I had a question today asking how VMware Virtual SAN (VSAN) compares to XYZ company. There are over a dozen virtual machine software based solutions that leverage the local disks in ESXi hosts to present storage back to the hosts in the vSphere cluster. Those solutions require a vSphere cluster to be created then their virtual machine must be installed on every host to handle the storage services. Some are more efficient at this than others but there is always level of effort to “build-your-own” storage on top of the vSphere cluster and those virtual machines can take up significant host resources to deliver on the storage services they offer. So converged infrastructure itself is nothing new or unique. Its how it’s done that is important.
Here’s what makes VMware Virtual SAN (VSAN) different:
- VSAN is the ONLY software defined storage solution that is embedded into the ESXi hypervisor making it the most efficient data path for performance. VM’s send their data through the hypervisor right to disk, there’s no middle man. In addition, VSAN is the most efficient in its use of the host resources to deliver on the storage service. VSAN is designed to take up no more than 10% of the host CPU and memory resources and testing with vSphere 6 show significantly less impact than that. Since VSAN is not a VM on top of the hypervisor, it has this distinct advantage. This was a positive tradeoff for the fact that VSAN is a VMware vSphere only solution.
- Being built in also makes it simple and easy to manage. There is no VSAN install, it is simply enabled as a feature of the hypervisor by clicking a check box. When enabled, VSAN will collect all the local disks on all the hosts and create the VSAN Datastore. Bear in mind, the server IO controller and disks must be in place and networking configurations must be completed to make sure VSAN will work when you click that check box.
- VSAN is fully integrated into VMware Storage Policy Based Management (SPBM), VASA, and VVOLs. When that check box is clicked, the VSAN datastore is created and it’s VASA provider is registered with vCenter to expose it’s capabilities to SPBM. This allows different policy to be created so the same pool of capacity can deliver different service levels to different VM’s based on performance, availability, and protection. When VM’s are attached to a policy service level, their VM objects get created on the VSAN datastore in the form of Virtual Volume (VVOL) objects. VSAN further breaks these VVOL objects up into components to deliver on the defined protection and performance service levels.
- VSAN deals with data protection at the software layer so it doesn’t suffer the performance and capacity penalty of hardware RAID. Different “tiers” of protection can be defined by policy and set for different VM’s using the same pool of disks in the VSAN datastore. Numbers of Failures to Tolerate settings determine how many data replicas are written to different hosts to deliver the desired protection level for VM’s.
- VSAN now supports a feature called “Rack Diversity”. I wrote about the benefits here. This brings Software Defined Self Healing with Failure Domains. Hosts in the same rack can be placed into the same fault domain so that if an entire rack is lost then data remains available since another replica copy of the data resides on another host in another rack.
- VSAN is a hybrid storage solution leveraging SSD as cache to accelerate both reads and writes and low cost high capacity hard disks to persist the data. This results in near All-Flash array performance at a fraction of the cost. With vSphere 6 along with Virtual SAN 6, an All-Flash VSAN is supported delivering extreme performance.
VMware Virtual SAN™ 6.0 Performance
- VSAN is one of the few software based storage solutions that can leverage the in host SSD/Flash for Read AND Write caching. There are many solutions that can leverage in host SSD/Flash for read caching. Write back caching is more difficult to implement but VSAN does it while maintaining high availability of those writes across the cluster.
All other converged software based storage solutions require running a Virtual Machine on top of ESXi. So all VM’s have to go through their own IO path, through the hypervisor, then through that single VM IO path, then back through the hypervisor, then to the disks. In some cases, the disks themselves need to be setup with a hardware RAID configuration then their VM solution implements software RAID in addition to the underlying hardware RAID paying a double performance and capacity penalty. Each of these VM’s take on additional host CPU and Memory. Some require 2-4 vCPU’s and 16GB or more of RAM. And some are limited to the number of nodes they can scale to and how much total capacity can be supported. Again, some solutions are more efficient and scalable than others so do the homework and ask the right questions when comparing. Finally, most don’t support VMware’s Storage Policy Based Management which is the VMware framework for managing all vSphere storage going forward.
VMware’s vision for Virtual SAN is that it be the best storage solution for Virtual Machines. With the release of vSphere 6 and Virtual SAN 6, VMware is closer to that vision. There are many software defined storage choices out there. Hopefully this helps in that decision making process.