FACEBOOK DARÁ UNA CHARLA SOBRE DATAX

El próximo jueves 8 de agosto desde las 15.30 hs se realizará una charla referida a DataX, una de las estrategias que está utilizando Facebook para manejar grandes volúmenes de datos. El encuentro estará a cargo de Diego Macadar, Engineering Manager de Facebook.

La charla, que será en español, es una buena oportunidad para conocer más de esta esta técnica y  los intereses de Facebook con respecto a la informática.

La actividad, que es gratuita, se llevará a cabo en el Aula 5 de Postgrado de la Facultad.

Los interesados en participar deben inscribirse en postgrado@lidi.info.unlp.edu.ar


“DataX at Scale”

The volume of data processed by Facebook’s analytics workload has been rapidly increasing, resulting in greater compute and storage demands. We have been investigating how to use sampling as a technique offset such demand while still providing good approximate query results. In this talk, we discuss the approaches we have been using to support the computation of analytical dashboards using sampling, where approximations result in negligible visual differences of the graphs.
We discuss the challenges that this poses to approximate computation, such as the need to consider uncertainty propagation when calculating aggregated metrics. We will also show the benefits in terms of resource consumption, in both compute and storage.