From: Bob McMahon <bob.mcmahon@broadcom.com>
To: David Lang <david@lang.hm>
Cc: Dave Taht <dave.taht@gmail.com>,
Make-Wifi-fast <make-wifi-fast@lists.bufferbloat.net>,
BBR Development <bbr-dev@googlegroups.com>,
bloat <bloat@lists.bufferbloat.net>
Subject: Re: [Bloat] [Make-wifi-fast] [bbr-dev] Aggregating without bloating - hard times for tcp and wifi
Date: Tue, 22 Nov 2022 12:48:07 -0800 [thread overview]
Message-ID: <CAHb6LvoS_LQ2juXT1Bzhwzkn6A5LL3OijP_aaM7MTs3k=2K+qA@mail.gmail.com> (raw)
In-Reply-To: <CAHb6LvqbaMDb75mrZ+tJM8HNVAmL9m55019s=t5C06MVSJwcjA@mail.gmail.com>
[-- Attachment #1.1: Type: text/plain, Size: 3639 bytes --]
I don't know Qualcomm's offerings but here are some from Broadcom.
https://www.broadcom.com/products/wireless/wireless-lan-infrastructure/bcm67263
The BCM4916 forwarding plane is done with a network processor and doesn't
run Linux. Linux may be used to build the forwarding tables and this is
standard "merchant silicon" forwarding approcch, let some CPU/stack build
the topology tables and then realize the packet forwarding in
(programmable) hardware.
https://docs.broadcom.com/doc/4916-PB1XX
Bob
On Tue, Nov 22, 2022 at 12:28 PM Bob McMahon <bob.mcmahon@broadcom.com>
wrote:
> Some main purposes of the WiFi CPU is 802.3 to 802.11 L2 translational
> bridging and handling 802.11 protocols for things like association. Most
> forwarded packets don't hit the main CPU anymore. This first sw to hw
> transition occurred decades ago with real internet routers (equipment that
> run IGPs and BGP) which started as software in the early 90s and then moved
> to hardware. The same engineering has been happening for home gateways or
> WiFi APs bridging wired to wireless.
>
> Bob
>
> On Tue, Nov 22, 2022 at 12:16 PM David Lang <david@lang.hm> wrote:
>
>> sorry, when I was saying 'the cpu', I was meaning the main one running
>> linux,
>> not something that's part of the wifi chipset.
>>
>> I would be very surprised if the wifi chipset is doing any packet
>> routing, as
>> opposed to just sending the packets to the main processor.
>>
>> Remember, the common case isn't forwarding from one wifi device to
>> another, it's
>> moving between wifi devices and the wired uplink.
>>
>> David Lang
>>
>> On Tue, 22 Nov 2022, Bob McMahon wrote:
>>
>> > An AP's radio complex may have a CPU but that doesn't mean it is the
>> > standard linux stack as most think of it. Many consider this as part of
>> > "firmware" which can be Linux, a Linux derivative or other. Also, there
>> > are some levels of wired/wireless forwarding plane integration done at
>> the
>> > hardware level that many might be surprised by.
>> >
>> > Bob
>> >
>> > On Tue, Nov 22, 2022 at 12:03 PM David Lang <david@lang.hm> wrote:
>> >
>> >> On Tue, 22 Nov 2022, Bob McMahon via Make-wifi-fast wrote:
>> >>
>> >>> Finally, many (most?) APs are forwarding and feeding packets at at the
>> >>> hardware level so not sure that the linux stack matters as much for
>> an AP
>> >>> based analysis, particularly when considering multi user
>> transmissions,
>> >>> i.e. multiple WiFi clients are active and sharing TXOPs.
>> >>
>> >> APs forward packets within the switch at the hardware level, but the
>> >> radios have
>> >> to go through the CPU, so any wired <-> wireless needs to go through
>> the
>> >> CPU,
>> >> and I would be incredibly surprised if the wifi chips did wireless <->
>> >> wireless
>> >> routing at the hardware level.
>> >>
>> >> David Lang
>> >>
>> >
>> >
>>
>
--
This electronic communication and the information and any files transmitted
with it, or attached to it, are confidential and are intended solely for
the use of the individual or entity to whom it is addressed and may contain
information that is confidential, legally privileged, protected by privacy
laws, or otherwise restricted from disclosure to anyone else. If you are
not the intended recipient or the person responsible for delivering the
e-mail to the intended recipient, you are hereby notified that any use,
copying, distributing, dissemination, forwarding, printing, or copying of
this e-mail is strictly prohibited. If you received this e-mail in error,
please return the e-mail to the sender, delete it from your computer, and
destroy any printed copy of it.
[-- Attachment #1.2: Type: text/html, Size: 4800 bytes --]
[-- Attachment #2: S/MIME Cryptographic Signature --]
[-- Type: application/pkcs7-signature, Size: 4206 bytes --]
next prev parent reply other threads:[~2022-11-22 20:48 UTC|newest]
Thread overview: 13+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-11-22 6:04 [Bloat] " Dave Taht
2022-11-22 19:42 ` [Bloat] [bbr-dev] " Bob McMahon
2022-11-22 20:03 ` [Bloat] [Make-wifi-fast] " David Lang
2022-11-22 20:13 ` Bob McMahon
2022-11-22 20:16 ` David Lang
2022-11-22 20:28 ` Bob McMahon
2022-11-22 20:48 ` Bob McMahon [this message]
2022-11-22 20:10 ` [Bloat] " Neal Cardwell
2022-11-22 20:53 ` Toke Høiland-Jørgensen
2022-11-22 21:00 ` Bob McMahon
2022-11-23 13:50 ` Toke Høiland-Jørgensen
2022-11-23 20:36 ` Bob McMahon
[not found] ` <003d01d8ffc5$2ace1a20$806a4e60$@umt.edu.pk>
2022-11-24 16:23 ` Dave Taht
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
List information: https://lists.bufferbloat.net/postorius/lists/bloat.lists.bufferbloat.net/
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to='CAHb6LvoS_LQ2juXT1Bzhwzkn6A5LL3OijP_aaM7MTs3k=2K+qA@mail.gmail.com' \
--to=bob.mcmahon@broadcom.com \
--cc=bbr-dev@googlegroups.com \
--cc=bloat@lists.bufferbloat.net \
--cc=dave.taht@gmail.com \
--cc=david@lang.hm \
--cc=make-wifi-fast@lists.bufferbloat.net \
/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