FO 3.1.6, CO 2.1.5

microsoft · Mar 10, 2021 · a132571 · a132571
2 parents 9144df8 + c071a81
commit a132571
Show file tree

Hide file tree

Showing 43 changed files with 936 additions and 798 deletions.
diff --git a/Build-COSFPkgs.ps1 b/Build-COSFPkgs.ps1
@@ -23,11 +23,11 @@ function Build-SFPkg {
 try {
     Push-Location $scriptPath
 
-    Build-SFPkg "Microsoft.ServiceFabricApps.ClusterObserver.Linux.SelfContained.2.1.4" "$scriptPath\bin\release\ClusterObserver\linux-x64\self-contained\ClusterObserverType"
-    Build-SFPkg "Microsoft.ServiceFabricApps.ClusterObserver.Linux.FrameworkDependent.2.1.4" "$scriptPath\bin\release\ClusterObserver\linux-x64\framework-dependent\ClusterObserverType"
+    Build-SFPkg "Microsoft.ServiceFabricApps.ClusterObserver.Linux.SelfContained.2.1.5" "$scriptPath\bin\release\ClusterObserver\linux-x64\self-contained\ClusterObserverType"
+    Build-SFPkg "Microsoft.ServiceFabricApps.ClusterObserver.Linux.FrameworkDependent.2.1.5" "$scriptPath\bin\release\ClusterObserver\linux-x64\framework-dependent\ClusterObserverType"
 
-    Build-SFPkg "Microsoft.ServiceFabricApps.ClusterObserver.Windows.SelfContained.2.1.4" "$scriptPath\bin\release\ClusterObserver\win-x64\self-contained\ClusterObserverType"
-    Build-SFPkg "Microsoft.ServiceFabricApps.ClusterObserver.Windows.FrameworkDependent.2.1.4" "$scriptPath\bin\release\ClusterObserver\win-x64\framework-dependent\ClusterObserverType"
+    Build-SFPkg "Microsoft.ServiceFabricApps.ClusterObserver.Windows.SelfContained.2.1.5" "$scriptPath\bin\release\ClusterObserver\win-x64\self-contained\ClusterObserverType"
+    Build-SFPkg "Microsoft.ServiceFabricApps.ClusterObserver.Windows.FrameworkDependent.2.1.5" "$scriptPath\bin\release\ClusterObserver\win-x64\framework-dependent\ClusterObserverType"
 }
 finally {
     Pop-Location

diff --git a/Build-SFPkgs.ps1 b/Build-SFPkgs.ps1
@@ -23,11 +23,11 @@ function Build-SFPkg {
 try {
     Push-Location $scriptPath
 
-    Build-SFPkg "Microsoft.ServiceFabricApps.FabricObserver.Linux.SelfContained.3.1.5" "$scriptPath\bin\release\FabricObserver\linux-x64\self-contained\FabricObserverType"
-    Build-SFPkg "Microsoft.ServiceFabricApps.FabricObserver.Linux.FrameworkDependent.3.1.5" "$scriptPath\bin\release\FabricObserver\linux-x64\framework-dependent\FabricObserverType"
+    Build-SFPkg "Microsoft.ServiceFabricApps.FabricObserver.Linux.SelfContained.3.1.6" "$scriptPath\bin\release\FabricObserver\linux-x64\self-contained\FabricObserverType"
+    Build-SFPkg "Microsoft.ServiceFabricApps.FabricObserver.Linux.FrameworkDependent.3.1.6" "$scriptPath\bin\release\FabricObserver\linux-x64\framework-dependent\FabricObserverType"
 
-    Build-SFPkg "Microsoft.ServiceFabricApps.FabricObserver.Windows.SelfContained.3.1.5" "$scriptPath\bin\release\FabricObserver\win-x64\self-contained\FabricObserverType"
-    Build-SFPkg "Microsoft.ServiceFabricApps.FabricObserver.Windows.FrameworkDependent.3.1.5" "$scriptPath\bin\release\FabricObserver\win-x64\framework-dependent\FabricObserverType"
+    Build-SFPkg "Microsoft.ServiceFabricApps.FabricObserver.Windows.SelfContained.3.1.6" "$scriptPath\bin\release\FabricObserver\win-x64\self-contained\FabricObserverType"
+    Build-SFPkg "Microsoft.ServiceFabricApps.FabricObserver.Windows.FrameworkDependent.3.1.6" "$scriptPath\bin\release\FabricObserver\win-x64\framework-dependent\FabricObserverType"
 }
 finally {
     Pop-Location

