International Business Machines Corporation

Shlomit Sarah Pinter

Michael Edward Factor

Gera Goft

Esther Yeger-Lotem

Dean Har'el Lorenz

Aviad Zlotnick

Leah Shalev

Shachar Fienblit

Mark Robert Funk

Paula Kim Ta-Shma

Alain Charles Azagury

Guy Laden

Alan Jay Wecker

Sara Porat

Dimitry Kloper

Mati Golani

Kenneth A Daniels

Andrew J Mauer

Esther Yeger Lotem

A method, system and computer program product is disclosed for scheduling data packets in a multi-processor system comprising a plurality of processor units and a multitude of multicast groups. The method comprises associating one of the processor units with each of the multicast groups, receiving a multitude of data packets from the multicast groups, and scheduling all of the data packets received from each of the multicast groups for processing by the one of the processor units associated with said each of the multicast groups. In one embodiment, scheduling is based on affinity of both transmit and received processing for multiple connections to a processor unit. In another embodiment, a system call is provided for transmitting the same data over multiple sockets. Additional system calls may be used for building multicast group socket lists.

Data affinity based scheme for mapping connections to CPUs in I/O adapter

A method for managing data, the method includes: providing a write-back cache unit coupled to at least one storage unit; receiving a request to write a new data version to a certain cache data allocation unit; determining, in response to a data storage policy, whether to overwrite a cached data version being cached in the certain cache data allocation unit or to perform a destage of the cached data version to a first storage unit before writing the new data version to the certain cache allocation unit; receiving a request to read a data version that corresponds to a certain point in time and scanning a first data structure representative of write operations and a second data structure representative of revert operations to determine a location of the requested data version.

System, method and computer program product for managing data using a write-back cache unit

A method for process modeling includes reading a record of executions of a process including at least first and second activities, and identifying in one of the executions in the record respective first and second lifespans of the first and second activities, defined by respective initiating and finish events, such that the initiating event of the second lifespan occurs during the first lifespan. A graphic model of the process is generated, so as to reflect a concurrency of the first and second activities, responsively to occurrence of the initiating event of the second lifespan during the first lifespan.

Automatic generation of process models

Techniques for facilitating communication between a first group communication system and a second group communication system. A naming convention of the first group communication system allows at least one name which contravenes a naming convention of the second group communication system. A communicator is joined to the second group communication system. The communicator was previously joined to the first group communication system and has a first name at the first group communication system. The communicator has a second name at the second group communication system. The second name can be requested from the second group communication system. The second name can also be generated by applying an algorithm to the first name. A processor performs translation between the first name and the second name in a communication between the communicator and the second group communication system. The translation is performed based on a translation data structure.

Extending name space size of legacy group communication systems

A method, device and computer program product for managing data versions. The method includes: (i) receiving a first request to generate a first version of a source volume; (ii) selectively updating a first control data structure that is indicative of changes of blocks of data associated with different versions of the source volume, in response to the first request, to reflect at least one latest modified block of data that was modified between a first point in time associated with the first version and between second point in time associated with a second version of the first source volume; wherein information representative of different versions of the source volume are stored in a target storage unit; and wherein blocks of data that remain unchanged between multiple versions of the source volume are shared between these multiple versions; wherein the first point in time follows the second point in time and wherein the at least one block data belongs to the volume; and (iii) selectively copying blocks of data from the source volume to the target volume in response to the content of the first control data structure.

System, method and computer program product for managing data versions

Method, device and computer program product for support of maintaining a system. The method includes: evaluating a current system state and detecting a first lattice element corresponding to the current system state; locating at least one state improvement path, within a lattice that represents states of the system, between the first lattice element and a second lattice element representative of a target system state; determining, for at least one state improvement path, rules that should be satisfied in order to reach the system target state; and determining how to fulfill the rules associated with at least one state improvement path.

Device, method and computer program readable medium for support of maintaining a system

A method for controlling operation of a computer software application running on a plurality of computing entities, which are members of a group of mutually-linked computing entities running the application within a distributed computing system. The method includes receiving an indication of a change in membership of the group together with a reason for the change. A membership change message is delivered to the members, so as to inform the members of the change and of the reason for the change.

Delivery of configuration change in a group

A group communication system (GCS), for use within a group of clustered computing nodes, provides a flexible group membership model. Flexible group members are defined generally as physical computing entities (such as computing nodes or other devices) or logical computing entities that take part in a distributed application. Such logical entities may include substantially any combination of processes, threads and callback functions. Logical entities that are members in the group may also be objects, such as files, that at least at some times during their existence have no active processes or threads. A single member may include multiple simultaneous processes.

Group communication system with flexible member model

A method for distributing messages among a group of member computing entities, which are mutually-linked in a distributed computing system. The members communicate in accordance with a communication protocol, which delivers a sequence of full-group multicast messages to all of the members in the group in an order that is uniform among all of the members. A sub-group is defined from among the members in the group, and a sub-group message is distributed to the members in the sub-group, such that the sub-group message is delivered to all of the sub-ground members in a uniform position with respect to the order of the full-group multicast messages, as well as with respect to other sub-group messages.

Ordered sub-group messaging in a group communications system

A method for controlling operation of a computer software application running on a given computing entity, which is a member of a group of mutually-linked computing entities running the application within a distributed computing system. The method includes selecting a partitioning strategy for the application from among a plurality of available strategies. When a message is received at the given computing entity indicative of a change in membership of the group, the given computing entity determines in accordance with the selected partitioning strategy whether the given computing entity belongs to a primary component of the group following the change in membership, such that running of the software application on the given entity is restricted if the entity does not belong to the primary component.

Middleware support for primary component in a partitionable cluster environment

A computer implemented technique for the static evaluation of the lifetime of objects allocated in memory is presented, which find application in reducing the overhead of generational garbage collection. The method combines pointer alias analysis with static object size determination, from which accurate generational assignment of newly created objects can be accomplished.

Growing community of inventors

Haifa, Israel

Shlomit Sarah Pinter