Conference paper Open Access
el Khaldi Ahanach, Elias;
Koulouzis, Spiros;
Zhao, Zhiming
When executing scientific workflows in a distributed
environment, anomalies of the workflow behavior are often
caused by a mixture of different issues, e.g., careless design
of the workflow logic, buggy workflow components, unexpected
performance bottlenecks or resource failure at the underlying
infrastructure. The provenance information only defines data
evolution at the workflow level, which does not have an explicit
connection with the system logs provided by the underlying
infrastructure. Analyzing provenance information and apposite
system metrics requires expertise and a considerable amount of
manual effort. Moreover, it is often time-consuming to aggregate
this information and correlate events occurring at different levels
in the infrastructure. In this paper, we propose an architecture
to automate the integration among the workflow provenance
information with the performance information collected from
infrastructure nodes running workflow tasks. Our architecture
enables workflow developers or domain scientists to effectively
browse workflow execution information together with the system
metrics, and analyze contextual information for possible anomalies.
Name | Size | |
---|---|---|
2019.conference.workshop.iwsg-cam.pdf
md5:20ab8e0bfc5f7dd1bd094fe5fa1b4991 |
633.3 kB | Download |
All versions | This version | |
---|---|---|
Views | 548 | 548 |
Downloads | 65 | 65 |
Data volume | 41.2 MB | 41.2 MB |
Unique views | 531 | 531 |
Unique downloads | 63 | 63 |