Protected? Cosy? Pffft, Reduxio prefer 'daring stupidity' Analysis Reduxio's array is a hybrid one with clever dedupe, and is restricted to an iSCSI interface, so let's move on. Actually let's not. Because under the covers something remarkable is going on. Co-founder and CTO Nir Peleg explained this to us press hacks at Reduxio's Israeli HQ in Petach Tikvah yesterday. At heart, he …
You've told us about the pro's, now how about the con's?
I love this type of technology, but as with all start-ups, its too much of a gamble because
a) they can't deliver an SLA to is acceptable to business
b) they target top of the market and set an unrealistic price for the medium market
I don't think they're targeting the top end of the market with an iSCSI-only hybrid array. The hardware sounds an awful lot like early Nimble, in fact; it's the software that's special. As to the SLA, that's a reasonable objection; on the other hand, a certain large storage vendor has seen a number of public failures of their all-flash solution, so buying big-brand kit is not necessarily a guarantee of reliability.
My prediction: Reduxio gets bought by NetApp, and their software gets rolled into OnTAP . . . five years or so after the acquisition.
"So suppose we had a big bucket containing all the world's data. Each unique chunk of data is stored in the bucket once and has a unique name. We could then add tags outside the bucket, referring to data chunks already in the bucket by their names."
So the data in the bucket remains the same but the tags keep growing in number... The more tags you need the bigger they need to be if they're to be unique so they also keep growing in size. At what point does the tag storage, retrieval and processing become the greater part of the problem?
Tags already are as big as they need to be in order to actually (not only theoretically) cover all the world's data with unique tags, so they don't really need to get any bigger.
As to the number of tags: Handling many tags is challenging. Granted. It is, however, not as hard as handling vast amounts of plain data, since unlike data, tags can be hierarchically organized. Moreover, tag management is easily scalable by distributing compute load. Given well thought out design, there is no practical limit to the scalability of tag management.
The Register 
Biting the hand that feeds IT
Copyright. All rights reserved © 1998–2024
