Amazon EC2 makes it easy to get a large number of servers on which to run MySQL, but there are many choices to be made about the server and storage to use. There are 5 types of servers: small, large, extra-large, high-cpu medium and high-cpu extra-large. There are at least two types of storage: local disk and EBS. Finally, the servers use virtualization and both server and network resources are shared with strangers.
This session presents benchmark results that explore the performance possible with MySQL on a variety of EC2 configurations. It uses OLTP and data warehouse workloads to measure best, average and worst case performance. Results are provided for long-running tests to determine whether performance varies significantly over time which is always a concern when resources are shared. It also provides results for patched versions of MySQL.
Results focus on benchmark throughput, IO throughput and latency and SMP scalability.
Mark lead the MySQL Engineering team at Google for 2.5 years. His current focus is on making MySQL perfect. He has more than 13 years of database internals experience at Informix, Oracle and now Google. He has an M.S. in Computer Science from the University of Wisconsin-Madison. He maintains a large MySQL patch at code.google.com and a smaller patch at launchpad.net. His blog is at mysqlha.blogspot.com.
For information on exhibition and sponsorship opportunities at the conference, contact Sharon Cordesse at scordesse@oreilly.com
Download the MySQL Sponsor/Exhibitor Prospectus
Download the Media & Promotional Partner Brochure (PDF) for information on trade opportunities with O'Reilly conferences or contact mediapartners@ oreilly.com
For media-related inquiries, contact Maureen Jennings at maureen@oreilly.com
To stay abreast of conference news and to receive email notification when registration opens, please sign up for the MySQL Conference newsletter.
View a complete list of MySQL contacts.