Implementing kubernetes node bin packing

7.4 relevance

Kubernetes resource optimization technique, directly applicable to cloud infrastructure.

Cloud blog.costgraph.ai

Answer the board on AI readiness

Arrive with evidence, not opinion. See how your foundation benchmarks against your peers, get a clear read, and leave with a ranked place to start.

Why It Matters

This matters for platform engineers because it provides a data-driven, multi-dimensional approach to node consolidation that directly reduces cloud costs and addresses the common challenge of justifying node count reductions.

Key Takeaways

Use real usage percentiles and workload volatility to rightsize pod requests and apply vector bin packing heuristics to consolidate Kubernetes nodes.

Tetris in d dimensions: packing pods by size strands memory across 4 nodes, fitting each pod to the hole left fills 3 nodes completely.

Summary

CostGraph treats Kubernetes node rightsizing as vector bin packing, using geometric heuristics (Panigrahy et al. 2011) to pack pods sized from 7-day P95 usage across CPU, memory, pod count, GPUs, disk, and IP constraints. Pod requests are rightsized by dividing P95 by a utilization target (90% for stable workloads with CV<0.25, 60% for spiky with CV>=0.75, else 80%), and the greedy packing yields a floor on savings for consolidation.

Author

Emmanuel Bakare