Join Newsletter
Forgot
password?
Register
Trusted Business Advisors, Expert Technology Analysts

Taneja Blog

Taneja Blog / Data Center Systems / Software Defined/Virtualized Infrastructure

Pernix Data FVP Now Cache Mashing RAM and Flash

Performance acceleration solutions tend to either replace key infrastructure or augment what you have. PernixData FVP for VMware clusters is firmly in the second camp, today with a new release making even better use of total cluster resources to provide IO performance acceleration to "any VM, on any host, with any shared storage".

PernixData has been popular for pooling server-side flash to make a fault-tolerant storage "caching" tier out of what might otherwise be isolated server-by-server flash investments.  Pooling flash across servers is a great approach to not only sharing the resources, but also drives higher availability as writes can be immediately replicated and acknowledged in the cache tier (across servers), then safely destaged to slower storage.  FVP also supports synchronous metro clustering for even wider fault tolerance.

Today, PernixData is expanding the resource pooling concept to let VM admins include server RAM in the cache tier with flash. We think this is a great move as we expect RAM prices to keep dropping, and over time flash to creep closer to the CPU. Practically, this means that whatever performance mix and/or price point one can make between RAM and flash will work, or rather, whatever resources one might already have are completely leveragable.

PernixData is also claiming that now supported backend storage can be any external file, block, or server DAS disk. So FVP is an acceleration solution that can be dropped in with no change to current storage architectures, which makes adoption pretty easy. Over time, legacy storage might have a longer shelf life when fronted by FVP for performance, and storage upgrades can focus more on cost-effective capacity.

FVP is a VMware kernel module and as a cache it's transparent to storage clients. This means it doesn't change or add new storage services, or help storage itself become more vm-aligned (like Tintri, Maxta, Virtual SAN, et.al.). But this does make it dead easy to implement on what might be deployed today.

As a fast cache it's an easy value proposition, but we also look forward to exploring some of the deeper implications of using RAM for cache v.s. in-memory processing trends, and also the impact server-side cache replication capabilities might have on practical data protection and DR strategies.

Bookmark and Share
  • Premiered: 04/23/14
  • Author: Mike Matchett
Topic(s): Pernix Flash Server Virtualization Storage Acceleration Data protection Storage

Comments

There are no comments to display. Scroll down to leave your own!

 

Leave a Comment

You must be logged in to comment. Click here to log in or register if you don't have an account.