<<< Previous speaker next speaker >>>

Chief Architect - EMEA Peter Holditch, Azul Systems

Chief Architect - EMEA Peter  Holditch Peter is the Chief Architect for Azul EMEA, working closely with both customers and Azul engineers in order to ensure customer requirements are met and their VM based applications are successfully integrated into the company's compute pool solution; Peter is based in the UK. Prior to joining Azul in 2005, Peter spent nine years at BEA Systems in both pre-sales and post-sales consultancy roles. His role at BEA spanned from providing technical advice to prospective customers about BEA's complete product portfolio, from Tuxedo through the CORBA OTM to the WebLogic Platform as well as helping customers to design and implement solutions based on the company's industry-leading middleware based systems. Before joining BEA, Peter led a small research and development team at Racal-Airtech, architecting and building supporting software and firmware for tamper-resistant hardware crypto devices. Prior to Racal-Airtech, Peter worked in research and development at Groupe Bull on the Tuxedo product. He helped design and implement recovery processing in the OSITP gateway, added NetBIOS networking support and did various porting and tuning work. Peter is also well published in the WebLogic Developers Journal and other highly publicized IT-related publications

Presentation: "Performance Considerations in Concurrent Garbage-Collected Systems"

Time: Tuesday 14:40 - 15:30

Location: Musikhuset C 103

Abstract:

This session examines specific considerations introduced by the recent availability of various concurrent (non-stop-the-world) garbage-collected environments. An overview of important modeling and tuning considerations unique to concurrent garbage collection (GC) specifically covers the delicate interplay between GC cycle time, object allocation rates, available free heap, and garbage collection policy.

The presentation discusses and explains relevant GC terminology and phrases common in concurrent and mostly concurrent GC, focusing on their effects and relationship to metrics such as heap size, real and effective live set size, and object allocation rates. These include concurrent and mostly concurrent marking, live set and card marking, generational operation, and compaction.

The session includes specific examples of concurrent GC behavior with a wide variety of heap sizes, live set sizes, and allocation rates. It demonstrates the sampling of behavior across a characterized range, from idle all the way to the "collapse" point of a certain configuration. It also shows results based on heap sizes and live set sizes from 1 Gbyte to 300 Gbytes as well as allocation rates from "idle" all the way up to 30 Gbytes per second.