公开(公告)号：US10599436B2

公开(公告)日：2020-03-24

申请号：US16006878

申请日：2018-06-13

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Haiyan Liu ,  Jun Xu ,  Qun Yu

IPC: G06F9/46 ,  G06F9/38 ,  G06F9/50

Abstract: A data processing method and apparatus are provided. A system includes a CPU pool and a storage pool, a mapper node and a reducer node respectively run on different CPUs in the CPU pool, and a remote storage area shared by the mapper node and the reducer node is delimited in the storage pool. In this method, the mapper node executes a map task, and stores a data segment obtained by executing the map task, into the remote storage area; and the reducer node directly obtains a data segment to be processed by the reducer node from the remote storage area, and executes a reduce task on the data segment. The method omits some actions in the prior art, and shortens a time for executing the Map/Reduce task.

公开(公告)号：US10157143B2

公开(公告)日：2018-12-18

申请号：US15445542

申请日：2017-02-28

Applicant: Huawei Technologies Co., Ltd.

Inventor： Jun Xu ,  Guanyu Zhu ,  Qun Yu

IPC: G06F12/00 ,  G06F12/1009 ,  G06F9/54 ,  G06F12/08

Abstract: A file access method and apparatus, and a storage system are provided. After receiving a file access request including a file identifier, first physical address space is accessed according to first virtual address space and a first mapping relationship between the first virtual address space and the first physical address space storing a file system. After obtaining, from the first physical address space, an index node of an object file indicated by the file identifier, a file page table is obtained according to information included in the index node, where the file page table records second physical address space of the object file. Then, second virtual address space is allocated to the object file. After establishing a second mapping relationship between the second physical address space and the second virtual address space, the object file in the second physical address space is accessed according to the second virtual address space.

公开(公告)号：US20180356979A1

公开(公告)日：2018-12-13

申请号：US16105315

申请日：2018-08-20

Applicant: HUAWEI TECHNOLOGIES CO.,LTD.

Inventor： Qun Yu ,  Jun Xu ,  Yuangang Wang

IPC: G06F3/06 ,  G06F12/0868

CPC classification number: G06F3/061 ,  G06F3/06 ,  G06F3/0614 ,  G06F3/065 ,  G06F3/0656 ,  G06F3/067 ,  G06F3/0689 ,  G06F12/0868 ,  G06F2212/1016 ,  G06F2212/222 ,  G06F2212/281

Abstract: A storage system includes a management node and a plurality of storage nodes forming a redundant array of independent disks (RAID). When the management node determines that not all data in an entire stripe is updated based on a received write request, the management node sends update data chunk obtained from to-be-written data to corresponding storage node.The storage node do not directly update, based on the received update data chunks, data block stored in storage device of the storage node, but store the update data chunk into non-volatile memories (NVM) cache of the storage node and send the update data chunk to another storage node to backup. According to the data updating method, write amplification problems caused in a stripe update process can be reduced, thereby improving update performance of the storage system.

公开(公告)号：US20170168953A1

公开(公告)日：2017-06-15

申请号：US15445542

申请日：2017-02-28

Applicant: Huawei Technologies Co., Ltd.

Inventor： Jun Xu ,  Guanyu Zhu ,  Qun Yu

IPC: G06F12/1009

CPC classification number: G06F12/1009 ,  G06F9/545 ,  G06F12/08 ,  G06F2212/1024

Abstract: A file access method and apparatus, and a storage system are provided. After receiving a file access request including a file identifier, first physical address space is accessed according to first virtual address space and a first mapping relationship between the first virtual address space and the first physical address space storing a file system. After obtaining, from the first physical address space, an index node of an object file indicated by the file identifier, a file page table is obtained according to information included in the index node, where the file page table records second physical address space of the object file. Then, second virtual address space is allocated to the object file. After establishing a second mapping relationship between the second physical address space and the second virtual address space, the object file in the second physical address space is accessed according to the second virtual address space.

