Updated alerts and dashboard changes

alert-policies/openstack-controller/MemoryUsage.yml

@@ -0,0 +1,40 @@
+# Name of the alert
+name: Memory Usage Percent
+
+# Description and details
+description: |+
+  This alert is triggered if the memory usage exceeds 90% for 5 minutes.
+# Type of alert
+type: STATIC
+
+# NRQL query
+nrql:
+
+  query: "SELECT average(`memoryUsedBytes`/`memoryTotalBytes`*100) FROM SystemSample facet entityName"
+
+# Function used to aggregate the NRQL query value(s) for comparison to the terms.threshold (Default: SINGLE_VALUE)
+valueFunction: SINGLE_VALUE
+
+# List of Critical and Warning thresholds for the condition
+terms:
+  - priority: CRITICAL
+    # Operator used to compare against the threshold.
+    operator: ABOVE
+    # Value that triggers a violation
+    threshold: 90
+    # Time in seconds; 120 - 3600
+    thresholdDuration: 300
+    # How many data points must be in violation for the duration
+    thresholdOccurrences: ALL
+  - priority: WARNING
+    # Operator used to compare against the threshold.
+    operator: ABOVE
+    # Value that triggers a violation
+    threshold: 85
+    # Time in seconds; 120 - 3600, must be a multiple of 60 for Baseline conditions
+    thresholdDuration: 300
+    # How many data points must be in violation for the duration
+    thresholdOccurrences: ALL  
+# Duration after which a violation automatically closes
+# Time in seconds; 300 - 2592000 (Default: 86400 [1 day])
+violationTimeLimitSeconds: 86400

alert-policies/openstack-controller/ServerFreeMemoryLow.yml

@@ -0,0 +1,41 @@
+# Name of the alert
+name: Server Free Memory Low(%)
+
+# Description and details
+description: |+
+  This alert is triggered when server free memory is less than 72% for 5 minutes.
+# Type of alert
+type: STATIC
+
+# NRQL query
+nrql:
+
+  query: "SELECT average(`memoryFreeBytes`/`memoryTotalBytes`*100) FROM SystemSample facet entityName"
+
+# Function used to aggregate the NRQL query value(s) for comparison to the terms.threshold (Default: SINGLE_VALUE)
+valueFunction: SINGLE_VALUE
+
+# List of Critical and Warning thresholds for the condition
+terms:
+  - priority: CRITICAL
+    # Operator used to compare against the threshold.
+    operator: BELOW
+    # Value that triggers a violation
+    threshold: 72
+    # Time in seconds; 120 - 3600
+    thresholdDuration: 300
+    # How many data points must be in violation for the duration
+    thresholdOccurrences: ALL
+  - priority: WARNING
+    # Operator used to compare against the threshold.
+    operator: BELOW
+    # Value that triggers a violation
+    threshold: 75
+    # Time in seconds; 120 - 3600, must be a multiple of 60 for Baseline conditions
+    thresholdDuration: 300
+    # How many data points must be in violation for the duration
+    thresholdOccurrences: ALL
+
+# Duration after which a violation automatically closes
+# Time in seconds; 300 - 2592000 (Default: 86400 [1 day])
+violationTimeLimitSeconds: 86400

alert-policies/openstack-controller/StateDown.yml

@@ -0,0 +1,41 @@
+# Name of the alert
+name: State Down(%)
+
+# Description and details
+description: |+
+  This alert is triggered when state is down for 5 minutes.
+# Type of alert
+type: STATIC
+
+# NRQL query
+nrql:
+
+  query: "SELECT average(`memoryFreeBytes`/`memoryTotalBytes`*100) FROM SystemSample facet entityName"
+
+# Function used to aggregate the NRQL query value(s) for comparison to the terms.threshold (Default: SINGLE_VALUE)
+valueFunction: SINGLE_VALUE
+
+# List of Critical and Warning thresholds for the condition
+terms:
+  - priority: CRITICAL
+    # Operator used to compare against the threshold.
+    operator: BELOW
+    # Value that triggers a violation
+    threshold: 72
+    # Time in seconds; 120 - 3600
+    thresholdDuration: 300
+    # How many data points must be in violation for the duration
+    thresholdOccurrences: ALL
+  - priority: WARNING
+    # Operator used to compare against the threshold.
+    operator: BELOW
+    # Value that triggers a violation
+    threshold: 75
+    # Time in seconds; 120 - 3600, must be a multiple of 60 for Baseline conditions
+    thresholdDuration: 300
+    # How many data points must be in violation for the duration
+    thresholdOccurrences: ALL
+
+# Duration after which a violation automatically closes
+# Time in seconds; 300 - 2592000 (Default: 86400 [1 day])
+violationTimeLimitSeconds: 86400

