[c-nsp] Products for dealing with packet re-ordering?

Alex K. nsp.lists at gmail.com
Wed Jan 10 14:59:30 EST 2018


Hello everyone,

I really glad to hear everyone opinion.

We're talking about a DC-to-DC scenario, aggregating a few 10GigE WAN
Ethernet links. Fun indeed :)

Brocade ASIC requirement is really discouraging, since no single boxes are
allowed at DCI level.

Sure, most things can survive out of order packets, especially when it
comes to TCP. And yet, since even at 2018, I still gladly discovering how
many still in use protocols, have their roots at 1970s :) that when we got
the idea, we should really consider the products I mentioned in my original
question. We're not disposed in favour of anyone of those I mentioned, just
sincerely looking forward for community opinion on those products.


בתאריך 10 בינו' 2018 5:45 PM,‏ "Gert Doering" <gert at greenie.muc.de> כתב:

Hi,

On Wed, Jan 10, 2018 at 12:38:35PM +0000, James Bensley wrote:
> However, if this is in the DC, if you customer is creating a LAG
> between their DC switch and a carrier DC switch and you're proposing N
> links between the same two devices in the same two racks, and you have
> the exact same copper/fibre runs that are the same length etc., then I
> would expect the miss-ordering to be minimal (not zero but likely an
> amount deemed as acceptable). In this scenario with proper monitoring
> to keep tabs on it, I would expect no special hardware required.

If it's all IP traffic, things are not very problematic.

Stay away from SNA, though...  "a single re-ordered packet = session lost"

(FCoE might also have a hearty dislike for reordering, though I'm not
as sure on that)

Fun :)

gert
--
now what should I write here...

Gert Doering - Munich, Germany
gert at greenie.muc.de

_______________________________________________
cisco-nsp mailing list  cisco-nsp at puck.nether.net
https://puck.nether.net/mailman/listinfo/cisco-nsp
archive at http://puck.nether.net/pipermail/cisco-nsp/


More information about the cisco-nsp mailing list