HN Explorer

Ask HN: Cheapest way to store 6TB online?

5 points by 3amOpsGuy ↗ HN
What is the cheapest way to store 6TB of key-value data online?

The data is accessed via random lookups and needs to maintain <0.5s service times per lookup and can expect around 200 concurrent accesses at any time.

It's currently hosted in a small Cassandra cluster and that gives lookup times of 15ms-20ms, well within acceptable limits. However there's no reason it couldn't be moved to another indexing system (it could even be moved to a suitably tuned filesystem with little effort).

9 comments

[ 3.2 ms ] story [ 9.1 ms ] thread
e-dard
I haven't checked, but I would think Amazon Glacier, assuming you only need to long-term archive the data.
mattbillenstein
Perhaps you missed the "< 500ms request time and 200 concurrent req/s" part of it??
bockris
Did you even read his post?

This is a key-value DB that he needs 1/2 sec response time to. Glacier is primarily a 'vault' type service where your access time is measured in hours.

e-dard
No! This crappy iOS app has a glitch and only showed the “cheapest way to store 6TB online” part!

That’s amused me somewhat chuckles

mattbillenstein
How big are your objects? 6TB in AWS S3 is about $720/month ...
NarwhalAttacks
If you are near a larger city, I would look into colocation hosting. Buy the hardware up front, and get some big disks. RAID or ZFS for redundancy.
3amOpsGuy
Thanks all for the leads. Hetzner are seriously low priced, impressive.

In the end we've gone for co-location, we tried to avoid this due to the hassles we've had in the past around physical access.

I guess this workload isn't a great fit for the cloud just yet. Maybe some day!