摘要:
Requested processing time of each batch job is complied with. A resource-correction control server calculating an amount of a resource required for setup of a batch application includes an intermediate-process-unit-data acquiring unit that compiles data of completed batch processes as a single data set at a predetermined time point, a resource-correction determining unit that, using the intermediate process unit, determines a process progress rate that is a progress rate of a process at the current time point and whether the process progress rate has reached a required progress rate that is a progress rate required to terminate the batch process within the requested processing time, and an allocation-resource calculating unit that, as a result of the determination, if the required progress rate has not been reached, calculates the amount of the resource required for recovery of the delay based on a delay-recovery-object progress rate and resource information.
摘要:
In registering operation of a document to be searched for, a document identifier management table for managing a range of a document identifier stored for each page and a page identifier of the page is created, and an individual-search-server's search range management table for managing the range of the document identifier in charge of each search server is created. In searching operation of each search server of the document to be searched for, the individual-search-server's search range management table is referred to acquire a range of the allocated document identifier. For each index key forming a query term specified as a query condition, the document identifier management table is referred to to acquire the page identifier storing the document identifier of the allocated range. The searching operation is carried out by referring to a page shown by the acquired page identifier.
摘要:
In registering operation of a document to be searched for, a document identifier management table for managing a range of a document identifier stored for each page and a page identifier of the page is created, and an individual-search-server's search range management table for managing the range of the document identifier in charge of each search server is created. In searching operation of each search server of the document to be searched for, the individual-search-server's search range management table is referred to acquire a range of the allocated document identifier. For each index key forming a query term specified as a query condition, the document identifier management table is referred to to acquire the page identifier storing the document identifier of the allocated range. The searching operation is carried out by referring to a page shown by the acquired page identifier.
摘要:
A parallel distributed processing system includes multiple parallel distributed processing execution servers which stores data blocks pre-divided in a storage device and executes tasks processing the data blocks in parallel, and a management computer controlling the multiple parallel distributed processing execution servers. The management computer collects resource use amounts of the multiple parallel distributed processing execution servers, acquires states of data blocks and tasks held by the multiple parallel distributed processing execution servers, selects a second parallel distributed processing execution server transferring a data block to the first parallel distributed processing execution server, based on processing progress situations of the data blocks held by the multiple parallel distributed processing execution servers and the resource use amounts of the multiple parallel distributed processing execution servers, and transmits a command to transfer the data block to the first parallel distributed processing execution server, to the selected second parallel distributed processing execution server.
摘要:
A parallel distributed processing system includes multiple parallel distributed processing execution servers which stores data blocks pre-divided in a storage device and executes tasks processing the data blocks in parallel, and a management computer controlling the multiple parallel distributed processing execution servers. The management computer collects resource use amounts of the multiple parallel distributed processing execution servers, acquires states of data blocks and tasks held by the multiple parallel distributed processing execution servers, selects a second parallel distributed processing execution server transferring a data block to the first parallel distributed processing execution server, based on processing progress situations of the data blocks held by the multiple parallel distributed processing execution servers and the resource use amounts of the multiple parallel distributed processing execution servers, and transmits a command to transfer the data block to the first parallel distributed processing execution server, to the selected second parallel distributed processing execution server.
摘要:
Requested processing time of each batch job is complied with. A resource-correction control server calculating an amount of a resource required for setup of a batch application includes an intermediate-process-unit-data acquiring unit that compiles data of completed batch processes as a single data set at a predetermined time point, a resource-correction determining unit that, using the intermediate process unit, determines a process progress rate that is a progress rate of a process at the current time point and whether the process progress rate has reached a required progress rate that is a progress rate required to terminate the batch process within the requested processing time, and an allocation-resource calculating unit that, as a result of the determination, if the required progress rate has not been reached, calculates the amount of the resource required for recovery of the delay based on a delay-recovery-object progress rate and resource information.