Thomas Schatzl
f2e110fe77
8067469: G1 ignores AlwaysPreTouch
...
Factor out pretouch code of the various virtual space management classes and use them everywhere including in G1.
Reviewed-by: stefank, ehelin, dholmes
2014-12-18 09:37:02 +01:00
Thomas Schatzl
5d868d4e0f
8066102: Clean up HeapRegionRemSet files
...
Remove dead code, tighten public interfaces and improve documentation in the HeapRegionRemSet implementation.
Reviewed-by: mgerdin, kbarrett
2014-12-09 12:47:19 +01:00
Jesper Wilhelmsson
9b430f2262
Merge
2014-12-04 10:40:19 +01:00
Yumin Qi
9767fa7cb2
Merge
2014-12-03 20:32:33 -08:00
Max Ockner
91dbd4f088
8060074: os::free() takes MemoryTrackingLevel but doesn't need it
...
Cleaned up unused arguments in os::free and it's callers.
Reviewed-by: lfoltan, coleenp, ctornqvi, dholmes
2014-12-01 12:16:15 -05:00
Leonid Mesnik
c8a147b8c7
8065579: WB method to start G1 concurrent mark cycle should be introduced
...
Add a WhiteBox callback to the VM to start a concurrent mark cycle in G1.
Reviewed-by: tschatzl, sjohanss
2014-11-28 09:33:48 +01:00
Stefan Johansson
02adde2aac
8065227: Report allocation context stats at end of cleanup
...
Moved allocation context update from remark to the cleanup phase.
Reviewed-by: mgerdin, jmasa
2014-11-27 11:09:55 +01:00
Jesper Wilhelmsson
11267d8d06
Merge
2014-11-26 17:24:57 +00:00
Mikael Gerdin
b5ef32af36
8065358: Refactor G1s usage of save_marks and reduce related races
...
Stop using save_marks in G1 related code and make setting the replacement field less racy.
Reviewed-by: brutisso, tschatzl
2014-11-26 10:53:31 +01:00
Jesper Wilhelmsson
1da0a96993
8065305: Make it possible to extend the G1CollectorPolicy
...
Added a G1CollectorPolicyExt where it is possible to extend the class.
Reviewed-by: sjohanss, tschatzl
2014-11-25 13:41:08 +01:00
Kim Barrett
f9d8e2ae9d
8062206: Remove unusable G1RSLogCheckCardTable command line argument
...
Remove dependent assertion and remove develop option
Reviewed-by: jwilhelm, mgerdin, tschatzl
2014-10-27 17:24:10 -04:00
Jesper Wilhelmsson
7339456266
8062836: BACKOUT - Parallelize clearing the next mark bitmap
...
Backing out due to non-trivial issues found in nightly testing
Reviewed-by: mgerdin, mlarsson
2014-11-05 15:50:14 +01:00
Bengt Rutisson
c1bc4be92b
8061449: G1: FreeRegionList_test() fails with G1 after the JDK-8058534 fix to HeapRegion::orig_end()
...
Reviewed-by: mgerdin, tschatzl, stefank
2014-11-05 10:12:51 +01:00
Marcus Larsson
4a9f067587
8049341: Parallelize clearing the next mark bitmap
...
Reviewed-by: mgerdin, tschatzl
2014-11-03 12:49:21 +01:00
Marcus Larsson
fe45f7091b
8054491: Remove wrong assert and refactor code in G1CollectorPolicy::record_concurrent_mark_end
...
Reviewed-by: tschatzl, brutisso
2014-11-03 11:29:00 +01:00
Marcus Larsson
5fd7516136
8043243: convert SCAN_AND_FORWARD, SCAN_AND_ADJUST_POINTERS, SCAN_AND_COMPACT macros to methods
...
Reviewed-by: mgerdin, kbarrett
2014-10-30 12:45:22 +01:00
Stefan Johansson
6306dce831
8061234: ResourceContext.requestAccurateUpdate() is unreliable
...
