-
公开(公告)号:US10884633B2
公开(公告)日:2021-01-05
申请号:US14994512
申请日:2016-01-13
Applicant: HEWLETT PACKARD ENTERPRISE DEVELOPMENT LP
Inventor: George A. Klarakis , Yan Xiao , Thomas G. Olson
Abstract: Systems, methods, and computer-readable storage media for inter-node data replication while reducing network traffic for remote backup. A system receives a command to duplicate a dataset, located on a source network node, to a remote network node, accesses, on the source network node, signatures of a previous snapshot of the dataset and signatures of a current snapshot of the dataset, performs, at the source network node, a local signature comparison between the previous snapshot and the current snapshot to identify one or more signatures that do not match, sends the signatures that do not match to the remote network node, searches, on the remote network node, for the signatures that do not match, and sends data associated with the signatures that do not match to the remote network node for incorporation within a current remote snapshot if they do not exist on a current remote network node.
-
公开(公告)号:US10862736B2
公开(公告)日:2020-12-08
申请号:US16776768
申请日:2020-01-30
Applicant: HEWLETT PACKARD ENTERPRISE DEVELOPMENT LP
Inventor: Glenn S. Watkins , John Michael Czerkowicz , Sumit Narayan , George A. Klarakis
Abstract: In an example, a system includes network nodes implementing an object store. The system may determine reference count updates for objects stored on the object store, and delay persisting the reference count updates to a persistent storage. The system may cancel reference count updates that increments and decrement between the determined reference count update and another reference count update received during the delay in persisting the reference count update to the persistent storage to minimize writing to the object record.
-
公开(公告)号:US20200169449A1
公开(公告)日:2020-05-28
申请号:US16776768
申请日:2020-01-30
Applicant: HEWLETT PACKARD ENTERPRISE DEVELOPMENT LP
Inventor: Glenn S. Watkins , John Michael Czerkowicz , Sumit Narayan , George A. Klarakis
Abstract: In an example, a system includes network nodes implementing an object store. The system may determine reference count updates for objects stored on the object store, and delay persisting the reference count updates to a persistent storage. The system may cancel reference count updates that increments and decrement between the determined reference count update and another reference count update received during the delay in persisting the reference count update to the persistent storage to minimize writing to the object record.
-
-