Data processing using different data formats based on shared resource utilization

摘要

When a plurality of jobs are processed using a plurality of data processing units, data formats of the jobs to be processed can be determined to distribute a data processing load of the data processing units. A method for controlling a data processing apparatus for causing a plurality of data processing units to process data of a job includes storing data of a first job in a storing unit in first and second data formats, determining whether to process the stored data of the first job in the first or second data format, and causing the plurality of data processing units to process the data in the determined data format. The determination is made based on whether processing of data of a second job by the first or second processing unit requires longer time.

主权项

1. A data processing apparatus for processing data of a job, the apparatus comprising:
a storing unit configured to store data of a first job in both a first data format and a second data format, where time for a second data processing of the data in the first data format is longer than time for a first data processing of the data in the first data format, and where time for the first data processing of the data in the second data format is longer than time for the second data processing of the data in the second data format; a processor configured to select one of the first data format and the second data format as a data format used to process the data of the first job, based on whether each of the first and second data processing is performed on data of a second job and based on whether time for the first data processing of the data of the second job or time for the second data processing of the data of the second job is longer, the second job being executed in parallel to the first job, the second job and the first job utilizing at least one same resource in order to perform each of the first and second data processing; and the processor is configured to cause at least one of the first and second data processing to be performed on the data in the selected data format for the first job.