debian-mirror-gitlab/config/prometheus/common_metrics.yml

231 lines
9.8 KiB
YAML
Raw Normal View History

2019-07-31 22:56:46 +05:30
dashboard: 'Environment metrics'
priority: 1
panel_groups:
2020-04-08 14:13:33 +05:30
- group: System metrics (Kubernetes)
priority: 15
panels:
- title: "Memory Usage (Total)"
type: "area-chart"
y_label: "Total Memory Used (GB)"
weight: 4
metrics:
- id: system_metrics_kubernetes_container_memory_total
query_range: 'avg(sum(container_memory_usage_bytes{container_name!="POD",pod_name=~"^%{ci_environment_slug}-(.*)",namespace="%{kube_namespace}"}) by (job)) without (job) /1024/1024/1024'
label: Total (GB)
unit: GB
- title: "Core Usage (Total)"
type: "area-chart"
y_label: "Total Cores"
weight: 3
metrics:
- id: system_metrics_kubernetes_container_cores_total
query_range: 'avg(sum(rate(container_cpu_usage_seconds_total{container_name!="POD",pod_name=~"^%{ci_environment_slug}-(.*)",namespace="%{kube_namespace}"}[15m])) by (job)) without (job)'
label: Total (cores)
unit: "cores"
- title: "Memory Usage (Pod average)"
type: "line-chart"
y_label: "Memory Used per Pod (MB)"
weight: 2
metrics:
- id: system_metrics_kubernetes_container_memory_average
query_range: 'avg(sum(container_memory_usage_bytes{container_name!="POD",pod_name=~"^%{ci_environment_slug}-([^c].*|c([^a]|a([^n]|n([^a]|a([^r]|r[^y])))).*|)-(.*)",namespace="%{kube_namespace}"}) by (job)) without (job) / count(avg(container_memory_usage_bytes{container_name!="POD",pod_name=~"^%{ci_environment_slug}-([^c].*|c([^a]|a([^n]|n([^a]|a([^r]|r[^y])))).*|)-(.*)",namespace="%{kube_namespace}"}) without (job)) /1024/1024'
label: Pod average (MB)
unit: MB
- title: "Canary: Memory Usage (Pod Average)"
type: "line-chart"
y_label: "Memory Used per Pod (MB)"
weight: 2
metrics:
- id: system_metrics_kubernetes_container_memory_average_canary
query_range: 'avg(sum(container_memory_usage_bytes{container_name!="POD",pod_name=~"^%{ci_environment_slug}-canary-(.*)",namespace="%{kube_namespace}"}) by (job)) without (job) / count(avg(container_memory_usage_bytes{container_name!="POD",pod_name=~"^%{ci_environment_slug}-canary-(.*)",namespace="%{kube_namespace}"}) without (job)) /1024/1024'
label: Pod average (MB)
unit: MB
track: canary
- title: "Core Usage (Pod Average)"
type: "line-chart"
y_label: "Cores per Pod"
weight: 1
metrics:
- id: system_metrics_kubernetes_container_core_usage
query_range: 'avg(sum(rate(container_cpu_usage_seconds_total{container_name!="POD",pod_name=~"^%{ci_environment_slug}-([^c].*|c([^a]|a([^n]|n([^a]|a([^r]|r[^y])))).*|)-(.*)",namespace="%{kube_namespace}"}[15m])) by (job)) without (job) / count(sum(rate(container_cpu_usage_seconds_total{container_name!="POD",pod_name=~"^%{ci_environment_slug}-([^c].*|c([^a]|a([^n]|n([^a]|a([^r]|r[^y])))).*|)-(.*)",namespace="%{kube_namespace}"}[15m])) by (pod_name))'
label: Pod average (cores)
unit: "cores"
- title: "Canary: Core Usage (Pod Average)"
type: "line-chart"
y_label: "Cores per Pod"
weight: 1
metrics:
- id: system_metrics_kubernetes_container_core_usage_canary
