←back to thread

309 points dban | 2 comments | | HN request time: 0.439s | source
Show context
jonatron ◴[] No.42743915[source]
Why would you call colocation "building your own data center"? You could call it "colocation" or "renting space in a data center". What are you building? You're racking. Can you say what you mean?
replies(10): >>42743999 #>>42744262 #>>42744459 #>>42744487 #>>42744684 #>>42745045 #>>42745071 #>>42745397 #>>42745493 #>>42746491 #
chatmasta ◴[] No.42744684[source]
It seems a bit disingenuous but it’s common practice. Even the hyperscalers, who do have their own datacenters, include their colocation servers in the term “datacenter.” Good luck finding the actual, physical location of a server in GCP europe-west2-a (“London”). Maybe it’s in a real Google datacenter in London! Or it could be in an Equinix datacenter in Slough, one room away from AWS eu-west-1.

Cloudflare has also historically used “datacenter” to refer to their rack deployments.

All that said, for the purpose of the blog post, “building your own datacenter” is misleading.

replies(3): >>42744705 #>>42745298 #>>42745377 #
matt-p ◴[] No.42744705[source]
The hyperscalers are absolutely not colo-ing their general purpose compute at Equinix! A cage for routers and direct connect, maybe some limited Edge CDN/compute at most.

Even where they do lease wholesale space, you'd be hard pushed to find examples of more than one in a single building. If you count them as Microsoft, Google, AWS then I'm not sure I can think of a single example off the top of my head. Only really possible if you start including players like IBM or Oracle in that list.

replies(4): >>42744718 #>>42744738 #>>42745016 #>>42745300 #
chatmasta ◴[] No.42744718[source]
Maybe leasing wholesale space shouldn’t be considered colocation, but GCP absolutely does this and the Slough datacenter was a real example.

I can’t dig up the source atm but IIRC some Equinix website was bragging about it (and it wasn’t just about direct connect to GCP).

replies(1): >>42744749 #
matt-p ◴[] No.42744749[source]
Google doesn't put GCP compute inside Equinx Slough. I could perhaps believe if they have a cage of routers and perhaps even CDN boxes/Edge, but no general cloud compute.

Google and AWS will put routers inside Equinx Slough sure, but that's literally written on the tin, and the only way a carrier hotel could work.

replies(1): >>42744779 #
chatmasta ◴[] No.42744779[source]
Then why do they obfuscate the location of their servers? If they were all in Google datacenters, why not let me see where my VM is?
replies(1): >>42744859 #
achierius ◴[] No.42744859[source]
Security reasons, I presume? Otherwise it would be trivial for an adversary to map out their resources by sampling VM rentals over a moderate time-period.
replies(1): >>42744894 #
lostlogin ◴[] No.42744894[source]
I’m very naive on the subject here - what advantage would this give someone?
replies(1): >>42745209 #
chupasaurus ◴[] No.42745209[source]
The knowledge of blast radii.
replies(1): >>42745413 #
1. jazzyjackson ◴[] No.42745413[source]
Gives whole new meaning to “reverse engineering”
replies(1): >>42745541 #
2. chupasaurus ◴[] No.42745541[source]
Well, the alternative name for it is "backwards engineering" for a reason.