Julien Danjou

Learn how to scrutinize your Python application in order to optimize them and make them run faster.

Getting inside knowledge of how your Python application runs is critical in order to achieve the best performance. Profiling is a mean to achieve this: by gathering all the runtime information available about the execution of your program, you might be able to understand how to optimize it. However, profiling running code in production might be a real challenge as it requires the profiler to be noninvasive and having low overhead.

Therefore, to profile production services, statistical profiling is the favorite analysis method. By regularly checking your program activity, you’ll be able to find production code bottlenecks down to the line of code. Profiling services that are running with real workload makes sure that you are collecting valuable data and that you are not guessing what the performance barrier might be.

This talk explains how it’s possible to build a statistical profiler that collects information about CPU time usage, memory allocation, and other information — all that while respecting the need for low overhead, data export format, and granularity. We’ll dig into some of the operating systems and CPython internals to understand how to build the best profiler possible.

Gnocchi is a time series database written in Python, that has been created in the context of the OpenStack cloud computing project. It offers highly-scalable data storage for measurements and provides access to its data via a REST API. In this lecture, we'll discuss the features the project is offering to its users, and how they can easily be leveraged in any application. In a second part, we'll see how the project has been built to scale, how Python was leveraged and made scalable.

Session with the GNU Guile and LUA communities

Session with the GNU Guile and LUA communities

Other people: Andy Wingo Christopher Webber Ludovic Courtès Hisham Muhammad Etiene Dalcol

During the year 2008, the awesome window manager jumped in and picked a programming language to allow its users to extend their configuration beyond the limit of the possible. History shows that Lua was picked and Guile completely ignored. Fast forward 7 years later: awesome is still used by tens of thousands of geeks around the globe who write Lua every day. This talk is going to relate how awesome ended up with Lua, how wonderful and terrible it was, and how and why Guile was discarded.

During the year 2008, the awesome window manager jumped in and picked a programming language to allow its users to extend their configuration beyond the limit of the possible. History shows that Lua was picked and Guile completely ignored. Fast forward 7 years later: awesome is still used by tens of thousands of geeks around the globe who write Lua every day. This talk is going to relate how awesome ended up with Lua, how wonderful and terrible it was, and how and why Guile was discarded.

Ceilometer is an OpenStack incubated project which started in April 2012 with the goal to provide a unique interface point to provide measurement in OpenStack. Our purpose for measurement started with a focus on metering (for billing) and has since been extended to other targets such as monitoring and alerting. This project is a collaboration of a wide variety of actors.

After a brief introduction of the project past and future, this talk will introduce the audience to the project's architecture before digging into how and why they can contribute to its future.

Other people: Nick Barcet Eoghan Glynn