CONTENT DISTRIBUTION SYSTEM CACHE MANAGEMENT

• US 20170026286A1
• Filed: 07/20/2015
• Published: 01/26/2017
• Est. Priority Date: 07/20/2015
• Status: Active Grant

• Current Assignee: Cisco Technology, Inc. (Cisco Systems, Inc.)
• Original Assignee: Cisco Technology, Inc. (Cisco Systems, Inc.)
• Inventors: Surcouf, Andre, Townsley, William Mark, Previdi, Stefano Benedetto, Vyncke, Eric
• Granted Patent: US 10,462,055 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: H04L 45/306 Route determination based on the nature of the carried application
• CPC Class Codes: H04L 45/742 Route cache; Operation thereof
• CPC Class Codes: H04L 45/745 Address table lookup; Address filtering
• 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

Abstract

Content distribution system cache management may be provided. First, a sync packet may be received by a cache server from a first server. The sync packet may include a list indicating a cache server where a chunk is to be stored and the address for the chunk. Next, an address for the chunk may be obtained by the cache server by parsing the sync packet. The cache server may then determine that the chunk is not stored on the cache server by using the address for the chunk. Next, in response to determining that the chunk is not stored on the cache server, a connection may be opened between the first server and the cache server. The cache server may then receive the chunk over the connection and cache the chunk on the cache server.

Claims

1. A method comprising:

receiving, by a cache server, a sync packet from a first server, the sync packet including a list indicating a cache server where a chunk is to be stored and the address for the chunk;

obtaining, by the cache server, an address for the chunk by parsing the sync packet;

determining, by the cache server, that the chunk is not stored on the cache server, wherein determining that the chunk is not stored on the cache server comprises using the address for the chunk;

opening, in response to determining that the chunk is not stored on the cache server, a connection between the first server and the cache server;

receiving, by the cache server, the chunk over the connection; and

caching, by the cache server, the chunk on the cache server.

2. The method of claim 1, wherein the sync packet indicates the first server as a source for the chunk and the cache server as a destination for the chunk.

3. The method of claim 1, wherein receiving the sync packet comprises receiving the sync packet from the first server through a router that knows the route between the first server and the cache server.

4. The method of claim 1, wherein determining that the chunk is not stored on the cache server comprises determining that there is no match for the address for the chunk in a lookup table located on the cache server.

5. The method of claim 1, wherein opening the connection between the first server and the cache server comprises:

creating, by the cache server, a sync/acknowledge packet;

sending, by the cache server, the sync/acknowledge packet to the first server;

receiving, by the cache server, an acknowledge packet from the first server, said acknowledge packet being created by said first server in response to receiving the sync/acknowledge packet; and

opening, in response to the cache server receiving the acknowledge packet, a socket between the first server and the cache server.

6. The method of claim 5, wherein receiving, by the cache server, the chunk over the connection comprises:

reading, by the cache server, data corresponding to the chunk written by the first server to the socket.

7. The method of claim 6, further comprising closing the socket when the chunk has been completely cached on the cache server.

8. An apparatus comprising:

a memory storage; and

a processing unit coupled to the memory storage, wherein the processing unit is operative to;

receive a sync packet from a first server, the sync packet including a list indicating an address for a chunk;

obtain the address for the chunk by parsing the sync packet;

determine that the chunk is not stored on the memory storage, wherein determining that the chunk is not stored on the memory storage comprises using the address for the chunk;

open, in response to determining that the chunk is not stored on the memory storage, a connection between the first server and the cache server;

receive the chunk over the connection; and

cache the chunk on the memory storage.

9. The apparatus of claim 8, wherein the processing unit is operative to receive the sync packet from the first server through a router that knows the route between the first server and the cache server.

10. The apparatus of claim 8, wherein the processing unit being operative to determine that the chunk is not stored on the cache server comprises the processing unit being operative to determine that there is no match for the address for the chunk in a lookup table located on the memory storage.

11. The apparatus of claim 8, wherein the processing unit being operative to open the connection between the first server and the cache server comprises the processing unit being operative to:

create a sync/acknowledge packet;

send the sync/acknowledge packet to the first server;

receive an acknowledge packet from the first server; and

open, in response to receiving the acknowledge packet, a socket between the first server and the apparatus.

12. The apparatus of claim 11, wherein the processing unit being operative to receive the chunk over the connection comprises the processing unit being operative to read data corresponding to the chunk from the socket, the data being written to the socket by the first server.

13. The apparatus of claim 12, further comprising the processing unit being operative to close the socket when the chunk has been completely cached on the memory storage.

14. A method comprising:

creating, by a source server, a first segment routing packet, the first segment routing packet including a list indicating a first cache server, a second cache server, and a third cache server where a chunk is to be stored;

receiving, by the first cache server, the first segment routing packet from the source server;

obtaining, by the first cache server, the address for the chunk by parsing the first segment routing packet;

determining, by the first cache server, that the chunk is not stored on the first cache server, wherein determining that the chunk is not stored on the first cache server comprises using the address for the chunk;

opening, in response to determining that the chunk is not stored on the first cache server, a first connection between the source server and the first cache server;

receiving, by the first cache server, the chunk over the first connection;

caching, by the first cache server, the chunk on the first cache server;

creating, by the first cache server, a second segment routing packet, the second segment routing packet including the list indicating the first cache server, the second cache server, and the third cache server where the chunk is to be stored;

receiving, by the second cache server, the second segment routing packet from the first cache server;

obtaining, by the second cache server, the address for the chunk by parsing the second segment routing packet; and

determining, by the second cache server, that the chunk is already stored on the second cache server, wherein determining that the chunk is already stored on the second cache server comprises using the address for the chunk.

15. The method of claim 14, further comprising:

creating, by the second cache server, a third segment routing packet, the third segment routing packet including the list indicating the first cache server, the second cache server, and the third cache server where the chunk is to be stored;

receiving, by the third cache server, the third segment routing packet from the second cache server;

obtaining, by the third cache server, the address for the chunk by parsing the third segment routing packet;

determining, by the third cache server, that the chunk is not stored on the third cache server, wherein determining that the chunk is not stored on the third cache server comprises using the address for the chunk;

opening, in response to determining that the chunk is not stored on the third cache server, a second connection between the first cache server and the third cache server;

receiving, by the third cache server, the chunk over the first connection; and

caching, by the third cache server, the chunk on the third cache server.

16. The method of claim 14, wherein creating the first segment routing packet comprises creating the first segment routing packet wherein the first segment routing packet indicates the source server as a source for the chunk and the first cache server, the second cache server, and the third cache server as a destination for the chunk.

17. The method of claim 14, wherein determining that the chunk is not stored on the first cache server comprises determining that there is no match for the address for the chunk in a lookup table located on the first cache server.

18. The method of claim 14, wherein opening the first connection between the source server and the first cache server comprises:

creating, by the first cache server, a sync/acknowledge packet;

sending, by the first cache server, the sync/acknowledge packet to the source server;

receiving, by the source server, the sync/acknowledge packet;

creating, by the source server in response to receiving the sync/acknowledge packet, an acknowledge packet sending, by the source server, the acknowledge packet to the first cache server;

receiving, by the first cache server, the acknowledge packet; and

opening, in response to the first cache server receiving the acknowledge packet, a socket between the source server and the first cache server.

19. The method of claim 18, wherein receiving, by the first cache server, the chunk over the first connection comprises:

writing, by the source server, data corresponding to the chunk in the socket; and

reading, by the first cache server, the data corresponding to the chunk from the socket.

20. The method of claim 19, further comprising closing the socket when the chunk has been completely cached on the first cache server.