Pavilion Data Systems, Storage Start-Up in Stealth Mode

San Jose, CA-based Pavilion Data Systems, Inc. was launched two years ago.

The start-up got financial funding (unknown amounts) through two rounds from three investors: Kleiner Perkins, Caufield & Byers, Artiman Ventures and SK Telecom Americas Innopartners.

Three main executives:

Kiran Malwankar, co-founder and CEO, was formerly, director of hardware engineering at Violin Memory for one year after working for Stokes, Inc., Andiamo, Cisco, Nishan and KLA-Tencor.

Sundar Kanthadai, co-founder and VP, came from SeaMicro (acquired by AMD) where he was SW director for 6 years and member of the founding team.
VR Satish, CTO, came from Nutanix (advisor), Artiman Ventures, Symantec (VP and CTO, storage and availability management group), and is also advisory board member of other storage start-up Sureline Systems.

We know about nothing on the start-up’ business. On its web site, there is only one sentence: “Pavilion Data Systems is a well funded stealth startup. We are innovating at the intersection of storage, memory, networking and systems.“

The company’ CEO has been assigned a patent that can give an indication of its activity:
Processor agnostic storage in PCIe-based shared storage environment
“Disclosed are a system, a method and/or an apparatus of processor agnostic data storage in a PCIE based shared storage environment. In one aspect, a method includes processing a storage based request received at an adapter circuit of a controller device associated with a disk array to direct the storage based request to at least one of a processor of the disk array and a plurality of storage devices of the disk array. The method also includes routing, through an interface circuit of the controller device, the data request in the other format compatible with the storage device directly to at least one storage device of the plurality of storage devices of the disk array coupled to the controller device agnostic to a processor of the disk array to store a data associated with the data request based on a mapping table.”