Enable reference discovery during concurrent marking by setting the reference processor field of the concurrent marking closure. Keep reference objects on the discovered reference lists alive during incremental evacuation pauses until they are processed at the end of concurrent marking.
Reviewed-by: ysr, tonyp
This change revamps the slow allocation path of G1. Improvements include the following: a) Allocations directly to old regions are now totally banned. G1 now only allows allocations out of young regions (with the only exception being humongous regions). b) The thread that allocates a new region (which is now guaranteed to be young) does not dirty all its cards. Each thread that successfully allocates out of a young region is now responsible for dirtying the cards that corresponding to the "block" that just got allocated. c) allocate_new_tlab() and mem_allocate() are now implemented differently and TLAB allocations are only done by allocate_new_tlab(). d) If a thread schedules an evacuation pause in order to satisfy an allocation request, it will perform the allocation at the end of the safepoint so that the thread that initiated the GC also gets "first pick" of any space made available by the GC. e) If a thread is unable to allocate a humongous object it will schedule an evacuation pause in case it reclaims enough regions so that the humongous allocation can be satisfied aftewards. f) The G1 policy is more careful to set the young list target length to be the survivor number +1. g) Lots of code tidy up, removal, refactoring to make future changes easier.
Reviewed-by: johnc, ysr
An evacuation failure while copying the roots caused an object, A, to be forwarded to itself. During the subsequent RSet updating a reference to A was processed causing the reference to be added to the RSet of A's heap region. As a result of adding to the remembered set we ran into the issue described in 6930581 - the sparse table expanded and the RSet scanning code walked the cards in one instance of RHashTable (_cur) while the occupied() counts the cards in the expanded table (_next).
Reviewed-by: tonyp, iveresov
There is a race between the concurrent refinement threads and the humongous object allocation that can cause the concurrent refinement threads to corrupt the part of the BOT that it is being initialized by the humongous object allocation operation. The solution is to do the humongous object allocation in careful steps to ensure that the concurrent refinement threads always have a consistent view over the BOT, region contents, and top. The fix includes some very minor tidying up in sparsePRT.
Reviewed-by: jcoomes, johnc, ysr
The changes from 6941395 did not clear the CMTask::_aborted_region fields when concurrent marking aborted because of overflow. As a result, the next time around we could see a memory region whose start address was above the global finger and the assertion tripped. Moved the clearing of the aborted regions to ConcurrentMark::clear_marking_state, which is executed on all of the exit paths.
Reviewed-by: tonyp, ysr, jmasa
The remembered set iterator for sparse tables incorrectly assumes that index 0 corresponds to the bottom of the heap, not address 0 as it is the case.
Reviewed-by: ysr, jmasa
Under certain circumstances a safepoint could happen between a JavaThread object being created and that object being added to the Java threads list. This could cause the active field of that thread's SATB queue to get out-of-sync with respect to the other Java threads. The solution is to activate the SATB queue, when necessary, before adding the thread to the Java threads list, not when the JavaThread object is created. The changeset also includes a small fix to rename the surrogate locker thread from "Surrogate Locker Thread (CMS)" to "Surrogate Locker Thread (Concurrent GC)" since it's also used in G1.
Reviewed-by: iveresov, ysr, johnc, jcoomes
Clear the concurrent marking "in progress" flag while the FullGCCount_lock is held. This avoids a race that can cause back to back System.gc() calls, when ExplicitGCInvokesConcurrent is enabled, to fail to initiate a marking cycle causing the requesting thread to hang.
Reviewed-by: tonyp, ysr
Re-enable use of the lock-free versions of region stack push() and pop() by recording aborted regions in a thread-local structure, which are then processed when scanning of the region stack restarts. The previous locking versions of these routines are retained for diagnostic purposes.
Reviewed-by: tonyp, ysr
We're renaming "evacuation failure" to "to-space overflow". I'm also piggy-backing a small additional change which removes the "Mark closure took..." output.
Reviewed-by: ysr, johnc
There are a few issues in the code that calculates whether to resize the heap and by how much: a) some calculations can overflow 32-bit size_t's, b) min_desired_capacity is not bounded by the max heap size, and c) the assrt that fires is in the wrong place. The fix also includes some tidying up of the related verbose code.
Reviewed-by: ysr, jmasa
During RSet updating, when ParallelGCThreads is zero, references that point into the collection set are added directly the referenced region's RSet. This can cause the sparse table in the RSet to expand. RSet scanning and the "occupied" routine will then operate on different instances of the sparse table causing the assert to trip. This may also cause some cards added post expansion to be missed during RSet scanning. When ParallelGCThreads is non-zero such references are recorded on the "references to be scanned" queue and the card containing the reference is recorded in a dirty card queue for use in the event of an evacuation failure. Employ the parallel code in the serial case to avoid expanding the RSets of regions in the collection set.
Reviewed-by: iveresov, ysr, tonyp
As part of 6944166 we disabled the concept of abandoned pauses (i.e., if the collection set is empty, we would still try to do a pause even if it is to update the RSets and scan the roots). This changeset removes the code and structures associated with abandoned pauses.
Reviewed-by: iveresov, johnc
The per-worker _new_refs array is used to hold references that point into the collection set. It is populated during RSet updating and subsequently processed. In the event of an evacuation failure it processed again to recreate the RSets of regions in the collection set. Remove the per-worker _new_refs array by processing the references directly. Use a DirtyCardQueue to hold the cards containing the references so that the RSets of regions in the collection set can be recreated when handling an evacuation failure.
Reviewed-by: iveresov, jmasa, tonyp
During concurrent refinment, filter cards in young regions after it has been determined that the region has been allocated from and the young type of the region has been set.
Reviewed-by: iveresov, tonyp, jcoomes
G1 was not handling explicit GCs correctly in many ways. It does now. See the CR for the list of improvements contained in this changeset.
Reviewed-by: iveresov, ysr, johnc
First, change the guarantee to raising a vm error. Second, set the interval dynamically, and based on the pause time target, if it is not set explicitly.
Reviewed-by: ysr, johnc
Rather than changing the default value of the G1UseFixedWindowMMUTracker, the flag and associated guarantee have been removed.
Reviewed-by: jcoomes, tonyp, ysr
6871109: G1: remove the concept of the scan only prefix
Removed scan only regions and associated code. The young portion of the collection set is now constructed incrementally - when a young region is retired as the current allocation region it is added to the collection set.
Reviewed-by: apetrusenko, iveresov, tonyp
The outgoing region map is not maintained properly and it's causing an assert failure. Given that we don't actually use it, I'm removing it. I'm piggy-backing a small change on this which removes a message that it's printed before a Full GC when DisableExplicitGC is set.
Reviewed-by: apetrusenko, ysr
The expression that calculates the live bytes for a heap region can overflow for a suitably large humongous region/object. Cache the object size in a suitably sized local variable so that the expression is converted to a wider type.
Reviewed-by: tonyp, jmasa, iveresov, apetrusenko
Humongous regions may contain multiple objects as a result of being retained as to-space from a previous GC and then re-used as to-space after being tagged as humongous. These changes include a check that causes retained to-space regions that are now tagged as humongous to be disregarded and a new to-space region allocated.
Reviewed-by: tonyp, iveresov
Make sure that two marking cycles do not overlap, i.e., a new one can only start after the concurrent marking thread finishes all its work. In the fix I piggy-back a couple of minor extra fixes: some general code reformatting for consistency (only around the code I modified), the removal of a field (G1CollectorPolicy::_should_initiate_conc_mark) which doesn't seem to be used at all (it's only set but never read), as well as moving the "is GC locker active" test earlier into the G1 pause / Full GC and using a more appropriate method for it.
Reviewed-by: johnc, jmasa, jcoomes, ysr
Calling the methods region_stack_push() and region_stack_pop() concurrent is not MT-safe. The assumption is that we will only call region_stack_push() during a GC pause and region_stack_pop() during marking. Unfortunately, we also call region_stack_push() during marking which seems to be introducing subtle marking failures. This change introduces lock-based methods for pushing / popping to be called during marking.
Reviewed-by: iveresov, johnc
