International Business Machines Corporation

John E Drake, Jr

Jeffrey Haskell Derby

Marcia Lambert Peters

Elizabeth A Hervatic

Marc Adam Kaplan

Diane Phylis Pozefsky

James P Gray

Kenneth Harvey Potter, Jr

Gerald Arnold Marin

Ken Van Vu

Roch A Guerin

Michael James Ward

Joshua S Auerbach

Andrew Hilliard Arrowood

Levent Gun

John G Dudley

Willibald A Doeringer

Douglas H Dykeman

Lee M Rafalow

Alan E Baratz

Theodore E Tedijanto

Haldon J Sandick

Prabandham M Gopal

John L Eisenbies

Kathryn E Clarke

Karla J Norsworthy

Claude R Galand

James Corvin Fletcher

Lap Thiet Huynh

Israel Cidon

Allen Leonid Roginsky

Shay Kutten

Andrew P Citron

Chee-Seng Chow

Owen H Choi

Zvonimir Ordanic

Michael A Lerner

Liang Li

Jeffrey G Knauth

Melinda R Pollard

David E Taber

Johnathan L Harter

Dirk K Kramer

Marsha E Ferree

William E Siddall

George A Grover

Richard M Doney

Ralph J Potok, Ii

Terence Dale Smetanka

Philip F Chimento, Jr

Joseph L McKinnon

Siddall, William E

Melinda P Stump

Rong-Feng Chang

Joseph W Pace

John E Fetvedt

A multinode, multicast communications network has a distributed control for the creation, administration and operational mode selection operative in each of the nodes of the network. Each node is provided with a Set Manager for controlling either creation of, administration or access to a set of users to whom a multicast is to be directed. The Set Manager maintains a record of the local membership of all users associated with the node in which the Set Manager resides. A given Set Manager for each designated set of users is assigned the task of being the Set Leader to maintain membership information about the entire set of users in the multicast group. One of the Set Managers in the communications network is designated to be the Registrar which maintains a list of all the Set Leaders in the network. The Registrar insures that there is one and only one Set Leader for each set of users, answers inquiries about the membership of the sets and directs inquiries to appropriate Set Leaders if necessary. All of the set creation, administration and control functions can therefore be carried out by any node of the system and provision is made to assume the function at a new node when failure or partition in the network occurs.

Distributed management communications network

Method and apparatus for managing internal-node communications in a packet switching network by calculating optimal routes for packets and addressing subnodes within packet nodes using a specific message format. Internal communication facilities called intranode links connect multiple subnodes within nodes. Each subnode contains a switching mechanism and routes packet to other nodes, subnodes, or user applications using a specific message format. The message format allows specific subnodes anywhere in the network to the addressed by any other subnode, making communications more efficient and simplifying the management of internode links.

Packet switching resource management within nodes

A management system for local area networks ensures selected levels of quality of service to all transmission requests submitted to the management system. This management system is attached to the network and receives requests from all other stations on the network to reserve facilities for a particular quality of service data stream. An allocator in the management system determines if the requested facilities are available and, if so, reserves these facilities for the requesting station. If the facilities are not available, the request is denied. A hierarchical data base containing all of the current parameters of all of the network resources and all of the currently supported data streams is used to support the allocation process.

Quality of service management for source routing multimedia packet

Method and apparatus for making limited internal-node communication facilities externally visible in a packet switching network. Internal-node communication facilities are called intranode links, can include any cable, channel, bus, etc. over which data passes, and are used to connect the multiple subnodes within a given node. Each subnode contains a switching mechanism and routes packets to other nodes, subnodes, or user applications. Each node provides network control functions such as topology, directory, path selection, and bandwidth management which can manage intranode links in the same manner that internode links are currently managed.

