tikv / tikv/pd

[next gen on clould] pd oom during tikv scaling up

Open
#9,555 1 comment 0 reactions 1 assignee Claimed by @rleungx View on GitHub
may-affects-6.5 may-affects-7.1 may-affects-7.5 may-affects-8.1 may-affects-8.5 nextgen severity/critical type/bug
Dominant language
Go
Stars
1.2k
Forks
783
Avg merge
5d 21h
Merged PRs (30d)
36

Description

## Bug Report

### What did you do?
3 * pd-4C-16GB
6 * tikv-16C-64GB
keyspace1:3 * tidb-16C-64GB
1、br restore 1400GB data to keyspace1
2、run workload with 160 threads
3、scale up tikv to 32C-128GB
Image

### What did you expect to see?
no oom

### What did you see instead?
1、two pd oom during tikv scaling up

Image

![Image](https://github.com/user-attachments/assets/c518cf91-2d85-4312-8aa2-4c55dba3597d)

2、pd leader cpu was nearly full before oom

### What version of PD are you using (`pd-server -V`)?
sh-5.1# ./pd-server -V
Release Version: v9.0.0-beta.2.pre-21-g071b864
Edition: Enterprise
Kernel Type: Next Generation
Git Commit Hash: 071b864ea68eef2fc1989c8591478cf2f15c4a65
Git Branch: HEAD
UTC Build Time: 2025-07-15 08:57:25
sh-5.1#

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.