SYMBIOMON: A High Performance, Composable Monitoring Service for Online Application Introspection and Adaptation
Event Type
ACM Student Research Competition: Graduate Poster
ACM Student Research Competition: Undergraduate Poster
Posters
In-Person Only
TP
XO / EX
TimeThursday, 18 November 20218:30am - 5pm CST
LocationSecond Floor Atrium
DescriptionThe construction of high-performance scientific software has shifted from a traditional monolithic message-passing interface (MPI) executable model to a coupled, services-style model in which simulations run alongside a host of distributed HPC data services within the same batch job allocation. Performance analysis of such a distributed system requires collecting, monitoring, aggregating, and exporting performance data from multiple sources online. We propose SYMBIOMON, a low-overhead monitoring service built by composing high-performance microservices. Compared to other monitoring services, SYMBIOMON stands apart in its choice to build and extend components developed using an existing HPC framework instead of building everything from scratch. This design choice ensures that SYMBIOMON is more maintainable, offers significantly more flexibility in resource allocation, and enables the user to toggle functionality as needed freely. SYMBIOMON is currently available online for experimental use. This poster will be presented in person in the poster session.
Archive view
