Cache optimization

• US 9,208,097 B2
• Filed: 11/12/2013
• Issued: 12/08/2015
• Est. Priority Date: 03/31/2008
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Richardson, David R., Scofield, Christopher L.
• Primary Examiner(s): DUDEK JR, EDWARD J
• Application Number:
  US14/078,274
• Publication Number:
  US 20140075109A1
• Time in Patent Office: 756 Days
• US Class Current: 1/1
• CPC Class Codes: G06F 12/0813 with a network or matrix configuration
• CPC Class Codes: G06F 12/0833 in combination with broadcast means (e.g. for invalidation or updating)
• CPC Class Codes: G06F 12/0866 for peripheral storage systems, e.g. disk cache
• CPC Class Codes: G06F 12/128 adapted to multidimensional cache systems, e.g. set-associative, multicache, multiset or multilevel
• CPC Class Codes: G06F 2212/62 Details of cache specific to multiprocessor cache arrangements
• CPC Class Codes: H04L 67/568 Storing data temporarily at an intermediate stage, e.g. caching

Abstract

A system and method for management and processing of resource requests at cache server computing devices is provided. Cache server computing devices segment content into an initialization fragment for storage in memory and one or more remaining fragments for storage in a media having higher latency than the memory. Upon receipt of a request for the content, a cache server computing device transmits the initialization fragment from the memory, retrieves the one or more remaining fragments, and transmits the one or more remaining fragments without retaining the one or more remaining fragments in the memory for subsequent processing.

Claims

1. A computer-implemented method comprising:

receiving, at a cache component, an object for storage;

segmenting the object into a first fragment for storage in memory, a second fragment for storage in a first media having higher latency than the memory, and a third fragment for storage in a second media having higher latency than the first media, wherein the size of the first fragment is based on a latency associated with retrieval of the second fragment, and wherein the size of the second fragment is based on a latency associated with retrieval of the third fragment;

receiving a request for the object at a cache component;

causing transmission of the first fragment from the memory;

causing transmission of the second fragment without retaining the second fragment in memory for subsequent processing; and

causing transmission of the third fragment without retaining the third fragment in the memory for subsequent processing.

2. A computer-implemented method comprising:

receiving a request for an object at a cache component;

causing transmission of a first fragment of the object from memory;

causing transmission of a second fragment of the object without retaining the second fragment in memory for subsequent processing; and

causing transmission of a third fragment of the object without retaining the third fragment in memory for subsequent processing.

3. The computer-implemented method of claim 2 further comprising retrieving the second fragment from local disk memory of the cache component.

4. The computer-implemented method of claim 2 further comprising retrieving the third fragment from disk memory of another cache component.

5. The computer-implemented method of claim 2 further comprising retrieving the third fragment from network-based memory.

6. The computer-implemented method of claim 2 further comprising retrieving the third fragment from an origin server.

7. The computer-implemented method of claim 2 further comprising collecting performance data associated with at least one of the retrieval of the second fragment or the transmission of the first fragment.

8. The computer-implemented method of claim 7 further comprising updating the size of the first fragment based on the collected performance data.

9. The computer-implemented method of claim 8, wherein updating the size of the first fragment comprises storing an incremental fragment in the memory to supplement the first fragment.

10. The computer-implemented method of claim 2 further comprising updating the size of the first fragment based on a determination of a latency associated with retrieval of the third fragment.

11. The computer-implemented method of claim 2 further comprising updating the size of the first fragment based on a frequency of a request for the object, such that a change in the size of the first fragment is based on a change in request frequency.

12. The computer-implemented method of claim 2 further comprising updating the size of the first fragment based on a frequency of a request for another object related to the requested object, such that a change in the size of the first fragment is based on a change in request frequency for the related object.

13. The computer-implemented method of claim 2 further comprising:

determining a new file size for the first fragment; and

storing an incremental fragment in the memory, wherein the first fragment and the increment fragment correspond to the new file size.

14. A system comprising:

a memory for storing first fragments of objects; and

one or more computing devices configured with specific executable instructions and operative to;

receive a request for an object;

cause transmission of a first fragment of the object from the memory;

cause transmission of a second fragment of the object without retaining the second fragment in memory for subsequent processing; and

cause transmission of a third fragment of the object without retaining the third fragment in memory for subsequent processing.

15. The system of claim 14, wherein the one or more computing devices is further operative to retrieve the second fragment from local disk memory of the one or more computing devices.

16. The system of claim 14, wherein the one or more computing devices is further operative to retrieve the third fragment from disk memory of a different computing device or cache component.

17. The system of claim 14, wherein the one or more computing devices is further operative to retrieve the third fragment from network-based memory.

18. The system of claim 14, wherein the one or more computing devices configured is further operative to retrieve the third fragment from an origin server.

19. The system of claim 14, wherein the one or more computing devices is further operative to collect performance data associated with at least one of the retrieval of the second fragment or the transmission of the first fragment.

20. The system of claim 19, wherein the one or more computing devices is further operative to update the size of the first fragment based on the collected performance data.

21. The system of claim 20, wherein updating the size of the first fragment comprises storing an incremental fragment in the memory to supplement the first fragment.

22. The system of claim 14, wherein the one or more computing devices is further operative to update the size of the first fragment based on a determination of a latency associated with retrieval of the third fragment.

23. The system of claim 14, wherein the one or more computing devices is further operative to update the size of the first fragment based on a frequency of a request for the object, such that a change in the size of the first fragment is based on a change in request frequency.

24. The system of claim 14, wherein the one or more computing devices is further operative to update the size of the first fragment based on a frequency of a request for another object related to the requested object, such that a change in the size of the first fragment is based on a change in request frequency for the related object.

25. The system of claim 14, wherein the one or more computing devices is further operative to:

determine a new file size for the first fragment; and

store an incremental fragment in the memory, wherein the first fragment and the increment fragment correspond to the new file size.