Writing data into redundant array of independent disks (RAID) of storage system

Patent metadata

Field	Value
Publication number	US-9959079-B2
Application number	US-201715630970-A
Country	US
Kind code	B2
Filing date	Jun 23, 2017
Priority date	Dec 31, 2014
Publication date	May 1, 2018
Grant date	May 1, 2018

Abstract

In a storage system, a control device determines that at least one first storage device of X storage devices is out of service. Then, the control device selects a second storage device from the X storage device. A quantity of stripe members of a data stripe stored in the second storage device is less than a ratio of T divided by X. The control device further writes target data into the second storage device. The target data is a data unit or a check unit used to update at least one stripe member of the data stripe stored in the first storage device.

First claim

What is claimed is:

1. A method for writing data into a storage system comprising a control device and X storage devices forming a redundant array of independent disks (RAID), wherein a data stripe having T stripe members is stored in the RAID, and wherein X and T are integers, the method comprising:
when a first storage device of the RAID that stores at least one stripe member is out of service, selecting, by the control device, a second storage device of the RAID, wherein a quantity of stripe members of the data stripe stored in the second storage device is less than a ratio of T divided by X; and
writing, by the control device, target data into the second storage device, wherein the target data is a data unit or a check unit that is used to update the at least one stripe member of the data stripe stored in the first storage device.

2. The method according to claim 1 , wherein the T stripe members of the data stripe include N data units and M check units generated based on the N data units, N and M are integers, N≥2, and M≥1, and wherein T>X, and T is not equal to a multiple of X.

3. The method according to claim 1 , wherein stripe members of the data stripe stored in the second storage device are less than stripe members of the data stripe stored in one of other storage devices of the RAID.

4. The method according to claim 1 , wherein a quantity of stripe members of the data stripe stored in the first storage device is less than or equal to a quantity of out-of-service stripe members that is tolerable to the RAID.

5. A method for writing data into a storage system comprising a control device and X storage devices forming a redundant array of independent disks (RAID), wherein a data stripe stored in the RAID includes N+M stripe members in which N are data units and M are check units generated based on the N data units, and wherein X, M and N are integers, N≥2, M≥1, and N+M≥X; the method comprising:
when a first storage device of the RAID that stores at least one stripe member is out of service, selecting, by the control device, Y+1 second storage devices of the RAID; and
writing, by the control device, target data into the Y+1 second storage devices,
wherein Y=M−(┌(N+M)/X┐−1), wherein the target data is one or more data units or one or more check units used to update the at least one stripe member of the data stripe stored in the first storage device, and wherein ┌(N+M)/X┐ is a ceiling function of (N+M)/X.

6. The method according to claim 5 , wherein a quantity of stripe members of the data stripe stored in the first storage device is less than or equal to a quantity of out-of-service stripe members that is tolerable to the RAID.

7. The method according to claim 5 , wherein X=6.

8. The method according to claim 5 , wherein X=5 and N+M=X.

9. A storage system, comprising a control device and X storage devices forming a redundant array of independent disks (RAID), wherein a data stripe having T stripe members is stored in the RAID, wherein X and T are integers;
wherein the control device is configured to:
when a first storage device of the RAID that stores at least one stripe member is out of service, select a second storage device of the RAID, wherein a quantity of stripe members of the data stripe stored in the second storage device is less than a ratio of T divided by X; and
write target data into the second storage device, wherein the target data is a data unit or a check unit that is used to update the at least one stripe member of the data stripe stored in the first storage device.

10. The system according to claim 9 , wherein the T stripe members of the data stripe include N data units and M check units generated based on the N data units, N and M are integers, N≥2, and M≥1, and wherein T>X, and T is not equal to a multiple of X.

11. The system according to claim 9 , wherein stripe members of the data stripe stored in the second storage device are less than stripe members of the data stripe stored in one of other storage devices of the RAID.

12. The system according to claim 9 , wherein a quantity of stripe members of the data stripe stored in the first storage device is less than or equal to a quantity of out-of-service stripe members that is tolerable to the RAID.

13. A storage system, comprising a control device and X storage devices forming a redundant array of independent disks (RAID), wherein a data stripe stored in the RAID includes N+M stripe members in which N are data units and M are check units generated based on the N data units, and wherein X, M and N are integers, N≥2, M≥1, and N+M≥X;
wherein the control device is configured to:
when a first storage device of the RAID that stores at least one stripe member is out of service, select Y+1 second storage devices of the RAID; and
write target data into the Y+1 second storage devices,
wherein Y=M−(┌(N+M)/X┐−1), wherein the target data is one or more data units or one or more check units used to update the at least one stripe member of the data stripe stored in the first storage device, and wherein ┌(N+M)/X┐ is a ceiling function of (N+M)/X.

14. The system according to claim 13 , wherein a quantity of stripe members of the data stripe stored in the first storage device is less than or equal to a quantity of out-of-service stripe members that is tolerable to the RAID.

15. The system according to claim 13 , wherein X=6.

16. The system according to claim 13 , wherein X=5 and N+M=X.

Assignees

• Huawei Tech Co Ltd

Inventors

• Yi Letian
• Fang Xin
• Zhang Zhenhua

Classifications

• G06F11/1084 Primary

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

• G06F3/0619

  in relation to data integrity, e.g. data losses, bit errors · CPC title

• G06F3/0665

  at area level, e.g. provisioning of virtual or logical volumes · CPC title

• G06F11/108

  Parity data distribution in semiconductor storages, e.g. in SSD · CPC title

• G06F3/0689 Primary

  Disk arrays, e.g. RAID, JBOD · CPC title