Performance Tuning Clinic (22/11)

Eyy devs !!

Next Wednesday we'll host a very interesting type of event : a performance tuning clinic.

This will be a participatory session meaning bring your questions and don’t feel shy to provide answers to others questions. Even better, if you have (non-sensitive) performance data such as garbage collection logs, do bring it along. Topic can go in many directions from why MicroServices are a performance game changer to why immutability is the wrong solution to the right question.

This event will be conducted by Kirk Pepperdine.

After getting his start in the world if super-computing, Kirk went on to the world of Java eventually becoming a Java Champion in 2006 in recognition for his work advancing the state of Java performance tuning. Since then Kirk has co-founded jClarity, a company building the next generation of performance diagnostic tooling based on JPDM, a performance diagnostic process that he developed. Additionally, he authored and delivers the original Java Performance Tuning Workshop. Kirk has written many articles and spoken at many conferences on the subject of performance tuning.

Hope to see you there :)

Register !!!!!

Hands on performance workshop (25/5)

Hi JUGgers!

Our Java & JVM Barcelona conference is almost there, but we are not going to stop just because of it, right? ;-)

One year ago we had a talk about Performance on the JVM, do you remember? Well, we thought that it was good to move on with the basics and play a little bit with software in order to settle all the concepts. That's the main reason behind this workshop, hope you will enjoy it ;-)

This introductory workshop will be driven by Galo Navarro, Guillermo Ontañón and Duarte Nunes and it is designed for developers who can write Java, Scala or any other JVM language, but have zero practical experience on performance analysis. After this workshop you'll take away hands on experience using diagnostic tools, profilers and writing micro benchmarks based on practical examples, all of which you can start applying on real projects.

The workshop will be very hands on so it's strongly advised that attendants are able to bring and use a laptop (preferably Linux or OSX.) ready to build Java projects.

About our speakers, Galo is a software engineer focused on scalability and distributed systems, mostly on the JVM. Currently working in Engineering Productivity at Schibsted, pior to that he implemented virtual networks at Midokura and social networks at Tuenti and Last.fm.

Guillermo is a software engineer specialized in systems / network / concurrent / distributed development on Linux. Java, Scala,C, C++, Python currenly working as a Staff Software Engineer in Schibsted Media Group.

Duarte Nunes is a Software Engineer working on ScyllaDB, where he develops a high performance, distributed database. He has a background in concurrent programming, distributed systems and low-latency software.

Finally, we have to thank once again to New Relic, because they have offered to host the event, and also they are going to invite us to some beers and pizzas! Thank you!

Nothing more, remember to RSVPed your seat and see you next 25th!

PS1: There are not too much free spots because this is a workshop and because of that it is not possible to have a large audience following it. Please, think twice if you are not able to come and free your spot.

PS2: Do not worry, we will announce soon the details about the pre-requisites you need in order to run the workshop smooth ;-)

Performance analysis and optimization on the JVM (26/5)

Hi JUGgers!

How are you? Hope you are doing well.

We have planned our next event, it will be Thursday 26th focused on the Performance analysis and optimization on the JVM and it will driven by Galo Navarro, software engineer at Zhilabs. 

This time this talk is aimed at developers interested in understanding the performance of applications written for the JVM. We'll try to give a broad overview of tools (from the JDK, OS to JMH, GcViewer, Flamegraphs, etc.) that can help us understand their behavior both on production and development. Using practical examples that expose common patterns we'll trace them back to decisions taken on development, discuss the cost of abstractions, coordination, etc. and consider some alternatives to alleviate them.

By the way, we would like to thank New Relic, because they have offered to host the event and also they will invite us to have some beers and pizzas after the talk to have fun and have a great networking after the presentation. 😉

Nothing more to add, remember to RSVPed your seat and see you next 26th!

Aeron: The next generation in high-performance messaging (8/10)

Hi guys !!!! We are back again !!!

This time we present an interesting event next 8th of October focused on messaging and high-performance in collaboration with other communities: FIBAlumni, ScalaBcn and Clojure Bcn.

Does TCP not meet your required latency consistently? Is UDP not reliable enough? Do you need to multicast? 

What about flow control, congestion control, and a means to avoid head of line blocking that can be integrated with the application? Or perhaps you're just fascinated by how to design for the cutting edge of performance? Maybe you have tried higher level messaging products and found they are way too complicated because of the feature bloat driven by product marketing cycles. 

Aeron takes it back-to-basics with a pure focus on performance and reliability. We have built it from the ground up with mechanical sympathy in its DNA. The data structures are lock-free, copy-free, and even persistent for our functional friends. Interaction with the media is layered so you can swap between UDP, Inifiniband, or Shared Memory as required. 

Aeron is open-source with implementations in Java and C++ that interoperate. There are no unnecessary features to bloat the implementation, yet the design is open so that it can be composed into higher level abstractions. This talk will focus on the design of Aeron and what we learned trying to achieve very consistent performance. We will explore the challenges of dealing with reliable message delivery over UDP and the data structures necessary to support transmission and retransmission in in a lock-free manner.  

Martin has over 2 decades of experience building complex and high-performance computing systems. He is most recently known for his work on Aeron and SBE. Previously at LMAX he was the co-founder and CTO when he created the Disruptor. Prior to LMAX Martin worked for Betfair, three different content companies wrestling with the world largest product catalogues, and was a lead on some of the most significant C++ and Java systems of the 1990s in the automotive and finance domains. He blogs at mechanical-sympathy.blogspot.com, and can be found giving training courses on performance and concurrency when he is not cutting code to make systems better.

Don't miss this great opportunity and come !!! Btw, be careful, this time we are not using MeetUp, please register in the eventBrite event page as the seats are limited.

See you next 8th of October!