tschatzl [Wed, 18 Apr 2018 11:36:48 +0200] rev 49810
8201596: java.lang.ref.Reference processing total time logging broken
Summary: Fix "Reference Processing" and add "Weak Processing" time
Reviewed-by: kbarrett, sangheki
tschatzl [Wed, 18 Apr 2018 11:36:48 +0200] rev 49809
8201490: Improve concurrent mark keep alive closure performance
Summary: Avoid doing marking work unless absolutely required.
Reviewed-by: sjohanss, kbarrett
tschatzl [Wed, 18 Apr 2018 11:36:48 +0200] rev 49808
8201487: Do not rebalance reference processing queues if not doing parallel reference processing
Reviewed-by: sangheki, kbarrett
tschatzl [Wed, 18 Apr 2018 11:36:48 +0200] rev 49807
8200730: Fix debug=gc+phases time tracking in Remark and Cleanup
Summary: Timing in Remark and Cleanup pauses did not use instance variables for the scoped timing objects, so these durations were always zero.
Reviewed-by: sangheki, sjohanss
tschatzl [Wed, 18 Apr 2018 11:36:48 +0200] rev 49806
8200426: Make G1 code use _g1h members
Summary: Consistently use _g1h member names for cached G1CollectedHeap* variables.
Reviewed-by: sangheki, sjohanss
tschatzl [Wed, 18 Apr 2018 11:36:48 +0200] rev 49805
8200723: Suppress rs_length and predicted_cards sampling during mixed gcs
Summary: Due to the impact of these measurements on pause time, their high difference to other collections during mixed collections, and their non-use during mixed collections, do not use rs_length and predicted_cards measurements done during mixed gc for the predictor. This avoids the young gen sizing after the mixed phase to be negatively affected by mixed collections.
Reviewed-by: kbarrett, sjohanss
tschatzl [Wed, 18 Apr 2018 11:36:48 +0200] rev 49804
8154528: Reclaim regions emptied by marking in Remark pause
Reviewed-by: shade, sjohanss