Method of checkpointing parallel processes in execution within plurality of process domains
AssigneeHewlett-Packard Development Company, L.P.
InventorsGopalakrishnan Janakiraman, Dinesh Subhraveti, Jose Santos, Yoshio Turner
Life of this patent
Estimating the term…
Abstract
An embodiment of a method of checkpointing parallel processes in execution within a plurality of process domains begins with a step of setting communication rules to stop communication between the process domains. Each process domain comprises an execution environment at a user level for at least one of the parallel processes. The method continues with a step of checkpointing each process domain and any in-transit messages. The method concludes with a step of resetting the communication rules to allow the communication between the process domains.
Claims25
A method of checkpointing parallel processes in execution within a plurality of process domains comprising the steps of:
- setting communication rules to stop communication between process domains, each process domain comprising an execution environment at a user level for at least one of the parallel processes;
- checkpointing each process domain and any in-transit messages;
- and
- resetting the communication rules to allow the communication between the process domains.
A method of checkpointing parallel processes in execution within a plurality of process domains comprising the steps of:
- setting communication rules to stop communication between process domains hosted on nodes, each node comprising at least one of the process domains, a user level, and a kernel level, each process domain comprising at least a portion of the user level, each process domain providing an execution environment for at least one of the parallel processes, the kernel level of each node comprising a loadable kernel module which virtualizes resources within the at least one of the process domains on the node;
- checkpointing each process domain and any in-transit messages;
- and
- resetting the communication rules to allow the communication between the process domains.
A computer readable medium comprising computer code for implementing a method of checkpointing parallel processes in execution within a plurality of process domains, the method of checkpointing the parallel processes comprising the steps of:
- setting communication rules to stop communication between process domains, each process domain comprising an execution environment at a user level for at least one of the parallel processes;
- checkpointing each process domain and any in-transit messages;
- and
- resetting the communication rules to allow the communication between the process domains.
A computer readable medium comprising computer code for implementing a method of checkpointing parallel processes in execution within a plurality of process domains, the method of checkpointing the parallel processes comprising the steps of:
- setting communication rules to stop communication between process domains hosted on nodes, each node comprising at least one of the process domains, a user level, and a kernel level, each process domain comprising at least a portion of the user level, each process domain providing an execution environment for at least one of the parallel processes, the kernel level of each node comprising a loadable kernel module which virtualizes resources within the at least one of the process domains on the node;
- checkpointing each process domain and any in-transit messages;
- and
- resetting the communication rules to allow the communication between the process domains.
Dependencies are inferred from the claim text.