Fixed assertion checking code that was attempting to translate addresses past end of space for card-table slot. Also elaborated some assertion checking messages.
Reviewed-by: iveresov, jmasa, tonyp
Fixed process_chunk_boundaries(), used for parallel card scanning when using ParNew/CMS, so as to prevent double-scanning, or worse, non-scanning of imprecisely marked objects exceeding parallel chunk size. Made some sizing parameters for parallel card scanning diagnostic, disabled ParallelGCRetainPLAB, and elaborated and clarified some comments.
Reviewed-by: stefank, johnc
BlockOffsetArrayUseUnallocatedBlock was intended to be turned off as part of BUG 6948538 but a code line in collectorPolicy.cpp actually kept it turned on.
Reviewed-by: jwilhelm, ysr
We should only undirty cards after we decide that they are not on a young region, not before. The fix also includes improvements to the verify_dirty_region() method which print out which cards were not found dirty.
Reviewed-by: johnc, brutisso
Created new "new" operator for CHeapObj that allows malloc to fail without causing fatal error. Also replaced "HeapAllocate" with "os::malloc" in decoder code to allow decoder to handle low memory scenario.
Reviewed-by: coleenp, dholmes
In G1 heap verification, we no longer scan perm to G1-collected heap refs as part of process_strong_roots() but rather in a separate explicit oop iteration over the perm gen. This preserves the original perm card-marks. Added a new assertion in younger_refs_iterate() to catch a simple subcase where the user may have forgotten a prior save_marks() call, as happened in the case of G1's attempt to iterate perm to G1 refs when verifying the heap before exit. The assert was deliberately weakened for ParNew+CMS and will be fixed for that combination in a future CR. Also made some (non-G1) cleanups related to code and comments obsoleted by the migration of Symbols to the native heap.
Reviewed-by: iveresov, jmasa, tonyp
Short-circuited an unnecessary double traversal of dirty card windows when iterating younger refs. Also renamed some cardtable methods for more clarity.
Reviewed-by: jmasa, stefank, poonam
Make CDS reorder vtables so that dump time vtables match run time order, so when redefine classes reinitializes them, they aren't in the wrong order.
Reviewed-by: dcubed, acorn
Removed the unused clear argument to various cardtbale methods and unused mod_oop_in_space_iterate method. Unrelated to synopsis, added a pair of clarifying parens in AllocationStats constructor.
Reviewed-by: brutisso, jcoomes
Use _max_num_q = max(discovery_degree, processing_degree), and let balance_queues() redistribute from discovery_degree to processing_degree of queues. This should also allow a more dynamic and flexible parallelism policy in the future.
Reviewed-by: jmasa, johnc
6627787: CMS: JVM refuses to start up with -Xms16m -Xmx16m
7000125: CMS: Anti-monotone young gen sizing with respect to maximum whole heap size specification
7027529: CMS: retire CMSUseOldDefaults flag
Simplify CMS heap sizing code, relying on ergonomic initial sizing consistent with other collectors for the most part, controlling only young gen sizing to rein in pause times. Make CMS young gen sizing default statically cpu-dependant. Remove inconsistencies wrt generation sizing and policy code, allowing for the fixing for 6627787 and 7000125. For 7027529, retire the flag CMSUseOldDefaults which had been introduced as a bridge from JDK 5 to JDK 6 a number of years ago.
Reviewed-by: brutisso, poonam
Bulk zeroing reduction didn't work with G1, because arraycopy would call pre-barriers on uninitialized oops. The solution is to have version of arraycopy stubs that don't have pre-barriers. Also refactored arraycopy stubs generation on SPARC to be more readable and reduced the number of stubs necessary in some cases.
Reviewed-by: jrose, kvn, never
7023151: G1: refactor the code that operates on _cur_alloc_region to be re-used for allocs by the GC threads
7018286: G1: humongous allocation attempts should take the GC locker into account
First, this change replaces the asymmetric locking scheme in the G1 slow alloc path by a summetric one. Second, it factors out the code that operates on _cur_alloc_region so that it can be re-used for allocations by the GC threads in the future.
Reviewed-by: stefank, brutisso, johnc
When verifying clean card ranges, use memory-range-bounded iteration over oops of objects overlapping that range, thus avoiding the otherwise quadratic worst-case cost of scanning large object arrays.
Reviewed-by: jmasa, jwilhelm, tonyp
Fix block_size_if_printezis_bits() so it does not expect the bits, only uses them when available. Fix block_size_no_stall() so it does not stall when the bits are missing such cases, letting the caller deal with zero size returns. Constant pool cache oops do not need to be unparsable or conc_unsafe after their klass pointer is installed. Some cosmetic clean-ups and some assertion checking for conc-usafety which, in the presence of class file redefinition, has no a-priori time boundedness, so all GCs must be able to safely deal with putatively conc-unsafe objects in a stop-world pause.
Reviewed-by: jmasa, johnc
Track allocated bytes in Thread's, update on TLAB retirement and direct allocation in Eden and tenured, add JNI methods for ThreadMXBean.
Reviewed-by: coleenp, kvn, dholmes, ysr
