchg(&global_nid, old_node, nid); > } else > queue_work(system_unbound_wq, &pw->pw_work); >=20 > ``` >=20 I am thinking something like static volatile atomic_t last_used_nid; list_for_each_entry(pw, &works, pw_list) if (job->numa_aware) { int old_node =3D atomic_read(&last_used_nid); =09 do { nid =3D next_node_in(old_node, node_states[N_CPU]); } while (!atomic_try_cmpxchg(&last_used_nid, &old_node, nid)); queue_work_node(nid, system_unbound_wq, &pw->pw_work); =09 } else { queue_work(system_unbound_wq, &pw->pw_work); } Note that we need to use next_node_in so we'll wrap around the node mask. Tim