Recording memory errors for use after restarts
AssigneeHewlett Packard Enterprise Development LP
InventorsDebdipta Ghosh, Renganathan Meenakshisundaram
Life of this patent
Estimating the term…
Abstract
In some examples, a system records, in a data structure stored in a non-volatile storage, information of memory errors in respective segments of a memory. The system determines whether memory errors of a subset of the segments satisfy a criterion, and in response to determining that the memory errors of the subset of the segments satisfy the criterion, the system groups the memory errors of the subset into a partition having a size greater than a size of a segment. The system records, in the data structure, information of memory errors in the partition, and in response to a restart of the system, retrieves the data structure from the non-volatile storage for use in an operation that addresses memory errors in the system.
Claims20
A non-transitory machine-readable storage medium comprising instructions that upon execution cause a system to:
- record, in a data structure stored in a non-volatile storage, information of memory errors in respective segments of a memory;
- determine whether memory errors of a subset of the segments satisfy a criterion;
- in response to determining that the memory errors of the subset of the segments satisfy the criterion, group the memory errors of the subset into a partition having a size greater than a size of a segment;
- record, in the data structure, information of memory errors in the partition;
- and
- in response to a restart of the system, retrieve the data structure from the non-volatile storage for use in an operation that addresses memory errors in the system.
A computer system comprising:
- a memory;
- and
- a controller to:
- receive indications of detected errors in the memory;
- record information of the detected errors in a data structure stored in a non-volatile storage;
- determine, based on the information, whether entries of the data structure are to be combined based on identifying multiple errors occurring within a common resource;
- combine the entries into a combined entry based on the determination;
- and
- in response to a restart of the computer system, retrieve the data structure including the combined entry from the non-volatile storage for use in an operation that addresses errors in the memory.
A method of a controller in a system, comprising:
- recording, in a data structure stored in a non-volatile storage, information of memory errors in respective segments of a memory, wherein plural entries of the data structure represent the memory errors in the respective segments;
- determining whether memory errors of a subset of the segments satisfy a criterion;
- in response to determining that the memory errors of the subset of the segments satisfy the criterion, grouping the memory errors of the subset into a partition having a size greater than a size of a segment;
- recording, in the data structure, information of memory errors in the partition based on combining entries in the data structure to form a combined entry that represents the memory errors in the partition;
- and
- in response to a restart of the system, retrieving the data structure from the non-volatile storage for use in an operation that addresses memory errors in the system.
Dependencies are inferred from the claim text.