what gives on net speed test

November 30, 2016 9:49 AM

When I use the xfinity site (my ISP is comcast) it shows a download speed of about 120mbs. When I use another random test, it shows about 70mbs. I am curious as to why there would be such a large difference.
posted by jtexman1 to Computers & Internet (6 answers total)

Giving xfinity the benefit of the doubt, it's because their tool is hosted on their servers, so they control all the connections in between your modem and the server where the tool is hosted. They can ensure the connection is working at its best possible speed.

Cynically it's because they have their finger on the scale.
posted by nathan_teske at 9:58 AM on November 30, 2016 [5 favorites]

It's because it depends where it's measuring the speed to. If it's a server very close to you, especially if it's on your ISP's own network you get what is basically your line rate. If the server is farther away then there's congestion at various peering points and you don't get the same bandwidth.
posted by GuyZero at 10:03 AM on November 30, 2016

Carriers will game the hell out of speed test sites. Not just xfinity to xfinity's site, but also expect preferential treatment of traffic to eg. speedtest.net and the other well-known ones.
posted by revertTS at 10:07 AM on November 30, 2016

Yep: It's likely because Xfinity is way over-selling their upstream pipe: You can get to Xfinitiy's data center just fine, but there are business and regulatory reasons why they don't have much incentive to spend the few tens of thousands of dollars it'd take to upgrade their interconnect.

Level 3, operators of big long-haul connections, have written about this a bit, “Chicken” | A Game Played as a Child and by some ISPs with the Internet and Observations of an Internet Middleman.
posted by straw at 10:07 AM on November 30, 2016

Oh, this is really the Level 3 blog post I was looking for, it's about Verizon, but many of the same things apply to Comcast: Verizon’s Accidental Mea Culpa:

Verizon has confirmed that everything between that router in their network and their subscribers is uncongested – in fact has plenty of capacity sitting there waiting to be used. Above, I confirmed exactly the same thing for the Level 3 network. So in fact, we could fix this congestion in about five minutes simply by connecting up more 10Gbps ports on those routers. Simple. Something we’ve been asking Verizon to do for many, many months, and something other providers regularly do in similar circumstances. But Verizon has refused. So Verizon, not Level 3 or Netflix, causes the congestion. Why is that? Maybe they can’t afford a new port card because they’ve run out – even though these cards are very cheap, just a few thousand dollars for each 10 Gbps card which could support 5,000 streams or more. If that’s the case, we’ll buy one for them. Maybe they can’t afford the small piece of cable between our two ports. If that’s the case, we’ll provide it. Heck, we’ll even install it.

posted by straw at 10:14 AM on November 30, 2016 [2 favorites]

Could be random congestion; do you consistently see the same different speeds on the two sites?

Measuring home bandwidth over 100 Mbps is actually kind of tricky. A lot of the older speed tests had limitations in the browser client or the test server that itself would limit speed to < 100 Mbps. If you want to do careful testing I think DSL Reports has the best speed tester out there.
posted by Nelson at 1:23 PM on November 30, 2016