From mboxrd@z Thu Jan 1 00:00:00 1970 From: Thomas Monjalon Subject: Re: Future Direction for rte_eth_stats_get() Date: Fri, 22 Jan 2016 17:37:12 +0100 Message-ID: <2905167.2LHbWGS9Eh@xps13> References: <78791945dbf442b291adb72df8ec09f3@XCH-RCD-016.cisco.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7Bit Cc: dev@dpdk.org To: "David Harton (dharton)" Return-path: Received: from mail-wm0-f41.google.com (mail-wm0-f41.google.com [74.125.82.41]) by dpdk.org (Postfix) with ESMTP id F335B8EA1 for ; Fri, 22 Jan 2016 17:38:13 +0100 (CET) Received: by mail-wm0-f41.google.com with SMTP id b14so141054958wmb.1 for ; Fri, 22 Jan 2016 08:38:13 -0800 (PST) In-Reply-To: <78791945dbf442b291adb72df8ec09f3@XCH-RCD-016.cisco.com> List-Id: patches and discussions about DPDK List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org Sender: "dev" 2016-01-22 16:04, David Harton: > I think parsing strings is expensive CPU wise [...] > wondering if something that is performance friendly for the user/application > and flexible for the drivers is possible. I think we need some numbers from experimentations and some requirements. How many cycles it takes to read stats? How often stats must be read at max?