Analysis of Possible Causes and Troubleshooting Directions and Solutions for Sudden Latency Increase and IO Rise in TiDB Database Cluster

This topic has been translated from a Chinese forum by GPT and might contain errors.

Original topic: TiDB 数据库集群 突然延迟增加,IO 上升,可能的原因分析及排查方向与方案?

| username: TiDBer_CQ

[TiDB Usage Environment] Production Environment / Testing / PoC
[TiDB Version] v7
[Reproduction Path] It seems that there have been continuous data write operations by the same job
[Encountered Issues: Problem Symptoms and Impact] Database query is slow, response is slow, query timeout, etc.
[Resource Configuration] Observed from TiDB Dashboard that latency, IO, etc., have increased and are unstable

| username: 像风一样的男子 | Original post link

Have slow queries increased? What abnormal SQL statements are there in topsql and SQL statement analysis?

| username: TiDBer_QYr0vohO | Original post link

Check the monitoring, CPU, disk I/O, etc., and see if there are more slow queries on the dashboard.

| username: zhaokede | Original post link

Business sharding, hotspots, slow SQL

| username: dba远航 | Original post link

Check large SQL

| username: TiDBer_JUi6UvZm | Original post link

Check which SQL statements are causing the slow SQL.

| username: zhanggame1 | Original post link

Take a look at the top SQL and slow queries when extracting issues.

| username: tidb狂热爱好者 | Original post link


| username: stephanie | Original post link

First, take a look at the slow SQL, then check the IO usage.

| username: YuchongXU | Original post link

Slow SQL

| username: TiDBer_21wZg5fm | Original post link

Did you check the disk IO bottleneck?

| username: stephanie | Original post link

Has the issue been resolved? You can check TiDB’s dashboard for clues.

| username: wangkk2024 | Original post link