Common Method Wrappers:

- updated histogram definition in Grafana dashboards
- updated prometheus queries

src/common/method_wrappers/tests/grafana_prometheus_component_rpc.json

@@ -15,8 +15,8 @@
   "editable": true,
   "gnetId": null,
   "graphTooltip": 0,
-  "id": 27,
-  "iteration": 1669995219512,
+  "id": 25,
+  "iteration": 1671297223428,
   "links": [],
   "panels": [
     {
@@ -174,10 +174,10 @@
       "targets": [
         {
           "exemplar": true,
-          "expr": "sum(increase(tfs_[[component]]_rpc_[[method]]_histogram_duration_bucket{pod=~\"[[pod]]\"}[$__rate_interval])) by (le)",
+          "expr": "sum(\r\n    max_over_time(tfs_[[component]]_rpc_[[method]]_histogram_duration_bucket{pod=~\"[[pod]]\"}[1m]) -\r\n    min_over_time(tfs_[[component]]_rpc_[[method]]_histogram_duration_bucket{pod=~\"[[pod]]\"}[1m])\r\n) by (le)",
           "format": "heatmap",
           "instant": false,
-          "interval": "10s",
+          "interval": "1m",
           "intervalFactor": 1,
           "legendFormat": "{{le}}",
           "queryType": "randomWalk",

src/common/method_wrappers/tests/grafana_prometheus_device_driver.json

@@ -15,8 +15,8 @@
   "editable": true,
   "gnetId": null,
   "graphTooltip": 0,
-  "id": 25,
-  "iteration": 1669993886467,
+  "id": 26,
+  "iteration": 1671318718779,
   "links": [],
   "panels": [
     {
@@ -174,10 +174,10 @@
       "targets": [
         {
           "exemplar": true,
-          "expr": "sum(increase(tfs_device_driver_[[method]]_histogram_duration_bucket{driver=~\"[[driver]]\", pod=~\"deviceservice-[[pod]]\"}[$__rate_interval])) by (le)",
+          "expr": "sum(\r\n    max_over_time(tfs_device_driver_[[method]]_histogram_duration_bucket{driver=~\"[[driver]]\", pod=~\"deviceservice-[[pod]]\"}[1m]) -\r\n    min_over_time(tfs_device_driver_[[method]]_histogram_duration_bucket{driver=~\"[[driver]]\", pod=~\"deviceservice-[[pod]]\"}[1m])\r\n) by (le)",
           "format": "heatmap",
           "instant": false,
-          "interval": "10s",
+          "interval": "60s",
           "intervalFactor": 1,
           "legendFormat": "{{le}}",
           "queryType": "randomWalk",

src/common/method_wrappers/tests/grafana_prometheus_service_handler.json

@@ -15,8 +15,8 @@
   "editable": true,
   "gnetId": null,
   "graphTooltip": 0,
-  "id": 26,
-  "iteration": 1669992491077,
+  "id": 27,
+  "iteration": 1671319012315,
   "links": [],
   "panels": [
     {
@@ -175,10 +175,10 @@
       "targets": [
         {
           "exemplar": true,
-          "expr": "sum(increase(tfs_service_handler_[[method]]_histogram_duration_bucket{handler=~\"[[handler]]\", pod=~\"serviceservice-[[pod]]\"}[$__rate_interval])) by (le)",
+          "expr": "sum(\r\n    max_over_time(tfs_service_handler_[[method]]_histogram_duration_bucket{handler=~\"[[handler]]\", pod=~\"serviceservice-[[pod]]\"}[1m]) -\r\n    min_over_time(tfs_service_handler_[[method]]_histogram_duration_bucket{handler=~\"[[handler]]\", pod=~\"serviceservice-[[pod]]\"}[1m])\r\n) by (le)",
           "format": "heatmap",
           "instant": false,
-          "interval": "10s",
+          "interval": "1m",
           "intervalFactor": 1,
           "legendFormat": "{{le}}",
           "queryType": "randomWalk",

src/common/method_wrappers/tests/prometheus_queries.txt

@@ -14,7 +14,11 @@ tfs_[[component]]_rpc_[[method]]_counter_requests_started_total
 tfs_[[component]]_rpc_[[method]]_counter_requests_completed_total
 tfs_[[component]]_rpc_[[method]]_counter_requests_failed_total
 tfs_[[component]]_rpc_[[method]]_histogram_duration_sum
-sum(increase(tfs_[[component]]_rpc_[[method]]_histogram_duration_bucket[$__rate_interval])) by (le)
+#sum(increase(tfs_[[component]]_rpc_[[method]]_histogram_duration_bucket[$__rate_interval])) by (le)
+sum(
+    max_over_time(tfs_[[component]]_rpc_[[method]]_histogram_duration_bucket{pod=~"[[pod]]"}[1m]) -
+    min_over_time(tfs_[[component]]_rpc_[[method]]_histogram_duration_bucket{pod=~"[[pod]]"}[1m])
+) by (le)
 
 
 TFS/Device/Driver:
@@ -33,8 +37,11 @@ tfs_device_driver_[[method]]_counter_requests_started_total{driver="[[driver]]"}
 tfs_device_driver_[[method]]_counter_requests_completed_total{driver="[[driver]]"}
 tfs_device_driver_[[method]]_counter_requests_failed_total{driver="[[driver]]"}
 tfs_device_driver_[[method]]_histogram_duration_sum{driver="[[driver]]"}
-sum(increase(tfs_device_driver_[[method]]_histogram_duration_bucket{driver="[[driver]]"}[$__rate_interval])) by (le)
-
+#sum(increase(tfs_device_driver_[[method]]_histogram_duration_bucket{driver="[[driver]]"}[$__rate_interval])) by (le)
+sum(
+    max_over_time(tfs_device_driver_[[method]]_histogram_duration_bucket{driver="[[driver]]", pod=~"deviceservice-[[pod]]"}[1m]) -
+    min_over_time(tfs_device_driver_[[method]]_histogram_duration_bucket{driver="[[driver]]", pod=~"deviceservice-[[pod]]"}[1m])
+) by (le)
 
 variables:
 name=method
@@ -49,4 +56,8 @@ tfs_service_handler_[[method]]_counter_requests_started_total{handler="[[handler
 tfs_service_handler_[[method]]_counter_requests_completed_total{handler="[[handler]]"}
 tfs_service_handler_[[method]]_counter_requests_failed_total{handler="[[handler]]"}
 tfs_service_handler_[[method]]_histogram_duration_sum{handler="[[handler]]"}
-sum(increase(tfs_service_handler_[[method]]_histogram_duration_bucket{handler="[[handler]]"}[$__rate_interval])) by (le)
+#sum(increase(tfs_service_handler_[[method]]_histogram_duration_bucket{handler="[[handler]]"}[$__rate_interval])) by (le)
+sum(
+    max_over_time(tfs_service_handler_[[method]]_histogram_duration_bucket{handler=~"[[handler]]", pod=~"serviceservice-[[pod]]"}[1m]) -
+    min_over_time(tfs_service_handler_[[method]]_histogram_duration_bucket{handler=~"[[handler]]", pod=~"serviceservice-[[pod]]"}[1m])
+) by (le)