Service Fabric StateLessService only instantiating on one node - azure-service-fabric

I created a brand-new Service Fabric app with a single StatelessService. I expected the service to be instantiated on all five nodes (see my ApplicationManifest.xml file, below), but for some reason it always instantiates on Node 1. Any help in this regard would be greatly appreciated.
<?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="AlgoistsType" ApplicationTypeVersion="1.0.0" xmlns="http://schemas.microsoft.com/2011/01/fabric">
<Parameters>
<Parameter Name="TradeSafe_ASPNETCORE_ENVIRONMENT" DefaultValue="" />
<Parameter Name="TradeSafe_MinReplicaSetSize" DefaultValue="3" />
<Parameter Name="TradeSafe_PartitionCount" DefaultValue="1" />
<Parameter Name="TradeSafe_TargetReplicaSetSize" DefaultValue="3" />
<Parameter Name="FrontEnd_ASPNETCORE_ENVIRONMENT" DefaultValue="" />
<Parameter Name="FrontEnd_InstanceCount" DefaultValue="-1" />
</Parameters>
<ServiceManifestImport>
<ServiceManifestRef ServiceManifestName="TradeSafePkg" ServiceManifestVersion="1.0.0" />
<ConfigOverrides />
<EnvironmentOverrides CodePackageRef="code">
<EnvironmentVariable Name="ASPNETCORE_ENVIRONMENT" Value="[TradeSafe_ASPNETCORE_ENVIRONMENT]" />
</EnvironmentOverrides>
</ServiceManifestImport>
<ServiceManifestImport>
<ServiceManifestRef ServiceManifestName="FrontEndPkg" ServiceManifestVersion="1.0.0" />
<ConfigOverrides />
<EnvironmentOverrides CodePackageRef="code">
<EnvironmentVariable Name="ASPNETCORE_ENVIRONMENT" Value="[FrontEnd_ASPNETCORE_ENVIRONMENT]" />
</EnvironmentOverrides>
</ServiceManifestImport>
<DefaultServices>
<Service Name="FrontEnd" ServicePackageActivationMode="ExclusiveProcess">
<StatelessService ServiceTypeName="FrontEndType" InstanceCount="[FrontEnd_InstanceCount]">
<SingletonPartition />
</StatelessService>
</Service>
</DefaultServices>
</ApplicationManifest>

Related

Service Fabric Explorer Health State Unknown

The node in my partition keeps switching between Health State = OK and Health State = unknown.
Sometimes the node disappears.
I have tried deleting the service, the app and unprovisioning the type, then redeploying, however I get the same problem.
It is a Service Fabric stateful service, and it's running fine locally, the issue I'm having is only in my dev environment.
I'm using 5 nodes.
ServiceManifest.xml:
<?xml version="1.0" encoding="utf-8"?>
<ServiceManifest Name="Integration.Optical.ServicePkg"
Version="1.0.0"
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">
<ServiceTypes>
<!-- This is the name of your ServiceType.
This name must match the string used in the RegisterServiceAsync call in Program.cs. -->
<StatefulServiceType ServiceTypeName="Integration.Optical.ServiceType" />
</ServiceTypes>
<!-- Code package is your service executable. -->
<CodePackage Name="Code" Version="1.0.0">
<EntryPoint>
<ExeHost>
<Program>Integration.Optical.Service.exe</Program>
<WorkingFolder>CodePackage</WorkingFolder>
</ExeHost>
</EntryPoint>
<EnvironmentVariables>
<EnvironmentVariable Name="ASPNETCORE_ENVIRONMENT" Value=""/>
<EnvironmentVariable Name="KEYVAULT_ENDPOINT" Value=""/>
</EnvironmentVariables>
</CodePackage>
<!-- Config package is the contents of the Config directoy under PackageRoot that contains an
independently-updateable and versioned set of custom configuration settings for your service. -->
<ConfigPackage Name="Config" Version="1.0.0" />
<Resources>
<Endpoints>
<!-- This endpoint is used by the communication listener to obtain the port on which to
listen. Please note that if your service is partitioned, this port is shared with
replicas of different partitions that are placed in your code. -->
<Endpoint Name="ServiceEndpoint" />
<!-- This endpoint is used by the replicator for replicating the state of your service.
This endpoint is configured through a ReplicatorSettings config section in the Settings.xml
file under the ConfigPackage. -->
<Endpoint Name="ReplicatorEndpoint" />
</Endpoints>
</Resources>
</ServiceManifest>
ApplicationManifest.xml:
<?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="Integration.OpticalType" ApplicationTypeVersion="1.0.0" xmlns="http://schemas.microsoft.com/2011/01/fabric">
<Parameters>
<Parameter Name="Integration.Optical.Service_ASPNETCORE_ENVIRONMENT" DefaultValue="" />
<Parameter Name="Integration.Optical.Service_KEYVAULT_ENDPOINT" DefaultValue="" />
<Parameter Name="Integration.Optical.Service_MinReplicaSetSize" DefaultValue="3" />
<Parameter Name="Integration.Optical.Service_PartitionCount" DefaultValue="1" />
<Parameter Name="Integration.Optical.Service_TargetReplicaSetSize" DefaultValue="3" />
</Parameters>
<!-- Import the ServiceManifest from the ServicePackage. The ServiceManifestName and ServiceManifestVersion
should match the Name and Version attributes of the ServiceManifest element defined in the
ServiceManifest.xml file. -->
<ServiceManifestImport>
<ServiceManifestRef ServiceManifestName="Integration.Optical.ServicePkg" ServiceManifestVersion="1.0.0" />
<ConfigOverrides />
<EnvironmentOverrides CodePackageRef="code">
<EnvironmentVariable Name="ASPNETCORE_ENVIRONMENT" Value="[Integration.Optical.Service_ASPNETCORE_ENVIRONMENT]" />
<EnvironmentVariable Name="KEYVAULT_ENDPOINT" Value="[Integration.Optical.Service_KEYVAULT_ENDPOINT]" />
</EnvironmentOverrides>
</ServiceManifestImport>
<DefaultServices>
<!-- The section below creates instances of service types, when an instance of this
application type is created. You can also create one or more instances of service type using the
ServiceFabric PowerShell module.
