Nix × IPFS – Milestone 1

Re:Nix × IPFS – Milestone 1 by takeda on Tuesday September 29, 2020 @01:27PM (#24630566)

Perhaps there are routers that don't handle well large amounts of data, but from my experience what typically is happening are two things:

1. the fairness in TCP is done per TCP connection, bittorrent opens many connections so they take over the whole bandwidth. You can limit number of connections or throttle the bandwidth used by BT (of course you will get slower speeds), maybe there are some other ways.

2. when you maximize your throughput ACKs might get dropped which slows everything down (I suspect that might be the issue you're talking about) again you could throttle or enable traffic shaping and give highest priority to ACKs. This worked well for me.

[ Parent | on HN ]

Re:Nix × IPFS – Milestone 1 by linsomniac on Tuesday September 29, 2020 @07:30PM (#24634283)

3. Bufferbloat. It's still a thing. dslreports has a bufferbloat score, one of my coworkers has been really impacted by it. http://www.dslreports.com/speedtest

[ Parent | on HN ]

Re:Nix × IPFS – Milestone 1 by takeda on Tuesday September 29, 2020 @08:03PM (#24634497)

I heard about bufferbloat, but I didn't think it was related to bittorrent maximizing throughput

[ Parent | on HN ]

Re:Nix × IPFS – Milestone 1 by linsomniac on Tuesday September 29, 2020 @11:06PM (#24635313)

It depends: packet loss due to bitorrent is a problem, but low loss and high latency makes it dramatically worse, and that is the bufferbloat cast. If you have 1-30 second pings (or I've seen even worse), when doing torrents or other heavy outbound traffic, it falls apart.

[ Parent | on HN ]

Re:Nix × IPFS – Milestone 1 by Dagger2 on Thursday October 01, 2020 @09:26AM (#24650545)

Even 1 second is already pretty severe bufferbloat, let alone 30 seconds. Your latency should increase by under 25-125ms even with upstream and downstream both running flat out.

[ Parent | on HN ]