Krkn lib prometheus client + kube_burner references removed

Signed-off-by: Tullio Sebastiani <tsebasti@redhat.com>
2026-02-14 18:10:00 +00:00 · 2024-01-09 16:28:49 +01:00
parent 93f1f19411
commit f2d7f88cb8
19 changed files with 154 additions and 275 deletions
--- a/config/alerts.yaml
+++ b/config/alerts.yaml
@@ -0,0 +1,90 @@
+# etcd
+
+- expr: avg_over_time(histogram_quantile(0.99, rate(etcd_disk_wal_fsync_duration_seconds_bucket[2m]))[10m:]) > 0.01
+  description: 10 minutes avg. 99th etcd fsync latency on {{$labels.pod}} higher than 10ms. {{$value}}s
+  severity: warning
+
+- expr: avg_over_time(histogram_quantile(0.99, rate(etcd_disk_wal_fsync_duration_seconds_bucket[2m]))[10m:]) > 1
+  description: 10 minutes avg. 99th etcd fsync latency on {{$labels.pod}} higher than 1s. {{$value}}s
+  severity: error
+
+- expr: avg_over_time(histogram_quantile(0.99, rate(etcd_disk_backend_commit_duration_seconds_bucket[2m]))[10m:]) > 0.007
+  description: 10 minutes avg. 99th etcd commit latency on {{$labels.pod}} higher than 30ms. {{$value}}s
+  severity: warning
+
+- expr: rate(etcd_server_leader_changes_seen_total[2m]) > 0
+  description: etcd leader changes observed
+  severity: warning
+
+- expr: (last_over_time(etcd_mvcc_db_total_size_in_bytes[5m]) / last_over_time(etcd_server_quota_backend_bytes[5m]))*100 > 95
+  description: etcd cluster database is running full. 
+  severity: critical
+  
+- expr: (last_over_time(etcd_mvcc_db_total_size_in_use_in_bytes[5m]) / last_over_time(etcd_mvcc_db_total_size_in_bytes[5m])) < 0.5
+  description: etcd database size in use is less than 50% of the actual allocated storage.
+  severity: warning  
+
+- expr: rate(etcd_server_proposals_failed_total{job=~".*etcd.*"}[15m]) > 5
+  description: etcd cluster has high number of proposal failures.
+  severity: warning 
+
+- expr: histogram_quantile(0.99, rate(etcd_network_peer_round_trip_time_seconds_bucket{job=~".*etcd.*"}[5m])) > 0.15
+  description: etcd cluster member communication is slow.
+  severity: warning 
+
+- expr: histogram_quantile(0.99, sum(rate(grpc_server_handling_seconds_bucket{job=~".*etcd.*", grpc_method!="Defragment", grpc_type="unary"}[5m])) without(grpc_type)) > 0.15
+  description: etcd grpc requests are slow.
+  severity: critical
+      
+- expr: 100 * sum(rate(grpc_server_handled_total{job=~".*etcd.*", grpc_code=~"Unknown|FailedPrecondition|ResourceExhausted|Internal|Unavailable|DataLoss|DeadlineExceeded"}[5m])) without (grpc_type, grpc_code) / sum(rate(grpc_server_handled_total{job=~".*etcd.*"}[5m])) without (grpc_type, grpc_code) > 5
+  description: etcd cluster has high number of failed grpc requests.
+  severity: critical      
+      
+- expr: etcd_server_has_leader{job=~".*etcd.*"} == 0
+  description: etcd cluster has no leader.
+  severity: warning    
+    
+- expr: sum(up{job=~".*etcd.*"} == bool 1) without (instance) < ((count(up{job=~".*etcd.*"}) without (instance) + 1) / 2)
+  description: etcd cluster has insufficient number of members.
+  severity: warning      
+
+- expr: max without (endpoint) ( sum without (instance) (up{job=~".*etcd.*"} == bool 0) or count without (To) ( sum without (instance) (rate(etcd_network_peer_sent_failures_total{job=~".*etcd.*"}[120s])) > 0.01 )) > 0
+  description: etcd cluster members are down.