The attribute ServiceTypeName below must match the name defined in the imported ServiceManifest.xml file. -->
<Service Name="Integration.Optical.Service" ServicePackageActivationMode="ExclusiveProcess">
<StatefulService ServiceTypeName="Integration.Optical.ServiceType" TargetReplicaSetSize="[Integration.Optical.Service_TargetReplicaSetSize]" MinReplicaSetSize="[Integration.Optical.Service_MinReplicaSetSize]">
<UniformInt64Partition PartitionCount="[Integration.Optical.Service_PartitionCount]" LowKey="-9223372036854775808" HighKey="9223372036854775807" />
</StatefulService>
</Service>
</DefaultServices>
</ApplicationManifest>
ApplicationParameters/Cloud.xml:
<?xml version="1.0" encoding="utf-8"?>
<Application xmlns:xsd="http://www.w3.org/2001/XMLSchema" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" Name="fabric:/Integration.Optical" xmlns="http://schemas.microsoft.com/2011/01/fabric">
<Parameters>
<Parameter Name="Integration.Optical.Service_ASPNETCORE_ENVIRONMENT" Value="" />
<Parameter Name="Integration.Optical.Service_KEYVAULT_ENDPOINT" Value="" />
<Parameter Name="Integration.Optical.Service_PartitionCount" Value="1" />
<Parameter Name="Integration.Optical.Service_MinReplicaSetSize" Value="1" />
<Parameter Name="Integration.Optical.Service_TargetReplicaSetSize" Value="1" />
</Parameters>
</Application>
Not sure what part of this fixed it. But this is what I did and it's now working:
In ServiceManifest.xml I added HasPersistedState = true:
<StatefulServiceType ServiceTypeName="Integration.Optical.ServiceType" HasPersistedState="true" />
I moved the app configuration code
ServiceRuntime.RegisterServiceAsync...
from Service.RunAsync() to Program.Main()

Trafeik , Service Fabric Backend , Stateless service, not reachable, always red in explorer

I have deployed trafeik in secured service fabric cluster , and i have made settings in servicemanifest of one of my application to use trafeik, eventhough trafeik is able to identify service but backend in trafeik is always red and my service is unreachable, if i use direct endpoint to my service it is reachable, need help in resolving same.
below is the toml of trafeik -
debug = true
logLevel = "INFO"
defaultEntryPoints = ["https"]
[entryPoints]
[entryPoints.https]
address = ":16080"
[entryPoints.https.tls]
[[entryPoints.https.tls.certificates]]
certFile = "certs/servicefabric.crt"
keyFile = "certs/servicefabric.key"
[entryPoints.traefik]
address = ":16081"
[api]
entryPoint = "traefik"
dashboard = true
debug = true
[servicefabric]
clustermanagementurl = "https://localhost:19080"
apiversion = "3.0"
[serviceFabric.tls]
cert = "certs/servicefabric.crt"
key = "certs/servicefabric.key"
insecureskipverify = true
Service manifest of trafik service -
<?xml version="1.0" encoding="utf-8"?>
<ServiceManifest Name="TraefikPkg" Version="1.0.0" 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">
<ServiceTypes>
<!-- This is the name of your ServiceType.
