Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

localhost and server-to-server tools + benchmarks #2

Open
salesiss opened this issue Jun 29, 2017 · 0 comments
Open

localhost and server-to-server tools + benchmarks #2

salesiss opened this issue Jun 29, 2017 · 0 comments

Comments

@salesiss
Copy link

salesiss commented Jun 29, 2017

There is a chance to try UDT on real world events:

Source code is simple (good+), and udt is a challenging protocol that is/was leading, but still untested or unkown by the masses:

let's make some tools out of this git and clarify for life:

  1. is udt still a challeging and good protocol, competitive to tcp-ip, or mux ?
    or it's today simply outdated;
  2. well we can sort it out:

Make two tools:

sendclient.c and receiveclient.c -> refactored and updated to match IPERF
results: achieve on localhost speeds up to 10 and 99GBPS as iperf does on a laptop or commodity hardware;

sendfile.c and receivefile.c -> make a connection between two vps, from japan to us and achieve better results than a tunnel, less cpu% consumption and much faster than kcp-tun (go) and/or tsunami

As for myself, I can publish benchmarks for the current UNPATCHED and unmodified versions of UDT quite fast, can we do that ?

So, is making UDT a world-class protocol still feasible ? Does it pay the effort ?
Can we publish results as they are from git ? Or: is there another project from the same (or near-like) authors that surpasses this git project ?

Thanks all for answering !

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant