public inbox for linux-wireless@vger.kernel.org
 help / color / mirror / Atom feed
From: "Tomas Winkler" <tomasw@gmail.com>
To: "Johannes Berg" <johannes@sipsolutions.net>
Cc: "David Miller" <davem@davemloft.net>,
	linville@tuxdriver.com, netdev@vger.kernel.org,
	linux-wireless@vger.kernel.org
Subject: Re: [RFC v2] mac80211: assign needed_headroom/tailroom for netdevs
Date: Mon, 5 May 2008 20:15:23 +0300	[thread overview]
Message-ID: <1ba2fa240805051015t7dfd3bd2nf7bc2fc1ab9799ca@mail.gmail.com> (raw)
In-Reply-To: <1210000923.8245.26.camel@johannes.berg>

On Mon, May 5, 2008 at 6:22 PM, Johannes Berg <johannes@sipsolutions.net> 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
>

  reply	other threads:[~2008-05-05 17:15 UTC|newest]

Thread overview: 38+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2008-05-04 21:24 [RFC] mac80211: assign needed_headroom/tailroom for netdevs Johannes Berg
2008-05-04 21:31 ` Johannes Berg
2008-05-04 21:32 ` [RFC v2] " Johannes Berg
2008-05-05  0:30   ` David Miller
2008-05-05  7:22     ` Johannes Berg
2008-05-05 14:27       ` Tomas Winkler
2008-05-05 15:22         ` Johannes Berg
2008-05-05 17:15           ` Tomas Winkler [this message]
2008-05-05 17:57             ` Johannes Berg
2008-05-05 18:58               ` David Miller
2008-05-05 19:05                 ` Johannes Berg
2008-05-05 19:50                   ` David Miller
2008-05-05 19:57                     ` Johannes Berg
2008-05-05 20:02                       ` David Miller
2008-05-05 20:10                         ` Johannes Berg
2008-05-05 20:44                           ` David Miller
2008-05-05 20:57                             ` Johannes Berg
2008-05-05 21:01                               ` David Miller
2008-05-05 22:37                               ` David Miller
2008-05-05 22:44                                 ` Johannes Berg
2008-05-05 23:14                                   ` David Miller
2008-05-05 23:23                                     ` Johannes Berg
2008-05-05 23:39                                       ` David Miller
2008-05-06  0:01                                         ` Johannes Berg
2008-05-06  0:08                                           ` David Miller
2008-05-06 11:13                                             ` Johannes Berg
2008-05-06  1:32                                         ` Herbert Xu
2008-05-13  5:01                                 ` David Miller
2008-05-05 23:03           ` David Miller
2008-05-05 23:17             ` Johannes Berg
2008-05-05 23:24               ` David Miller
2008-05-05 23:30                 ` Johannes Berg
2008-05-05 23:36             ` Johannes Berg
2008-05-05 23:40               ` David Miller
2008-05-13  3:52   ` David Miller
2008-05-13  9:01     ` Johannes Berg
2008-05-13  9:45       ` David Miller
2008-05-13 10:07         ` Johannes Berg

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1ba2fa240805051015t7dfd3bd2nf7bc2fc1ab9799ca@mail.gmail.com \
    --to=tomasw@gmail.com \
    --cc=davem@davemloft.net \
    --cc=johannes@sipsolutions.net \
    --cc=linux-wireless@vger.kernel.org \
    --cc=linville@tuxdriver.com \
    --cc=netdev@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox