Method and device for achieving space distribution in storage pool

A storage pool and internal space technology, applied in the direction of input/output to record carrier, etc., can solve problems such as successful allocation of space for new business data, reduction of data reliability, failure to write data reconstruction business data, etc., to achieve stable performance , The effect of reliability improvement

Active Publication Date: 2014-03-12
HUAWEI TECH CO LTD
View PDF4 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] When there is a faulty disk in the storage space, it is necessary to reconstruct the data of the faulty CKG in the storage pool or write new business data in the storage pool. The reconstructed data or new business data successfully allocates space, resulting in the failure of data reconstruction or writing of new business data; if the available CK is selected from the original member disk of the faulty CKG or the available CK is selected from the faulty disk It will lead to unstable performance of the new CKG and reduce the reliability of the data

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
  • Method and device for achieving space distribution in storage pool
  • Method and device for achieving space distribution in storage pool
  • Method and device for achieving space distribution in storage pool

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0045] This embodiment provides a method for realizing space allocation in a storage pool, please refer to figure 2 , the method flow includes:

[0046] 201. A faulty disk in the storage pool is detected;

[0047] 202. Determine the default disk array RAID attribute of the continuous space group CKG to be allocated;

[0048] 203. Determine whether the available disks in the storage pool are sufficient to allocate the CKG according to the default RAID attribute;

[0049] 204. If the available disk cannot allocate the CKG according to the default RAID attribute, select multiple contiguous spaces CK from the available disk to form a first CKG, and the RAID attribute of the first CKG is the same as the default RAID attribute. The RAID attributes are different.

[0050] Further, allocating the first CKG different from the default RAID attribute in the available disk includes:

[0051] Select a plurality of continuous spaces in the available disk to form the first CKG.

[0052...

Embodiment 2

[0073] This embodiment provides a method for realizing space allocation in a storage pool, please refer to image 3 , the method flow includes:

[0074] 301. It is detected that a faulty disk occurs in a storage pool.

[0075] 302. Determine a faulty continuous space group CKG corresponding to the faulty disk.

[0076] 303. Determine that the RAID attribute of the faulty CKG is the default RAID attribute.

[0077] 304. Determine whether the available disks in the storage pool are sufficient to allocate new CKGs according to the default RAID attributes.

[0078] 305. If the available disk cannot be assigned a new CKG according to the default RAID attribute, then determine whether the available space of the available disk in the storage pool other than the faulty disk is not lower than the space occupied by the data in the faulty CKG; if If yes, go to step 2041, otherwise go to step 2042.

[0079] 3051. Randomly select multiple CKs in the available space of the available dis...

Embodiment 3

[0097] This embodiment provides a method for implementing space allocation in a storage pool. see Image 6 , the method flow includes:

[0098] 601. Receive new service data.

[0099] 602. It is detected that a faulty disk occurs in the storage pool.

[0100] 603. Determine that the RAID attribute of the CKG allocated by the new service data request is the default RAID attribute.

[0101] 604. Determine whether the available disks in the storage pool are sufficient to allocate a new CKG according to the default RAID attribute.

[0102] 605. If the available disk cannot allocate a new CKG according to the default RAID attribute, allocate a first CKG in the available disk that is different from the default RAID attribute.

[0103] 606. Write new service data into the first CKG.

[0104] Specifically, when selecting a CK, it may be required that the hard disks of each selected CK are different, that is, each available disk only contributes one CK, so the problem of increased...

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 invention discloses a method and device for achieving space distribution in a storage pool and belongs to the field of electronic data storage. The method comprises the steps that a fault disk in the storage pool is detected; the default attribute of redundant arrays of independent disks (RAID) of chunk groups (CKG) which needs distribution is determined; whether a usable disk in the storage pool is sufficient for distributing the CKG according to the default attribute of the RAID is judged; and if the usable disk cannot distribute the CKG according to the default attribute of the RAID, a plurality of chunks (CK) are selected in the usable disk to form a first CKG, and the attribute of the RAID of the first CKG is different from the default attribute of the RAID. When the fault disk exists in the storage pool and the CKG needs distribution, even if the number of normal usable hard disks is small and space distribution cannot carried out according to the default attribute of the RAID of the CKG which needs distribution, by changing the default attribute of the RAID, a plurality of CK are selected in the usable disks to form the first CKG with the attribute different from the default attribute of the RAID of the CKG which needs distribution, and space distribution is achieved.

Description

technical field [0001] The invention relates to the field of electronic data storage, in particular to a method and device for realizing space allocation in a storage pool. Background technique [0002] When a hard disk failure occurs in a storage pool, it is necessary to restore the data in the faulty disk and save it to a normal hard disk through data reconstruction, or to write new business data to a normal hard disk. Therefore, a An effective method for realizing space allocation in the storage pool to ensure the success of data reconstruction and new business data writing. [0003] In the prior art, after a faulty disk occurs, the method to realize the space allocation in the storage pool is: when performing data reconstruction, the data on the faulty disk is divided into CK (Chunk, a continuous space on the hard disk) as the granularity, from other hard disks Look for a normally available CK, that is, a hot standby CK, and form a new CKG (ChunkGroup, a group composed ...

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 Applications(China)
IPC IPC(8): G06F3/06
Inventor 刘晓瑞薛迎春
Owner HUAWEI TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products