query_range: 'avg(sum(rate(container_cpu_usage_seconds_total{container_name!="POD",pod_name=~"^%{ci_environment_slug}-canary-(.*)",namespace="%{kube_namespace}"}[15m])) by (job)) without (job) / count(sum(rate(container_cpu_usage_seconds_total{container_name!="POD",pod_name=~"^%{ci_environment_slug}-canary-(.*)",namespace="%{kube_namespace}"}[15m])) by (pod_name))'
label: Pod average (cores)
unit: "cores"
track: canary
- title: "Knative function invocations"
type: "area-chart"
y_label: "Invocations"
weight: 1
metrics:
- id: system_metrics_knative_function_invocation_count
query_range: 'sum(ceil(rate(istio_requests_total{destination_service_namespace="%{kube_namespace}", destination_service=~"%{function_name}.*"}[1m])*60))'
label: invocations / minute
unit: requests
2019-07-31 22:56:46 +05:30
# NGINX Ingress metrics for pre-0.16.0 versions
2019-02-15 15:39:39 +05:30
- group: Response metrics (NGINX Ingress VTS)
2017-09-10 17:25:29 +05:30
priority: 10
2019-07-31 22:56:46 +05:30
panels:
2017-09-10 17:25:29 +05:30
- title: "Throughput"
2019-07-31 22:56:46 +05:30
type: "area-chart"
2017-09-10 17:25:29 +05:30
y_label: "Requests / Sec"
weight: 1
2019-07-31 22:56:46 +05:30
metrics:
2018-11-20 20:47:30 +05:30
- id: response_metrics_nginx_ingress_throughput_status_code
query_range: 'sum(rate(nginx_upstream_responses_total{upstream=~"%{kube_namespace}-%{ci_environment_slug}-.*"}[2m])) by (status_code)'
2017-09-10 17:25:29 +05:30
unit: req / sec
2018-03-17 18:26:18 +05:30
label: Status Code
2017-09-10 17:25:29 +05:30
- title: "Latency"
2019-07-31 22:56:46 +05:30
type: "area-chart"
2017-09-10 17:25:29 +05:30
y_label: "Latency (ms)"
2020-04-08 14:13:33 +05:30
y_axis:
format: milliseconds
2017-09-10 17:25:29 +05:30
weight: 1
2019-07-31 22:56:46 +05:30
metrics:
2018-11-20 20:47:30 +05:30
- id: response_metrics_nginx_ingress_latency_pod_average
query_range: 'avg(nginx_upstream_response_msecs_avg{upstream=~"%{kube_namespace}-%{ci_environment_slug}-.*"})'
2019-10-12 21:52:04 +05:30
label: Pod average (ms)
2017-09-10 17:25:29 +05:30
unit: ms
- title: "HTTP Error Rate"
2019-07-31 22:56:46 +05:30
type: "area-chart"
2019-10-12 21:52:04 +05:30
y_label: "HTTP Errors (%)"
2020-04-08 14:13:33 +05:30
y_axis:
format: percentHundred
2017-09-10 17:25:29 +05:30
weight: 1
2019-07-31 22:56:46 +05:30
metrics:
2018-11-20 20:47:30 +05:30
- id: response_metrics_nginx_ingress_http_error_rate
query_range: 'sum(rate(nginx_upstream_responses_total{status_code="5xx", upstream=~"%{kube_namespace}-%{ci_environment_slug}-.*"}[2m])) / sum(rate(nginx_upstream_responses_total{upstream=~"%{kube_namespace}-%{ci_environment_slug}-.*"}[2m])) * 100'
2019-10-12 21:52:04 +05:30
label: 5xx Errors (%)
2018-11-08 19:23:39 +05:30
unit: "%"
2019-02-15 15:39:39 +05:30
# NGINX Ingress metrics for post-0.16.0 versions
- group: Response metrics (NGINX Ingress)
priority: 10
2019-07-31 22:56:46 +05:30
panels:
2019-02-15 15:39:39 +05:30
- title: "Throughput"
2019-07-31 22:56:46 +05:30
type: "area-chart"
2019-02-15 15:39:39 +05:30
