US 9,753,647 B2Granted

Deduplicating chunk digests received for chunks in objects provided by clients to store

AssigneeInternational Business Machines Corporation

InventorsArthur John Colvig, Yu Meng Li, Michael G. Sisco

Life of this patent

Estimating the term…

Loading patent…

Abstract

Provided are a computer program product, system, and method for deduplicating chunk digests received for chunks in objects in objects provided by clients to store in a storage. An index has chunk signatures calculated from chunks of data in the data objects in the storage. A transaction requests a shared lock for a chunk digest calculated from a chunk in an object to add to the storage. In response to not receiving the shared lock, the transaction is granted a shared lock to the chunk digest in wait mode. The transaction does not proceed until being granted the shared lock. In response to receiving the shared lock, a determination is made as to whether the chunk digest is in the index. A reference to the chunk data is provided for the object when the chunk digest is indicated in the index.

Claims22

Dependent claims

A computer program product for performing deduplication for a storage, the computer program product comprising a computer readable storage medium having computer readable program code embodied therein that executes to perform operations, the operations comprising:

maintaining an index of chunk digests calculated from chunks of data in data objects in the storage, wherein each index entry includes a chunk digest and a reference to a chunk of data from which the chunk digest was calculated;
requesting, by a transaction, a shared lock for a chunk digest calculated from a chunk in an object to add to the storage, wherein the transaction is to perform deduplication on the chunk from which the chunk digest is calculated using the chunk digest;
in response to not receiving the shared lock, granting the transaction a shared lock to the chunk digest in wait mode, wherein the transaction does not proceed until being granted the shared lock;
in response to receiving the shared lock, determining whether the chunk digest is in the index;
and
providing a reference to the chunk of data for the object when the chunk digest is indicated in the index.

3 more elements

A system for performing deduplication for a storage, comprising:

a processor;
and
a computer readable storage medium having computer program code that when executed by the processor performs operations, the operations comprising:
maintaining an index of chunk digests calculated from chunks of data in data objects in the storage, wherein each index entry includes a chunk digest and a reference to a chunk of data from which the chunk digest was calculated;
requesting, by a transaction, a shared lock for a chunk digest calculated from a chunk in an object to add to the storage, wherein the transaction is to perform deduplication on the chunk from which the chunk digest is calculated using the chunk digest;
in response to not receiving the shared lock, granting the transaction a shared lock to the chunk digest in wait mode, wherein the transaction does not proceed until being granted the shared lock;
in response to receiving the shared lock, determining whether the chunk digest is in the index;
and
providing a reference to the chunk of data for the object when the chunk digest is indicated in the index.

6 more elements

A method for performing deduplication for a storage, comprising:

maintaining an index of chunk digests calculated from chunks of data in data objects in the storage, wherein each index entry includes a chunk digest and a reference to a chunk of data from which the chunk digest was calculated;
requesting, by a transaction, a shared lock for a chunk digest calculated from a chunk in an object to add to the storage, wherein the transaction is to perform deduplication on the chunk from which the chunk digest is calculated using the chunk digest;
in response to not receiving the shared lock, granting the transaction a shared lock to the chunk digest in wait mode, wherein the transaction does not proceed until being granted the shared lock;
in response to receiving the shared lock, determining whether the chunk digest is in the index;
and
providing a reference to the chunk of data for the object when the chunk digest is indicated in the index.

3 more elements

Dependencies are inferred from the claim text.