Distributed performance monitoring: methods, tools, and applications

Hofmann, Richard; Klar, Rainer; Mohr, Bernd; Quick, Andreas; Siegle, Markus

doi:10.1109/71.285605

Cited by 59 publications

(19 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A sensor trigger policy may either be event-driven or time-driven (these correspond to tracing and sampling respectively) [6]. In an eventdriven policy, instrumentation data is collected synchronously with the occurrence of an event, whereas in a time-driven policy the data is collected asynchronously.…”

Section: Software Instrumentationmentioning

confidence: 99%

An entropy-based algorithm for time-driven software instrumentation in parallel systems

Ozmen¹

2006

Proceedings 20th IEEE International Parallel &Amp; Distributed Processing Symposium

View full text Add to dashboard Cite

show abstract

Section: Software Instrumentationmentioning

confidence: 99%

An entropy-based algorithm for time-driven software instrumentation in parallel systems

Ozmen¹

2006

Proceedings 20th IEEE International Parallel &Amp; Distributed Processing Symposium

View full text Add to dashboard Cite

show abstract

“…Still further, because the collected data are usually large there is also a need for a tradeoff analysis between collection overhead and the accuracy of the model. Moreover, appropriate techniques have to be developed, so that it can be applied to ensure the quality of the derived workload model [90], [91]. While they are more accurate models of workloads, trace driven models incur overhead in terms of instrumentation setup and the amount of collected data.…”

Section: Trace-driven or Measurementmentioning

confidence: 99%

Capacity metric for chip heterogeneous multiprocessors

Otoom

Paul

2011

Proceedings of the Seventh IEEE/ACM/IFIP International Conference on Hardware/Software Codesign and System Synthesis

View full text Add to dashboard Cite

The primary contribution of this thesis is the development of a new performance metric, Capacity, which evaluates the performance of Chip Heterogeneous Multiprocessors (CHMs) that process multiple heterogeneous channels. Performance metrics are required in order to evaluate any system, including computer systems. A lack of appropriate metrics can lead to ambiguous or incorrect results, something discovered while developing the secondary contribution of this thesis, that of workload modes for CHMsor Workload Specific Processors (WSPs).For many decades, computer architects and designers have focused on techniques that reduce latency and increase throughput. The change in modern computer systems built around CHMs that process multi-channel communications in the service of single users calls this focus into question. Modern computer systems are expected to integrate tens to hundreds of processor cores onto single chips, often used in the service of single users, potentially as a way to access the Internet. Here, the design goal is to integrate as much functionality as possible during a given time window. Without the ability to correctly identify optimal designs, not only will the best performing designs not be found, but resources will be wasted and there will be a lack of insight to what leads to better performing designs. To address performance evaluation challenges of the next generation of computer systems, such as multicore computers inside of cell phones, we found that a structurally different metric is needed and proceeded to develop such a metric.In contrast to single-valued metrics, Capacity is a surface with dimensionality related to the number of input streams, or channels, processed by the CHM. We develop some fundamental Capacity curves in two dimensions and show how Capacity shapes reveal interaction of not only programs and data, but the interaction of multiple data streams as they compete for access to resources on a CHM as well. For the analysis of Capacity surface shapes, we propose the development of a demand characterization method in which its output is in the form of a surface. By overlaying demand surfaces over Capacity iii surfaces, we are able to identify when a system meets its demands and by how much.Using the Capacity metric, computer performance optimization is evaluated against workloads in the service of individual users instead of individual applications, aggregate applications, or parallel applications. Because throughput was originally derived by drawing analogies between processor design and pipelines in the automobile industry, we introduce our Capacity metric for CHMs by drawing an analogy to automobile production, signifying that Capacity is the successor to throughput. By developing our Capacity metric, we illustrate how and why different processor organizations cannot be understood as being better performers without both magnitude and shape analysis in contrast to other metrics, such as throughput, that consider only magnitude.In this work, we make the following major ...

show abstract

“…According to Hofmann et al [4], both monitoring and modeling rely on a common abstraction of a system's dynamic behavior, the event, and therefore can be integrated to one comprehensive methodology for measurement, validation and evaluation.…”

Section: Event As the Integration Elementmentioning

confidence: 99%