Infineta Systems Explained

Infineta Systems
Type:	Private
Foundation:	California 2008
Fate:	shutdown and sold IP to Riverbed Technology, Inc.
Location City:	Santa Clara, California
Industry:	Networking hardware

Infineta Systems was a company that made WAN optimization products for high performance, latency-sensitive network applications. The company advertised that it allowed application data rate to exceed the nominal data rate of the link. Infineta Systems ceased operations by February 2013, a liquidator was appointed, and its products will no longer be manufactured, sold or distributed.

Riverbed Technology purchased some of Infineta's assets from the liquidator.^[1]

Company

Infineta was founded in 2008 by Raj Kanaya, the CEO, and K.V.S. Ramarao, the CTO. Ramarao concluded the computational resources, especially I/O operations and CPU cycles, associated with data compression technologies would ultimately limit their scalability.^[2] He and Kanaya determined founded Infineta to develop algorithms and hardware. The company had six patents pending.

Infineta was headquartered in San Jose, California and attracted $30 million in two rounds of venture funding from Alloy Ventures, North Bridge Venture Partners, and Rembrandt Venture Partners.^{[3] [4]}

Products

Infineta announced its Data Mobility Switch in June 2011. The DMS was the first WAN optimization technology to work at throughput rates of 10 Gbit/s.^[5] Infineta designed the product in FPGA hardware around a multi-Gigabit switch fabric to minimize latency.The DMS used compression similar to data deduplication.

The product was designed to addresses the long-standing issue of TCP performance^[6] on long fat networks, so even unreduced data can achieve throughputs equivalent to the WAN bandwidth. To illustrate what this means, take the example of transferring a 2.5 GBytes (20 billion bits) file from New York to Chicago (15 ms latency, 30 ms round-trip time) over a 1 Gbit/s link. With standard TCP, which uses a 64 KB window size, the file transfer would take about 20 minutes. The theoretical maximum throughput is 1 Gbit/s, or about 20 seconds. The DMS performs the transfer in 19.5 to 21 seconds.^[7]

See also

• Data migration
• WAN optimization
• Network latency
• Network congestion

External links

• Web site: Infineta Systems—WAN Optimization for Big Traffic . Company web site . dead . https://web.archive.org/web/20121223052330/http://www.infineta.com/ . December 23, 2012 . June 27, 2013 .

Notes and References

1. Web site: Technology Migration – Contact Sales Infineta . Web page . . June 27, 2013 .
2. Book: Martynov, Maxim. 2009 Proceedings of 18th International Conference on Computer Communications and Networks . Challenges for High-Speed Protocol-Independent Redundancy Eliminating Systems . 11 September 2009. 6. 10.1109/ICCCN.2009.5235389. 8391963 . 1095-2055.
3. Web site: San Jose-Based Infineta Systems Raises $15 Million in Second Round . Silicon Valley Wire . 2011-06-06 . 2011-07-29.
4. Web site: Infineta raises $15M to move big data across data centers — Cloud Computing News . Gigaom.com . 2011-06-06 . 2011-07-29.
5. Web site: Rath. John. Infineta Ships 10Gbps Data Mobility Switch. June 7, 2011. 2011-06-07.
6. Web site: Jacobson. Van. TCP Extensions for High Performance. Network Working Group V. Jacobson Request for Comments: 1323. ietf.org.
7. Throughput can be calculated as: Throughput \le (RWIN)/(RTT) where RWIN is the TCP Receive Window and RTT is the latency to and from the target. The default TCP window size in the absence of window scaling is 65,536 bytes, or 524,228 bits. So for this example, Throughput = 524,228 bits / 0.03 seconds = 17,476,267 bits/second or about 17.5 Mbit/s. Divide the bits to be transferred by the rate of transfer: 20,000,000,000 bits / 17,476,267 = 1,176.5 seconds, or 19.6 minutes.