The process for determining the best communication route from a source end station to a destination end station is distributed over both source and destination network nodes. Network nodes, at the interface between a wide area network (WAN) and each subnetwork, contain access agents to control the communication flow between the wide area network and an end station in the subnetwork. The task of selecting the best route between two end stations is distributed between the access agents at the WAN interface in the first subnetwork, and the access agents at the WAN interface in the second subnetwork. Each access agent at one WAN interface obtains the best route from itself to the end station in its subnetwork. Each access agent at the other WAN interface finds the best route from each access agent at the first WAN interface through itself to the end station in its subnetwork. One designated access agent collects all the best route information. This best route information is concatenated, and the route with the least weight is selected as the best route between end stations.

Distributed processing of route selection across networks and subnetworks

An end-to-end, closed loop flow and congestion control system for packet communications networks exchanges rate request and rate response messages between data senders and receivers to allow the sender to adjust the data rate to avoid congestion and to control the data flow. Requests and responses are piggy-backed on data packets and result in changes in the input data rate in a direction to optimize data throughput. GREEN, YELLOW and RED operating modes are defined to increase data input, reduce data input and reduce data input drastically, respectively. Incremental changes in data input are altered non-linearly to change more quickly when further away from the optimum operating point than when closer to the optimum operating point.

Adaptive rate-based congestion and flow control in packet communications

Access agents in nodes at the LAN/WAN interface are formed into a group of access agents so that the access agents may be managed by the WAN as a group. The group must maintain group operation integrity in that if communications between agents in the group are broken, the access agents will coalesce into subgroups and continue performing communication jobs as a group activity. Each of the access agents contains a finite state machine to perform the tasks of group formation and maintenance. The formation of interconnected access agents into a group is accomplished by one access agent being identified as a group leader. All other access agents communicating with the group leader within the LAN may then join the group. The maintenance of group activity integrity is accomplished by detecting a break in group communication integrity and thereafter reforming the group into multiple smaller groups. The maintenance of group operation integrity also includes the merger of small groups into a large group when a bridge is added between LAN segments.

Forming and maintaining access groups at the lan/wan interface

Access control for a packet communications network includes a dynamic bandwidth updating mechanism which continuously monitors the mean bit rate of the signal source and the loss probability of the connection. These values are filtered to remove noise and then used to test whether the values fall within a pre-defined acceptable adaptation region in the mean bit rate, loss probability plane. Values falling outside of this region trigger bandwidth updating procedures which, in turn, result in acquiring a new connection bandwidth, and determining new filter parameters and new parameters for a leaky bucket access mechanism.

Dynamic bandwidth estimation and adaptation for packet communications

In a multicast network communication system, administration of the communication path making up the multicast tree itself has been separated from control and administration of the network. Creation of a multicast distribution tree and control over the membership thereof, is separately controlled independently from the creation and use of the tree transmission path used to communicate among the members of a multicast set. Transmission distribution trees are set up when a transmission request is received and the properties of the transmission path that is required are known. Transmission paths are created and controlled by all nodes in the communications system, each node having necessary control code and processors for responding to requests from set members to transmit a message to groups of users by creating and activating the necessary tree communication path distribution linkages. A distribution tree is created by the Tree Leader by generating a tree address using a random number generator. A tree address correlator is generated utilizing network and node identifiers unique for the network, and a list of subnodes or users connected for each member of the multicast tree set is generated. Using this information, a tree distribution path is computed to cover all of the subnodes required and a tree set up request message is sent by the Tree Leader along a computed path to each involved subnode. Each subnode returns a message indicating whether the tree address is already in use or is available for use. Successfully negotiated tree addresses are marked at the path link initiation and termination points at each node through the network.

Multicast communication tree creation and control method and apparatus

A method is disclosed for determining whether to use a preempt/resume protocol or an alternate protocol in transmitting data packets from a local system to a remote system. Each system informs the other whether it supports preempt/resume and provides the sizes of the largest low priority data packets it can send and receive. The local system always elects the alternate protocol unless both support preempt/resume. The local system then selects the lesser of (a) the largest low-priority data packet it can send and (b) the largest low-priority data packet the remote system can receive. Use of prompt/resume is initiated by the local system only where a packet of the selected size would be delayed in reaching the remote system by more than a predetermined interval.

