International Business Machines Corporation

Bmc Software, Inc.

Nigel G Slinger

Wen Jie Zhu

John Benjamin Tobler

Shu Wang

Min Fang

Li Fei Zheng

Di Jin

Zhen Yu Shi

Arthur Marais

Daniel Kozin

Wenjie Zhu

Christopher J Munson

Sudipta Sengupta

Meichi M Lin

Zhenyu Shi

Roxanne Kallman

Wen J Zhu

John Flournoy

John Joseph Campbell

Catherine E Drummond

Jeremy Riegel

Catherine Drummond

Terence Patrick Purcell

Thomas Abel Beavin

David R Moy

Matt Helliwell

Jerome P Kenyon

Maggie M Lin

Timothy E McAllister

Bart J L Steegmans

Mei Zhen Cao

A data stream of performance metrics characterizing a technology landscape may be received. From a plurality of performance prediction models and based on the performance metrics, a subset of performance prediction models may be selected. The subset of performance prediction models may be combined into a composite prediction model. The composite prediction model may be loaded into a model processor for scoring against the data stream of performance metrics to obtain a performance prediction for the technology landscape based thereon.

Performance prediction using dynamic model correlation

A technology landscape may be characterized using a performance characterization that includes scores assigned to performance metrics for the technology landscape and using at least one trained machine learning model. In response to a detected calibration trigger, a calibratable performance metric of the performance metrics may be determined. A relationship may be determined between conforming values of the calibratable performance metric during a conforming period for which the at least one trained machine learning model was trained, and non-conforming values of the calibratable performance metric occurring during a calibration period initiated by the calibration trigger. In this way, a score assigned to the calibratable performance metric may be calibrated, based on the relationship.

Short-term model calibration in system monitoring

An event graph schema for a technology landscape may be determined, where the technology landscape is characterized using scores assigned to performance metrics. The event graph schema may include a plurality of nodes corresponding to the performance metrics and the scores, and directional edges connecting node pairs of the plurality of nodes, with each directional edge having a score-dependent validity criteria defined by scores of a corresponding node pair. Anomalous scores associated with an event within the technology landscape may be used to find anomalous nodes. Valid edges connecting two of the anomalous nodes and satisfying the score-dependent validity criteria thereof may be used to determine at least one path that includes the valid edges and connected anomalous nodes. In this way, it is possible to traverse the at least one path to identify at least one of the connected anomalous nodes as a root cause node of the event.

Using an event graph schema for root cause identification and event classification in system monitoring

When a restart event is detected within a technology landscape, restart-impacted performance metrics and non-restart-impacted performance metrics may be identified. The non-restart-impacted performance metrics may continue to be included within a performance characterization of the technology landscape. The restart-impacted performance metrics may be monitored, while being excluded from the performance characterization. The restart-impacted performance metric of the restart-impacted performance metrics may be transitioned to a non-restart-impacted performance metric, based on a monitored value of the restart-impacted performance metric following the restart event.

Restart tolerance in system monitoring

Computer program products and a system for managing processing resource usage at a workload manager and an application are described. The workload manager and application may utilize safe stop points to reduce processing resource usage during high cost processing periods while preventing contention in the processing resources. The workload manager and application may also implement lazy resumes or processing resource utilization at the application to allow for continued reduced usage of the processing resources.

Intelligent contentionless processing resource reduction in a multiprocessing system

Embodiments of the present invention disclose a method, computer program product, and system for inserting one or more records into a database table. An insert request for inserting a new record to a database table is received, wherein the new record includes at least one key field. a partial identity of at least one record matching the at least one key field of the new record is searched for. A partial identity is assigned to the new record based on a result of the searching.

Record insertion by generating unique index bases

Data records may be managed in a relational database by monitoring, a record length for a first data record in a page of memory, an amount of free space in the page, and a page length. In response to receiving an operator command to replace the first data record with a second data record, a database management system may determine whether an estimated record length of a compressed second data record is outside of the amount of free space in the page. In response to determining the estimated record length of a compressed second data record is outside of the amount of free space in the page, the database management system may determine whether an estimated length of a compressed page is outside of the page length. In response to determining the estimated length of a compressed page is within the page length, the page may be compressed.

Managing data records

An approach for index B-tree page creation associated with linear sequential insertions in database management systems (DBMS). A linear pre-splitter receives a current index leaf page for linear sequential insertion. The linear pre-splitter asynchronously creates index leaf pages where the current index leaf page is in a predetermined position at least one page away from a last index leaf page. The linear pre-splitter updates index leaf page position identifiers associated with the index leaf pages where the index leaf page position identifiers link the index leaf pages and the last index leaf page and the linear pre-splitter inserts index leaf page identifiers and index key metadata associated with each of the index leaf pages into index non-leaf pages.

Index B-tree maintenance for linear sequential insertion

Allocating free space in a database table. Statistics associated with records in a database are received, including an average record byte size for records stored in the database table. A primary free space byte size for record updates is determined, including comparing a preliminary free space byte size to the average record byte size and a byte size of a record subjected to a database operation. Based on the primary free space byte size, free space at the page level of the database table is allocated.

Allocating free space in a database

Embodiments of the present invention provide computer-implemented methods, computer systems and computer program products. According to one embodiment of the present invention, an index of a database is obtained, where the index includes at least one node associated with index information of at least one old data entry that has been deleted from the database, and the node is marked as invalid. Then, a node included in the index is selected based on a key value in index information of a new data entry in response to the new data entry being inserted into the database. Next, the selected node is updated with the index information of the new data entry.

Index management

According to one embodiment of the present invention, a system for processing a database query stores one or more result sets for one or more first database queries in a data store. The system receives a second database query and compares the second database query to the one or more first database queries to determine presence of a corresponding result set in the data store for the second database query. The system provides the corresponding result set from the data store for the second database query based on the comparison. Embodiments of the present invention further include a method and computer program product for processing a database query in substantially the same manners described above.

Dynamic result set caching with a database accelerator

As disclosed herein a method, executed by a computer, includes storing, by one or more processors, entries associated with an index to a first buffer of at least two buffers allocated to the index, and moving, by a batch operation, by one or more processors, entries in the first buffer into an index page for the index in response to an entry movement condition being met. The method further includes storing, by one or more processors, new entries associated with the index to another buffer of the at least two buffers while moving the entries in the first buffer. A computer program product corresponding to the above method is also disclosed herein. A computer program product and computer system corresponding to the above method are also disclosed herein.

Growing community of inventors

Los Gatos, CA, United States of America

Nigel G Slinger