https://platformengineering.org logo
Title
r

rei

01/31/2023, 9:25 AM
Hi there, do you know on methods or tooling to assign a Pod a specific IO load (load 1/5/15) profile? We have several pod as queue workers running across the cluster, they only need about 300m CPU and 400Mi RAM, however each Pod generate a lot of IO and compute load, hence slowing everything down. Is there any method to distribute the Pods better and not just set a high
resources.requests.cpu
, we do not want to waste computing power with almost empty nodes. Currently is not possible to change the software to be more performant 🤷
d

Dusan Gligoric

01/31/2023, 10:41 AM
You could try assigning more memory to the pod, might decrease the IO if your sys is swapping, faster disks if its possible, or use topology spread to make use of more nodes thus have more IO throughput disclaimer: not really an expert on topic https://kubernetes.io/docs/concepts/scheduling-eviction/topology-spread-constraints/
r

rei

01/31/2023, 10:42 AM
I am already using several pools
d

Dusan Gligoric

01/31/2023, 10:44 AM
a

Aly Ibrahim

01/31/2023, 3:53 PM
Another opened issue for the same