News for hackers. Stuff that matters.

mad_fab

Re:The Linux kernel MultiPath TCP project on Saturday April 20, 2013 @06:21AM (#5580966)
1. The server and the client must be MPTCP-"aware", so the anwser is yes (but look, someone is talking about a proxy up there, it's a solution to avoid this problem).

2. I'm in the team working in the Linux Kernel implementation and yes this is open source! http://multipath-tcp.org/pmwiki.php?n=Users.DoItYourself

Re:The Linux kernel MultiPath TCP project on Saturday April 20, 2013 @06:16AM (#5580951)
In short: hard to deploy because of middleboxes dropping all non-TCP/UDP traffic..
Re:The Linux kernel MultiPath TCP project on Saturday April 20, 2013 @06:13AM (#5580946)
The main advantage is: the congestion control! With MPTCP you could deal with congestion at the transport level. Meaning, if you have three flow MPTCP will select the best (less RTT, space in the win, etc..) link to send datas, where the bonding is just balancing with a XOR or a round robin. This is definitely a big advantage, not only in datacenters but if you have a 3G and a WiFi connection. More about the congestion control: http://tools.ietf.org/html/draft-ietf-mptcp-congestion
Re:The Linux kernel MultiPath TCP project on Saturday April 20, 2013 @06:08AM (#5580937)
Yes, a proxy solution is definitely a way to go, but to help the deployment only. In the end we shouldn't need those.
Re:The Linux kernel MultiPath TCP project on Saturday April 20, 2013 @06:02AM (#5580928)
If you want to try it; it's easy http://multipath-tcp.org/pmwiki.php?n=Users.HowToInstallMPTC...

Also, we have a measurements campaign running, if you want to contribute ;) http://multipath-tcp.org/pmwiki.php?n=Users.AboutMeasures