diff options
Diffstat (limited to 'config/prometheus/additional_metrics.yml')
| -rw-r--r-- | config/prometheus/additional_metrics.yml | 38 |
1 files changed, 34 insertions, 4 deletions
diff --git a/config/prometheus/additional_metrics.yml b/config/prometheus/additional_metrics.yml index 5eb01d62924..0642a0b2fe9 100644 --- a/config/prometheus/additional_metrics.yml +++ b/config/prometheus/additional_metrics.yml @@ -1,3 +1,33 @@ +- group: Response metrics (NGINX Ingress) + priority: 10 + metrics: + - title: "Throughput" + y_label: "Requests / Sec" + required_metrics: + - nginx_upstream_requests_total + weight: 1 + queries: + - query_range: 'sum(rate(nginx_upstream_requests_total{upstream=~"%{kube_namespace}-%{ci_environment_slug}-.*"}[2m]))' + label: Total + unit: req / sec + - title: "Latency" + y_label: "Latency (ms)" + required_metrics: + - nginx_upstream_response_msecs_avg + weight: 1 + queries: + - query_range: 'avg(nginx_upstream_response_msecs_avg{upstream=~"%{kube_namespace}-%{ci_environment_slug}-.*"})' + label: Average + unit: ms + - title: "HTTP Error Rate" + y_label: "HTTP 500 Errors / Sec" + required_metrics: + - nginx_upstream_responses_total + weight: 1 + queries: + - query_range: 'sum(rate(nginx_upstream_responses_total{status_code="5xx", upstream=~"%{kube_namespace}-%{ci_environment_slug}-.*"}[2m]))' + label: HTTP Errors + unit: "errors / sec" - group: Response metrics (HA Proxy) priority: 10 metrics: @@ -68,18 +98,18 @@ - nginx_upstream_response_msecs_avg weight: 1 queries: - - query_range: 'avg(nginx_upstream_response_msecs_avg{%{environment_filter}}) * 1000' + - query_range: 'avg(nginx_upstream_response_msecs_avg{%{environment_filter}})' label: Upstream unit: ms - title: "HTTP Error Rate" - y_label: "Error Rate (%)" + y_label: "HTTP 500 Errors / Sec" required_metrics: - nginx_responses_total weight: 1 queries: - - query_range: 'sum(rate(nginx_responses_total{status_code="5xx", %{environment_filter}}[2m])) / sum(rate(nginx_requests_total{server_zone!="*", server_zone!="_", %{environment_filter}}[2m]))' + - query_range: 'sum(rate(nginx_responses_total{status_code="5xx", %{environment_filter}}[2m]))' label: HTTP Errors - unit: "%" + unit: "errors / sec" - group: System metrics (Kubernetes) priority: 5 metrics: |