WoodITWork.com

Tech Field Day 11 is happening in Boston, from 22-24 June and I’m super happy to be invited as a delegate.

I’ve been previewing the companies attending, have a look at my introductory post: I’m heading to Tech Field Day 11 and DockerCon!

Plexistor

Plexistor has been developing its product for 3 years which it started selling in January 2016. It is headquartered in Sunnyvale, California with an R&D center in Herzeliya, Israel.

The product has the tagline of “Software Defined Memory” which is a term that doesn’t have an obvious meaning but is a near-memory speed storage platform for crunching data at scale while keeping the infrastructure simple.

It is a software layer above your bare metal infrastructure which presents storage to scale out applications such as Cassandra, MongoDB, Varnish, Redis, Hbase, RockDB and Spark. Memory is fast but expensive so Plexistor allows you to tier “slower” than memory storage devices such as SSDs where cold data can be moved when it is no longer active in faster memory. This tiering is also being built for much faster upcoming solutions such as NVDIMMs and 3D XPoint. You can also use AWS Flash based EC2 instances as a tier.

Plexistor also allows you to create a tiered persistent storage layer for your in-memory applications that don’t have easy resilience at the application level.

It is interesting that there are a number of companies that make slower storage faster such as PernixData or Atlantis, we’ve come full circle when we’re needing to make faster storage slower!

Its very early days for Plexistor so I wonder whether they are looking to get acquired early to broaden the offering of someone else who needs more clever tiering or can stand alone. I do hope this isn’t just a technology fixer to make in-memory databases cheaper because memory is expensive or providing better persistent storage for applications when applications are getting better at managing their availability themselves and potentially manage their own tiering as well. Big Data applications cost big money so enterprises do have money to spend for performance for the right solution. Is Big Data ripe for commoditisation though (argument for another day!)?

Looking forward to hearing more, storage is a hot industry at the moment.

Gestalt IT is paying for travel, accommodation and things to eat to attend Tech Field Day but isn’t paying a penny for me to write anything good or bad about anyone.