For some months ago (october 2008) I wrote an abstract for a paper to present at the HOTSOS 2009 symposium. Although I hoped I was selected to give the presentation, I was not selected by Hotsos. This was a pitty but looking at the people and the presentations who made it to the agenda of the HOTSOS 2009 symposium, it would have been very special to be there also. Due to the high quality of the sysmposium and the fact that it is the place to be for every performance geek out there, I planned together with my collegae Marco Gralike a trip to the symposium this year only as an attendee.
Last week I received unexpectedly an email from Cary Millsap with a very special opportunity within. Cary asked me if I was still interested in presenting at the comming symposium and although very little time I said of course YES. So although late I was added to the HOTSOS 2009 symposium agenda to give a presentation called “Practical Use of Method Gapp to Find Performance Bottlenecks for Business Processes in Complex Architectures”
I hope personal that I will give a presentation wich will be equally or even more interresting than the one I gave at the HOTSOS Symposium 2008. As a last word I really like to thank Cary Millsap for this opportunity.
It is now almost a year ago I came up with the name GAPP to promote my method “General Approach Performance Profiling”. The last couple of months I have been very busy to use the method in practice and was able to fine tune the way to gather data and do the analysis quicker and quicker.
The power of the method comes to its full exposure in situations that a lot of servers are involved and the business process are very hard to be traced in any way. The latest customer I helped with the method had a system with a hardware loadbalancer, 8 application servers, 2 database servers running 30 databases each and a NETAPP storage. In this situation I was able to pinpoint that problems in the garbage collection on the application servers was there mean issue and a second important issue was residing on a synchronization process on the NETAPP.
The used data mining made it possible to find relations in the data, which are very hard to be determined without extensive tracing. Also the capabilities of data mining to predict with a model future bottlenecks, make GAPP very powerfull. Although it is probably a pitty to tell, I had still not the time to finish my whitepaper. There is a version, but is still beta and should be more professional and enriched with more information about the practical use of the method. For now I have put it online, but be aware it is very beta.
I hope I will from this moment on, not again let you wait to get some new content on this blog.
Sunday 21 September 2008 at Oracle Open World, I had the opportunity to present my method “GAPP” once more (HOTSOS 2008 and Planboard may 2008). This time I also mentioned how the method can be used with Service Oriented Architectures (SOA). For people not knowing what “GAPP” is all about I give a small introduction to the method. I also like to tell you why I started with “GAPP” in the first place and what the added value is of the method above other methods.
“GAPP” means General Approach Performance Profiling and can be used to find out where in your architecture the most wait time variance can be explained from your business process. “GAPP” makes it possible with very little data, in higly complex technical infrastructures, still be able to find the performance bottlenecks for a specific business process. The nice thing about the method is that it is not only able to pinpoint a bottleneck which is already there, it is also able to pinpoint a future bottleneck in a normal running system. This is something what only “GAPP” can do.
What makes “GAPP” special:
- The method can analyse the full infrastructure, so from front-end to back-end
- The method is not focussing on one piece of the infrastructure, like only the database
- The method is able to predict how the response time of a business process will react on changes in involved factors
- The method is able to predict when a certain bottleneck will evolve to a real problem
The third of march 2008 I had the opportunity to present my developed performance profiling approach called “GAPP” at the HOTSOS Symposium 2008 in Dallas. “GAPP” is an abbreviation of “General Approach Performance Profiling” and is based on data mining of all kind of gathered system statistics (but also other data is possible).
The presentation went well and a lot of people attended my presentation. I got a lot of nice criticism and was questioned a lot by Dr. Neil Gunther. Before and after the presentation I had a lot of nice discussion with him and he even offered to help me make this approach even bigger. For me this was a real honor and I really was very happy with his input.
Also a lot of other “important” people attended the presentation, like Anjo Kolk, James Morle, Cary Millsap, Jeroen Evers, Toon Koppelaars and many others. I personally was very happy to have the chance to present for such an audience, and was very happy with their reactions and criticism. I personal think that the HOTSOS Symposium is “The Place” for performance in the world. Continue reading