Memory space management
    14.
    发明授权

    公开(公告)号:US09946660B2

    公开(公告)日:2018-04-17

    申请号:US15223754

    申请日:2016-07-29

    Abstract: Examples include a device for memory space management. Some examples include receiving, from a host, a space management request that identifies a virtual page address. The virtual page address may be associated with a compressed page that includes a compression metadata having a reference count that indicates a number of virtual pages of data in the compressed page. The virtual page table entry associated with the virtual page address in a virtual page table may be looked up. The virtual page table entry may identify the compressed page. In such examples, the virtual page table entry may be marked as invalid without updating the reference count in the compressed page. A determination may be made as to whether each virtual page table entry that identifies the compressed page is marked invalid. Based on the determination that each virtual page table entry that identifies the compressed page is invalid, a free space bitmap entry for the compressed page may be updated to indicate that the compressed page is free.

    VOLUME MIGRATION FOR A STORAGE AREA NETWORK
    17.
    发明申请
    VOLUME MIGRATION FOR A STORAGE AREA NETWORK 审中-公开
    存储区域网络的容量迁移

    公开(公告)号:US20160342362A1

    公开(公告)日:2016-11-24

    申请号:US15112796

    申请日:2014-01-23

    Abstract: Disclosed herein is a storage array configured for volume migration. An example of the storage array includes migration logic, at least partially comprising hardware logic, to establish a pass-through volume in the storage array wherein the pass-through volume is not associated with local storage in the storage array, such that communication paths between a host computing device, a source volume, and the pass-through volume during are maintained during migration. The migration logic is configured to convert the pass-through volume to a destination volume in the storage array after data migration, wherein the destination volume is associated with local storage within the storage array.

    Abstract translation: 这里公开了一种配置用于体积迁移的存储阵列。 存储阵列的示例包括至少部分地包括硬件逻辑的迁移逻辑,以在存储阵列中建立传递卷,其中传递卷不与存储阵列中的本地存储相关联,使得在 迁移期间维护主机计算设备,源卷和传递卷。 迁移逻辑被配置为在数据迁移之后将传递卷转换为存储阵列中的目标卷,其中目标卷与存储阵列中的本地存储相关联。

    COMMITMENT OF ACKNOWLEDGED DATA IN RESPONSE TO REQUEST TO COMMIT

    公开(公告)号:US20180373653A1

    公开(公告)日:2018-12-27

    申请号:US15629350

    申请日:2017-06-21

    Abstract: An example computing resource may include computing circuitry that includes logic. The logic may be executable to receive a series of data and an end of transfer message associated with the series of data. The logic may also be executable to, in response to a determination that the end of transfer message indicates a request for acknowledgment, send an acknowledgment to a sender of the series of data after receipt of all the series of data at the computing circuitry is complete and before the series of data is committed to a memory associated with a processing resource. The memory and the processing resource are separate from the computing circuitry. The logic may also be executable to, in response to a request to commit received data, commit the acknowledged and uncommitted series of data to the memory associated with the processing resource and interrupt the processing resource. The interrupt indicates that the acknowledged series of data is committed to the memory associated with the processing resource.

    TRANSACTION MANAGEMENT FOR MULTI-NODE CLUSTERS

    公开(公告)号:US20180314570A1

    公开(公告)日:2018-11-01

    申请号:US15770845

    申请日:2016-03-31

    Abstract: Examples include transaction management for a multi-node cluster. Some examples include generating a request log entry at an owner node that identifies a duplicate data location, tagging the duplicate data location with a requested tag, and issuing a zero-copy request that identifies the duplicate data location. In some such examples, a service node may generate a service log entry based on the zero-copy request that identifies the duplicate data location, process the zero-copy request, and tag the duplicate data location with a serviced tag. A determination may be made as to whether at least one of the owner node and the service node have failed and based on the determination that at least one has failed, the failed node may be recovered via at least one of the requested tag and the serviced tag of the duplicate data location.

Patent Agency Ranking