StorageMojo has observed, many times, that great marketing of a mediocre product beats mediocre marketing of a great product all the time. Thus it is always of interest when someone comes up with an innovative marketing wrinkle.
That’s what Infinidat has done with their Faster than all flash challenge. Their claim is that their system will outperform any all flash array (generally available prior to 1-1-2017) or they donate $10,000 to the charity of your choice.
A safe bet?
Infinidat says their system beats AFAs because:
- Massive parallelism.
- Machine learning to optimize caching.
- DRAM is used to cache hot data.
- Missed cache hits are usually serviced by NAND.
In theory, they might have some longer-tailed I/Os than an AFA. But if most of the workload is being served out of DRAM, then sure, they should get MUCH higher performance. I doubt they’ll be donating to many charities.
The StorageMojo take
Good marketing does a credible job of presenting and resolving customer pain points. Great marketing links the product to something greater, something meaningful, and taps into the powerful human desire to make a difference. This does both.
StorageMojo supports the Verde Valley Sanctuary, and I’d love to see them get $10k from Infinidat. But I don’t have an enterprise workload to try them out on.
If you have, or will, take Infinidat up on their offer, please drop StorageMojo a line on how it goes. What’s the worst that can happen?
Courteous comments welcome, of course.
Update: From Infinidat’s Drew Schlussel:
Just to clarify, INFINIDAT will make a donation regardless of who wins. The fine print is that the â€œwinnerâ€ determines where the donation goes. It is the best example of â€œitâ€™s all goodâ€.
End of update.