diff --git a/ClusterObserver.nuspec.template b/ClusterObserver.nuspec.template
@@ -2,8 +2,8 @@
 <package xmlns="http://schemas.microsoft.com/packaging/2013/05/nuspec.xsd">
   <metadata minClientVersion="3.3.0">
     <id>%PACKAGE_ID%</id>
-    <version>2.1.4</version>
-    <releaseNotes>FO 3.1.5 support. Bug fixes. Significant refactoring.</releaseNotes>
+    <version>2.1.5</version>
+    <releaseNotes>FO 3.1.6 support.</releaseNotes>
     <authors>Microsoft</authors>
     <license type="expression">MIT</license>
     <requireLicenseAcceptance>false</requireLicenseAcceptance>

diff --git a/ClusterObserver/ClusterObserver.cs b/ClusterObserver/ClusterObserver.cs
@@ -219,7 +219,7 @@ private async Task ReportClusterHealthAsync(CancellationToken token)
                         var telemetry = new TelemetryData(FabricClientInstance, token)
                         {
                             HealthState = "Ok",
-                            HealthEventDescription = "Cluster has recovered from previous Error/Warning state.",
+                            Description = "Cluster has recovered from previous Error/Warning state.",
                             Metric = "AggregatedClusterHealth",
                             Source = ObserverName,
                         };
@@ -335,7 +335,7 @@ e is TimeoutException ||
                     var telemetryData = new TelemetryData(FabricClientInstance, token)
                     {
                         HealthState = "Warning",
-                        HealthEventDescription = msg,
+                        Description = msg,
                     };
 
                     await ObserverTelemetryClient.ReportHealthAsync(telemetryData, token);
@@ -435,7 +435,7 @@ private async Task ProcessApplicationHealthAsync(IList<ApplicationHealthState> a
                         {
                             ApplicationName = appName.OriginalString,
                             HealthState = Enum.GetName(typeof(HealthState), appHealth.AggregatedHealthState),
-                            HealthEventDescription = telemetryDescription,
+                            Description = telemetryDescription,
                             Source = ObserverName,
                         };
 
@@ -486,7 +486,7 @@ private async Task ProcessApplicationHealthAsync(IList<ApplicationHealthState> a
                                     {
                                         foTelemetryData.ApplicationName,
                                         foTelemetryData.HealthState,
-                                        foTelemetryData.HealthEventDescription,
+                                        foTelemetryData.Description,
                                         foTelemetryData.Metric,
                                         foTelemetryData.ObserverName,
                                         foTelemetryData.NodeName,
@@ -519,7 +519,7 @@ private async Task ProcessApplicationHealthAsync(IList<ApplicationHealthState> a
                                 {
                                     ApplicationName = appName.OriginalString,
                                     HealthState = Enum.GetName(typeof(HealthState), appHealth.AggregatedHealthState),
-                                    HealthEventDescription = telemetryDescription,
+                                    Description = telemetryDescription,
                                     Source = ObserverName,
                                 };
 
@@ -596,7 +596,7 @@ private async Task ProcessNodeHealthAsync(IList<NodeHealthState> nodeHealthState
                     // From FO?
                     if (foStats != null)
                     {
-                        telemetryDescription += foStats.HealthEventDescription;
+                        telemetryDescription += foStats.Description;
                         sourceObserver = foStats.ObserverName;
                         metric = foStats.Metric;
                     }
@@ -626,7 +626,7 @@ await FabricClientInstance.QueryManager.GetNodeListAsync(
                         {
                             NodeName = node.NodeName,
                             HealthState = Enum.GetName(typeof(HealthState), node.AggregatedHealthState),
-                            HealthEventDescription = $"{telemetryDescription}{Environment.NewLine}Node Status: {(targetNode != null ? Enum.GetName(typeof(NodeStatus), targetNode.NodeStatus) : string.Empty)}",
+                            Description = $"{telemetryDescription}{Environment.NewLine}Node Status: {(targetNode != null ? Enum.GetName(typeof(NodeStatus), targetNode.NodeStatus) : string.Empty)}",
                             Metric = metric ?? "AggregatedClusterHealth",
                             ObserverName = sourceObserver ?? string.Empty,
                             Source = ObserverName,
@@ -675,7 +675,7 @@ private async Task ProcessGenericEntityHealthAsync(HealthEvaluation evaluation,
 
