Verizon Digital Media Services Inc.

Seiko Epson Corporation

Verizon Patent and Licensing Inc.

Edgecast Inc.

Edgecast Networks, Inc.

Derek Shiell

Robert J Peters

Amir Reza Khakpour

Jing Xiao

Harkeerat Singh Bedi

Donnevan Scott Yeager

Alexander A Kazerani

David Andrews

Sergio Leonardo Ruiz

Hayes Kim

Mehrdad Arshad Rad

Jayson G Sakata

Hooman Mahyar

Marcel Eric Schechner Flores

Brian W Joe

Juan Bran

Kyriakos Zarifis

William Pressly

Karthik Sathyanarayana

Reed Morrison

Hossein Lotfi

Paulo Tioseco

William Rosecrans

Dian Peng

Thomren Boyd

Francois Lacroix

Daniel Lockhart

Provided is an edge compute platform ('ECP') for serving optimized content from local cache or from output of a shared customizable function executed by a compute device at the network edge on behalf of different customer content such that the function is not redundantly deployed for different customer content, and is not be executed each time the same variant of the optimized content is requested. The ECP may canonicalize first transformation parameters of a received original request according to a transformation parameter definition of a particular function that is implicated by the original request, may generate second transformation parameters with a different ordering than the first transformation parameters as a result of the canonicalization, may generate a variant of the original file by inputting the second transformation parameters to the particular function, and may provide the variant in response to the original request.

Systems and methods for dynamic content optimization at the network edge using shared customizable functions

An Edge Compute Network ('ECN') may provide compute devices with configurable compute resources at different network edges for selective localized and low latency execution of user-defined operations. A user may provide a set of operations in any of several supported programming languages, and the ECN may create an executable environment that can execute the set of operations using the compute resources of any ECN compute device. A function manager for a compute device may selectively initialize, based on requests to execute the set of operations and an initialization policy, the executable environment so that the set of operations can be directly executed using the compute resources of that compute device upon request. The function manager may also selectively remove initialized executable environments based on compute device resource utilization, executable environment usage, and a removal policy.

Function manager for an edge compute network

Provided is a controller for dynamically balancing load between different servers using different thresholds that are continually modified for each of the servers. The controller may generate a baseline load measure based on load measures received from the different servers, and may configure a first threshold for a first server and a second threshold for a second server based on the load measure at the first server deviating from the baseline load measure by a first amount that is greater than a second amount by which the load measure at the second server deviates from the baseline load measure. The controller may allocate an additional server to distribute first content with the first server in response to first content load at the first server satisfying the first threshold and the same load or a greater load of second content at the second server not satisfying the second threshold.

Systems and methods for dynamic load balancing based on server utilization and content popularity

Provided is an edge key value ('EKV') store for receiving data from any of network location of a distributed platform, and for distributed a synchronized copy of the data to servers at the network locations where the data is requested regardless of where, how, and when the data is updated. The EKV store may receive a first value for a key at a first storage device of the EKV store based on a message issued by a first user through a first network location, may receive a second value for the key at a second storage device of the EKV store based on a message issued by a second user through a second network location, and may store the second value as a current value for the key by forming a consensus across the storage devices that the second value is the most recent value for the key.

Edge key value store for a distributed platform

A Multi-Threaded Indexed ('MTI') file system may use a first set of threads, processes, or executable instances to index desired file attributes in a database while simultaneously but independently executing file operations with a second set of threads, processes, or executable instances. In response to receiving a file operation, the second set of threads, processes, or executable instance may query the database to directly identify files that are indirectly implicated by the file operation with a wildcard, regular expression, and/or other expression that indirectly identifies the files based on different file attributes, paths, name expressions, or combinations thereof. The second set of threads, processes, or executable instances are therefore able to identify the files implicated by the file operation based solely on the indexed file attributes already entered in the database without the need to load and scan the metadata of files in directories targeted by the file operation.

Systems and methods for large scale complex storage operation execution

The embodiments provide systems and methods for efficiently and accurately differentiating requests directed to uncacheable content from requests directed to cacheable content based on identifiers from the requests. The differentiation occurs without analysis or retrieval of the content being requested. Some embodiments hash identifiers of prior requests that resulted in uncacheable content being served in order to set indices within a bloom filter. The bloom filter then tracks prior uncacheable requests without storing each of the identifiers so that subsequent requests for uncacheable requests can be easily identified based on a hash of the request identifier and set indices of the bloom filter. Some embodiments produce a predictive model identifying uncacheable content requests by tracking various characteristics found in identifiers of prior requests that resulted in uncacheable content being served. Subsequent requests with identifiers having similar characteristics to those of the predictive model can then be differentiated.

