Acceleration layer architecture and I/O request

When installing PernixData FVP or VMware vFlash Read Cache you are introducing an acceleration layer that (drumroll)…..accelerates data. Although this might seem very obvious to you, it will have an impact on how you test the new environment. Let’s start of by reviewing the traditional architecture and the new … [Read more...]

A short series on evaluating an acceleration platform

Testing an acceleration platform differs from testing an traditional environment in which the central storage system is responsible for providing both the data services as well as the I/O performance of the application. In this short series of articles I will focus on some of the pitfalls one need to avoid when testing … [Read more...]

Design considerations for the host local FVP architecture

With FVP 1.0 release this week, the questions on host local architecture starting to explode. More and more people are starting to test FVP and they want to create the most optimal environment to test on. And I don’t blame them . Questions such as, should I use one disk or multiple disks, Which RAID level, SSD … [Read more...]

Only two days left to sign up for your VMworld speaker shirt!

During our advisory call with CloudPhysics, a great idea was born. Why not provide all the speakers at VMworld a cool speaker shirt? Unfortunately in 2011 VMworld made the decision to stop providing speaker shirts to the people on stage, so most people started wearing older speaker shirt or even RUN DRS shirts ☺. For … [Read more...]

FVP Remote flash access

Last year, when I was introduced to FVP one thing stood out and that was the seamless support of vSphere clustering features such as HA and DRS. In order to support clustering you need to provide a clustered solution yourself. Creating a clustered solution is not an end to itself, but it’s the foundation for the remote … [Read more...]

Have you seen the new video introduction to PernixData?

I know PernixData FVP is cool, you know it’s cool, now how can you tell you all your friends and colleagues about it? Going around and telling them one by one doesn’t scale, just show them this video! I think Jeff sums it up nicely: The post Have you seen the new video introduction to PernixData? appeared … [Read more...]

FVP Writeback policy deepdive whiteboard session

The post “Writeback and write through policies in FVP” received a lot of great questions. During this weeks’ visit to PernixData HQ I asked Satyam to address the questions in a deepdive whiteboard session. The questions we cover are: Erik Lenten: What will happen when your delayed writes cannot be … [Read more...]

Write-Back and Write-Through policies in FVP

Fault tolerant write acceleration is one of the key features of FVP. Once you select a virtual machine to be accelerated by FVP you can choose to apply a write through policy or write back policy with a x number of replicas of the virtual machine. Before expanding upon replicas, let’s review the basics of write … [Read more...]

FVP Release Candidate expected Monday, July 15th

A new release of the FVP software is expected on Monday, July 15th. Due to the reduction in checksum and logging activity the release candidate code will have significant performance improvements compared to the current beta release. If you are not participating in the Beta program yet, sign up here. Heads up for all … [Read more...]

Basic elements of FVP – Part 2 – Using own platform versus in-place file system

One topic I discussed with Satyam and Murali Vilayannur was about the file system we used for storing the data on the flash devices. Interesting fact to know is that it was Satyam who created VMFS3, Murali was the lead engineer developing VMFS5. From that perspective it made sense that we used VMFS. It was a big … [Read more...]