"Event Stream Processing (ESP) is a well-established approach for low-latency data processing enabling users to quickly react to relevant situations in soft real-time. In order to cope with the huge amount of data being generated each day and to cope with fluctuating workloads
from data sources such as twitter and facebook, such systems must be highly scalable and elastic. Hence, ESP systems are typically long running applications deployed on several hundreds of nodes in either dedicated data centers or cloud environments such as Amazon EC2. In such
environments, nodes are likely to fail due to software aging, process or hardware errors whereas the unbounded stream of data asks for continues processing.
Active replication and rollback recovery based on checkpoints and in-memory logging (upstream backup) are two commonly used approaches in order to cope with such failures in ESP systems. However, these approaches suffer either from a high resources footprint, low throughput
or unresponsiveness due to long recovery times.
In this status talk, I will present related work in the area of ESP systems with the focus on fault tolerance and discuss the advantages and disadvantages of these works. I will also present my research contributions made so far, in particular, the new ways to reduce the run-time and resource overhead of the aforementioned approaches as well as hybrid approaches for guaranteeing low latency and high throughput. I will conclude the talk with a sketch of the road map for the remainder
of my doctoral thesis."
Contato do palestrante: andre.martin
Nenhum comentário:
Postar um comentário