y_label: "Requests / Sec"
weight: 1
2019-07-31 22:56:46 +05:30
metrics:
2019-02-15 15:39:39 +05:30
- id: response_metrics_nginx_ingress_16_throughput_status_code
query_range: 'sum(label_replace(rate(nginx_ingress_controller_requests{namespace="%{kube_namespace}",ingress=~".*%{ci_environment_slug}.*"}[2m]), "status_code", "${1}xx", "status", "(.)..")) by (status_code)'
unit: req / sec
label: Status Code
- title: "Latency"
2019-07-31 22:56:46 +05:30
type: "area-chart"
2019-02-15 15:39:39 +05:30
y_label: "Latency (ms)"
weight: 1
2019-07-31 22:56:46 +05:30
metrics:
2019-02-15 15:39:39 +05:30
- id: response_metrics_nginx_ingress_16_latency_pod_average
query_range: 'sum(rate(nginx_ingress_controller_ingress_upstream_latency_seconds_sum{namespace="%{kube_namespace}",ingress=~".*%{ci_environment_slug}.*"}[2m])) / sum(rate(nginx_ingress_controller_ingress_upstream_latency_seconds_count{namespace="%{kube_namespace}",ingress=~".*%{ci_environment_slug}.*"}[2m])) * 1000'
2019-10-12 21:52:04 +05:30
label: Pod average (ms)
2019-02-15 15:39:39 +05:30
unit: ms
- title: "HTTP Error Rate"
2019-07-31 22:56:46 +05:30
type: "area-chart"
2019-10-12 21:52:04 +05:30
y_label: "HTTP Errors (%)"
2019-02-15 15:39:39 +05:30
weight: 1
2019-07-31 22:56:46 +05:30
metrics:
2019-02-15 15:39:39 +05:30
- id: response_metrics_nginx_ingress_16_http_error_rate
query_range: 'sum(rate(nginx_ingress_controller_requests{status=~"5.*",namespace="%{kube_namespace}",ingress=~".*%{ci_environment_slug}.*"}[2m])) / sum(rate(nginx_ingress_controller_requests{namespace="%{kube_namespace}",ingress=~".*%{ci_environment_slug}.*"}[2m])) * 100'
2019-10-12 21:52:04 +05:30
label: 5xx Errors (%)
2019-02-15 15:39:39 +05:30
unit: "%"
2017-09-10 17:25:29 +05:30
- group: Response metrics (HA Proxy)
priority: 10
2019-07-31 22:56:46 +05:30
panels:
2017-09-10 17:25:29 +05:30
- title: "Throughput"
2019-07-31 22:56:46 +05:30
type: "area-chart"
2017-09-10 17:25:29 +05:30
y_label: "Requests / Sec"
weight: 1
2019-07-31 22:56:46 +05:30
metrics:
2018-11-20 20:47:30 +05:30
- id: response_metrics_ha_proxy_throughput_status_code
query_range: 'sum(rate(haproxy_frontend_http_requests_total{%{environment_filter}}[2m])) by (code)'
2017-09-10 17:25:29 +05:30
unit: req / sec
2018-11-20 20:47:30 +05:30
label: Status Code
2017-09-10 17:25:29 +05:30
- title: "HTTP Error Rate"
2019-07-31 22:56:46 +05:30
type: "area-chart"
2017-09-10 17:25:29 +05:30
y_label: "Error Rate (%)"
weight: 1
2019-07-31 22:56:46 +05:30
metrics:
2018-11-20 20:47:30 +05:30
- id: response_metrics_ha_proxy_http_error_rate
query_range: 'sum(rate(haproxy_frontend_http_responses_total{code="5xx",%{environment_filter}}[2m])) / sum(rate(haproxy_frontend_http_responses_total{%{environment_filter}}[2m]))'
2019-10-12 21:52:04 +05:30
label: HTTP Errors (%)
2017-09-10 17:25:29 +05:30
unit: "%"
- group: Response metrics (AWS ELB)
priority: 10
2019-07-31 22:56:46 +05:30
panels:
2017-09-10 17:25:29 +05:30
- title: "Throughput"
2019-07-31 22:56:46 +05:30
type: "area-chart"
2017-09-10 17:25:29 +05:30
y_label: "Requests / Sec"
