Attempting to initiate a marking cycle when allocating a humongous object can, if a marking cycle is successfully initiated by another thread, result in the allocating thread spinning until the marking cycle is complete. Eliminate a deadlock between the main ConcurrentMarkThread, the SurrogateLocker thread, the VM thread, and a mutator thread waiting on the SecondaryFreeList_lock (while free regions are going to become available) by not manipulating the pending list lock during the prologue and epilogue of the cleanup pause.
Reviewed-by: brutisso, jcoomes, tonyp
Revamp of the mechanism that chooses old regions for inclusion in the CSet. It simplifies the code and introduces min and max bounds on the number of old regions added to the CSet at each mixed GC to avoid pathological cases. It also ensures that when we do a mixed GC we'll always find old regions to add to the CSet (i.e., it eliminates the case where a mixed GC will collect no old regions which can happen today).
Reviewed-by: johnc, brutisso
Replace calls to os::javaTimeMillis() that are used to update the milliseconds since the last GC to an equivalent that uses a monotonically non-decreasing time source.
Reviewed-by: ysr, jmasa
If we try to schedule an initial-mark GC in order to explicit start a conc mark cycle and it gets pre-empted by antoher GC, we should retry the attempt as long as it's appropriate for the GC cause.
Reviewed-by: brutisso, johnc
Some minor profile based optimizations. Reduce the number of branches and branch mispredicts by removing some virtual calls, through closure specalization, and refactoring some conditional statements.
Reviewed-by: brutisso, tonyp
Re-enable survivors during the initial-mark pause. Afterwards, the concurrent marking threads have to scan them and mark everything reachable from them. The next GC will have to wait for the survivors to be scanned.
Reviewed-by: brutisso, johnc
Remove the separate counting phase of concurrent marking by tracking the amount of marked bytes and the cards spanned by marked objects in marking task/worker thread local data structures, which are updated as individual objects are marked.
Reviewed-by: brutisso, tonyp
During an initial mark pause, signal the Concurrent Mark thread after the pause output from PrintGC/PrintGCDetails is complete.
Reviewed-by: tonyp, brutisso
There is a high number of mispredicted branches associated with calling BitMap::iteratate() from within CMBitMapRO::iterate(). Implement a version of CMBitMapRO::iterate() directly using inline-able routines.
Reviewed-by: tonyp, iveresov
This change simplifies the interaction between GC and concurrent marking. By disabling survivor spaces during the initial-mark pause we don't need to propagate marks of objects we copy during each GC (since we never need to copy an explicitly marked object).
Reviewed-by: johnc, brutisso
Store the "next chunk start index" in the length field of the to-space object, instead of the from-space object, so that we can always reliably read the size of all from-space objects.
Reviewed-by: johnc, ysr, jmasa
Parallelize the removal of self forwarding pointers etc. by wrapping in a HeapRegion closure, which is then wrapped inside an AbstractGangTask.
Reviewed-by: tonyp, iveresov
Introduce a flag that is set when a heap expansion attempt during a GC fails so that we do not consantly attempt to expand the heap when it's going to fail anyway. This not only prevents the excessive ergo output (which is generated when a region allocation fails) but also avoids excessive and ultimately unsuccessful expansion attempts.
Reviewed-by: jmasa, johnc
Change variables representing the number of GC workers to uint from int and size_t. Change the parameter in work(int i) to work(uint worker_id).
Reviewed-by: brutisso, tonyp
Serialize the worker threads that are generating output during parallel heap verification to make sure the output is consistent.
Reviewed-by: brutisso, johnc, jmasa
Replaces calls to os::javaTimeMillis(), which does not (and cannot) guarantee monotonicity, in GC code to an equivalent expression that uses os::javaTimeNanos(). os::javaTimeNanos is guaranteed monotonically non-decreasing if the underlying platform provides a monotonic time source. Changes in OS files are to make use of the newly defined constants in globalDefinitions.hpp.
Reviewed-by: dholmes, ysr
Running G1 with ParallelGCThreads==0 results in various crashes and asserts. Most of these are caused by unguarded references to the worker threads array or an incorrect number of active workers.
Reviewed-by: jmasa, tonyp
Renamed partially-young GCs as mixed and fully-young GCs as young. Change all external output that includes those terms (GC log and GC ergo log) as well as any comments, fields, methods, etc. The changeset also includes very minor code tidying up (added some curly brackets).
Reviewed-by: johnc, brutisso
Cache workers' calculated starting heap region, used for parallel iteration over the collcection set, for subsequent reuse.
Reviewed-by: tonyp, brutisso
As a result of the changes for 4965777, the G1 reference field scanning closure could be applied to the discovered field of a reference object twice. The failing assert is too strong if the result of the first application of the closure is stolen, and the referenced object, evacuated by another worker thread.
Reviewed-by: ysr, tonyp
