Push the remembered sets of large objects with few referenced into the dirty card queue at the beginning of the evacuation so that they may end up with zero remembered set entries at the end of the collection, and are potentially reclaimed. Also improve timing measurements of the early reclaim mechanism, and shorten flag names.
Reviewed-by: brutisso, jmasa, dfazunen
8062957: Heap is not shrunk when deallocating under memory pressure
Added explicit -XX:-ExplicitGCInvokesConcurrent to invocations
Reviewed-by: brutisso, tschatzl
Remove -XX:-G1DeferredRSUpdate functionality as it is racy. During evacuation failure handling, threads where evacuation failure handling occurred may try to add remembered sets to regions which remembered sets are currently being scanned. The iterator to handle the remembered set scan does not support addition of entries during scan and so may skip valid references.
Reviewed-by: iveresov, brutisso, mgerdin
Enable shrinking within the heap by removing some code added for JDK-8054818. Enable the test case that checks that again too.
Reviewed-by: jwilhelm, jmasa
When G1 is run with -XX:-G1DeferredRSUpdate, the VM crashes because of wrong initialization order of member variables. The change makes the initalization explicit, not relying on initialization order any more.
Reviewed-by: brutisso, mgerdin
The test launched a 32 bit VM with UseCompressedOops enabled. This is not supported on 32 bit VMs, causing a test failure. Investigation showed that the use of this flag is not required at all, so simply remove it.
Reviewed-by: tschatzl, jwilhelm
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
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
8027455: Improve symbol table scan times during gc pauses
Parallelize string table and symbol table scan during remark and full GC. Some additional statistics output if the experimental flag G1TraceStringSymbolTableScrubbing is set.
Reviewed-by: mgerdin, coleenp, brutisso
Change checks for isHumongous() to continuesHumongous() as installing a code root for a humongous object is valid, but not for continuations of humongous objects. Cleaned up asserts.
Reviewed-by: jmasa, tamao
The initialization for the remembered set summary data structures used the wrong thread count, i.e. number of worker threads instead of number of refinement threads.
Reviewed-by: brutisso
Add memory consumption breakdown on a per region type in the G1 remembered set summary statistics. This simplifies remembered set memory consumption analysis.
Reviewed-by: brutisso
Fixed the output of G1SummarizeRSetStats: too small datatype for the number of concurrently processed cards, added concurrent remembered set thread time retrieval for Linux and Windows (BSD uses os::elapsedTime() now), and other cleanup. The information presented during VM operation is now relative to the previous output, not always cumulative if G1SummarizeRSetStatsPeriod > 0. At VM exit, the code prints a cumulative summary.
Reviewed-by: johnc, jwilhelm
Paul Hohensee
Thomas Schatzl
Stefan Johansson
Andrey Zakharov
Kim Barrett
Jesper Wilhelmsson
Bengt Rutisson
Sangheon Kim
Marcus Larsson
Andrey Zakharov
Jon Masamitsu
Per Lidén
Mikael Vidstedt
John Cuthbertson