Efficient Rebuilding of Large Java Heaps From Event Traces
Sprache des Vortragstitels:
12th International Conference on Principles and Practice of Programming in Java, 2015
Sprache des Tagungstitel:
Understanding and tracking down memory-related performance problems, such as long garbage collection times and memory leaks, is a tedious task in large and complex applications. Memory profilers can support developers in this task by recording detailed traces of the application's memory behavior which can then be analyzed offline. Unfortunately, these traces can become huge, and processing them is a real challenge. If the goal is to rebuild the heap from a trace in order to analyze it, most state-of-the-art tools perform badly, because they are either too slow or provide only a coarse-grained view of the monitored application.
In this paper we present novel techniques and data structures for efficiently processing large event traces and for reconstructing the heap with only a fraction of the monitored application's memory. The reconstructed heap contains vital information about all objects, such as their addresses, their types, their allocation sites, and their allocating threads.
We also provide a detailed evaluation of our approach on 33 benchmarks, showing that we can rebuild the heap from a trace efficiently using only about 18% of the memory that was used in the monitored application.