Method and device for managing storage system

Patent metadata

Field	Value
Publication number	US-11269726-B2
Application number	US-201816021699-A
Country	US
Kind code	B2
Filing date	Jun 28, 2018
Priority date	Jun 30, 2017
Publication date	Mar 8, 2022
Grant date	Mar 8, 2022

Abstract

A method and device for managing a storage system comprising multiple storage devices in a first layer and at least one backup storage device in a second layer. In response to receiving a request for writing target data to the storage system, storing the target data to a first portion of storage devices among the multiple storage devices in the first layer; storing a first parity, determined on the basis of a first algorithm, of data in the first portion of storage devices to a second portion of storage devices among the multiple storage devices in the first layer; and storing a second parity, determined on the basis of a second algorithm, of data in the first portion of storage devices to a first backup storage device of the at least one backup storage device in the second layer.

First claim

The invention claimed is:

1. A method for managing a storage system, the storage system comprising multiple storage devices in a first layer and at least one backup storage device in a second layer, the method comprising:
in response to receiving a request for writing target data to the storage system, storing the target data to a first portion of storage devices among the multiple storage devices in the first layer;
providing a first RAID level of reliability to the stored target data, the providing of the first RAID level of reliability comprising:
determining, on the basis of a first algorithm, a P parity of the target data stored in the first portion of storage devices; and
storing the P parity to a second portion of storage devices among the multiple storage devices in the first layer;

in response to the storing of the P parity, returning a response indicating that the target data has been written to the storage system; and
in a background process:
providing a second RAID level of reliability to the target data, the providing of the second RAID level of reliability comprising:
determining, in the background process, a Q parity of the target data on the basis of a second algorithm; and
storing, in the background process, the Q parity to a first backup storage device of the at least one backup storage device in the second layer, the storage system having higher access efficiency due to the determining and the storing of the single P parity of the target data in the first layer, and the storage system having higher reliability due to the determining and the storing, in the background process, of the additional Q parity of the target data in the second layer.

2. The method according to claim 1 , wherein the storing the Q parity to the first backup storage device comprises:
in response to receiving a request for increasing reliability of the storage system, storing the Q parity to the first backup storage device.

3. The method according to claim 1 , further comprising:
in response to data in the first portion of storage devices being modified, sending the request.

4. The method according to claim 3 , wherein the storing the Q parity to the first backup storage device further comprises:
determining the Q parity on the basis of a parity, determined according to the second algorithm, of modified data in the first portion of storage devices; and
storing the determined Q parity to the first backup storage device.

5. The method according to claim 3 , wherein the storage system comprises a first stripe comprising multiple storage devices in a first layer and at least one backup storage device in a second layer, wherein the sending the request comprises:
in response to data in the first portion of storage devices in the first layer comprised in the first stripe being modified, setting a mark for the first stripe as a request for increasing reliability of the first stripe comprised in the storage system.

6. The method according to claim 5 , wherein the storing the Q parity to the first backup storage device further comprises:
determining the Q parity on the basis of a parity, determined according to the second algorithm, of modified data in the first portion of storage devices in the first layer of the first stripe; and
storing the Q parity to the first backup storage device of the at least one backup storage device comprised in the first stripe.

7. The method according to claim 1 , further comprising:
storing an R parity, determined on the basis of a third algorithm, of data in the first portion of storage devices to a second backup storage device of the at least one backup storage device in the second layer.

8. The method according to claim 1 , further comprising:
in response to a first device among the multiple storage devices in the first layer failing, recovering data in the first device on the basis of data in a storage device other than the first device in the first layer.

9. The method according to claim 1 , further comprising:
in response to the first backup storage device failing, determining the Q parity of the data in the first portion of storage devices on the basis of the second algorithm; and
recovering data in the first backup storage device on the basis of the Q parity.

10. The method according to claim 8 , further comprising:
in response to a second storage device in the storage system failing, recovering data in the first device and the second device on the basis of data in a storage device other than the first device and the second device in the storage system.

11. A method for managing a storage system, the storage system comprising multiple storage devices in a first layer and at least one backup storage device in a second layer, the method comprising:
in response to receiving a request for writing target data to the storage system, storing the target data to a first portion of storage devices among the multiple storage devices in the first layer;
storing a P parity, determined on the basis of a first algorithm, of data in the first portion of storage devices to a second portion of storage devices among the multiple storage devices in the first layer, the single P parity of the data providing a first RAID level of reliability to the data in the first portion of storage devices;
in a background process, storing a Q parity, determined on the basis of a second algorithm, of data in the first portion of storage devices to a first backup storage device of the at least one backup storage device in the second layer, the additional Q parity of the data providing a second RAID level of reliability to the data in the first portion of storage devices, the second RAID level providing an increased level of reliability to the data in the first portion of storage devices relative to the first RAID level;
in response to data in the first portion of storage devices being modified, sending the request, the storage system comprising a first stripe comprising multiple storage devices in a first layer and at least one backup storage device in a second layer, the sending of the request comprising:
in response to data in a first portion of storage devices in the first layer comprised in the first stripe being modified, setting a mark for the first stripe as a request for increasing reliability of the first stripe comprised in the storage system, the storage system comprising a second stripe comprising multiple storage devices in a first layer and at least one backup storage device in a second layer, the Q parity comprising a parity associated with the first stripe and a parity associated with the second stripe; and

storing the parity associated with the first stripe and the parity associated with the second stripe to different storage devices.

12. The method according to claim 11 , wherein storage devices in the first layer comprise at least one redundant array, wherein the storing the Q parity to the first backup storage device comprises:
determining the Q parity on the basis of the second algorithm according to data in a first portion of storage devices and a second portion of storage devices comprised in each redundant array of the at least one redundant array; and
storing the determined Q parity to the first backup storage device.

13. A device for managing a storage system, comprising:
one or more processors;
a memory coupled to at least one processor of the one or more processors;
computer program instructions stored in the memory which, when executed by the at least one processor, cause the device to execute a method for managing a storage system, the storage system comprising multiple storage devices in a first lay

Assignees

• Emc Ip Holding Co Llc

Inventors

• Xu Tao
• Xu Xinlei
• Li Liam Xiongcheng
• Yang Lifeng
• Gao Jian
• Han Geng

Classifications

• G06F11/1076 Primary

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

• G06F2201/82

  Solving problems relating to consistency · CPC title

• G06F3/0619 Primary

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

• G06F11/2094

  Redundant storage or storage space (G06F11/2056 takes precedence) · CPC title

• G06F11/1469

  Backup restoration techniques · CPC title