By deploying several research applications, we found that capturing usage context (e.g., CPU and memory) is highly valuable for debugging and interpreting results, even if that context information appears unrelated to the application. We have developed a general tool called SystemSens to help researchers capture usage context in their deployments in an extendible way. This paper describes and motivates the design choices underlying our tool and evaluates its overheads in terms of phone resources and data.
No takes yet. Share an insight, caveat, or question.
Falaki et al. (2011) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: