From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: <dev-bounces@dpdk.org> Received: from dpdk.org (dpdk.org [92.243.14.124]) by inbox.dpdk.org (Postfix) with ESMTP id 1BBDDA04B1; Mon, 23 Nov 2020 08:40:53 +0100 (CET) Received: from [92.243.14.124] (localhost [127.0.0.1]) by dpdk.org (Postfix) with ESMTP id 16D0037AF; Mon, 23 Nov 2020 08:40:51 +0100 (CET) Received: from szxga01-in.huawei.com (szxga01-in.huawei.com [45.249.212.187]) by dpdk.org (Postfix) with ESMTP id 4E0C4375B; Mon, 23 Nov 2020 08:40:48 +0100 (CET) Received: from DGGEMM403-HUB.china.huawei.com (unknown [172.30.72.56]) by szxga01-in.huawei.com (SkyGuard) with ESMTP id 4CffFm11RMzXfLC; Mon, 23 Nov 2020 15:40:28 +0800 (CST) Received: from DGGEMM533-MBX.china.huawei.com ([169.254.5.42]) by DGGEMM403-HUB.china.huawei.com ([10.3.20.211]) with mapi id 14.03.0487.000; Mon, 23 Nov 2020 15:40:33 +0800 From: wangyunjian <wangyunjian@huawei.com> To: Thomas Monjalon <thomas@monjalon.net>, "anatoly.burakov@intel.com" <anatoly.burakov@intel.com> CC: "stable@dpdk.org" <stable@dpdk.org>, "dev@dpdk.org" <dev@dpdk.org>, "david.marchand@redhat.com" <david.marchand@redhat.com>, "Lilijun (Jerry)" <jerry.lilijun@huawei.com>, xudingke <xudingke@huawei.com>, "bruce.richardson@intel.com" <bruce.richardson@intel.com>, "john.mcnamara@intel.com" <john.mcnamara@intel.com>, "asafp@nvidia.com" <asafp@nvidia.com> Thread-Topic: [dpdk-stable] [dpdk-dev] [PATCH v3] eal: fix create user mem map repeatedly when it exists Thread-Index: AQHWo57F7aOjtaNYVkifJCCXNTgsH6mgB8gAgCjglwCAC0J9gIABZLFQ Date: Mon, 23 Nov 2020 07:40:33 +0000 Message-ID: <34EFBCA9F01B0748BEB6B629CE643AE60DB32BD6@DGGEMM533-MBX.china.huawei.com> References: <1595515713-24640-1-git-send-email-wangyunjian@huawei.com> <1768774.JEQ3pMzOXi@thomas> <6957254.HVmevjuWZl@thomas> <11688709.CXgpgmMZx0@thomas> In-Reply-To: <11688709.CXgpgmMZx0@thomas> Accept-Language: en-US Content-Language: zh-CN X-MS-Has-Attach: X-MS-TNEF-Correlator: x-originating-ip: [10.174.187.156] Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 X-CFilter-Loop: Reflected Subject: Re: [dpdk-dev] [dpdk-stable] [PATCH v3] eal: fix create user mem map repeatedly when it exists X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK patches and discussions <dev.dpdk.org> List-Unsubscribe: <https://mails.dpdk.org/options/dev>, <mailto:dev-request@dpdk.org?subject=unsubscribe> List-Archive: <http://mails.dpdk.org/archives/dev/> List-Post: <mailto:dev@dpdk.org> List-Help: <mailto:dev-request@dpdk.org?subject=help> List-Subscribe: <https://mails.dpdk.org/listinfo/dev>, <mailto:dev-request@dpdk.org?subject=subscribe> Errors-To: dev-bounces@dpdk.org Sender: "dev" <dev-bounces@dpdk.org> > -----Original Message----- > From: Thomas Monjalon [mailto:thomas@monjalon.net] > Sent: Monday, November 23, 2020 2:20 AM > To: anatoly.burakov@intel.com; wangyunjian <wangyunjian@huawei.com> > Cc: stable@dpdk.org; dev@dpdk.org; david.marchand@redhat.com; Lilijun > (Jerry) <jerry.lilijun@huawei.com>; xudingke <xudingke@huawei.com>; > bruce.richardson@intel.com; john.mcnamara@intel.com; asafp@nvidia.com > Subject: Re: [dpdk-stable] [dpdk-dev] [PATCH v3] eal: fix create user mem= map > repeatedly when it exists >=20 > 15/11/2020 15:23, Thomas Monjalon: > > 20/10/2020 16:09, Thomas Monjalon: > > > 16/10/2020 11:28, wangyunjian: > > > > From: Yunjian Wang <wangyunjian@huawei.com> > > > > > > > > Currently, a issue that a container has many devices and the > > > > application will map the same memory many times. The kernel driver > > > > returns EEXIST as long as there are overlapping memory areas. As a > > > > result, we repeatedly create new user mem map entry for the same > > > > memory segment and this will lead to no more space for other user > > > > mem maps. > > > > > > > > To resolve the issue, add support to remove the same entry in the > > > > function compact_user_maps(). > > > > > > Sorry I don't understand the explanations above. > > > Anatoly, please could you help in rewording? > > > > Ping for rewording please. >=20 > What is the conclusion? This fix is not worth the effort? >=20 In my opinion, this issue needs to be fixed. Currently, the 'user_mem_maps-= >maps[]' may store many same user mem maps but the maps array is limited, which will= lead to other mem maps cannot be created because of no more space left. Thanks, Yunjian