Uneven PG Distribution in a Ceph Cluster

Problem Description

**Table 1** Basic information
Item	Information
Source of the Problem	Online maintenance
Product	Kunpeng BoostKit
Sub-item	SDS
	Debugging and running
Component	Other
Output Time	2019-10-28
Author	Chen Xiaobo 00416232
Team	Kunpeng BoostKit
Review Result	Review passed
Review Date	2019-11-05
Release Date	2020-03-20
Keywords	Uneven distribution of PGs

Symptom

When the drives are heavy-loaded during the I/O test, the load of some drives reaches 100%, while that of some drives is less than 80%. The overall drive load is unbalanced. After the ceph pg dump command is executed, it is found that the placement groups (PGs) are not evenly distributed in the Ceph cluster.

Key Process and Cause Analysis

The number of PGs on each OSD varies greatly. Some OSDs are overloaded and become bottlenecks.

Conclusion and Solution

Use the balancer plugin to optimize PG distribution.

Check the PG distribution.
- Method 1:
```
ceph balancer eval
```
- Method 2:
```
ceph pg dump
```
Use either of the preceding commands.
Enable automatic balancing for Ceph PGs.
```
ceph balancer mode upmap
ceph balancer on
```
Ceph adjusts PG distribution every 60 seconds.
Repeat step 1. If the PG distribution does not change, the PG distribution is optimal.