From mboxrd@z Thu Jan 1 00:00:00 1970 From: Stephen Hemminger Subject: Re: long initialization of rte_eal_hugepage_init Date: Tue, 5 Sep 2017 21:24:06 -0700 Message-ID: References: <6DAF063A35010343823807B082E5681F1A72FDB1@mbx05.360buyAD.local> Mime-Version: 1.0 Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable Cc: dev@dpdk.org, users@dpdk.org To: =?UTF-8?B?546L5b+X5YWL?= Return-path: Received: from mail-pg0-f47.google.com (mail-pg0-f47.google.com [74.125.83.47]) by dpdk.org (Postfix) with ESMTP id B46BF3DC for ; Wed, 6 Sep 2017 06:24:08 +0200 (CEST) Received: by mail-pg0-f47.google.com with SMTP id m9so13250878pgd.3 for ; Tue, 05 Sep 2017 21:24:08 -0700 (PDT) In-Reply-To: <6DAF063A35010343823807B082E5681F1A72FDB1@mbx05.360buyAD.local> List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org Sender: "dev" Linux zeros huge pages by default. There was a fix in later releases On Sep 5, 2017 8:24 PM, "=E7=8E=8B=E5=BF=97=E5=85=8B" wr= ote: > Hi All, > > I observed that rte_eal_hugepage_init() will take quite long time if ther= e > are lots of huge pages. Example I have 500 1G huge pages, and it takes > about 2 minutes. That is too long especially for application restart case= . > > If the application only needs limited huge page while the host have lots > of huge pages, the algorithm is not so efficent. Example, we only need 1G > memory from each socket. > > What is the proposal from DPDK community? Any solution? > > Note I tried version dpdk 16.11. > > Br, > Wang Zhike >