[zeromq-dev] Scalable data stores?

[Blair Bethwaite]

On 1 June 2011 10:12, Pieter Hintjens <ph at imatix.com> wrote:
> Well, the overall semantics are file based, i.e. objects will be much
> larger than memory size.

I'm not sure size has anything to do with file-like semantics. Files
makes me think: hierarchical organisation; human readable names; read,
write, _update_ capability; access etc. metadata.

Amazon S3 objects, for example, can be up to 5 terabytes. And on the
surface of it, looking at the rest of the use-case you outlined, S3
coupled with CloudFront appears to be the elephant in the room...
RackSpace have open sourced their object store and are merging it into
OpenStack, if you want a proven starting point to look at.

-- 
Blair Bethwaite
Researcher, Developer, SysAdmin, Nimrod and Grid support specialist
Monash eScience and Grid Engineering Lab (http://www.messagelab.monash.edu.au/)
+61 3-9903-2800