Methods and systems for advanced content cacheability determination

The embodiments provide request multiplexing whereby a server receiving a first request for content clones and issues the cloned request to an origin to initiate retrieval of the content. The first request and subsequent requests for the same content are placed in a queue. The server empties a receive buffer that is populated with packets of the requested content as the packets arrive from the origin by writing the packets directly to local storage without directly distributing packets from the receive buffer to any user. The rate at which the server empties the receive buffer is therefore independent of the rate at which any user receives the packets. A first set of packets written to local storage can then be simultaneously distributed to one or more queued requests as the server continues emptying the receive buffer and writing a second set of packets to local storage.

Request multiplexing

Provided is a device that persistently distributes connectionless traffic across different simultaneously executing server instances in a manner that allows a first set of server instances of the device to commence a new first set of connectionless data streams during a first interval, and a different second set of server instances of the device to commence a different second set of connectionless data streams as the first set of server instances respond to ongoing connectionless data streams of the first set of connectionless data streams during a subsequent second interval. The persistent distribution further supports virtual connection migration by distributing, to the same server instance, data packets that are directed to the same connectionless data stream even when the sending user equipment changes addressing during the connectionless data stream.

Persistent distribution of connectionless traffic supporting virtual connection migration

Some embodiments provide partitioned serialized caching and delivery of large sized content and files. Some embodiments partition requests for large sized content into segment requests with each segment request identifying a different byte range of the requested content. Each segment request is hashed to identify a particular server from a set of servers tasked with caching and delivering a different segment of the requested content. In this manner, no single server caches or delivers the entirety of large sized content. The segment requests are distributed serially across the set of servers so that the segments are passed in order, wherein the serial distribution involves handing-off the requesting user's connection serially to each server of the set of server in the order with which the set of servers deliver the content segments.

Partitioned serialized caching and delivery of large files

The solution distributes the management of stream segments from a central storage cluster to different edge servers that upload stream segments to and receive stream segments from the central storage cluster. Each edge server tracks the stream segments it has uploaded to the central storage cluster as well as the expiration times for those segments. The tracking is performed without a database using a log file and file system arrangement. First-tier directories are created in the file system for different expiration intervals. Entries under the first-tier directories track individual segments that expire within the expiration interval of the first-tier directory with the file system entries being files or a combination of subdirectories and files. Upon identifying expired stream segments, the edge servers instruct the central storage cluster to delete those stream segments. This removes the management overhead from the central storage cluster and implements the distributed management without a database.

Distributed management of live stream storage

The embodiments provide peer cache filling. The peer cache filling allocates a set of caching servers to distribute content in response to user requests with a limited first subset of the set of servers having access to retrieve the content from an origin and with a larger second subset of the set of servers retrieving the content from the first subset of servers without accessing the origin. The peer cache filling dynamically escalates and deescalates the allocation of the caching servers to the first and second subsets as demand for the content rises and falls. Peer cache filling is implemented by modifying request headers to identify designated hot content, provide a request identifier hash result for identifying the ordering of servers, and provide a value for designating which servers in the ordering as primary server with access to the origin.

Peer cache filling

Disclosed are different implementations for rapid configuration propagation across multiple servers of a distributed platform. One implementation is a push based distribution of update segments that are generated from a onetime differential analysis of an updated particular configuration relative to a previous instance of the particular configuration. Sequence numbers attached to the updated segments identify is a server's copy of a configuration is up-to-date and can receive a new updated segment or if missing intervening segments are to be retrieved from peers and applied prior to applying the new updated segment. Another implementation is a pull based distribution of compressed images of the configurations. A complete set of configurations are distributed as a compressed file system that is loaded into server memory. Individual configurations are read out of the file system and loaded into memory when implicated by client requests.

Rapid configuration propagation in a distributed multi-tenant platform

Some embodiments provide a multi-tenant over-the-top multicast solution that integrates the per user stream customizability of unicast with the large scale streaming efficiencies of multicast. The solution involves an application, different multicast groups streaming an event with different customizations, and a manifest file or metadata identifying the different groups and customizations. The solution leverages the different multicast groups in order to provide different time shifts in the event stream, different quality level encodings of the event stream, and different secondary content to be included with a primary content stream. The application configured with the manifest file or metadata dynamically switches between the groups in order to customize the experience for a user or user device on which the application executes. Switching from multicast to unicast is also supported to supplement available customizations and for failover.

Growing community of inventors

Los Angeles, CA, United States of America

Derek Shiell