Method of determining whether to use preempt/resume or alternate

Each node in a multinode communication system is provided with programming to act as a Set Manager for a given set of nodes and users. Functions of the Set Manager include operation processes for creating distribution trees for efficient multicast and bandwidth reservation tasks. Because set membership is not necessarily fixed or accurate at the time the distribution tree is created, the Tree Leader task that creates and maintains the trees needs accurate and updated information showing the number of users at the nodes it serves which are participating in the distribution tree. The count of active users at nodes served by the Tree Leader is provided in response to an indicia established at the time the Tree Leader sets up the tree. Each Set Manager at a given node monitors for changes in set membership and link failure and notifies the requesting Tree Leaders for each tree in which it participates whenever changes in the number of users either by joining or leaving the set or link failures occur by direct communication between the Set Managers and the Tree Leaders without requiring intervention of other elements in the system.

Maintenance of message distribution trees in a communications network

The present invention is an improvement in a known LOCATE process used to locate resources in a computer network. The known LOCATE process always requires that information about a target resource be verified by forwarding a LOCATE request to the node owning the target resource. The present invention improves upon this process by use of selective verification. If predetermined conditions are met, a node in the network may reply to a received LOCATE request by using information about the target resource found in its cache directory. The LOCATE request need not be propagated to the node owning the target resource except for predetermined types of sessions or where past attempts to use selective verification have not been successful.

System for locating a node containing a requested resource and for

Enhanced type 2.1 nodes for SNA networks provide network routing of information between non-adjacent network nodes and program-to-program linkage across the network. These nodes are called 'advanced peer to peer networking' (abbreviated APPN) nodes. Network state information, describing the topology and resources of the network is disseminated betweeen APPN nodes by a first data link control exchange of identification (XID) information indicating node type (and thereby distinguishing APPN nodes from other nodes) and other exchanges conducted over a newly defined control point to control point (abbreviated CP--CP) session having a message architecture unique to APPN type nodes. The XID exchange is conducted whenever a link between nodes is activated, and when the exchanging nodes are both APPN, and if both are available to participate in as CP--CP session, they automatically engage in a second exchange of session binding signals which establish a pair of sessions between the nodes. By internal conventions, the node components which use the session pair for exchanging their network state information adapt the sessions to be used in simplex modes with one session flowing from one node to the other and the other flowing in reverse from the other node to the one node. Within these sessions, for the sake of efficiency, communications are not directly acknowledged. Instead, a process transparent to the sessions monitors for link failure and upon such occurrence notifies all affected components to terminate their use of the session and deactivate the session.

Node initiating XID exchanges over an activated link including an

In a communications network, each network node can maintain its own list of network resources in a topology database. When the state of a resource 'owned' by a particular node changes, that node broadcasts a topology database update (TDU) message to adjacent nodes. Each adjacent node updates its own topology database and rebroadcasts the message. To minimize the amount of information that must be included in TDU messages when two nodes are reconnected after an outage, each node assigns flow reduction sequence numbers (FRSNs) to TDU meassages and keeps a record of the FRSN for the last TDU message sent to an adjacent node. The node also records, for each resource in its database, the FRSN of the last TDU message including that resource. When two nodes are reconnected, the sending node includes in the TDU message only those resources having a FRSN greater than the FRSN assigned to the last TDU sent to the adjacent node to which the TDU message is directed.

Method of reducing the amount of information included in topology

The links in a data communications network following Systems Network Architecture may be categorized as limited resource links if those links are shared access transport facilities, such as a switched telephone network, X.21, X.25 or token ring local area network facilities. In setting up LU--LU sessions between network users, a limited resource session identifier field is set to a specific value if any of the links in the session data path is defined as a limited resource link. When a conversation between two users ends, the primary logical unit responds by determining whether the session has been identified as a limited resource session. If it has, the primary logical unit initiates action to deactivate the session without waiting for network control operation action. Allowing the primary logical unit to deactivate a limited resources session assures that the limited resource link or links will not remain allocated needlessly to an unused session.

Method of controlling limited resource sessions in a data communications

Growing community of inventors

Pittsboro, NC, United States of America

John E Drake, Jr