VettedGaps

Grafana

Marketplace · 178 pain cards
Sample

Sample from Grafana

1 of 178 pain cards, shown in full — score, summary and a real quote from the thread it came from.

21
Kubernetes operators face CPU throttling and OOM from misconfigured resource requests and

We're seeing production issues because CPU limits cause throttling even when the node has spare capacity, and memory limits above requests lead to OOM kills fo…

CPU request is how much CPU is reserved for your pod if it needs it. The limit is a hard cap. Hit it and the kernel throttles the pod, even when the node still has spare CPU. That is the usual cause of CPU throttling on Kubernetes. It does not protect the neighboring pods. In my simple Web API test, adding a CPU limit took typical latency from 23 ms to 87 ms, (4x slower), with the limited pod throttled in half of all CFS windows, and the average CPU graph looked fine the whole time.

Performance & Reliability
10 posts
Pro

177 more pains are available in Pro

The blurred cards below are placeholders. No locked title, quote, score or id is sent to the browser.

Page 1 of 8 · 178 pains · 25 per page

Grafana is a Pro marketplace

Create a free account, then upgrade to Pro to unlock all 178 cards in Grafana.

Create free account

Already have an account? Sign in