The UseImplicitHost attribute indicates this is a guest executable service. -->
<StatelessServiceType ServiceTypeName="TraefikType" UseImplicitHost="true" />
</ServiceTypes>
<!-- Code package is your service executable. -->
<CodePackage Name="Code" Version="1.0.0">
<!-- The SetupEntryPoint is an optional element used to specify a
program to be executed before the service's code is launched. -->
<EntryPoint>
<ExeHost>
<Program>traefik.exe</Program>
<Arguments>--configfile=traefik.toml</Arguments>
<WorkingFolder>CodePackage</WorkingFolder>
<!-- Uncomment to log console output (both stdout and stderr) to one of the
service's working directories. Do not use in production. -->
<!--<ConsoleRedirection FileRetentionCount="5" FileMaxSizeInKb="2048" />-->
</ExeHost>
</EntryPoint>
</CodePackage>
<!-- Config package is the contents of the Config directoy under PackageRoot that contains an
independently-updateable and versioned set of custom configuration settings for your service. -->
<ConfigPackage Name="Config" Version="1.0.0" />
<Resources>
<Endpoints>
<!-- This endpoint is used by the communication listener to obtain the port on which to
listen. Please note that if your service is partitioned, this port is shared with
replicas of different partitions that are placed in your code. -->
<Endpoint Protocol="https" Name="TraefikTypeEndpoint" Type="Input" Port="16080" CertificateRef="ClusterThumbprint"/>
<Endpoint Protocol="https" Name="TraefikTypeAPIEndpoint" Type="Input" Port="16081" CertificateRef="ClusterThumbprint"/>
</Endpoints>
</Resources>
</ServiceManifest>
Application manifest of trafeik service -
<?xml version="1.0" encoding="utf-8"?>
<ApplicationManifest ApplicationTypeName="TraefikType" ApplicationTypeVersion="1.0.0" 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">
<Parameters>
<Parameter Name="Traefik_InstanceCount" DefaultValue="-1" />
<Parameter Name="Stateless1_PlacementConstraints" DefaultValue="(NodeTypeName==fntensvcp)" />
</Parameters>
<ServiceManifestImport>
<ServiceManifestRef ServiceManifestName="TraefikPkg" ServiceManifestVersion="1.0.0" />
<ConfigOverrides />
<Policies>
<RunAsPolicy CodePackageRef="Code" UserRef="AdminUser" EntryPointType="All" />
</Policies>
</ServiceManifestImport>
<DefaultServices>
<Service Name="Traefik" ServicePackageActivationMode="ExclusiveProcess">
<StatelessService ServiceTypeName="TraefikType" InstanceCount="[Traefik_InstanceCount]">
<SingletonPartition />
<PlacementConstraints>[Stateless1_PlacementConstraints]</PlacementConstraints>
</StatelessService>
</Service>
</DefaultServices>
<Principals>
<Users>
<User Name="AdminUser">
<MemberOf>
<SystemGroup Name="Administrators" />
</MemberOf>
</User>
</Users>
</Principals>
<Certificates>
<EndpointCertificate X509FindValue="b22bb9d3e74da3339e5f6709798107443553ae48" Name="ClusterThumbprint" />
</Certificates>
</ApplicationManifest>
For my application below is service manifest -
<?xml version="1.0" encoding="utf-8"?>
<ServiceManifest Name="CSM.IE.SMA.C360.RevenueServicePkg" Version="1.0.0" 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" ManifestId="25bba1ad-7380-4cbf-b9ed-9a90ee3dd086">
<ServiceTypes>
<!-- This is the name of your ServiceType.
This name must match the string used in RegisterServiceType call in Program.cs. -->
<StatelessServiceType ServiceTypeName="CSM.IE.SMA.C360.RevenueServiceType">
<Extensions>
<Extension Name="Traefik">
<Labels xmlns="http://schemas.microsoft.com/2015/03/fabact-no-schema">
<Label Key="traefik.frontend.rule.c360Revenue">PathPrefixStrip: /C360/RevenueService</Label>
<Label Key="traefik.enable">true</Label>
<Label Key="traefik.frontend.passHostHeader">true</Label>
</Labels>
</Extension>
</Extensions>
</StatelessServiceType>
</ServiceTypes>
<!-- Code package is your service executable. -->
<CodePackage Name="Code" Version="1.0.0">
<EntryPoint>
<ExeHost>
<Program>CSM.IE.SMA.C360.RevenueService.exe</Program>
</ExeHost>
</EntryPoint>
</CodePackage>
<!-- Config package is the contents of the Config directoy under PackageRoot that contains an
independently-updateable and versioned set of custom configuration settings for your service. -->
<ConfigPackage Name="Config" Version="1.0.0" />
<Resources>
<Endpoints>
<!-- This endpoint is used by the communication listener to obtain the port on which to
listen. Please note that if your service is partitioned, this port is shared with
replicas of different partitions that are placed in your code. -->
<!--<Endpoint Name="ServiceEndpoint" Protocol="http" Port="8082"/>-->
<Endpoint Protocol="https" Name="ServiceEndpoint" Type="Input" Port="19616" CertificateRef="ClusterThumbprint" />
</Endpoints>
</Resources>
</ServiceManifest>
for my application below is application manifest file -
<?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="IE_SmartAssistance" ApplicationTypeVersion="1.0.0" xmlns="http://schemas.microsoft.com/2011/01/fabric" ManifestId="1ff9d8a9-ecbc-4d55-931e-eb59eb229f15">
<Parameters>
<Parameter Name="MultiTPIDConsumptionService_InstanceCount" DefaultValue="2" />
<Parameter Name="SupportService_InstanceCount" DefaultValue="2" />
<Parameter Name="ConsumptionService_InstanceCount" DefaultValue="2" />
<Parameter Name="AgreementService_InstanceCount" DefaultValue="2" />
<Parameter Name="RevenueService_InstanceCount" DefaultValue="2" />
<Parameter Name="ProfileProxyService_InstanceCount" DefaultValue="2" />
<Parameter Name="Stateless1_PlacementConstraints" DefaultValue="(NodeTypeName==fntensvcp)" />
