StarWind Virtual SAN™
Cost of ownership
Cost of ownership is cut by at least half – meaning both Operational and Capital Expenditure. StarWind Virtual SAN completely eliminates the actual physical shared storage, corresponding infrastructure and associated deployment and maintenance activities. There is physically less expensive hardware to buy and service.
Simplicity is a key feature. StarWind Virtual SAN runs as a native hypervisor component so it does not require any deep storage and network orchestration or UNIX management skills. A typical system administrator with minimal experience in either Hyper-V or Windows can install, configure and maintain Virtual SAN operations.
Performance is uncompromised by the reduced deployment and management costs. StarWind Virtual SAN brings to the table server-side flash and memory caches, log-structuring and an absolutely minimalistic I/O path. The resulting performance can’t be matched by either typical virtual appliances or physical shared storage.
Virtual SAN is a natural part of the hypervisor. The result is both outstanding performance and unified administration using hypervisor-specific management tools. Virtual SAN “gets the job done” with all major virtualization platforms running on Hyper-V and Windows as a native application and on vSphere or Xen nested inside a VM. Non-virtualized clusters typically deployed for performance-intensive SQL Server and Exchange installations are also fully supported. Learn More
StarWind Virtual SAN can also run on a dedicated set of hosts creating a separated storage layer being used by consumers. Though a hyper-converged scenario is an industry trend now, the differentiation of compute and storage layers makes sense if there’s need to grow by capacity only. Typical use cases are shared storage for huge clustered SQL Server and Oracle deployments and an inexpensive block back-end for Scale-Out File Servers. Learn More
Virtual SAN provisions and manages storage with VM workload in mind. General-purpose storage arrays are usually the best candidates to serve hypervisors. Virtual SAN uses Log-Structured File System and sophisticated caching in order to avoid as much of a random I/O dominating VM world as possible but still without deploying extremely expensive and cost-inefficient all-flash model. Learn More
Virtual SAN reduces I/O latency and eliminates much of the network traffic to an absolute minimum by utilizing distributed RAM and flash-based caches. Performance is drastically improved. Caches are kept coherent between multiple hosts so that a lightning-fast write back policy is safe and achievable with commodity hardware. Learn More
Virtual SAN basically “mirrors” the actual storage and caches between the given numbers of hosts creating a fault-tolerant storage pool. It is completely up to the system administrator as to how many replicas of a particular VM or LUN are kept alive and how many active storage controllers a cluster should use. Individual disks, memory modules, whole compute and storage hosts can fail but uptime is never compromised. Learn More
StarWind Virtual SAN flexibly adopts both Scale-Up and Scale-Out architectures. Capacity can be increased by simply throwing more spindles into the existing storage cluster node. Bringing in a new host with its own CPU, RAM and internal storage can scale storage capacity, I/O performance and VM number crunching facilities out. Learn More
StarWind Virtual SAN utilizes inexpensive commodity hardware. “Magic” happens with the help of proprietary in-house developed software and general-purpose x64 servers, MLC flash, spinning disks and Ethernet. Virtual SAN can definitely take care of higher-performing SAS, more reliable SLC flash and a faster 10 or 40/56 GbE network but all of that “higher league” gear is fully optional. Learn More
Virtual SAN comes with an effective mechanism to ensure that the mission-critical business data is replicated to a disaster recovery site. Replication is implemented to be asynchronous, background, deduplication, and compression-aware as well as snapshot-based. Primary I/O operations do not suffer from leaned resources and WAN channel requirements being sparse. Learn More
StarWind Virtual SAN implements inter-node tiering technology to offload cold data such as snapshots from fast and expensive primary storage to slower but inexpensive secondary storage. The combined result allows for the use of a much smaller amount of flash as primary tier with cheap spindles as a secondary tier. Learn More
StarWind Virtual SAN implements VM and flash-friendly space reduction technologies such as in-line deduplication and compression. The result allows for the increased usable capacity of all-flash configurations, boosts I/O performance as more data can be pinpointed to now virtually “bigger” deduplicated caches and also prolongs flash life since the amount of write operations is dramatically reduced. Learn More
StarWind Virtual SAN does VTL allowing the use of a fast spinning disks to emulate traditional physical tape drives, auto-loaders and libraries. The demand on this technology is driven by the fact that tape drives are very relevant, cost-effective and designed to store data for a long period of time. Lots of companies fall under regulatory requirements insisting on tapes with company data being vaulted. Virtual Tape Library allows seamless integration into existing backup infrastructure without the need to break it up. Disk-to-Disk-to-Tape backup provides a smaller backup window compared to traditional Disk-to-Tape scenario and gives better reliability because an intermediary copy of all backup data is stored in an extra location which is a spinning disk. Learn More