Reserved cache space in content delivery networks

• US 10,257,307 B1
• Filed: 12/11/2015
• Issued: 04/09/2019
• Est. Priority Date: 12/11/2015
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Baldwin, Matthew Graham
• Primary Examiner(s): Lo, Ann J
• Assistant Examiner(s): Khan, Masud K
• Application Number:
  US14/967,227
• Time in Patent Office: 1,215 Days
• CPC Class Codes: G06F 12/084 with a shared cache
• CPC Class Codes: G06F 12/0891 using clearing, invalidating or resetting means
• CPC Class Codes: G06F 12/0893 Caches characterised by their organisation or structure
• CPC Class Codes: G06F 2212/1016 Performance improvement
• CPC Class Codes: G06F 2212/154 Networked environment
• CPC Class Codes: H04L 67/5682 Policies or rules for updating, deleting or replacing the stored data

Abstract

Systems and methods are described to reserve cache space of points of presence (“POPs”) within a content delivery network (“CDN”). A provider may submit a request to the CDN to reserve cache space on one or more POPs for data objects designated by that provider. Thereafter, the CDN may implement a provider-specific cache on the POPs of the CDN, which is distinct from a shared cache space on the POPs. The provider may further select a custom cache eviction policy for the provider-specific cache, which causes the POPs to manage data objects within the provider-specific cache according to the custom cache eviction policy, independently of a cache eviction policy applied to the shared cache.

Claims

1. A content delivery system comprising:

a non-transitory data store implementing a shared data cache for storing data objects from multiple providers, the shared data cache including a plurality of data objects previously accessed by end users of the content delivery system and information indicating a most recent access time for individual data objects of the plurality of data objects;

a computing device comprising a processor and memory, the processor configured with specific computer-executable instructions that, when executed, cause the processor to;

receive a request to create a reserved cache on the content delivery system for data objects associated with a first provider of a plurality of providers;

implement a provider-specific cache, on the non-transitory data store, associated with a threshold size, wherein the provider-specific cache is separated from the shared data cache and is designated to store data objects associated with the first provider;

migrate one or more data objects associated with the first provider from the shared data cache to the provider-specific cache;

obtain, from a computing device of the first provider, provider-supplied code executable to implement a cache eviction policy by which data objects are selected for eviction from the provider-specific cache;

determine that a collective size of data objects within the provider-specific cache exceeds the threshold size;

select at least one data object for eviction from the provider-specific cache based at least in part on execution of the provider-supplied code; and

remove the at least one data object from the provider-specific cache.

2. The content delivery system of claim 1, wherein the specific computer-executable instructions, when executed, further cause the processor to:

receive requests from at least two providers to create a reserved cache on the content delivery system;

for individual providers of the at least two providers;

implement a provider-specific cache on the non-transitory data store for the individual provider, wherein the provider-specific cache is designated to store data objects associated with the individual provider, and is separate from the shared data cache and other provider-specific caches implemented on the non-transitory data store;

obtain, from a computing device of the individual provider, additional provider-supplied code executable to implement a cache eviction policy by which data objects are selected for eviction from the provider-specific cache implemented for the individual provider;

determine that a collective size of data objects within the provider-specific cache implemented for the individual provider exceeds the specified data size;

select at least one data object for eviction from the provider-specific cache implemented for the individual provider based at least in part on execution of the additional provider-supplied code; and

remove the at least one data object from the provider-specific cache implemented for the individual provider.

3. The content delivery system of claim 1, wherein the specific computer-executable instructions, when executed, further cause the processor to:

receive a request for a first data object associated with the first provider;

determine that the first data object is not stored within the provider-specific cache implemented for the first provider;

retrieve the first data object from a content source; and

place the first data object within the provider-specific cache implemented for the first provider.

4. The content delivery system of claim 1, wherein the information indicating a most recent access time for individual data objects of the plurality of data objects in the shared cache comprises the relative recency of access between the data objects.

5. The content delivery system of claim 1, wherein the specific computer-executable instructions, when executed, further cause the processor to order the data objects within the provider-specific cache according to the cache eviction policy.

6. The content delivery system of claim 1, wherein the cache eviction policy specifies an order of eviction of data objects within the provider-specific cache based on at least one of frequency of access, recency of access, and size of the data objects.

7. A computer-implemented method comprising:

implementing a shared data cache for storing data objects from multiple providers, the shared data cache identifying a plurality of data objects, stored within a non-transitory memory, that were previously accessed by end users;

receiving a request to create a provider-specific cache for data objects associated with a first provider;

generating the provider-specific cache on the non-transitory data store, wherein the provider-specific cache is at least partially different from the shared data cache and is designated to store data objects associated with the first provider;

receiving, from a computing device of the first provider, provider-supplied code executable to implement a cache eviction policy by which data objects are selected for eviction from the provider-specific cache;

determining that a collective size of data objects within the provider-specific cache exceeds a threshold size;

selecting at least one data object for eviction from the provider-specific cache based at least in part on execution of the provider-supplied code; and

removing the at least one data object from the provider-specific cache.

8. The computer-implemented method of claim 7 further comprising migrating one or more data objects from the shared data cache to the provider-specific cache.

9. The computer-implemented method of claim 7, wherein the request is from the first provider and specifies a desired size of the provider-specific cache.

10. The computer-implemented method of claim 7, wherein generating the provider-specific cache on the non-transitory data store comprising allocating a portion of the non-transitory data store with a size greater than a desired size specified by the first provider.

11. The computer-implemented method of claim 7, wherein the non-transitory data store comprises a plurality of data storage devices collectively configured to implement the non-transitory data store.

12. Non-transitory computer-readable media including instructions executable by a computing device to:

implement a shared data cache for storing data objects from multiple providers, the shared data cache identifying a plurality of data objects, stored within a non-transitory memory, that were previously accessed by end users;

obtain instructions to create a provider-specific cache for data objects associated with a first provider;

generate the provider-specific cache, wherein the provider-specific cache is at least partially different from the shared data cache and is designated to store data objects associated with the first provider;

obtain, from a computing device of the first provider, provider-supplied code executable to implement a cache eviction policy by which data objects are selected for eviction from the provider-specific cache;

determine that a collective size of data objects within the provider-specific cache exceeds a threshold size;

select at least one data object for eviction from the provider-specific cache based at least in part on execution of the provider-supplied code; and

remove the at least one data object from the provider-specific cache.

13. The non-transitory computer-readable media of claim 12, wherein the instructions are further executable by the computing device to cause migration of one or more data objects from the shared data cache to the provider-specific cache.

14. The non-transitory computer-readable media of claim 12, wherein the shared data cache and the provider-specific cache are implemented on a common non-transitory data store.

15. The non-transitory computer-readable media of claim 14, wherein the common non-transitory data store comprises a plurality of data storage devices collectively configured to implement the non-transitory data store.

16. The non-transitory computer-readable media of claim 14, wherein the instructions are executable by the computing device to generate the provider-specific cache at least partly by allocating a portion of the non-transitory data store with a size greater than a specified desired size for the provider-specific cache.