[113379] in North American Network Operators' Group
[SPAM] Re: Forward Erasure Correction (FEC) and network performance
daemon@ATHENA.MIT.EDU (Jean-Michel Planche)
Fri Apr 10 13:00:17 2009
From: Jean-Michel Planche <jmp@witbe.net>
To: Marshall Eubanks <tme@multicasttech.com>
In-Reply-To: <B84DE4F1-B8AA-4D1A-A10E-78B3CB810FC2@multicasttech.com>
Date: Sat, 11 Apr 2009 01:57:38 +0900
Cc: "nanog@nanog.org list" <nanog@nanog.org>
Errors-To: nanog-bounces+nanog.discuss=bloom-picayune.mit.edu@nanog.org
Le 11 avr. 09 =E0 00:03, Marshall Eubanks a =E9crit :
> What level of packet loss would trigger response from network =20
> operators ? How bad does a sustained packet loss need
> to be before it is viewed as a problem to be fixed ? Conversely, =20
> what is a typical packet loss fraction during periods
> of good network performance ?
It really depend on a lot of parameters and it's why I think this =20
approach is not relevent at all since IP centric solutions.
In past, some peoples said that if you loose less than 0,1% of packet, =20=
all is good.
Now, you can loose 1% of packet and acheive something that work for =20
the end user with Flash 10 technology and ... despite all you can =20
loose 0,01% packet and see a lot of defaults because HD / 8 Mbps / =20
H264 encoding. (we've presented that with Cisco last year at IBC =20
Amsterdam)
Fortunatly if you thing about IP centric solution, you can install =20
enough intelligence in the Set Top Box, for exemple or on a PC client =20=
side in order to :
- re-ask paquets
- and / or repair missing one (fec)
Booth of this solution are in operation today and permit a really not =20=
too bad IPTV with DSL long lines in many operators that I know.
> (To be clear, I am aware that many ISPs offer some sort of MPLS =20
> service with a packet loss SLA for video carriage. I am really =20
> asking about
> Internet transport here, although I would be pleased to learn of =20
> MPLS statistics if anyone wants to provide them.)
You can ask what you want to yours ISP but the magic is : all can =20
happen and loss packet and jitter are not relevent at all !
Then solution is not to ask 100% SLA to ISP (except if you find some =20
crazy man to offer you this with good penalty) but to take care about =20=
your service, with a real end to end monitoring. There is no more =20
correlation between backbone artefacts and human artefacts. Best way =20
is a user centric monitoring, top down approach that can understand if =20=
all is good at service / application / usage level, in order to =20
control principal real artefacts (blockiness, jerkiness, bluriness and =20=
availability of image and sound). That's exist, you can believe me ;-)
=
--------------------------------------------------------------------------=
--------------------------------------------------------
Jean-Michel Planche www.jmp.net =
www.twitter.com/jmplanche 2.0
jmp@witbe.net www.witbe.net =
1.0
www.internetforeveryone.fr =
0.0
