公开(公告)号：US20160357634A1

公开(公告)日：2016-12-08

申请号：US15173327

申请日：2016-06-03

Applicant: HUAWEI TECHNOLOGIES CO.,LTD.

Inventor： Daohui Wang ,  Feng Zhang ,  Wei Fan ,  Zhile Zhang ,  Yongqiang Zeng

IPC: G06F11/10 ,  G06F3/06

CPC classification number: G06F11/1076 ,  G06F3/0617 ,  G06F3/0619 ,  G06F3/0631 ,  G06F3/064 ,  G06F3/067 ,  G06F9/466 ,  G06F9/5011 ,  G06F11/00

Abstract: A data storage method is used to improve storage consistency of a distributed storage system. The method includes: a primary storage node performs EC coding on a to-be-stored data segment to obtain a target EC stripe; determines in a storage node group to which the primary storage node belongs, m+k target storage nodes used to store m+k target EC blocks of the target EC stripe; sends a preparation message to the target storage nodes; receives a response message sent by a target storage node; and sends an execution message to the target storage nodes to instruct the target storage nodes to write target EC blocks that are in preparation logs.

Abstract translation: 数据存储方法用于提高分布式存储系统的存储一致性。 该方法包括：主存储节点对待存储的数据段执行EC编码以获得目标EC条带; 在主存储节点所属的存储节点组中确定m + k个目标存储节点，用于存储目标EC条带的m + k个目标EC块; 向目标存储节点发送准备消息; 接收目标存储节点发送的响应消息; 并向目标存储节点发送执行消息以指示目标存储节点写入准备日志中的目标EC块。

公开(公告)号：US09442673B2

公开(公告)日：2016-09-13

申请号：US14291314

申请日：2014-05-30

Applicant: Huawei Technologies Co., Ltd.

Inventor： Zhihui Chen ,  Daohui Wang ,  Zhenxing Dai

IPC: G06F12/00 ,  G06F3/06 ,  G06F17/30 ,  G06F11/07

CPC classification number: G06F3/065 ,  G06F3/0604 ,  G06F3/0614 ,  G06F3/0631 ,  G06F3/0683 ,  G06F3/0689 ,  G06F11/0727 ,  G06F11/0793 ,  G06F17/30 ,  G06F2003/0692 ,  G06F2003/0697

Abstract: The storage method according to the present invention includes: partitioning raw data into several data blocks; calculating, according to a preset mapping algorithm, three consecutive virtual storage partitions to which a first data block is mapped, where a virtual storage partition is a partition obtained by dividing a virtual storage area, each of the virtual storage partitions is mapped to one physical disk, physical disks have consecutive sequence numbers, and sequence numbers of three physical disks that are mapped to the three consecutive virtual storage partitions are in an arithmetic sequence with a non-zero common difference; and storing, according to the calculated three consecutive virtual storage partitions and the three physical disks that are mapped to the three consecutive virtual storage partitions, the first data block and a first copy and a second copy of the first data block in the three physical disks in sequence.

Abstract translation: 根据本发明的存储方法包括：将原始数据分割成多个数据块; 根据预设映射算法，计算映射有第一数据块的三个连续的虚拟存储分区，其中虚拟存储分区是通过划分虚拟存储区域获得的分区，每个虚拟存储分区被映射到一个物理 磁盘，物理磁盘具有连续的序列号，映射到三个连续的虚拟存储分区的三个物理磁盘的序列号是具有非零公共差异的算术序列; 并且根据计算出的三个连续的虚拟存储分区和映射到三个连续虚拟存储分区的三个物理磁盘，存储在三个物理磁盘中的第一数据块和第一数据块的第一副本和第二副本 按顺序。

公开(公告)号：US20150113218A1

公开(公告)日：2015-04-23

申请号：US14586186

申请日：2014-12-30

Applicant: Huawei Technologies Co., Ltd.

Inventor： Shengbing Shi ,  Daohui Wang ,  Yan Wang

IPC: G06F3/06 ,  G06F17/30

CPC classification number: G06F3/0619 ,  G06F3/061 ,  G06F3/065 ,  G06F3/0665 ,  G06F3/067 ,  G06F3/0689 ,  G06F16/2237

Abstract: The distributed data processing method includes receiving storage information of a logical volume; receiving a data reading or writing command sent by the user, and determining a first storage information according to the data reading or writing command and the storage information of the logical volume; determining a data processing node corresponding to each group of four-tuple storage information according to the tree identifier and the data block identifier in each group of four-tuple information; and sending, by the cluster client processing apparatus, a data processing command to the data processing node corresponding to each group of four-tuple information. The distributed data processing method and apparatus avoid a resource consumption problem brought by a need for global setting or Bitmap reading/writing in a distributed storage system, and improve data processing efficiency.

Abstract translation: 分布式数据处理方法包括：接收逻辑卷的存储信息; 接收用户发送的数据读取或写入命令，根据数据读取或写入命令和逻辑卷的存储信息确定第一存储信息; 根据每个四元组信息组中的树标识符和数据块标识符确定与每组四元组存储信息相对应的数据处理节点; 以及由所述集群客户端处理装置将数据处理命令发送到与每组四元组信息对应的数据处理节点。 分布式数据处理方法和装置避免了在分布式存储系统中需要全局设置或位图读/写所带来的资源消耗问题，并提高了数据处理效率。

公开(公告)号：US20130111187A1

公开(公告)日：2013-05-02

申请号：US13706068

申请日：2012-12-05

Applicant: Huawei Technologies Co., Ltd.

Inventor： Xian Liu ,  Daohui Wang ,  Deping Yang

IPC: G06F12/10

CPC classification number: G06F12/1018 ,  G06F3/0614 ,  G06F3/0626 ,  G06F3/065 ,  G06F3/067 ,  G06F3/0673 ,  G06F11/2094

Abstract: The present disclosure provides a data read and write method and apparatus and a storage system. The data read and write method includes: receiving, by a block storage driver of an origination device, a request for an LBA-based operation on a volume; converting the LBA-based operation request into a Key addressing-based operation request; and sending the Key addressing-based operation request to a routing library. Therefore, according to the present disclosure, reliability, availability, extensibility, and cheapness of the storage system may be improved, satisfying mass storage requirements for high extensibility, high reliability, high availability, and cheapness.

Abstract translation: 本公开提供了数据读写方法和装置以及存储系统。 数据读写方法包括：通过发起设备的块存储驱动器接收对卷的基于LBA的操作的请求; 将基于LBA的操作请求转换为基于键寻址的操作请求; 并将基于密钥寻址的操作请求发送到路由库。 因此，根据本公开，可以提高存储系统的可靠性，可用性，可扩展性和便宜性，满足高可扩展性，高可靠性，高可用性和便宜性的大容量存储要求。