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

CEPH placement group distribution method and device, server and storage medium

An allocation method and a technology for placing groups, which are applied in the field of distributed databases and can solve the problems of not considering the actual storage situation of each OSD and affecting performance, etc.

Active Publication Date: 2020-11-13
柏科数据技术(深圳)股份有限公司
View PDF6 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In view of this, the embodiments of the present invention provide a CEPH placement group allocation method, device, server and storage medium to solve the problem that the allocation of placement groups in the CEPH distributed storage system in the prior art does not take into account the actual storage situation of each OSD, Technical issues that in turn affect performance

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
  • CEPH placement group distribution method and device, server and storage medium
  • CEPH placement group distribution method and device, server and storage medium
  • CEPH placement group distribution method and device, server and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0027] figure 1 It is a schematic flowchart of the CEPH placement group allocation method provided by Embodiment 1 of the present invention. This embodiment is applicable to the allocation of placement groups PG in the CEPH distributed system, and the method can be executed by the allocation device of the CEPH placement group , and can be integrated in the CEPH distributed database server, specifically including the following steps:

[0028] S110. Read the affinity value of each OSD and the storage pool corresponding to the placement group to be allocated, where the affinity value is used to represent the storage capacity of the storage pool corresponding to the OSD.

[0029] In order to facilitate the management of data distribution, the system will first create a storage pool, and then the storage pool will be divided into multiple PGs.

[0030] The full name of PG is Placement Groups, which is translated into Chinese as a placement group. It is a carrier for placing object...

Embodiment 2

[0045] figure 2 It is a schematic flowchart of the CEPH placement group allocation method provided in Embodiment 2 of the present invention. In this embodiment, the method may further include the following step: adjusting the affinity of the OSD.

[0046] Correspondingly, the CEPH placement group allocation method provided by the embodiment of the present invention includes:

[0047] S210. Read the affinity value of each OSD and the storage pool corresponding to the placement group to be allocated, where the affinity value is used to represent the storage capacity of the storage pool corresponding to the OSD.

[0048] S220. Determine a mapping OSD according to the affinity value, and correspondingly assign the mapping OSD to the placement group.

[0049] S230, adjusting the affinity of the OSD.

[0050] After the OSD corresponding to the PG is allocated storage, the storage capacity of the mapped OSD changes accordingly. Obviously, after the PG is mapped to the OSD, part o...

Embodiment 3

[0054] image 3 It is a schematic flowchart of the allocation method of the CEPH placement group provided by the third embodiment of the present invention. This embodiment is optimized on the basis of the above-mentioned embodiment, and the affinity of the OSD will be adjusted according to the assigned PG. The specific optimization is: calculate The average PG number avg_sum allocated to the unit capacity of the entire pool; calculate the average PG number avg_self of the unit capacity of the OSD; for OSDs with avg_self greater than avg_sum, adjust their corresponding affinity downwards.

[0055] S310. Read the affinity value of each OSD and the storage pool corresponding to the placement group to be allocated, where the affinity value is used to represent the storage capacity of the storage pool corresponding to the OSD.

[0056] S320. Determine a mapping OSD according to the affinity value, and correspondingly assign the mapping OSD to the placement group.

[0057] S330. Ca...

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 embodiment of the invention discloses a CEPH placement group distribution method and device, a server and a storage medium, and the method comprises the steps: reading the affinity value of each OSD and a storage pool corresponding to a to-be-distributed placement group, wherein the affinity value is used for representing the storage capability corresponding to the OSD; and determining a mapping OSD according to the affinity value, and correspondingly allocating the mapping OSD to the placement group. The placement group PG can be reasonably distributed according to the actual storage capacity of the OSD. Existing hardware resources can be utilized in an expected mode, and different requirements of different users in respective use scenes can be met.

Description

technical field [0001] The present invention relates to the technical field of distributed databases, in particular to a method, device, equipment and storage medium for allocating CEPH placement groups. Background technique [0002] CEPH is a unified, distributed file system designed for excellent performance, reliability, and scalability. CEPH abandons the traditional centralized storage metadata addressing scheme, adopts the CRUSH algorithm, the data distribution is balanced, and the parallelism is high. It also considers the isolation of disaster recovery domains, and can implement replica placement rules for various loads, such as cross-computer room, rack awareness, etc. It can support the scale of thousands of storage nodes and support TB to PB level data. [0003] The traditional distributed storage system CEPH cuts data into objects of fixed size and introduces the concept of PG (PlacementGroup). PG is the logical layer between objects and OSD (Object Storage De...

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): G06F16/182G06F16/13G06F16/11
CPCG06F16/11G06F16/137G06F16/182
Inventor 黄汝林孟军
Owner 柏科数据技术(深圳)股份有限公司