Nitin Gupta, 42330 38Th St, New York, NY 10016

8204058, Jun 19, 2012

Jul 26, 2006

11/494364

David Tze-Si Wu - Fremont CA, US
Soren Lasen - San Francisco CA, US
Nitin Gupta - Fremont CA, US
Vivasvat Keswani - Fremont CA, US

Riverbed Technology, Inc. - Sna Francisco CA

H04L 12/28

370392, 709227

Network traffic is monitored and an optimal framing heuristic is automatically determined and applied. Framing heuristics specify different rules for framing network traffic. While a framing heuristic is applied to the network traffic, alternative framing heuristics are speculatively evaluated for the network traffic. The results of these evaluations are used to rank the framing heuristics. The framing heuristic with the best rank is selected for framing subsequent network traffic. Each client/server traffic flow may have a separate framing heuristic. The framing heuristics may be deterministic based on byte count and/or time or based on traffic characteristics that indicate a plausible point for framing to occur. The choice of available framing heuristics may be determined partly by manual configuration, which specifies which framing heuristics are available, and partly by automatic processes, which determine the best framing heuristic to apply to the current network traffic from the set of available framing heuristics.

8346792, Jan 1, 2013

Nov 9, 2010

12/942950

Steven D. Baker - San Francisco CA, US
Michael Flaster - Menlo Park CA, US
Nitin Gupta - Santa Clara CA, US
Paul Haahr - San Francisco CA, US
Srinivasan Venkatachary - Sunnyvale CA, US
Yonghui Wu - Riverside CA, US

Google Inc. - Mountain View CA

G06F 17/30

707759, 707769

Methods, systems, and apparatus, including computer program products, for generating synthetic queries using seed queries and structural similarity between documents are described. In one aspect, a method includes identifying embedded coding fragments (e. g. , HTML tag) from a structured document and a seed query; generating one or more query templates, each query template corresponding to at least one coding fragment, the query template including a generative rule to be used in generating candidate synthetic queries; generating the candidate synthetic queries by applying the query templates to other documents that are hosted on the same web site as the document; identifying terms that match structure of the query templates as candidate synthetic queries; measuring a performance for each of the candidate synthetic queries; and designating as synthetic queries the candidate synthetic queries that have performance measurements exceeding a performance threshold.

8411570, Apr 2, 2013

Jul 26, 2006

11/494352

David Tze-Si Wu - Fremont CA, US
Nitin Gupta - San Francisco CA, US
Kand Ly - Richmond CA, US

Riverbed Technologies, Inc. - San Francisco CA

H04L 12/26

370235, 709232

Serial clustering uses two or more network devices connected in series via a local and/or wide-area network to provide additional capacity when network traffic exceeds the processing capabilities of a single network device. When a first network device reaches its capacity limit, any excess network traffic beyond that limit is passed through the first network device unchanged. A network device connected in series with the first network device intercepts and will process the excess network traffic provided that it has sufficient processing capacity. Additional network devices can process remaining network traffic in a similar manner until all of the excess network traffic has been processed or until there are no more additional network devices. Network devices may use rules to determine how to handle network traffic. Rules may be based on the attributes of received network packets, attributes of the network device, or attributes of the network.

8462624, Jun 11, 2013

Jul 26, 2006

11/494025

Steve McCanne - Berkeley CA, US
Nitin Gupta - San Francisco CA, US

Riverbed Technologies, Inc. - San Francisco CA

H04L 12/26

370230, 370241, 714 48

A network stack includes a packet loss analyzer that distinguishes between packet losses due to congestion and due to lossyness of network connections. The loss analyzer observes the packet loss patterns for comparison with a packet loss model. The packet loss model may be based on a Forward Error Correction (FEC) system. The loss analyzer determines if lost packets could have been recovered by a receiving network device, if FEC had been used. If the lost packets could have been corrected by FEC, the loss analyzer assumes that no network congestion exists and that the packet loss comes from the lossy aspects of the network, such as radio interference for wireless networks. If the loss analyzer determines that some of the lost packet could not have been recovered by the receiving network device, the loss analyzer assumes that network congestion causes these packet losses and reduces the data rate.

