Received-SPF: pass (google.com: domain of linux-kernel+bounces-97402-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.199.223 as permitted sender) client-ip=147.75.199.223;
Date: Fri, 8 Mar 2024 12:35:37 -0500
From: Daniel Jordan <daniel.m.jordan@oracle.com>
To: Gang Li <gang.li@linux.dev>
Cc: Andrew Morton <akpm@linux-foundation.org>,
        David Hildenbrand <david@redhat.com>,
        David Rientjes <rientjes@google.com>,
        Muchun Song <muchun.song@linux.dev>,
        Tim Chen <tim.c.chen@linux.intel.com>,
        Steffen Klassert <steffen.klassert@secunet.com>,
        Jane Chu <jane.chu@oracle.com>,
        "Paul E . McKenney" <paulmck@kernel.org>,
        Randy Dunlap <rdunlap@infradead.org>, linux-mm@kvack.org,
        linux-kernel@vger.kernel.org, ligang.bdlg@bytedance.com
Subject: Re: [PATCH v6 8/8] hugetlb: parallelize 1G hugetlb initialization
Message-ID: <vbj76pzf5mvooydne5fg2ewgjiducgficskq7hcsdxwywsda7l@qisdlq5q2n3o>
References: <20240222140422.393911-1-gang.li@linux.dev>
 <20240222140422.393911-9-gang.li@linux.dev>
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20240222140422.393911-9-gang.li@linux.dev>
Precedence: bulk
MIME-Version: 1.0
X-MS-Exchange-AntiSpam-MessageData-ChunkCount: 1
X-MS-Exchange-AntiSpam-MessageData-0: 
	=?us-ascii?Q?xCa9qsmd5xQ648J1H2oRh/CkluChQJKqanzyN3anWrJ3DdxGslBHK2H2PjlQ?=
 =?us-ascii?Q?BamP4d+kRwsLAV5ivtdfy8bUBtRSZBnkx01VSLf2+O7F8kYam68koYH4W+Zg?=
 =?us-ascii?Q?trzD0Mi9vs+AyHdY17AUPAS0YWAM4pbMaG5uqA4SJMgl6lkuXQ455f48sCPt?=
 =?us-ascii?Q?8Sf/AJSa4BTPxY/SimikYKd38Y/6pKsxwqHzTec/nQ05BKO/Pih61KD0MkBV?=
 =?us-ascii?Q?FxWUYJfm0KVTKsaYGyV8mgCDziVPiFXzFD1tts8p3UHdD0o/SNlsDrGXL3uf?=
 =?us-ascii?Q?ql7CaANt1EWIC4vyVCubRiwg8BPJPSdnv8kK5L8z1/XAoJf4fAyDm6Jj/z1n?=
 =?us-ascii?Q?wwgEEu3m76IFjTB7QFTSzREt33KhNzsblj1MjDokx6L07u5MBmk6HKZNns4+?=
 =?us-ascii?Q?TPnuWocCiB3Jegs0qrHeFaOE9PivSh6pv3E8vRxc2/NsLIGDKSPgxIzP8+UI?=
 =?us-ascii?Q?JBa5NxJi/ZEV5htPquHHp2gBl+Y1mk+NNBgjtsdaEcB/CmlUmAhUaai2/QkO?=
 =?us-ascii?Q?+33fIjkCy+7vhjwEQ3METKeeNnt1DMQtmyUKTC/0tYaqgO0ktubGyE25pwzT?=
 =?us-ascii?Q?mY8DwESiT1TFy62OFPy/nsYq4fMwNusgw3M89OPp0t/c6cpahxk7l+I185jL?=
 =?us-ascii?Q?y7ZXi7g9FcdYQcsWXW4lTYEeZeXhQOuMqked0zdwa7wcMtRn0uE3zahxJlFJ?=
 =?us-ascii?Q?PgAZAa7zRUkoornCa9QGOLdOgSnMOA+bW/uJMeiuz+LZs9LaCS2IkYJtOr77?=
 =?us-ascii?Q?lLW6bO50PQvDOdiVXJFxB0iCgI4um2bW8ZDtXWWlGC7x0XmYWrFMEbhvLaLq?=
 =?us-ascii?Q?bQSrwtgXRXmhLI0BU0XD1pzScjZNq2nAIYJeFye+iwHRW4Iw+0/4KX6AAWBS?=
 =?us-ascii?Q?+jeH6n2nHtfuJsxYoGu5L7penF7+3wukzQ0SVBotXvQDr76HqQC2RN26dD7L?=
 =?us-ascii?Q?YHJNbskljr1cAD6ASrWGhLmNzrrA1r8xiAtnEWpSc9HtCiPjkIByrJo1S3t9?=
 =?us-ascii?Q?xV7jlT2EI/roDnRLVqK59+525fZ8B17wS24RJ7LCP++oD3uko+GJrzM7K18j?=
