From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: <jianbo.liu@linaro.org> Received: from mail-yb0-f179.google.com (mail-yb0-f179.google.com [209.85.213.179]) by dpdk.org (Postfix) with ESMTP id CB29329CF for <dev@dpdk.org>; Mon, 26 Sep 2016 07:12:47 +0200 (CEST) Received: by mail-yb0-f179.google.com with SMTP id i83so7047285ybi.3 for <dev@dpdk.org>; Sun, 25 Sep 2016 22:12:47 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; h=mime-version:in-reply-to:references:from:date:message-id:subject:to :cc; bh=GY35vXD72rNdU2oOESRCWXml6oU+Lm+kpzg09bneh6c=; b=IK8gu9nyyIeQljrmLCqmeLBa4NSR5N+97h4XChNSx/f2eW5b7TtigICq7W1f0X8Jdc DsA9dL7N5dKo4Hghi6F4Rh4I3dFE6A3eyRn7GzIarWr9PePbte3CfBKeESstLjzxJ5N0 9vgIb4D35nMsRw1yxHId6jN72nMMx47oLs6J8= X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20130820; h=x-gm-message-state:mime-version:in-reply-to:references:from:date :message-id:subject:to:cc; bh=GY35vXD72rNdU2oOESRCWXml6oU+Lm+kpzg09bneh6c=; b=khQ55t0LJLSrYVTS0W9pxoa/o/QHsKKbUC3R1TFUMVao+xMd4do/x7db2dARmR2BYk qF4MNBdk5O4qyvHOFHgWAlqBgoNLFc9C9WOJ5u0hHqNf9a0lWkT2+23nelX/ofl52co1 WZUGrvI6HzLq0WqQD7LkoqgG0JRnwVlk9aWYP1B8+qChGJSLoG/bxYNnKm+bd4bCibBk SZ3QEqBCK1o/ijxooWAn11D2fCfSXu7/dMGNqXsIuX7xs7k23rIVwQX3aiLFGZvHoqEa qAxpZJeQBS82OCPOjQrs4HLDoMDXYTkyFXb1j0r1BkV+K+KO4If0a4Hs+bsaVt/utZmQ oLOA== X-Gm-Message-State: AE9vXwPKseaVREuKJxqkMyxYe0fAsuBNnq/Vw9MZDOLcMEXxyyBucCAmaV/sOjmv8HWna4sXTiJqGQXnTJTPAmxe X-Received: by 10.37.174.137 with SMTP id b9mr15955215ybj.126.1474866767221; Sun, 25 Sep 2016 22:12:47 -0700 (PDT) MIME-Version: 1.0 Received: by 10.37.25.6 with HTTP; Sun, 25 Sep 2016 22:12:46 -0700 (PDT) In-Reply-To: <8F6C2BD409508844A0EFC19955BE09414E7B6EA6@SHSMSX103.ccr.corp.intel.com> References: <1471319402-112998-1-git-send-email-zhihong.wang@intel.com> <8F6C2BD409508844A0EFC19955BE09414E7B6204@SHSMSX103.ccr.corp.intel.com> <CAP4Qi3_DxAnvs0jX1P=G_PiLnRRbP5Wty-eU-OPE_81RGCAuTA@mail.gmail.com> <1536480.IYe8r5XoNN@xps13> <8F6C2BD409508844A0EFC19955BE09414E7B6EA6@SHSMSX103.ccr.corp.intel.com> From: Jianbo Liu <jianbo.liu@linaro.org> Date: Mon, 26 Sep 2016 13:12:46 +0800 Message-ID: <CAP4Qi39FfeA_B1-5D-5wzXK_S2wJXGUHp9S+w2Z_BtoedAfrfQ@mail.gmail.com> To: "Wang, Zhihong" <zhihong.wang@intel.com> Cc: Thomas Monjalon <thomas.monjalon@6wind.com>, "dev@dpdk.org" <dev@dpdk.org>, Yuanhan Liu <yuanhan.liu@linux.intel.com>, Maxime Coquelin <maxime.coquelin@redhat.com> Content-Type: text/plain; charset=UTF-8 Subject: Re: [dpdk-dev] [PATCH v3 0/5] vhost: optimize enqueue X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: patches and discussions about DPDK <dev.dpdk.org> List-Unsubscribe: <http://dpdk.org/ml/options/dev>, <mailto:dev-request@dpdk.org?subject=unsubscribe> List-Archive: <http://dpdk.org/ml/archives/dev/> List-Post: <mailto:dev@dpdk.org> List-Help: <mailto:dev-request@dpdk.org?subject=help> List-Subscribe: <http://dpdk.org/ml/listinfo/dev>, <mailto:dev-request@dpdk.org?subject=subscribe> X-List-Received-Date: Mon, 26 Sep 2016 05:12:48 -0000 On 25 September 2016 at 13:41, Wang, Zhihong <zhihong.wang@intel.com> wrote: > > >> -----Original Message----- >> From: Thomas Monjalon [mailto:thomas.monjalon@6wind.com] >> Sent: Friday, September 23, 2016 9:41 PM >> To: Jianbo Liu <jianbo.liu@linaro.org> >> Cc: dev@dpdk.org; Wang, Zhihong <zhihong.wang@intel.com>; Yuanhan Liu >> <yuanhan.liu@linux.intel.com>; Maxime Coquelin >> <maxime.coquelin@redhat.com> .... > This patch does help in ARM for small packets like 64B sized ones, > this actually proves the similarity between x86 and ARM in terms > of caching optimization in this patch. > > My estimation is based on: > > 1. The last patch are for mrg_rxbuf=on, and since you said it helps > perf, we can ignore it for now when we discuss mrg_rxbuf=off > > 2. Vhost enqueue perf = > Ring overhead + Virtio header overhead + Data memcpy overhead > > 3. This patch helps small packets traffic, which means it helps > ring + virtio header operations > > 4. So, when you say perf drop when packet size larger than 512B, > this is most likely caused by memcpy in ARM not working well > with this patch > > I'm not saying glibc's memcpy is not good enough, it's just that > this is a rather special use case. And since we see specialized > memcpy + this patch give better performance than other combinations > significantly on x86, we suggest to hand-craft a specialized memcpy > for it. > > Of course on ARM this is still just my speculation, and we need to > either prove it or find the actual root cause. > > It can be **REALLY HELPFUL** if you could help to test this patch on > ARM for mrg_rxbuf=on cases to see if this patch is in fact helpful > to ARM at all, since mrg_rxbuf=on the more widely used cases. > Actually it's worse than mrg_rxbuf=off.