Questions? Call Now!
+61 2 8205 3139

Violin-Memory

Violin provides the industry’s fastest and most scalable memory appliances. Built from the ground up to provide scalable high performance memory infrastructure for large dataset applications, Violin’s memory appliances lower the total cost of memory (TCM), providing an 80% savings in space and power.

Violin’s memory appliances bring a new level of reliability, availability and serviceability (RAS) by providing:

  • Unmatched scalability
  • Industry’s fastest I/O performance
  • Memory fault tolerance
  • Ultra-green power efficiency
  • Compelling price performance

 

 

 

 

Memory Arrays are designed for high IOPS, spike-free latency and network flexibility. The Violin Memory Arrays can be clustered via PCIe with one or more Memory Gateways that provide any of the following high bandwidth connections:

  • Fibre Channel; 8Gb/s or 4Gb/s
  • 10 GbE; iSCSI or FCoE
  • InfiniBand or
  • Combinations of the above!

 

A single Memory Gateway can support up to 4 Violin Memory Arrays, 400K IOPS and over 3GB/s. Through striping, each LUN on the system can get the full bandwidth and IOPS capability of the cluster. LUNs can range in size from 1GB to 120TB!

This cluster architecture enables either Violin or Partners (see FalconStor Press Release) to provide a Memory Gateway with value added functionality such as:

  • LUN Masking & MPIO
  • Thin Provisioning of LUNs
  • Read & Write Caching to HDD storage
  • Snapshots & Continuous Data protection

 

 

 

 

If the network changes, the cluster can be reconfigured to support the new network interfaces or higher bandwidths.

Violin’s Fibre Channel Memory Gateway supports up to 8 ports of 2/4/8 Gbit/s FC and enables very low latency and high bandwidth connectivity to the data center network.

Typical deployment scenarios have the Violin Memory Arrays and gateways operating as peers to existing HDD arrays on the same network. Applications with high IOPS or low latency requirements move their LUNs to operate on the Memory Arrays.