 =?us-ascii?Q?ENO2DeOA4yAP+av+88+hFL6+kssfClFOpVHDOZ8V80ntUeu2RBlEEZlUYS2Y?=
 =?us-ascii?Q?ETm8y2YF318tlBo5COdfR3Jkn95N4i3kgxLmSLDxjGt58b+vZXOd2HTRIE4A?=
 =?us-ascii?Q?wpW1IZB/iyqcyhNY+cv3jmHTi4L/S0gi0BLydHPOiVP79g0eWXkVu4hX9t/o?=
 =?us-ascii?Q?E51SEnAlug4T2lwPOigIvFqQomIpsM0MZJyUVJt/P9j5Absm74uvCrnIXEfV?=
 =?us-ascii?Q?zwJmMQ5rufMOyuTifErp1LaWlJRin8GGlmhR8Qov1Wkjgjr9HGRq5Nt6UD5L?=
 =?us-ascii?Q?VqfPk8HT6ItKpGZJAmiSlWuva7wq9gQ4//3P/RvEVRPuu9/SN1jrjZ5+umpD?=
 =?us-ascii?Q?3uCKcs/eRIcLlOu/H0mREofbKrEgcFiJqhhdfdskxXBIxDG8EMxvMp4r+mMx?=
 =?us-ascii?Q?RQhfcMwa2ozxZ3J6IOS9S25fOixP9Oyf30pJzlFXlrp9iGWcBqZaacI9Anni?=
 =?us-ascii?Q?X3WAukyVJ17CNSVUmFe/bSMTG5F6xcbbPrTshAkMaRhgQ49+WCy1D8pjpoLd?=
 =?us-ascii?Q?lQ=3D=3D?=
X-MS-Exchange-AntiSpam-ExternalHop-MessageData-ChunkCount: 1
X-MS-Exchange-AntiSpam-ExternalHop-MessageData-0: 
	CK4GssEZwA8f6QLaCq4aq0u7Ip6o/WjR9qZ70DUaFZ9hL+17nJahwUVFrOCrVTQ3Pl7hZeFp+UgZF8MeU1EVUx4xSn+/6oy8x+dwvIQW+iZfNjAInhh5ghBjno/kYXvqmNoNsVFU4pgjaf5bnjtfVMGi1/kvZYJrjPTcggxfBue+6TdVlutLhpK2VThnIXXxwoBkVToLdHmJD5t3r/V9XumZ99zUJiiqxqTF2otCj3E29k4/86c4iyS2gfU9WAYE2x3pXTrIinuxGnVSNB7pWD+xDSZmRtWrB5HvJ3bCo+yIj7LeiM9YqyZq0kZQmKIPBgMUzT9F9q6hoQmFfApSC8hrGqbMtK9Y3QFD3LU4ezL/XDb41TBJ/zrRMccrvLWkxDO+F2t/L75Ak7DD/XDdHgtFyVUH67KkM5/9KdUWsEfwxbvd+vZBpX0nHnjtlRBNGbt/fGpb3t5Hde2174paNveXGCbcm+JHI4dERgjnpTjD4LeJRU0NYDK4v17Pbj/CAuQdqThIC743JRjFuZx+1o+yGZs9XONu9H9N26y0FElxMJDkOo3zfkyb+vS7WSUV/xAqrsdeuY+xZGXIZK951fGJu8mrxHaiGXFfoRuf3vI=
X-OriginatorOrg: oracle.com
X-MS-Exchange-CrossTenant-Network-Message-Id: e96b58e7-241a-4d13-19d9-08dc3f962c5f
X-MS-Exchange-CrossTenant-AuthSource: SA1PR10MB5711.namprd10.prod.outlook.com
X-MS-Exchange-CrossTenant-AuthAs: Internal
X-MS-Exchange-CrossTenant-OriginalArrivalTime: 08 Mar 2024 17:35:40.3813
 (UTC)
X-MS-Exchange-CrossTenant-FromEntityHeader: Hosted
X-MS-Exchange-CrossTenant-Id: 4e2c6054-71cb-48f1-bd6c-3a9705aca71b
X-MS-Exchange-CrossTenant-MailboxType: HOSTED
X-MS-Exchange-CrossTenant-UserPrincipalName: /sFe2Yly1VxlKWu96EBIljO3BtTUFZaqK9Ca5s72OGHjKHYaTripnv1oX7sgKVjGaEqHvCdwBpqDvU1LITX0q0c+BeGKjWgvOHd+uJ8TmZ0=
X-MS-Exchange-Transport-CrossTenantHeadersStamped: DM6PR10MB4348
X-Proofpoint-Virus-Version: vendor=baseguard
 engine=ICAP:2.0.272,Aquarius:18.0.1011,Hydra:6.0.619,FMLib:17.11.176.26
 definitions=2024-03-08_08,2024-03-06_01,2023-05-22_02
X-Proofpoint-Spam-Details: rule=notspam policy=default score=0 bulkscore=0 adultscore=0
 mlxlogscore=999 suspectscore=0 spamscore=0 malwarescore=0 mlxscore=0
 phishscore=0 classifier=spam adjust=0 reason=mlx scancount=1
 engine=8.12.0-2311290000 definitions=main-2403080140
X-Proofpoint-ORIG-GUID: Wtmjmqk5sFMOAU1ZG28wRXm303TTZ-Xk
X-Proofpoint-GUID: Wtmjmqk5sFMOAU1ZG28wRXm303TTZ-Xk

