International Business Machines Corporation

James Liam Finnie

Xun Xue

Garret Frederick Swart

Stewart L Palmer

Matthew Albert Huras

Gopi K Attaluri

Aamer U Sachedina

Roger L Q Zheng

Piotr M Plachta

Keriley Kay Romanufa

Lan Pham

Adam J Storm

Sam Sampson Lightstone

Maheswaran Surendra

Christian Marcelo Garcia-Arellano

Yixin Diao

Ronen Grosman

Daniele Costante Zilio

Gary Valentin

Sunil Jeevananda Kamath

Kevin R Rose

Andrew David Buckler

Roger Luo Quan Zheng

Roger L Zheng

Taavi Andrew Burns

Roger Lq Zheng

In a shared data system comprising one or more primary nodes and a plurality of secondary nodes, global lock manager on a primary node manages locks for shared resources by exchanging an abstract lock state with local lock managers on the secondary nodes. The abstract lock state includes a particular representation of all of the applications on the nodes that are requesting or are granted locks. The exchange of these particular lock states instead of individual requests improves performance by increasing concurrency and reducing off-machine communication. A global deadlock detector on a node detects and resolves global deadlocks, in conjunction with local deadlock detectors on the secondary nodes.

Two-level management of locks on shared resources

Lock communications in a shared disk database system is reduced by several approaches: sending a single message to a lock manager for locks required for an operation and locks that will be required in the future, the operations may include row update, row delete, large scan, and row insert; performing an operation in two executions, where in a first execution locks required for the operation is determined without performing the operation, and in a second execution a single message is sent to a lock manager for the required locks and the operation is performed; in free space searching, sending a single message to a lock manager for row and page locks before a row insert is actually performed; and granting locks in an unfair manner.

Approaches to reducing lock communications in a shared disk database

Methods and systems are provided for tuning memory allocated among a plurality of applications in a data processing system. In one implementation, the method includes generating memory benefit data for the plurality of applications, comparing the generated memory benefit data associated with each of the plurality of applications, and dynamically reallocating memory from one or more of the plurality of applications to one or more other of the plurality of applications based on the comparison. A method and system is also provided for tuning memory allocated among a plurality of individual memory consumers for a given application.

Method and apparatus for distributing memory in a data processing system

A system and method for managing shared resources is disclosed. The system includes a primary coherency processing unit which processes lock requests from a plurality of data processing hosts, the primary coherency processing unit also storing a first current lock state information for the plurality of data processing hosts, the first current lock state information including a plurality of locks held by the plurality of data processing hosts. The system further includes a standby coherency processing unit storing fewer locks than the primary coherency processing unit, the locks stored by the standby coherency processing unit being a subset of locks included in the first current lock state information, the standby coherency unit configured to perform a plurality of activities of the primary coherency processing unit using the subset of locks in response to a failure of the primary coherency processing unit.

Improving data availability during failure detection and recovery processing in a shared resource system

A method and system for improving memory access patterns of software systems on NUMA systems discovers NUMA system resources where the NUMA system resources comprises a plurality of NUMA nodes; determines a plurality of database threads, processes, and objects for a database configuration; and generates a policy which assigns the plurality of database threads, processes, and objects to the plurality of NUMA nodes, wherein the generating of the policy is performed prior to initialization of the plurality of database threads, processes, and objects. The assignment of the database threads, processes, or objects to NUMA nodes is such that the amount of remote memory accesses is reduced. When the database thread, process, or object initializes, the database server queries the policy for its assigned NUMA node(s). The database thread, process, or object is then bound to the assigned NUMA node(s).

System and method for optimally configuring software systems for a NUMA platform

Growing community of inventors

Toronto, Canada

James Liam Finnie