Rules-based transaction prefetching using connection end-point proxies

• US 20060212524A1
• Filed: 11/14/2005
• Published: 09/21/2006
• Est. Priority Date: 03/15/2005
• Status: Active Grant

• Current Assignee: Riverbed Technology, LLC (Riverbed Technology Incorporated)
• Original Assignee: Riverbed Technology Incorporated
• Inventors: Wu, David Tze-Si, Keswani, Vivasvat, Larsen, Case
• Granted Patent: US 7,853,699 B2
• Time in Patent Office: Days
• US Class Current: 709/206
• CPC Class Codes: H04L 67/10 in which an application is distributed across nodes in the network software deployment G06F8/60; multiprogramming arrangements G06F9/46
• CPC Class Codes: H04L 67/1095 Replication or mirroring of data, e.g. scheduling or transport for data synchronisation between network nodes
• CPC Class Codes: H04L 67/568 Storing data temporarily at an intermediate stage, e.g. caching

Abstract

Network proxies reduce server latency in response to series of requests from client applications. Network proxies intercept messages clients and a server. Intercepted client requests are compared with rules. When client requests match a rule, additional request messages are forwarded to the server on behalf of a client application. In response to the additional request messages, the server provides corresponding response messages. A network proxy intercepts and caches the response messages. Subsequent client requests are intercepted by the network application proxy and compared with the cached messages. If a cached response message corresponds with a client request message, the response message is returned to the client application immediately instead of re-requesting the same information from the server. A server-side network proxy can compare client requests with the rules and send additional request messages. The corresponding response messages can be forwarded to a client-side network proxy for caching.

Claims

1. A method for accelerating a client-server transaction, the method comprising:

(a) receiving a first message from a client application;

(b) comparing the first message with a set of rules;

(c) forwarding the first message and at least one additional message to a server application in response to the first message matching at least one of the set of rules;

(d) receiving from the server application at least one response message corresponding with the additional message;

(e) storing in a message cache the response message corresponding with the additional message;

(f) receiving a second message from the client application;

(g) determining if the second message is similar to the additional message; and

(h) forwarding the response message stored in the message cache to the client application in response to the second message being similar to the additional message.

2. The method of claim 1, wherein (a), (b), (c), and (d) are performed by a server-side network proxy and (e), (f), (g), and (h) are performed by a client-side network proxy.

3. The method of claim 2, wherein (e) further comprises:

sending the at least one response message from the server-side network proxy to the client-side network proxy.

4. The method of claim 3, wherein sending the response message further comprises wrapping the response message with additional information adapted to indicate to the client-side network proxy that the response message is to be stored in the message cache.

5. The method of claim 4, wherein the additional information identifies the additional message corresponding with the response message.

6. The method of claim 3, further comprising:

in response to (e), determining if a cache limit has been reached;

sending, by the client-side proxy, a throttling message to the server-side proxy in response to a determination that the cache limit has been reached; and

suspending the sending of at least one response message from the server-side network proxy to the client-side network proxy in response to the server-side network proxy receiving the throttling message.

7. The method of claim 6, further comprising, in response to (h):

removing the forwarded response message from the response cache;

determining if the cache storage limit has been reached;

sending by the client-side proxy, an un-throttling message to the server-side proxy in response to a determination the cache storage limit has not been reached; and

resuming the sending of at least one response message from the server-side network proxy to the client-side network proxy in response to the server-side network proxy receiving the un-throttling message.

8. The method of claim 1, further comprising:

generating a preacknowledgment message corresponding with the first message; and

forwarding the preacknowledgement message to the client application.

9. The method of claim 8, further comprising:

receiving an acknowledgment message from the server application, wherein the acknowledment message is a response to the first message;

analyzing a status code of the acknowledgment message;

discarding the acknowledgment message in response to the status code indicating a success condition; and

forwarding a response message indicating a failure condition to the client application following the receipt of the second message from the client application in response to the status code of the acknowledment message indicating a failure condition.

10. A method for accelerating a client-server transaction, the method comprising:

receiving a message from a client application directed to a server application;

determining if the message is consistent with a previous message sent to the server application;

sending the message to the server in response to a determination that the message is consistent with the previous message sent to the server application;

comparing the message with a set of rules;

generating at least one additional message in response to the message matching at least one rule; and

forwarding the additional message to the server application.

11. The method of claim 10, wherein the previous message was generated by a server-side proxy in response to at least one additional previous message matching the set of rules.

12. The method of claim 10, further comprising:

determining if the message is inconsistent with at least a portion of a results cache storing a results message corresponding with the previous message sent to the server application in response to a determination that the message is inconsistent with previous messages sent to the server application; and

invalidating the portion of the results cache in response to a determination that the message is inconsistent with the portion of a results cache.

13. The method of claim 10, further comprising:

receiving a second message from the server application;

determining if the second message is a response to the additional message; and

wrapping the second message to indicate that the second message is to be stored in a results cache included in a network proxy associated with the client application and forwarding the wrapped second message to the network proxy associated with the client application in response to a determination that the second message is a response to the additional message.

