| 8b68c5bedfca08872de4e153684f880ae6b9ea31 |
|
11-May-2017 |
Nicolas Geoffray <ngeoffray@google.com> |
Revert "Revert "Use IsMarked instead of Mark for profiling info.""
Bug in the original change was that we were infitely looping on the
same inline cache entry, expecting null when it was actually an old
pointer to a GC'ed class object.
bug: 37693252
Test: test.py --jit
This reverts commit 3afefba4b5558f5f726338485c1f6ddc7f107719.
(cherry picked from commit 13056a1720aca64945541812a3c7602acfe4a937)
Change-Id: Ia637d4a7db4394964d1de5c92370921c98a103fa
|
| 350cf8a406486a4fa96549114b3b21b975a5c8f8 |
|
29-Apr-2017 |
Mathieu Chartier <mathieuc@google.com> |
Add basic heap corruption detection ConcurrentCopying::Copy
Detect objects that have a null class. This also detects objects that
are not in the from-space allocated area since this area is zero
initialized.
Test: test-art-host
Bug: 37683299
Bug: 12687968
Bug: 37187694
Change-Id: Ib7b9a1913a582692ce05791104c181b75e0f7bcb
|
| 988136bf7a731710c1c0979d6f2deec6abe4574f |
|
24-Apr-2017 |
Andreas Gampe <agampe@google.com> |
ART: More header cleanup - CC
Forward-declare AtomicStack in CC. Use stack_reference in atomic_stack.h.
Test: mmma art
Change-Id: I863ca8d4a8dfd5e83279fd68ea0e1a94c3c5df6d
(cherry picked from commit 291ce17ada5a126be99f0fc069a028d2100bcf9e)
|
| 1ca689096b532e007dc9f8ba16db4731e6afd719 |
|
18-Apr-2017 |
Mathieu Chartier <mathieuc@google.com> |
More robust GC verification and corruption dumping
Added a test for GC heap corruption dumping, added more info to the
dump like adjacent bytes and card table.
Added heap corruption detection in
ConcurrentCopying::MarkNonMoving().
Bug: 37187694
Bug: 12687968
Test: mm test-art-host-gtest-verification_test -j20
Change-Id: I8c90e45796d0784265aa091b2f8082f0cfb62719
|
| 3ed8ec10be0c79e7f7bbe73a754da0daf997b994 |
|
21-Apr-2017 |
Mathieu Chartier <mathieuc@google.com> |
Store java_lang_Object_ in the flip callback
There was a race where the GC thread would not have is_marking =
true, and call
WellKnownClasses::ToClass(WellKnownClasses::java_lang_Object). This
meant that the returned class was maybe in the from-space for the
no image case. The fix was to move this decoding into the flip
callback since this callback is called before flipping any thread
roots.
Bug: 37531237
Bug: 12687968
Test: test-art-host
Change-Id: I9a09249e9c6ea2b3b124e957a9e4b61017869306
|
| a1467d07c4c1e838ff5c07a4ff4ec35aab6a701f |
|
22-Feb-2017 |
Mathieu Chartier <mathieuc@google.com> |
Revert "Revert "Add missing card mark verification to CC""
Add missing write barrier for AddStrongRoot on the dex cache.
Test: test-art-host-run-test ART_TEST_INTERPRETER=true ART_TEST_OPTIMIZING=true ART_TEST_GC_STRESS=true
Bug: 12687968
This reverts commit 50805e747cbb7e9c8d30bd3b49e27ab0741f3cf8.
Change-Id: I72c6de2120d8e0ddc2512dd41010776aecfc9e2c
|
| 50805e747cbb7e9c8d30bd3b49e27ab0741f3cf8 |
|
22-Feb-2017 |
Nicolas Geoffray <ngeoffray@google.com> |
Revert "Add missing card mark verification to CC"
Fails in read-barrier-gcstress for 944-transform-classloaders
Bug: 12687968
This reverts commit 49ba69667ce70f8efbed7d68814ab184bee53486.
Change-Id: Ie91eaa034cea77918235766983661efa14fb1a14
|
| 057d977aed600843dd4a617dca7098555d79110b |
|
18-Feb-2017 |
Hiroshi Yamauchi <yamauchi@google.com> |
Always mark reference referents in transaction mode.
Fix a to-space invariant check failure in EnqueueFinalizerReferences.
Reference processing can be a problem and useless during transaction
because it's not easy to roll back what reference processing does and
there's no daemon threads running (in the unstarted runtime). To avoid
issues, always mark reference referents.
Add a do_atomic_update parameter to MarkHeapReference.
Bug: 35417063
Test: test-art-host with CC/CMS/SS.