</Parameters>
<!-- Import the ServiceManifest from the ServicePackage. The ServiceManifestName and ServiceManifestVersion
should match the Name and Version attributes of the ServiceManifest element defined in the
ServiceManifest.xml file. -->
<ServiceManifestImport>
<ServiceManifestRef ServiceManifestName="CSM.IE.SMA.C360.MultiTPIDConsumptionServicePkg" ServiceManifestVersion="1.0.0" />
<ConfigOverrides />
<Policies>
<EndpointBindingPolicy EndpointRef="ServiceEndpoint" CertificateRef="ClusterThumbprint" />
<RunAsPolicy CodePackageRef="Code" UserRef="LocalAdmin" />
</Policies>
</ServiceManifestImport>
<ServiceManifestImport>
<ServiceManifestRef ServiceManifestName="CSM.IE.SMA.C360.AgreementServicePkg" ServiceManifestVersion="1.0.0" />
<ConfigOverrides />
<Policies>
<EndpointBindingPolicy EndpointRef="ServiceEndpoint" CertificateRef="ClusterThumbprint" />
<RunAsPolicy CodePackageRef="Code" UserRef="LocalAdmin" />
</Policies>
</ServiceManifestImport>
<ServiceManifestImport>
<ServiceManifestRef ServiceManifestName="CSM.IE.SMA.C360.RevenueServicePkg" ServiceManifestVersion="1.0.0" />
<ConfigOverrides />
<Policies>
<EndpointBindingPolicy EndpointRef="ServiceEndpoint" CertificateRef="ClusterThumbprint" />
<RunAsPolicy CodePackageRef="Code" UserRef="LocalAdmin" />
</Policies>
</ServiceManifestImport>
<ServiceManifestImport>
<ServiceManifestRef ServiceManifestName="CSM.IE.SMA.C360.ProfileProxyServicePkg" ServiceManifestVersion="1.0.0" />
<ConfigOverrides />
<Policies>
<EndpointBindingPolicy EndpointRef="ServiceEndpoint" CertificateRef="ClusterThumbprint" />
<RunAsPolicy CodePackageRef="Code" UserRef="LocalAdmin" />
</Policies>
</ServiceManifestImport>
<ServiceManifestImport>
<ServiceManifestRef ServiceManifestName="CSM.IE.SMA.C360.ConsumptionServicePkg" ServiceManifestVersion="1.0.0" />
<ConfigOverrides />
<Policies>
<EndpointBindingPolicy EndpointRef="ServiceEndpoint" CertificateRef="ClusterThumbprint" />
<RunAsPolicy CodePackageRef="Code" UserRef="LocalAdmin" />
</Policies>
</ServiceManifestImport>
<ServiceManifestImport>
<ServiceManifestRef ServiceManifestName="CSM.IE.SMA.C360.SupportServicePkg" ServiceManifestVersion="1.0.0" />
<ConfigOverrides />
<Policies>
<EndpointBindingPolicy EndpointRef="ServiceEndpoint" CertificateRef="ClusterThumbprint" />
<RunAsPolicy CodePackageRef="Code" UserRef="LocalAdmin" />
</Policies>
</ServiceManifestImport>
<DefaultServices>
<!-- The section below creates instances of service types, when an instance of this
application type is created. You can also create one or more instances of service type using the
ServiceFabric PowerShell module.
The attribute ServiceTypeName below must match the name defined in the imported ServiceManifest.xml file. -->
<Service Name="CSM.IE.SMA.C360.MultiTPIDConsumptionService" ServicePackageActivationMode="ExclusiveProcess">
<StatelessService ServiceTypeName="CSM.IE.SMA.C360.MultiTPIDConsumptionServiceType" InstanceCount="[MultiTPIDConsumptionService_InstanceCount]">
<SingletonPartition />
<PlacementConstraints>[Stateless1_PlacementConstraints]</PlacementConstraints>
</StatelessService>
</Service>
<Service Name="IE_SmartAssistance_Customer360Service_AgreementService-Microservice_API">
<StatelessService ServiceTypeName="CSM.IE.SMA.C360.AgreementServiceType" InstanceCount="[AgreementService_InstanceCount]">
<SingletonPartition />
<PlacementConstraints>[Stateless1_PlacementConstraints]</PlacementConstraints>
</StatelessService>
</Service>
<Service Name="RevenueService-Microservice_API" ServicePackageActivationMode="ExclusiveProcess">
<StatelessService ServiceTypeName="CSM.IE.SMA.C360.RevenueServiceType" InstanceCount="[RevenueService_InstanceCount]">
<SingletonPartition />
<PlacementConstraints>[Stateless1_PlacementConstraints]</PlacementConstraints>
</StatelessService>
</Service>
<Service Name="CSM.IE.SMA.C360.ProfileProxyService" ServicePackageActivationMode="ExclusiveProcess">
<StatelessService ServiceTypeName="CSM.IE.SMA.C360.ProfileProxyServiceType" InstanceCount="[ProfileProxyService_InstanceCount]">
<SingletonPartition />
<PlacementConstraints>[Stateless1_PlacementConstraints]</PlacementConstraints>
</StatelessService>
</Service>
<Service Name="CSM.IE.SMA.C360.ConsumptionService" ServicePackageActivationMode="ExclusiveProcess">
<StatelessService ServiceTypeName="CSM.IE.SMA.C360.ConsumptionServiceType" InstanceCount="[ConsumptionService_InstanceCount]">
<SingletonPartition />
<PlacementConstraints>[Stateless1_PlacementConstraints]</PlacementConstraints>
</StatelessService>
</Service>
<Service Name="CSM.IE.SMA.C360.SupportService" ServicePackageActivationMode="ExclusiveProcess">
<StatelessService ServiceTypeName="CSM.IE.SMA.C360.SupportServiceType" InstanceCount="[SupportService_InstanceCount]">
<SingletonPartition />
<PlacementConstraints>[Stateless1_PlacementConstraints]</PlacementConstraints>
</StatelessService>
</Service>
</DefaultServices>
<Principals>
<Users>
<User Name="LocalAdmin" AccountType="NetworkService">
<MemberOf>
<SystemGroup Name="Administrators" />
</MemberOf>
</User>
</Users>
</Principals>
<Certificates>
<EndpointCertificate X509FindValue="b22bb9d3e74da3339e5f6709798107443553ae48" Name="ClusterThumbprint" />
</Certificates>
</ApplicationManifest>

Register-ServiceFabricApplicationType : Value cannot be null. Parameter name: source

I'm trying to run my Service Fabric App locally but I'm receiving the follow error:
Register-ServiceFabricApplicationType : Value cannot be null.
