Method, electronic device and computer readable storage medium for i/o management

Patent metadata

Field	Value
Publication number	US-11366608-B2
Application number	US-201916354767-A
Country	US
Kind code	B2
Filing date	Mar 15, 2019
Priority date	Jul 20, 2018
Publication date	Jun 21, 2022
Grant date	Jun 21, 2022

Abstract

Techniques perform I/O management. The techniques involve: in response to receiving an I/O request for a redundant array of independent disks (RAID), determining a stripe of the RAID related to the I/O request; determining metadata corresponding to the stripe, the metadata indicating validity of current data in a corresponding data block of the RAID, the data block comprising one or more stripes; in response to the metadata indicating that the current data is valid, executing the I/O request by accessing the RAID; and in response to the metadata indicating that the current data is invalid, responding to the I/O request with zero data as the current data. Accordingly, disk access is reduced, metadata cache efficiency is increased, I/O performance is improved and the RAID reliability is enhanced.

First claim

We claim:

1. A method of input/output (I/O) management, the method comprising:
in response to receiving an I/O request for a redundant array of independent disks (RAID), determining a stripe of the RAID related to the I/O request;
determining metadata corresponding to the stripe, the metadata indicating validity of current data in a corresponding data block of the RAID, the data block comprising one or more stripes, wherein the metadata corresponding to the stripe comprises an individual bit indicating validity of the corresponding data block of the RAID;
in response to the metadata indicating that the current data is valid, executing the I/O request by accessing the RAID; and
in response to the metadata indicating that the current data is invalid and the I/O request being a read operation for the stripe of the RAID related to the I/O request, responding to the I/O request by directly returning zero data as a result of the read operation without reading any disk in the RAID, wherein the metadata was previously modified from indicating that the corresponding data block was valid to indicating that the corresponding data block is invalid by an instruction from a user, wherein the instruction from the user comprises a notification received from the user indicating that the corresponding data block is out of use.

2. The method of claim 1 , wherein determining the metadata comprises:
determining a position of the metadata in the RAID based on the determined stripe; and
obtaining the metadata from the RAID based on the determined position.

3. The method of claim 1 , wherein executing the I/O request comprises:
in response to the I/O request being a read operation, reading the current data in the stripe of the RAID as a result of the read operation; and
in response to the I/O request being a write operation, writing write-in data comprised in the I/O request into the stripe of the RAID.

4. The method of claim 1 , wherein responding to the I/O request with zero data as the current data comprises:
in response to the I/O request being a write operation,
writing the zero data into the stripe to replace the current data, and
writing write-in data comprised in the I/O request into the stripe into which the zero data has been written.

5. The method of claim 4 , further comprising:
in response to the I/O request being the write operation, modifying the metadata to indicate that the current data in the stripe is valid.

6. The method of claim 1 , further comprising:
in response to creation of the RAID, initializing each metadata for each of data blocks in the RAID, such that each metadata indicates that current data in the corresponding data block of the RAID is invalid.

7. The method of claim 1 , further comprising:
in response to failure of a first disk in the RAID, recovering metadata in the first disk based on metadata in a further disk of the RAID.

8. The method of claim 1 , further comprising:
in response to failure of a first disk in the RAID, determining the metadata corresponding to each of data blocks associated with the first disk; and
recovering, based on the determined metadata, data in each of data blocks associated with the first disk.

9. The method of claim 8 , wherein recovering the data comprises:
in response to the metadata indicating that the current data is valid, recovering the data of the data block in the first disk based on data of a corresponding data block in a further disk of the RAID; and
in response to the metadata indicating that the current data is invalid, maintaining the data block as null data in the first disk.

10. The method of claim 1 , wherein the metadata indicating that the data is invalid further indicates that the corresponding data block is capable of being internally wiped.

11. The method of claim 10 , wherein the metadata indicating that the data is invalid further indicates that the corresponding data block is unmapped.

12. An electronic device, comprising:
a processing unit; and
a memory storing instructions which, when executed by the processing unit, cause the electronic device to:
in response to receiving an input/output (I/O) request for a redundant array of independent disks (RAID), determine a stripe of the RAID related to the I/O request,
determine metadata corresponding to the stripe, the metadata indicating validity of current data in a corresponding data block of the RAID, the data block comprising one or more stripes, wherein the metadata corresponding to the stripe comprises an individual bit indicating validity of the corresponding data block of the RAID,
in response to the metadata indicating that the current data is valid, execute the I/O request by accessing the RAID, and
in response to the metadata indicating that the current data is invalid and the I/O request being a read operation for the stripe of the RAID related to the I/O request, respond to the I/O request by directly returning zero data as a result of the read operation without reading any disk in the RAID, wherein the metadata was previously modified from indicating that the corresponding data block was valid to indicating that the corresponding data block is invalid by an instruction from a user, wherein the instruction from the user comprises a notification received from the user indicating that the corresponding data block is out of use.

13. The electronic device of claim 12 , wherein the memory further stores instructions which, when executed by the processing unit, cause the electronic device to:
determine a position of the metadata in the RAID based on the determined stripe; and
obtain the metadata from the RAID based on the determined position.

14. The electronic device of claim 12 , wherein the memory further stores instructions which, when executed by the processing unit, cause the electronic device to:
in response to the I/O request being a read operation, read the current data in the stripe of the RAID as a result of the read operation; and
in response to the I/O request being a write operation, write write-in data comprised in the I/O request into the stripe of the RAID.

15. The electronic device of claim 12 , wherein the memory further stores instructions which, when executed by the processing unit, cause the electronic device to:
in response to the I/O request being a write operation,
write the zero data into the stripe to replace the current data, and
write write-in data comprised in the I/O request into the stripe into which the zero data has been written.

16. The electronic device of claim 15 , wherein the memory further stores instructions which, when executed by the processing unit, cause the electronic device to:
in response to the I/O request being the write operation, modify the metadata to indicate that the current data in the stripe is valid.

17. The electronic device of claim 12 , wherein the memory further stores instructions which, when executed by the processing unit, cause the electronic device to:
in response to creation of the RAID, initialize each metadata for each of data blocks in the RAID, such that each metadata indicates that current data in the corresponding data block of the RAID is invalid.

18. The electronic device of claim 12 , wherein the memory further stores instructions which, when executed by the processing unit, cause the electronic device to:
in response to failure of a first disk in the RAID, recover metadata in the first disk based on metadata in a further disk of the RAID.

19. The electronic device of claim 12 , wherein the

Assignees

• Emc Ip Holding Co Llc

Inventors

• Kang Jianbin
• Han Geng
• Dong Jibing
• Gao Hongpo
• Tang Haiying
• Xu Xinlei
• Gao Jian

Classifications

• G06F3/0655

  Vertical data movement, i.e. input-output transfer; data movement between one or more hosts and one or more storage devices · CPC title

• G06F3/0689

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

• G06F3/061 Primary

  Improving I/O performance · CPC title

• G06F11/1076

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

• G06F3/0659 Primary

  Command handling arrangements, e.g. command buffers, queues, command scheduling · CPC title