Removed MDP (Multi Data path) how to configure new

Elastic Stack Elasticsearch
1

Now that I just learned that Elk is removing MDP that means I won't be assign multiple raw disk. :sob: ( which is bad idea)

but now it is there how do I configure. which is step back.

if I use raid1 then I am loosing half
if I use raid0 I have no fail safe whatever
if I use riid5, 6 loosing disk and speed.

what are people generally using for data path?

I have 4x2TB NVME in a data node and using /data01, /data02, /data03, /data04 at this time.

2

I'd say you have three options:

  1. Use RAID0 with a single Elasticsearch instance.
    1. Elastic from what I can tell recommends the use of RAID0, when using RAID, as data resiliency/redundancy is intended to be handled at the application layer via replicas + allocation awareness.
  2. Split the CPU and RAM resources the your existing Elasticsearch instance uses by 4, then run 4 instances of Elasticsearch on the same node.
    1. This can most easily be achieved by using containers (either via Docker or Kubernetes)
  3. You could also split it by two (2) and have two (2) RAID 0 arrays with two (2) instances of Elasticsearch each using one (1). Though this would be mixing both options 1 and 2, and probably adds unneeded complication/management overhead.

If you were to provide your reasoning behind using multi-path currently, it might help in providing a more accurate/useful solution.

3

What I like about using multi-path is all the disk is being used and full i/o achieved.
if I loose one disk I only have 1/4 of shard unavailable untill I replace the a disk.

performance is what I am after. and seems like you have good suggestion, I didn't thought about 2nd 3rd option at all.

was only thinking how I can setup raid :slight_smile:

each data node has 98 gig ram, and on 10 gig network.

4

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