Parameter name: source
What is source in this context? And why is it null?
In ApplicationManifest.xml I defined <EnvironmentOverrides> w/ one <EnvironmentVariable> entry but I didn't define that <EnvironmentVariable> in ServiceManifest.xml.
Sample project to illustrate
ApplicationManifest.xml
<?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="Application1Type" ApplicationTypeVersion="1.0.0" xmlns="http://schemas.microsoft.com/2011/01/fabric">
<Parameters>
<Parameter Name="Web1_InstanceCount" DefaultValue="-1" />
<Parameter Name="OverrideTest" DefaultValue="Do I Get a Useless Error Message?" />
</Parameters>
<ServiceManifestImport>
<ServiceManifestRef ServiceManifestName="Web1Pkg" ServiceManifestVersion="1.0.0" />
<ConfigOverrides />
<EnvironmentOverrides CodePackageRef="Code">
<EnvironmentVariable Name="OverrideTest" Value="[OverrideTest]" />
</EnvironmentOverrides>
</ServiceManifestImport>
....
</DefaultServices>
</ApplicationManifest>
ServiceManifest.xml
<?xml version="1.0" encoding="utf-8"?>
<ServiceManifest Name="Web1Pkg"
Version="1.0.0"
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">
<ServiceTypes>
<StatelessServiceType ServiceTypeName="Web1Type" />
</ServiceTypes>
<CodePackage Name="Code" Version="1.0.0">
<EntryPoint>
<ExeHost>
<Program>Web1.exe</Program>
<WorkingFolder>CodePackage</WorkingFolder>
</ExeHost>
</EntryPoint>
<!--Uncomment the EnvironmentVariables to get rid of Value cannot be null. >Parameter name: source-->
<!--<EnvironmentVariables>
<EnvironmentVariable Name="OverrideTest" Value="Uncomment-me to get rid of the error" />
</EnvironmentVariables>-->
</CodePackage>
...
</ServiceManifest>

Why can't I connect to this Service Fabric cluster?

I'm blocked by an error when connecting to a remote service fabric cluster running on premise (not on Azure) using the Connect-ServiceFabricCluster PowerShell command for a network-connected virtual machine:
WARNING: Failed to contact Naming Service. Attempting to contact Failover Manager Service...
WARNING: Failed to contact Failover Manager Service, Attempting to contact FMM...
False
WARNING: A connection attempt failed because the connected party did not properly respond after a period of time, or established connection failed because connected host has failed to respond 192.168.1.102:19000
Connect-ServiceFabricCluster : No cluster endpoint is reachable, please check if there is connectivity/firewall/DNS issue.
At Install.ps1:3 char:1
+ Connect-ServiceFabricCluster -ConnectionEndpoint "FABRICTESTSRV:19000" -WindowsCred ...
+ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ CategoryInfo : InvalidOperation: (:) [Connect-ServiceFabricCluster], FabricException
+ FullyQualifiedErrorId : TestClusterConnectionErrorId,Microsoft.ServiceFabric.Powershell.ConnectCluster
The command is:
Connect-ServiceFabricCluster -ConnectionEndpoint "FABRICTESTSRV:19000" -WindowsCredential:$True
Why isn't it working?
Here is what I have tried:
I have tried turning Windows Firewall off entirely. No luck there.
Connecting locally to the cluster while inside of the virtual machine works just fine: Connect-ServiceFabricCluster "localhost:19000"
This is not a DNS issue. I can ping the FQDN of the machine just fine.
Note: This is not an Azure hosted Virtual Machine. This is simply a network-connected virtual machine running Service Fabric Core, vanilla Windows 8.1 x64 fully up to date.
