Data placement and recovery in the event of partition failures

    公开(公告)号:US11842063B2

    公开(公告)日:2023-12-12

    申请号:US17704978

    申请日:2022-03-25

    Applicant: eBay Inc.

    CPC classification number: G06F3/0644 G06F3/067 G06F3/0619 G06F3/0659

    Abstract: Software defined storage service (SDS) provides users with remote data volumes spread across multiple storage nodes across multiple failure domains. A distributed volume may be spread across replicas (e.g., failure domains), each replica having a number of partitions stored on storage nodes associated with a particular failure domain. In the event of a node failure, a partition stored on the failed node may be dynamically moved and remapped to another node in the same failure domain or within another failure domain that is different from a failure domain that includes a partition that is complementary to the partition stored on the failed node. The partition move and remapping may be transparent to a user. A partition move may occur while a distributed volume is in use by a client device or in an idle (e.g., offline) mode.

    Modified database traffic mirroring through a distributed data service

    公开(公告)号:US11354217B2

    公开(公告)日:2022-06-07

    申请号:US16774390

    申请日:2020-01-28

    Applicant: eBay Inc.

    Abstract: Defects are identified in a pre-production version of an application. Input used to test the pre-production version is derived from input received by a production version of the application. Input to the production version may be selectively filtered and/or amplified before being provided as test input to the pre-production version. In this way, the makeup and rate of the test input can be controlled while maintaining the character, pattern, and unpredictable nature of real-world input. Defects may be identified when the test input causes the pre-production version to crash, hang, write to an error log, or otherwise manifest or report a malfunction. In addition to identifying defects, filtered and amplified input may also be used to perform regression testing, load testing, performance testing, etc.

    Allocation of replica-sets in a storage cluster
    3.
    发明授权
    Allocation of replica-sets in a storage cluster 有权
    分配存储集群中的副本集

    公开(公告)号:US09262278B2

    公开(公告)日:2016-02-16

    申请号:US13946551

    申请日:2013-07-19

    Applicant: eBay Inc.

    Abstract: A data storage system may be configured to allocate replica-sets in a balanced manner and mark some of these balanced replica-sets as being spares. As one or more drives or machines fail, the data storage system may move all copies of an affected replica-set to a marked spare replica-set and mark the affected replica-set as being inactive or invalid. As the failed drives are replaced, the data storage system may reconfigure those inactive replica-sets and use them as new spares. The data storage system may implement a coordinator module that handles the balancing and allocation of spares within a sub-cluster. The coordinator may also reallocate entire replica-sets across sub-clusters to maintain balance at the cluster level.

    Abstract translation: 数据存储系统可以被配置为以平衡的方式分配副本集,并将这些平衡副本集中的一些标记为备用。 当一个或多个驱动器或计算机出现故障时,数据存储系统可将受影响的副本集的所有副本移动到标记的备用副本集,并将受影响的副本集标记为不活动或无效。 当更换失败的驱动器时,数据存储系统可以重新配置那些不活动的副本集并将其用作新的备件。 数据存储系统可以实现一个协调器模块,该协调器模块处理子集群内备件的平衡和分配。 协调器还可以跨子群集重新分配整个副本集,以在群集级别保持平衡。

    DATA PLACEMENT AND RECOVERY IN THE EVENT OF PARTITION FAILURES

    公开(公告)号:US20230305726A1

    公开(公告)日:2023-09-28

    申请号:US17704978

    申请日:2022-03-25

    Applicant: eBay Inc.

    CPC classification number: G06F3/0644 G06F3/0659 G06F3/0619 G06F3/067

    Abstract: Software defined storage service (SDS) provides users with remote data volumes spread across multiple storage nodes across multiple failure domains. A distributed volume may be spread across replicas (e.g., failure domains), each replica having a number of partitions stored on storage nodes associated with a particular failure domain. In the event of a node failure, a partition stored on the failed node may be dynamically moved and remapped to another node in the same failure domain or within another failure domain that is different from a failure domain that includes a partition that is complementary to the partition stored on the failed node. The partition move and remapping may be transparent to a user. A partition move may occur while a distributed volume is in use by a client device or in an idle (e.g., offline) mode.

    MODIFIED DATABASE TRAFFIC MIRRORING THROUGH A DISTRIBUTED DATA SERVICE

    公开(公告)号:US20210232488A1

    公开(公告)日:2021-07-29

    申请号:US16774390

    申请日:2020-01-28

    Applicant: eBay Inc.

    Abstract: Defects are identified in a pre-production version of an application. Input used to test the pre-production version is derived from input received by a production version of the application. Input to the production version may be selectively filtered and/or amplified before being provided as test input to the pre-production version. In this way, the makeup and rate of the test input can be controlled while maintaining the character, pattern, and unpredictable nature of real-world input. Defects may be identified when the test input causes the pre-production version to crash, hang, write to an error log, or otherwise manifest or report a malfunction. In addition to identifying defects, filtered and amplified input may also be used to perform regression testing, load testing, performance testing, etc.

Patent Agency Ranking