Efficient Concurrent Mark-Sweep Cycle Collection.ppt

* * * * Efficient Concurrent Mark-Sweep Cycle Collection Daniel Frampton, Stephen Blackburn, Luke Quinane and John Zigman (Pending submission) Presented by Jose Joao CS395T - Mar 23, 2009 Outline Motivation Backup tracing Trial deletion Mark-Sweep Cycle Detection (MSCD) Results What worked and what didn’t Discussion Motivation Reference counting can directly (i.e. locally) identify garbage Low pause times Reasonable throughput (deferred , coalescing, ulterior) But it cannot reclaim circular garbage Existing general solutions are expensive: Trace the whole heap (backup tracing) Temporarily delete an object and see if the cycle collapses (trial deletion) Trial deletion Is partial mark-sweep (no roots required): find objects that are alive only because they are reachable from themselves Three phases: Assume candidate object is dead and markdecrement children recursively. Trace again from candidate object, marking incrementing if some RC is not zero, i.e. if the object is externally reachable Sweep objects with a zero count Bacon and Rajan: process candidates en masse, avoid acyclic objects, concurrent algorithm Usually less efficient than concurrent tracing Backup tracing Trace all live objects and sweep the entire heap Shortcomings: Increases pause times Concurrency for low pause times requires synchronization, e.g. write barrier Visits all objects, although some cannot be part of a cycle MSCD: base algorithm Add roots to mark queue Mark until empty mark queue Pop from queue and process (mark, scan and add children to queue) Enqueue objects subject to races (fixup set) Sweep MSCD: concurrency Builds on top of coalescing RC with a snapshot-at-the-beginning write barrier: Atomic state update to process each object only once Record all pre-mutation pointers for deferred decrement RC Record object as mutated MSCD: concurrency Black: marked and scanned Grey: marked, not yet scanned White: not yet visited C is never visited and incorrectly collected Again, C is ne