Data recovery method, data recovery device and distributed storage system

Patent metadata

Field	Value
Publication number	US-9529675-B2
Application number	US-201414331485-A
Country	US
Kind code	B2
Filing date	Jul 15, 2014
Priority date	Jul 26, 2013
Publication date	Dec 27, 2016
Grant date	Dec 27, 2016

Abstract

A data recovery method, a data recovery device and a distributed storage system are provided, where the method includes: in a case that a distributed storage system loses data of three nodes, recovering data on a target data storage node of the data on the three nodes according to data of a parity node and a data storage node without data loss; and performing degraded recovery on the remaining lost data according to the recovered data of the target data storage node. According to the embodiments of the present invention, a target data storage node first recovered is determined according to the symmetry of lost data, and the lost data of three nodes is recovered according to parity data and data that is not lost, which can improve the data recovery performance of the distributed storage system in a case that the data of three nodes is lost.

First claim

What is claimed is:

1. A data recovery method, comprising:
in a case that a distributed storage system loses data on three nodes, recovering data on a target data storage node of the data on the three nodes according to data on a parity node and a data storage node without data loss, wherein the target data storage node is determined according to symmetry of the lost data; and
performing degraded recovery on the remaining lost data according to the recovered data of the target data storage node.

2. The data recovery method according to claim 1 , wherein:
in a case that the lost data on the three nodes comprises data on three data storage nodes, the target data storage node is a data storage node with data loss and having an intermediate disk number; and
the recovering data on a target data storage node of the data on the three nodes according to data on a parity node and a data storage node without data loss comprises:
generating a diagonal adjuster and an inverse diagonal adjuster according to parity data, wherein the parity data comprises data on a horizontal parity node, a diagonal parity node and an inverse diagonal parity node;
generating first horizontal parity data, first diagonal parity data and first inverse diagonal parity data according to the data on the data storage node without data loss, the diagonal adjuster and the inverse diagonal adjuster; and
obtaining data on the data storage node with data loss and having the intermediate disk number by performing an optimized cross transposition operation according to the diagonal adjuster, the inverse diagonal adjuster, the first horizontal parity data, the first diagonal parity data and the first inverse diagonal parity data.

3. The data recovery method according to claim 2 , wherein generating a diagonal adjuster and an inverse diagonal adjuster according to parity data comprises:
generating the diagonal adjuster by using a formula

Q
s

=

⊕

i
=
0

p
-
2

⁢

(

P
i

⊕

Q
i

)

;

 and
generating the inverse diagonal adjuster by using a formula

R
s

=

⊕

i
=
0

p
-
2

⁢

(

P
i

⊕

R
i

)

,

 wherein:
Q s is the diagonal adjuster, R s is the inverse diagonal adjuster, P i is data of the i th stripe unit on the horizontal parity node, Q i is data of the i th stripe unit on the diagonal parity node, R i is data of the i th stripe unit on the inverse diagonal parity node, 0≦i≦p-2, and p is a prime number greater than or equal to a quantity of the data storage nodes.

4. The data recovery method according to claim 3 , wherein generating first horizontal parity data, first diagonal parity data and first inverse diagonal parity data according to the data on the data storage node without data loss, the diagonal adjuster and the inverse diagonal adjuster comprises:
generating the first horizontal parity data by using a formula

P
i
′

=

P
i

⊕

(

⊕

j
=
0

j
≠
r

,
s
,
t

p
′

-
1

⁢

D

i
,
j

)

;

generating the first diagonal parity data by using a formula

Q
i
′

=

Q
s

⊕

Q
i

⊕

(

⊕

j
=
0

j
≠
r

,
s
,
t

p
′

-
1

⁢

D

Assignees

• Huawei Tech Co Ltd

Inventors

• Ma Xiaohui
• Sun Yaping
• Chen Haixiao

Classifications

• G06F11/1088 Primary

  Reconstruction on already foreseen single or plurality of spare disks · CPC title

• G06F11/1076

  Parity data used in redundant arrays of independent storages, e.g. in RAID systems · CPC title

• G06F2211/1028

  Distributed, i.e. distributed RAID systems with parity · CPC title

• G06F11/1084

  Degraded mode, e.g. caused by single or multiple storage removals or disk failures · CPC title