Qualcomm Incorporated

Digital Fountain, Inc.

Compaq Computer Corporation, Inc.

Other

Digital Equipment Corporation

International Computer Science Institute

Digital Foundation, Inc.

Michael G Luby

Mark Watson

Lorenz Christoph Minder

M Amin Shokrollahi

Thomas Stockhammer

Payam Pakzad

Lorenzo Vicisano

Bin Wang

Soren Bogh Lassen

Mohammad Amin Shokrollahi

Gavin Bernard Horn

Yinian Mao

Armin D Haken

Thomas J Richardson

Charles Nung Lo

Michael David Mitzenmacher

Jeffrey J Persch

Ying Hai Chen

John Byers

Fatih Ulupinar

Gordon Kent Walker

Kevin Roland Fall

Qiang Gao

Steve (Aihua) Chen

Daniel A Spielman

Diane Hernek

Volker Stemann

Jun Wang

Ralph Akram Gholmieh

Nikolai Konrad Leung

Nagaraju Naik

Lars Eilstrup Rasmussen

Donald William Gillies

Roberto Attias

Ronen Vainish

David Kushi

Soren Lassen

Bill Seed

Thomas Kunz

Matt Doucleff

Avi Wigderson

Michael Walfish

Adrian Perrig

Jens Rasmussen

Serban Simu

Ying Chen

Kuo-Chun Lee

Matthew Stuart Grob

Amin Shokrollahi

Punyaslok Purkayastha

Carlos Marcelo Dias Pazos

Jaber Mohammad Borran

Jack Shauh

Deviprasad Putchala

Vivek K Goyal

Chaitali Gupta

William R Seed

Shravya Kunamalla

Andres Albanese

Mahdi Cheraghchi Bashi Astaneh

Jeffrey A Edmonds

Johannes F Bloemer

Jourdan J Clish

Lorenz Minder

Mike Mitzenmacher

Per Knudsgaard

Joseph A Vo

Christian Foisy

Barry Dobyns

Manu Prasad

Amin M Shokrollahi

A block-request streaming system provides for improvements in the user experience and bandwidth efficiency of such systems, typically using an ingestion system that generates data in a form to be served by a conventional file server (HTTP, FTP, or the like), wherein the ingestion system intakes content and prepares it as files or data elements to be served by the file server. A client device can be adapted to take advantage of the ingestion process. The client device might be configured to optimize use of resources, given the information available to it from the ingestion system. This may include configurations to determine the sequence, timing and construction of block requests based on monitoring buffer size and rate of change of buffer size, use of variable sized requests, mapping of block requests to underlying transport connections, flexible pipelining of requests, and/or use of whole file requests based on statistical considerations.

Enhanced block-request streaming using block partitioning or request controls for improved client-side handling

A block-request streaming system provides for low-latency streaming of a media presentation. A plurality of media segments are generated according to an encoding protocol. Each media segment includes a random access point. A plurality of media fragments are encoded according to the same protocol. The media segments are aggregated from a plurality of media fragments.

Enhanced block-request streaming system for handling low-latency streaming

A block-request streaming system provides for improvements in the user experience and bandwidth efficiency of such systems, typically using an ingestion system that generates data in a form to be served by a conventional file server (HTTP, FTP, or the like), wherein the ingestion system intakes content and prepares it as files or data elements to be served by the file server. The system might include controlling the sequence, timing and construction of block requests, time based indexing, variable block sizing, optimal block partitioning, control of random access point placement, including across multiple presentation versions, dynamically updating presentation data, and/or efficiently presenting live content and time shifting.

Enhanced block-request streaming system using signaling or block creation

Systems and methods providing for storing fragments for one or more source objects at storage nodes of multiple cluster instances comprising a cluster set are disclosed. Repair of the stored data is operated within cluster instances autonomously or semi-autonomously of other cluster instances of the cluster set according to embodiments. Embodiments may provide a storage process operable to generate fragments for a first source object to be stored in a storage system using a first encoding, wherein a different plurality of fragments of the generated fragments are stored at different cluster instances of a cluster set. A repair process may be enacted at each cluster instance of the cluster set, wherein a repair process enacted at a cluster instance is used to maintain the recoverability of the fragments of the first source object stored at that cluster instance using a second encoding.

