International Business Machines Corporation

Cisco Technology, Inc.

Barron Cornelius Housel, Iii

David Bruce Lindquist

Robert Michael Batz

Reed Richard Bittinger

Chris O'Rourke

Tzu-Ming Tsang

Pranav Tiwari

Louis F Menditto

Gaurang Shah

Ian Beaumont Shields

Michael Levi Fraenkel

Ajamu Akinwunmi Wesley

Mark Albert

Jan Vilhuber

Michael L Fraenkel

Scott W Brim

Mauro Zallocco

Anurag Bhargava

Steven C Klein

John Raithel Hind

Jonathan Paul Munson

Kathryn Heninger Britton

Norman Howard Cohen

Steve Mastrianni

Stephen C Baber

Hung-yang Chang

Richard Allen Floyd

Carl D Tait

Marshall Shapiro

Michael C Wanderski

Richard Mandfred Pruss

Marion Lee Blount

Teresa A Meriwether

James L Hall

Steve Wang

Wayne Roiger

Peter Williams Volkmar

William Anthony Kingston

Ray W Boyles

Douglas Burnette Blakeley

Nils C Brubaker

Ethan M Young

Chandrasekaran Venkatapathy

An improved client network address translation ('NAT') system is provided. Methods are provided for initializing connection control blocks with the client NAT addresses when a storage pool of connection control blocks are allocated. This avoids the costly overhead as connections are created and destroyed. Unlike the prior art solutions, once the connection control blocks of the present invention are allocated, they remain in effect until the storage subpool is deleted. Secondly, in order to provide as large a pool of client NAT addresses as possible, methods are provided for using intervals to allocate and reclaim client NAT addresses as subpools are allocated and freed.

Preallocation of client network address translation addresses for client-server networks

An information service provider network includes a content gateway to process requests for information from a client terminal. The content gateway includes a router for receiving a request for information from the client terminal. The request includes a domain name and additional content. The router forwards the request according to the domain name to a selected one of a plurality of processors to further process the request. The selected one of the plurality of processors identifies an information source to satisfy the request in response to the additional content of the request.

System and method for processing a request for information in a network

An apparatus includes a network system and a message. The network system includes a client terminal and a receiver. The client terminal includes a browser, an identifier, and a positioner. The positioner inserts the identifier into the message. The message is transmitted from the client terminal through an internet service provider and through a plurality of firewalls and is received by the receiver. The receiver includes a component that recognizes the identifier within the message and directs the message to one of a plurality of servers. The component also recognizes a subsequent message related to the identifier and directs the subsequent message to the one of the plurality of servers. The one of the plurality of servers then directs each of the messages to a service provider for processing. A related response is generated by the service provider and returned through the network system and to the client terminal.

Method and apparatus for tracking related information in a network

Mechanisms and techniques provide a method for routing a packet that includes a content request and an Internet Protocol address and port number that identify a source transmitting the packet. The method relates to selecting a routing policy to forward the packet, based upon at least a portion of content request. The method includes a data communications device receiving a packet having a content request and an Internet Protocol address and port number that identify a source transmitting the packet. The device performs a network address translation, based upon at least a portion of the content request, to translate the Internet Protocol address and port number of the packet to a respective communications device Internet Protocol address and communications device port number. The device then selects a routing policy based upon the communications device Internet Protocol address and routes the packet to a destination according to the routing policy.

Methods and apparatus for routing a content request

A network () includes a load balancer () that passes traffic between a client () and a gateway (). For initial messages from a client (), the load balancer () selects an appropriate gateway () for message processing. A session is then established between the client () and the appropriate gateway (). The session is indicated by a session identifier. At any point, the client () may choose to suspend the session for later resumption. Upon suspension, the load balancer () keeps track of the session identifier and the appropriate gateway () associated with the session. Upon a resumption request from the client (), the load balancer () determines which of the gateways () is associated with the resumption request according to the session identifier. In this manner, the client may continue a session with the same gateway () for seamless operation.

System and method for maintaining seamless session operation

A network includes a service selection gateway that receives information from a network user having a network locator address in order to establish a communications session and an identity of the network user. A client service gateway can receive a request from the network user upon establishment of the communications session. In response to the request, the client service gateway determines if there is an association in a local memory for the network locator address and an identity of the network user, obtains additional information associated with the network user, and processes the request according to the additional information. If an association is not stored in the local memory, the client service gateway sends a query for the identity of the network user to the service selection gateway.

