International Business Machines Corporation

Shaorong Liu

Sam Sampson Lightstone

Xing Yi Chen

Ilya Volvovski

Manish Motwani

Ethan S Wozniak

Thomas Abel Beavin

Naresh K Chainani

David C Kalmuk

Jordan Harrison Williams

Paul C Huffman

Anthony J Baldocchi

Edison Lao Ting

David C Sharpe

Chi Man J Sizto

A method for execution by a request scheduler includes receiving a set of requests for execution from at least one request issuer. Resource requirements are determined for each of the set of requests, and current resource availability data is determined for resources indicated in the resource requirements. Scheduling data is generated for the set of requests based on the resource requirements and the current resource availability data. A first subset of the set of requests are added to a queue in response to the scheduling data indicating the first subset of the set of requests be queued for execution. Execution of the set of requests is facilitated in accordance with the scheduling data by facilitating immediate, simultaneous execution of a second subset of the set of requests and by facilitating serial execution of the first subset of the set of requests.

Scheduling requests based on resource information

Performing a join of first and second database tables for a query includes applying a predicate of the query to the first table as a first predicate and determining how many distinct join key values the first table has that survive the applying of the first predicate, wherein a join key value of the first table that survives the applying of the first predicate is a surviving join key value for a second predicate. A selection includes selecting among applying the second predicate to the second table, probing the second table with the second predicate, and neither applying the second predicate to the second table nor probing the second table with the second predicate, wherein the selecting is responsive to the number of distinct, surviving join key values.

Technology for join processing

Methods, devices and computer program products for performing predicate evaluation on a compressed variable length character string are disclosed. Aspects include determining upper and lower boundaries of a false positive range for a predicate, the false positive range for the predicate being a range in which a result of the predicate evaluation may lead to a false positive error. Aspects also include compression-encoding the upper and lower boundaries of the false positive range and performing a first comparison for comparing the compressed variable length character string with the compression-encoded upper and lower boundaries of the false positive range. Aspects further include determining a result of the predicate evaluation based on at least a result of the first comparison processing.

Performing predicate evaluation on compressed character string of variable length

A computer-implemented method includes receiving a request to transmit column group data to a target node, the column group data comprising C columns within a column-oriented data table and determining a transmission row count R for transmitting the column group data to the target node. The method may also include transmitting a transmission packet comprising R sequentially-ordered data elements for each of the C columns to the target node. The R data elements for each column may be sequentially retrieved from memory. A corresponding method includes receiving, at a target node, a request to receive the column group data, determining the transmission row count R for receiving the column group data, and receiving a transmission packet comprising R sequentially-ordered data elements for each of the C columns and storing the sequentially-ordered data elements within memory. A corresponding computer system and corresponding computer program products are also disclosed herein.

Data transfers in columnar data systems

Techniques are disclosed for accessing a dimensional data model when processing a query. In one embodiment, the query is processed by performing a two-stage zigzag join operation including a zigzag main join and a zigzag back join. The zigzag main join is configured to generate a set of row identifiers of fact records satisfying any local predicates in the query. The zigzag back join is configured to generate query results based on the set of row identifiers. The query results are returned responsive to the query.

Accessing a dimensional data model when processing a query

Markup language node level hash join operations for evaluating a query language query are performed. The markup language node level hash join mechanism, i.e. the 'XHashJoin' operator, is a multi-way join operator that uses two hash tables, BUILD and PROBE, to intersect document nodes from multiple index scans and to buffer intermediate query results. The BUILD hash table stores document nodes matching the predicates of a query, and buffers document nodes satisfying extraction nodes, of each portion of the query up to a current portion of the query being evaluated. The BUILD hash table and the PROBE hash table are switched at each portion of the query being evaluated. Query results are generated by linking document nodes buffered in the BUILD hash table based on the semantics of each extraction node.

Growing community of inventors

Evanston, IL, United States of America

Shaorong Liu