TCP/UDP acceleration

• US 8,949,471 B2
• Filed: 11/02/2001
• Issued: 02/03/2015
• 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
• Primary Examiner(s): Benoit, Esther
• Application Number:
  US10/415,330
• Publication Number:
  US 20040111523A1
• Time in Patent Office: 4,841 Days
• Field of Search: 709/250
• US Class Current: 709/250
• 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: G06F 3/0601 Interfaces specially adapted for storage systems
• CPC Class Codes: G06F 3/0673 Single storage device
• CPC Class Codes: H04L 41/0806 for initial configuration or provisioning, e.g. plug-and-play
• CPC Class Codes: H04L 41/12 Discovery or management of network topologies
• CPC Class Codes: H04L 41/5003 Managing SLA; Interaction between SLA and QoS
• CPC Class Codes: H04L 47/193 at the transport layer, e.g. TCP related
• CPC Class Codes: H04L 47/2466 using signalling traffic
• 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 67/01 Protocols
• CPC Class Codes: H04L 67/1001 for accessing one among a plurality of replicated servers
• CPC Class Codes: H04L 67/1008 based on parameters of servers, e.g. available memory or workload monitoring of computer activity G06F11/30
• CPC Class Codes: H04L 67/101 based on network conditions
• CPC Class Codes: H04L 67/1017 based on a round robin mechanism
• CPC Class Codes: H04L 67/1019 Random or heuristic server selection
• CPC Class Codes: H04L 67/1023 based on a hash applied to IP addresses or costs
• CPC Class Codes: H04L 67/1027 Persistence of sessions during load balancing
• 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 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 69/161 : Implementation details of TCP/IP or UDP/IP stack architecture; Specification of modified or new header fields
• CPC Class Codes: H04L 69/163 : In-band adaptation of TCP data exchange; In-band control procedures
• CPC Class Codes: H04L 69/164 : Adaptation or special uses of UDP protocol
• CPC Class Codes: H04L 69/165 : Combined use of TCP and UDP protocols; selection criteria therefor
• CPC Class Codes: H04L 69/22 : Parsing or analysis of headers
• 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 69/325 : in the network layer [OSI layer 3], e.g. X.25 H04L69/16 takes precedence
• CPC Class Codes: H04L 69/326 : in the transport layer [OSI layer 4] H04L69/16 takes precedence
• CPC Class Codes: H04L 69/327 : in the session layer [OSI layer 5]
• CPC Class Codes: H04L 69/329 : in the application layer [OSI layer 7]
• 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. In a digital processing system, a method of accelerating processing of packets in a series of packets, the method comprising:

establishing, within the system, a first protocol stack for processing packets requiring exception processing, and a second protocol stack for simplified processing of packets not requiring exception processing,

testing each packet in the series of packets to determine whether a given packet requires exception processing,

forwarding to the second protocol stack, as a function of the testing, packets not requiring exception processing,

forwarding to the first protocol stack, as a function of the testing, packets requiring exception processing,

maintaining state synchronization between the first and second protocol stacks by exchanging control messages between a fast path processing engine processing packets in the second protocol stack and a slow-path processing engine processing packets in the first protocol stack, and

reducing processing volume or time in the slow-path processing engine in response to the maintaining of state synchronization.

2. The method of claim 1 wherein the maintaining of state synchronization comprises the exchange of state information between respective processing modules associated with the first and second stacks.

3. The method of claim 1 wherein the first and second stacks are configured for TCP packet processing, and the testing comprises testing, for each packet, that the packet has been received in sequence.

4. The method claim 1 wherein the testing step includes testing, for each packet, that the packet has no associated retransmission requirement.

5. The method of claim 1 wherein the testing step includes testing, for each packet, that there is no data queued in an associated socket'"'"'s Send buffer.

6. The method of claim 1 wherein the testing step comprises testing, for each packet, that there are no TCP-atypical flags set for the packet.

7. The method of claim 1 wherein the testing step comprises testing, for each packet, that no associated options are set other than timestamp.

8. The method of claim 1 wherein the testing step comprises testing, for each packet, that the associated timestamp is correct.

9. The method of claim 2 wherein the maintaining of state synchronization comprises maintaining state synchronization between and among the first, second, and at least a third stack.

10. The method of claim 9 wherein the maintaining of state synchronization comprises the exchange of state information between respective processing modules associated with each stack.

11. The method of claim 2 wherein state lost in one stack due to at least one system error and failure can be restored through resynchronization with an undisrupted stack.

12. In a digital network comprising at least a first client, a storage resource, and a switch element operable to direct a series of packets between the client and the storage resource, a method of accelerating processing of packets in a series of packets, the method comprising:

providing, within the switch element,

a first configurable set of processor elements to process storage resource connection requests,

a second configurable set of processor elements capable of communications with the first configurable set of processor elements to receive, from the first configurable set of processor elements, storage resource connection requests representative of client requests, and to route the requests to elements of the storage resource, and

a configurable switching fabric interconnected between the first and second sets of processor elements, for

receiving at least a first storage resource connection request from one of the first set of processor elements,

determining an appropriate one of the second set of processors for processing the storage resource connection-request,

automatically configuring the storage resource connection request in accordance with a protocol utilized by the selected one of the second set of processors, and

forwarding the request for storage resource connection to the selected one of the second set of processors for routing to elements of the storage resource,

establishing, in the switch element, a first protocol stack for processing packets requiring exception processing, and a second protocol stack for simplified processing of packets not requiring exception processing,

receiving, in the switch element, the series of packets for processing,

testing, in the switch element, each packet in the series of packets to determine whether a given packet requires exception processing,

forwarding to the second protocol stack, as a function of the testing, packets not requiring exception processing,

forwarding to the first protocol stack, as a function of the testing, packets requiring exception processing,

maintaining state synchronization between the first and second protocol stacks by exchanging control messages between a fast path processing engine processing packets in the second protocol stack and a slow-path processing engine processing packets in the first protocol stack, and

reducing processing volume or time in the slow-path processing engine in response to the maintaining of state synchronization.

13. The method of claim 12 wherein the maintaining of state synchronization comprises the exchange of state information between respective processor elements, in the switch element, associated with the first and second stacks.

14. The method of claim 12 or 13 wherein the first and second stacks are configured for TOP packet processing, and the testing step comprises testing, for each packet, that the packet has been received in sequence.

15. The method of claim 12 wherein the testing step comprises testing, for each packet, that the packet has no associated retransmission requirement.

16. The method of claim 12 wherein the testing step comprises testing, for each packet, that there is no data queued in an associated socket'"'"'s Send buffer.

17. The method of claim 12 wherein the testing step comprises testing, for each packet, that there are no TOP-atypical flags set for the packet.

18. The method of claim 12 wherein the testing step comprises testing, for each packet, that no associated options are set other than timestamp.

19. The method of claim 12 wherein the testing step comprises testing, for each packet, that the associated timestamp is correct.

20. The method of claim 13 wherein state lost in one stack due to at least one of system error and failure can be restored, in the switch element, through resynchronization with an undisrupted stack.