Pure Storage, Inc.

Vinay Perneti

John Colgrove

Sergey Zhuravlev

Patrick D Lee

Terence W Noonan

Deepak Chawla

Jikui Su

Ronald S Karr

Feng Wang

Ethan L Miller

Wei Zhang

Cary A Sandvig

A method may include detecting, by a computing device based on a problem signature, that a system has experienced a problem that is associated with the problem signature, wherein the problem signature comprises a specification of a pattern of events indicative of the particular problem experienced by at least one other system; determining that the particular problem violates an operational policy of the system; and deploying, without user intervention, one or more corrective measures that modify the system to resolve the problem.

Problem signature-based corrective measure deployment

Synchronizing snapshots between storage systems, including: receiving, from a source storage system, an identification of a snapshot to be replicated to a destination storage system, wherein the source storage system and the destination storage system are of different types; identifying, from hint information stored on the destination storage system, a most recent version of the snapshot that is stored on the destination storage system; issuing, to the source storage system, a request for an identification of the differences between the snapshot to be replicated to the destination storage system and the most recent version of the snapshot that is stored on the destination storage system; receiving, from the source storage system, the identification of the differences; and issuing a request to transfer, from the source storage system to the destination storage system, data associated with the differences.

Efficient replication of a dataset to the cloud

An illustrative method includes detecting, by a cloud based storage system services provider based on a problem signature, that a storage system has experienced a problem that is associated with the problem signature; and deploying, without user intervention, one or more corrective measures that modify the storage system to resolve the problem.

Cloud-based providing of one or more corrective measures for a storage system

Proactively providing corrective measures for storage arrays includes: receiving data from a storage array, the data including one or more events; detecting, in dependence upon a problem signature, one or more events from the data indicative of a particular problem, where the problem signature comprises a specification of a pattern of events indicative of the particular problem experienced by at least one other storage array; determining whether the particular problem violates an operational policy of the storage array, the operational policy specifying at least one requirement for an operational metric of the storage array; and if the particular problem violates the operational policy of the storage array, deploying automatically without user intervention one or more corrective measures to prevent the storage array from experiencing the particular problem.

Proactively providing corrective measures for storage arrays

Synchronizing snapshots between storage systems, including: receiving, from a source storage system, an identification of a snapshot to be replicated to a destination storage system; identifying, from hint information stored on the destination storage system, a most recent version of the snapshot that is stored on the destination storage system; issuing, to the source storage system, a request for an identification of the differences between the snapshot to be replicated to the destination storage system and the most recent version of the snapshot that is stored on the destination storage system; receiving, from the source storage system, the identification of the differences; and issuing a request to transfer, from the source storage system to the destination storage system, data associated with the differences.

Cloud-based snapshot replication

Preventing storage errors using problem signatures

A data block may be received. Hash values correspond to portions of the data block may be generated. A determination that none of the plurality of hash values matches with another hash value associated with a previously received data block may be made. In response to determining that none of the plurality of hash values match with the other hash value associated with the previously received data block, a subset of the plurality of hash values may be stored based on a first alignment and a second alignment.

Efficient deduplication signature utilization

Automatic deployment of corrective measures for storage arrays

Partially replicating a snapshot between storage systems

The method includes storing data including an index summary (IS) and a deduplication map (DDM) in volatile memory of a deduplication system. The method also includes detecting that the stored data exceeds a data allocation size limit for the volatile memory. The method includes evicting the data from the volatile memory using a memory eviction policy to meet the data allocation size limit. The method further includes performing a first eviction by evicting the DDM levels from an oldest DDM level to a newest DDM level until a first one of the data allocation size limit or a DDM threshold is met. The method also includes performing a second eviction by evicting the IS levels from an oldest IS level to a newest IS level until a first one of the data allocation size limit or IS threshold is met in response to the data allocation size limit not being met by the first eviction.

Growing community of inventors

Mountain View, CA, United States of America

Vinay Perneti