From mboxrd@z Thu Jan 1 00:00:00 1970 From: Eric Dumazet Subject: Re: [PATCH] net: mv643xx_eth: Add GRO support Date: Thu, 11 Apr 2013 09:10:44 -0700 Message-ID: <1365696644.3887.172.camel@edumazet-glaptop> References: <1365684023-9967-1-git-send-email-sebastian.hesselbarth@gmail.com> <20130411131333.GD1910@1wt.eu> <20130411150326.GA19978@1wt.eu> <20130411153256.GH1910@1wt.eu> <1365695675.3887.165.camel@edumazet-glaptop> <20130411160258.GI1910@1wt.eu> Mime-Version: 1.0 Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: 7bit Cc: Sebastian Hesselbarth , Andrew Lunn , Jason Cooper , Benjamin Herrenschmidt , linux-kernel@vger.kernel.org, Florian Fainelli , Soeren Moch , Paul Mackerras , Lennert Buytenhek , Dale Farnsworth , netdev@vger.kernel.org, linuxppc-dev@lists.ozlabs.org, "David S. Miller" , linux-arm-kernel@lists.infradead.org To: Willy Tarreau Return-path: In-Reply-To: <20130411160258.GI1910@1wt.eu> Sender: linux-kernel-owner@vger.kernel.org List-Id: netdev.vger.kernel.org On Thu, 2013-04-11 at 18:02 +0200, Willy Tarreau wrote: > OK, that makes sense indeed, I didn't think about this case. All > I remember was that the old call achieved a higher packet rate > than napi_gro_receive, but it was on an older kernel and I can't > be more specifics after several months :-/ Its probably true that the GRO handler consumes more cpu for packets that cant be aggregated in the end. Thats a trade off, and maybe we could add in the core stack a device feature to instruct gro handler to do a short cut for packets with no checksum. Or better a sysctl so that a static_branch can be used.