Prioritizing microservices on a container platform for a restore operation

    公开(公告)号:US10853196B2

    公开(公告)日:2020-12-01

    申请号:US16053976

    申请日:2018-08-03

    Abstract: Systems and methods for discovering applications. An application may be discovered by determining a topology of the application in a containerized platform. Discovering the topology may include determining the components of the application and then determining relationships between the components. The relationships may include whether a component (e.g., a microservice) is user facing and may be based on traffic patterns between the components. The components or microservices may be prioritized or ranked based on the topology. The topology can be used when performing a data protection operation such as a restore operation.

    System and method for data retention in a decentralized system

    公开(公告)号:US10853188B2

    公开(公告)日:2020-12-01

    申请号:US16395399

    申请日:2019-04-26

    Abstract: A node for use in a data management system includes a persistent storage and a data protection agent. The persistent storage stores data. The data protection agent makes an identification of a data protection strategy change event for the data; in response to the identification: makes a determination that the data protection strategy change event is a scale down event; in response to the determination: identifies a number of replicas of the data in other nodes that are in a predetermined state; makes a second determination that the number of the replicas of the data in the other nodes that are in the predetermined state exceeds a threshold specified by a data protection policy associated with the data protection strategy change event; and reduces the number of replicas that exceed the threshold to be less than the threshold in response to the second determination.

    METHOD AND SYSTEM FOR PERFORMANCE-DRIVEN LOAD SHIFTING

    公开(公告)号:US20200351339A1

    公开(公告)日:2020-11-05

    申请号:US16403365

    申请日:2019-05-03

    Abstract: A method and system for performance-driven load shifting. Specifically, the method and system disclosed herein entail transferring user program workloads, for processing, between local computing resources available on a client device and cloud computing resources available on an offload domain based on the assessed performance score of the client device at any given point in time. Seamless load shifting is further guaranteed due substantively to the employment of a mobile network facilitating communications between the client device and the offload domain.

    OPTIMIZING FILE SYSTEM DEFRAG FOR DEDUPLICATED BLOCK STORAGE

    公开(公告)号:US20200311030A1

    公开(公告)日:2020-10-01

    申请号:US16368008

    申请日:2019-03-28

    Abstract: A method for data defragmentation is disclosed, including: selecting a file that is stored in a content-addressable storage system, the file including a plurality of blocks, and the storage system including a plurality of deduplication chunks; arranging the plurality of blocks in block groups, each block group including a set of consecutive blocks having a combined size that matches a deduplication chunk size of the storage system; aligning each block group with a different one of the plurality of deduplication chunks of the storage system, such that the blocks in each block group are stored in the storage system in an order that is based on the order in which the blocks are positioned within the file.

    Methods, systems, and apparatuses to update point in time journal using map reduce to create a highly parallel update

    公开(公告)号:US10776211B1

    公开(公告)日:2020-09-15

    申请号:US15390996

    申请日:2016-12-27

    Abstract: A storage system comprises an object store, which comprises a plurality of metadata objects, a plurality of change objects, and a plurality of data objects associated with data stored in at least one logical unit of a production site, and a replication site configured to generate a requested point in time (PIT) based at least in part on the plurality of data objects, by: dividing the plurality of metadata objects into a plurality of respective portions of metadata objects; mapping each respective portion of metadata objects to a respective one of a plurality of reducer nodes; performing map reduce operations on the respective portion of metadata objects, at each respective one of the plurality of reducer nodes, to apply the most recent list of changes that occurred to each offset before the first requested PIT; and merging together the list of changes from each reducer node into the requested PIT.

    STORAGE SYSTEM CONFIGURED TO GENERATE SUB-VOLUME SNAPSHOTS

    公开(公告)号:US20200272600A1

    公开(公告)日:2020-08-27

    申请号:US16285377

    申请日:2019-02-26

    Abstract: A method includes designating one or more particular portions of a storage volume of a storage system for inclusion in a sub-volume snapshot. The method further includes generating the sub-volume snapshot as a point-in-time copy that includes the one or more designated portions of the storage volume and excludes one or more non-designated portions of the storage volume. The method is performed by at least one processing device comprising a processor coupled to a memory. The storage volume illustratively comprises a logical unit of a virtual machine file system, with the one or more designated portions of the logical unit of the virtual machine file system illustratively comprising at least one virtual machine storage drive file of the virtual machine file system. In some embodiments, a bitmap or other data structure is maintained for the storage volume with particular entries in the data structure corresponding to respective ones of the portions.

    Data management and backup for image and video media

    公开(公告)号:US10747621B2

    公开(公告)日:2020-08-18

    申请号:US15947834

    申请日:2018-04-08

    Abstract: The management and backup of image and video media is automatically performed by evaluating a media file to characterize the content; transforming the media file, as by compressing it, based upon its evaluation and established policies and requirements; and storing the transformed media file with a high resolution in a storage tier having first access characteristics for a first retention period. Following the first retention period, the stored file is re-evaluated and further transformed and stored with lesser resolution in another tier having different access characteristics for a second retention period. Subsequently, the further transformed media file may be transformed again and stored in archive storage.

    DECENTRALIZED DATA PROTECTION SYSTEM USING LOCAL METADATA

    公开(公告)号:US20200233760A1

    公开(公告)日:2020-07-23

    申请号:US16253005

    申请日:2019-01-21

    Abstract: In a decentralized system of nodes configured to provide data protection functionality, wherein at least a subset of the nodes store and share data using content-addresses managed via a distributed hash table in each of the subset of nodes, a given one of the subset of nodes locally stores: a data protection policy to be implemented by the given node; data protected on the given node; and metadata comprising information indicating placement of a given data set on one or more other ones of the subset of nodes. The given node accesses the locally stored metadata to manage protection of the given data set on the one or more other ones of the subset of nodes.

Patent Agency Ranking