Abstract
Programming development tools are a vital com- ponent for understanding the
behavior of parallel applica- tions. Event tracing is a principal ingredient to these tools,
but new and serious challenges place event tracing at risk on extreme-scale machines.
As the quantity of captured events increases with concurrency, the additional data can
over- load the parallel file system and perturb the application be- ing observed. In this
work we present a solution for event tracing on extreme-scale machines. We enhance
an I/O for- warding software layer to aggregate and reorganize log data prior to writing
to the storage system, significantly reduc- ing the burden on the underlying file system.
Furthermore, we introduce a sophisticated write buffering capability to limit the impact.
To validate the approach, we employ the Vampir tracing toolset using these new
capabilities. Our re- sults demonstrate that the approach increases the maximum
traced application size by a factor of 5x to more than 200,000 processes.
