Method and apparatus for pre-packetized caching for network servers

• US 20060112185A1
• Filed: 11/22/2004
• Published: 05/25/2006
• Est. Priority Date: 11/22/2004
• Status: Active Grant

• Current Assignee: RPX Corporation
• Original Assignee: Alcatel-Lucent USA, Inc. (Nokia Corporation)
• Inventors: van Bemmel, Jeroen
• Granted Patent: US 7,711,799 B2
• Time in Patent Office: Days
• US Class Current: 709/238
• CPC Class Codes: H04L 67/02 based on web technology, e.g. hypertext transfer protocol [HTTP]
• CPC Class Codes: H04L 67/5682 Policies or rules for updating, deleting or replacing the stored data
• CPC Class Codes: H04L 69/16 Implementation or adaptation of Internet protocol [IP], of transmission control protocol [TCP] or of user datagram protocol [UDP]
• CPC Class Codes: H04L 69/163 In-band adaptation of TCP data exchange; In-band control procedures
• CPC Class Codes: H04L 69/166 IP fragmentation; TCP segmentation
• CPC Class Codes: H04L 69/32 Architecture of open systems interconnection [OSI] 7-layer type protocol stacks, e.g. the interfaces between the data link level and the physical level
• CPC Class Codes: H04L 69/329 in the application layer [OSI layer 7]

Abstract

A method and apparatus for caching client node requested data stored on a network server is disclosed. The method and apparatus comprise caching server responses at the pre-packetized level thereby decreasing response time by minimizing packet processing overhead, reducing disk file reading and reducing copying of memory from disk buffers to network interfaces.

Claims

1. A method for caching server response data, comprising:

retrieving data from a server;

separating the retrieved data into a plurality of response packets containing static and dynamic content;

setting dynamic fields of at least one response packet to a predetermined fixed value;

caching the dynamic fields and static fields of the at least one response packet to a memory buffer; and

feeding the resulting at least one response packet from the memory buffer to a network interface for transmission over a communication network.

2. The method of claim 1, wherein the predetermined fixed value for the dynamic fields is set to zero.

3. The method of claim 1, further including setting an error detection value in a field of the at least one response packet.

4. The method of claim 3, wherein the error detection value is a TCP checksum value.

5. The method of claim 4, wherein the dynamic fields are selected from a group comprising:

an Ethernet destination MAC address;

an IP destination address;

a TCP destination port;

a TCP sequence number;

TCP headers from the client node request; and

a TCP checksum.

6. The method of claim 5, in response to a second client node request, further comprising:

updating the dynamic fields to a second predetermined fixed value;

adjusting the TCP checksum incrementally;

caching the updated dynamic fields value and incrementally adjusted TCP checksum in the memory buffer; and

feeding the updated at least one response packet cached to the memory buffer to a network interface for transmission over the communication network.

7. The method of claim 6, wherein, if the dynamic fields include the TCP headers, the method further comprising caching N copies of the at least one response packet, where N is an integer equal to the number of particular TCP headers.

8. An apparatus for caching server response data, comprising:

a server comprising a memory buffer for storing pre-packetized data for transmission to at least one client node in response to a client request, wherein the pre-packetized data comprises static fields, and dynamic fields set to a predetermined fixed value; and

a network interface card for connecting the server to a communication network and for transmitting the at least one cached packetized data from the memory buffer of the server to the at least one client node.

9. The information processing apparatus of claim 8, wherein the memory buffer is aligned to suit the processor architecture.

10. The information processing apparatus of claim 8, wherein the memory buffer is suitable for direct transmission to the network interface card.

11. A computer readable medium having computer-executable instructions stored thereon, the computer-executable instructions, when executed by a computer, causing the computer to perform a method for caching at least one response packet on a server, comprising:

providing a plurality of client nodes coupled via a plurality of network links to the server;

retrieving data, to include in the at least one response packet, from a memory database of the server, the at least one response packet including static and dynamic fields;

setting the dynamic fields of the response packet to a predetermined fixed value; and

caching the dynamic and static fields of the resulting at least one response packet in a memory buffer of the server.

12. The computer readable medium of claim 11, wherein the predetermined fixed value for the dynamic fields is set to zero.

13. The computer readable medium of claim 11, further including setting an error detection value in a field of the at least one response packet.

14. The method of claim 13, wherein the error detection value is a TCP checksum value.

15. The computer readable medium of claim 11, wherein the dynamic fields are selected from a group comprising:

an Ethernet destination MAC address;

an IP destination address;

a TCP destination port;

a TCP sequence number;

TCP headers from the client request; and

a TCP checksum.

16. The computer readable medium of claim 15, in response to a second client node request, the method further comprising:

updating the dynamic fields to a second predetermined fixed value;

adjusting the TCP checksum incrementally;

caching the updated dynamic fields value and incrementally adjusted TCP checksum in the memory buffer; and

feeding the updated at least one response packet cached to the memory buffer to a network interface for transmission over the communication network.

17. The computer readable medium of claim 11, wherein, if the dynamic fields include the TCP headers, the method further comprising caching N copies of the at least one response packet, where N is an integer equal to the number of TCP headers.

18. A method for caching server response data, comprising:

means for retrieving data from a server;

means for separating the retrieved data into a plurality of response packets containing static and dynamic content;

means for setting dynamic fields of at least one response packet to a predetermined fixed value;

means for caching the dynamic fields and static fields of the at least one response packet to a memory buffer; and

means for feeding the resulting at least one response packet from the memory buffer to a network interface for transmission over a communication network.