Systems and methods for storing, maintaining, and accessing objects in storage system clusters

An over-the-air (OTA) broadcast middleware unit is configured to receive aggregated session description data for a plurality of sessions, wherein each of the sessions transports media data related to common media content, and wherein each of the sessions is transmitted as part of an OTA broadcast, and extract at least some of the media data from the OTA broadcast based on the aggregated session description data. The OTA broadcast middleware unit may further deliver the extracted media data to a streaming client, such as a Dynamic Adaptive Streaming over HTTP (DASH) client.

Session description information for over-the-air broadcast media data

Systems and methods which implement repair bandwidth control techniques, such as may provide a feedback control structure for regulating repair bandwidth in the storage system. Embodiments control a source object repair rate in a storage system by analyzing source objects represented in a repair queue to determine repair rate metrics for the source objects and determining a repair rate based on the repair rate metrics to provide a determined level of recovery of source data stored as by the source objects and to provide a determined level of repair efficiency in the storage system. For example, embodiments may determine a per storage object repair rate (e.g., a repair rate preference for each of a plurality of source objects) and select a particular repair rate (e.g., a maximum repair rate) for use by a repair policy. Thereafter, the repair policy of embodiments may implement repair of one or more source objects in accordance with the repair rate.

Systems and methods for repair rate control for large erasure coded data storage

Systems and methods utilizing available storage space within a storage system (e.g., as 'supplemental' storage) and/or implement less physical storage space in the storage system (e.g., reduced storage overhead) through operation of fragment pre-storage techniques are disclosed. Such fragment pre-storage utilization of the aforementioned available storage space may provide operation emulating larger storage overhead than is actually provided in the storage system, facilitate improved repair rates, and/or facilitate reduced repair bandwidth in the storage system according to embodiments. A fragment pre-storage repair policy may implement source object repair whereby additional fragments for the source object are pre-generated and pre-stored in the storage system as transient fragments, whereby the transient fragments are moved to corresponding storage nodes when those storage nodes become physically present in the storage system.

Systems and methods for pre-generation and pre-storage of repair fragments in storage systems

Systems and methods which implement one or more data organization techniques that facilitate efficient access to source data stored by a storage system are disclosed. Data organization techniques implemented according to embodiments are adapted to optimize (e.g., maximize) input/output efficiency and/or (e.g., minimize) storage overhead, while maintaining mean time to data loss, repair efficiency, and/or traffic efficiency. Data organization techniques as may be implemented by embodiments include blob based organization techniques, grouped symbols organization techniques, data ordering organization techniques, and combinations thereof.

Systems and methods for data organization in storage systems using large erasure codes

Systems and methods which implement forward checking of data integrity are disclosed. A storage system of embodiments may, for example, comprise data integrity forward checking logic which is operable to perform forward checking of data integrity in real-time or near real-time to check that a number of node failures can be tolerated without loss of data. Embodiments may be utilized to provide assurance that a number of fragments needed for source data recovery will be available for the source objects most susceptible to failure when a certain number of additional fragments are lost, such as due to storage node failures.

Systems and methods for verification of code resiliency for data storage

Content (e.g., multimedia streams, audio-video streams, video files, text, etc.) may be delivered to receiver devices over a broadcast channel and/or via a broadcast network via components (e.g., servers, receiver device, software applications, modules, processes, etc.) configured to communicate the content in a manner that reduces the amount of information communicated over the broadcast network, reduces the amount network bandwidth consumed by the communication, meets precise timing requirements for the individual objects that are communicated, and enables each receiver device to receive, decode, and render the content without consuming an excess amount of that receiver device's battery or processing resources.

Methods for delivery of flows of objects over broadcast/multicast enabled networks

Encoding of a plurality of encoded symbols is provided wherein an encoded symbol is generated from a combination of a first symbol generated from a first set of intermediate symbols and a second symbol generated from a second set of intermediate symbols, each set having at least one different coding parameter, wherein the intermediate symbols are generated based on the set of source symbols. A method of decoding data is also provided, wherein a set of intermediate symbols is decoded from a set of received encoded symbols, the intermediate symbols organized into a first and second sets of symbols for decoding, wherein intermediate symbols in the second set are permanently inactivated for the purpose of scheduling the decoding process to recover the intermediate symbols from the encoded symbols, wherein at least some of the source symbols are recovered from the decoded set of intermediate symbols.

Methods and apparatus employing FEC codes with permanent inactivation of symbols for encoding and decoding processes

Growing community of inventors

Berkeley, CA, United States of America

Michael G Luby