Change-Id: If32eba8fca19ef86e5d13f7925d179c8aecb9e27
|
| 49ba69667ce70f8efbed7d68814ab184bee53486 |
|
15-Feb-2017 |
Mathieu Chartier <mathieuc@google.com> |
Add missing card mark verification to CC
Easier than adapting the code in heap.cc to do this. The verification
ensures that objects on clean cards never reference objects in newly
allocated regions.
Revert some changes from aog/341344 that caused the verification to
fail.
Bug: 12687968
Test: test-art-host with CC
Change-Id: Iad583644bb76633ccea0dba87cb383f30adaa80b
|
| 65f5f247a367af9d6b9ac63767b69ecf3ab079bc |
|
19-Dec-2016 |
Hiroshi Yamauchi <yamauchi@google.com> |
Fix race condition btw DelayReferenceRefernent vs Reference.clear().
Rename IsMarkedHeapReference to IsNullOrMarkedHeapReference.
Move the null check from the caller of IsMarkedHeapReference into
IsNullOrMarkedHeapReference.
Make sure that the referent is only loaded once between the null
check and the IsMarked call.
Use a CAS in ConcurrentCopying::IsNullOrMarkedHeapReference when
called from DelayReferenceRefernent.
Bug: 33389022
Test: test-art-host without and with CC.
Change-Id: I20edab4dac2a4bb02dbb72af0f09de77b55ac08e
|
| 31e88225b2ef68e7f32f11186acf922c74ddabab |
|
15-Oct-2016 |
Mathieu Chartier <mathieuc@google.com> |
Move most mirror:: args to ObjPtr
Fixed possible moving GC bugs in ClinitImageUpdate class.
Bug: 31113334
Test: test-art-host
Change-Id: I0bf6578553d58b944aaa17665f1350bdf5ed15ec
|
| febd0cf9b5070ecc54ba433b951b65e14a54ccde |
|
15-Sep-2016 |
Hiroshi Yamauchi <yamauchi@google.com> |
Fix a deadlock in the CC collector.
Fix a deadlock between CC GC disabling system weaks and thread attach.
See 31500969#2 for more details.
Bug: 31500969
Bug: 12687968
Test: test-art-host with CC. N9 libartd boot. Ritz EAAC.
Change-Id: Ic9a8bfb1c636643a03f4580b811fe890273576b6
|
| a5931185c97c7b17981a9fc5016834a0bdd9480b |
|
02-Sep-2016 |
Chih-Hung Hsieh <chh@google.com> |
Fix google-explicit-constructor warnings in art.
* Add explicit keyword to conversion constructors,
or NOLINT for implicit converters.
Bug: 28341362
Test: build with WITH_TIDY=1
Change-Id: I1e1ee2661812944904fedadeff97b620506db47d
|
| bdf7f1c3ab65ccb70f62db5ab31dba060632d458 |
|
31-Aug-2016 |
Andreas Gampe <agampe@google.com> |
ART: SHARED_REQUIRES to REQUIRES_SHARED
This coincides with the actual attribute name and upstream usage.
Preparation for deferring to libbase.
Test: m
Test: m test-art-host
Change-Id: Ia8986b5dfd926ba772bf00b0a35eaf83596d8518
|
| c381c36aacf977f7e314e6a91e47b31b04639f62 |
|
23-Aug-2016 |
Mathieu Chartier <mathieuc@google.com> |
Avoid CAS for marking region space bitmap for baker
Only have the GC thread mark it. This occurs when popping from the
mark stack. The race where an object may be pushed to the mark
stack twice is handled by not scanning if it is already marked.
Also avoid checking is_active when marking from the GC.
EAAC: 1263 -> 1253 (average of 30 runs)
GC time: 7.21s -> 6.83s (average of 18 runs)
Timings on 960 mhz N6P.
Bug: 12687968
Change-Id: I47e98c3e258829d2ba0babd803a219c82a36168c
Test: test-art-host, debug N6P booting with baker CC.
|
| cca44a0d65a4f43662f152d287025366a03162cb |
|
17-Aug-2016 |
Mathieu Chartier <mathieuc@google.com> |
Track cumulative objects and bytes copied for CC
Also print out these values when dumping GC performance info.
Bug: 12687968
Test: Test that values are reasonable after running EAAC.
Change-Id: Id04fadeaf52511560fd4b261f5287ea0a5dae9d4
|
| 962cd7adf3d9d2a1dedf0318056a29e9390f1c38 |
|
16-Aug-2016 |
Mathieu Chartier <mathieuc@google.com> |
Always mark zygote large objects for CC
Prevent needing to gray holders of zygote large objects.
System wide zygote space PSS after boot:
12644 kB -> 5571 kB for CC.
Also PSS reduction in zygote large objects themselves since their
gray bit would have been set each GC.