公开(公告)号：US11422703B2

公开(公告)日：2022-08-23

申请号：US16937946

申请日：2020-07-24

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Qun Yu ,  Jun Xu ,  Yuangang Wang

IPC: G06F3/06 ,  G06F12/08 ,  G06F12/0868

Abstract: A storage system includes a management node and a plurality of storage nodes forming a redundant array of independent disks (RAID). When the management node determines that not all data in an entire stripe is updated based on a received write request, the management node sends update data chunk obtained from to-be-written data to corresponding storage node. The storage node do not directly update, based on the received update data chunks, data block stored in storage device of the storage node, but store the update data chunk into non-volatile memories (NVM) cache of the storage node and send the update data chunk to another storage node to backup. According to the data updating method, write amplification problems caused in a stripe update process can be reduced, thereby improving update performance of the storage system.

公开(公告)号：US11030092B2

公开(公告)日：2021-06-08

申请号：US16748372

申请日：2020-01-21

Applicant: Huawei Technologies Co., Ltd.

Inventor： Jun Xu ,  Qun Yu ,  Licheng Chen

IPC: G06F12/02 ,  G06F3/06 ,  G06F12/0804 ,  G06F12/0868 ,  G06F12/0866

Abstract: An access request processing apparatus comprises, a processor determines an object cache page according to a write request when receiving the write request. After determining that the NVM stores a log chain of the object cache page, the processor inserts, into the log chain of the object cache page, a second data node recording information about a second log data chunk. The log chain already includes a first data node recording information about the first log data chunk. The second log data chunk is at least partial to-be-written data of the write request. Then, the processor sets, in the first data node, data that is in the first log data chunk and that overlaps the second log data chunk to invalid data.

公开(公告)号：US20200159655A1

公开(公告)日：2020-05-21

申请号：US16748372

申请日：2020-01-21

Applicant: Huawei Technologies Co., Ltd.

Inventor： Jun Xu ,  Qun Yu ,  Licheng Chen

IPC: G06F12/02 ,  G06F3/06 ,  G06F12/0866 ,  G06F12/0868 ,  G06F12/0804

Abstract: An access request processing apparatus comprises, a processor determines an object cache page according to a write request when receiving the write request. After determining that the NVM stores a log chain of the object cache page, the processor inserts, into the log chain of the object cache page, a second data node recording information about a second log data chunk. The log chain already includes a first data node recording information about the first log data chunk. The second log data chunk is at least partial to-be-written data of the write request. Then, the processor sets, in the first data node, data that is in the first log data chunk and that overlaps the second log data chunk to invalid data.

公开(公告)号：US10649897B2

公开(公告)日：2020-05-12

申请号：US16021555

申请日：2018-06-28

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Jun Xu ,  Qun Yu ,  Yuangang Wang

IPC: G06F12/00 ,  G06F11/00 ,  G06F12/0804 ,  G06F11/16 ,  G06F12/0868 ,  G06F12/02 ,  G06F11/14

Abstract: An access request processing method and apparatus, and a computer device are disclosed. The computer device includes a processor, a dynamic random-access memory (DRAM), and a non-volatile memory (NVM). When receiving a write request, the processor may identify an object cache page according to the write request. The processor obtains the to-be-written data from a buffer according to a buffer pointer in the write request, the to-be-written data including a new data chunk to be written into the object cache page. The processor then inserts a new data node into a log chain of the object cache page, where the NVM stores data representing the log chain of the object cache page. The new data node includes information regarding the new data chunk of the object cache page. The computer device provided in this application can reduce system overheads while protecting data consistency.

公开(公告)号：US10061711B2

公开(公告)日：2018-08-28

申请号：US15445349

申请日：2017-02-28

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Guanyu Zhu ,  Jun Xu ,  Qun Yu

IPC: G06F12/00 ,  G06F12/1009 ,  G06F12/109

CPC classification number: G06F12/1009 ,  G06F3/061 ,  G06F3/0643 ,  G06F3/0679 ,  G06F12/00 ,  G06F12/109 ,  G06F16/13 ,  G06F2212/1024 ,  G06F2212/651 ,  G06F2212/656 ,  G06F2212/657

Abstract: A file access method and apparatus, and a storage system are provided. After receiving a file access request from a process, a first physical address space is accessed according to a preset first virtual address space and a preset first mapping relationship between the first virtual address space and the first physical address space, where the first physical address space stores a file system. After obtaining an index node of a target file from the first physical address space according to a file identifier of the target file carried in the file access request, a file page table of the target file is obtained according to file page table information. The file page table records a second physical address space in the first physical address space. The target file is accessed according to the second physical address space.