From: "" <slowforce@zju.edu.cn>
To: ajz@cambridgebroadband.com
Cc: linuxppc-embedded@lists.linuxppc.org
Subject: Re: ATM issue: one Host Four Nodes
Date: Fri, 06 Sep 2002 11:53:28 +0800 [thread overview]
Message-ID: <200209060357.WAA15082@lists.linuxppc.org> (raw)
Hi Alex£¬
you mean that maybe i need an ATM switch to creat the ring topology
how can i implement it? can you give more detail info on it?
Regards
Li
ÔÚÄúµÄÀ´ÐÅÖÐÔø¾Ìáµ½:
>From:Alex Zeffertt <ajz@cambridgebroadband.com>
>Reply-To:
>To: <slowforce@zju.edu.cn>
>Subject: Re: ATM issue: one Host Four Nodes
>
>On Thu, 5 Sep 2002, wrote:
>
>
>In each NODE set up 1 terminated VC, and 3 switched VCs (using the
>atm-860.o specific /proc/net/atm/switch interface).
>
>here's an example of how to set up a switched VC from 0.0.32 to 0.0.32
>using the atm-860.o driver:
>
>echo add 0.0.32 0.0.32 1000 cbr > /proc/net/atm/switch
>
> ^ ^ ^ ^
> from-VC to-VC PCR TT
>
>See http://mpc860sar.sourceforge.net for the source code.
>
>Alex
>
>BTW: If you're board only has one PHY then you need an ATM switch in the
>middle to create the ring topology. If it's multi PHY then you will need
>to modify the atm-860.o driver because it doesn't support this yet. (I
>think that multi-PHY is only available on MPC862s anyway....)
>
>>
>> Hi all,
>> We just have such a system to build.
>> ________
>> | |
>> RX | ATM |_TX____________________________
>> |---------------------------->| HOST | |
>> | | | |
>> | |______| |
>> | |
>> | ________ ________ ________ ________ |
>> | | | | | | | | | |
>> | TX | ATM | RX TX| ATM | RX TX| ATM | RX TX| ATM | RX |
>> |------| NODE |<------| NODE |<-------| NODE |<------| NODE |<------|
>> | | | | | | | |
>> |______| |______| |______| |______|
>> A B C D
>> It's used to perform high speed data acqusition.
>> ATM HOST -- a pc with an ATM card
>> ATM NODE -- MPC860 with linux-2.4.4
>>
>> The ATM HOST is responisble for sending controlling information to ATM NODEs
>> and receiving data from each NODEs.
>> The ATM NODE is responsible for performing data acqusition.
>>
>> As the diagram show,ATM NODEs are connected one after another.
>> we use one VPI/VCI to identify one ATM NODE, so if the ATM HOST send the
>> control message to ATM NODE D, the message will touch ATM NODE A¡¢B¡¢C first,
>> then ATM NODE D. In order to improve the system capacity and efficiency,
>> the ATM NODE A¡¢B¡¢C should ignore this message(not parse it) and send it
>> to the next node, in another words, this message should be bypassed in low
>> level(e.g. PHY level) by ATM NODE A¡¢B¡¢C. How can i get this point?
>> Any advice will be greatly appreciated!
>> Best Regards!
>> Li
>>
>>
>>
>
>
** Sent via the linuxppc-embedded mail list. See http://lists.linuxppc.org/
next reply other threads:[~2002-09-06 3:53 UTC|newest]
Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top
2002-09-06 3:53 slowforce [this message]
2002-09-06 8:37 ` ATM issue: one Host Four Nodes Alex Zeffertt
-- strict thread matches above, loose matches on Subject: below --
2002-09-05 13:00 slowforce
2002-09-05 15:54 ` Alex Zeffertt
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=200209060357.WAA15082@lists.linuxppc.org \
--to=slowforce@zju.edu.cn \
--cc=ajz@cambridgebroadband.com \
--cc=linuxppc-embedded@lists.linuxppc.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;
as well as URLs for NNTP newsgroup(s).