From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-wm0-f51.google.com (mail-wm0-f51.google.com [74.125.82.51]) by dpdk.org (Postfix) with ESMTP id D9583377E for ; Tue, 24 Jan 2017 16:24:28 +0100 (CET) Received: by mail-wm0-f51.google.com with SMTP id r144so214464495wme.1 for ; Tue, 24 Jan 2017 07:24:28 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=6wind-com.20150623.gappssmtp.com; s=20150623; h=from:date:to:cc:subject:message-id:in-reply-to:references :mime-version:content-transfer-encoding; bh=BjnunfN7+Jfn7qTiSCf3ImG82E8sh+uhrpsRiKFTQyM=; b=JJDWXbHh7Ztu+StysmQBS0y6WLKK/NCR9XADii/4ns0dqvIVSoBek5rJP9Li7vxGUW PjgEg1mf8hRKH8JFGTXDsZZQiGrrg9SYggIC2OC1oJkTtquLCj6PJ5TzsFz8t/coHaPd lgkzQx9UrbtmT9owJPn1uK/x7S8ieyVF7A0Vk2fo5M4WLln3D8XfYEj9M6AQGKW/8Q55 OXtKs32ft/qZxY1mi6UudylxVorXbEUo4KkxmazzLY8yqFUP14Vp8xu2u0OvlXwJwNwY L5FgPmUW+2D6hKP8mDKlj8tIy7etYbHDz/cnd1bAFcV4JZfPZ0pqZNsT0hssS7NMNPPZ UbYA== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:from:date:to:cc:subject:message-id:in-reply-to :references:mime-version:content-transfer-encoding; bh=BjnunfN7+Jfn7qTiSCf3ImG82E8sh+uhrpsRiKFTQyM=; b=cUH5v9m8ZejosCArpzihOjeuAVOAFaaFkY0daEc3Tgw47dGuMZSGkwR4pD/ZwFv6qc kEXsfKLNLNtJ0lx0FBM+sdgM0Lhe7wwiHFWZTinoeT3Xf+2+YUUsg4UYE4btsN6yn6Pv ecNji+99CqAR9SFknsQAdcqj41N0GzD21L8IBNAxVI9OUcA1WSKptERYnSOSDW+R6fiw SqiJfzryWDKXaI9GKXZyMR/7gOwevorgNh2ZClWKpM4w+1RoLgXaRcEiHqSVWzN1yt6o 4jJAdD8bt6kNG8hBsNWkwIfU09KdDKclFC/YjOtG3OnSaztNKxtTaGvvGyiBWbtdxzMs S1xw== X-Gm-Message-State: AIkVDXI+eXtwcm9eR+p6rwK13z26FkoiQvHFNU89uf5sY6vP8uID12zAn1ZizddOnAqcLAeT X-Received: by 10.28.14.65 with SMTP id 62mr19185569wmo.46.1485271468367; Tue, 24 Jan 2017 07:24:28 -0800 (PST) Received: from glumotte.dev.6wind.com (host.78.145.23.62.rev.coltfrance.com. [62.23.145.78]) by smtp.gmail.com with ESMTPSA id a186sm26926665wmh.1.2017.01.24.07.24.28 (version=TLS1_2 cipher=ECDHE-RSA-CHACHA20-POLY1305 bits=256/256); Tue, 24 Jan 2017 07:24:28 -0800 (PST) From: Olivier MATZ X-Google-Original-From: Olivier MATZ Date: Tue, 24 Jan 2017 16:24:21 +0100 To: Olivier Matz Cc: Jerin Jacob , "Mcnamara, John" , "Horton, Remy" , "dev@dpdk.org" , "Pattan, Reshma" , Thomas Monjalon , "Richardson, Bruce" Message-ID: <20170124162421.5ffc7815@glumotte.dev.6wind.com> In-Reply-To: <20170118211128.78592a1b@platinum> References: <1484583573-30163-1-git-send-email-remy.horton@intel.com> <1484583573-30163-6-git-send-email-remy.horton@intel.com> <20170117042935.GA32676@localhost.localdomain> <20170117123418.GA2611@localhost.localdomain> <20170117162515.GA28925@localhost.localdomain> <20170118211128.78592a1b@platinum> X-Mailer: Claws Mail 3.14.1 (GTK+ 2.24.30; x86_64-pc-linux-gnu) MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Subject: Re: [dpdk-dev] [PATCH v7 5/6] lib: added new library for latency stats X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 24 Jan 2017 15:24:29 -0000 On Wed, 18 Jan 2017 21:11:28 +0100, Olivier Matz wrote: > Hi guys, > > On Tue, 17 Jan 2017 21:55:16 +0530, Jerin Jacob > > Oliver, > > > > Could you please suggest how to proceed further? > > > > Sorry for the lack of response. I know people are waiting for > me, but these days I have too many things to do at the same time, and > it's difficult to find time. > > In few words (I'll provide more detailed answers to the thread by > friday): I expected to post the mbuf rework patchset for this release, > which includes the structure changes (Jerin's patch for arm access, > timestamp, port, nb_segs, refcnt changes). But the patchset is clearly > not ready yet, it needs a rebase, and it lacks test. > > Jerin, I know that you submitted your patch a long time ago, and I'm > the only one to blame, please do not see any vendor preference in it. > > I'll check friday what's the effective state of the patchset in my > workspace. If I can extract a minimal patch that only change the > structure, I'll send it for discussion. But from what I remember, the > mbuf structure rework depends on changing the way we access the > refcnt, so it can be moved to the 2nd cache line. > > If that's not possible, I'll try propose some alternatives. I just posted a mbuf RFC patchset [1]. I think it contains most things that were mentioned on the ML. As checked with Thomas, it's too late to have it included in 17.02. I'll tend to agree with John that having the timestamp in the mbuf for latency is not an ABI break, since it is added at the end of the structure. So I won't oppose to add this field in the mbuf structure for the release. The mbuf rearm patch was not forgotten, but it took clearly too long to be integrated. With the benefit of hindsight, it should have been pushed without waiting the mbuf rework. Again, apologies for that, I understand it's quite frustrating. Anyway, tests or comments on my RFC patchset are welcome, so we can integrate it at the beginning of the 17.05 cycle. Regards, Olivier [1] http://dpdk.org/ml/archives/dev/2017-January/056187.html