From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mga02.intel.com (mga02.intel.com [134.134.136.20]) by dpdk.org (Postfix) with ESMTP id 6CC595A52 for ; Thu, 24 Dec 2015 09:34:16 +0100 (CET) Received: from orsmga002.jf.intel.com ([10.7.209.21]) by orsmga101.jf.intel.com with ESMTP; 24 Dec 2015 00:34:15 -0800 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.20,472,1444719600"; d="scan'208";a="877940342" Received: from fmsmsx108.amr.corp.intel.com ([10.18.124.206]) by orsmga002.jf.intel.com with ESMTP; 24 Dec 2015 00:34:15 -0800 Received: from fmsmsx155.amr.corp.intel.com (10.18.116.71) by FMSMSX108.amr.corp.intel.com (10.18.124.206) with Microsoft SMTP Server (TLS) id 14.3.248.2; Thu, 24 Dec 2015 00:34:14 -0800 Received: from shsmsx103.ccr.corp.intel.com (10.239.110.14) by FMSMSX155.amr.corp.intel.com (10.18.116.71) with Microsoft SMTP Server (TLS) id 14.3.248.2; Thu, 24 Dec 2015 00:34:14 -0800 Received: from shsmsx101.ccr.corp.intel.com ([169.254.1.190]) by SHSMSX103.ccr.corp.intel.com ([169.254.4.28]) with mapi id 14.03.0248.002; Thu, 24 Dec 2015 16:34:13 +0800 From: "Qiu, Michael" To: "Wang, Zhihong" , "dev@dpdk.org" Thread-Topic: [dpdk-dev] [RFC PATCH 0/2] Reduce DPDK initialization time Thread-Index: AQHRIewXasWQGsd2UUaIN6b9Cug5Ew== Date: Thu, 24 Dec 2015 08:34:12 +0000 Message-ID: <533710CFB86FA344BFBF2D6802E6028622F002AE@SHSMSX101.ccr.corp.intel.com> References: <1447817231-10510-1-git-send-email-zhihong.wang@intel.com> Accept-Language: en-US Content-Language: en-US X-MS-Has-Attach: X-MS-TNEF-Correlator: x-originating-ip: [10.239.127.40] Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Cc: "Mata, Jhoanna E" Subject: Re: [dpdk-dev] [RFC PATCH 0/2] Reduce DPDK initialization time X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: patches and discussions about DPDK List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 24 Dec 2015 08:34:16 -0000 On 11/18/2015 6:30 PM, Zhihong Wang wrote:=0A= > This RFC patch aims to reduce DPDK initialization time, which is importan= t in cases such as micro service.=0A= >=0A= > Changes are:=0A= >=0A= > 1. Reduce timer initialization time=0A= >=0A= > 2. Remove unnecessary hugepage zero-filling operations=0A= >=0A= > With this patch:=0A= >=0A= > 1. Timer initialization time can be reduced by 4/10 second=0A= >=0A= > 2. Memory initialization time can be reduced nearly by half=0A= >=0A= > The 2nd topic has been brought up before in this thread:=0A= > http://dpdk.org/dev/patchwork/patch/4219/=0A= >=0A= > Zhihong Wang (2):=0A= > lib/librte_eal: Reduce timer initialization time=0A= > lib/librte_eal: Remove unnecessary hugepage zero-filling=0A= >=0A= > lib/librte_eal/linuxapp/eal/eal_memory.c | 5 +----=0A= > lib/librte_eal/linuxapp/eal/eal_timer.c | 2 +-=0A= > 2 files changed, 2 insertions(+), 5 deletions(-)=0A= >=0A= =0A= As I tested with 8192 hugepages(size 2M), one nic 82599 bind, using time=0A= to get the seconds used:=0A= with this patch:=0A= =0A= echo quit | time ./x86_64-native-linuxapp-gcc/app/testpmd -c 0x3 -n 4 -- -i= =0A= 2.15 user=0A= 5.55 system=0A= 0:07.82 elapsed=0A= =0A= Without patch:=0A= echo quit | time ./x86_64-native-linuxapp-gcc/app/testpmd -c 0x3 -n 4 -- -i= =0A= 3.18 user=0A= 5.63 system=0A= 0:09.32 elapsed=0A= =0A= 1.5s saved, 16% improvement, I don't know if this is good enough, but=0A= indeed save lots of time.=0A= =0A= Thanks,=0A= Michael=0A=