8462629, Jun 11, 2013

Jun 13, 2007

11/762688

Nitin Gupta - San Francisco CA, US
William Welch - San Francisco CA, US
Steven McCanne - Berkeley CA, US

Riverbed Technology, Inc. - San Francisco CA

G01R 31/08

370235, 370465

Methods, systems, and apparatus provide efficient and flexible networking quality of service as well as transport protocol design. A hybrid transport/network quality of service (HTNQ) scheme improves the performance of TCP over specific links or network paths that are subject to high latency, a high bandwidth-delay product, high packet loss, and/or bit errors. A callback mechanism can be used between a packet scheduler and a transport module to control the transmission rate of packets across one or more connections or links.

8463843, Jun 11, 2013

May 29, 2007

11/754940

Kartik Subbanna - Fremont CA, US
Nitin Gupta - San Francisco CA, US
Daniel Conor O'Sullivan - San Francisco CA, US
Shashidhar Merugu - Mountain View CA, US
Steven James Procter - San Francisco CA, US
Vivasvat Manohar Keswani - San Francisco CA, US

Riverbed Technology, Inc. - San Francisco CA

G06F 15/16

709203, 709202, 709218, 709228, 709232

In a system where transactions are accelerated with asynchronous writes that require acknowledgements, with pre-acknowledging writes at a source of the writes, a destination-side transaction accelerator includes a queue for queue writes to a destination, at least some of the writes being pre-acknowledged by a source-side transaction accelerator prior to the write completing at the destination, a memory for storing a status of a destination-side queue and possibly other determinants, and logic for signaling to the source-side transaction accelerator with instructions to alter pre-acknowledgement rules to hold off on and pursue pre-acknowledgements based on the destination-side queue status. The rules can take into account adjusting the flow of pre-acknowledged requests or pre-acknowledgements at the sender-side transaction accelerator based at least on the computed logical length.

8473620, Jun 25, 2013

Jul 26, 2010

12/843754

Michael J. Demmer - San Francisco CA, US
Kand Ly - Richmond CA, US
Nitin Gupta - Fremont CA, US

Riverbed Technology, Inc. - San Francisco CA

G06F 15/16

709227

Methods and apparatus are provided for intercepting a client-server communication connection in a computing environment. A first network intermediary configured to facilitate optimization of client-server transactions may be installed in a path of communications between the client and the server. A second network intermediary configured to cooperate with the first network intermediary is not in the path of communications between the client and the server. The first network intermediary intercepts a connection request from the client and forwards a modified request toward the server. A module within the server intercepts the connection request and redirects it to the second network intermediary. The client-server connection is thus split-terminated at the two network intermediaries, which establish cooperative sessions between themselves and with the client and with the server.

8533310, Sep 10, 2013

Mar 7, 2008

12/044861

Charles Huang - Palo Alto CA, US
Nitin Gupta - Fremont CA, US
Vivasvat Keswani - Fremont CA, US
Bart Robinson - Richmond CA, US

Riverbed Technology, Inc. - San Francisco CA

G06F 15/173
G06F 15/16
G06F 9/34

709223, 709219, 709246, 711213

Association information is used to build association trees to associate base pages and embedded objects at a proxy. An association tree has a root node containing a URL for a base page, and zero or more leaf nodes each containing a URL for an embedded object. In most cases, an association tree will maintain the invariant that all leaves contain distinct URLs. However, it is also possible to have an association tree in which the same URL appears in multiple nodes. An association tree may optionally contain one or more internal nodes, each of which contains a URL that is an embedded object for some other base page, but which may also be fetched as a base page itself. Given a number of association trees and a base-page URL, a prefetch system finds the root or interior node corresponding to that URL (if any) and traverses the tree from that node, prefetching URLs until the URL of the last leaf node is prefetched. The prefetching starts the process of bringing over the various embedded objects before the user or program would ordinarily fetch them.