             var telemetryData = new TelemetryData(FabricClientInstance, token)
             {
-                HealthEventDescription = telemetryDescription,
+                Description = telemetryDescription,
                 HealthState = healthState,
                 Source = ObserverName,
             };
@@ -728,7 +728,7 @@ await FabricClientInstance.QueryManager.GetNodeListAsync(
                         var telemetry = new TelemetryData(FabricClientInstance, token)
                         {
                             HealthState = "Ok",
-                            HealthEventDescription = $"{nodeDictItem.Key} is now Up.",
+                            Description = $"{nodeDictItem.Key} is now Up.",
                             Metric = "NodeStatus",
                             NodeName = nodeDictItem.Key,
                             Value = "Up",
@@ -807,7 +807,7 @@ await FabricClientInstance.QueryManager.GetNodeListAsync(
                             var telemetry = new TelemetryData(FabricClientInstance, token)
                             {
                                 HealthState = "Warning",
-                                HealthEventDescription = message,
+                                Description = message,
                                 Metric = "NodeStatus",
                                 NodeName = kvp.Key,
                                 Value = $"{kvp.Value.NodeStatus}",

diff --git a/ClusterObserver/PackageRoot/ServiceManifest.xml b/ClusterObserver/PackageRoot/ServiceManifest.xml
@@ -1,6 +1,6 @@
 <?xml version="1.0" encoding="utf-8"?>
 <ServiceManifest Name="ClusterObserverPkg"
-                 Version="2.1.4"
+                 Version="2.1.5"
                  xmlns="http://schemas.microsoft.com/2011/01/fabric"
                  xmlns:xsd="http://www.w3.org/2001/XMLSchema"
                  xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
@@ -11,7 +11,7 @@
   </ServiceTypes>
 
   <!-- Code package is your service executable. -->
-  <CodePackage Name="Code" Version="2.1.4">
+  <CodePackage Name="Code" Version="2.1.5">
     <EntryPoint>
       <ExeHost>
         <Program>ClusterObserver</Program>
@@ -21,7 +21,7 @@
 
   <!-- Config package is the contents of the Config directory under PackageRoot that contains an 
        independently-updateable and versioned set of custom configuration settings for your service. -->
-  <ConfigPackage Name="Config" Version="2.1.4" />
+  <ConfigPackage Name="Config" Version="2.1.5" />
 
   <Resources>
     <Endpoints>

diff --git a/ClusterObserver/Utilities/Telemetry/AppInsightsTelemetry.cs b/ClusterObserver/Utilities/Telemetry/AppInsightsTelemetry.cs
@@ -144,7 +144,7 @@ public Task ReportHealthAsync(
                     { "Application", telemetryData.ApplicationName ?? string.Empty },
                     { "ClusterId", telemetryData.ClusterId ?? string.Empty },
                     { "ErrorCode", telemetryData.Code ?? string.Empty },
-                    { "HealthEventDescription", telemetryData.HealthEventDescription ?? string.Empty },
+                    { "Description", telemetryData.Description ?? string.Empty },
                     { "HealthState", telemetryData.HealthState ?? string.Empty },
                     { "Metric", telemetryData.Metric ?? string.Empty },
                     { "NodeName", telemetryData.NodeName ?? string.Empty },

diff --git a/ClusterObserver/Utilities/Telemetry/TelemetryData.cs b/ClusterObserver/Utilities/Telemetry/TelemetryData.cs
@@ -32,7 +32,7 @@ public string ContainerId
             get; set;
         }
 