Edit: Get-ServiceFabricClusterManifest reads as follows:
<ClusterManifest xmlns:xsd="http://www.w3.org/2001/XMLSchema" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" Name="ComputerName-Local-Cluster" Version=
"1.0" xmlns="http://schemas.microsoft.com/2011/01/fabric">
<NodeTypes>
<NodeType Name="NodeType0">
<Endpoints>
<ClientConnectionEndpoint Port="19000" />
<LeaseDriverEndpoint Port="19001" />
<ClusterConnectionEndpoint Port="19002" />
<HttpGatewayEndpoint Port="19080" Protocol="http" />
<HttpApplicationGatewayEndpoint Port="19081" Protocol="http" />
<ServiceConnectionEndpoint Port="19006" />
<ApplicationEndpoints StartPort="30001" EndPort="31000" />
</Endpoints>
</NodeType>
<NodeType Name="NodeType1">
<Endpoints>
<ClientConnectionEndpoint Port="19010" />
<LeaseDriverEndpoint Port="19011" />
<ClusterConnectionEndpoint Port="19012" />
<HttpGatewayEndpoint Port="19082" Protocol="http" />
<HttpApplicationGatewayEndpoint Port="19083" Protocol="http" />
<ServiceConnectionEndpoint Port="19016" />
<ApplicationEndpoints StartPort="31001" EndPort="32000" />
</Endpoints>
</NodeType>
<NodeType Name="NodeType2">
<Endpoints>
<ClientConnectionEndpoint Port="19020" />
<LeaseDriverEndpoint Port="19021" />
<ClusterConnectionEndpoint Port="19022" />
<HttpGatewayEndpoint Port="19084" Protocol="http" />
<HttpApplicationGatewayEndpoint Port="19085" Protocol="http" />
<ServiceConnectionEndpoint Port="19026" />
<ApplicationEndpoints StartPort="32001" EndPort="33000" />
</Endpoints>
</NodeType>
<NodeType Name="NodeType3">
<Endpoints>
<ClientConnectionEndpoint Port="19030" />
<LeaseDriverEndpoint Port="19031" />
<ClusterConnectionEndpoint Port="19032" />
<HttpGatewayEndpoint Port="19086" Protocol="http" />
<HttpApplicationGatewayEndpoint Port="19087" Protocol="http" />
<ServiceConnectionEndpoint Port="19036" />
<ApplicationEndpoints StartPort="33001" EndPort="34000" />
</Endpoints>
</NodeType>
<NodeType Name="NodeType4">
<Endpoints>
<ClientConnectionEndpoint Port="19040" />
<LeaseDriverEndpoint Port="19041" />
<ClusterConnectionEndpoint Port="19042" />
<HttpGatewayEndpoint Port="19088" Protocol="http" />
<HttpApplicationGatewayEndpoint Port="19089" Protocol="http" />
<ServiceConnectionEndpoint Port="19046" />
<ApplicationEndpoints StartPort="34001" EndPort="35000" />
</Endpoints>
</NodeType>
</NodeTypes>
<Infrastructure>
<WindowsServer IsScaleMin="true">
<NodeList>
<Node NodeName="_Node_0" IPAddressOrFQDN="localhost" IsSeedNode="true" NodeTypeRef="NodeType0" FaultDomain="fd:/0" UpgradeDomain="0" />
<Node NodeName="_Node_1" IPAddressOrFQDN="localhost" IsSeedNode="true" NodeTypeRef="NodeType1" FaultDomain="fd:/1" UpgradeDomain="1" />
<Node NodeName="_Node_2" IPAddressOrFQDN="localhost" IsSeedNode="true" NodeTypeRef="NodeType2" FaultDomain="fd:/2" UpgradeDomain="2" />
<Node NodeName="_Node_3" IPAddressOrFQDN="localhost" NodeTypeRef="NodeType3" FaultDomain="fd:/3" UpgradeDomain="3" />
<Node NodeName="_Node_4" IPAddressOrFQDN="localhost" NodeTypeRef="NodeType4" FaultDomain="fd:/4" UpgradeDomain="4" />
</NodeList>
</WindowsServer>
</Infrastructure>
<FabricSettings>
<Section Name="Security">
<Parameter Name="ClusterCredentialType" Value="None" />
<Parameter Name="ServerAuthCredentialType" Value="None" />
</Section>
<Section Name="FailoverManager">
<Parameter Name="ExpectedClusterSize" Value="4" />
<Parameter Name="TargetReplicaSetSize" Value="3" />
<Parameter Name="MinReplicaSetSize" Value="3" />
<Parameter Name="ReconfigurationTimeLimit" Value="20" />
<Parameter Name="BuildReplicaTimeLimit" Value="20" />
<Parameter Name="CreateInstanceTimeLimit" Value="20" />
<Parameter Name="PlacementTimeLimit" Value="20" />
</Section>
<Section Name="ReconfigurationAgent">
<Parameter Name="ServiceApiHealthDuration" Value="20" />
<Parameter Name="ServiceReconfigurationApiHealthDuration" Value="20" />
<Parameter Name="LocalHealthReportingTimerInterval" Value="5" />
<Parameter Name="IsDeactivationInfoEnabled" Value="true" />
<Parameter Name="RAUpgradeProgressCheckInterval" Value="3" />
</Section>
<Section Name="ClusterManager">
<Parameter Name="TargetReplicaSetSize" Value="3" />
<Parameter Name="MinReplicaSetSize" Value="3" />
<Parameter Name="UpgradeStatusPollInterval" Value="5" />
<Parameter Name="UpgradeHealthCheckInterval" Value="5" />
<Parameter Name="FabricUpgradeHealthCheckInterval" Value="5" />
</Section>
<Section Name="NamingService">
<Parameter Name="TargetReplicaSetSize" Value="3" />
<Parameter Name="MinReplicaSetSize" Value="3" />
</Section>
<Section Name="Management">
