Aggressive data deduplication using lazy garbage collection
AssigneePure Storage, Inc.
InventorJohn D. Davis
Life of this patent
Estimating the term…
Abstract
A method for extending data lifetime for reference in deduplication is provided. The method includes determining that a quantity of user data has at least a threshold amount of data that is re-created in a storage system. The method includes protecting at least portions of the quantity of user data from erasure by garbage collection in the storage system during a predetermined time interval, wherein the protected at least portions are available for data deduplication of further user data in the storage system during the predetermined time interval.
Claims20
A method, comprising:
- tracking how often incoming data to a storage system repeats;
- indicating in metadata that at least portions of repeated data associated with memory to be reclaimed are to have deletion immunity responsive to the tracking;
- protecting the at least portions of the repeated data representing unused data from deletion by garbage collection, during a predetermined time interval;
- and
- performing garbage collection except where the deletion immunity as indicated by the metadata prevents the deletion during the garbage collection.
A tangible, non-transitory, computer-readable media having instructions thereupon which, when executed by a processor in a storage system, cause the processor to perform a method comprising:
- tracking how often incoming data to the storage system repeats a same data;
- indicating in metadata that at least portions of repeated data are to have deletion immunity responsive to the tracking;
- protecting the at least portions of the repeated data representing unused data from deletion by garbage collection, during a predetermined time interval;
- and
- performing garbage collection except where the deletion immunity as indicated by the metadata prevents the deletion during the garbage collection.
A storage system, with deduplication, comprising:
- storage memory;
- and
- at least one processor of the storage system, configured to write an indicator to metadata of the storage system, the indicator protecting at least portions of user data from deletion during garbage collection, wherein the at least one processor tracks how often incoming data to the storage system repeats, wherein the at least one processor is configured to execute a garbage collection process, which includes deleting portions of storage memory of the storage system except where metadata prevents the deletion during the garbage collection, the metadata indicating that repeated data representing unused data within the portions of storage memory are to have deletion immunity for a predetermined time period and wherein writing the indicator is based on how often incoming data to the storage system repeats.
Dependencies are inferred from the claim text.