+  severity: warning  
+
+# API server
+- expr: avg_over_time(histogram_quantile(0.99, sum(irate(apiserver_request_duration_seconds_bucket{apiserver="kube-apiserver", verb=~"POST|PUT|DELETE|PATCH", subresource!~"log|exec|portforward|attach|proxy"}[2m])) by (le, resource, verb))[10m:]) > 1
+  description: 10 minutes avg. 99th mutating API call latency for {{$labels.verb}}/{{$labels.resource}} higher than 1 second. {{$value}}s
+  severity: error
+
+- expr: avg_over_time(histogram_quantile(0.99, sum(irate(apiserver_request_duration_seconds_bucket{apiserver="kube-apiserver", verb=~"LIST|GET", subresource!~"log|exec|portforward|attach|proxy", scope="resource"}[2m])) by (le, resource, verb, scope))[5m:]) > 1
+  description: 5 minutes avg. 99th read-only API call latency for {{$labels.verb}}/{{$labels.resource}} in scope {{$labels.scope}} higher than 1 second. {{$value}}s
+  severity: error
+
+- expr: avg_over_time(histogram_quantile(0.99, sum(irate(apiserver_request_duration_seconds_bucket{apiserver="kube-apiserver", verb=~"LIST|GET", subresource!~"log|exec|portforward|attach|proxy", scope="namespace"}[2m])) by (le, resource, verb, scope))[5m:]) > 5
+  description: 5 minutes avg. 99th read-only API call latency for {{$labels.verb}}/{{$labels.resource}} in scope {{$labels.scope}} higher than 5 seconds. {{$value}}s
+  severity: error
+
+- expr: avg_over_time(histogram_quantile(0.99, sum(irate(apiserver_request_duration_seconds_bucket{apiserver="kube-apiserver", verb=~"LIST|GET", subresource!~"log|exec|portforward|attach|proxy", scope="cluster"}[2m])) by (le, resource, verb, scope))[5m:]) > 30
+  description: 5 minutes avg. 99th read-only API call latency for {{$labels.verb}}/{{$labels.resource}} in scope {{$labels.scope}} higher than 30 seconds. {{$value}}s
+  severity: error
+
+# Control plane pods
+
+- expr: up{job=~"crio|kubelet"} == 0
+  description: "{{$labels.node}}/{{$labels.job}} down"
+  severity: warning
+
+- expr: up{job="ovnkube-node"} == 0
+  description: "{{$labels.instance}}/{{$labels.pod}} {{$labels.job}} down"
+  severity: warning
+
+# Service sync latency
+- expr: histogram_quantile(0.99, sum(rate(kubeproxy_network_programming_duration_seconds_bucket[2m])) by (le)) > 10
+  description: 99th Kubeproxy network programming latency higher than 10 seconds. {{$value}}s 
+  severity: warning
+
+# Prometheus alerts
+- expr: ALERTS{severity="critical", alertstate="firing"} > 0
+  description: Critical prometheus alert. {{$labels.alertname}}
+  severity: warning
--- a/config/alerts_openshift.yaml
+++ b/config/alerts_openshift.yaml
--- a/config/config.yaml
+++ b/config/config.yaml
@@ -51,15 +51,13 @@ cerberus:
 performance_monitoring:
    deploy_dashboards: False                              # Install a mutable grafana and load the performance dashboards. Enable this only when running on OpenShift
    repo: "https://github.com/cloud-bulldozer/performance-dashboards.git"
-    kube_burner_binary_url: "https://github.com/cloud-bulldozer/kube-burner/releases/download/v1.7.0/kube-burner-1.7.0-Linux-x86_64.tar.gz"
    capture_metrics: False
-    config_path: config/kube_burner.yaml                  # Define the Elasticsearch url and index name in this config
    metrics_profile_path: config/metrics-aggregated.yaml
    prometheus_url:                                       # The prometheus url/route is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes.
    prometheus_bearer_token:                              # The bearer token is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes. This is needed to authenticate with prometheus.
    uuid:                                                 # uuid for the run is generated by default if not set
    enable_alerts: False                                  # Runs the queries specified in the alert profile and displays the info or exits 1 when severity=error
-    alert_profile: config/alerts                          # Path or URL to alert profile with the prometheus queries
+    alert_profile: config/alerts.yaml                          # Path or URL to alert profile with the prometheus queries
    check_critical_alerts: False                          # When enabled will check prometheus for critical alerts firing post chaos
 tunings:
    wait_duration: 60                                      # Duration to wait between each chaos scenario
@@ -90,3 +88,6 @@ telemetry:
    oc_cli_path: /usr/bin/oc                                # optional, if not specified will be search in $PATH
    events_backup: True                                     # enables/disables cluster events collection

+
+
+
--- a/config/config_kind.yaml
+++ b/config/config_kind.yaml
@@ -20,15 +20,13 @@ cerberus:
 performance_monitoring:
    deploy_dashboards: False                              # Install a mutable grafana and load the performance dashboards. Enable this only when running on OpenShift
    repo: "https://github.com/cloud-bulldozer/performance-dashboards.git"
-    kube_burner_binary_url: "https://github.com/cloud-bulldozer/kube-burner/releases/download/v0.9.1/kube-burner-0.9.1-Linux-x86_64.tar.gz"
    capture_metrics: False
-    config_path: config/kube_burner.yaml                  # Define the Elasticsearch url and index name in this config
    metrics_profile_path: config/metrics-aggregated.yaml
    prometheus_url:                                       # The prometheus url/route is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes.