<Parameter Name="ImageStoreConnectionString" Value="file:C:\SfDevCluster\Data\ImageStoreShare" />
<Parameter Name="ImageCachingEnabled" Value="false" />
<Parameter Name="EnableDeploymentAtDataRoot" Value="true" />
</Section>
<Section Name="Hosting">
<Parameter Name="EndpointProviderEnabled" Value="true" />
<Parameter Name="RunAsPolicyEnabled" Value="true" />
<Parameter Name="DeactivationScanInterval" Value="60" />
<Parameter Name="DeactivationGraceInterval" Value="10" />
<Parameter Name="EnableProcessDebugging" Value="true" />
<Parameter Name="ServiceTypeRegistrationTimeout" Value="20" />
<Parameter Name="CacheCleanupScanInterval" Value="300" />
</Section>
<Section Name="HttpGateway">
<Parameter Name="IsEnabled" Value="true" />
</Section>
<Section Name="PlacementAndLoadBalancing">
<Parameter Name="MinLoadBalancingInterval" Value="300" />
</Section>
<Section Name="Federation">
<Parameter Name="NodeIdGeneratorVersion" Value="V4" />
<Parameter Name="UnresponsiveDuration" Value="0" />
</Section>
<Section Name="ApplicationGateway/Http">
<Parameter Name="IsEnabled" Value="true" />
</Section>
<Section Name="FaultAnalysisService">
<Parameter Name="TargetReplicaSetSize" Value="3" />
<Parameter Name="MinReplicaSetSize" Value="3" />
</Section>
<Section Name="Trace/Etw">
<Parameter Name="Level" Value="4" />
</Section>
<Section Name="Diagnostics">
<Parameter Name="ProducerInstances" Value="ServiceFabricEtlFile, ServiceFabricPerfCtrFolder" />
<Parameter Name="MaxDiskQuotaInMB" Value="10240" />
</Section>
<Section Name="ServiceFabricEtlFile">
<Parameter Name="ProducerType" Value="EtlFileProducer" />
<Parameter Name="IsEnabled" Value="true" />
<Parameter Name="EtlReadIntervalInMinutes" Value=" 5" />
<Parameter Name="DataDeletionAgeInDays" Value="3" />
</Section>
<Section Name="ServiceFabricPerfCtrFolder">
<Parameter Name="ProducerType" Value="FolderProducer" />
<Parameter Name="IsEnabled" Value="true" />
<Parameter Name="FolderType" Value="ServiceFabricPerformanceCounters" />
<Parameter Name="DataDeletionAgeInDays" Value="3" />
</Section>
<Section Name="TransactionalReplicator">
<Parameter Name="CheckpointThresholdInMB" Value="64" />
</Section>
</FabricSettings>
</ClusterManifest>
Why isn't it working?
It is not working because you set IP address of your nodes as localhost thus making them undiscoverable. It will work for local debug cluster, but for on-premises and for Azure clusters you have to specify valid and reachable IP address or qualified name.
Also, I'm not 100% sure right now, but I can suggest to specify FQDN instead of IP address if you want your cluster be accessible by URI and not by IP. I remember I had troubles with this, but it is still not clear what has helped — FQDN or something else.
There were a few issues, but the biggest, as #cassandrad mentioned, was that the default deployment binds to the TCP FQDN of localhost (IPAddressOrFQDN="localhost") and not the IP address of the machine, so it only allows local connections by default.
Here are complete steps for fixing my issue:
I first ran netstat -a | FindStr "19000" in Command Prompt to check what bindings were active, in order to affirm what #cassandrad said.
Reading this guide, I decided to download the Service Fabric standalone package for Windows Server (works just fine outside of Windows Server, on Windows 8.1 x64 by the way).
I copied and then modified ClusterConfig.Unsecure.DevCluster.json, under the nodes section I changed all nodes' iPAddress to be 192.168.1.102. I called the new file ClusterConfig.Unsecure.CustomDevCluster.json.
I ran CreateServiceFabricCluster.ps1. It asked me what JSON configuration to use, so I gave it ClusterConfig.Unsecure.DevCluster.json.
The first time it failed because of an error fetching Newtonsoft.JSON version 6.0.0.0, as visible from the traces, which was a rather annoying, obfuscated error. The error was because I did not have .NET Framework 4.6.2, so I downloaded and installed it.
The second time it failed because a Microsoft Azure Service Fabric MSI was installed. This error came up because I had previously installed MicrosoftAzure-ServiceFabric-CoreSDK.exe. I went to Programs and Features and uninstalled Microsoft Azure Service Fabric (I left the Microsoft Azure Service Fabric SDK installed).
I ran the script one last time, fingers crossed, it finally worked.
It is an unsecure cluster, so I was able to simply connect to it using Connect-ServiceFabricCluster "192.168.1.102:19000". If you want to enable other authentication mechanisms, modify and use some of the other .json sample configurations.

