From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Tomas Winkler" Subject: Re: [RFC v2] mac80211: assign needed_headroom/tailroom for netdevs Date: Mon, 5 May 2008 20:15:23 +0300 Message-ID: <1ba2fa240805051015t7dfd3bd2nf7bc2fc1ab9799ca@mail.gmail.com> References: <1209936253.7304.10.camel@johannes.berg> <1209936745.7304.16.camel@johannes.berg> <20080504.173051.133197507.davem@davemloft.net> <1209972139.3655.9.camel@johannes.berg> <1ba2fa240805050727r2060b0b4x3a9b3240647b66b1@mail.gmail.com> <1210000923.8245.26.camel@johannes.berg> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Cc: "David Miller" , linville-2XuSBdqkA4R54TAoqtyWWQ@public.gmane.org, netdev-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, linux-wireless-u79uwXL29TY76Z2rM5mHXA@public.gmane.org To: "Johannes Berg" Return-path: In-Reply-To: <1210000923.8245.26.camel-YfaajirXv214zXjbi5bjpg@public.gmane.org> Content-Disposition: inline Sender: linux-wireless-owner-u79uwXL29TY76Z2rM5mHXA@public.gmane.org List-Id: netdev.vger.kernel.org On Mon, May 5, 2008 at 6:22 PM, Johannes Berg wrote: > > > I've did some measurement of the TX path on an embedded system (2.6.23 kernel) > > When bridging packets from an ethernet device to wireless there is > > loss of 12% in the CPU utilization and equivalent throughput reduction > > in data packets that are checked and expanded in > > ieee80211_subif_start_xmit function. > > Yeah, I figured. > > > > The expansion is just due to bigger size of the 80211 header size, yet > > the whole packet is reallocated and copied. As we are reaching 11n > > rates 200bps and up this starts to be visible. > > When header was reserved to the proper side already in the ethernet > > driver the overhead was gone. Yet this doesn't seems to be a correct > > solution for bridging or forwarding. > > For example Iwlwifi HW supports scattered packets this would allow > > just reallocate the header, providing data portion is aligned. > > Right. Not all hardware supports this though, I would set NETIF_F_SG OR FRAGLIS to features...? (What actually is the difference?) but even when it does I > don't see what we can do unless we want to do all this inside mac80211 > which I'd rather not. Like Sending mac80211 header OOB as xmit function argument? This will probably affect all the wme code as well... Not good. > SKBs don't have a way to say "I need N bytes writable headroom but I can > do s/g operation for the rest" which is what we'd need. If that was > available, we could even work with clones, then we could pull away the > ethernet header and build the 802.11/device headers in separate buffers, > demoting the old 'skb head' buffer to a data buffer... > Isn't this a requirement that header fits into a continuous buffer ? It's sounds strange to me that there is no solution for efficient bridging... Can bridging code handle this if we have native interface? Thanks Tomas > johannes > -- To unsubscribe from this list: send the line "unsubscribe linux-wireless" in the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org More majordomo info at http://vger.kernel.org/majordomo-info.html