Change 8035330: Remove G1ParScanPartialArrayClosure and G1ParScanHeapEvacClosure broke the debug build on AIX. The method do_oop_partial_array() is added in a header, but requires the inline function par_write_ref() through several inlined calls. In some cpp files, like arguments.cpp, par_write_ref() is not defined as the corresponding inline header and is not included. The AIX debug VM does not start because of the missing symbol. This change solves this by cleaning up include dependencies.
Reviewed-by: tschatzl, stefank
The free list is being maintained in a sorted fashion and old and humongous regions are allocated from the bottom of the heap while young regions are allocated at the top.
Co-authored-by: Staffan Friberg <staffan.friberg@oracle.com>
Reviewed-by: tschatzl, mgerdin
Pad and cache-align BiasedMappedArray instances by default to avoid performance variability problems due to false sharing, as instances of this data structures are typically used for performance sensitive code.
Reviewed-by: brutisso, stefank
Mentioned closures are actually wrapped methods. This adds confusion to readers, and in this case also increases code size as G1ParScanHeapEvacClosure is part of the oop_oop_iterate() methods. Move them into G1ParScanThreadState as methods.
Reviewed-by: stefank
Detailed breakdown of time spent in the evacuation failure handling phases to make the "Other" time roughly correspond to the sum of its parts.
Reviewed-by: jwilhelm, jmasa
The from card cache is a very frequently accessed data structure. It is essentially a 2d array of per-region values, one row of values for every GC thread. Pad and align the data structure to avoid false sharing.
Reviewed-by: stefank
Change the code cache remembered sets data structure from a GrowableArray to a chunked list of nmethods. This makes the data structure more amenable to parallelization, and decreases freeing time.
Reviewed-by: mgerdin, brutisso
Revert JDK-6976350 because it does not improve PLAB fragmentation. To the contrary, it tends to increase the amount of wasted space with many threads.
Reviewed-by: brutisso
Remove the assumption that G1CollectedHeap::in_cset_fast_test needs to check for NULL references. Most of the time this is not required, making the code doing this check multiple times.
Reviewed-by: stefank, mgerdin, jmasa
Move methods that are not dependent on any of G1ParCopyClosure's template parameters into G1ParCopyHelper. Further remove unused methods and members of the class hierarchy.
Reviewed-by: mgerdin, stefank
When string and symbol table unlink are not performed in parallel, the claim index we check is not updated, and so a guarantee fails. Take this into account when checking the guarantee.
Reviewed-by: brutisso, jwilhelm
Clean up and slightly optimize reference handling from the GC reference task queue. Since we never push partial array chunks as narrowOop* we can manually specialize the code so that some code can be optimized away.
Reviewed-by: tonyp, brutisso, stefank