weight: 1
2019-07-31 22:56:46 +05:30
metrics:
2018-11-20 20:47:30 +05:30
- id: response_metrics_aws_elb_throughput_requests
query_range: 'sum(aws_elb_request_count_sum{%{environment_filter}}) / 60'
2019-10-12 21:52:04 +05:30
label: Total (req/sec)
2017-09-10 17:25:29 +05:30
unit: req / sec
- title: "Latency"
2019-07-31 22:56:46 +05:30
type: "area-chart"
2017-09-10 17:25:29 +05:30
y_label: "Latency (ms)"
weight: 1
2019-07-31 22:56:46 +05:30
metrics:
2018-11-20 20:47:30 +05:30
- id: response_metrics_aws_elb_latency_average
query_range: 'avg(aws_elb_latency_average{%{environment_filter}}) * 1000'
2019-10-12 21:52:04 +05:30
label: Average (ms)
2017-09-10 17:25:29 +05:30
unit: ms
- title: "HTTP Error Rate"
2019-07-31 22:56:46 +05:30
type: "area-chart"
2017-09-10 17:25:29 +05:30
y_label: "Error Rate (%)"
weight: 1
2019-07-31 22:56:46 +05:30
metrics:
2018-11-20 20:47:30 +05:30
- id: response_metrics_aws_elb_http_error_rate
query_range: 'sum(aws_elb_httpcode_backend_5_xx_sum{%{environment_filter}}) / sum(aws_elb_request_count_sum{%{environment_filter}})'
2019-10-12 21:52:04 +05:30
label: HTTP Errors (%)
2017-09-10 17:25:29 +05:30
unit: "%"
- group: Response metrics (NGINX)
priority: 10
2019-07-31 22:56:46 +05:30
panels:
2017-09-10 17:25:29 +05:30
- title: "Throughput"
2019-07-31 22:56:46 +05:30
type: "area-chart"
2017-09-10 17:25:29 +05:30
y_label: "Requests / Sec"
weight: 1
2019-07-31 22:56:46 +05:30
metrics:
2018-11-20 20:47:30 +05:30
- id: response_metrics_nginx_throughput_status_code
query_range: 'sum(rate(nginx_server_requests{server_zone!="*", server_zone!="_", %{environment_filter}}[2m])) by (code)'
2017-09-10 17:25:29 +05:30
unit: req / sec
2018-03-17 18:26:18 +05:30
label: Status Code
2017-09-10 17:25:29 +05:30
- title: "Latency"
2019-07-31 22:56:46 +05:30
type: "area-chart"
2017-09-10 17:25:29 +05:30
y_label: "Latency (ms)"
weight: 1
2019-07-31 22:56:46 +05:30
metrics:
2018-11-20 20:47:30 +05:30
- id: response_metrics_nginx_latency
query_range: 'avg(nginx_server_requestMsec{%{environment_filter}})'
2019-10-12 21:52:04 +05:30
label: Upstream (ms)
2017-09-10 17:25:29 +05:30
unit: ms
2019-10-12 21:52:04 +05:30
- title: "HTTP Error Rate (Errors / Sec)"
2019-07-31 22:56:46 +05:30
type: "area-chart"
2017-09-10 17:25:29 +05:30
y_label: "HTTP 500 Errors / Sec"
2020-04-08 14:13:33 +05:30
y_axis:
precision: 0
2017-09-10 17:25:29 +05:30
weight: 1
2019-07-31 22:56:46 +05:30
metrics:
2018-11-20 20:47:30 +05:30
- id: response_metrics_nginx_http_error_rate
query_range: 'sum(rate(nginx_server_requests{code="5xx", %{environment_filter}}[2m]))'
2017-09-10 17:25:29 +05:30
label: HTTP Errors
unit: "errors / sec"
2020-04-22 19:07:51 +05:30
- title: "HTTP Error Rate"
type: "area-chart"
y_label: "HTTP Errors (%)"
weight: 1
metrics:
- id: response_metrics_nginx_http_error_percentage
query_range: 'sum(rate(nginx_server_requests{code=~"5.*", host="*", %{environment_filter}}[2m])) / sum(rate(nginx_server_requests{code="total", host="*", %{environment_filter}}[2m])) * 100'
label: 5xx Errors (%)
unit: "%"