THE INSTITUTE OF ELECTRICAL AND ELECTRONICS ENGINEERS, INC.

COMMUNICATIONS & VEHICULAR TECHNOLOGY SOCIETIES

 2017 TECHNICAL LUNCHEON PROGRAM

Technical Presentation:

Highly Accurate Simulations of Big-Data Clusters for System Planning and Optimization
– Mike Riess, Strategic Business Development Manager, Intel Corp.

DATE: Tuesday 21 February 2017

TIME: Luncheon starts at 11:30 a.m.
Main Presentation is from 12:00-1:00p.m.

**MEETING LOCATION**
Cafe Max
1600 Alma Road Richardson, TX 75081
Additional parking behind restaurant.

COST: Lunch
Students and IEEE Life Members: $5
IEEE Members: $10
Non-Members: $15

Please RSVP to Judah Epstein

Abstract:

“Highly Accurate Simulations of Big-Data Clusters for System Planning and Optimization”

Using Intel’s CoFluent Technology for Big Data to model and simulate clusters can significantly improve the accuracy of optimizations for performance versus component cost. Using Intel’s Rack Scale Design can further improve performance for various cluster configurations. The combination of technologies can substantially increase the accuracy of pre-planning cluster architecture, help optimize component costs for your business needs, and help minimize total cost of ownership.

Performance issues in the storage system can affect the performance of all applications that run on top of that storage system. In this paper, we demonstrate some of the capabilities of Intel’s CoFluent technology for Big Data (Intel’s CoFluent technology) that improve system throughput and performance. Testing was performed with Intel’s Rack Scale Design hardware. This hardware allows for automated, software-based inventory of datacenter resources and assembly of purpose-built servers from disaggregated pools of resources.

Intel CoFluent technology is a planning and optimization solution that identifies performance issues in hardware and software, such as in a cluster of servers. For example, using Intel CoFluent technology, we can examine different hardware and software configurations to find the best solution for performance versus component cost for a Big Data cluster. When paired with Intel Rack Scale Design hardware, configurations can be easily adjusted to achieve maximum resource utilization and help minimize total cost of operations.

For this paper, we used Intel CoFluent technology for Big Data to model, simulate, and compare an OpenStack Swift*1-based object storage system on an Intel Rack Scale Design. By using Intel CoFluent technology, we were able to identify the performance characteristics (including issues) of different object sizes. This allowed us to see how performance changed with different hardware configurations. Validation of the model shows a simulation accuracy that averages 95% or higher.2

Our work shows the value of using Intel CoFluent Technology to optimize cluster performance versus cost, and build a more balanced system of compute, storage, and networking components to better handle the different types of workloads. Thanks to Intel Rack Scale Design and its ability to easily configure network resources, we have been able to significantly improve the throughput of a Swift-based storage system over a fixed 10GbE infrastructure of large objects (>1MB). Specifically, our results demonstrate an excellent 3x throughput improvement in a 25Gb fabric configuration, and an even greater throughput improvement of up to 5x in a 50Gb fabric configuration.

Bio:

Mike is responsible for enabling and accelerating system modeling and simulation technologies and products growth by developing strategic business relationships with Intel internal groups/BU’s and external customers in the America’s and Europe. He is engaged with large worldwide companies, for example Ericsson, HP/HPE, Dell, Cerner, Cern Labs, and many more. Mike has a strong back ground in Big Data Analytics and Cluster Planning, and Performance Optimization utilizing Intel CoFluent Technology for Big Data for customers like Ericsson, HPE, and Dell. He also supports the Wind River SIMICS product for external customers such as Microsoft, Apple, Dell, HP, and Lenovo. Mike has excellent knowledge/background in IoT in working with GE, Accenture, Kontron, and others on IoT End to End simulation capabilities with Intel CoFluent Technology for IoT.

Mike was previously a Strategic Relationship Manager in the Enterprise Solution Sales Group of Intel SMG from 2006 -2014. He provided global account management strategies and implementation for Raytheon and General Dynamics with an emphasis in the areas of Cloud, HPC, Big Data Analytics, Data Center Software solutions, HaDoop Apache Distribution, Lustre File System, Crypto, and McAfee Security software. Prior Mike was the District Sales Manager and Channel Manager for the Intel Embedded Comm’s Group from 2000 to 2006. Effectively delivered management and support for district sales in ECG, and served as National Channel Sales Manager for the Embedded and Communications Group. Additional focus on the management and oversight of embedded processors around cPCI, ATCA solutions for communications and military applications. Mike also spent 14 years with Hewlett Packard prior to Intel, as Worldwide OEM Account Manager for Compaq and Dell.

Mike studied executive management/engineering management, graduating with Honors from SMU with a Master’s Degree in Engineering Management and Business. He received his BSEE from Washington University in St. Louis. Mike is married and enjoys spending time with his family.