Overall LOS savings hard to measure, could be up to 316 * 4KB per
app since there are 316 zygote large objects.
Also clear mod-union tables for image spaces to prevent dirty
image pages if any of the image spaces point to zygote large objects.
System wide .art mmap: 37432 kB -> 34372 kB
System server before (N6P):
LOS shared dirty: 12888 kB
Zygote space shared dirty: 700 kB
Zygote space private dirty: 868 kB
.art private dirty: 1696 kB
After:
LOS shared dirty 13672 kB
Zygote space shared dirty: 1072 kB
Zygote space private dirty: 496 kB
.art private dirty: 1432 kB
Bug: 29516968
Test: test-art-host with baker CC, debug N6P phone booting
Change-Id: Ia37ce2c11217cf56885bd1d1dc084332fcbb7843
|
| 36a270ae4f288e49493432b7128f899ad579849e |
|
29-Jul-2016 |
Mathieu Chartier <mathieuc@google.com> |
Change one read barrier bit to mark bit
Optimization to help slow path performance. When the GC marks an
object through the read barrier slow path. The GC sets the mark bit
in the lock word of that reference. This bit is checked from the
assembly entrypoint the common case is that it is set. If the bit is
set, the read barrier knows the object is already marked and there is
no work to do.
To prevent dirty pages in zygote and image, the bit is set by the
image writer and zygote space creation.
EAAC score (lower is better):
N9: 777 -> 700 (average 31 of runs)
N6P (960000 mhz): 1737.48 -> 1442.31 (average of 25 runs)
Bug: 30162165
Bug: 12687968
Test: N9, N6P booting, test-art-host, test-art-target all with CC
Change-Id: Iae0cacfae221e33151d3c0ab65338d1c822ab63d
|
| d6636d3440efc68e1fa43f437ffbe77581096399 |
|
28-Jul-2016 |
Mathieu Chartier <mathieuc@google.com> |
Avoid read barrier for IntArray::GetArrayClass
Changed the code use Mark instead of read barrier, this showed an
existing lock violation and possible deadlock which was fixed.
Prevent DCHECK failure from the assert.
Bug: 30469265
Test: test-art-host with CC
Change-Id: I275f953f06f6d13262043fc62eb88dca0356465a
|
| 21328a15e15005815efc843e774ac6974e94d4d8 |
|
22-Jul-2016 |
Mathieu Chartier <mathieuc@google.com> |
Improve CC handling for immune objects
Currently we reduce ram for immune objects by racing agianst the
mutators to try and finish processing them before the mutators
change many objects to gray. However there is still a window of time
where the mutator can dirty immune pages by changing the lock words
to gray. These pages remain dirty for the lifetime of the app.
This CL changes uses the FlipCallback pause to gray all of the
immune objects that have a dirty card. Once these objects are all
gray we don't to gray any more objects in the immune spaces since
these objects are the only ones that may reference non immune
objects.
Also only scan objects that are gray when scanning immune spaces to
reduce scanning time.
System wide PSS after boot on N9, before:
61668 kB: .art mmap
11249 kB: .Zygote
After:
36013 kB: .art mmap
12251 kB: .Zygote
Results are better than demonstrated since there are more apps
running after.
Maps PSS / Private Dirty, before:
.art mmap 3703 3116
.Zygote 577 480
After:
.art mmap 1655 1092
.Zygote 476 392
System server before:
.art mmap 4453 3956
.Zygote 849 780
After:
.art mmap 2326 1748
.Zygote 640 564
EAAC:
Before:
ScanImmuneSpaces takes 669.434ms GC time
Scores: 718, 761, 753 average 744
GC time: 4.2s, 4.35s, 4.3s average 4.28s
After:
ScanImmuneSpaces takes 138.328ms GC time
Scores: 731, 730, 704 average 722
GC time: 3.92s, 3.83s, 3.85s average 3.87s
Additional GC pause time is 285us on Maps on N9.
TODO: Reduce this pause time.
Test: N9 booting, test-art-host, EAAC all run with CC
Bug: 29516968
Bug: 12687968
Change-Id: I584b10d017547b321f33eb23fb5d64372af6f69c
|
| 56fe25895e91d34a0a017429468829a20bdd5ae4 |
|
14-Jul-2016 |
Mathieu Chartier <mathieuc@google.com> |
Add a way to measure read barrier slow paths
If enabled, this option counts number of slow paths, measures the
total slow path time per GC and records the info into a histogram.
Also added support for systrace to see which threads are performing
slow paths.
Added runtime option -Xgc:measure to enable. The info is dumped
for SIGQUIT.
