I had a query recently from a partner who was deploying VMware Horizon View 6.1 on top of an all-flash VSAN 6.0. They had done all the due diligence with configuring the AF-VSAN appropriately, marking certain flash devices as capacity devices, and so on. The configuration looked something like this:
The they went ahead and deployed Horizon View 6.1, which they had done many times before on hybrid configurations. They were able to successfully deploy full clone pools on the AF-VSAN, but hit a strange issue when deploying linked clone pools (floating/dedicated). The clone virtual machine operation would fail with an “Insufficient disk space on datastore” error, similar to the following:
A couple of months back, I wrote a short article on Rubrik. They were just coming out of stealth mode and had started an early access program. Since they had not officially launched, there wasn’t a lot that I was allowed to say about the company, other than give a high level overview. As they have now officially launched their r300 series of products, along with news of a massive $41 million Series B of funding, I can now share some additional details about their products and technology. Just to recap on what Rubrik do, they are offering a converged and scale-out backup software and backup storage appliance. The Rubrik appliance (Brik) is a “rack and go” architecture, with the ability to scale from three to thousands of nodes (unlimited) using industry standard 2U commodity appliance hardware.
The whole pitch is the idea that “backups suck”, and they want to give administrators a much better back and restore experience, similar to Apple’s ‘Time Machine’ feature.
With the release of VSAN 6.0, and the new all-flash configuration (AF-VSAN), I have received a number of queries around our 10% cache recommendation. The main query is, since AF-VSAN no longer requires a read cache, can we get away with a smaller write cache/buffer size?
Before getting into the cache sizing, it is probably worth beginning this post with an explanation about the caching algorithm changes between version 5.5 and 6.0. In VSAN 5.5, which came as a hybrid configuration only with a mixture of flash and spinning disk, cache behaved as both a write buffer (30%) and read cache (70%). If a read request was not satisfied by the cache, in other words there was a read cache miss, then the data block was retrieved from the capacity layer. This was an expensive operation, especially in terms of latency, so the guideline was to keep your working set in cache as much as possible. Since the majority of virtualized applications have a working set somewhere in the region of 10%, this was where the cache size recommendation of 10% came from. With hybrid, there is regular destaging of data blocks from write cache to spinning disk. This is a proximal algorithm, which looks to destage data blocks that are contiguous (adjacent to one another). This speeds up the destaging operations.
In Virtual SAN version 6.0, VMware introduced support for an all-flash VSAN. In other words, both the caching layer and the capacity layer could be made up of flash-based devices such as SSDs. However, the mechanism for marking some flash devices as being designated for the capacity layer, while leaving other flash devices as designated for the caching layer, is not at all intuitive at first glance. For that reason, I’ve included some steps here on how to do it.
Another hyper-converged storage company has just emerged out of stealth. Last week I had the opportunity to catch up with the team from SpringPath (formerly StorVisor), based in Silicon Valley. The company has a bunch of ex-VMware folks on-board, such as Mallik Mahalingam and Krishna Yadappanavar. Mallik and Krishna were both involved in a number of I/O related initiatives during their time at VMware. Let’s take a closer look at their new hyper-converged storage product.
The embargo on what’s new in vSphere 6.0 has now been lifted, so we can now start to discuss publicly about new features and functionality. For the last number of months, I’ve been heavily involved in preparing for the Virtual SAN launch. What follows is a brief description of what I find to be the most interesting and exciting of the upcoming features in Virtual SAN 6.0. Later on, I will be following up with more in-depth blog posts on the new features and functionality.
After a great VMworld 2014 in San Francisco, it’s nearly time for the European version which is once again in the beautiful city of Barcelona, Spain. I thought I’d put together a short post on some of my activities, Hopefully you can join me for some.
Introduction to Virtual Volumes – vBrownBag session (Tuesday, October 14th at 2:15pm – Hang Space) I’m delighted to be joined by Nick Dyer of Nimble Storage for an overview of our forthcoming Virtual Volumes. I’ll be sharing our vision for VVols in the whole Software Define Storage story, and Nick will share with you some examples of how Nimble are implementing VVols. Thanks to the vBrownBag team for hosting us.