This framework has been developed around the idea of the serverless computing and containers, that is, to only allocate for the resources an application needs at any moment, and in the same way, to bill for such resources. All the resource monitoring is perform by using BDWatchdog.

By deploying applications on containers around this autoscaling platform, the user is given a serverless environment where the resources allocated vary over time to adjust to those actually used, all the while maintaining a virtual environment that is really close to a virtual machine or traditional cloud instance.

More specifically, this tools is able to change the resource limits applied to a container, or a group of containers, in real time and in an automatic way without the need for any user intervention.

BDWatchdog is a framework to provide both per-proces resource monitoring (CPU, memory, disk and network), as well as profiling information. All of this information is generated, processed and stored in real time by using a time series database (OpenTSDB) for monitoring and a document-based database (mongodb) for profiling. The architecture used is also scalable to support large clusters.

The end result of using this framework is two-fold:

• Time series detailing how the resources were used along the execution time, with the possibility of filtering by using different tags like host, command, as well as performing aggregation operations like summatory o average.

• Interactive flame graphs showing the percentage of time spent in a specific Java class, being subsequently subdivided across its calls.

This platform was designed from the start with novel concepts to specifically enhance Big Data workloads in two ways:

• Docker containers are used instead of virtual machines backed by hypervisors.
• Thanks to the use of Mesos as the resource scheduler, a disk-aware capability is implemented and added. This feature gives the users the option of choosing disks as dedicated resources in the same way as CPUs and memory.

I strongly believe that computing science has the duty of serving as a tool to aid research that tackles society's current biggest challenges, among which we could include climate change, food and water security or health.

Volunteering computing is a type of distributed computing that has been going on since the 90's (with SETI as its first project) and that allows users of the whole world to connect their computers to a network in order to donate their computing resources, thus creating a cluster. This cluster offers researchers of any country or institution equal and usually free access to a pool of resources, with the only condition that any research result has to be given back to the community.