Parallel computer, and job information acquisition method for parallel computer

A computer-readable recording medium having stored therein a job information acquisition program for a parallel computer including a plurality of calculation nodes executing a calculation job distributively in parallel and a management node managing the plurality of calculation nodes, the job information acquisition program causing the parallel computer to execute a process comprising:

• acquiring job information about a calculation job handled by each of the calculation nodes according to a period timing common to the calculation nodes;
• retaining the job information in a retention unit of each of the calculation nodes, which enables retention of job information corresponding to a plurality of periods, in association with an identification number identifying the period timing at which the job information is acquired;
• when a transmission request for the job information about a designated identification number is received from the management node, transmitting job information about the designated identification number to the management node in a case where the job information about the designated identification number exists in the retention unit, and transmitting job information about an identification number just before the designated identification number to the management node in a case where the job information about the designated identification number does not exist in the retention unit and the job information about the identification number just before the designated identification number exists in the retention unit;
• retaining the job information in a retention unit of the management node, which enables retention of job information corresponding to a plurality of periods with respect to each of the calculation nodes, when the job information is received from each of the calculation nodes according to the transmission request;
• retaining, as a snapshot, job information of the same identification number when the job information of the same identification number about the calculation nodes is detected in the retention unit of the management node;
• clearing job information other than the job information of the same identification number retained in the retention unit of the management node;
• transmitting a clear request to each of the calculation nodes when the job information of the same identification number is retained as a snapshot;
• and
• clearing all the job information retained in the retention unit of the calculation node when the clear request is received from the management node.

A job information acquisition method for a parallel computer including a plurality of calculation nodes executing a calculation job distributively in parallel and a management node managing the plurality of calculation nodes, the job information acquisition method comprising:

• acquiring job information about a calculation job handled by each of the calculation nodes according to a period timing common to the calculation nodes;
• retaining the job information in a retention unit of each of the calculation nodes, which enables retention of job information corresponding to a plurality of periods, in association with an identification number identifying the period timing at which the job information is acquired;
• when a transmission request for the job information about a designated identification number is received from the management node, transmitting job information about the designated identification number to the management node in a case where the job information about the designated identification number exists in the retention unit, and transmitting job information about an identification number just before the designated identification number to the management node in a case where the job information about the designated identification number does not exist in the retention unit and the job information about the identification number just before the designated identification number exists in the retention unit;
• retaining the job information in a retention unit of the management node, which enables retention of job information corresponding to a plurality of periods with respect to each of the calculation nodes, when the job information is received from each of the calculation nodes according to the transmission request;
• retaining, as a snapshot, job information of the same identification number when the job information of the same identification number about the calculation nodes is detected in the retention unit of the management node;
• clearing job information other than the job information of the same identification number retained in the retention unit of the management node;
• transmitting a clear request to each of the calculation nodes when the job information of the same identification number is retained as a snapshot;
• and
• clearing all the job information retained in the retention unit of the calculation node when the clear request is received from the management node.