International Business Machines Corporation

James R Challenger

Louis Degenaro

James R Giles

Rohit Wagle

Paul Reed

Arun Kwangil Iyengar

George Prentice Copeland

Paul Michael Dantzig

Mark Holmes Linehan

Edward Adam Epstein

Gabriela Jacques Da Silva

Burn Lewin Lewis

Subbarao K Meduri

Gerald A Spivak

Jaroslaw Cwiklik

Rajesh Agarwalla

A distributable and serializable finite state machine and methods for using the distributable and serializable finite state machine are provided wherein finite state machine instance can be location-shifted, time-shifted or location-shift and time-shifted, for example by serializing and deserializing each instance. Each instance can be located-shifted between agents, and a persistent memory storage location is provided to facilitate both location-shifting and time-shifting. Finite state machine instances and the actions that make up each instance can be run in a distributed fashion among a plurality of agents.

Distributable serializable finite state machine

A system for processing analytics on a cluster of computing resources may receive a user request to process a Job, Service or Reservation, and may include an Orchestrator, Resource Manager, Process Manager, and one or more Agents and Job Drivers, which together deploy the Job onto one or more nodes in the cluster for parallelized processing of Jobs and their associated work items.

Distributed UIMA cluster computing (DUCC) facility

Methods and systems are provided for unified job processing of interdependent heterogeneous tasks within a domain containing a plurality of nodes. Jobs containing components to be processed in the domain are submitted and are identified by type. A job control flow associated with the job type is identified and used to process the components of the job on various nodes within the domain. Multiple job control flows are handled simultaneously, and provisions are made for sharing common job components among jobs. The job control flow utilizes a finite state machine where a given instance of the finite state machine applies to a specific job type. The finite state machine can be expressed using extensible mark-up language schema.

Unified job processing of interdependent heterogeneous tasks using finite state machine job control flow based on identified job type

Plug-in configurable middleware is provided for managing distributed applications. The middleware includes at least one core runtime engine configured as a plurality of concurrent instantiations on one or more hosts within a distributed architecture. These hosts can represent separate nodes or a single node within the architecture. Each core runtime engine instance provides the minimum amount of functionality required to support the instantiation of one or more plug-ins within that core runtime engine instance. Each core runtime engine instance is in communication with other concurrent core runtime engine instances and can share the functionality of plug-in instances with the other core runtime engine instances, for example through the use of proxies. A plurality of personalities representing pre-defined functions is defined and one of more of these personalities is associated with each core runtime engine instance. A plurality of pre-defined plug-ins are defined and associated with the personalities.

Distributed pluggable middleware services

A method is provided for the recovery of an instance of a job manager running on one of a plurality of nodes used to execute the processing elements associated with jobs that are executed within a cooperative data stream processing system. The states of the processing elements are checkpointed to a persistence mechanism in communication with the job manager. From the checkpointed processing element states, the state of each distributed job is determined and checkpointed. Processing element states are also checkpointed locally to the nodes one which the processing elements are running. Following a failure of the job manager, the job manager is reinstantiated on one of the nodes. The recovery instance of the job manger obtains state data for processing elements and jobs from the persistence mechanism and constructs an initial state for jobs and processing elements. These initial states are reconciled against the current states of the processing elements and adjustments are made accordingly. Once the job and processing element states are reconciled, the system is returned to normal operation.

Distributed job manager recovery

Distributable and serializable finite state machine

Finite state machines are provided to run instances of user-defined routines within a computing system. The finite state machines and updates to the finite state machines are user-defined and are checked for compliance with one or more prescribed schemas by a finite state machine engine. Compliant finite state machine specifications are interpreted for the plurality of states and transitions that constitute the finite state machine. Requested instances of a finite state machine specification are initiated by the finite state machine engine, which creates proxies to monitor the current state of any given requested instance.

Data-driven finite state machine engine for flow control

A determination can be made of how changes to underlying data affect the value of objects. Examples of applications include: caching dynamic Web pages; client-server applications whereby a server sending objects (which are changing all the time) to multiple clients can track which versions are sent to which clients and how obsolete the versions are; and any situation where it is necessary to maintain and uniquely identify several versions of objects, update obsolete objects, quantitatively assess how different two versions of the same object are, and/or maintain consistency among a set of objects. A directed graph, called an object dependence graph, may be used to represent the data dependencies between objects. Another aspect is constructing and maintaining objects to associate changes in remote data with cached objects. If data in a remote data source changes, database change notifications are used to 'trigger' a dynamic rebuild of associated objects. Thus, obsolete objects can be dynamically replaced with fresh objects. The objects can be complex objects, such as dynamic Web pages or compound-complex objects, and the data can be underlying data in a database. The update can include either: storing a new version of the object in the cache; or deleting an object from the cache. Caches on multiple servers can also be synchronized with the data in a single common database. Updated information, whether new pages or delete orders, can be broadcast to a set of server nodes, permitting many systems to simultaneously benefit from the advantages of prefetching and providing a high degree of scaleability.

Growing community of inventors

Garrison, NY, United States of America

James R Challenger