freshness

Author: Larry Franks

articles/machine-learning/service/how-to-assign-roles.md

@@ -9,7 +9,7 @@ ms.topic: conceptual
 ms.reviewer: jmartens
 ms.author: larryfr
 author: Blackmist
-ms.date: 07/10/2019
+ms.date: 11/06/2019
 ms.custom: seodec18
 
 ---

articles/machine-learning/service/how-to-change-storage-access-key.md

@@ -9,7 +9,7 @@ ms.topic: conceptual
 ms.author: aashishb
 author: aashishb
 ms.reviewer: larryfr
-ms.date: 08/16/2019
+ms.date: 11/06/2019
 
 
 ---

articles/machine-learning/service/how-to-consume-web-service.md

@@ -9,7 +9,7 @@ ms.topic: conceptual
 ms.author: aashishb
 author: aashishb
 ms.reviewer: larryfr
-ms.date: 08/15/2019
+ms.date: 11/06/2019
 ms.custom: seodec18
 
 

articles/machine-learning/service/how-to-deploy-azure-kubernetes-service.md

@@ -9,7 +9,7 @@ ms.topic: conceptual
 ms.author: jordane
 author: jpe316
 ms.reviewer: larryfr
-ms.date: 10/25/2019
+ms.date: 11/06/2019
 ---
 
 # Deploy a model to an Azure Kubernetes Service cluster
@@ -117,12 +117,16 @@ If you already have AKS cluster in your Azure subscription, and it is lower than
 >
 > If you want to secure your AKS cluster using an Azure Virtual Network, you must create the virtual network first. For more information, see [Secure experimentation and inference with Azure Virtual Network](how-to-enable-virtual-network.md#aksvnet).
 
+When attaching an AKS cluster to a workspace, you can define how you will use the cluster by setting the `cluster_purpose` parameter.
+
+If you do not set the `cluster_purpose` parameter, or set `cluster_purpose = AksCompute.ClusterPurpose.FAST_PROD`, then the cluster must have at least 12 virtual CPUs available.
+
+If you set `cluster_purpose = AksCompute.ClusterPurpose.DEV_TEST`, then the cluster does not need to have 12 virtual CPUs. We recommend at least 2 virtual CPUs for dev/test. However a cluster that is configured for dev/test is not suitable for production level traffic and may increase inference times. Dev/test clusters also do not guarantee fault tolerance.
+
 > [!WARNING]
-> When attaching an AKS cluster to a workspace, you can define how you will use the cluster by setting the `cluster_purpose` parameter.
->
-> If you do not set the `cluster_purpose` parameter, or set `cluster_purpose = AksCompute.ClusterPurpose.FAST_PROD`, then the cluster must have at least 12 virtual CPUs available.
+> Do not create multiple, simultaneous attachments to the same AKS cluster from your workspace. For example, attaching one AKS cluster to a workspace using two different names. Each new attachment will break the previous existing attachment(s).
 >
-> If you set `cluster_purpose = AksCompute.ClusterPurpose.DEV_TEST`, then the cluster does not need to have 12 virtual CPUs. We recommend at least 2 virtual CPUs for dev/test. However a cluster that is configured for dev/test is not suitable for production level traffic and may increase inference times. Dev/test clusters also do not guarantee fault tolerance.
+> If you want to re-attach an AKS cluster, for example to change SSL or other cluster configuration setting, you must first remove the existing attachment by using [AksCompute.detatch()](https://docs.microsoft.com/python/api/azureml-core/azureml.core.compute.akscompute?view=azure-ml-py#detach--).
 
 For more information on creating an AKS cluster using the Azure CLI or portal, see the following articles:
 

articles/machine-learning/service/how-to-deploy-existing-model.md

@@ -9,7 +9,7 @@ ms.topic: conceptual
 ms.author: jordane
 author: jpe316
 ms.reviewer: larryfr
-ms.date: 10/25/2019
+ms.date: 11/06/2019
 ---
 
 # Use an existing model with Azure Machine Learning

articles/machine-learning/service/monitor-resource-reference.md

@@ -10,7 +10,7 @@ ms.topic: conceptual
 ms.reviewer: larryfr
 ms.author: aashishb
 author: aashishb
-ms.date: 11/04/2019
+ms.date: 11/06/2019
 ---
 
 # Azure machine learning monitoring data reference
@@ -50,7 +50,7 @@ The following table lists the properties for Azure Machine Learning resource log
 | JobErrorMessage | detailed message of Job error |
 | NodeId | ID of the node created where job is running |
 
-### AmlComputerClusterEvents table
+### AmlComputeClusterEvents table
 
 | Property | Description |
 |:--- |:--- |

includes/machine-learning-service-aci-deploy-config.md

@@ -2,7 +2,7 @@
 author: larryfr
 ms.service: machine-learning
 ms.topic: include
-ms.date: 07/26/2019
+ms.date: 10/06/2019
 ms.author: larryfr
 ---
 

includes/machine-learning-service-aks-deploy-config.md

@@ -2,7 +2,7 @@
 author: larryfr
 ms.service: machine-learning
 ms.topic: include
-ms.date: 07/26/2019
+ms.date: 10/06/2019
 ms.author: larryfr
 ---
 

includes/machine-learning-service-inference-config.md

@@ -2,7 +2,7 @@
 author: larryfr
 ms.service: machine-learning
 ms.topic: include
-ms.date: 07/19/2019
+ms.date: 11/06/2019
 ms.author: larryfr
 ---
 

includes/machine-learning-service-install-extension.md

@@ -2,7 +2,7 @@
 author: larryfr
 ms.service: machine-learning
 ms.topic: include
-ms.date: 08/13/2019
+ms.date: 11/06/2019
 ms.author: larryfr
 ---