Так там в статті ж не тільки про це. Наприклад про прекрасний принцип "як стався дефіцит пам'яті"Scoffer: ↑ 27.05.2026 15:32 Шаред гпу виявились супер-пупер дірявими і це внятно не лікується, принаймні поки що не вигадали як. На тому свого часу графічно-прискорений vdi загнувся як клас сервісів.
Memory overprovisioning sits at 79%. Organizations are paying for infrastructure that their workloads don’t even request.
The mechanics are simple: teams pad resource requests to avoid throttling and OOM evictions, the cost of that padding is invisible to the team in charge of the platform, and there’s no systematic process to revisit those definitions after deployment.
Helm charts use conservative estimates across services. Cluster autoscalers respond to inflated requests as if they were genuine demand, provisioning nodes to match the demand. The gap becomes structural.
The counterintuitive part is reliability.
The common assumption is that more headroom means fewer crashes. It doesn’t work that way. One cluster we looked at averaged 40–50 OOM kills per measurement interval with generous resource padding. After automated rightsizing was deployed – which also cut provisioned CPUs by roughly half – OOM kills dropped to near zero.
