Mr. Language Person appreciates you holding the line
Thank you for saying "on-premises" despite EMC's slide saying "on-premise".
Dell EMC is working on fixing the increasing split between primary storage data on flash and capacity data storage on object arrays by logically combining them underneath a 2 TIERS software abstraction layer. The starting point is that SAN disk or hybrid flash/disk arrays are diverging into separate arrays under the pressures …
Not sure where is the novelty?
Many vendors today support flash with backend object tier
exposing it as SAN is like riding a horse in a highway, why would you do that when the world is moving to consume data using shared access patterns like file, object, records and streams, with scale-out built in to the data/app layer
Seems like Enterprise storage vendors still haven't internalized the cloud era
Yaron
Nate, check out Amazon aurora, MySQL clone running over tiered object, Its 6x faster and scale linearly
Also look at Oracle Exadata and MS Sql over SMB 3.0, Google Spanner, way faster and more scalable than Block based DBs
Block based DBs are outdated, do full scans, locks,.. It doesn't scale and doesn't benefit from flash random access attributes
Yaron
When you talk about cloud you talk as it is a responds for a technology problem Cloud is a operational model, and will try to resolve an operational cost issue. Now, if we come back to this blog conversation, that is a real technology issue that we can resolve at application layer, software layer or hardware layer, witch is better? I am not sure, DSSD resolve the hot part of that with hardware, ViPR resolve that with software, but, at application level I don IT know.
This post has been deleted by its author
The previous comments dont get the scope of this. It's more than a single namespace, it's doing block/file/object at the same time. Regardless of the location of the object or file storage. The author considered StorNext as in this realm, which is incorrect. There are competitors though: IBM GPFS and DDN.
In practice also, the object and file layers will pickup OneFS ACL translation too so the posix block side will be dynamically mapped to real accessible ACLs on the capacity side.