mirror of
https://github.com/openjdk/jdk.git
synced 2025-09-21 11:34:38 +02:00
7011379: G1: overly long concurrent marking cycles
This changeset introduces filtering of SATB buffers at the point when they are about to be enqueued. If this filtering clears enough entries on each buffer, the buffer can then be re-used and not enqueued. This cuts down the number of SATB buffers that need to be processed by the concurrent marking threads. Reviewed-by: johnc, ysr
This commit is contained in:
parent
a484211e0b
commit
05b7df20dd
8 changed files with 130 additions and 18 deletions
|
@ -28,7 +28,7 @@
|
|||
#include "gc_implementation/g1/concurrentMark.hpp"
|
||||
#include "gc_implementation/g1/g1CollectedHeap.hpp"
|
||||
#include "gc_implementation/g1/g1CollectorPolicy.hpp"
|
||||
#include "gc_implementation/g1/heapRegionSeq.hpp"
|
||||
#include "gc_implementation/g1/heapRegionSeq.inline.hpp"
|
||||
#include "utilities/taskqueue.hpp"
|
||||
|
||||
// Inline functions for G1CollectedHeap
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue