Runtime monitoring on multicores via OASES

Nagarajan, Vijay; Gupta, Rajiv

doi:10.1145/1531793.1531798

Cited by 8 publications

(3 citation statements)

References 22 publications

(13 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Second, by running it on a single processor, several race conditions that existed when run concurrently on a multicore processor may disappear and the original sbug may not be reproducible. We enable debugging of multithreaded programs by utilizing recently proposed architectural support for monitoring multithreaded programs on multicores [20,21]. The architectural support in question exposes cache events to software, and thus all shared memory dependencies are exposed to the programmer.…”

Section: Handling Multithreaded Programsmentioning

confidence: 99%

See 1 more Smart Citation

A system for debugging via online tracing and dynamic slicing

et al. 2011

Self Cite

View full text Add to dashboard Cite

Dynamic slicing is a promising trace based technique that helps programmers in the process of debugging. In order to debug a failed run, dynamic slicing requires the dynamic dependence graph (DDG) information for that particular run. The two major challenges involved in utilizing dynamic slicing as a debugging technique are the efficient computation of the DDG and the efficient computation of the dynamic slice, given the DDG.In this paper, we present an efficient debugger, which first computes the DDG efficiently while the program is executing; dynamic slicing is later performed efficiently on the computed DDG, on demand. To minimize program slowdown during the online computation of DDG, we make the design decision of not outputting the computed dependencies to a file, instead, storing them in memory in a specially allocated fixed size circular buffer. The size of the buffer limits the length of the execution history that can be stored. To maximize the execution history that can be maintained, we introduce optimizations to eliminate the storage of most of the generated dependencies, at the same time ensuring that those that are stored are sufficient to capture the bug. Experiments conducted on CPU-intensive programs show that our optimizations are able to reduce the trace rate from 16 to 0.8 bytes per executed instruction. This enables us to store the dependence trace history for a window of 20 million executed instructions in a 16-MB buffer. Our debugger is also very efficient, yielding slicing times of around a second, and only slowing down the execution of the program by a factor of 19 during the online tracing step. Using recently proposed architectural support for monitoring, we are also able to handle multithreaded programs running on multicore processors. ‡ Indeed, our online tracing infrastructure [1], which is available for download, uses Valgrind. We chose DynamoRio for our prototype because it introduces negligible overhead when programs are run without any instrumentation. Valgrind, on the other hand, is designed for building heavyweight tools and has a robust shadow memory support, but introduces significant runtime overhead even when programs are run without any instrumentation.

show abstract

Section: Handling Multithreaded Programsmentioning

confidence: 99%

“…When a multithreaded program is run on a multicore, the computed dependencies can face correctness issues caused by the races between data and meta-data accesses. We show how recently proposed architectural support for monitoring parallel programs running on multicores [20,21] can be used to safely and efficiently debug multithreaded programs.…”

mentioning

confidence: 99%

A system for debugging via online tracing and dynamic slicing

et al. 2011

Self Cite

View full text Add to dashboard Cite

show abstract

“…On the one hand, new and efficient monitoring algorithms can be developed to reduce this limitation. On the other hand, the use of multi‐core platforms [31, 32] can also reduce this limitation because it can make the monitoring cost acceptable.…”

Section: Experimental Validationmentioning

confidence: 99%

Web services property sequence chart monitor: a tool chain for monitoring BPEL‐based web service composition with scenario‐based specifications

Zhang

Leung

et al. 2013

IET softw.

View full text Add to dashboard Cite

Web service composition is a new paradigm to develop distributed and reactive software-intensive systems. Owing to the autonomous nature of basic services, the validation of composite service must be extended from design-time to run-time. Here, the authors describe a novel tool chain called web services property sequence chart monitor to monitor temporal, timing and probabilistic properties in composite service based on scenario-based property specifications called property sequence chart, timed property sequence chart and probabilistic timed property sequence chart, respectively. The tool chain provides a completely graphical front-end that eliminates the need to deal with any particular textual and logical formalism. Furthermore, the framework and implementation detail of the tool chain are also presented. Finally, the feasibility and usability of the tool have been validated by the case studies and performance measurement.

show abstract

Efficient dynamic program monitoring on multi-core systems

Zhai

2011

Journal of Systems Architecture

View full text Add to dashboard Cite

Runtime monitoring on multicores via OASES

Cited by 8 publications

References 22 publications

A system for debugging via online tracing and dynamic slicing

A system for debugging via online tracing and dynamic slicing

Web services property sequence chart monitor: a tool chain for monitoring BPEL‐based web service composition with scenario‐based specifications

Efficient dynamic program monitoring on multi-core systems

Contact Info

Product

Resources

About