From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Burakov, Anatoly" Subject: Re: DPDK 17.11.4 (Madvise)Transparent Huge pages Date: Tue, 8 Jan 2019 16:10:45 +0000 Message-ID: References: <6982c4b0-6475-eca5-49f3-b27fe8364768@intel.com> Mime-Version: 1.0 Content-Type: text/plain; charset=utf-8; format=flowed Content-Transfer-Encoding: 7bit Cc: dev@dpdk.org To: chetan bhasin Return-path: Received: from mga17.intel.com (mga17.intel.com [192.55.52.151]) by dpdk.org (Postfix) with ESMTP id 16E001B20A for ; Tue, 8 Jan 2019 17:10:48 +0100 (CET) In-Reply-To: Content-Language: en-US List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org Sender: "dev" On 08-Jan-19 1:15 PM, chetan bhasin wrote: > Thanks Anatoly > > On Tue, Jan 8, 2019, 16:01 Burakov, Anatoly wrote: > > On 02-Jan-19 3:31 PM, chetan bhasin wrote: > > Hi, > > > > I am using DPDK 17.11.4 version . Do anybody have idea that DPDK > is using > > benefit of Transparent huge-pages in case of Madvise. > > > > Thanks, > > Chetan Bhasin > > > > Hi, > > DPDK does not use MADVISE flags to allocate its hugepages - it > allocates > hugepages explicitly [1] [2]. > > [1] > http://git.dpdk.org/dpdk/tree/lib/librte_eal/linuxapp/eal/eal_memalloc.c#n367 > [2] > http://git.dpdk.org/dpdk/tree/lib/librte_eal/linuxapp/eal/eal_memory.c#n336 > > -- > Thanks, > Anatoly > Apologies, i didn't notice that the question was about 17.11, so the source code links are incorrect. However, the answer itself is still correct - we always did allocate hugepages directly, and we never used MADVISE flags. -- Thanks, Anatoly