Goals: Netstack?!? (was: Not-yet-finished ALTQ patch.)

[Max Laier]

g> <3fc8ad5b$0$80973$415eb37d at xxxxxxxxxxxxxxxxxxxxxxxxxxxxxx> <20031129160152.GA98507 at xxxxxxxxxx> <20031129160830.GB98507 at xxxxxxxxxx> <20031129191030.GD98507 at xxxxxxxxxx> <3fc945d9$0$80976$415eb37d at xxxxxxxxxxxxxxxxxxxxxxxxxxxxxx> <20031130170326.GE98507 at xxxxxxxxxx> <200311302024.hAUKO9NY016079 at xxxxxxxxxxxxxxxxxxxx> <20031130203609.GF98507 at xxxxxxxxxx> <cone.1070372550.990476.12740.1001 at xxxxxxxxxxxxxxxxxxx> <200312021847.hB2IlNnN029141 at xxxxxxxxxxxxxxxxxxxx>
In-Reply-To: <200312021847.hB2IlNnN029141 at xxxxxxxxxxxxxxxxxxxx>
Content-Type: text/plain; charset=us-ascii; format=flowed
Content-Transfer-Encoding: 7bit
Lines: 27
NNTP-Posting-Host: 217.227.156.60
X-Trace: 1070394247 crater_reader.dragonflybsd.org 80977 217.227.156.60
Xref: crater_reader.dragonflybsd.org dragonfly.kernel:2550

Matthew Dillon wrote:
>     There's also an issue in regards to Jeff's work, which I think should
>     have priority over altq.  If altq is messing with ifqueue then
>     it probably conflicts fairly seriously with what Jeff is doing.

understood! In that case I guess net related stuff should be delayed 
till after Jeff has finished ....

. .. with whatsoever he's doing ;)

I'd like to know more about DF's net stack/netisr handling and the goals 
in that area. I understand that your intention is to keep as much data 
as possible locally. Yet, this is very tricky (and extensive) work when 
it comes to protocol dependencies, routing code and alike. Per protocol 
lwkt & messaging is a way out (I guess), but at the expense of writing 
quite a bunch of net code from scratch ...

. .. so my basic question: Is this Jeff-only work for now? Are there any 
goals/prototypes, yet? Anything written down? If that's still "confi- 
dential" work, when will we you go public with this stuff?

Thanks for clues, pointers ... anything really.

----
Best regards,
Max		mailto:max at xxxxxxxxxxxxxx