Equipe Communications Corporation

Ciena Corporation

Daniel J Sullivan, Jr

Joseph D Kidder

Barbara A Fox

Nicholas A Langrind

Terrence S Pearson

Brian Branscomb

Darryl Black

James R Perry

Thomas R Perry

Corey Simons

Chris R Noel

Peter Pothier

Jonathan D Madsen

Christine Pecina

Richard L Whitesel

Umesh Bhatt

The present invention provides methods and apparatus for decoupling functional processes, such as network protocol applications and device drivers, from hardware resources through the use of logical resources. Logical resources are created to represent the hardware resources within a computer system and a map is created which associates each logical resource with each hardware resource. Functional processes are associated with the logical resources instead of with the hardware resources such that a functional process may be moved to a different hardware resource simply by changing the map to associate the logical resource associated with the functional process with a different hardware resource.

Decoupling processes from hardware with logical identifiers

The present invention provides a method for upgrading embedded configuration databases while a network device is operating and with minimal disruption to network device operation. While a network device is operating and using an embedded primary configuration database, an embedded backup configuration database stops performing as a backup database and is upgraded. The upgraded configuration database is then switched over to become the primary configuration database. The original primary configuration database may immediately become the backup configuration database, or the original primary configuration database may remain unchanged until the upgrade is committed. If the upgrade is not committed, for example, due to errors, then the original primary configuration database may be quickly switched over to again become the primary configuration database. As a result, embedded configuration databases may be upgraded while a network device is operating and with minimal disruption to network device operation.

Method for upgrading embedded configuration databases

Methods are disclosed for establishing a path for data transmissions in a system having a plurality of possible paths by creating a configuration database and establishing internal connection paths based upon a configuration policy and the configuration database. The configuration policy can be based on available system resources and needs at a given time. In one embodiment, one or more tables are initiated in the configuration database to provide connection information to the system. For example, a path table and a service endpoint table can be employed to establishing a partial record in the configuration database whenever a user connects to a particular port on a universal port card in the system. The method can further include periodically polling records in the path table and transmitting data from the partial records to a policy provisioning manager (PPM). The PPM then implements a connection policy by comparing one or more of the new path characteristics, to the available forwarding card resources in the quadrant containing the universal port card port and path. The path characteristics can include the protocol, the desired number of time slots, the desired number of virtual circuits, and any virtual circuit scheduling restrictions. The PPM can also take other factors into consideration, including quality of service, for example, redundancy requirements or dedicated resource requirements, and balancing resource usage (i.e., load balancing) evenly within a quadrant.

Policy based provisioning of network device resources

Computer systems and methods of data processing are disclosed in which fault/event management is carried out in accordance with a configurable fault recovery policy. In addition, computer systems and methods of data processing are disclosed in which hierarchical levels of fault management (or more generally 'event' management) are provided in accordance with the configurable fault policy.

Configurable fault recovery policy for a computer system

Computer systems and methods of data processing are disclosed in which hierarchical levels of fault/event management are provided that intelligently monitor hardware and software and proactively take action in accordance with a defined fault policy. A fault policy based on a defined hierarchy ensures that for each particular type of failure the most appropriate action is taken. In one embodiment, a master Software Resiliency Manager (SRM) serves as the top hierarchical level fault/event manager, with one or more slave SRMs serving as the next hierarchical level fault/event manager. The software applications resident on each board can also include sub-processes (e.g., local resiliency managers or LRMs) that serve as the lowest hierarchical level fault/event managers.

Hierarchical fault management in computer systems

A distributed software redundancy design is disclosed to minimize network outages and other problems associated with component/process failures by spreading software backup (in the so-called &ldquo;hot state&rdquo;) across multiple elements. The distributed redundancy architecture of the present invention also permits the location of the hardware backup element to float, that is, if a primary element fails, the functions can be transferred over to the backup element. When the failed primary element is replaced, the replacement hardware can serve as the hardware backup. If one or more of the primary processes on a particular element experiences a software fault, the processor on the line card may terminate and restart the failing process or processes. Once the process or processes are restarted, a copy of the last known dynamic state (i.e., the backup state) can be retrieved a from corresponding backup processes executing on a second line card and initiate an audit process to synchronize retrieved state with the dynamic state of associated other processes.

Distributed process redundancy

The invention provides a method for fault isolation in a computer system, such as a network device. The method calls for providing a plurality of modular processes, and forming groups, based on hardware in the computer system, of one or more of the plurality of modular processes. A fault within a group is detected, and recovery from the detected fault is accomplished without affecting processes or hardware in other groups.

Vertical fault isolation in a computer system

The present invention provides a computer system having a modular control process, and a modular device driver process that works in conjunction with the control process. The device driver process is capable of continuing operation even if the control process is terminated, for example, upon detection of a fault. In one aspect, the invention provides a network device that includes a control plane and a data plane. The control plane includes a modular control application for establishing and terminating network connections, and the data plane has an independent, modular device driver process for transmitting data over network connections established by the control application. The device driver process is capable of continuing to transmit data over established network connections even if the control application is terminated.

Independent restoration of control plane and data plane functions

The present invention provides a method and apparatus for supporting multiple redundancy schemes in a single network device. In one network device, various redundancy schemes are supported including 1:1, 1&plus;1, 1:N, no redundancy or a combination of redundancy schemes. In addition, the redundancy scheme or schemes for physical network device cards (i.e., universal port cards) or ports may be different from the redundancy scheme or schemes for forwarding network device cards. For example, a network manager may want to provide 1:1 or 1&plus;1 redundancy for all universal port cards and/or ports but only 1:N redundancy for each N group of forwarding cards. As another example, the network manager may provide certain customers with 1:1 redundancy on both universal port cards (or ports) and forwarding cards to ensure that customer's network availability while providing other customers, with lower availability requirements, with various other redundancy scheme combinations, for example, 1:1, 1&plus;1, 1:N or no redundancy for port cards or ports and 1:N or no redundancy for forwarding cards. The present invention allows customers having different availability/redundancy needs to be serviced by same network device.

Growing community of inventors

Hopkinton, MA, United States of America

Daniel J Sullivan, Jr