erik.corry@gmail.com
e8ffc2bebd
Make the speed of incremental marking depend also on the rate
...
at which we are hitting expensive write barrier operations,
not just on the rate of allocation.
Review URL: https://chromiumcodereview.appspot.com/10974003
git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@12618 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2012-09-26 11:35:42 +00:00
erik.corry@gmail.com
42e5dc2cc0
Make Kraken fasta.
...
Review URL: https://chromiumcodereview.appspot.com/10978040
git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@12611 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2012-09-26 09:01:13 +00:00
mstarzinger@chromium.org
3018b875b1
Integrate map marking into static marking visitor.
...
This refactors the specialized marking of map contents to be done by the
static marking visitor shared between full and incremental marking. This
also fixes an issue where some maps weren't accounted for in the object
stats tracker. But more importantly, it simplifies the code base.
R=verwaest@chromium.org
Review URL: https://codereview.chromium.org/10919294
git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@12526 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2012-09-17 10:04:39 +00:00
erik.corry@gmail.com
1987542825
Fix invariant so that we cannot record relocation slots for
...
white objects when compacting. Add flag for incremental code
compaction.
Review URL: https://chromiumcodereview.appspot.com/10907174
git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@12483 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2012-09-11 14:01:39 +00:00
mstarzinger@chromium.org
abede994d9
Refactor incremental marking to use static visitor.
...
This is a refactoring only change that switches incremental marking to
use a static object visitor. It also shares the common code between the
non-incremental and the incremental marker. Sharing that would require
semantical changes will be done later.
R=verwaest@chromium.org
Review URL: https://chromiumcodereview.appspot.com/10816007
git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@12193 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2012-07-25 15:23:07 +00:00
mstarzinger@chromium.org
97cbaec08a
Add OS::GetCurrentProcessId and prepend output from trace-gc with the current pid
...
BUG=none
TEST=manual
Review URL: https://chromiumcodereview.appspot.com/9817002
Patch from Jochen Eisinger <jochen@chromium.org>.
git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@12032 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2012-07-10 12:52:36 +00:00
mstarzinger@chromium.org
f9b93e6cc7
Implement map collection for incremental marking.
...
This causes map transitions to be treated weakly during incremental
marking and hence allows clearing of non-live transitions. The marking
code is now shared between incremental and non-incremental mode.
R=vegorov@chromium.org
BUG=v8:1465
TEST=cctest/test-heap/Regress1465
Review URL: https://chromiumcodereview.appspot.com/10310168
git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@11577 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2012-05-16 10:07:50 +00:00
mstarzinger@chromium.org
88a9350f14
Revert r11556 and r11558 to allow roll.
...
R=yangguo@chromium.org
Review URL: https://chromiumcodereview.appspot.com/10383182
git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@11564 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2012-05-15 12:01:23 +00:00
mstarzinger@chromium.org
0c54a2371c
Implement map collection for incremental marking.
...
This causes map transitions to be treated weakly during incremental
marking and hence allows clearing of non-live transitions. The marking
code is now shared between incremental and non-incremental mode.
R=vegorov@chromium.org
BUG=v8:1465
TEST=cctest/test-heap/Regress1465
Review URL: https://chromiumcodereview.appspot.com/10386046
git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@11556 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2012-05-15 08:39:25 +00:00
ulan@chromium.org
2b554f2448
Make progress in incremental marking if scavenge is delaying mark-sweep.
...
R=mstarzinger@chromium.org
Review URL: https://chromiumcodereview.appspot.com/9965054
git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@11213 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2012-04-03 07:32:19 +00:00
vegorov@chromium.org
74ef753067
Change inlined cache of intanceof stub to use indirection through cell.
...
The stub was directly patching caller's code without issuing write barrier which violated incremental marking invariants.