dashboards/openstack-controller/openstack-controller.json

@@ -217,7 +217,7 @@
           "layout": {
             "column": 1,
             "row": 1,
-            "width": 2,
+            "width": 3,
             "height": 3
           },
           "linkedEntityGuids": null,
@@ -242,9 +242,9 @@
         {
           "title": "Domain",
           "layout": {
-            "column": 3,
+            "column": 4,
             "row": 1,
-            "width": 2,
+            "width": 3,
             "height": 3
           },
           "linkedEntityGuids": null,
@@ -269,14 +269,14 @@
         {
           "title": "Block storage backup",
           "layout": {
-            "column": 5,
+            "column": 7,
             "row": 1,
             "width": 4,
             "height": 3
           },
           "linkedEntityGuids": null,
           "visualization": {
-            "id": "viz.stacked-bar"
+            "id": "viz.area"
           },
           "rawConfiguration": {
             "facet": {
@@ -288,7 +288,7 @@
             "nrqlQueries": [
               {
                 "accountIds": [],
-                "query": "select latest(`openstack.cinder.limits.maxTotalBackupGigabytes`) as maxTotalBackupGigabytes,  latest(`openstack.cinder.limits.totalBackupGigabytesUsed`) as totalBackupGigabytesUsed from OSBlockStorageSample TIMESERIES "
+                "query": "SELECT latest(openstack.cinder.limits.maxTotalBackups) AS 'Max total backups', latest(openstack.cinder.limits.totalBackupsUsed) AS 'Total backups used' FROM OSBlockStorageSample TIMESERIES "
               }
             ],
             "platformOptions": {
@@ -299,7 +299,7 @@
         {
           "title": "Cinder volume",
           "layout": {
-            "column": 9,
+            "column": 11,
             "row": 1,
             "width": 2,
             "height": 3
@@ -325,33 +325,6 @@
         },
         {
           "title": "Cinder snapshots",
-          "layout": {
-            "column": 11,
-            "row": 1,
-            "width": 2,
-            "height": 3
-          },
-          "linkedEntityGuids": null,
-          "visualization": {
-            "id": "viz.billboard"
-          },
-          "rawConfiguration": {
-            "facet": {
-              "showOtherSeries": false
-            },
-            "nrqlQueries": [
-              {
-                "accountIds": [],
-                "query": "SELECT latest(openstack.cinder.snapshots.size) AS 'Snapshots Size', latest(openstack.cinder.snapshots.count) AS 'Snapshots Count' FROM OSBlockStorageSample "
-              }
-            ],
-            "platformOptions": {
-              "ignoreTimeRange": false
-            }
-          }
-        },
-        {
-          "title": "Snapshots",
           "layout": {
             "column": 1,
             "row": 4,
@@ -369,7 +342,7 @@
             "nrqlQueries": [
               {
                 "accountIds": [],
-                "query": "SELECT latest(openstack.cinder.limits.maxTotalSnapshots) AS 'Total', latest(openstack.cinder.limits.totalSnapshotsUsed) AS 'Used' FROM OSBlockStorageSample "
+                "query": "SELECT latest(openstack.cinder.snapshots.size) AS 'Snapshots Size', latest(openstack.cinder.snapshots.count) AS 'Snapshots Count' FROM OSBlockStorageSample "
               }
             ],
             "platformOptions": {
@@ -382,21 +355,24 @@
           "layout": {
             "column": 3,
             "row": 4,
-            "width": 2,
+            "width": 4,
             "height": 3
           },
           "linkedEntityGuids": null,
           "visualization": {
-            "id": "viz.billboard"
+            "id": "viz.stacked-bar"
           },
           "rawConfiguration": {
             "facet": {
               "showOtherSeries": false
             },
+            "legend": {
+              "enabled": true
+            },
             "nrqlQueries": [
               {
                 "accountIds": [],
-                "query": "SELECT latest(openstack.cinder.limits.maxTotalVolumes) AS 'Max', latest(openstack.cinder.limits.totalVolumesUsed) AS 'Used' FROM OSBlockStorageSample "
