TiDB Deployment NUMA Allocation

Translated
1

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

Original topic: tidb部署 numa分配

| username: 大鱼海棠

[TiDB Usage Environment] Production Environment / Testing / PoC
[TiDB Version] V5.4.1 v6.1
[Reproduction Path] What operations were performed that caused the issue
[Encountered Issue: Issue Phenomenon and Impact]
On a Haiguang server, when preparing to bind NUMA during deployment, the server has two dual-port network cards. Do these two optical cards only occupy one NUMA node? I am not familiar with hardware. Also, do disk interfaces occupy NUMA nodes? How can I check this? Can an expert provide some knowledge?
[Resource Configuration]
[Attachments: Screenshots/Logs/Monitoring]

2
| username: Kongdom | Original post link

Is there any reference content in the official documentation here?

3
| username: 大鱼海棠 | Original post link

I have already made the adjustments mentioned here. Now, I need to avoid the node where the network card is located, but I’m not very familiar with the hardware. So, I would like to ask:
Do two network cards actually occupy several NUMA nodes? Also, does the hard drive interface occupy them as well?

4
| username: alfred | Original post link

You can refer to this.

5
| username: system | Original post link

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