Technique for referencing failure information representative of multiple related failures in a distributed computing environment

A distributed method for referencing failure information in a distributed computing environment having a plurality of non-dedicated nodes, said method comprising:

• upon detection of a first program failure condition at a first node detecting the first program failure, creating a first program failure report by recording information on said first program failure condition and storing the first program failure report at the first node;
• assigning a first identifier to said first program failure report which uniquely identifies the first program failure report including said node within the distributed computing environment creating said first program failure report and where within storage associated with said node said first program failure report is located;
• upon detecting a second program failure condition at a second node which is related to said first program failure condition, creating a second program failure report by recording information on said second program failure condition, and storing the second program failure report at the second node, wherein said second node and said first node may comprise the same node or different nodes within said distributed computing environment;
• and
• assigning a second identifier to said second program failure report which uniquely identifies the second program failure report including said second node within the distributed computing environment creating said second program failure report, where within storage associated with said second node said second program failure report is located, and said first program identifier for said first program failure report on said first program failure condition related to said second program failure condition.

A system for referencing failure information in a distributed computing environment having a plurality of non-dedicated nodes, said system comprising:

• a distributed failure data capture system disposed across the plurality of non-dedicated nodes, said distributed failure data capture system comprising persistent storage at the plurality of non-dedicated nodes for storing error reports in a distributed manner across the plurality of non-dedicated nodes, said distributed failure data capture system comprising:
• means for creating a failure report by recording information on a failure condition upon detection of said failure condition at a node of the plurality of non-dedicated nodes detecting the failure;
• and
• means for assigning an identifier to said failure report and for storing said failure report at said node in persistent storage of the distributed failure data capture system, said identifier uniquely identifying the failure report including said node within the distributed computing environment creating said failure report and where within storage associated with said node said failure report is located within the distributed computing environment.

A system for referencing failure information in a distributed computing environment having a plurality of non-dedicated nodes, said system comprising:

• a distributed failure data capture system distributed across the plurality of non-dedicated nodes, said distributed failure data capture system comprising persistent storage at the plurality of non-dedicated nodes for storing error reports in a distributed manner across the plurality of non-dedicated nodes;
• at least one non-dedicated processing node of said plurality of nodes employing the distributed failure data capture system to create a failure report by recording information at the at least one node on a failure condition upon detection of the failure condition at the at least one node;
• and
• the distributed failure data capture system being further adapted to assign an identifier to the failure report and store the failure report at said at least one node in said persistent storage of the distributed failure data capture system, said identifier uniquely identifying the failure report including the at least one node within the distributed computing environment creating and storing said failure report and where within storage associated with said at least one node said failure report is located.

A system for referencing failure information in a distributed computing environment having a plurality of non-dedicated nodes, said system comprising:

• means for creating a first program failure report by recording information on a first program failure condition detected at a first node and for storing the first program failure report at the first node;
• means for assigning a first identifier to said first program failure report which uniquely identifies the first program failure report including said node within the distributed computing environment creating said first program failure report and where within storage associated with said node said first program failure report is located;
• means for creating a second program failure report upon detecting a second program failure condition at a second node which is related to the first program failure condition, said second program failure report being created by recording information on said second program failure condition, and for storing the second program failure report at the second node, wherein said second node and said first node may comprise the same node or different nodes within the distributed computing environment;
• and
• means for assigning a second identifier to said second program failure report which uniquely identifies the second program failure report including said second node within the distributed computing environment creating said second program failure report, where within storage associated with said second node said second program failure report is located, and said first identifier for said first program failure report of said first program failure condition related to said second program failure condition.

A system for referencing failure information in a distributed computing environment having a plurality of non-dedicated nodes, said system comprising:

• a first node of said plurality of nodes being adapted to create a first program failure report by recording information on said first program failure condition using first failure data capture interface logic and being adapted to store the first program failure report at the first node;
• said first node further being adapted to assign a first identifier to said first program failure report which uniquely identifies the first program failure report including said first node within the distributed computing environment creating said first program failure report and where within storage associated with said node said first program failure report is located, said first identifier being assigned using said first failure data capture interface logic of said first node;
• a second node adapted to create a second program failure report by recording information on a second program failure condition occurring at said second node, wherein said second program failure condition is related to said first program failure condition, and said second node is adapted to store the second program failure report at the second node, and said second node and said first node may comprise the same node or different nodes within said distributed computing environment, and wherein said second node creates said second program failure report using a first failure data capture interface logic at said second node;
• and
• said second node being further adapted to assign a second identifier to said second program failure report using said first failure data capture interface logic of said second node, said second identifier uniquely identifying the second program failure report including said second node within the distributed computing environment creating said second program failure report, where within storage associated with said second node said second program failure report is located, and said first identifier for said first program failure report of said first program failure condition related to said second program failure condition.

At least one program storage device readable by a machine, tangibly embodying at least one program of instructions executable by the machine to perform a method for referencing failure information in a distributed computing environment having a plurality of non-dedicated nodes, said method comprising:

• employing a distributed failure data capture system across the plurality of non-dedicated nodes, said distributed failure data capture system comprising persistent storage at the plurality of non-dedicated nodes for storing error reports in a distributed manner across the plurality of non-dedicated nodes, said employing including using the distributed failure data capture system to
• create a failure report by recording information on a failure condition upon detection of said failure condition at a node of the plurality of non-dedicated nodes detecting the failure;
• and
• assign an identifier to said failure report and store said failure report at said node in said persistent storage of the distributed failure data capture system, said identifier uniquely identifying the failure report including said node within the distributed computing environment creating and storing said failure report and where within storage associated with said node said failure report is located.

At least one program storage device readable by a machine, tangibly embodying at least one program of instructions executable by the machine to perform a method for referencing failure information in a distributed computing environment having a plurality of non-dedicated nodes, said method comprising:

• upon detection of a first program failure condition at a first node detecting the first program failure, creating a first program failure report by recording information on said first program failure condition and storing the first program failure report at the first node;
• assigning a first identifier to said first program failure report which uniquely identifies the first program failure report including said node within the distributed computing environment creating said first program failure report and where within storage associated with said node said first program failure report is located;
• upon detecting a second program failure condition at a second node which is related to said first program failure condition, creating a second program failure report by recording information on said second program failure condition, and storing the second program failure report at the second node, wherein said second node and said first node may comprise the same node or different nodes within said distributed computing environment;
• and
• assigning a second identifier to said second program failure report which uniquely identifies the second program failure report including said second node within the distributed computing environment creating said second program failure report, where within storage associated with said second node said second program failure report is located, and said first program identifier for said first program failure report on said first program failure condition related to said second program failure condition.