Non-volatile memory over fabric (NVMe-oF) is used to stream video, computer games, and the like to client devices from network storage embodied by solid state storage devices (SSDs). To provide for redundancy, multiple copies of a single piece of content, e.g., a computer game or video file, are stored on multiple SSDs. To provide information to address the block-level storage based on a client demand for the content, a data structure correlates each content with the SSDs and related block numbers at which the content is stored. Sourcing of the content as it is being streamed may be dynamically switched between SSDs to provide for load balancing or loss of a SSD.

A digital content recording network controller device determines a first content of a set of content to be more likely to be requested by a user of a content access device than a second content of the set of content based on monitored behavior of the user. The device stores the first content in a first storage device of a tiered group of storage devices and stores the second content in a second storage device of the tiered group of storage devices wherein the content access device is located closer to the first storage device than the second storage device. This balances storage load with accessibility, resulting in a faster responding system that does not require as much storage.

The present document describes a method (500) for providing combined audio and video content from a source device (210) to an audio sink device (230) and to a video sink device (220). The method (500) comprises determining (501) latency information regarding the video latency for processing the video content and the audio latency for processing the audio content of the combined audio and video content along the device chain (100) between the source device (210) and the audio and video sink devices (220, 230). Furthermore, the method (5009 comprises delaying (502) the audio content or the video content in dependence of the latency information, and providing (503) the combined audio and video content with the delayed audio content or the delayed video content.

Systems, devices, and methods for streaming or otherwise delivering media content over a network are provided. One exemplary method of streaming media content over a network using a RS-DVR system involves receiving, at the RS-DVR system, a request for a portion of the media content from a media player on a client device via the network, receiving, at the RS-DVR system, the portion of the media content from an origin server on the network, buffering the portion of the media content at the RS-DVR system, and transmitting the portion of the media content to the media player on the client device. The portion of media content may be transmitted using a modified transport layer protocol, and in some embodiments, marked as non-cacheable.

Methods, systems, and computer readable media may be operable to facilitate the dynamic selection of a storage device for storing media. When a recording request is received, storage information associated with resources of one or more networks and one or more storage devices may be retrieved, and a network may be selected for recording and storing the requested media based upon an algorithm that considers the retrieved information. One or more specific storage devices located on the selected network may be selected for recording and storing the requested media. The selection of the one or more specific storage devices may be made based upon an algorithm that considers the available resources and capabilities of available storage devices.

The disclosed computer-implemented method includes determining that incoming media item requests are to be skewed from a random distribution among server nodes, using a random distribution algorithm, to a directed distribution among the server nodes. The method then includes identifying, in a loading assignment, which media items are to be loaded onto specific server nodes to produce the directed distribution of media item requests. The method next includes preloading the identified media items onto the server nodes according to the loading assignment and receiving media item requests for the preloaded media items. The method then includes routing the received media item requests to the server nodes using the random distribution algorithm, where the random distribution algorithm is skewed to the directed distribution based on the preloading of the media items according to the identified loading assignment. Various other methods, systems, and computer-readable media are also disclosed.

A system for creating video content from two or more video content segments has a first video content source storing the video content as two or more video content segments. A second video content source stores the video content as two or more video content segments. A content requestor selects a source of a video content segment in response to an end user request. The selection is made as a function of one or more characteristics of transmission of the video content segment from a selected video content source to the end user. The content requestor monitors the video content segments transmitted by a selected video content source to determine whether a value for the video content characteristic has changed, and determines whether the video content source for a second video content segment source is to be changed from the video content source of the video content segment as a function of the change in the characteristic.

Systems and methods are described herein for streaming during unavailability of a content server. Upon determining that there are conditions indicating buffering issues during delivery of a media asset, a server determines a first group of devices suitable for receiving the media asset from the server and sharing the media asset on a peer-to-peer network. Then, the server determines a second group of devices suitable for receiving the media asset on a peer-to-peer network from a first group device. The server then determines groupings within which to share and receive the media asset. Next, the server transmits instructions to the devices in the first group to maintain in buffer and share certain portions of the media asset with the second group devices within their grouping. Finally, the server updates information detailing the media asset portions the devices are maintaining in buffer and sharing.

An edge server (1510) of a Content Delivery Network (2000) comprises an electronic communication unit adapted to be connected to a telematic network and a processing electronic unit adapted to process data packages received and to be transmitted by the electronic communication unit; the processing electronic unit comprises a first storage sub-unit suitable adapted to store contents and a second storage sub-unit adapted to store configuration information related to a home Point Of Presence (1500) of the edge server (1510); the electronic processing unit is programmed to deal with content requests, so that in response to a request for a content if it is, in whole or in part, locally possessed, sends the content and otherwise determines a server address (1520, 1610) by performing a mathematical calculation on a name of the content taking into account configuration information, and causes a request related to the content to be sent to the server address (1520, 1610); at least the choice of server can also be influenced by artificial intelligence algorithms. Examples of embodiments of the present invention achieve high throughput and ultralow latency, i.e. they can be defined as HTULL.

A method for determining a media server and a sever are provided. In the method, a live streaming access request from a target account is received; an audience number type of an anchor account in the live streaming room is determined; a target media server matching the audience number type is determined; and a live video stream in the live streaming room is transmitted, based on the target media server, to a terminal from which the target account is logged in.