Skip to content
Snippets Groups Projects
Commit 3997cec7 authored by Dhiraj Bodicherla's avatar Dhiraj Bodicherla
Browse files

Update reuben-test.yml

parent 95b0b0df
No related branches found
No related tags found
No related merge requests found
Pipeline #12776644 failed
---
dashboard: Environment metrics
priority: 1
dashboard: 'Pod metrics'
priority: 10
templating:
variables:
pod_name: 'thanos-query-85b468854c-xrxbx'
pod_name2: 'thanos-query-85b468854c-xrxbx'
panel_groups:
- 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
metric_id: 48
- 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
metric_id: 49
- 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
metric_id: 50
- 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
metric_id: 51
- 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
metric_id: 52
- 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
metric_id: 53
- 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
metric_id: 93
- group: Response metrics (NGINX Ingress VTS)
priority: 10
panels:
- title: Throughput
type: area-chart
y_label: Requests / Sec
weight: 1
metrics:
- 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)
unit: req / sec
label: Status Code
metric_id: 37
- title: Latency
type: area-chart
y_label: Latency (ms)
y_axis:
format: milliseconds
weight: 1
metrics:
- id: response_metrics_nginx_ingress_latency_pod_average
query_range: avg(nginx_upstream_response_msecs_avg{upstream=~"{{kube_namespace}}-{{ci_environment_slug}}-.*"})
label: Pod average (ms)
unit: ms
metric_id: 38
- title: HTTP Error Rate
type: area-chart
y_label: HTTP Errors (%)
y_axis:
format: percentHundred
weight: 1
metrics:
- 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
label: 5xx Errors (%)
unit: "%"
metric_id: 39
- group: Response metrics (NGINX Ingress)
priority: 10
panels:
- title: Throughput
type: area-chart
y_label: Requests / Sec
weight: 1
metrics:
- 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
metric_id: 60
- title: Latency
type: area-chart
y_label: Latency (ms)
weight: 1
metrics:
- 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
label: Pod average (ms)
unit: ms
metric_id: 61
- title: HTTP Error Rate
type: area-chart
y_label: HTTP Errors (%)
weight: 1
metrics:
- 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
label: 5xx Errors (%)
unit: "%"
metric_id: 62
- group: Response metrics (HA Proxy)
priority: 10
panels:
- title: Throughput
type: area-chart
y_label: Requests / Sec
weight: 1
metrics:
- id: response_metrics_ha_proxy_throughput_status_code
query_range: sum(rate(haproxy_frontend_http_requests_total{ {{environment_filter}}
}[2m])) by (code)
unit: req / sec
label: Status Code
metric_id: 40
- title: HTTP Error Rate
type: area-chart
y_label: Error Rate (%)
weight: 1
metrics:
- 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]))
label: HTTP Errors (%)
unit: "%"
metric_id: 41
- group: Response metrics (AWS ELB)
priority: 10
panels:
- title: Throughput
type: area-chart
y_label: Requests / Sec
weight: 1
metrics:
- id: response_metrics_aws_elb_throughput_requests
query_range: sum(aws_elb_request_count_sum{ {{environment_filter}} }) / 60
label: Total (req/sec)
unit: req / sec
metric_id: 42
- title: Latency
type: area-chart
y_label: Latency (ms)
weight: 1
metrics:
- id: response_metrics_aws_elb_latency_average
query_range: avg(aws_elb_latency_average{ {{environment_filter}} }) * 1000
label: Average (ms)
unit: ms
metric_id: 43
- title: HTTP Error Rate
type: area-chart
y_label: Error Rate (%)
weight: 1
metrics:
- 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}} })
label: HTTP Errors (%)
unit: "%"
metric_id: 44
- group: Response metrics (NGINX)
priority: 10
panels:
- title: Throughput
type: area-chart
y_label: Requests / Sec
weight: 1
metrics:
- id: response_metrics_nginx_throughput_status_code
query_range: sum(rate(nginx_server_requests{server_zone!="*", server_zone!="_",
{{environment_filter}} }[2m])) by (code)
unit: req / sec
label: Status Code
metric_id: 45
- title: Latency
type: area-chart
y_label: Latency (ms)
weight: 1
metrics:
- id: response_metrics_nginx_latency
query_range: avg(nginx_server_requestMsec{ {{environment_filter}} })
label: Upstream (ms)
unit: ms
metric_id: 46
- title: HTTP Error Rate (Errors / Sec)
type: area-chart
y_label: HTTP 500 Errors / Sec
y_axis:
precision: 0
weight: 1
metrics:
- id: response_metrics_nginx_http_error_rate
query_range: sum(rate(nginx_server_requests{code="5xx", {{environment_filter}}
}[2m]))
label: HTTP Errors
unit: errors / sec
metric_id: 47
- 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: "%"
metric_id: 234
- group: Business metrics (Custom)
priority: 0
panels:
- type: area-chart
title: Memory Usage
y_label: Usage
metrics:
- 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
unit: MB
label: ''
metric_id: 201
- type: area-chart
title: test1
y_label: a
metrics:
- query_range: up
unit: b
label: ''
metric_id: 305
- group: System metrics (Custom)
priority: -10
panels:
- type: area-chart
title: Overall CPU usage
y_label: Idle
metrics:
- query_range: 100 * (1 - avg by(instance)(irate(node_cpu_seconds_total{mode='idle'}[5m])))
unit: perc
label: ''
metric_id: 129
- type: area-chart
title: Memory multi metric
y_label: Memory (GiB)
metrics:
- query_range: avg(sum(container_memory_usage_bytes{id="/"}) by (job)) without
(job) / 2^30
unit: GiB
label: Usage (GiB)
metric_id: 236
- query_range: sum(kube_node_status_capacity_memory_bytes{kubernetes_namespace="gitlab-managed-apps"})/2^30
unit: GiB
label: Capacity (GiB)
metric_id: 238
- query_range: sum(kube_pod_container_resource_requests_memory_bytes{kubernetes_namespace="gitlab-managed-apps"})/2^30
unit: GiB
label: Requested (GiB)
metric_id: 237
- group: CPU metrics
panels:
- title: "CPU usage"
type: "line-chart"
y_label: "Cores per pod"
metrics:
- id: pod_cpu_usage_seconds_total
query_range: 'rate(container_cpu_usage_seconds_total{pod_name="{{pod_name}}",container_name="POD"}[5m])'
unit: "cores"
label: pod_name
- title: "Memory usage working set"
type: "line-chart"
y_label: "Working set memory (MiB)"
metrics:
- id: pod_memory_working_set1
query_range: 'container_memory_working_set_bytes{pod_name="{{pod_name2}}",container_name="POD"}/1024/1024'
unit: "MiB"
label: pod_name
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment