<  Back to the Polytechnique Montréal portal

Wait analysis of distributed systems using kernel tracing

Francis Giraldeau and Michel R. Dagenais

Article (2016)

[img]
Preview
Published Version
Terms of Use: IEEE OA Publishing Agreement.
Download (483kB)
Cite this document: Giraldeau, F. & Dagenais, M. R. (2016). Wait analysis of distributed systems using kernel tracing. IEEE Transactions on Parallel and Distributed Systems, 27(8), p. 2450-2461. doi:10.1109/tpds.2015.2488629
Show abstract Hide abstract

Abstract

We propose a new class of profiler for distributed and heterogeneous systems. In these systems, a task may wait for the result of another task, either locally or remotely. Such wait dependencies are invisible to instruction profilers. We propose a host-based, precise method to recover recursively wait causes across machines, using blocking as the fundamental mechanism to detect changes in the control flow. It relies solely on operating system events, namely scheduling, interrupts and network events. It is therefore capable of observing kernel threads interactions and achieves user-space runtime independence. Given a task, the algorithm computes its active path from the trace, which is presented in an interactive viewer for inspection. We validated our new method with workloads representing major architecture and operating conditions found in distributed programs. We then used our method to analyze the execution behavior of five different distributed systems.We found that the worst case tracing overhead for a distributed application is 18 percent and that the typical average overhead is about 5 percent. The analysis implementation has linear runtime according to the trace size.

Uncontrolled Keywords

Performance measurement, operating systems, tracing, reverse engineering

Open Access document in PolyPublie
Subjects: 2700 Technologie de l'information > 2700 Technologie de l'information
2700 Technologie de l'information > 2715 Optimisation
2700 Technologie de l'information > 2720 Logiciel de systèmes informatiques
Department: Département de génie informatique et génie logiciel
Research Center: Non applicable
Funders: CRSNG/NSERC, EfficiOS, Ericsson Software Research
Date Deposited: 04 May 2018 16:35
Last Modified: 24 Oct 2018 16:13
PolyPublie URL: https://publications.polymtl.ca/3078/
Document issued by the official publisher
Journal Title: IEEE Transactions on Parallel and Distributed Systems (vol. 27, no. 8)
Publisher: IEEE
Official URL: https://doi.org/10.1109/tpds.2015.2488629

Statistics

Total downloads

Downloads per month in the last year

Origin of downloads

Dimensions

Repository Staff Only