The cat is officially out of the bag, as they say!. Everyone in the world should now be aware of the fact that VMware Virtual SAN 6.0 supports an all-flash architecture. I think it’s time to discuss a couple of items with regards to a new architecture.
The Virtual SAN 6.0 All-Flash architecture uses flash-based devices for both caching and persistent storage. In this architecture, the flash cache is used completely as write buffer. This all-flash architecture introduces a two-tier model of flash devices:
- Write-intensive, high endurance caching tier for the writes
- Read-intensive, cost-effective flash device tier for data persistence
The new device tiering model not only deliver incredible performance results, but it can also potentially introduce cost savings for the Virtual SAN 6.0 all-flash architecture depending on the design and hardware configuration of the solution.
Virtual SAN Configuration Requirements
In order to configure Virtual SAN 6.0 for the all-flash architecture, the flash devices need to be appropriately identified within the system. In Virtual SAN, flash devices are identified and categorized for the caching tier by default. In order to successfully enabled the all-flash architecture configuration we need manually to flag the flash devices that will be utilized for data persistence or capacity. This configuration is performed via one of the supported command line interface tools such as RVC or ESXCLI.
RVC handles the configuration of the devices at a cluster level. Below you’ll find an image, which illustrates the usable syntax for flagging the flash devices with RVC.
ESXCLI handles it at the per-host level. Below you’ll find an image, which illustrates the usable syntax for flagging the flash devices with esxcli.
Another command line utility that is worth knowing is the VSAN Disk Query (vdq). This utility allows users to identify when the flash devices are configured for used in the capacity tier as well as if they are eligible to be use by Virtual SAN.
Whenever vdq is used to query the flash devices on a host as illustrated below, the output will display a new property called “IsCapacityFlash”. This property specifies whether a flash device will be utilized for the capacity tier instead of the caching tier.
For more in-depth information on the use of vdq, please take a look at a post by one of VMware’s elite engineers and VSAN Champion William Lam.
It’s important to highlight that flagging flash devices to be used for capacity cannot be performed from the option available in the vSphere Web Client UI. It has to be performed via the CLI. (wait for it….wait for it)
Once the flash devices, they will be displayed as magnetic devices (HDD) in the disk management section of the Virtual SAN management tab.
That’s about it, after the flash devices have been properly tagged, the rest of the Virtual SAN configuration procedure is as easy as it was in the previous version.
So in the spirit of making things easy and reduce any contention with getting into the CLI and manually flagging every disk. I’ve been able to design a tool along with my good pal and now a VSAN Champion Brian Graf that should take care of disk tagging process for just about everyone.
Here is a demo of how simple it is to configure a Virtual SAN 6.0 all-flash cluster with a teaser of the Virtual SAN All-Flash Configuration Utility. Oh yeah, I almost forgot to mention….. It’s a 64 node all-flash cluster (The BigDaddy).
For future updates on Virtual SAN (VSAN), vSphere Virtual Volumes (VVOLs) and other Software-defined Storage technologies as well as vSphere + OpenStack be sure to follow me on Twitter: @PunchingClouds