System, device, and method for communicating user identification information over a communications network

Methods, systems and computer program products are provided for concurrently transferring a plurality of files between a first data processing system and a second data processing system by multiplexing chunks of the plurality of files onto a connection between the first data processing system and the second data processing system and dynamically determining a chunk size for each multiplexed chunk. A 'chunk' is an amount of data from a file to be transferred wherein the amount of data in the chunk is dynamically defined such that differing amounts of data are transferred in each chunk. Furthermore, the transfer of each multiplexed file is tracked so as to allow restarting of an interrupted file transfer from a point of interruption of the transfer.

Methods, systems and computer program products for restartable multiplexed file transfers

An improved client network address translation ('NAT') system is provided. A memory allocation scheme is provided for initializing connection control blocks with the client NAT addresses when a storage pool of connection control blocks are allocated. This avoids the costly overhead as connections are created and destroyed. Unlike the prior art solutions, once the connection control blocks of the present invention are allocated, they remain in effect until the storage subpool is deleted. Secondly, the allocation scheme enables a large pool of client NAT addresses and reclaim client NAT addresses as subpools are allocated and freed.

Method allocation scheme for maintaining server load balancers services in a high throughput environment

An information service provider network includes a content gateway to process requests for information from a client terminal. The content gateway includes a router for receiving a domain name server query from an originator associated with a request for information. The router including a database defining a relationship between domain names and addresses associated with accelerated servicing of requests. The router determines whether the domain name of the domain name server query is indexed in the database. The domain name is qualified in response to the domain name being in the database. If qualified, the router sends an address to the originator of the query corresponding in the database to the domain name. The address is to a processor associated with the router that performs accelerated services on the request.

System and method for qualifying requests in a network

A system for reducing data volume transferred over a wireless communications network includes a browser operable to communicate a sequence to a network interface. The system further includes the network interface operable to receive the sequence from the browser, generate a signature for the sequence, store the sequence and signature in memory, associate the sequence and signature with the browser, communicate a cache header and the signature to the browser, and communicate at least one request header to a server. The browser, upon sending a subsequent communication to the server, communicates the cache header and signature to the network interface. In this manner HTTP request headers need not be transferred for every request from the browser.

Method and system for reducing data volume transferred over a wireless communications network

A method, system, and computer-readable code with which a scheduling system can be implemented that allows a sender and a receiver to change priorities of queued messages. A technique is also defined for providing a receiver with an advance notice of intended message priority, enabling the receiver to request a priority change before transmission begins. These techniques provide the flexibility to respond to changes in dynamic, volatile network environments, as well as changes in user's wishes or requirements. A ranking technique is defined, whereby requests to change priority may be accepted or denied through a ranking algorithm that resolves potential conflicts in desired transmission priority using proposals exchanged by the parties (e.g. during connection establishment).

Dynamic priority-based scheduling in a message queuing system

A method, system, and computer-readable code for embedding a file index among the fixed-length data blocks of a random-access file to which the index pertains. In the preferred embodiment, a B-tree index is used. The nodes of the B-tree are stored using blocks of the random-access file, so that the index records are embedded among the data records to which the index pertains. This technique avoids a number of problems that result when a data file and its index are separately located. Record updates and retrievals operate more efficiently, and the data records remain synchronized with the corresponding index when file operations (e.g., close, flush) complete successfully. In an optional enhancement, synchronization is ensured when record-level operations (write, delete) complete successfully.

Increasing efficiency of indexing random-access files composed of fixed-length data blocks by embedding a file index therein

Method, apparatus and program products are provided for persistent cache synchronization for a first communication session and a concurrent second communication session over an external communication link between a client protocol conversion application executing on a first computer and a server protocol conversion application executing on a second computer located remote from the first computer. An active cache is established independently for each session with a corresponding cache for each session at the other computer for use with the first and the second communication session respectively. A checkpoint request is transmitted to the server application indicating one of the active protocol caches from either the first session or the second session to be used to provide a checkpoint. On receipts of the request from the server application, the active protocol cache for the indicated session is copied to provide a checkpoint cache of the second computer. Regardless of which session was indicated, the resulting checkpoint cache of the second computer is associated with both the first and the second session. A checkpoint confirmation message is transmitted to the client application with the first computer responsive to the copying operation. On receipt of the checkpoint confirmation message, the client application creates a checkpoint cache of the first computer as a copy of the indicated one of the first or second sessions protocol cache. The checkpoint cache of the first computer is associated with both the first session and the second session to provide a checkpoint. Operations to create new checkpoints are repeated as desired based upon checkpoint criteria.

Methods, systems and computer program products for maintaining a common checkpoint cache for multiple sessions between a single client and server

Growing community of inventors

Chapel Hill, NC, United States of America

Barron Cornelius Housel, Iii