Preliminary results from testing..

Randall Stewart rrs at netflix.com
Wed Dec 9 16:13:49 UTC 2015


All:

Ok so I have had a first cut of an A/B test with a machine using fixed calls to tcp_do_segment/output etc and
one using the new pluggable pointer based stack. As expected I can’t really tell any real difference between
the two machines.

They are both Intel Ivy Bridge E5-2650L Intel CPU’s. Running at 1.7Ghz, 64G of memory and 10 physical cores.

Here are png’s of the per second cpu use and the overall serving bandwidth (if anyone wants the raw numbers
let me know).

The two machines are basically the same, serving the same content.

I have a few other pairs I will be trying this on.. though I don’t expect any real difference.

Robert, how are you coming on investigating the overhead of function pointers on non-intel devices ?

I would like to commit the tcp-stack changes soon if possible :-)

R




--------
Randall Stewart
rrs at netflix.com
803-317-4952







More information about the freebsd-transport mailing list