Electrical computers and digital processing systems: multicomput – Computer-to-computer session/connection establishing
Reexamination Certificate
1998-06-30
2004-06-01
Jaroenchonwanit, Bunjob (Department: 2143)
Electrical computers and digital processing systems: multicomput
Computer-to-computer session/connection establishing
C709S245000
Reexamination Certificate
active
06745243
ABSTRACT:
COPYRIGHT NOTICE
A portion of the disclosure of this patent document contains material which is subject to copyright protection. The copyright owner has no objection to the facsimile reproduction by anyone of the patent document or the patent disclosure, as it appears in the Patent and Trademark Office patent file or records, but otherwise expressly reserves all rights whatsoever in said copyright works.
BACKGROUND OF THE INVENTION
1. Field of the Invention
The present invention relates to the field of data network management and, in particular, to a method and apparatus for network caching and load balancing employing network address translation.
2. Background Information
As computer technology has evolved, so too has the use of networks which communicatively couple computer systems together allowing remote computer systems to communicate with one another. One of the more popular of such computer networks is colloquially referred to as the Internet, which is an internetworking of a number of publicly accessible networks (e.g., Local Area Networks (LANs)) and servers throughout the world via network switches, bridges, routers and the like, generically referred to as network devices. However, the explosive growth in computer sales has led to congestion of network traffic on the worlds networks. In response to inadequate bandwidth infrastructure, customers and vendors search for methods of reducing the bandwidth requirements of the most heavily used of the network protocols. Recently, network caches and other load balancing devices have been added to networks in an effort to more efficiently manage the finite bandwidth of the Internet.
In general, a network cache operates by intercepting certain network traffic, in accordance with a network management strategy. In a typical implementation on the Internet, a network cache intercepts internet protocol (IP) requests for information in a higher layer protocol. For example, a network cache may be employed to cache all world-wide web requests made through it to the Internet. Accordingly, the network cache will monitor the transmission control protocol (TCP) port 80, commonly assigned for the HyperText Transfer Protocol (HTTP) messages associated with WWW usage, and determines whether it can satisfy the request locally. If the request can be fulfilled locally, then the request need not be forwarded, thus reducing the bandwidth requirements of the protocol, and the client receives a quicker response, thus improving the perceived performance of the network. If the request cannot be fulfilled locally, the cache re-issues the request, destined to the proper origin server which responds to the request. The response returned by the origin server may then be cached by the network cache to satisfy later requests for the same information.
One problem commonly associated with network caches is the extra processing required for each packet in the data flow, i.e., the cache must decide which packets to forward normally and which to process for caching. Generally, network caches typically make this determination based on layer 3 or, layer 4 level information (of the International Standards Organization's (ISO) Open System Interconnection (OSI) reference model).
That is, network caches have historically relied on layer 3 and/or layer 4 information embedded within the network traffic to identify that traffic which is cacheable. Those skilled in the art will appreciate that layer 3 is the network layer, and provides path control within the transmission medium of the data network. Typically, network devices route packets of information over a data network based on network layer address information. The OSI network layer is the domain wherein connection-oriented and connectionless-oriented networks operate, network addresses are assigned, network topology is known and routing decision processes are typically performed. One example of a layer 3 protocol is the Internet Protocol (IP) suite used within the Internet.
Typically, however, prior art network caches discriminate network traffic based on layer 4 information. Layer 4 of the OSI reference model is defined as the transport layer. Layer 4 defines the transport layer of the OSI reference mode and controls the movement of data between systems, defines protocols for structuring messages and supervises the validity of transmissions by performing error checking. Again, with reference to the Internet, the transport layer (e.g., layer 4) would include the Transmission Control Protocol (TCP), for example. An example of a network cache employing OSI layer 4 functionality is the Cisco Cache Engine™ commonly available from Cisco Systems.
Thus, while it is easy to discriminate network traffic at layer 3 and/or layer 4 (e.g., all IP traffic, or all traffic passing through TCP port 80), it can quickly overwhelm the processing capability of prior art network caches, necessitating the deployment of several caches throughout the network to handle the network traffic. Accordingly, the introduction of prior art network caches, although heralded as network-saving devices, have themselves become network traffic congestion points.
Load balancing devices of the prior art also suffer from the aforementioned limitations. A load balancing device is designed to route network traffic through optimal data paths based on a number of traffic-centric and network-centric parameters, in accordance with a network management strategy. Accordingly, load balancing devices typically support a large number of network connections and must perform rudimentary address translation. Thus, a load balancing device is typically implemented as a front end for a collection of servers. Clients connect to the load balancing device instead of directly to the servers. Based on certain metrics (server load, distance, etc.) the load balancing device assigns the client to a server. The load balancing device then translates and forwards all traffic between the client and the assigned server.
None of the prior art network caches or load balancing devices, however, are optimized to discriminate network traffic based on network session information, e.g., at OSI layer 5, as means for selecting traffic to cache or determining network routing. As a result, prior art network caches/load balancers are tasked with attempting to cache all network traffic adhering network management strategy based on layer 3 and/or layer 4 information.
Accordingly, an improved method and apparatus for network caching and load balancing is presented, unencumbered by the deficiencies and inherent limitations commonly associated with the network devices of the prior art. It will be apparent to those skilled in the art, from the description to follow, that the present invention achieves these and other desired results.
SUMMARY OF THE INVENTION
In accordance with the teachings of the present invention, a method and apparatus for network caching and load balancing is provided. In particular, in accordance with one embodiment of the present invention, an apparatus comprising a network interface coupled to a data network, a network address translator and a controller is presented. The network interface receives network traffic from a communicatively coupled data network adhering to any of a number of alternative network protocols. The network address translator identifies network session information within the received network traffic adhering to any of a number of alternative protocols. The controller selects network traffic to be cached based, at least in part, on the network session information identified by the network address translator.
REFERENCES:
patent: 5425028 (1995-06-01), Britton et al.
patent: 5485455 (1996-01-01), Dobbins et al.
patent: 5509121 (1996-04-01), Nakata et al.
patent: 5511208 (1996-04-01), Boyles et al.
patent: 5566170 (1996-10-01), Bakke et al.
patent: 5720032 (1998-02-01), Picazo, Jr. et al.
patent: 5737333 (1998-04-01), Civanlar et al.
patent: 5774660 (1998-06-01), Brendel et al.
patent: 5787470 (1998-07-01), DeSimone et al.
patent: 5793763 (1998-08-01), M
Luciani James V.
Squire Matthew B.
Blakely , Sokoloff, Taylor & Zafman LLP
Jaroenchonwanit Bunjob
Nortel Networks Limited
LandOfFree
Method and apparatus for network caching and load balancing does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Method and apparatus for network caching and load balancing, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method and apparatus for network caching and load balancing will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3362033