International Business Machines Corporation

Hewlett-packard Development Company, L.p.

Google Inc.

Dinesh Kumar Subhraveti

Prasenjit Sarkar

Gopalakrishnan Janakiraman

Yoshio Frank Turner

Jose Renato Santos

Karan Gupta

Marc Philippe Vertes

Philippe Bergheaud

David Lowell

Roger Lee Haskin

Himabindu Pucha

Reshu Jain

Mark James Seaman

Min Li

Richard Edwin Harper

Soumitra Sarkar

Jose Ranato Santos

Yoshio Tumer

Ahmed Mohammad Bashir

Samer Al Kiswany

Comeliu Mihail Constantinescu

Victor S Wen

A method for replicating a program and data storage according to one embodiment comprises sending program replication data from a first program to a second program, the second program having an application program that is a replica of an application program of the first program; sending data storage requests from the first program to a first storage system; and replicating data stored in the first storage system in a second storage system. Additional methods, systems, and computer program products are disclosed.

Continuously available program replicas

A method, system and program product for recording a program execution comprising recording processor context for each thread of the program, results of system calls by the program, and memory pages accessed by the program during an execution interval in a checkpoint file. Processor context includes register contents and descriptor entries in a segment descriptor table of the operating system. System calls are recorded for each program thread, tracked by an extension to the operating system kernel and include returned call parameter data. Accessed memory pages are recorded for each program process and include data, libraries and code pages. The program address space, processor context, and program threads are reconstructed from checkpoint data for replaying the program execution in a different operating system environment.

Partial recording of a computer program execution for replay

A method, computer program and system for controlling accesses to memory by threads created by a process executing on a multiprocessor computer. A page table structure is allocated for each new thread and copied from the existing threads. The page access is controlled by a present bit and a writable bit. Upon a page fault the access is provided to one thread. The kernel handles the new page entry creation process and set the page present bits to zero which creates page faults. In a second embodiment, two page table structures are created, one for one thread having access to the address space and the other page table structure shared by all the other threads not having access to the address space.

Method and system to manage memory accesses from multithread programs on multiprocessor systems

A mechanism for replicating programs executing on a computer system having a first storage means is provided. The mechanism identifies the events corresponding to requests from one executing program, which may be different from the executing program to be replicated, which are non-deterministic and identifies the 'Non Abortable Events' (NAE's), which change irremediably the state of the external world that need to be reproduced in the replay of the programs. These events are immediately transferred for replay and the executing program is blocked until the transfer is acknowledged. For the other non-deterministic events, they are logged and sent to the executing program, the executing programs remaining blocked only if the log is full and/or if a timer between two NAEs expires, in this case a log transfer to the standby machine is performed to prepare replication before unblocking of the executing program.

Transfer of event logs for replication of executing programs

Embodiments of the invention relate to a shared group of resource and efficient processing of one or more jobs in the share group of resources. Tools are provided in the shared group of resource to assess and organize a topology of the shared resources, including physical and virtual machines, as well as storage devices. The topology is stored in a known location and utilized for efficient assignment of one or more jobs responsive to the hierarchy.

Efficient execution of jobs in a shared pool of resources

Embodiments of the invention relate to data replication and block allocation in a file system to support write transactions. Regions in a cluster file system are defined to support a block allocation. Blocks in the defined regions are allocated to support the data replication. A pipeline manager is provided to schedule population of the blocks in the allocated region(s) based upon network characteristics.

Snapshot based replication

Embodiments of the invention relate to block layout and block allocation in a file system to support transparency of application processing. At least one copy of an application is replicated in a write affinity region of a secondary server, and at least one copy of the application is replicated in a wide striping region across a cluster file system. When the application is subject to failure, application processing is transferred from the failure location to the write affinity copy. At the same time, the failed application is rebuilt using the wide striping replication of the application. Once the application is rebuilt, processing may return to the failed location employing the rebuilt application.

Application recovery in a file system

Provided are a method, system, and program for gathering pages allocated to an application to include in checkpoint information. A call from an application is intercepted to allocate memory pages to cause indication of pages allocated to the application that have modified data. An operation is initiated to create checkpoint information for the application. Pages allocated to the application that have modified data are determined in response to the operation to create the checkpoint information. The determined pages are saved in the checkpoint information.

Gathering pages allocated to an application to include in checkpoint information

Embodiments of the invention relate to co-migration in a shared pool of resources with similarity across data sets of a migrating application. The data sets are processed and profiled. Metadata is reviewed to remove duplicate elements and to distribute the processing load across available nodes. At the same time, a ranking may be assigned to select metadata to support a prioritized migration. Non-duplicate data chunks are migrated across the shared pool of resources responsive to the assigned prioritization.

Virtual machine image co-migration

Mechanisms for managing task events during the scheduling period of a task executing on a processor. Only events of specific portions of the scheduling period are logged, wherein a first shared resource access has been granted for the task, this portion of the scheduling period involving gathering all the non-deterministic events which cannot be replayed by simple task re-execution. Other independent non-deterministic event records are still logged as usual when they occur out of the portion of the scheduling period for which a record has been created. This limits the number of logged events during a recording session of an application and limits the frequency of events to transmit from the production machine to the replay machine.

Growing community of inventors

Milpitas, CA, United States of America

Dinesh Kumar Subhraveti