Add latest changes from gitlab-org/gitlab@13-3-stable-ee

4 files changed, 82 insertions, 57 deletions

diff --git a/config/prometheus/cluster_metrics.yml b/config/prometheus/cluster_metrics.yml
index 1e396f4bbbd..a76a162820a 100644
--- a/config/prometheus/cluster_metrics.yml
+++ b/config/prometheus/cluster_metrics.yml
@@ -2,12 +2,10 @@ dashboard: 'Cluster health'
 priority: 1
 panel_groups:
 - group: Cluster Health
-  priority: 10
   panels:
   - title: "CPU Usage"
     type: "area-chart"
     y_label: "CPU (cores)"
-    weight: 1
     metrics:
       - id: cluster_health_cpu_usage
         query_range: 'avg(sum(rate(container_cpu_usage_seconds_total{id="/"}[15m])) by (job)) without (job)'
@@ -24,7 +22,6 @@ panel_groups:
   - title: "Memory Usage"
     type: "area-chart"
     y_label: "Memory (GiB)"
-    weight: 1
     metrics:
       - id: cluster_health_memory_usage
         query_range: 'avg(sum(container_memory_usage_bytes{id="/"}) by (job)) without (job) / 2^30'
diff --git a/config/prometheus/common_metrics.yml b/config/prometheus/common_metrics.yml
index d9aaff12a4d..67994740ff1 100644
--- a/config/prometheus/common_metrics.yml
+++ b/config/prometheus/common_metrics.yml
@@ -2,12 +2,10 @@ dashboard: 'Environment metrics'
 priority: 1
 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
       # Remove the second metric (after OR) when we drop support for K8s 1.13
@@ -18,7 +16,6 @@ panel_groups:
   - title: "Core Usage (Total)"
     type: "area-chart"
     y_label: "Total Cores"
-    weight: 3
     metrics:
     - id: system_metrics_kubernetes_container_cores_total
       # Remove the second metric (after OR) when we drop support for K8s 1.13
@@ -29,7 +26,6 @@ panel_groups:
   - 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
       # Remove the second metric (after OR) when we drop support for K8s 1.13
@@ -40,7 +36,6 @@ panel_groups:
   - 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
       # Remove the second metric (after OR) when we drop support for K8s 1.13
@@ -52,7 +47,6 @@ panel_groups:
   - title: "Core Usage (Pod Average)"
     type: "line-chart"
     y_label: "Cores per Pod"
-    weight: 1
     metrics:
     - id: system_metrics_kubernetes_container_core_usage
       # Remove the second metric (after OR) when we drop support for K8s 1.13
@@ -63,7 +57,6 @@ panel_groups:
   - 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
       # Remove the second metric (after OR) when we drop support for K8s 1.13
@@ -75,7 +68,6 @@ panel_groups:
   - 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))'
@@ -83,12 +75,10 @@ panel_groups:
       unit: requests
 # NGINX Ingress metrics for pre-0.16.0 versions
 - 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)'
@@ -99,7 +89,6 @@ panel_groups:
     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}}-.*"})'
@@ -110,7 +99,6 @@ panel_groups:
     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'
@@ -118,12 +106,10 @@ panel_groups:
       unit: "%"
 # NGINX Ingress metrics for post-0.16.0 versions
 - 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)'
@@ -132,7 +118,6 @@ panel_groups:
   - 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'
@@ -141,19 +126,16 @@ panel_groups:
   - 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: "%"
 - 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)'
@@ -162,19 +144,16 @@ panel_groups:
   - 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: "%"
 - 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'
@@ -183,7 +162,6 @@ panel_groups:
   - 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'
@@ -192,19 +170,16 @@ panel_groups:
   - 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: "%"
 - 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)'
@@ -213,7 +188,6 @@ panel_groups:
   - 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}} })'
@@ -224,7 +198,6 @@ panel_groups:
     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]))'
@@ -233,7 +206,6 @@ panel_groups:
   - 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'
diff --git a/config/prometheus/pod_metrics.yml b/config/prometheus/pod_metrics.yml
index 29575ec543e..b9395124405 100644
--- a/config/prometheus/pod_metrics.yml
+++ b/config/prometheus/pod_metrics.yml
@@ -1,59 +1,115 @@
-dashboard: 'Pod metrics'
-priority: 10
+dashboard: 'K8s pod health'