R=mstarzinger@chromium.org
BUG=http://crbug.com/109448
TEST=cctest/test-heap/InstanceOfStubWriteBarrier
Review URL: http://codereview.chromium.org/9158015
git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@10380 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2012-01-11 09:39:37 +00:00
ulan@chromium.org
8dc728126e
Start incremental marking on idle notification.
...
BUG=v8:1458
TEST=cctest/test-api/IdleNotification*
Review URL: http://codereview.chromium.org/8519002
git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@10093 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2011-11-30 11:13:36 +00:00
ulan@chromium.org
0d536dec26
Shrink the new space and uncommit marking deque on low memory notification.
...
BUG=v8:1669
TEST=cctest/test-heap/CollectingAllAvailableGarbageShrinksNewSpace
Review URL: http://codereview.chromium.org/8065003
git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@9912 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2011-11-08 12:42:02 +00:00
erik.corry@gmail.com
cd8d915c72
Clean up the marking speed heuristics. This reduces the
...
max heap size on 64 bit from ca. 300Mbytes to ca. 200Mbytes
on Ulan's splay variant. On 32 bit not much change.
Review URL: http://codereview.chromium.org/8494012
git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@9906 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2011-11-08 10:28:58 +00:00
vegorov@chromium.org
858320725b
Split incremental marking write barrier into fast and slow paths.
...
Force inlining of the fast path.
Force inlining LiteralBuffer::AddChar and Scanner::AddLiteralChar.
R=erik.corry@gmail.com
Review URL: http://codereview.chromium.org/8431010
git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@9853 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2011-10-31 20:59:28 +00:00
vegorov@chromium.org
af876ee474
Avoid incremental marking write-barrier when constructing descriptor arrays.
...
R=erik.corry@gmail.com
Review URL: http://codereview.chromium.org/8360004
git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@9735 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2011-10-21 10:32:38 +00:00
fschneider@chromium.org
e8a26d1eb1
Add write barrier helper for code patching and refactor stack check patching.
...
The new helper avoids expensive FindCodeForInnerPointer invocation when we have
the host code object available. It is used when patching stack checks.
Also some comments on the ARM platform are corrected.
Review URL: http://codereview.chromium.org/8330021
git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@9687 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2011-10-18 15:07:42 +00:00
mstarzinger@chromium.org
554a12fbbc
Fix free list node ending up on evacuation candidate.
...
This is a temporary fix which avoids compaction when incremental marking
is restarted during an old-space-step. That could turn the page that
holds the chosen free list node into an evacuation candidate. It could
also cause several other inconsistencies if it happens during scavenge.
R=vegorov@chromium.org
Review URL: http://codereview.chromium.org/8228010
git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@9585 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2011-10-11 16:50:58 +00:00
vegorov@chromium.org
36ae5f3811
Pass correct anchor_slot for EMBEDDED_OBJECT pointers from code objects.
...
Correctly initialize newly created large-object pages when incremental marking with compaction is in progress.
R=erik.corry@gmail.com
BUG=v8:1737
Review URL: http://codereview.chromium.org/8070002
git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@9475 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2011-09-28 17:45:58 +00:00
lrn@chromium.org
610281f4ee
Fix calculation of live-bytes in pages.
...
The "live bytes" count is *really* a "marked black" count - i.e., the count of bytes *known* to be live.
Fix aggravating bug on X64 where assembler code used a value that was off
by a factor of 2^31.
Ensure that sweeping clears live-bytes. Added other missing increments.
Added print statements to trace live-byte modifications, under a flag.
Still a few cases of undercounting left.
(New issue to merge from GC branch to bleeding_edge)
Review URL: http://codereview.chromium.org/7970009
git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@9338 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2011-09-20 11:20:00 +00:00
vegorov@chromium.org
ac36cb4504
Merge experimental/gc branch to the bleeding_edge.
...
Review URL: http://codereview.chromium.org/7945009
git-svn-id: http://v8.googlecode.com/svn/branches/bleeding_edge@9328 ce2b1a6d-e550-0410-aec6-3dcde31c8c00
2011-09-19 18:36:47 +00:00