TCP/UDP ACCELERATION

• US 20150032691A1
• Filed: 08/14/2014
• Published: 01/29/2015
• Est. Priority Date: 11/02/2000
• Status: Active Grant

• Current Assignee: Oracle America, Inc. (Oracle Corporation)
• Original Assignee: Oracle America, Inc. (Oracle Corporation)
• Inventors: Hall, Howard, Sokolinski, Ilia, Merhar, Milan
• Granted Patent: US 9,639,553 B2
• Time in Patent Office: Days
• US Class Current: 707/610
• CPC Class Codes: G06F 16/178 Techniques for file synchronisation in file systems
• CPC Class Codes: G06F 16/183 Provision of network file services by network file servers, e.g. by using NFS, CIFS network file access protocols H04L67/1097
• CPC Class Codes: H04L 47/125 by balancing the load, e.g. traffic engineering
• CPC Class Codes: H04L 47/193 at the transport layer, e.g. TCP related
• CPC Class Codes: H04L 47/2458 Modification of priorities while in transit
• CPC Class Codes: H04L 47/2466 using signalling traffic
• CPC Class Codes: H04L 47/2483 involving identification of individual flows
• CPC Class Codes: H04L 47/726 Reserving resources in multiple paths to be used simultaneously by balancing the load H04L47/125
• CPC Class Codes: H04L 49/00 Packet switching elements
• CPC Class Codes: H04L 69/10 Streamlined, light-weight or high-speed protocols, e.g. express transfer protocol [XTP] or byte stream
• 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 69/165 Combined use of TCP and UDP protocols; selection criteria therefor
• CPC Class Codes: H04L 9/40 Network security protocols

Abstract

A method for accelerating TCP/UDP packet switching. The method involves determining whether exception processing is necessary; if not, the packet is forwarded to a special stack for expedited processing. Packets requiring exception processing are forwarded to the conventional stack.

Claims

1. A digital processing system for processing data packets in at least one data network, said system comprising:

a first resource card, comprising;

a receiving module, wherein the receiving module;

receives packets from the data network; and

executes a lookup in a forwarding database for an entry corresponding to each received packet; and

a first processing module, wherein the first processing module;

receives packets from the receiving module having corresponding entries in the forwarding database;

executes a lookup in a flow database for a corresponding flow ID for those packets having corresponding entries in the forwarding database; and

inserts corresponding flow IDs into the packets; and

a second resource card operatively interconnected to the first resource card by a switching fabric, wherein the first processing module forwards packets having corresponding flow IDs to the second resource card, wherein the second resource card comprises;

a first stack for performing a first type of packet processing;

a slow path processing engine associated with the first stack;

a second stack for performing a second type of packet processing that comprises fewer processing steps than does the first type of packet processing; and

a fast path processing engine associated with the second stack, wherein the fast path processing engine receives packets having corresponding flow IDs from the first processing module and determines whether the received packets correspond to the first or second types of packet processing, wherein the fast path processing engine injects packets that correspond to the first type of packet processing into the first stack and processes packets that correspond to the second type of packet processing according to the second stack.

2. The system of claim 1, wherein the slow path and fast path processing engines exchange control messages to both maintain state synchronization between the first and second stacks and hand off control between the first and second stacks.

3. The system of claim 2, wherein the first and second stacks are configured for TCP packet processing, and wherein the fast path processing engine determines whether the packets correspond to the first or second type of packet processing by testing, for each packet, that the packet has been received in sequence.

4. The system of claim 2, wherein state lost in one of the first and second stacks due to at least one of system error and failure can be restored through resynchronization with an undisrupted one of the first and second stacks.

5. The system of claim 1, wherein the first and second stacks are configured for TCP packet processing, and wherein the fast path processing engine determines whether the packets correspond to the first or second type of packet processing by testing, for each packet, that the packet has been received in sequence.

6. The system of claim 1, wherein the fast path processing engine determines whether the packets correspond to the first or second type of packet processing by testing, for each packet, that the packet has no associated retransmission requirement.

7. The system of claim 1, wherein the fast path processing engine determines whether the packets correspond to the first or second type of packet processing by testing, for each packet, that there is no data queued in an associated socket'"'"'s Send buffer.

8. The system of claim 1, wherein the fast path processing engine determines whether the packets correspond to the first or second type of packet processing by testing, for each packet, that there are no TCP-atypical flags set for the packet.

9. The system of claim 1, wherein the fast path processing engine determines whether the packets correspond to the first or second type of packet processing by testing, for each packet, that no associated options are set other than timestamp.

10. The system claim 1, wherein the fast path processing engine determines whether the packets correspond to the first or second type of packet processing by testing, for each packet, that an associated timestamp is correct.

11. The system of claim 1, wherein the first resource card comprises a local area network (LAN) resource card that interconnects the system with the data network, and the second resource card comprises a storage resource card that interconnects the system with an external storage device.

12. The system of claim 1, wherein the fast path processing engine hands a packet directly to an application after the packet has been processed according to the second stack.

13. The system of claim 1, wherein the fast path processing engine processes packets according to the second stack by performing at least one of updating TCP counters, releasing any ACK-ed data, and generating any ACK packets.

14. The system of claim 1, wherein the entries in the forwarding database comprise IP addresses corresponding to virtual storage endpoints (VSEs) associated with a virtual storage domain (VSD).