+priority: 2
+
+templating:
+  variables:
+    pod:
+      label: 'Pod name'
+      type: metric_label_values
+      options:
+        series_selector: 'container_memory_working_set_bytes'
+        label: 'pod'
+
 panel_groups:
 - group: CPU metrics
   panels:
   - title: "CPU usage"
     type: "line-chart"
-    y_label: "Cores per pod"
+    y_label: "Cores per container"
     metrics:
     - id: pod_cpu_usage_seconds_total
-      query_range: 'rate(container_cpu_usage_seconds_total{pod_name="{{pod_name}}",container_name="POD"}[5m])'
+      query_range: >-
+        sum(
+          rate(container_cpu_usage_seconds_total{pod="{{pod}}",container!="POD"}[5m])
+        )
+        by (container)
       unit: "cores"
-      label: pod_name
+      label: container
+
+  - title: "CPU throttling"
+    type: "line-chart"
+    y_label: "Cores per container"
+    metrics:
+    - id: pod_cpu_cfs_throttle
+      query_range: >-
+        sum(
+          rate(container_cpu_cfs_throttled_seconds_total{pod="{{pod}}"}[5m])
+        )
+        by (container)
+      unit: "cores"
+      label: container
+
 - group: Memory metrics
   panels:
   - title: "Memory usage working set"
     type: "line-chart"
-    y_label: "Working set memory (MiB)"
+    y_label: "Working set memory"
     metrics:
     - id: pod_memory_working_set
-      query_range: 'container_memory_working_set_bytes{pod_name="{{pod_name}}",container_name="POD"}/1024/1024'
-      unit: "MiB"
-      label: pod_name
+      query_range: >-
+        sum(
+          container_memory_working_set_bytes{pod="{{pod}}",container!="POD"}
+        ) by (container)
+      unit: "bytes"
+      label: container
+
 - group: Network metrics
   panels:
   - title: "Network Receive (In)"
     type: "line-chart"
-    y_label: "Received (KiB/sec)"
+    y_label: "Received (bytes/sec)"
     metrics:
     - id: pod_network_receive
-      query_range: 'rate(container_network_receive_bytes_total{pod_name="{{pod_name}}",container_name="POD"}[5m])/1024'
-      unit: "KiB / sec"
-      label: pod_name
+      query_range: >-
+        sum(
+          rate(
+            container_network_receive_bytes_total{pod="{{pod}}"}[5m]
+          )
+        ) by (pod)
+      unit: "bytes"
+      label: pod
+
   - title: "Network Transmit (Out)"
     type: "line-chart"
-    y_label: "Transmitted (KiB/sec)"
+    y_label: "Transmitted (bytes/sec)"
     metrics:
     - id: pod_network_transmit
-      query_range: 'rate(container_network_transmit_bytes_total{pod_name="{{pod_name}}",container_name="POD"}[5m])/1024'
-      unit: "KiB / sec"
-      label: pod_name
+      query_range: >-
+        sum(
+          rate(
+            container_network_transmit_bytes_total{pod="{{pod}}"}[5m]
+          )
+        ) by (pod)
+      unit: bytes
+      label: pod
+
 - group: Disk metrics
   panels:
   - title: "Disk Reads"
     type: "line-chart"
-    y_label: "Disk reads (KiB/sec)"
+    y_label: "Disk reads (bytes/sec)"
     metrics:
     - id: pod_disk_reads
-      query_range: 'rate(container_fs_reads_bytes_total{container_name="POD",pod_name="{{pod_name}}"}[5m])/1024'
-      unit: "KiB / sec"
-      label: pod_name
+      query_range: >-
+        sum(
+          rate(
+            container_fs_reads_bytes_total{pod="{{pod}}", container!="POD"}[5m]
+          )
+        ) by (container,device)
+
+      unit: "bytes / sec"
+      label: "{{container}} {{device}}"
+
   - title: "Disk Writes"
     type: "line-chart"
-    y_label: "Disk writes (KiB/sec)"
+    y_label: "Disk writes (bytes/sec)"
     metrics:
     - id: pod_disk_writes
-      query_range: 'rate(container_fs_writes_bytes_total{container_name="POD",pod_name="{{pod_name}}"}[5m])/1024'
-      unit: "KiB / sec"
-      label: pod_name
+      query_range: >-
+        sum(
+          rate(
+            container_fs_writes_bytes_total{pod="{{pod}}", container!="POD"}[5m]
+          )
+        ) by (container,device)
+      unit: "bytes / sec"
+      label: "{{container}} {{device}}"
diff --git a/config/prometheus/self_monitoring_default.yml b/config/prometheus/self_monitoring_default.yml
index 50e6f4585e4..024733bf2f0 100644
--- a/config/prometheus/self_monitoring_default.yml
+++ b/config/prometheus/self_monitoring_default.yml
@@ -1,4 +1,4 @@
-dashboard: 'Default dashboard'
+dashboard: 'Overview'
 priority: 1
 
 templating: