7102445: G1: Unnecessary Resource allocations during RSet scanning
Add a new per-worker thread line in the PrintGCDetails output. GC Worker Other is the difference between the elapsed time for the parallel phase of the evacuation pause and the sum of the times of the sub-phases (external root scanning, mark stack scanning, RSet updating, RSet scanning, object copying, and termination) for that worker. During RSet scanning, stack allocate DirtyCardToOopClosure objects; allocating these in a resource area was causing abnormally high GC Worker Other times while the worker thread freed ResourceArea chunks.
Reviewed-by: tonyp, jwilhelm, brutisso
Acquire the pending list lock in the prologue method of G1's concurrent VM_Operation and release the lock in the epilogue() method. The locking/unlocking order of the pending list lock and the Heap_lock should match that in the prologue and epilogue methods of VM_GC_Operation.
Reviewed-by: tonyp, ysr
Add a new, separate, pointer to the base of the array of discovered reference lists and use this new pointer in places where we iterate over the entire array.
Reviewed-by: ysr, brutisso
Removed unused fields and methods, removed the G1CollectoryPolicy_BestRegionsFirst class and folded its functionality into the G1CollectorPolicy class.
Reviewed-by: ysr, brutisso, jcoomes
Integrate bsd-port/hotspot and macosx-port/hotspot changes as of 2011.09.29.
Co-authored-by: Greg Lewis <glewis@eyesbeyond.com>
Co-authored-by: Kurt Miller <kurt@intricatesoftware.com>
Co-authored-by: Alexander Strange <astrange@apple.com>
Co-authored-by: Mike Swingler <swingler@apple.com>
Co-authored-by: Roger Hoover <rhoover@apple.com>
Co-authored-by: Victor Hernandez <vhernandez@apple.com>
Co-authored-by: Pratik Solanki <psolanki@apple.com>
Reviewed-by: kvn, dholmes, never, phh
There is a race between one thread successfully forwarding and copying the klass mirror for the SoftReference class (including the static master clock) and another thread attempting to use the master clock while attempting to discover a soft reference object. Maintain a shadow copy of the soft reference master clock and use the shadow during reference discovery and reference processing.
Reviewed-by: tonyp, brutisso, ysr
Also reviewed by mikael.gerdin@oracle.com; Changed to the `` syntax instead. Also changed "source" to ".".
Reviewed-by: never, stefank, dsamersoff, rottenha
Removed the code for skipping over NULL regions in _markedRegions, replacing it with an assertion that a NULL region is never encountered; removed dead methods, remove() and remove_region(), and inlined a simplified addRegion() directly into fillCache().
Reviewed-by: brutisso, tonyp
Retry the call to fast_exception_handler_bci_for() after it returned with a pending exception. Don't cache the exception handler pc computed by compute_compiled_exc_handler() if the handler is for another (nested) exception.
Reviewed-by: kamg, kvn
ADLC generates code to prepare the register string to be printed in a char array but then calls print without the char array as an argument.
Reviewed-by: never
Co-authored-by: Greg Lewis <glewis@eyesbeyond.com>
Co-authored-by: Jung-uk Kim <jkim@freebsd.org>
Co-authored-by: Christos Zoulas <christos@zoulas.com>
Co-authored-by: Landon Fuller <landonf@plausible.coop>
Co-authored-by: The FreeBSD Foundation <board@freebsdfoundation.org>
Co-authored-by: Michael Franz <mvfranz@gmail.com>
Co-authored-by: Roger Hoover <rhoover@apple.com>
Co-authored-by: Alexander Strange <astrange@apple.com>
Reviewed-by: kvn, twisti, jrose
Abstracted way to declare that the MachNode has the effect of a call (kills caller save registers, preserves callee save registers)
Reviewed-by: twisti, never
When refactoring the code for a previous fix, a condition was not correctly negated which prevents the G1 policy from adding the correct number of old regions to the CSet when the young gen size is fixed. The changeset also fixes a small syntactical issue in g1ErgoVerbose.hpp which is causing compiler warnings.
Reviewed-by: brutisso, ysr
During remembered set scanning, the reference processor could discover a reference object whose referent was in the process of being copied and so may not be completely initialized. Do not perform reference discovery during remembered set scanning.
Reviewed-by: tonyp, ysr
Some objects may not be marked in the event of an evacuation failure in a partially young GC, during a marking cycle. Avoid this situation by not allowing partially young GCs during a marking cycle.
Reviewed-by: tonyp, ysr, brutisso
G1 now uses two reference processors - one is used by concurrent marking and the other is used by STW GCs (both full and incremental evacuation pauses). In an evacuation pause, the reference processor is embedded into the closures used to scan objects. Doing so causes causes reference objects to be 'discovered' by the reference processor. At the end of the evacuation pause, these discovered reference objects are processed - preserving (and copying) referent objects (and their reachable graphs) as appropriate.
Reviewed-by: ysr, jwilhelm, brutisso, stefank, tonyp
The desired min / max heap sizes are miscalculated at initialization when NewRatio is used. The changeset also includes an additional small change to turn a print statement into a warning.
Reviewed-by: johnc, jmasa, ysr, brutisso
As a result of the changes for 7080389, an evacuation failure during an initial mark pause may result in some root objects not being marked. Pass whether the caller is a root scanning closure into the evacuation failure handling code so that the thread that successfully forwards an object to itself also marks the object.
Reviewed-by: ysr, brutisso, tonyp
Extend the SA to recognize the G1CollectedHeap and implement any code that's needed by our serviceability tools (jmap, jinfo, jstack, etc.) that depend on the SA.
Reviewed-by: never, poonam, johnc
Fixed inconsistencies and mistakes in the young list target length calculations so that a) the calculated target length is optimal (before, it was not), b) other parameters like max survivor size and max gc locker eden expansion are always consistent with the calculated target length (before, they were not always), and c) the resulting target length was always bound by desired min and max values (before, it was not).
Reviewed-by: brutisso, johnc
If and when the reference handler thread is able to use the discovered field to link reference objects in its pending list, so will GC. In that case, GC will scan through this field once a reference object has been placed on the pending list, but not scan that field before that stage, as the field is used by the concurrent GC thread to link discovered objects. When ReferenceHandleR thread does not use the discovered field for the purpose of linking the elements in the pending list, as would be the case in older JDKs, the JVM will fall back to the old behaviour of using the next field for that purpose.
Reviewed-by: jcoomes, mchung, stefank
It introduces ergonomic decision logging in G1 for the following heuristics: heap sizing, collection set construction, concurrent cycle initiation, and partially-young GC start/end. The code has a bit of refactoring in a few places to make the decision logging possible. It also replaces alternative ad-hoc logging that we have under different parameters and switches (G1_DEBUG, G1PolicyVerbose).
Reviewed-by: johnc, ysr
