公开(公告)号：US10860539B2

公开(公告)日：2020-12-08

申请号：US15486536

申请日：2017-04-13

Applicant: Huawei Technologies Co., Ltd.

Inventor： Yanhui Zhong ,  Chengwei Zhang

IPC: G06F16/174 ,  G06F16/14 ,  G06F16/11 ,  G06F16/182 ,  G06F3/06 ,  G06F11/14

Abstract: A de-duplication-based remote replication method and an apparatus are provided in a system including a primary end device and a disaster recovery end device, and both the primary end device and the disaster recovery end device store a first snapshot; the primary end device obtains a second snapshot of the primary end device, and sends the first data block, the fingerprint of the first data block, and metadata of the added data blocks to the disaster recovery end device when a fingerprint of a first data block in the added data blocks is different from the fingerprints of the data blocks in the first snapshot.

公开(公告)号：US10725692B2

公开(公告)日：2020-07-28

申请号：US16232815

申请日：2018-12-26

Applicant: Huawei Technologies Co., Ltd.

Inventor： Yanhui Zhong

IPC: G06F3/06 ,  G06F12/00 ,  G06F11/10

Abstract: A data storage method and an apparatus are provided in a distributed storage system including a computing node and a plurality of storage nodes. The computing node writes the N data slices and the M check slices into the R storage nodes in each storage node group to improve reliability and stability of data in a data center.

公开(公告)号：US20170235754A1

公开(公告)日：2017-08-17

申请号：US15486536

申请日：2017-04-13

Applicant: Huawei Technologies Co., Ltd.

Inventor： Yanhui Zhong ,  Chengwei Zhang

IPC: G06F17/30

Abstract: A de-duplication-based remote replication method and an apparatus are provided in a system including a primary end device and a disaster recovery end device, and both the primary end device and the disaster recovery end device store a first snapshot; the primary end device obtains a second snapshot of the primary end device, and sends the first data block, the fingerprint of the first data block, and metadata of the added data blocks to the disaster recovery end device when a fingerprint of a first data block in the added data blocks is different from the fingerprints of the data blocks in the first snapshot.

公开(公告)号：US20190129649A1

公开(公告)日：2019-05-02

申请号：US16232815

申请日：2018-12-26

Applicant: Huawei Technologies Co., Ltd.

Inventor： Yanhui Zhong

IPC: G06F3/06

Abstract: A data storage method and an apparatus are provided in a distributed storage system including a computing node and a plurality of storage nodes. The computing node writes the N data slices and the M check slices into the R storage nodes in each storage node group to improve reliability and stability of data in a data center.

公开(公告)号：US08760956B1

公开(公告)日：2014-06-24

申请号：US14140945

申请日：2013-12-26

Applicant: Huawei Technologies Co., Ltd.

Inventor： Yanhui Zhong ,  Zongquan Zhang

IPC: G11C8/00

CPC classification number: G06F3/0641 ,  G06F3/0608 ,  G06F3/061 ,  G06F3/0619 ,  G06F3/067 ,  G06F3/0673 ,  G06F12/0868 ,  G06F12/0875 ,  G06F2212/452

Abstract: Embodiments of the present invention provide a data processing method and apparatus. According to the embodiments of the present invention, when it is found that a data hash value in a currently received data stream exceeds a preset first threshold, a part or all of data in the data stream is not deduplicated, and is directly stored, so as to prevent the data in the data stream from being dispersedly stored into a plurality of storage areas; instead, the part or all of the data is stored into a storage area in a centralized manner, so that a deduplication rate is effectively improved on the whole, particularly in a scenario of large data storage amount.

公开(公告)号：US20170031933A1

公开(公告)日：2017-02-02

申请号：US15291249

申请日：2016-10-12

Applicant: Huawei Technologies Co., Ltd.

Inventor： Yong Xie ,  Yuguo Li ,  Yanhui Zhong ,  Xudong Fu

IPC: G06F17/30

CPC classification number: G06F16/128 ,  G06F16/00 ,  G06F16/119

Abstract: A checkpoint reclaim method in a copy-on-write (COW) file system includes: obtaining, according to a checkpoint reclaim instruction, M data blocks allocated by the file system between a moment of a previous checkpoint reclaim and a moment of a current checkpoint reclaim, and the M data blocks are data blocks allocated for at least one of a checkpoint or a snapshot generated between the moment of the previous checkpoint reclaim and the moment of the current checkpoint reclaim; performing an addition operation with a fixed step on a reference count of a data block that needs to be reserved in the M data blocks, and determining, in the M data blocks, a first data block for reclaiming; determining, in N data blocks allocated for at least one of a checkpoint or a snapshot reserved at the moment of the previous checkpoint reclaim, a second data block for reclaiming.

Abstract translation: 在写时复制（COW）文件系统中的检查点回收方法包括：根据检查点回收指令，获取文件系统在先前检查点回收的时刻与当前检查点的时刻之间分配的M个数据块 并且M个数据块是分配给在先前检查点回收的时刻与当前检查点回收的时刻之间生成的检查点或快照中的至少一个的数据块; 在需要在M个数据块中保留的数据块的参考计数上以固定步长执行加法运算，并且在M个数据块中确定用于回收的第一数据块; 确定在为先前检查点回收时保留的检查点或快照中的至少一个分配的N个数据块中，确定用于回收的第二数据块。

公开(公告)号：US20140258625A1

公开(公告)日：2014-09-11

申请号：US14120286

申请日：2014-05-14

Applicant: Huawei Technologies Co., Ltd.

Inventor： Yanhui Zhong ,  Zongquan Zhang

IPC: G06F3/06 ,  G06F12/08

CPC classification number: G06F3/0641 ,  G06F3/0608 ,  G06F3/061 ,  G06F3/0611 ,  G06F3/0619 ,  G06F3/067 ,  G06F3/0673 ,  G06F12/0868 ,  G06F12/0875 ,  G06F2212/452

Abstract: Embodiments of the present invention provide a data processing method and apparatus. According to the embodiments of the present invention, when it is found that a data hash value in a currently received data stream exceeds a preset first threshold, a part or all of data in the data stream is not deduplicated, and is directly stored, so as to prevent the data in the data stream from being dispersedly stored into a plurality of storage areas; instead, the part or all of the data is stored into a storage area in a centralized manner, so that a deduplication rate is effectively improved on the whole, particularly in a scenario of large data storage amount.

Abstract translation: 本发明的实施例提供一种数据处理方法和装置。 根据本发明的实施例，当发现当前接收的数据流中的数据散列值超过预设的第一阈值时，数据流中的部分或全部数据不被重复数据删除，并被直接存储，所以 以防止数据流中的数据被分散地存储到多个存储区域中; 相反，部分或全部数据以集中的方式存储在存储区域中，从而整体上有效地提高了重复数据删除率，特别是在大数据存储量的情况下。