News for hackers. Stuff that matters.

A comment on The Linux kernel MultiPath TCP project. Parent comment

Re:The Linux kernel MultiPath TCP project by jallmann on Friday April 19, 2013 @02:57PM (#5578142)
Wasn't sure if there was something particular about SCTP that could induce algorithmic latency such as a buffering requirement, setup/negotiation, congestion control, other overhead, etc.
[ Parent | on HN ]
Re:The Linux kernel MultiPath TCP project by lttlrck on Saturday April 20, 2013 @09:47AM (#5581378)
It uses CRC32 as a checksum and that cannot be offloaded to most commercial NICs. This will also have an impact on routers that manipulate the transport layer ports due to checksum recalculation cost (which is trivial for the checksum used in UDP and TCP)
[ Parent | on HN ]
Re:The Linux kernel MultiPath TCP project by Nrsolis on Saturday April 20, 2013 @08:52PM (#5583415)
Routers almost NEVER manipulate the transport unless they are doing something very un-Layer3 like NAT or some other encapsulation.
[ Parent | on HN ]