Merge branch '34636-update-prometheus-metrics-library' into 'master'

Update Prometheus Metrics Library

See merge request !12621

1 files changed, 68 insertions, 18 deletions

diff --git a/config/prometheus/additional_metrics.yml b/config/prometheus/additional_metrics.yml
index daecde49570..d33fae4182d 100644
--- a/config/prometheus/additional_metrics.yml
+++ b/config/prometheus/additional_metrics.yml
@@ -1,32 +1,82 @@
-- group: Kubernetes
-  priority: 1
+- group: AWS Elastic Load Balancer
+  priority: 10
   metrics:
-  - title: "Memory usage"
-    y_label: "Values"
+  - title: "Throughput"
+    y_label: "Requests / Sec"
     required_metrics:
-      - container_memory_usage_bytes
+      - aws_elb_request_count_sum
     weight: 1
     queries:
-    - query_range: 'avg(container_memory_usage_bytes{%{environment_filter}}) / 2^20'
-      label: Container memory
-      unit: MiB
-  - title: "Current memory usage"
+    - query_range: 'sum(aws_elb_request_count_sum{%{environment_filter}}) * 60'
+      label: Total
+      unit: req / sec
+  - title: "Latency"
+    y_label: "Latency (ms)"
     required_metrics:
-     - container_memory_usage_bytes
+      - aws_elb_latency_average
     weight: 1
     queries:
-    - query: 'avg(container_memory_usage_bytes{%{environment_filter}}) / 2^20'
-      display_empty: false
-      unit: MiB
-  - title: "CPU usage"
+    - query_range: 'avg(aws_elb_latency_average{%{environment_filter}}) * 1000'
+      label: Average
+      unit: ms
+  - title: "HTTP Error Rate"
+    y_label: "Error Rate (%)"
     required_metrics:
-     - container_cpu_usage_seconds_total
+      - aws_elb_request_count_sum
+      - aws_elb_httpcode_backend_5_xx_sum
+    weight: 1
+    queries:
+    - query_range: 'sum(aws_elb_httpcode_backend_5_xx_sum{%{environment_filter}}) / sum(aws_elb_request_count_sum{%{environment_filter}})'
+      label: HTTP Errors
+      unit: "%"
+- group: NGINX
+  priority: 10
+  metrics:
+  - title: "Throughput"
+    y_label: "Requests / Sec"
+    required_metrics:
+      - nginx_requests_total
+    weight: 1
+    queries:
+    - query_range: 'sum(rate(nginx_requests_total{server_zone!="*", server_zone!="_", %{environment_filter}}[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{%{environment_filter}}) * 1000'
+      label: Upstream
+      unit: ms
+  - title: "HTTP Error Rate"
+    y_label: "Error Rate (%)"
+    required_metrics:
+      - nginx_responses_total
+    weight: 1
+    queries:
+    - query_range: 'sum(nginx_responses_total{status_code="5xx", %{environment_filter}}) / sum(nginx_responses_total{server_zone!="*", server_zone!="_", %{environment_filter}})'
+      label: HTTP Errors
+      unit: "%"
+- group: Kubernetes
+  priority: 5
+  metrics:
+  - title: "Memory Usage"
+    y_label: "Memory Usage (MB)"
+    required_metrics:
+      - container_memory_usage_bytes
     weight: 1
     queries:
-    - query_range: 'avg(rate(container_cpu_usage_seconds_total{%{environment_filter}}[2m])) * 100'
-  - title: "Current CPU usage"
+    - query_range: '(sum(container_memory_usage_bytes{container_name!="POD",%{environment_filter}}) / count(container_memory_usage_bytes{container_name!="POD",%{environment_filter}})) /1024/1024'
+      label: Average
+      unit: MB
+  - title: "CPU Utilization"
+    y_label: "CPU Utilization (%)"
     required_metrics:
      - container_cpu_usage_seconds_total
     weight: 1
     queries:
-    - query: 'avg(rate(container_cpu_usage_seconds_total{%{environment_filter}}[2m])) * 100'
+    - query_range: 'sum(rate(container_cpu_usage_seconds_total{container_name!="POD",%{environment_filter}}[2m])) / count(container_cpu_usage_seconds_total{container_name!="POD",%{environment_filter}}) * 100'
+      label: Average
+      unit: "%"