RDMA based real-time video client playback architecture

• US 7,996,482 B1
• Filed: 07/31/2007
• Issued: 08/09/2011
• Est. Priority Date: 07/31/2007
• Status: Active Grant

• Current Assignee: ZAMA Innovations LLC
• Original Assignee: Qurio Holdings Incorporated
• Inventors: Evans, Gregory M., Roberts, Thomas A., Evans, James
• Primary Examiner(s): WASEL, MOHAMED A
• Application Number:
  US11/831,228
• Time in Patent Office: 1,470 Days
• Field of Search: 709212-214, 709/216
• US Class Current: 709/212
• CPC Class Codes: H04L 65/612 for unicast
• CPC Class Codes: H04L 67/1097 for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
• CPC Class Codes: H04L 67/568 Storing data temporarily at an intermediate stage, e.g. caching
• CPC Class Codes: H04L 67/5683 Storage of data provided by user terminals, i.e. reverse caching
• CPC Class Codes: H04L 9/40 Network security protocols
• CPC Class Codes: H04N 21/23805 Controlling the feeding rate to the network, e.g. by controlling the video pump
• CPC Class Codes: H04N 21/2387 Stream processing in response to a playback request from an end-user, e.g. for trick-play
• CPC Class Codes: H04N 21/44004 involving video buffer management, e.g. video decoder buffer or video display buffer
• CPC Class Codes: H04N 21/4621 Controlling the complexity of the content stream or additional data, e.g. lowering the resolution or bit-rate of the video stream for a mobile client with a small screen arrangements for using the results of monitoring on user's side in broadcast systems H04H60/65; flow control in packet networks H04L47/10

Abstract

A client playback architecture for a media content distribution system is provided. In the preferred embodiment, the client playback architecture is a Remote Direct Memory Access (RDMA) based architecture. The RDMA based architecture enables the client playback device to obtain media content from a central server in real-time or in substantially real-time as the media content is needed for playback at the client playback device. More specifically, the playback device includes RDMA enabled playback circuitry operating to perform RDMA transfers for select media content, buffer the media content received as a result of the RDMA transfers, and provide the media content for presentation to one or more associated viewers via one or more audio/video interfaces.

Claims

1. A system comprising:

a) a Remote Direct Memory Access (RDMA) enabled network interface;

b) RDMA enabled playback circuitry associated with the RDMA enabled network interface comprising;

i) an RDMA enabled buffer circuit associated with the RDMA enabled network interface and adapted to;

receive an RDMA address range of select media content defining a range of addresses in a storage unit of a centralized media content server in which the select media content is stored; and

perform at least one RDMA transfer via the RDMA enabled network interface to transfer data stored in the RDMA address range from the storage unit of the centralized media content server to the RDMA enabled buffer circuit;

ii) a playback buffer circuit associated with the RDMA enabled buffer circuit comprising;

a media content processing function adapted to;

receive the data from the RDMA enabled buffer circuit based on a playback clock; and

process the data to provide the select media content in a format ready for playback; and

a playback buffer adapted to store the select media content from the media content processing function for playback.

2. The system of claim 1 wherein the RDMA enabled buffer circuit comprises:

a buffer; and

a data mover function adapted to receive the RDMA address range of the select media content and perform the at least one RDMA transfer via the RDMA enabled network interface to transfer the data stored in the RDMA address range from the storage unit of the centralized media content server to the buffer.

3. The system of claim 2 wherein in order to perform the at least one RDMA transfer, the data mover function is further adapted to:

generate a first RDMA transfer request based on an amount of storage available in the buffer;

issue the first RDMA transfer request to the RDMA enabled network interface, wherein data received in response to the first RDMA transfer request is stored in the buffer.

4. The system of claim 3 further comprising:

a plurality of RDMA enabled buffer circuits comprising the RDMA enabled buffer circuit;

wherein the RDMA enabled buffer circuit further comprises an RDMA address compare function adapted to;

compare RDMA addresses of data received from the RDMA enabled network interface in response to RDMA transfer requests from the plurality of RDMA enabled buffer circuits to RDMA addresses requested by the first RDMA transfer request to identify the data received in response to the first RDMA transfer request; and

trigger storage of the data received in response to the first RDMA transfer request in the buffer of the RDMA enabled buffer circuit.

5. The system of claim 3 wherein in order to generate the first RDMA transfer request, the data mover function is further adapted to set a starting address of the first RDMA transfer request to a first address in the RDMA address range of the select media content.

6. The system of claim 5 wherein in order to generate the first RDMA transfer request, the data mover function is further adapted to set an ending address of the first RDMA transfer request to the starting address of the first RDMA transfer request plus a value determined based on the amount of storage available in the buffer.

