From mboxrd@z Thu Jan 1 00:00:00 1970 From: John Fastabend Subject: Re: [PATCH RFC 11/11] net/mlx5e: XDP TX xmit more Date: Wed, 7 Sep 2016 06:44:18 -0700 Message-ID: <57D019B2.7070007@gmail.com> References: <1473252152-11379-1-git-send-email-saeedm@mellanox.com> <1473252152-11379-12-git-send-email-saeedm@mellanox.com> Mime-Version: 1.0 Content-Type: text/plain; charset=windows-1252 Content-Transfer-Encoding: 7bit Cc: netdev@vger.kernel.org, Tariq Toukan , Brenden Blanco , Alexei Starovoitov , Tom Herbert , Martin KaFai Lau , Jesper Dangaard Brouer , Daniel Borkmann , Eric Dumazet , Jamal Hadi Salim To: Saeed Mahameed , iovisor-dev Return-path: Received: from mail-pf0-f171.google.com ([209.85.192.171]:35571 "EHLO mail-pf0-f171.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752277AbcIGNog (ORCPT ); Wed, 7 Sep 2016 09:44:36 -0400 Received: by mail-pf0-f171.google.com with SMTP id w87so6938582pfk.2 for ; Wed, 07 Sep 2016 06:44:35 -0700 (PDT) In-Reply-To: <1473252152-11379-12-git-send-email-saeedm@mellanox.com> Sender: netdev-owner@vger.kernel.org List-ID: On 16-09-07 05:42 AM, Saeed Mahameed wrote: > Previously we rang XDP SQ doorbell on every forwarded XDP packet. > > Here we introduce a xmit more like mechanism that will queue up more > than one packet into SQ (up to RX napi budget) w/o notifying the hardware. > > Once RX napi budget is consumed and we exit napi RX loop, we will > flush (doorbell) all XDP looped packets in case there are such. > > XDP forward packet rate: > > Comparing XDP with and w/o xmit more (bulk transmit): > > Streams XDP TX XDP TX (xmit more) > --------------------------------------------------- > 1 4.90Mpps 7.50Mpps > 2 9.50Mpps 14.8Mpps > 4 16.5Mpps 25.1Mpps > 8 21.5Mpps 27.5Mpps* > 16 24.1Mpps 27.5Mpps* > Hi Saeed, How many cores are you using with these numbers? Just a single core? Or are streams being RSS'd across cores somehow. > *It seems we hit a wall of 27.5Mpps, for 8 and 16 streams, > we will be working on the analysis and will publish the conclusions > later. > Thanks, John