Opportunistic block transmission with time constraints

• US 8,024,523 B2
• Filed: 04/04/2008
• Issued: 09/20/2011
• Est. Priority Date: 11/07/2007
• Status: Active Grant

• Current Assignee: Numecent Holdings Incorporated
• Original Assignee: Endeavors Technologies, Inc. (DivestCap Management, Inc.)
• Inventors: de Vries, Jeffrey, Hitomi, Arthur Shingen
• Primary Examiner(s): Doan; Duc T
• Application Number:
  US12/062,789
• Publication Number:
  US 20090119458A1
• Time in Patent Office: 1,264 Days
• Field of Search: None
• US Class Current: 711/118
• CPC Class Codes: G06F 12/0802 Addressing of a memory level in which the access to the desired data or data block requires associative addressing means, e.g. caches
• CPC Class Codes: G06F 12/0862 with prefetch
• CPC Class Codes: G06F 12/0864 using pseudo-associative means, e.g. set-associative or hashing
• CPC Class Codes: G06F 13/1673 using buffers
• CPC Class Codes: H04L 41/0896 Bandwidth or capacity management, i.e. automatically increasing or decreasing capacities flow or congestion control using dynamic resource allocation, e.g. in-call renegotiation, H04L47/76
• CPC Class Codes: H04L 65/612 for unicast
• CPC Class Codes: H04L 65/70 Media network packetisation
• CPC Class Codes: H04L 67/5681 Pre-fetching or pre-delivering data based on network characteristics

Abstract

A technique for determining a data window size allows a set of predicted blocks to be transmitted along with requested blocks. A stream enabled application executing in a virtual execution environment may use the blocks when needed.

Claims

1. A system comprising:

a virtual execution environment;

a block granularity caching engine;

a cache;

wherein, in operation;

a process associated with a stream-enabled application is executed in the virtual execution environment;

the virtual execution environment intercepts a resource request for a resource from the process executing in the virtual execution environment;

the virtual execution environment identifies one or more blocks that are associated with the resource;

the virtual execution environment makes a block request requesting a block associated with the resource;

the block granularity engine makes the block request available to a streaming server so as to prefetch a predictively streamed block based on the block request wherein the predictively streamed block is ordered in a priority queue by probability, based at least in part on the requested block, that the predictively streamed block will be requested;

the block granularity engine receives blocks of the stream-enabled application, including the predictively streamed block and the requested block, within an interactivity threshold;

the block granularity engine checks the cache for blocks to satisfy the block request;

the block granularity engine provides the predictively streamed block to the virtual execution environment if the predictively streamed block is found in the cache;

the virtual execution environment satisfies the resource request of the process using the predictively streamed block.

2. The system of claim 1, wherein the requested block has not been predictively streamed and stored in the cache, further comprising:

an interface, wherein, in operation, the interface sends the block request to a streaming system.

3. The system of claim 1 further comprising:

an interface, wherein, in operation, the interface receives the predictively streamed block from a streaming system.

4. The system of claim 1 further comprising:

a network data engine;

a stream enabler;

a streaming server;

a network coupling the streaming server to the block granularity caching engine;

wherein, in operation,

the stream enabler that breaks deliverables into blocks of a size that facilitates providing the requested block and the predictively streamed block within the interactivity threshold;

the network data engine provides information useful for determining a data window using throughput and a latency of the network;

the streaming server aggregates the requested and predicted blocks into an output buffer wherein the predicted blocks include the predictively streamed block.

5. A method comprising:

executing a process associated with a stream-enabled application that provides a first request requesting a block for resources, wherein a streaming server provides a first predictively streamed block using a priority queue of predictively streamed blocks ordered by probability based at least in part on the first request, wherein the first predictively streamed block is first in the priority queue;

receiving, within a data window, one or more blocks including resources used to satisfy the first request for resources as well as the first predictively streamed block;

receiving the first predictively streamed block and the requested block in an amount of time that is less than or equal to an interactivity threshold;

storing the first predictively streamed block in a cache;

providing a second request for resources;

checking the cache to find the first predictively streamed block to satisfy the second request for resources;

at least partially satisfying the second request for resources using the first predictively streamed block in the cache.