OrientDB Embedded and Distributed error: Distributed Storage was not installed

Hello thank you for reading this question. I have orient db set up and would like to add a second server and have them replicate between each other. When one goes on its own it runs fine and I have been using it for months. When enabling the hazelcast plugin, the servers start communicating, and I can see they start to talk to each other. An error happens when they try to write to each other though. This is the same issue discussed here:
https://groups.google.com/forum/#!topic/orient-database/QpZPG4y_KpU
For what its worth, I have both of these servers deployed on the same machine, each with their own embedded database. The database paths are plocal:/home/chris/dbs/db2 and plocal:/home/chris/dbs/db1
2015-10-08 08:56:14:048 INFO [db2-orient] Saving distributed configuration file for database 'db' to: ./databases/db/distributed-config.json [OHazelcastPlugin]
2015-10-08 08:56:14:049 INFO [db2-orient] received new status idp2-orient.idp=SYNCHRONIZING [OHazelcastPlugin]
2015-10-08 08:56:18:054 WARNING [db2-orient]->[[db1-orient]] requesting deploy of database 'db' on local server... [OHazelcastPlugin]
Then on the other server, the one that started first, I see
[OHazelcastPlugin]{db=db} [db1-orient]<-[db2-orient] error on executing distributed request 0: deploy_db
com.orientechnologies.orient.server.distributed.ODistributedException: Distributed storage was not installed for database 'db'. Implementation found: com.orientechnologies.orient.core.storage.impl.local.paginated.OLocalPaginatedStorage
at com.orientechnologies.orient.server.hazelcast.OHazelcastPlugin.executeOnLocalNode(OHazelcastPlugin.java:745)
at com.orientechnologies.orient.server.hazelcast.ODistributedWorker.onMessage(ODistributedWorker.java:298)
at com.orientechnologies.orient.server.hazelcast.ODistributedWorker.run(ODistributedWorker.java:121)
I put a breakpoint on the line that throws that exception, and the storage type present at that time is indeed OLocalPaginatedStorage. My orientDB version is 2.0.15.
My distributed config. (Same on both servers)
{
"autoDeploy": true,
"hotAlignment": false,
"executionMode": "undefined",
"readQuorum": 1,
"writeQuorum": 2,
"failureAvailableNodesLessQuorum": false,
"readYourWrites": true,
"clusters": {
"internal": {
},
"index": {
},
"*": {
"servers" : [ "<NEW_NODE>" ]
}
}
}
This is how I start my server. It is embedded, and started via a java application.
OServer server = OServerMain.create(true);
OPartitionedDatabasePool pool = server.startup(config.toString()).activate().getDatabasePoolFactory().get(dbPath, OUser.ADMIN, OUser.ADMIN);
The config the server uses to start up is this
<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<orient-server>
<handlers>
<handler class="com.orientechnologies.orient.server.hazelcast.OHazelcastPlugin">
<parameters>
<parameter name="nodeName" value="db2-orient" />
<parameter name="enabled" value="true" />
<parameter name="configuration.db.default" value="${orientDBConfigs}/orientdb-default-distributed-db-config.json" />
<parameter name="configuration.hazelcast" value="${orientDBConfigs}/orientdb-hazelcast.xml" />
<parameter name="conflict.resolver.impl" value="com.orientechnologies.orient.server.distributed.conflict.ODefaultReplicationConflictResolver" />
<parameter name="sharding.strategy.round-robin" value="com.orientechnologies.orient.server.hazelcast.sharding.strategy.ORoundRobinPartitioninStrategy" />
</parameters>
</handler>
<handler class="com.orientechnologies.orient.server.handler.OAutomaticBackup">
<parameters>
<parameter name="enabled" value="false" />
<parameter name="delay" value="4h" />
<parameter name="target.directory" value="backup" />
<parameter name="target.fileName" value="${DBNAME}-${DATE:yyyyMMddHHmmss}.json" />
<parameter name="db.include" value="" />
<parameter name="db.exclude" value="" />
</parameters>
</handler>
<handler class="com.orientechnologies.orient.server.plugin.mail.OMailPlugin">
<parameters>
<parameter name="enabled" value="false" />
<parameter name="profile.default.mail.smtp.host" value="localhost" />
<parameter name="profile.default.mail.smtp.port" value="25" />
<parameter name="profile.default.mail.smtp.auth" value="true" />
<parameter name="profile.default.mail.smtp.starttls.enable" value="true" />
<parameter name="profile.default.mail.smtp.user" value="" />
<parameter name="profile.default.mail.smtp.password" value="" />
<parameter name="profile.default.mail.date.format" value="yyyy-MM-dd HH:mm:ss" />
</parameters>
</handler>
<handler class="com.orientechnologies.orient.server.handler.OServerSideScriptInterpreter">
<parameters>
<parameter name="enabled" value="false" />
</parameters>
</handler>
</handlers>
<network>
<protocols>
<protocol name="binary" implementation="com.orientechnologies.orient.server.network.protocol.binary.ONetworkProtocolBinary" />
</protocols>
<listeners>
<listener protocol="binary" ip-address="0.0.0.0" port-range="2424-2430" />
</listeners>
<cluster>
</cluster>
</network>
<storages>
<storage name="${dbName}" path="${dbPath}" loaded-at-startup="true" />
</storages>
<users>
<user name="root" password="root" resources="*"/>
</users>
<properties>
<entry name="db.pool.min" value="1" />
<entry name="db.pool.max" value="20" />
<entry name="cache.level1.enabled" value="false" />
<entry name="cache.level1.size" value="1000" />
<entry name="cache.level2.enabled" value="true" />
<entry name="cache.level2.size" value="1000" />
<entry name="profiler.enabled" value="true" />
<entry name="log.console.level" value="info" />
<entry name="log.file.level" value="fine" />
<entry name="plugin.dynamic" value="false"/>
</properties>
Thanks again.
as wolf4ood pointed out, the storage type is replaced by the hazelcast plugin in the hazelcast plugin's onOpen method. Paginated storage gets switched to Distributed. This replacement does not happen if the path doesnt start with "plocal:./databases". Solution: make the path start with that. I have no idea if this is a good idea or not. That check seems to be in there for a reason, the comments in the code seem to indicate something about running on the same jvm.