Changing copy_allocation_context_stats to return if there are more stats available after the copy.
Reviewed-by: rriggs, jcoomes
2014-10-30 10:51:06 +01:00
Kim Barrett
8f8d87ece5
8061748: Remove check_ct_logs_at_safepoint()
...
Remove unused function and related closure class
Reviewed-by: jwilhelm, mgerdin
2014-10-23 16:19:32 -04:00
Erik Helin
3a3e45ab40
8061630: G1 iterates over JNIHandles two times
...
Reviewed-by: mgerdin, brutisso
2014-10-23 11:43:29 +02:00
Erik Helin
f3997d8eed
8064721: The card tables only ever need two covering regions
...
Reviewed-by: jmasa, tschatzl, kbarrett
2014-11-18 10:36:42 +01:00
Staffan Friberg
04bdb774e1
8064473: Improved handling of age during object copy in G1
...
Reviewed-by: brutisso, tschatzl
2014-11-14 15:03:39 +01:00
Mikael Gerdin
4feb7b4dab
8058209: Race in G1 card scanning could allow scanning of memory covered by PLABs
...
Read _top before _gc_time_stamp in saved_mark_word() with LoadLoad order to ensure we get a consistent view
Reviewed-by: brutisso, dcubed, dholmes, stefank
2014-11-14 14:23:25 +01:00
Kim Barrett
294a63af5f
8062036: ConcurrentMarkThread::slt may be invoked before ConcurrentMarkThread::makeSurrogateLockerThread causing intermittent crashes
...
Suppress gc_alot during VM init, improve error for SLT uninitialized.
Reviewed-by: jmasa, brutisso, tschatzl
2014-11-11 13:39:00 -05:00
Marcus Larsson
46e9fb5176
6979279: remove special-case code for ParallelGCThreads==0
...
Reviewed-by: jwilhelm, brutisso, kbarrett
2014-10-21 11:57:22 +02:00
Stefan Johansson
bd227a9bac
8058568: GC cleanup phase can cause G1 skipping a System.gc()
...
Marking G1 FullGC as a _full collection and passing down the correct before count.
Reviewed-by: brutisso, mgerdin
2014-10-20 10:18:17 +02:00
Stefan Karlsson
d410f19961
8056240: Investigate increased GC remark time after class unloading changes in CRM Fuse
...
Reviewed-by: mgerdin, coleenp, bdelsart
2014-10-02 10:55:36 +02:00
Sangheon Kim
8d288ccc54
8027428: Different conditions for printing taskqueue statistics for parallel gc, parNew and G1
...
Changed flag names for printing taskqueue and termination statistics for parallel gc, parNew and G1.
Reviewed-by: jwilhelm, brutisso, tschatzl
2014-10-14 20:58:43 +02:00
Sangheon Kim
3f18eda414
8058801: G1TraceReclaimDeadHumongousObjectsAtYoungGC only prints humongous object liveness output when there is at least one candidate humongous object
...
If G1TraceReclaimDeadHumongousObjectsAtYoungGC is enabled, always print humongous object liveness output.
Reviewed-by: tschatzl
2014-10-10 12:15:51 +02:00
Thomas Schatzl
60f3ade82b
8059758: Footprint regressions with JDK-8038423
...
Changes in JDK-8038423 always initialize (zero out) virtual memory used for auxiliary data structures. This causes a footprint regression for G1 in startup benchmarks. This is because they do not touch that memory at all, so the operating system does not actually commit these pages. The fix is to, if the initialization value of the data structures matches the default value of just committed memory (=0), do not do anything.
Reviewed-by: jwilhelm, brutisso
2014-10-09 11:40:11 +02:00
Marcus Larsson
6d1c35615a
8058298: Separate heap region iterator claim values from the data structures iterated over
...
Reviewed-by: tschatzl, brutisso
2014-10-07 14:54:53 +02:00
Stefan Johansson
18eb46eb95
8059466: Force young GC to initiate marking cycle when stat update is requested
...
Enable yc to be forced for stat update.
