Deployment Configuration Issues

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

Original topic: 部署配置问题

| username: TiDBer_yUoxD0vR

[TiDB Usage Environment] Production Environment / Testing / PoC
[TiDB Version]
[Reproduction Path] What operations were performed that led to the issue
For TiKV nodes, using 3 nodes with 32 cores and 64GB each, or using 6 nodes with 16 cores and 32GB each, which deployment method offers better performance? Is it better to have fewer nodes with higher configuration, or more nodes with lower configuration?
[Encountered Issues: Problem Phenomenon and Impact]
[Resource Configuration]
[Attachments: Screenshots/Logs/Monitoring]

| username: YuchongXU | Original post link

Multiple replicas also depend on your disk configuration and network configuration.

| username: zhanggame1 | Original post link

It’s better to deploy virtual machines separately, and then adjust the memory and CPU configuration based on the actual load situation.

| username: xfworld | Original post link

Decisively take it apart, save yourself the trouble.

| username: srstack | Original post link

:dotted_line_face: If deployed separately, the performance of a single node will be low, but resource isolation will prevent resource contention issues.

| username: redgame | Original post link

Fewer nodes with higher configuration is better.

| username: tidb菜鸟一只 | Original post link

If there are no network issues, then 6 nodes with 16 cores and 32GB each are definitely better, as you don’t need to worry about resource contention.

| username: Anna | Original post link

6 nodes with 16 cores and 32GB of RAM each

| username: system | Original post link

This topic was automatically closed 60 days after the last reply. New replies are no longer allowed.