-        public string HealthEventDescription
+        public string Description
         {
             get; set;
         }

diff --git a/ClusterObserverApp/ApplicationPackageRoot/ApplicationManifest.xml b/ClusterObserverApp/ApplicationPackageRoot/ApplicationManifest.xml
@@ -1,5 +1,5 @@
 <?xml version="1.0" encoding="utf-8"?>
-<ApplicationManifest xmlns:xsd="http://www.w3.org/2001/XMLSchema" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" ApplicationTypeName="ClusterObserverType" ApplicationTypeVersion="2.1.4" xmlns="http://schemas.microsoft.com/2011/01/fabric">
+<ApplicationManifest xmlns:xsd="http://www.w3.org/2001/XMLSchema" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" ApplicationTypeName="ClusterObserverType" ApplicationTypeVersion="2.1.5" xmlns="http://schemas.microsoft.com/2011/01/fabric">
   <Parameters>
     <!-- ClusterObserver settings. -->
     <Parameter Name="ClusterObserver_InstanceCount" DefaultValue="1" />
@@ -14,7 +14,7 @@
        should match the Name and Version attributes of the ServiceManifest element defined in the 
        ServiceManifest.xml file. -->
   <ServiceManifestImport>
-    <ServiceManifestRef ServiceManifestName="ClusterObserverPkg" ServiceManifestVersion="2.1.4" />
+    <ServiceManifestRef ServiceManifestName="ClusterObserverPkg" ServiceManifestVersion="2.1.5" />
     <ConfigOverrides>
       <ConfigOverride Name="Config">
         <Settings>

diff --git a/Documentation/Using.md b/Documentation/Using.md
@@ -111,7 +111,7 @@ Example Output in SFX:
 ![alt text](/Documentation/Images/DiskWarnDescriptionNode.jpg "Logo Title Text 1")  
 
 
-**Memory Usage** 
+**Memory Usage - Private Working Set as Percentage of Total Physical Memory** 
 
 ***Problem:*** I want to know how much memory some or all of my services are using and warn when they hit some meaningful percent-used thresold.  
 
@@ -137,6 +137,32 @@ The third one scopes to all services _but_ 3 and asks AppObserver to warn when a
   }
 ```   
 
+**Memory Usage - Private Working Set - MB in Use** 
+
+***Problem:*** I want to know how much memory some or all of my services are using and warn when they hit some meaningful Megabytes in use thresold.  
+
+***Solution:*** AppObserver is your friend.  
+
+The first two JSON objects below tell AppObserver to warn when any of the services under MyApp app reach 30% memory use (as a percentage of total memory). 
+
+The third one scopes to all services _but_ 3 and asks AppObserver to warn when any of them hit 40% memory use on the machine (virtual or not).
+
+```JSON
+  {
+    "targetApp": "fabric:/MyApp",
+    "memoryWarningLimitMb": 300
+  },
+  {
+    "targetApp": "fabric:/AnotherApp",
+    "memoryWarningLimitMb": 500
+  },
+  {
+    "targetApp": "fabric:/SomeOtherApp",
+    "serviceExcludeList": "WhoNeedsMemoryService, NoMemoryNoProblemService, Service42",
+    "memoryWarningLimitMb": 600
+  }
+```   
+
 
 **Different thresholds for different services belonging to the same app**  
 
@@ -187,6 +213,70 @@ The following configuration tells AppObserver to monitor and report Warnings for
   }
 ``` 
 
