Mixin / Scheduler
57,909

Created 5/5/2024
Updated 5/6/2024
Revision 2
Categories
DockerWeb Servers
Grafana Version >=10.4.1
Datasources
Prometheus

Description

This dashboard monitors the health and performance of a scheduling service by aggregating core metrics such as up and various scheduling latency buckets to track liveliness and end-to-end delays. It emphasizes latency distribution with 99th percentile measures like Scheduling latency 99th Quantile, Post Request Latency 99th Quantile, and Get Request Latency 99th Quantile, while also providing throughput signals via Kube API Request Rate and system resources through Memory, CPU usage, and Goroutines to spot resource contention and scaling needs.

Source Grafana.com

Used Metrics 14

  • go_goroutines

  • process_cpu_seconds_total

  • process_resident_memory_bytes

  • rest_client_request_duration_seconds_bucket

  • rest_client_requests_total

  • scheduler_binding_duration_seconds_bucket

  • scheduler_binding_duration_seconds_count

  • scheduler_e2e_scheduling_duration_seconds_bucket

  • scheduler_e2e_scheduling_duration_seconds_count

  • scheduler_scheduling_algorithm_duration_seconds_bucket

  • scheduler_scheduling_algorithm_duration_seconds_count

  • scheduler_volume_scheduling_duration_seconds_bucket

  • scheduler_volume_scheduling_duration_seconds_count

  • up

Get Dashboard
Download
Copy to Clipboard