Most active commenters
  • yolovoe(4)
  • tptacek(3)

←back to thread

SSDs have become fast, except in the cloud

(databasearchitects.blogspot.com)
589 points greghn | 20 comments | | HN request time: 2.663s | source | bottom
Show context
pclmulqdq ◴[] No.39443994[source]
This was a huge technical problem I worked on at Google, and is sort of fundamental to a cloud. I believe this is actually a big deal that drives peoples' technology directions.

SSDs in the cloud are attached over a network, and fundamentally have to be. The problem is that this network is so large and slow that it can't give you anywhere near the performance of a local SSD. This wasn't a problem for hard drives, which was the backing technology when a lot of these network attached storage systems were invented, because they are fundamentally slow compared to networks, but it is a problem for SSD.

replies(30): >>39444009 #>>39444024 #>>39444028 #>>39444046 #>>39444062 #>>39444085 #>>39444096 #>>39444099 #>>39444120 #>>39444138 #>>39444328 #>>39444374 #>>39444396 #>>39444429 #>>39444655 #>>39444952 #>>39445035 #>>39445917 #>>39446161 #>>39446248 #>>39447169 #>>39447467 #>>39449080 #>>39449287 #>>39449377 #>>39449994 #>>39450169 #>>39450172 #>>39451330 #>>39466088 #
jsnell ◴[] No.39444096[source]
According to the submitted article, the numbers are from AWS instance types where the SSD is "physically attached" to the host, not about SSD-backed NAS solutions.

Also, the article isn't just about SSDs being no faster than a network. It's about SSDs being two orders of magnitude slower than datacenter networks.

replies(3): >>39444161 #>>39444353 #>>39448728 #
pclmulqdq ◴[] No.39444161[source]
It's because the "local" SSDs are not actually physically attached and there's a network protocol in the way.
replies(14): >>39444222 #>>39444248 #>>39444253 #>>39444261 #>>39444341 #>>39444352 #>>39444373 #>>39445175 #>>39446024 #>>39446163 #>>39446271 #>>39446742 #>>39446840 #>>39446893 #
1. yolovoe ◴[] No.39446742[source]
You’re wrong. Instance local means SSD is physically attached to the droplet and is inside the server chassis, connected via PCIe.

Sourece: I work on nitro cards.

replies(1): >>39447200 #
2. tptacek ◴[] No.39447200[source]
"Attached to the droplet"?
replies(4): >>39447513 #>>39447821 #>>39453545 #>>39462446 #
3. hipadev23 ◴[] No.39447513[source]
digitalocean squad
replies(1): >>39449627 #
4. sargun ◴[] No.39447821[source]
Droplets are what EC2 calls their hosts. Confusing? I know.
replies(2): >>39447828 #>>39462378 #
5. tptacek ◴[] No.39447828{3}[source]
Yes! That is confusing! Tell them to stop it!
replies(1): >>39448983 #
6. kiwijamo ◴[] No.39448983{4}[source]
FYI it's not a AWS term, it's a DigitalOcean term.
replies(3): >>39449067 #>>39449367 #>>39462407 #
7. tptacek ◴[] No.39449067{5}[source]
I could not be more confused. Does EC2 quietly call their hosting machines "droplets"? I knew "droplets" to be a DigitalOcean team, but DigitalOcean doesn't have Nitro cards.
replies(2): >>39449214 #>>39449914 #
8. apitman ◴[] No.39449214{6}[source]
Now I'm wondering if that's where DO got the name in the first place
replies(1): >>39449620 #
9. sargun ◴[] No.39449367{5}[source]
I believe AWS was calling them droplets prior to digital ocean.
10. chatmasta ◴[] No.39449620{7}[source]
Surely "droplet" is a derivative of "ocean?"
replies(1): >>39449858 #
11. jbnorth ◴[] No.39449627{3}[source]
No, that’s AWS.
12. arrakeenrevived ◴[] No.39449858{8}[source]
Clouds (like, the big fluffy things in the sky) are made up of many droplets of liquid. Using "droplet" to refer to the things that make up cloud computing is a pretty natural nickname for any cloud provider, not just DO. I do imagine that DO uses "droplet" as a public product branding because it works well with their "Ocean" brand, though.

...now I'm actually interested in knowing if "droplet" is derived from "ocean", or if "Digital Ocean" was derived from having many droplets (which was derived from cloud). Maybe neither.

replies(1): >>39455023 #
13. ◴[] No.39449914{6}[source]
14. Rudisimo ◴[] No.39453545[source]
That is more than likely a team-specific term being used outside of its context. FYI, the only place where you will find the term <droplet> used, is in the public-facing AWS EC2 API documentation under InstanceTopology:networkNodeSet[^1]. Even that reference seems like a slip of the tongue, but the GP did mention working on the Nitro team, which makes sense when you look at the EC2 instance topology[^2].

[^1]: https://docs.aws.amazon.com/AWSEC2/latest/APIReference/API_I... [^2]: https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/how-ec2-...

15. driftnet ◴[] No.39455023{9}[source]
Clouds are water vapor, not droplets.
replies(2): >>39455368 #>>39518545 #
16. abadpoli ◴[] No.39455368{10}[source]
“Cloud: Visible mass of liquid droplets or frozen crystals suspended in the atmosphere“

https://en.wikipedia.org/wiki/Cloud

17. yolovoe ◴[] No.39462378{3}[source]
Yes, we internally call servers droplets. We have multiple hosts/mobos in the same server these days so calling them hosts is confusing, and droplet is a really old term here from what i can tell.
18. yolovoe ◴[] No.39462407{5}[source]
It’s an internal ec2 term too. We don’t use it externally and I shouldn’t have used it to avoid all this confusion.

Internally, we say droplet instead of host as there are multiple hosts/mobos per droplet these days. It’s no longer true that when you get a metal droplet, you get the entire droplet.

19. yolovoe ◴[] No.39462446[source]
I shouldn’t have said droplet. Like sibling says, that’s our internal name for a “server” and not what we use externally.
20. singleshot_ ◴[] No.39518545{10}[source]
Clouds are condensed water droplets in the air. The air below the cloud has just about the same amount of water in it, but at the altitude of the bottom of the cloud, the atmosphere is cool enough for that water vapor to condense, forming the cloud.

Search terms include “lapse rate” if you would like to learn more.