Electrical computers and digital processing systems: multicomput – Computer network managing – Computer network monitoring
Reexamination Certificate
1997-06-05
2001-01-09
Rinehart, Mark H. (Department: 2756)
Electrical computers and digital processing systems: multicomput
Computer network managing
Computer network monitoring
C709S217000, C709S223000, C709S225000, C709S226000, C709S229000
Reexamination Certificate
active
06173322
ABSTRACT:
BACKGROUND OF THE INVENTION
1. Field of the Invention
The present invention relates generally to network servers, and more particularly to the distribution of client requests received from a network to a number of content servers based on one or more static rules and dynamic performance data.
2. Related Art
Today, millions of computer-users worldwide are communicating via the Internet. The Internet provides an unparalleled medium for the exchange and dissemination of ideas, for cheap and efficient long-distance communication, and for the conduct of business. Many entities in the public, private, and governmental sectors are rushing to establish a presence on the Internet.
However, the growth of computer networks is not limited to the Internet alone. Many are finding that additional efficiencies may be realized from computer resources when in-house computers are linked by a network. Businesses, governmental agencies, and academic institutions are all creating vast internal networks to increase the flow of information between their employees or students. In many instances, these networks are accessible to the general public as well.
Those wishing to establish a site on the Internet (i.e., a “web site”) must have some means for handling the requests directed to the web site from other network users (i.e., “client requests”). This job of handling client requests becomes complicated when these requests may actually be serviced by a computer, or one of many computers, other than the computer running the web site software. These computers will hereinafter be referred to as “content servers,” as they are the machines responsible for providing the content that is the subject of the client request.
Many software products are available today which are capable of distributing client requests amongst multiple content servers. However, these products suffer from numerous drawbacks. First, some existing products are only able to distribute client requests amongst content servers which are of identical hardware design. Others are only able to distribute client requests amongst geographically co-located content servers. Still others are limited to content servers running the same software and having access to identical data. Obviously, these restrictions can be extremely limiting where the web site owner has many content servers, including a variety of hardware and software configurations, geographically dispersed in a number of distant locations.
Some existing products do not consider the processing loads carried by, or even the availability of, content servers when determining which will service a particular client request. Other products rely solely on pre-defined static rules to determine how client requests are distributed rather than altering the distribution based on dynamic changes within the network environment. Still other products are unable to base distribution decisions on the nature of the client request (i.e., sending certain types of client requests to certain content servers).
Conventional products suffer other disadvantages as well. Some are unable to successfully redistribute client requests when the first content server fails. Some require special software to be installed on each content server to report data to the central request handler. Other are inefficient in terms of message traffic sent across the network.
A need exists for an improved system and method for distributing client requests which addresses these problems. The system and method should be able to distribute client requests to content servers of various hardware and software design, and without geographical limitation so long as the content server is accessible via a network.
Further, as web sites become increasingly complex and the flow of client requests swells, those managing the web site would benefit greatly from having sophisticated, customizable software for determining how these burdens are distributed across the content servers tasked to handle these requests. The distribution should be based on both pre-defined static rules, and content server performance data monitored over time. The desired distribution should be achieved without requiring special software to be installed on each content server, and without unduly increasing network message traffic.
Thus, what is required is an improved system and method for distributing client requests to a variety of content servers according to static rules and dynamic monitoring of content server performance.
SUMMARY OF THE INVENTION
Briefly stated, the present invention is directed to a system and method for the distribution of client requests received from a digital computer network. The present invention acts as an intermediary between the client and one or more content servers which actually service the client request.
A feature of the present invention is that client requests are distributed amongst groups of content servers according to one or more static rules. The present invention applies these static rules to determine which group of content servers will service each client request. Content servers may be grouped arbitrarily, so long as each content server within a group is capable of servicing all the client requests sent to that group.
An advantage of the present invention is that subject to the restriction that each content server within a group be capable of servicing all client requests sent to that group, content servers may be grouped without regard to hardware configuration and without regard to where the content server resides within the network. In other words, a single group may include content servers configured of various hardware. A single group may also include content servers accessible via a local network, and other content servers accessible via a wide-area network.
Another feature of the present invention is that client requests may be distributed amongst the content servers within each group according to a dynamic metric. The present invention forms the dynamic metric based on measurements made over time of the available processing capacity of each content server within a group. Client requests may then be distributed to those content servers within a group that are best able to handle additional processing burdens.
An advantage of the present invention is that the available processing capacity of each content server is measured without requiring special software to be installed in the content servers, and without increasing network message traffic over and above that already required to process client requests.
Another feature of the present invention is that content server failures are handled without disrupting the client. The present invention detects in an efficient manner when content servers fail and when they return to service.
Another feature of the present invention is that connections may be established with content servers in one of two modes. In a proxy mode, the present invention acts on behalf of the client by forwarding the client request to a content server for servicing, then returns the results of the servicing to the client. In a redirect mode, the present invention returns to the client whatever information is required to enable the client to establish a direct connection with the content server.
Another feature of the present invention is that frequently accessed data may be stored in a cache for quick retrieval. Data accessed by client requests may be cached, as well as network connections to content servers. With respect to the latter, significant time savings may be realized by holding open frequently used network connections for some period of time and storing data related to these connections.
Further features and advantages of the invention, as well as the structure and operation of various embodiments of the invention, are described in detail below with reference to the accompanying drawings. In the drawings, like reference numbers generally indicate identical, functionally similar, and/or structurally similar elements. The drawing in which an element first appears is indicated by the leftmost digit
Rinehart Mark H.
Romero Almari
Silicon Graphics Inc.
Sterne Kessler Goldstein & Fox P.L.L.C.
LandOfFree
Network request distribution based on static rules and... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Network request distribution based on static rules and..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Network request distribution based on static rules and... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2485927