Around the Storage Block
cancel
Showing results for 
Search instead for 
Did you mean: 

An Introduction to HPE Elastic Platform for Analytics Sizing Tool

StorageExpert

 

Meet the HPE Elastic Platform for Analytics Sizing Tool—designed to provide an approximate bill of materials for both traditional and asymmetric clusters based on user inputs.

HPE EPA Sizing Tool_Big Data_blog.jpgThe HPE Elastic Platform for Analytics (EPA) is a modular infrastructure foundation designed to address the need for a scalable multi-tenant platform by enabling independent scaling of compute and storage through infrastructure building blocks that are optimized for density and running disparate workloads. 

HPE supports two different types of Hadoop cluster deployments under this platform:

  1. Workload and Density Optimized (WDO) environments allow for the independent scaling of compute and storage mentioned earlier, and are built on faster speed networks. WDO environments will typically have HPE Apollo 2000 for compute and HPE Apollo 4200 for the storage tier.
  2. Balanced and Density Optimized (BDO) environments are traditional cluster deployments, scaling compute and storage together. Traditional deployments are typically based on HPE ProLiant DL380 servers, with density optimized environments using HPE Apollo 4200 servers

The HPE EPA Sizing Tool is a sizer that can provide an approximate bill of materials for both traditional and asymmetric clusters based on a series of inputs from a user. You only need to know the capacity required for the cluster in order to produce BOMs containing each server type, networking, rack options, software and services. Additional information can be provided to the tool, but even with limited knowledge it is possible to get an approximate BOM for clusters of various shapes and sizes.

The tool was developed by the HPE Big Data Engineering team, and through partnership with the HPE Sizers and Tools team was brought under their umbrella of sizers in March 2017.  It is available here: www.hpe.com/info/sizers.

The sizer will allow for the creation of a new solution or the loading of a previously saved solution. The sizer also contains links to reference architectures and other white papers containing information regarding specific Hadoop distributions.  It also provides links to more general papers and articles providing additional information on how to leverage the advanced features of the HPE server family in configuring EPA business solutions.HPE EPA Sizing Tool_figure 1J.jpg

Figure 1. HPE EPA Sizing Tool Home Screen

Reference Architectures within the tool contain BOMs that can be further customized within the tool or they can be viewed with your browser of choice or exported into a spreadsheet or sent via email.HPE EPA Sizing Tool_figure 2J.jpg

Figure 2. HPE EPA Sizing Tool Reference Architecture view

Learn more about the HPE EPA Sizer Tool

Custom solutions can also be built with the tool. As mentioned earlier, it is possible to produce a BOM with limited information, but the tool will present a series of inputs allowing a user to specify additional detail regarding disk capacity, compute performance, Hadoop services, hardware configuration of the different server types, software licenses, network speed and services. After finishing the interview, a solution is provided containing both a traditional cluster architecture and an asymmetric (WDO) cluster architecture. A single-page summary for each type of cluster is provided, as well as a side by side comparison. Either solution can be customized further if necessary.

Configuration details for each solution are presented providing the design requirements entered during the interview, the details for the configuration of each server type and BOMs for each that can be viewed via browser, word and pdf file types. They can also be emailed.

Several categories of metrics data for each solution type are also provided. Metrics include (but are not limited to) total cost, performance, capacity, density and cost metrics relating to performance and power. Some of the metrics are customizable, allowing for the exclusion or inclusion of specific node types for WDO solutions. 

Graphical representations of the solutions are available that will open in a separate window providing additional detail per node type, a view of the front and rear of the solutions that is exportable into Visio and a BOM listing cost breakdowns between hardware and services.

In the coming months we hope to add next-generation hardware platforms and new reference architectures as they become available. Check back in the future for more information.

We hope you will find the HPE EPA Sizing Tool useful and look forward to your continued feedback and support.

Brian Richard Big Data HPE.jpg

 Meet Around the Storage Block blogger Brian Richard, Solution Architect, ESP Database and Big Data Solutions Engineering, HPE.

 

0 Kudos
About the Author

StorageExpert

Our team of Hewlett Packard Enterprise storage experts helps you to dive deep into relevant infrastructure topics.

Labels
Events
28-30 November
Madrid, Spain
Discover 2017 Madrid
Join us for Hewlett Packard Enterprise Discover 2017 Madrid, taking place 28-30 November at the Feria de Madrid Convention Center
Read more
HPE at Worldwide IT Conferences and Events -  2017
Learn about IT conferences and events  where Hewlett Packard Enterprise has a presence
Read more
View all