Deduplication system threshold based on an amount of wear of a storage device
AssigneeHewlett Packard Enterprise Development LP
InventorsJohn Butt, Dave Donaghy, Mayuri Jain
Life of this patent
Estimating the term…
Abstract
Examples may include a deduplication system threshold based on an amount of wear of a storage device. Examples may obtain an indication of an amount of wear experienced by at least one storage device storing a plurality of container indexes of a deduplication system, and may adjust a threshold of the deduplication system based on the amount of wear.
Claims20
A method comprising:
- obtaining an indication of an amount of wear experienced by at least one storage device storing a plurality of container indexes of a deduplication system;
- adjusting a container index threshold based on the amount of wear;
- identifying;
- among the plurality of container indexes;
- container indexes having hits for a given portion of a given data stream;
- retrieving, from the at least one storage device, a number of the identified container indexes, the number not exceeding the container index threshold, wherein the container index threshold is a maximum number of identified container indexes to be read from the at least one storage device for deduplication of a single portion of any data stream;
- and
- performing deduplication of the given portion in relation to the retrieved container indexes.
A deduplication system comprising:
- at least one processing resource;
- and
- at least one non-transitory machine-readable storage medium comprising instructions executable by at least one processing resource to:
- obtain an indication of an amount of wear experienced by at least one storage device storing a plurality of container indexes of the deduplication system, each of the container indexes comprising one or more entries;
- adjust a compaction threshold based on the amount of wear;
- perform compaction on a selected one of the container indexes having a number of unreferenced entries that is greater than or equal to the compaction threshold, wherein performance of the compaction comprises writing the selected container index to a different location on the at least one storage device without the unreferenced entries;
- and
- prevent compaction of any of the container indexes having a number of unreferenced entries that is less than the compaction threshold.
An article comprising at least one non-transitory machine-readable storage medium comprising instructions executable by at least one processing resource of a deduplication system to:
- determine whether a hardware storage target for container indexes for the deduplication system comprises one or more storage devices of a first type or one or more storage devices of a second type, wherein storage devices of the second type of have a lesser operational life for write operations than storage devices of the first type;
- in response to a determination that the deduplication system is to store container indexes on one or more storage devices of a first type, set a container index threshold to a first value;
- in response to a determination that the deduplication system is to store container indexes on one or more storage devices of the second type;
- set the container index threshold to a second value higher than the first value;
- store a plurality of container indexes on the hardware storage target;
- identify, among the plurality of container indexes, container indexes having hits for a given portion of a given data stream;
- and
- retrieve, from the hardware storage target, a number of the container indexes having hits, the number not exceeding the container index threshold, wherein the container index threshold is a maximum number of container indexes having hits to be read from the hardware storage target for deduplication of a single portion of any data stream;
- and
- perform deduplication of the given portion in relation to the retrieved container indexes.
Dependencies are inferred from the claim text.