6. The method of claim 5 further comprising transmitting network information useful for determining a network latency or throughput used in determining a data window size.

7. A system comprising:

blocks of a stream-enabled application embodied in a computer readable medium;

an output buffer, wherein, in operation, the output buffer stores one or more of the blocks of the stream enabled application;

a data window engine, wherein, in operation, the data window engine determines a data window size using an interactivity threshold to limit predicted block aggregation;

a predicted block aggregation engine, wherein, in operation, the predicted block aggregation engine orders predicted blocks by probability, based on a requested block, in a priority queue and stores a set of predicted blocks from the front of the priority queue in the output buffer until or before the size of the output buffer reaches the data window size;

an interface, wherein, in operation, the interface sends the one or more blocks, a requested block and the set of predicted blocks in the output buffer.

8. The system of claim 7, further comprising:

a logical block probability table embodied in a computer non-transitory readable medium, wherein, in operation, the block prediction engine populates the logical block probability table with blocks for which the future requests are predicted, wherein the predicted blocks have a higher probability for being requested than other predicted blocks in the logical block probability table.

9. The system of claim 7 further comprising a network data engine, wherein the network data engine calculates a throughput;

and the data window engine uses the throughput to determine the data window size.

10. The system of claim 7 wherein the data window engine calculates a latency and the data window engine uses the latency to determine the data window size.

11. A method comprising:

predicting one or more blocks that are associated with a request requesting a block for resources of a stream-enabled application;

ordering in a priority queue the one or more predictive blocks based at least in part on the requested block;

adding a set of predicted blocks from the front of the priority queue to an output buffer until the output buffer has reached a data window size;

continuously updating the data window size using a continuously updated value for latency;

transmitting within an interactivity threshold the set of predicted blocks and the requested block in the output buffer.

12. The method of claim 11 further comprising continuously calculating a data window size by continuously recalculating latency and throughput.

13. The method of claim 11 further comprising determining the data window size using an interactivity threshold, a network latency, and a network throughput.

14. The method of claim 11 further comprising continuously recalculating the data window size by regularly recalculating latency by pinging a streaming playback device.

15. The method of claim 11 further comprising reducing the data window size to account for an increase in latency found by pinging a streaming playback device.

16. A system comprising:

a streaming playback device;

a streaming server;

wherein, in operation, the streaming server;

adds blocks of the stream-enabled application to an output buffer;

predicts one or more blocks that will be needed by the streaming playback device based on a request requesting a block;

orders the one or more blocks, by probability based on the requested block, in a priority queue;

adds a set of predicted blocks from the front of the priority queue to the output buffer, up to a limit of a data window size set in accordance with an interactivity threshold limiting the amount of time for transmission of blocks to preserve a quality of execution of the stream-enabled application;

provides the contents of the output buffer, including the requested block and the set of predicted blocks, to the streaming playback device.

17. The system of claim 16 wherein one or more blocks are streamed based on priority and block priority is adjusted continuously based on blocks requested.

18. The system of claim 16 wherein the streaming playback device receives predictively streamed blocks of a stream enabled application in addition to requested blocks.

19. The system of claim 16 wherein the streaming server includes a data window engine, and the data window engine sets the data window size based on the interactivity threshold, a network latency, and a network throughput.

20. The system of claim 16 wherein the streaming playback device includes a stream-enabled application executing in a virtual environment, and the stream enabled application requests a resource that is satisfied from a predictively streamed block stored in a cache.

21. The system of claim 16 wherein the streaming playback device includes a resource requesting engine and a cache, and the resource requesting engine translates a resource request into a plurality of block requests and one or more block requests is canceled by satisfying the request using predictively streamed blocks found in a cache.