Unlock instant, AI-driven research and patent intelligence for your innovation.

Data processing method and device in raid reconstruction process

A data processing and data technology, applied in the storage field, can solve problems such as business data loss, data loss, and inability to complete business processing, so as to avoid data loss and improve correctness

Active Publication Date: 2022-08-02
MACROSAN TECH
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] During the above RAID reconstruction process, if the member disk fails to be read, the corresponding data will be lost, and the reconstruction of the corresponding area cannot be completed.
Similarly, if reading the disk based on the front-end business request fails, the corresponding business data will be lost, and the corresponding business processing cannot be completed

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Data processing method and device in raid reconstruction process
  • Data processing method and device in raid reconstruction process
  • Data processing method and device in raid reconstruction process

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0112] In the first embodiment, the RAID may determine corresponding first location information for each first subcommand.

[0113] still with image 3 The block D604 shown is taken as an example, if subcommand 21 and subcommand 23 are both the first subcommand that fails to read, then RAID determines the area corresponding to subcommand 21 for repairing based on the start address and end address of subcommand 21 The position in the stripe of the desired read data, i.e., image 3 The position of the region pointed to by the neutron command 21 in the bar; based on the start address and the end address of the subcommand 23, determine the position of the required read data in the bar for repairing the corresponding region of the subcommand 23, that is, image 3 The position in the bar of the region pointed to by neutron command 23.

[0114] After the first position information corresponding to each first subcommand is determined in step 102, step 103 and step 104 are performed ...

Embodiment 2

[0118] In the second embodiment, the RAID determines the first position information of the data to be read in step 102 according to the area corresponding to the read command in step 101, or directly specifies that the first position information is the entire strip.

[0119] For example, when the read command in step 101 is a command issued based on the service read IO, it may only correspond to part of the data in a certain block, such as Figure 5 As shown, the read command corresponds to the shaded area on the left in the bar. The RAID determines the position of the shadow area in the stripe as the first position information.

[0120] like Image 6 As shown, the RAID reads the data of the corresponding area (shaded area) in P302 and D X data of the corresponding area (shaded area) in . RAID is based on the read data of the shaded area in P302 and D X The data in the shaded area is checked and calculated to obtain the data in the area corresponding to the read command in...

Embodiment 3

[0124] In the third embodiment, the RAID determines, according to the address ranges corresponding to all the failed read subcommands (first subcommands), the first location information of the read data needed to repair the area corresponding to the failed read subcommand.

[0125] Specifically, the start address corresponding to each first subcommand is obtained. From the obtained start addresses, the minimum start address and the maximum start address are determined. The corresponding position of the minimum start address in the bar is determined as the start position of the first position information; the corresponding position of the end address of the first subcommand including the largest start address in the bar is determined as the first position The end position of the location information. That is, the position in the strip of the area between the minimum start address and the maximum end address is determined as the first position information.

[0126] still with ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The present application provides a data processing method and device in a RAID reconstruction process. In this method, after the RAID read disk fails, the disk read command is split into several subcommands and sent to the disk. Based on the read result returned by each subcommand, the RAID retains the data in the area corresponding to the successfully read subcommand, and uses the data in the hot spare disk to restore the data in the area corresponding to the failed read subcommand. Since the service write IO will still be processed during the RAID reconstruction process, the hot spare disk will be involved in the process of executing the service write IO, that is to say, the hot spare disk has the correct data to be written. The data in the area corresponding to the read failure subcommand for data restoration in the spare disk can be effectively improved, and the correctness of data restoration can be effectively improved to avoid data loss as much as possible.

Description

technical field [0001] The present application relates to the field of storage technologies, and in particular, to a data processing method and device in a RAID reconstruction process. Background technique [0002] Redundant Array of Independent Disks (English: Redundant Array of Independent Disks, abbreviation: RAID) is a combination of multiple independent physical disks according to different data organization methods to form a disk group, providing higher storage performance and reliability than a single disk. sex. [0003] Each physical disk in a RAID can also be called a member disk of the RAID. When RAID detects a member disk failure, it needs to read the data in other member disks, reconstruct the data in the faulty disk according to the read data in other member disks, and write it into the hot spare disk, and use the hot spare disk to replace the faulty disk. disks, restoring the data redundancy of the RAID, a process called RAID reconstruction. [0004] During ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06F3/06G06F11/16
CPCG06F3/0607G06F3/0632G06F3/0689G06F11/16
Inventor 高玉之
Owner MACROSAN TECH