7. The system of claim 3 wherein the first RDMA transfer request is for a first block of the RDMA address range determined based on the amount of storage available in the buffer, and in order to perform the at least one RDMA transfer, the data mover function is further adapted to:

generate a subsequent RDMA transfer request to transfer a subsequent block of the RDMA address range when sufficient storage becomes available in the buffer;

issue the subsequent RDMA transfer request to the RDMA enabled network interface, wherein data received in response to the subsequent RDMA transfer request is stored in the buffer.

8. The system of claim 7 wherein in order to perform the at least one RDMA transfer, the data mover function is further adapted to continue to generate subsequent RDMA transfer requests to transfer subsequent blocks of the RDMA address range when sufficient storage becomes available in the buffer and issue the subsequent RDMA transfer requests to the RDMA enabled network interface until transfer of the RDMA address range is complete.

9. The system of claim 1 further comprising:

a plurality of RDMA enabled buffer circuits including the RDMA enabled buffer circuit;

a plurality of playback buffer circuits including the playback buffer circuit; and

controllable switching circuitry adapted to interconnect the plurality of RDMA enabled buffer circuits to the plurality of playback buffer circuits in a desired manner.

10. The system of claim 9 further comprising a control function adapted to:

receive user input identifying the select media content;

assign the select media content to the RDMA enabled buffer circuit from the plurality of RDMA enabled buffer circuits;

identify the playback buffer circuit from the plurality of playback buffer circuits to be used for playback of the select media content; and

control the controllable switching circuitry to interconnect the RDMA enabled buffer circuit to the playback buffer circuit.

11. The system of claim 1 wherein the playback buffer circuit further comprises a clock generation function adapted to provide the playback clock.

12. The system of claim 11 wherein the clock generation function is controlled based on at least one of a group consisting of;

a status of the buffer of the playback buffer circuit and user input controlling playback of the select media content.

13. A method comprising:

performing at least one Remote Direct Memory Access (RDMA) transfer via an RDMA enabled network interface to transfer data stored in an RDMA address range for select media content from a storage unit of a centralized media content server to an RDMA enabled buffer circuit; and

transferring the data from the RDMA enabled buffer circuit to a playback buffer circuit based on a playback clock;

processing the data to provide the select media content in a format ready for playback; and

storing the data in a playback buffer to enable playback of the select media content from the playback buffer.

14. The method of claim 13 wherein performing the at least one RDMA transfer comprises:

generating a first RDMA transfer request based on an amount of storage available in a buffer of the RDMA enabled buffer circuit;

issuing the first RDMA transfer request via the RDMA enabled network interface;

receiving data in response to the first RDMA transfer request; and

storing the data received in response to the first RDMA transfer request in the buffer of the RDMA enabled buffer circuit.

15. The method of claim 14 wherein receiving the data in response to the first RDMA transfer request comprises:

receiving data in response to a plurality of RDMA transfer requests comprising the first RDMA transfer request issued by a plurality of RDMA enabled buffer circuits comprising the RDMA enabled buffer circuit;

comparing RDMA addresses of the data received in response to the plurality of RDMA transfer requests to RDMA addresses of the first RDMA transfer request to identify the data received in response to the first RDMA transfer request; and

triggering storage of the data received in response to the first RDMA transfer request in the buffer of the RDMA enabled buffer circuit.

16. The method of claim 14 wherein generating the first RDMA transfer request comprises setting a starting address of the first RDMA transfer request to a first address in the RDMA address range of the select media content.

17. The method of claim 14 wherein the first RDMA transfer request is for a first block of the RDMA address range determined based on the amount of storage available in the buffer, and performing the at least one RDMA transfer further comprises:

generating a subsequent RDMA transfer request to transfer a subsequent block of the RDMA address range when sufficient storage becomes available in the buffer of the RDMA enabled buffer circuit;

issuing the subsequent RDMA transfer request via the RDMA enabled network interface;

receiving data in response to the subsequent RDMA transfer request; and

storing the data received in response to the subsequent RDMA transfer request in the buffer of the RDMA enabled buffer circuit.

18. The method of claim 17 wherein performing the at least one RDMA transfer further comprises continuing to generate subsequent RDMA transfer requests to transfer subsequent blocks of the RDMA address range when sufficient storage becomes available in the buffer of the RDMA enabled buffer circuit and to issue the subsequent RDMA transfer requests to the RDMA enabled network interface until transfer of the RDMA address range is complete.

19. The method of claim 13 wherein the RDMA enabled buffer circuit is one of a plurality of RDMA enabled buffer circuits and the playback buffer circuit is one of a plurality of playback buffer circuits, and the method further comprises interconnecting the RDMA enabled buffer circuit to the playback buffer circuit via switching circuitry.