Re:Building the largest known Kubernetes cluster, with 130k ...
by senorrib on Monday November 24, 2025 @09:19AM
(#46034387)
No a k8s dev, but I feel like this is the answer. K8s isn't usually just scheduling pods round robin or at random. There's a lot of state to evaluate, and the problem of scheduling pods becomes an NP-hard problem similar to bin packing problem. I doubt the implementation tries to be optimal here, but it feels a computationally heavy problem.
[ Parent
| on HN ]
Re:Building the largest known Kubernetes cluster, with 130k ...
by OvervCW on Monday November 24, 2025 @10:24AM
(#46035077)
In what way is it NP-hard? From what I can gather it just eliminates nodes where the pod wouldn't be allowed to run, calculates a score for each and then randomly selects one of the nodes that has the lowest score, so trivially parallelizable.
Re:Building the largest known Kubernetes cluster, with 130k ...
by femiagbabiaka on Monday November 24, 2025 @08:16PM
(#46041311)
I think filtering and scoring fall under a heuristics based approach to address NP-hardness?
Binpacking seems to be a well-defined NP-hard problem: https://en.wikipedia.org/wiki/Bin_packing_problem
Re:Building the largest known Kubernetes cluster, with 130k ...
by stevefan1999 on Tuesday November 25, 2025 @02:56AM
(#46043406)
That's greedy