Data storage systems using elastic spares

    公开(公告)号:US10936453B2

    公开(公告)日:2021-03-02

    申请号:US15937335

    申请日:2018-03-27

    Abstract: A system utilizing elastic spares includes nodes and devices to store one or more data objects having information. The data object includes data object units each assigned to a storage location on a different node than the other units. The data object includes one or more spare units to store reconstructed information of a failed unit. When one of the data objects has a failed unit and no spare units available to store reconstructed information, a controller of the system assigns an elastic spare unit to an available storage location of one of the nodes. Reconstructed information of the failed unit is stored in the elastic spare unit.

    DATA STORAGE SYSTEMS USING ELASTIC SPARES
    2.
    发明申请

    公开(公告)号:US20190087290A1

    公开(公告)日:2019-03-21

    申请号:US15937335

    申请日:2018-03-27

    Abstract: A system utilizing elastic spares includes nodes and devices to store one or more data objects having information. The data object includes data object units each assigned to a storage location on a different node than the other units. The data object includes one or more spare units to store reconstructed information of a failed unit. When one of the data objects has a failed unit and no spare units available to store reconstructed information, a controller of the system assigns an elastic spare unit to an available storage location of one of the nodes. Reconstructed information of the failed unit is stored in the elastic spare unit.

    MONITORING MODIFICATIONS TO DATA BLOCKS
    3.
    发明申请

    公开(公告)号:US20190155522A1

    公开(公告)日:2019-05-23

    申请号:US15821577

    申请日:2017-11-22

    Inventor: Nathaniel Rutman

    Abstract: A node includes a controller that includes one or more processors. The controller may be configured to load data from a storage data block of a plurality of storage data blocks stored on one or more first data storage devices to a working data block stored on one or more second data storage devices. In response to a node experiencing a failure, the controller can be configured to determine a change value for the working data block. The controller can be configured to determine whether data stored in the working data block is different than data stored in the corresponding storage data block based on the determined change value and a provided change value that corresponds to the storage data block.

    Multiple concurrent in-flight replies in a distributed state system

    公开(公告)号:US09912727B1

    公开(公告)日:2018-03-06

    申请号:US14733309

    申请日:2015-06-08

    CPC classification number: H04L67/025 G06F11/14 H04L69/40

    Abstract: In distributed state systems, server nodes can receive operation requests from multiple clients. When a server node executes an operation request, the server node can store an indicator of the operation request to a log of operations and send a reply message to the requesting client. The reply message can include a reply log having a list of N executed operation requests. If the server needs rebuilding, any operations not already stored to the server node log may be lost. The server can rebuild lost operations of a file system by receiving the reply logs or indicators of the operations therein from one or more clients.

    Data storage composite layouts for data objects

    公开(公告)号:US10977131B2

    公开(公告)日:2021-04-13

    申请号:US15707523

    申请日:2017-09-18

    Abstract: A composite layout including a plurality of ranked sub-layouts may be used to provide various functionality for data object look-up and file system activities. Each sub-layout may include mapping information linking one or more extents of a data object to one or more locations on one or more storage apparatuses. Generally, mapping information in the highest priority sub-layout including mapped extents may be used during “reads” while the highest priority sub-layout may be used for “writes.”

    Monitoring modifications to data blocks

    公开(公告)号:US10331363B2

    公开(公告)日:2019-06-25

    申请号:US15821577

    申请日:2017-11-22

    Inventor: Nathaniel Rutman

    Abstract: A node includes a controller that includes one or more processors. The controller may be configured to load data from a storage data block of a plurality of storage data blocks stored on one or more first data storage devices to a working data block stored on one or more second data storage devices. In response to a node experiencing a failure, the controller can be configured to determine a change value for the working data block. The controller can be configured to determine whether data stored in the working data block is different than data stored in the corresponding storage data block based on the determined change value and a provided change value that corresponds to the storage data block.

Patent Agency Ranking