On Thu, Feb 22, 2024 at 10:04:21PM +0800, Gang Li wrote:
> Optimizing the initialization speed of 1G huge pages through
> parallelization.
> 
> 1G hugetlbs are allocated from bootmem, a process that is already
> very fast and does not currently require optimization. Therefore,
> we focus on parallelizing only the initialization phase in
> `gather_bootmem_prealloc`.
> 
> Here are some test results:
>       test case       no patch(ms)   patched(ms)   saved
>  ------------------- -------------- ------------- --------
>   256c2T(4 node) 1G           4745          2024   57.34%
>   128c1T(2 node) 1G           3358          1712   49.02%
>      12T         1G          77000         18300   76.23%

Another great improvement.

> +static void __init gather_bootmem_prealloc_parallel(unsigned long start,
> +						    unsigned long end, void *arg)
> +{
> +	int nid;
> +
> +	for (nid = start; nid < end; nid++)
> +		gather_bootmem_prealloc_node(nid);
> +}
> +
> +static void __init gather_bootmem_prealloc(void)
> +{
> +	struct padata_mt_job job = {
> +		.thread_fn	= gather_bootmem_prealloc_parallel,
> +		.fn_arg		= NULL,
> +		.start		= 0,
> +		.size		= num_node_state(N_MEMORY),
> +		.align		= 1,
> +		.min_chunk	= 1,
> +		.max_threads	= num_node_state(N_MEMORY),
> +		.numa_aware	= true,
> +	};
> +
> +	padata_do_multithreaded(&job);
> +}

Looks fine from the padata side.

Acked-by: Daniel Jordan <daniel.m.jordan@oracle.com> # padata