利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

11 条记录 (耗时 0.021 秒)

    LOCAL NON-VOLATILE MEMORY EXPRESS VIRTUALIZATION DEVICE
    1.
    发明申请
    LOCAL NON-VOLATILE MEMORY EXPRESS VIRTUALIZATION DEVICE 有权

    公开(公告)号：US20210349841A1

    公开(公告)日：2021-11-11

    申请号：US16868285

    申请日：2020-05-06

    申请人： Microsoft Technology Licensing, LLC

    发明人： Vadim MAKHERVAKS ,  Aaron William OGUS ,  Jason David ADRIAN

    IPC分类号： G06F13/16 ,  G06F13/40 ,  G06F9/455 ,  G06F12/02

    摘要： A server system is provided that includes one or more compute nodes that include at least one processor and a host memory device. The server system further includes a plurality of solid-state drive (SSD) devices, a local non-volatile memory express virtualization (LNV) device, and a non-transparent (NT) switch for a peripheral component interconnect express (PCIe) bus that interconnects the plurality of SSD devices and the LNV device to the at least one processor of each compute node. The LNV device is configured to virtualize hardware resources of the plurality of SSD devices. The plurality of SSD devices are configured to directly access data buffers of the host memory device. The NT switch is configured to hide the plurality of SSD devices such that the plurality of SSD devices are not visible to the at least one processor of each compute node.

    LOCAL NON-VOLATILE MEMORY EXPRESS VIRTUALIZATION DEVICE
    3.
    发明申请
    LOCAL NON-VOLATILE MEMORY EXPRESS VIRTUALIZATION DEVICE 有权

    公开(公告)号：US20220283967A1

    公开(公告)日：2022-09-08

    申请号：US17750523

    申请日：2022-05-23

    申请人： Microsoft Technology Licensing, LLC

    发明人： Vadim MAKHERVAKS ,  Aaron William OGUS ,  Jason David ADRIAN

    IPC分类号： G06F13/16 ,  G06F9/455 ,  G06F12/02 ,  G06F13/40

    摘要： A server system is provided that includes one or more compute nodes that include at least one processor and a host memory device. The server system further includes a plurality of solid-state drive (SSD) devices, a local non-volatile memory express virtualization (LNV) device, and a non-transparent (NT) switch for a peripheral component interconnect express (PCIe) bus that interconnects the plurality of SSD devices and the LNV device to the at least one processor of each compute node. The LNV device is configured to virtualize hardware resources of the plurality of SSD devices. The plurality of SSD devices are configured to directly access data buffers of the host memory device. The NT switch is configured to hide the plurality of SSD devices such that the plurality of SSD devices are not visible to the at least one processor of each compute node.

    ERASURE CODING WITH OVERLAPPED LOCAL RECONSTRUCTION CODES
    4.
    发明申请
    ERASURE CODING WITH OVERLAPPED LOCAL RECONSTRUCTION CODES 有权

    公开(公告)号：US20210208782A1

    公开(公告)日：2021-07-08

    申请号：US17059873

    申请日：2018-06-01

    申请人： MICROSOFT TECHNOLOGY LICENSING, LLC

    发明人： Jianfeng ZHU ,  Yiheng TAO ,  Cheng HUANG ,  Aaron William OGUS ,  Yilong ZHAO ,  Terry CHEN ,  Zhenshan YU ,  Tejas SHAH ,  Sridhar SRINIVASAN

    IPC分类号： G06F3/06 ,  G06F11/10

    摘要： Various embodiments, methods, and systems for erasure coding with overlapped local reconstruction codes, are provided. An erasure coding scheme can be defined based on Overlapped Local Reconstruction Codes (OLRC) that achieve high storage efficiency by providing fault tolerance properties that optimize reconstruction for common cases of failures while maintaining the reconstruction costs for uncommon case of failures. In operation, a data chunk is divided into data fragments. The data fragments correspond to zones. A plurality of parity fragments is computed using the data fragments. A parity fragment is computed using a subset of the data fragments. The plurality of parity fragments are assigned to the zones comprising the data fragments, where the data fragments and the plurality of parity fragments define overlapped local construction codes having a plurality of local groups. An unavailable data fragment is recoverable from at least two local groups from the plurality of local groups.

    DISTRIBUTED DATA OBJECT MANAGEMENT SYSTEM OPERATIONS
    5.
    发明申请
    DISTRIBUTED DATA OBJECT MANAGEMENT SYSTEM OPERATIONS 审中-公开

    公开(公告)号：US20180365104A1

    公开(公告)日：2018-12-20

    申请号：US15626073

    申请日：2017-06-16

    申请人： MICROSOFT TECHNOLOGY LICENSING, LLC

    发明人： Cheng HUANG ,  Jin LI ,  Aaron William OGUS ,  Douglas W. PHILLIPS ,  Yu Lin CHEN ,  Shuai MU ,  Jinyang LI

    IPC分类号： G06F11/10 ,  H03M13/15

    摘要： In various embodiments, methods and systems for implementing distributed data object management are provided. The distributed data object management system includes a local metadata-consensus information store and one or more remote metadata-consensus information stores for metadata-consensus information and a local data store and one or more remote data stores for erasure coded fragments. For a write operation, corresponding metadata writes and data writes are performed in parallel using a metadata write path and a data write path, respectively, when writing to the local metadata-consensus information store and the one or more remote metadata-consensus information stores and the local data store and the one or more remote data stores. And, for a read operation, corresponding metadata reads and data reads are performed in parallel using a metadata read path and a data read path, respectively, when reading from the metadata-consensus information stores and the data stores.

    MAINTENANCE OF STORAGE DEVICES WITH MULTIPLE LOGICAL UNITS
    9.
    发明申请
    MAINTENANCE OF STORAGE DEVICES WITH MULTIPLE LOGICAL UNITS 审中-公开

    公开(公告)号：US20190303243A1

    公开(公告)日：2019-10-03

    申请号：US15943555

    申请日：2018-04-02

    申请人： Microsoft Technology Licensing, LLC

    发明人： Scott Chao-Chueh LEE ,  Aaron William OGUS ,  Subhasish BHATTACHARYA ,  Bryan Stephen MATTHEW ,  Srinivasan MALAYALA

    IPC分类号： G06F11/10 ,  G06F3/06 ,  G06F11/20 ,  G06F11/16

    摘要： The techniques described herein are configured to improve the remanufacturing process by waiting to rebuild selective data items stored on a storage device that is unavailable. A storage device is unavailable when it is taken offline and/or disconnected from a network. The storage device may be taken offline due to a failed component (e.g., an actuator arm, an actuator head, damage to the underlying storage media, etc.). The storage device comprises multiple independent logical units, where a logical unit is a uniquely addressable portion of a storage device that is visible and/or that is exposed to a host. Accordingly, the techniques described herein are configured to conserve resources by selectively rebuilding data items stored in logical units of an offline storage device that are not affected by a remanufacturing process implemented due to a failed component.