Merge pull request #191445 from kasun04/master

Updating Premium scaling guidelines

Author: PRMerger8

articles/event-hubs/event-hubs-premium-overview.md

@@ -37,7 +37,7 @@ In comparison to the dedicated offering, the premium tier provides the following
 - Scale far more elastically and quicker
 - PUs can be dynamically adjusted
 
-Therefore, the premium tier is often a more cost effective option for mid-range (<120MB/sec) throughput requirements, especially with changing loads throughout the day or week, when compared to the dedicated tier. 
+Therefore, the premium tier is often a more cost effective option for event streaming workloads up to 160 MB/sec (per namespace), especially with changing loads throughout the day or week, when compared to the dedicated tier. 
 
 For the extra robustness gained by availability-zone support, the minimal deployment scale for the dedicated tier is 8 capacity units (CU), but you'll have availability zone support in the premium tier from the first PU in all availability zone regions. 
 

articles/event-hubs/event-hubs-scalability.md

@@ -35,7 +35,9 @@ For more information about the auto-inflate feature, see [Automatically scale th
 
  [Event Hubs Premium](./event-hubs-premium-overview.md) provides superior performance and better isolation with in a managed multitenant PaaS environment. The resources in a Premium tier are isolated at the CPU and memory level so that each tenant workload runs in isolation. This resource container is called a *Processing Unit*(PU). You can purchase 1, 2, 4, 8 or 16 processing Units for each Event Hubs Premium namespace. 
 
-How much you can ingest and stream with a processing unit depends on various factors such as your producers, consumers, the rate at which you're ingesting and processing, and much more. One processing unit can approximately offer core capacity of ~5-10 MB/s ingress and 10-20 MB/s egress, given that we have sufficient partitions so that storage is not a throttling factor.  
+How much you can ingest and stream with a processing unit depends on various factors such as your producers, consumers, the rate at which you're ingesting and processing, and much more. 
+
+For example, Event Hubs Premium namespace with 1 PU and 1 event hub(100 partitions) can approximately offer core capacity of ~5-10 MB/s ingress and 10-20 MB/s egress for both AMQP or Kafka workloads.
 
 To learn about configuring PUs for a premium tier namespace, see [Configure processing units](configure-processing-units-premium-namespace.md).