Reviewed-by: mgerdin, jcoomes
2014-10-06 10:11:13 +02:00
Bengt Rutisson
82931dcc1c
8059452: G1: Change the default values for G1HeapWastePercent and G1MixedGCLiveThresholdPercent
...
Reviewed-by: tschatzl, jwilhelm
2014-09-30 13:14:22 +02:00
Jesper Wilhelmsson
261735f6fa
8047976: Ergonomics for GC thread counts should update the flags
...
Ergonomics updates flags for number of GC threads
Reviewed-by: tschatzl, jwilhelm
2014-09-27 15:11:41 +02:00
Jesper Wilhelmsson
f9b921bd25
Merge
2014-09-22 16:22:21 +02:00
Sangheon Kim
30cb2dcb12
8036116: Fix thread-id types in G1 remembered set implementations
...
Reviewed-by: stefank, jprovino, brutisso
2014-09-24 11:00:12 +02:00
Stefan Karlsson
1a452ae3ae
Merge
2014-09-23 12:52:57 +00:00
Joseph Provino
b0b5fa7bc6
8027450: Improve time reporting in G1 remark
...
Reviewed-by: stefank, tschatzl
2014-09-23 12:34:37 +02:00
Antonios Printezis
da5afa76ab
8058495: G1: normalize names for isHumongous() and friends
...
Reviewed-by: tschatzl, brutisso
2014-09-23 11:43:24 +02:00
Niclas Adlertz
37c8ef911c
Merge
2014-09-19 17:14:13 +02:00
Tobias Hartmann
cd01de591a
8015774: Add support for multiple code heaps
...
Support for segmentation of the code cache. Separate code heaps are created and used to store code of different types.
Reviewed-by: kvn, iveresov, roland, anoll, egahlin, sla
2014-09-17 08:00:07 +02:00
Thomas Schatzl
adf66602a0
8052172: Evacuation failure handling in G1 does not evacuate all objects if -XX:-G1DeferredRSUpdate is set
...
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
2014-09-16 10:28:15 +02:00
Mikael Gerdin
7bf45791e8
8057722: G1: Code root hashtable updated incorrectly when evacuation failed
...
Reviewed-by: brutisso, jwilhelm
2014-09-08 17:47:43 +02:00
Bengt Rutisson
c9d4b7a93c
8057910: G1: BOT verification should not pass top
...
Reviewed-by: stefank, tschatzl
2014-09-09 14:27:10 +02:00
John Coomes
d50a563314
8057827: notify an obj when allocation context stats are available
...
Reviewed-by: mikael, jmasa, tschatzl
2014-09-10 16:06:53 -07:00
John Coomes
fd0e5093ca
8057824: methods to copy allocation context statistics
...
Reviewed-by: mikael, jmasa, tschatzl
2014-09-10 13:01:13 -07:00
John Coomes
40155ae18d
8057818: collect allocation context statistics at gc pauses
...
Reviewed-by: mikael, jmasa
2014-09-10 13:01:13 -07:00
Stefan Johansson
0856ec5961
8057710: Refactor G1 heap region default sizes
...
Refactored the defines to instead be static const in a HeapRegionBounds class.
Reviewed-by: mgerdin, tschatzl
2014-09-09 04:48:41 +02:00
Stefan Johansson
3e6d46d28b
8057658: Enable G1 FullGC extensions
...
Refactored the G1 FullGC code to enable it to be extended.
Reviewed-by: mgerdin, brutisso
2014-09-09 00:05:25 +02:00
Bengt Rutisson
ff1498ba6b
8025564: gc/memory/UniThread/Linear1 times out during heap verification
...
Reviewed-by: stefank, tschatzl
2014-09-08 10:41:06 +02:00
Stefan Johansson
f8137659f5
8057536: Refactor G1 to allow context specific allocations
...
Splitting out a g1 allocator class to simply specialized allocators which can associate each allocation with a given context.
Reviewed-by: mgerdin, brutisso
2014-09-05 09:49:19 +02:00
