trims [Tue, 01 Feb 2011 18:57:53 -0800] rev 7929
Merge
trims [Fri, 21 Jan 2011 02:07:11 -0800] rev 7928
Merge
iveresov [Fri, 21 Jan 2011 00:01:41 -0800] rev 7927
7013812: C1: deopt blob too far from patching stub
Summary: Use long jumps to get from patching stubs to deopt blob
Reviewed-by: kvn, never
trims [Thu, 20 Jan 2011 18:24:04 -0800] rev 7926
Merge
trims [Thu, 20 Jan 2011 17:53:38 -0800] rev 7925
Merge
johnc [Thu, 20 Jan 2011 13:57:12 -0800] rev 7924
Merge
tonyp [Wed, 19 Jan 2011 19:30:42 -0500] rev 7923
6977804: G1: remove the zero-filling thread
Summary: This changeset removes the zero-filling thread from G1 and collapses the two free region lists we had before (the "free" and "unclean" lists) into one. The new free list uses the new heap region sets / lists abstractions that we'll ultimately use it to keep track of all regions in the heap. A heap region set was also introduced for the humongous regions. Finally, this change increases the concurrency between the thread that completes freeing regions (after a cleanup pause) and the rest of the system (before we'd have to wait for said thread to complete before allocating a new region). The changest also includes a lot of refactoring and code simplification.
Reviewed-by: jcoomes, johnc
johnc [Wed, 19 Jan 2011 13:04:37 -0800] rev 7922
Merge
johnc [Wed, 19 Jan 2011 13:01:11 -0800] rev 7921
7012642: G1: JumbleGC002 test aborts with segmentation violation due to uncaught stack overflow
Summary: With recent G1 allocation path changes, the value of StackShadowPages in fast debug builds of the JVM, is no longer large enough to prevent the JVM C++ code from touching the stack guard pages. Increase the value of StackShadowPages to a suitable value.
Reviewed-by: ysr, tonyp, coleenp
tonyp [Wed, 19 Jan 2011 09:35:17 -0500] rev 7920
7011379: G1: overly long concurrent marking cycles
Summary: 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