Live data from Hacker News

Dropbox’s Exodus from the Amazon Cloud

wired.com

151–160 of 252 posts

Re: Dropbox’s Exodus from the Amazon Cloud

#151
post #52

Earlier quoted context omitted.

Yes, a 1PB+ failure domain only made sense because Magic Pocket is very good at automatic cluster management and repair.

Are you using spindle or ssd or flash? (admittedly I dont know if you consider flash and ssd to be the same) What is your price per GB raw?

> Are you using spindle or ssd or flash? (admittedly I dont know if you consider flash and ssd to be the same)

We have flash caches (NVMe) in the machines, but the long-term storage devices are spindle--PMR and SMR.

> What is your price per GB raw?

I cannot disclose, exactly, but it is well below any other public price I've seen.

Re: Dropbox’s Exodus from the Amazon Cloud

#152
post #122

Earlier quoted context omitted.

Did you build your own centers? Running our hosting we had far more constraints on our power than anything else. Even though we only had 20U of equipment we ended up taking a 44u rack. Our disk arrays being the largest consumers. This made the case for moving to SSDs even stronger.

That was the problem I always had in my pre-cloud days. We were usually running racks half-full because of power restrictions in the DC. It was convenient because you could keep you cold spares and tools in your expensive space, but it always seemed like you should be putting more useful stuff in the racks.

You can substantially change the economics if you design your own power distribution systems.

Re: Dropbox’s Exodus from the Amazon Cloud

#153

The word "cloud" loses all meaning in this article. "The irony is that in fleeing the cloud, Dropbox is showing why the cloud is so powerful. It too is building infrastructure so that others don’t have to. It too is, well, a cloud company." Wait ... so using AWS is "cloud", having your own servers is "cloud" too. Everything is cloudy!

What they probably mean is that Dropbox has its own cloud. I'm assuming that they do have some kind of system similar to amazon ec2 to start and kill vms at will, and other similar basic cloud services.

Re: Dropbox’s Exodus from the Amazon Cloud

#155
post #2

Hi HN! A couple of us from the Magic Pocket software team are around to answer questions if anyone has some.

Not related to Magic Pocket, but when the article talks about Dropbox in house cloud, are they saying that you have your own instance of some minimal cloud-computing services? If you're permitted to disclose, I would love to know whether its based off OpenStack.

Re: Dropbox’s Exodus from the Amazon Cloud

#156
post #144
post #2

Hi HN! A couple of us from the Magic Pocket software team are around to answer questions if anyone has some.

> If a bunch of people shared some files via Dropbox, the company stored the files on Amazon’s Simple Storage Service, or S3, while housing all the metadata related to those files—who they belonged to, who was allowed to download them, and more—on its own machines inside its own data center space. I'm surprised at this. I would have expected the opposite: using AWS for the application and metadata but managing your o…

Building a massive, super-reliable storage system was not really feasible given Dropbox's resources back when it first started up.

Re: Dropbox’s Exodus from the Amazon Cloud

#157
post #37

> Measuring only one-and-half-feet by three-and-half-feet by six inches, each Diskotech box holds as much as a petabyte of data This number is very interesting. Basically Diskotech stores 1PB in 18" × 6" × 42" = 4,536 cubic inch volume, which is 10% bigger than standard 7U (17" × 12.2" × 19.8" = 4,107 cubic inch). 124 days ago Dropbox Storage Engineer jamwt posted here ( https://news.ycombinator.com/item?id=10541052…

Not to knock Dropbox's engineering, because it is sexy, but there are off the shelf enclosures right now that will fit 90 drives in a 4u case. Given that said enclosures have full rack rails and all, and are narrower, I don't doubt that a more densely designed server is feasible in the least with dropbox's design.

These are standard-width rackmount chassis btw. They're 1.5x depth but otherwise it's standard 4U.

The dimensions given are just an approximation.

Re: Dropbox’s Exodus from the Amazon Cloud

#159
From a business sense, this is a great move. Amazon's cloud storage offerings are pretty expensive, even with various deduping strategies in place, Dropbox needed both store and move in and out massive amounts of traffic. If DB had reached the point where they could staff the extra over head of doing it themselves, and figure out how to spread the hardware cost out well, it will give them more pricing flexibility in the near future.

Re: Dropbox’s Exodus from the Amazon Cloud

#160

Earlier quoted context omitted.

We were pushing over a terabit of data transfer at peak, so 4-5PB per day.

i.e. 1Tbps? Jeez! That is crazy.

If you are moving bits from $External_DC to AWS, your best bet is to colo inside Equinix (or equivalent) and use their cross-connect to AWS service. If you have 100 fiber interconnects between you and AWS, you can move a lot of data (it becomes an interesting programming problem to figure out how to saturate that much fiber consistently).

In terms of your customers getting data to you, again, fiber interconnects inside the DC are your best bet. Colo'ing is the fastest way to move bits because it relies on arteries, not capillaries, for moving bits from place to place (no last mile problem).

Post reply on HN