    prometheus_bearer_token:                              # The bearer token is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes. This is needed to authenticate with prometheus.
    uuid:                                                 # uuid for the run is generated by default if not set
    enable_alerts: False                                  # Runs the queries specified in the alert profile and displays the info or exits 1 when severity=error
-    alert_profile: config/alerts                          # Path to alert profile with the prometheus queries
+    alert_profile: config/alerts.yaml                          # Path to alert profile with the prometheus queries

 tunings:
    wait_duration: 60                                      # Duration to wait between each chaos scenario
--- a/config/config_kubernetes.yaml
+++ b/config/config_kubernetes.yaml
@@ -19,15 +19,13 @@ cerberus:
 performance_monitoring:
    deploy_dashboards: False                              # Install a mutable grafana and load the performance dashboards. Enable this only when running on OpenShift
    repo: "https://github.com/cloud-bulldozer/performance-dashboards.git"
-    kube_burner_binary_url: "https://github.com/cloud-bulldozer/kube-burner/releases/download/v0.9.1/kube-burner-0.9.1-Linux-x86_64.tar.gz"
    capture_metrics: False
-    config_path: config/kube_burner.yaml                  # Define the Elasticsearch url and index name in this config
    metrics_profile_path: config/metrics-aggregated.yaml
    prometheus_url:                                       # The prometheus url/route is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes.
    prometheus_bearer_token:                              # The bearer token is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes. This is needed to authenticate with prometheus.
    uuid:                                                 # uuid for the run is generated by default if not set
    enable_alerts: False                                  # Runs the queries specified in the alert profile and displays the info or exits 1 when severity=error
-    alert_profile: config/alerts                          # Path to alert profile with the prometheus queries
+    alert_profile: config/alerts.yaml                         # Path to alert profile with the prometheus queries
    check_critical_alerts: False                          # When enabled will check prometheus for critical alerts firing post chaos after soak time for the cluster to settle down
 tunings:
    wait_duration: 60                                      # Duration to wait between each chaos scenario
--- a/config/config_performance.yaml
+++ b/config/config_performance.yaml
@@ -41,15 +41,13 @@ cerberus:
 performance_monitoring:
    deploy_dashboards: True                               # Install a mutable grafana and load the performance dashboards. Enable this only when running on OpenShift
    repo: "https://github.com/cloud-bulldozer/performance-dashboards.git"
-    kube_burner_binary_url: "https://github.com/cloud-bulldozer/kube-burner/releases/download/v0.9.1/kube-burner-0.9.1-Linux-x86_64.tar.gz"
    capture_metrics: True
-    config_path: config/kube_burner.yaml                  # Define the Elasticsearch url and index name in this config
    metrics_profile_path: config/metrics-aggregated.yaml
    prometheus_url:                                       # The prometheus url/route is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes.
    prometheus_bearer_token:                              # The bearer token is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes. This is needed to authenticate with prometheus.
    uuid:                                                 # uuid for the run is generated by default if not set
    enable_alerts: True                                   # Runs the queries specified in the alert profile and displays the info or exits 1 when severity=error
-    alert_profile: config/alerts                          # Path to alert profile with the prometheus queries
+    alert_profile: config/alerts.yaml                          # Path to alert profile with the prometheus queries

 tunings:
    wait_duration: 60                                      # Duration to wait between each chaos scenario
--- a/config/kube_burner.yaml
+++ b/config/kube_burner.yaml
@@ -1,15 +0,0 @@
---
-
-global:
-  writeToFile: true
-  metricsDirectory: collected-metrics
-  measurements:
-    - name: podLatency
-      esIndex: kraken
-
-  indexerConfig:
-    enabled: true
-    esServers: [http://0.0.0.0:9200]  # Please change this to the respective Elasticsearch in use if you haven't run the podman-compose command to setup the infrastructure containers
-    insecureSkipVerify: true
-    defaultIndex: kraken
-    type: elastic