We describe the PerDiS persistent distributed store and its garbage collection algorithm. The PerDiS store behaves like an object-oriented persistent shared memory, and is accessed transactionally. Applications get direct access to persistent data in their own memory, and use the usual C/C++ pointer dereferencing and assignment to navigate and modify the object graph. PerDiS provides persistence by reachability based on the Larchant algorithm. We focus on the issues of implementation for large-scale sharing. The main problems we face involve concurrency, ordering and consistency. We also address performance/modularity trade-offs