Method for caching and delivery of compressed content in a content delivery network

• US 20040010621A1
• Filed: 07/11/2002
• Published: 01/15/2004
• Est. Priority Date: 07/11/2002
• Status: Active Grant

• Current Assignee: Akamai Technologies, Inc.
• Original Assignee: Akamai Technologies, Inc.
• Inventors: Afergan, Michael M., Hong, Duke P., Rao, Satish Balusu, Schlossberg, Charisma
• Granted Patent: US 7,395,355 B2
• Time in Patent Office: Days
• US Class Current: 709/247
• CPC Class Codes: G06F 15/167 using a common memory, e.g. mailbox
• CPC Class Codes: G06F 16/9574 of access to content, e.g. by caching
• CPC Class Codes: H04L 12/66 Arrangements for connecting between networks having differing types of switching systems, e.g. gateways
• CPC Class Codes: H04L 45/20 Hop count for routing purposes, e.g. TTL
• CPC Class Codes: H04L 67/02 based on web technology, e.g. hypertext transfer protocol [HTTP]
• CPC Class Codes: H04L 67/568 Storing data temporarily at an intermediate stage, e.g. caching
• CPC Class Codes: H04L 69/04 Protocols for data compression, e.g. ROHC

Abstract

A content delivery network (CDN) edge server is provisioned to provide last mile acceleration of content to requesting end users. The CDN edge server fetches, compresses and caches content obtained from a content provider origin server, and serves that content in compressed form in response to receipt of an end user request for that content. It also provides “on-the-fly” compression of otherwise uncompressed content as such content is retrieved from cache and is delivered in response to receipt of an end user request for such content. A preferred compression routine is gzip, as most end user browsers support the capability to decompress files that are received in this format. The compression functionality preferably is enabled on the edge server using customer-specific metadata tags.

Claims

1. A server operative in a content delivery network, comprising:

a compression utility;

code responsive to a first metadata tag for applying the compression utility to given first content prior to caching; and

code responsive to a second metadata tag for applying the compression utility to given second content prior to serving.

2. The server as described in claim 1 wherein the compression utility is gzip.

3. The server as described in claim 1 wherein the given first content is content that has a given time-to-live (TTL) associated therewith that is greater than zero.

4. The server as described in claim 1 wherein the given first content is content that is unassociated with an ESI request.

5. The server as described in claim 1 wherein the given second content is content that has a given time-to-live (TTL) associated therewith that is zero.

6. The server as described in claim 1 wherein the given second content is content that is associated with an ESI request.

7. The server as described in claim 1 wherein the code is executable in a processor.

8. In a content delivery network (CDN) edge server having a processor, a cache, an HTTP server-side request handling routine and an HTTP client-side request handling routine, the improvement comprising:

a first compression routine associated with the server-side request handling routine;

a second compression routine associated with the client-side request handling routine; and

a metadata routine (a) responsive to a first metadata tag associated with a given first piece of content for applying the first compression routine to the given first piece of content, and (b) responsive to a second metadata tag associated with a given second piece of content for applying the second compression routine to the given second piece of content.

9. In the CDN edge server as described in claim 8 wherein the given first piece of content is stored in the cache following compression by the first compression routine.

10. In the CDN edge server as described in claim 9 wherein the HTTP client side request handling routine retrieves the given first piece of content from the cache and serves said content in compressed form in response to an HTTP request for the given first piece of content.

11. In the CDN edge server as described in claim 10 wherein the client side HTTP request handling routine retrieves the given second piece of content from the cache and serves said content in response to an HTTP request for the given second piece of content following application of the second compression routine.

12. In the CDN edge server as described in claim 8 wherein the first and second compression routines are gzip.

13. A content delivery method operative at an edge server to which an end user has been directed by a CDN request routing mechanism, the edge server having a cache, comprising the unordered steps of:

upon receipt of a request for given first content that cannot be serviced at the edge server, fetching the given first content from an origin server;

determining whether a first metadata tag is associated with the given first content;

if the first metadata tag is associated with the given first content, compressing the given first content prior to caching in the edge server;

upon receipt of a request for given second content cached at the edge server, fetching the given second content from cache;

determining whether a second metadata tag is associated with the given second content; and

if the second metadata tag is, associated with the given second content, compressing the given second content as it is being served from the edge server.

14. The content delivery method as described in claim 13 further including the step of serving the given first content in compressed form upon receipt of a new request for the given first content.

15. The content delivery method as described in claim 13 wherein a given content provider is billed for delivery of its associated content as a function of a size of the content in uncompressed form.

16. The content delivery method as described in claim 13 wherein the first given content is compressed using gzip.

17. The content delivery method as described in claim 13 wherein the second given content is compressed using gzip.

18. A content delivery method operative at an edge server to which an end user has been directed by a CDN request routing mechanism, the edge server having a cache, comprising:

upon receipt of a request for given content from the end user that cannot be serviced at the edge server, fetching the given content from an origin server;

determining whether the given content should be stored in the cache in an uncompressed or compressed form by evaluating a function trading off anticipated storage time in the cache versus processing overhead required to perform the compression; and

selectively storing the given content either uncompressed or compressed based on the determination.

19. The content delivery method as described in claim 18 wherein the determining step is performed upon a given condition.

20. The content delivery method as described in claim 19 wherein the given condition is a determination based on evaluating properties of a connection between the edge server and a client machine.

21. A content delivery method operative at an edge server to which an end user has been directed by a CDN request routing mechanism, the edge server having a cache, comprising:

upon receipt of a request for given content from the end, fetching an uncompressed form of the given content from the cache; and

selectively compressing the given content as the given content is being delivered to the end user in response to the request as a function of given metadata.

22. The content delivery method as described in claim 21 wherein the given content is stored in uncompressed form in the cache as a function of given metadata.

23. The content delivery method as described in claim 21 wherein a given content provider is billed for delivery of the given content delivered to the end user as a function of a size of the given content in the uncompressed form irrespective of a number of bytes delivered to the end user.

24. A content delivery method operative at an edge server to which an end user has been directed by a CDN request routing mechanism, the edge server having a cache, comprising:

upon receipt of a request for given content from the end user that cannot be serviced at the edge server, fetching the given content from an origin server;

determining whether the given content should be served from the cache in an uncompressed or compressed form by evaluating a function trading off anticipated performance benefit, anticipated storage time in the cache, and processing overhead required to perform the compression; and

selectively serving the given content either uncompressed or compressed based on the determination.

25. A content delivery method operative at an edge server to which end users are directed by a CDN request routing mechanism, the edge server having a cache, comprising:

with respect to a first request for given content, making a first determination as to whether the given content should be stored in the cache in an uncompressed or compressed form, or whether the given content should be served from the cache in an uncompressed or compressed form; and

with respect to a second request for the given content, making a determination, independent of the first determination and/or as a byproduct of the first determination, as to whether the given content should be stored in the cache in an uncompressed or compressed form, or whether the given content should be served from the cache in an uncompressed or compressed form.

26. A managed service provided on behalf of an origin server at which a content provider publishes given content, comprising:

a server, managed by an entity other than the content provider, for providing the given content to a requesting client, the server comprising;

a cache;

a compression routine; and

a mechanism for selectively storing or serving the given content in compressed form.