+                "query": "SELECT latest(openstack.cinder.limits.maxTotalVolumes) AS 'Max', latest(openstack.cinder.limits.totalVolumesUsed) AS 'Used' FROM OSBlockStorageSample TIMESERIES"
               }
             ],
             "platformOptions": {
@@ -405,28 +381,25 @@
           }
         },
         {
-          "title": "Block storage backup",
+          "title": "Snapshots",
           "layout": {
-            "column": 5,
+            "column": 7,
             "row": 4,
-            "width": 4,
+            "width": 3,
             "height": 3
           },
           "linkedEntityGuids": null,
           "visualization": {
-            "id": "viz.area"
+            "id": "viz.billboard"
           },
           "rawConfiguration": {
             "facet": {
               "showOtherSeries": false
             },
-            "legend": {
-              "enabled": true
-            },
             "nrqlQueries": [
               {
                 "accountIds": [],
-                "query": "SELECT latest(openstack.cinder.limits.maxTotalBackups) AS 'Max total backups', latest(openstack.cinder.limits.totalBackupsUsed) AS 'Total backups used' FROM OSBlockStorageSample TIMESERIES "
+                "query": "SELECT latest(openstack.cinder.limits.maxTotalSnapshots) AS 'Total', latest(openstack.cinder.limits.totalSnapshotsUsed) AS 'Used' FROM OSBlockStorageSample "
               }
             ],
             "platformOptions": {
@@ -437,9 +410,9 @@
         {
           "title": "Snapshot count",
           "layout": {
-            "column": 9,
+            "column": 10,
             "row": 4,
-            "width": 4,
+            "width": 3,
             "height": 3
           },
           "linkedEntityGuids": null,
@@ -603,7 +576,7 @@
           }
         },
         {
-          "title": "Minimum disk",
+          "title": "Average disk",
           "layout": {
             "column": 1,
             "row": 4,
@@ -612,7 +585,7 @@
           },
           "linkedEntityGuids": null,
           "visualization": {
-            "id": "viz.line"
+            "id": "viz.stacked-bar"
           },
           "rawConfiguration": {
             "facet": {
@@ -624,14 +597,11 @@
             "nrqlQueries": [
               {
                 "accountIds": [],
-                "query": "SELECT latest(openstack.glance.image.min_disk) FROM OSImageSample TIMESERIES "
+                "query": "SELECT average(openstack.glance.image.min_disk) FROM OSImageSample TIMESERIES "
               }
             ],
             "platformOptions": {
               "ignoreTimeRange": false
-            },
-            "yAxisLeft": {
-              "zero": true
             }
           }
         },
@@ -768,7 +738,7 @@
           },
           "linkedEntityGuids": null,
           "visualization": {
-            "id": "viz.line"
+            "id": "viz.area"
           },
           "rawConfiguration": {
             "facet": {
@@ -785,9 +755,6 @@
             ],
             "platformOptions": {
               "ignoreTimeRange": false
-            },
-            "yAxisLeft": {
-              "zero": true
             }
           }
         },
@@ -1188,7 +1155,7 @@
       "description": null,
       "widgets": [
         {
-          "title": "Networks",
+          "title": "Networks(click on the network name to filter)",
           "layout": {
             "column": 1,
             "row": 1,
@@ -1350,7 +1317,7 @@
           }
         },
         {
-          "title": "Network Tenant Id",
+          "title": "Network tenant Id",
           "layout": {
             "column": 5,
             "row": 4,
@@ -1431,7 +1398,7 @@
           }
         },
         {
-          "title": "Maximum Transmission Units (MTU's)",
+          "title": "Maximum transmission units (MTU's)",
           "layout": {
             "column": 3,
             "row": 7,
@@ -1464,7 +1431,7 @@
           }
         },
         {
-          "title": "Network Revision Number",
+          "title": "Network revision number",
           "layout": {
             "column": 6,
             "row": 7,
@@ -1491,7 +1458,7 @@
           }
         },
         {
-          "title": "Network Description",
+          "title": "Network description",
           "layout": {
             "column": 9,
             "row": 7,