#autoscaling — Public Fediverse posts
Live and recent posts from across the Fediverse tagged #autoscaling, aggregated by home.social.
-
The hailstorm last week pushed several Swiss insurance claim portals to their limits. ⛈️
Portals were temporarily overloaded or unreachable.
With Managed Kubernetes (NKE), the Horizontal Pod and Cluster Autoscaler can scale things, provided they're configured. ⚙️
That's not a default setting, it needs the right configuration, and database/backend must not become the bottleneck either.
How ready is your infrastructure for the next spike?
-
The hailstorm last week pushed several Swiss insurance claim portals to their limits. ⛈️
Portals were temporarily overloaded or unreachable.
With Managed Kubernetes (NKE), the Horizontal Pod and Cluster Autoscaler can scale things, provided they're configured. ⚙️
That's not a default setting, it needs the right configuration, and database/backend must not become the bottleneck either.
How ready is your infrastructure for the next spike?
-
The hailstorm last week pushed several Swiss insurance claim portals to their limits. ⛈️
Portals were temporarily overloaded or unreachable.
With Managed Kubernetes (NKE), the Horizontal Pod and Cluster Autoscaler can scale things, provided they're configured. ⚙️
That's not a default setting, it needs the right configuration, and database/backend must not become the bottleneck either.
How ready is your infrastructure for the next spike?
-
The hailstorm last week pushed several Swiss insurance claim portals to their limits. ⛈️
Portals were temporarily overloaded or unreachable.
With Managed Kubernetes (NKE), the Horizontal Pod and Cluster Autoscaler can scale things, provided they're configured. ⚙️
That's not a default setting, it needs the right configuration, and database/backend must not become the bottleneck either.
How ready is your infrastructure for the next spike?
-
KEDA как финансовый гардрейл: scale-to-zero, лимиты реплик и автоскейлинг по событиям в Kubernetes
Разберем KEDA именно как практический FinOps-гардрейл для Kubernetes: где HPA уже не хватает, как устроен ScaledObject, как безопасно подходить к scale-to-zero, какие ограничения ставить через maxReplicaCount и какие метрики собрать до пилота, чтобы потом доказать эффект цифрами.
https://habr.com/ru/companies/finops_ru/articles/1056066/
#keda #kubernetes #autoscaling #finops #hpa #devops #sre #cloudcost #prometheus #rabbitmq
-
Model Predictive Control для Kubernetes autoscaling: что получилось, где HPA оказался сильнее
Короткий пик нагрузки может закончиться раньше, чем Kubernetes успеет добавить готовую ёмкость. Разбираю, почему HPA и MPC-подходы упираются не только в алгоритм, но и в задержку метрик, запуск Pod и readiness. Разобрать лаг автоскейлинга
https://habr.com/ru/articles/1043074/
#kubernetes #hpa #autoscaling #автоскейлинг #prometheus #readiness #p95 #p99 #Model_Predictive_Control #mpc