Core file limiter for abnormally terminating processes
AssigneeInternational Business Machines Corporation
InventorsMichael E. Aho, John E. Attinella, Thomas M. Gooding
Life of this patent
Estimating the term…
Abstract
Computer program product and system to limit core file generation in a massively parallel computing system comprising a plurality of compute nodes each executing at least one task, of a plurality of tasks, by: upon determining that a first task executing on a first compute node has failed, performing an atomic load and increment operation on a core file count; generating a first core file upon determining that the core file count is below a predefined threshold; and not generating the first core file upon determining that the core file count is not below the predefined threshold.
Claims12
A parallel computing system, comprising:
- a plurality of compute nodes each executing at least one task, of a plurality of tasks, each compute node having at least a processor and a memory, wherein a first compute node, of the plurality of compute nodes, is configured to perform an operation to limit core file generation, by:
- upon determining that a first task executing on the first compute node has failed:
- performing, by the first task, an atomic load and increment operation on a core file count received from a leader node of the plurality of compute nodes;
- generating, by the first task, a first core file upon determining that the core file count is below a predefined threshold;
- and
- not generating, by the first task, the first core file upon determining that the core file count is not below the predefined threshold.
A computer program product to limit core file generation in a massively parallel computing system comprising a plurality of compute nodes each executing at least one task, of a plurality of tasks, the computer program product comprising:
- a non-transitory computer-readable storage medium having computer-readable program code embodied therewith, the computer-readable program code comprising:
- computer-readable program code configured to, upon determining that a first task executing on a first compute node has failed:
- perform, by the first task, an atomic load and increment operation on a core file count received from a leader node of the plurality of compute nodes;
- generate, by the first task, a first core file upon determining that the core file count is below a predefined threshold;
- and
- not generate, by the first task, the first core file upon determining that the core file count is not below the predefined threshold.
Dependencies are inferred from the claim text.