Received-SPF: pass (google.com: domain of linux-nfs+bounces-2716-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:45d1:ec00::1 as permitted sender) client-ip=2604:1380:45d1:ec00::1;
From: Charles Hedrick <hedrick@rutgers.edu>
To: "linux-nfs@vger.kernel.org" <linux-nfs@vger.kernel.org>
Subject: Re: optimization for nfsd_set_fh_dentry
Thread-Topic: optimization for nfsd_set_fh_dentry
Thread-Index: AQHaiOz0yLe16yGdgkeM/Wdo4AR5CLFeQ8QH
Date: Mon, 8 Apr 2024 11:51:04 +0000
Message-ID:
 <PH0PR14MB54937D8D139D9203AF4897C2AA002@PH0PR14MB5493.namprd14.prod.outlook.com>
References:
 <PH0PR14MB549329F998F7DB972744F45FAA012@PH0PR14MB5493.namprd14.prod.outlook.com>
In-Reply-To:
 <PH0PR14MB549329F998F7DB972744F45FAA012@PH0PR14MB5493.namprd14.prod.outlook.com>
Accept-Language: en-US
Content-Language: en-US
msip_labels:
x-ms-publictraffictype: Email
x-ms-traffictypediagnostic: PH0PR14MB5493:EE_|SJ0PR14MB6602:EE_
x-ms-exchange-senderadcheck: 1
x-ms-exchange-antispam-relay: 0
x-microsoft-antispam: BCL:0;
x-microsoft-antispam-message-info:
 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
x-forefront-antispam-report:
 CIP:255.255.255.255;CTRY:;LANG:en;SCL:1;SRV:;IPV:NLI;SFV:NSPM;H:PH0PR14MB5493.namprd14.prod.outlook.com;PTR:;CAT:NONE;SFS:(13230031)(376005)(1800799015)(366007);DIR:OUT;SFP:1102;
x-ms-exchange-antispam-messagedata-chunkcount: 1
x-ms-exchange-antispam-messagedata-0:
 =?iso-8859-1?Q?Dv3U5AgJolz6x9Loy2A4T3BrDZBt4lk6taqpVt+I0BMUHQX9HYPassURDO?=
 =?iso-8859-1?Q?6DDH7IWKoLjDrdAgNPUedqQO0fm7Ue2DHDXIfZJr7ZfCwee9TdDwmT5Qha?=
 =?iso-8859-1?Q?bWctOmpkCytGK6AWGaXXI4fjIPKPHh7ecUnME5RFC3aIW+/VjvcIxh46IF?=
 =?iso-8859-1?Q?NSrBQFnWS6u2krgQO7sZOod0n0zwTEo/P6T7sqcwJrAQ7eUrIhG1nuifMs?=
 =?iso-8859-1?Q?KMJDIqE+IrKLK8wiy6TVGpE6ZqmSQcbDW+Zp1okLlimi1QJ9vrY8q92ROG?=
 =?iso-8859-1?Q?rAHyVFR/t9zWgeQ/HFfZ5px5wp/6axprvdGAlVMaRAyCsJ0/VGQ6UGMB5h?=
 =?iso-8859-1?Q?JbXnvMw/p9qmHxUnDao/bQZqQ4K9pgtBq8zN7wHd2Ni4MhCdlV/oJvoiz1?=
 =?iso-8859-1?Q?ucejTbPlf5SvkeW1oAuLBsWp837Ki5WLnz7sdLy7WyozXiAX7DPvE8Pi+l?=
 =?iso-8859-1?Q?krmDHH7eJuo93rLOXMvgY39PD2HkUonA3nv/yucQoqSBgH0qAlqDreYYkA?=
 =?iso-8859-1?Q?ISWwVCKCxeocIl25jjay6cDEI7W1XGV7lO4eBU8nqNYstyI+mb9ZDFWNdq?=
 =?iso-8859-1?Q?Qo+1k5trbVsgmp0hfzCJUMAe4kg5Ccoz9E3m+RquKfqbRDnvtn0c7EG5JB?=
 =?iso-8859-1?Q?tr+ucBWL+4rKa78p78IHO1PA5qYbqVaVOggDEp9fkE9Q3WxCHT3WZ4xKRV?=
 =?iso-8859-1?Q?z2GgL8+7ZsI+vBmJ2CCja7VTsCo9qzgj565EJv9tvc6YSFy7MS/UVU4bJz?=
 =?iso-8859-1?Q?FVpG9r/uQgMJ0AjMNWTSUWd53N+SfFbYPAMAPQyIK79YX8IH54TNk6hZuu?=
 =?iso-8859-1?Q?NL3qTrGRkpT/IDg3NeEoBmLtCiGv6WU0PadD6Idwxh1IGvW81wrm+XYXuU?=
 =?iso-8859-1?Q?j1hepbgu0ptr4vzMYP7Q1o3JEDIPA4dQioBoNUQbMRxBmQl7frpISIpttv?=
 =?iso-8859-1?Q?d5yv8V3KqrcURVX1ajwFSvNOH7AmkKY9/Gjyk/j58wEtUguWWMkMcqXGRk?=
 =?iso-8859-1?Q?GsJzu8LS5L5hfbc3s+0WQeuGyR4VJ8++e04RL8Mhv2BUSkkyAMqqh2i0KI?=
 =?iso-8859-1?Q?aBEaUc137ll/h35bZwkhenEiscC1JpJqDLGgNnwBRJJ4xmyytvmn6fMBBH?=
