Thesis Proposal: Regional Garbage Collection

The ongoing shift from 32-bit to 64-bit processor environments forces garbage collectors to cope with the larger heaps made possible by the increased address space. On 32-bit machines, generational collectors that occasionally pause to collect the entire heap work well enough for many applications, but that paradigm does not scale up because collection pauses that take time proportional to the total heap size can cause alarming or annoying delays [18], even if they occur rarely. Real-time, incremental, and concurrent collectors eliminate such delays but introduce complex invariants to the memory management system. Maintenance of these invariants during execution reduces application throughput. Also, supporting these invariants increases the complexity of compilers, run-time infrastructure, and low-level libraries (e.g. client modules written in C and linked via a foreign function interface). In non-real-time operating environments, real-time garbage collection is overkill. It would be better to preserve the throughput of generational collectors while eliminating the long delays associated with major collections. Implementors would also appreciate a system with hard bounds on pause times, but simpler than contemporary real-time memory managers. Will Clinger (my thesis advisor) and I have designed, and I am implementing, a regional garbage collector that collects bounded subsets of the heap during every collection, thus disentangling the worstcase mutator pause time from the total heap size. The design isolates collection-related work not directly associated with moving objects; a separate processor core can perform such work without direct interaction with the mutator thread. The three primary goals of the design are: