Fine-tuning for RAID0 HDD array

Elastic Stack Elasticsearch
1

Hello,

This may be a bit of a naive question.

It is recommended to have the following settings in case spinning disks are used for ES data storage:

index.store.throttle.type: none
index.merge.scheduler.max_thread_count: 1

However, let's say a RAID0 array of 16 HDDs is used. Is the above recommendation still valid in that context, given that IO operations on RAID0 arrays are optimized?

Otherwise, how these settings could be changed to get the most out of the spinning HD RAID0-based storage?

Thanks,
MG

2

You'd need to experiment with it, but in such a setup you could try raising the max thread count to eg. 2 or 3.

3

This topic was automatically closed 28 days after the last reply. New replies are no longer allowed.