Transparent System Call Based Performance Debugging for Cloud Computing
Source: Carnegie Mellon University
Problem diagnosis and debugging in distributed environments such as the cloud and popular distributed systems frameworks has been a hard problem. The authors explore an evaluation of a novel way of debugging distributed systems, such as the MapReduce framework, by using system calls. Performance problems in such systems can be hard to diagnose and to localize to a specific node or a set of nodes. Additionally, most debugging systems often rely on forms of instrumentation and signatures that sometimes cannot truthfully represent the state of the system (logs or application traces for example). They focus on evaluating the performance debugging of these frameworks using a low level of abstraction - system calls.