+**All App Monitoring** 
+
+***Problem:*** I don't care what the app is, I just want to monitor all app services deployed to any node.  
+
+***Solution:*** AppObserver is your friend.  Note, you can specify all app targets using either "*" or "All" (case doesn't matter). 
+The configuration below specifies that AppObserver is to monitor and report thresholds breaches for a collection of metrics on all services belong to any app that is deployed to the node.  
+Note that AppObserver does not (and will not) monitor fabric:/System app services. Also, individual targetApp configuration items will override the global configuration when there the same metrics are supplied. 
+So, in the example below, the setting for cpuWarningLimitPercent for fabric:/MyApp will override the same setting specified in the all inclusive config item. fabric:/MyApp will still be monitored for the other global metrics.
+
+```JSON
+[
+  {
+    "targetApp": "*",
+    "cpuWarningLimitPercent": 75,
+    "memoryWarningLimitMb" : 500,
+    "networkWarningActivePorts": 2000,
+    "networkWarningEphemeralPorts": 1500
+  },
+  {
+    "targetApp": "fabric:/MyApp",
+    "cpuWarningLimitPercent": 50
+  }
+]
+```   
+***Problem:*** I don't care what the app is, I just want to monitor all app services deployed to any node, except for fabric:/MyApp, where I only care about raw memory use (MB) by any of its services. 
+
+***Solution:*** AppObserver is your friend.  Note, you can specify all app targets using either "*", "All", or "Any" (case doesn't matter). 
+The configuration below specifies that AppObserver is to monitor and report thresholds breaches for a collection of metrics on all services belong to any app that is deployed to the node, except for fabric:/MyApp.  
+
+```JSON
+[
+  {
+    "targetApp": "*",
+    "appExcludeList": "fabric:/MyApp",
+    "cpuWarningLimitPercent": 75,
+    "memoryWarningLimitPerceent" : 40,
+    "networkWarningActivePorts": 2000,
+    "networkWarningEphemeralPorts": 1500
+  },
+  {
+    "targetApp": "fabric:/MyApp",
+    "memoryWarningLimitMb": 600
+  }
+]
+```   
+***Problem:*** I want to monitor the same resource metrics used by 3 apps and I don't like writing JSON.
+
+***Solution:*** AppObserver is your friend.  Note, you can specify all app targets using either "*", "All", or "Any" (case doesn't matter). 
+The configuration below specifies that AppObserver is to monitor and report thresholds breaches for a collection of metrics on all services that belong to the apps supplied in appIncludeList.  
+
+```JSON
+[
+  {
+    "targetApp": "*",
+    "appIncludeList": "fabric:/MyApp, fabric:/MyApp2, fabric:/MyApp3",
+    "cpuWarningLimitPercent": 75,
+    "memoryWarningLimitPerceent" : 40,
+    "networkWarningActivePorts": 2000,
+    "networkWarningEphemeralPorts": 1500
+  }
+]
+
+``` 
+
 > You can learn all about the currently implemeted Observers and their supported resource properties [***here***](/Documentation/Observers.md). 
 
 

diff --git a/FabricObserver.Extensibility/MachineInfoModel/ApplicationInfo.cs b/FabricObserver.Extensibility/MachineInfoModel/ApplicationInfo.cs
@@ -19,6 +19,16 @@ public string TargetAppType
             get; set;
         }
 
+        public string AppExcludeList
+        {
+            get; set;
+        }
+
+        public string AppIncludeList
+        {
+            get; set;
+        }
+
         public string ServiceExcludeList
         {
             get; set;
@@ -84,11 +94,6 @@ public int NetworkErrorFirewallRules
             get; set;
         }
 
-        public int NetworkWarningFirewallRules
-        {
-            get; set;
-        }
-
         public bool DumpProcessOnError
         {
             get; set;
@@ -106,6 +111,8 @@ public int WarningOpenFileHandles
 
         public override string ToString() => $"ApplicationName: {TargetApp ?? string.Empty}{Environment.NewLine}" +
                                              $"ApplicationTypeName: {TargetAppType ?? string.Empty}{Environment.NewLine}" +
+                                             $"AppExcludeList: {AppExcludeList ?? string.Empty}{Environment.NewLine}" +
+                                             $"AppIncludeList: {AppIncludeList ?? string.Empty}{Environment.NewLine}" +
                                              $"ServiceExcludeList: {ServiceExcludeList ?? string.Empty}{Environment.NewLine}" +
                                              $"ServiceIncludeList: {ServiceIncludeList ?? string.Empty}{Environment.NewLine}" +
                                              $"MemoryWarningLimitMB: {MemoryWarningLimitMb}{Environment.NewLine}" +
@@ -118,8 +125,6 @@ public override string ToString() => $"ApplicationName: {TargetApp ?? string.Emp
                                              $"NetworkWarningActivePorts: {NetworkWarningActivePorts}{Environment.NewLine}" +
                                              $"NetworkErrorEphemeralPorts: {NetworkErrorEphemeralPorts}{Environment.NewLine}" +
                                              $"NetworkWarningEphemeralPorts: {NetworkWarningEphemeralPorts}{Environment.NewLine}" +
-                                             $"NetworkErrorFirewallRules: {NetworkErrorFirewallRules}{Environment.NewLine}" +
-                                             $"NetworkWarningFirewallRules: {NetworkWarningFirewallRules}{Environment.NewLine}" +
                                              $"DumpProcessOnError: {DumpProcessOnError}{Environment.NewLine}" +
                                              $"ErrorOpenFileHandles: {ErrorOpenFileHandles}{Environment.NewLine}" +
                                              $"WarningOpenFileHandles: {WarningOpenFileHandles}{Environment.NewLine}";