14. The method of claim 13, further comprising:

determining if the second message is a response to the message from the client application; and

forwarding the second message to the client application in response to a determination that the second message is a response to the message from the client application.

15. The method of claim 13, further comprising:

determining if the second message invalidates at least a portion of the results cache included in the network proxy associated with the client application; and

sending a cache invalidation message to the network proxy specifying that the portion of the results cache should be invalidated.

16. A method for accelerating a client-server transaction, the method comprising:

receiving a message from a client application directed to a server application;

determining if the message corresponds with data in a results cache;

sending the message to the server application in response to a determination that the message does not correspond with the data in the results cache; and

sending a response message to the client application in response to a determination that the message does correspond with at least a portion of the data in the results cache, wherein the response message includes at least a portion of the data from the results cache.

17. The method of claim 16, further comprising:

generating a preacknowledgment message and forwarding the preacknowledgment message to the client application in response to the determination that the message does not correspond with the data in the results cache.

18. The method of claim 17, further comprising:

receiving an acknowledgment message from the server application, wherein the acknowledment message is a response to the message from the client application;

analyzing a status code of the acknowledgment message;

discarding the acknowledgment message in response to the status code indicating a success condition;

receiving a second message from the client application directed to the server application; and

forwarding a response message indicating a failure condition to the client application following the receipt of the second message from the client application in response to the status code of the acknowledment message indicating a failure condition.

19. The method of claim 16, further comprising:

receiving a second message from a server-side proxy;

determining if the second message includes additional data prefetched by the server-side proxy or a response to the message from the client application;

storing the additional data in the results cache in response to a determination that the additional data was prefetched by the server-side proxy; and

sending the second message to the client application in response to a determination that the additional data is a response to the message from the client application.

20. The method of claim 16, further comprising:

determining if the second message is a cache invalidation message; and

invalidating at least a portion of the results cache in response to a determination that the second message is a cache invalidation message.

21. The method of claim 19, further comprising:

determining a capacity for the results cache in response to receiving the second message;

sending a throttling message to the server-side proxy in response to a determination that the results cache is at full capacity.

22. The method of claim 21, further comprising:

removing at least a portion of the data from the results cache in response to sending the response message including at least a portion of the data from the results cache to the client application; and

sending an unthrottling message to the server-side proxy in response to removing at least a portion of the data from the results cache.

23. A network proxy adapted to accelerate a client-server transaction, the network proxy comprising:

a first network interface adapted to exchange messages with a client application;

a second network interface adapted to exchange messages with a server application;

a rule store adapted to store at least one rule, wherein the rule includes a rule element specifying an attribute of a set of at least one message from the client application and an action element specifying at least a portion of an additional message associated with the set of at least one message; and

a match engine adapted to compare a message received from the client application via the first network interface with the rule element of the rule store, to generate the additional message from the action element in response to the message from the client application matching the attribute of the rule element, and to send the additional message to the server application.

24. The network proxy of claim 23, further comprising:

an invalidation checker adapted to determine if the second message invalidates at least a portion of the results cache included in a network proxy associated with the client application and to send a cache invalidation message to the network proxy associated with the client application specifying that the portion of the results cache should be invalidated.

25. The network proxy of claim 23, further comprising logic adapted to:

determine if a second message received from the server application is a response to the additional message; and

wrap the second message to indicate that the second message is to be stored in a results cache included in a network proxy associated with the client application and forward the wrapped second message to the network proxy associated with the client application in response to a determination that the second message is a response to the additional message.

26. The network proxy of claim 25, further comprising logic adapted to:

determine if the second message is a response to a message from the client application; and

forward the second message to the client application in response to a determination that the second message is a response to the message received from the client application.

27. A network proxy adapted to accelerate a client-server transaction, the network proxy comprising:

a first network interface adapted to exchange messages with a client application;

a second network interface adapted to exchange messages with a server application;

a results cache adapted to store data including response messages prefetched on behalf of the client application; and

logic adapted to;

determine if a message received from a client application and directed to a server application corresponds with data in a results cache;

send the message to the server application in response to a determination that the message does not correspond with the data in the results cache; and

send the response message stored in the results cache to the client application in response to a determination that the message does correspond with at least a portion of the data in the results cache.

28. The network proxy of claim 27, further comprising logic adapted to:

receive a second message from a server-side proxy;

determine if the second message includes additional data prefetched by the server-side proxy or a response to a previous message from the client application;

store the additional data in the results cache in response to a determination that the additional data was prefetched by the server-side proxy; and

send the second message to the client application in response to a determination that the additional data is a response to the previous message from the client application.

29. The network proxy of claim 27, further comprising logic adapted to:

generate a preacknowledgrnent message and forward the preacknowledgment message to the client application in response to the determination that the message received from the client application does not correspond with the data in the results cache.

30. The network proxy of claim 29, further comprising logic adapted to:

receive an acknowledgment message from the server application, wherein the acknowledgment message is a response to the message received from the client application;

analyze a status code of the acknowledgment message;

discard the acknowledgment message in response to the status code indicating a success condition; and

forward a response message indicating a failure condition to the client application following the receipt of a subsequent message from the client application in response to the status code of the acknowledment message indicating a failure condition.