Comment by eddythompson80
1 day ago
Of course they are not complex. They do have a network effect though. If you go to your local ISP and say “hey, my 500mbps plan is only doing 100mbps on Speedtest.net”, they’ll “fix it” (usually by working with Ookla to put an edge endpoint on their network)
If you tell the “hey frankyspeeddetect.com isn’t doing my 500mbps” they’ll tell you to it’s an issue with that random website. ISPs and services reach out to Ookla to onboard with them because they have a network effect/mindshare of whatever you wanna call it
When I used a major cable ISP, often my connection seemed slow, so I'd go to speedtest.com. The speedtest would be fine... and then I would magically have faster network performance again.
It happened enough times that I'm suspicious the ISP had some way to detect if you run a speedtest, and then prioritized traffic to that customer.
This was one of the reasons given, at the time, for why Netflix created fast.com. It's served by the same infra that does their streaming, and is thus difficult for isps to game. That is, it'd be hard for them to do some hack to make fast.com numbers without also benefiting Netflix streaming performance in the bargain.
Actually I thought Netflix had already acquired Ookla / speedtest.com, so I was surprised to see this headline. But it looks like this was just the Mandela effect.
That said, why didn't Netflix acquire the market leader in this space? Creating their own seems way less useful, since network effects are the whole point.
5 replies →
> It happened enough times that I'm suspicious the ISP had some way to detect if you run a speedtest, and then prioritized traffic to that customer.
ISPs definitely know when you run a speedtest.net test. 90% of the time, the data for that comes from boxes/services they host themselves. It’s not exactly hidden either. It’s a typical program any ISP can sign up for and you can easily see the destination the test is running against. I won’t be surprised if some have some logic to prioritize particular subscribers plan once they have detected a test from them. They probably view it as a “customer support calls reduction” feature.
>When I used a major cable ISP, often my connection seemed slow, so I'd go to speedtest.com. The speedtest would be fine... and then I would magically have faster network performance again.
Yeah, I suspect you could script it to do it daily. They definitely seem to deprioritize traffic from people that don't complain.
http://speed.cloudflare.com is a bit harder to argue with though.
All these numbers are fake. They are all special cased in most ISPs with the cooperation of cloudflare, Netflix, OOkla, Akamai, Google, etc. The centralization of the internet around AWS, Azure, Google, Netflix, Cloudflare, etc has been a godsend to ISPs and the internet infrastructure in general. Maintaining good network conditions to 4 or 5 dozen networks and working with them closely is so so much easier than maintaining full peer-to-peer network conditions. Go ahead and try to test internet speed to your home network over a wireguard VPN and compare it to the performance of the same VPN when connecting to any of the major services. Try to setup a tunnel between your house and your friends house in the same city and test the speed and compare it to fast.com or cloudflare.com or speedtest.net
I had not heard of http://speed.cloudflare.com either. I just tried it and I did not get accurate numbers. wifiman.com, from Ubiquiti/Unifi team does provide more accurate numbers. fast.com numbers are pretty accurate as well.
I'm a huge fan of https://speed.cloudflare.com/ and you'll have to come with better evidence. Also fast.com doesn't even give upload speed and latency.
2 replies →
They serve so many sites that they are probably the best test there's now.
> I did not get accurate numbers.
That's why speedtest.net is a great purchase for Accenture. Of course Cloudflare's speed test is accurate: it's a test of how fast your connection is to their network. No more, no less. That their network doesn't have the same PoPs means it'll have different numbers than Ookla's test, your ISPs advertised numbers, Netflix's test, and any other speed test. But for people that don't see the Internet as a pile of different interconnected networks, the conclusion that a particular test is inaccurate is a win for Accenture.
The difference is that until now I had never heard of speed.cloudflare.com before. (I know about fast.com though.)