 =?iso-8859-1?Q?BVxuBkoSETD9QMDp+vgSfB1cSo046PCak3XXC/4bb4ioXMjwoeaCD9lERX?=
 =?iso-8859-1?Q?qvtnE82W+wQsX7NFiEE5ArUW6jaE6Z7FVPnwxTqTAhfXoN1KQjcoMuXnNC?=
 =?iso-8859-1?Q?QtdkWLYW6eCOIMWGetPAEYyOmlBFdOBRZGt32y5vPKHkHaF1NKnsk3qcjl?=
 =?iso-8859-1?Q?rWmCc0Sfu/mbIw9zMTZrF0RbeceZgVDNPlOHqJRhmYfbfynol1CFbPDwy+?=
 =?iso-8859-1?Q?VuJ8TPAqmFVUK0KSCCbAlSmpVF0xQGQ30Me2sHdE4hNJNUkyp5JUe5DKly?=
 =?iso-8859-1?Q?1uDp6UDCNUmble4GEtdJYA9Sce3i8MILYCIaWmRUEE0IGLp4xNSGJRGm6/?=
 =?iso-8859-1?Q?smKphOBTu4dgoVWS/EHzO7mq3c5+DZ42meM4DnEbty8VBPwUMAxnzOQzYb?=
 =?iso-8859-1?Q?ZLt1RDjx/jgO4l2Ou6eWX+vRQ2H2p+vY/5AUG1bysUHkM+aRv+NXTqJK3w?=
 =?iso-8859-1?Q?jTiomJW1GMuuVVmkiVEeyN/Al8TaC482aK?=
Content-Type: text/plain; charset="iso-8859-1"
Content-Transfer-Encoding: quoted-printable
Precedence: bulk
X-Mailing-List: linux-nfs@vger.kernel.org
List-Id: <linux-nfs.vger.kernel.org>
List-Subscribe: <mailto:linux-nfs+subscribe@vger.kernel.org>
List-Unsubscribe: <mailto:linux-nfs+unsubscribe@vger.kernel.org>
MIME-Version: 1.0
X-OriginatorOrg: rutgers.edu
X-MS-Exchange-CrossTenant-AuthAs: Internal
X-MS-Exchange-CrossTenant-AuthSource: PH0PR14MB5493.namprd14.prod.outlook.com
X-MS-Exchange-CrossTenant-Network-Message-Id: 16aac063-b04f-4082-012f-08dc57c22b49
X-MS-Exchange-CrossTenant-originalarrivaltime: 08 Apr 2024 11:51:04.1111
 (UTC)
X-MS-Exchange-CrossTenant-fromentityheader: Hosted
X-MS-Exchange-CrossTenant-id: b92d2b23-4d35-4470-93ff-69aca6632ffe
X-MS-Exchange-CrossTenant-mailboxtype: HOSTED
X-MS-Exchange-CrossTenant-userprincipalname: KxYQDAs6r3jo96vasEsEWr8x6LAhUfuJ8J3+9je4iTMJz4Cx1MHsuGMlxrRliHSvOKZ3enDLg7G2IKcOGEraCw==
X-MS-Exchange-Transport-CrossTenantHeadersStamped: SJ0PR14MB6602

My apologies. Please ignore this. I misread a backtrace and code.=0A=
=0A=
> nfsd_set_fh_dentry is used in setfh and a number of other places. It call=
s exportfs_decode_fh_raw with an argument > > >nfsd_acceptable.=0A=
>=0A=
>That is a test that always returns 1 if NFSEXP_NOSUBTREECHECK is set.=0A=
>=0A=
>However there is an optimization in exportfs_decode_fh_raw that skips a lo=
t of file system stuff if NULL is passed as the test. A >test that always r=
eturns 1 still triggers all the file system stuff, even though it's not nee=
ded.=0A=
>=0A=
>nfsd_set_fh_dentry should pass NULL to exportfs_decode_fh_raw if NFSEXP_NO=
SUBTREECHECK is set.=0A=
>=0A=
> discovered this while looking into a performance problem caused by a path=
ological client that was sending 40,000 RPCs/sec, ?>almost all get=0A=
>GETATTR or ACCESS. It was causing the nfsd's to be stuck at 100% CPU by lo=
cks in file system code invoked by this unnecessary >code.=0A=
=0A=
(We fixed the client by mounting with NFS3 rather than NFS4. This suggests =
an issue with the NFS 4 client side. Unfortunately I don't have enough info=
rmation to make a useful report.)=0A=
=0A=
=0A=
=0A=
=0A=