Test: Volantis boot with CC, test-art-host with CC, run EEAC with CC
and -Xgc:measure
Bug: 30162165
Change-Id: I3c2bdb4156065249c45695f13c77c0579bc8e57a
|
| d8db5a22d8a2cffc75f4b080cbafef5e04800244 |
|
28-Jun-2016 |
Hiroshi Yamauchi <yamauchi@google.com> |
Revert "Revert "Gray only immune objects mutators access.""
To reduce image/zygote dirty pages.
GC doesn't gray immune space objects except when visiting the thread
GC roots of suspended threads during the thread flip and in
FillWithDummyObject(). GC updates the fields of immune space objects
without pushing/popping them through the mark stack. GC sets a bool
flag after updating the fields of immune space objects. After this
point, mutators don't need gray to immune space objects. Removed the
mark bitmaps for immune spaces.
This reverts commit ddeb172eeedb58ab96e074a55a0d1578b5df4110.
Bug: 29516465
Bug: 12687968
Test: art tests, libartd device boot, ritzperf, jdwp test.
Change-Id: If272373aea3d41b2719e40a6a41f44d9299ba309
|
| ddeb172eeedb58ab96e074a55a0d1578b5df4110 |
|
28-Jun-2016 |
Nicolas Geoffray <ngeoffray@google.com> |
Revert "Gray only immune objects mutators access."
Fails with:
art F 11338 11338 art/runtime/gc/collector/concurrent_copying-inl.h:83] Check failed: !kGrayImmuneObject || updated_all_immune_objects_.LoadRelaxed() || gc_grays_immune_objects_
Bug: 29516465
Bug: 12687968
This reverts commit 16292fcc98f03690576d0739b2e5fb04b375933c.
Change-Id: I1d2d988b7707e03cc94f019cf8bef5b9a9099060
|
| 16292fcc98f03690576d0739b2e5fb04b375933c |
|
21-Jun-2016 |
Hiroshi Yamauchi <yamauchi@google.com> |
Gray only immune objects mutators access.
To reduce image/zygote dirty pages.
GC doesn't gray immune space objects except when visiting the thread
GC roots of suspended threads during the thread flip. GC updates the
fields of immune space objects without pushing/popping them through
the mark stack. GC sets a bool flag after updating the fields of
immune space objects. After this point, mutators don't need gray to
immune space objects. Removed the mark bitmaps for immune spaces.
Bug: 29516465
Bug: 12687968
Test: art tests, libartd device boot, ritzperf.
Change-Id: Idfcffbdb94dfc8bfc89c30d6aff8888f04990a56
|
| 8016bdee7ca1a066221a5d2fe5e60890de950a5b |
|
16-Jun-2016 |
Mathieu Chartier <mathieuc@google.com> |
Use collector specific helper classes
Changed to use inner classes. Also changed some visitors to lambdas.
Bug: 29413717
Bug: 19534862
(cherry picked from commit a07f55913824ab4215a9a4f827fa9c043c0d44d9)
Change-Id: I631c8bfe5f795eda4623c5bb4f357f2dd12358e2
|
| a07f55913824ab4215a9a4f827fa9c043c0d44d9 |
|
16-Jun-2016 |
Mathieu Chartier <mathieuc@google.com> |
Use collector specific helper classes
Changed to use inner classes. Also changed some visitors to lambdas.
Bug: 29413717
Bug: 19534862
Change-Id: I631c8bfe5f795eda4623c5bb4f357f2dd12358e2
|
| daf61a19177e23beed4bff0134a825d7e5a9207b |
|
10-Jun-2016 |
Hiroshi Yamauchi <yamauchi@google.com> |
Disable the CC collector / read barrier checks in non-debug build.
Bug: 12687968
Change-Id: Ia8295354b705018ffa864eb8101aa5c09528af13
|
| 8e67465aa57ee58425be8812c8dba2f7f59cdc2e |
|
22-Dec-2015 |
Hiroshi Yamauchi <yamauchi@google.com> |
Avoid the need for the black color for the baker-style read barrier.
We used to set marked-through non-moving objects to black to
distinguish between an unmarked object and a marked-through
object (both would be white without black). This was to avoid a rare
case where a marked-through (white) object would be incorrectly set to
gray for a second time (and left gray) after it's marked
through (white/unmarked -> gray/marked -> white/marked-through ->
gray/incorrect). If an object is left gray, the invariant would be
broken that all objects are white when GC isn't running. Also, we
needed to have an extra pass over non-moving objects to change them
from black to white after the marking phase.
To avoid the need for the black color, we use a 'false gray' stack to
detect such rare cases and register affected objects on it and change
the objects to white at the end of the marking phase. This saves some
GC time because we can avoid the gray-to-black CAS per non-moving
object as well as the extra pass over non-moving objects.
Ritzperf EAAC (N6):
Avg GC time: 232 -> 183 ms (-21%)
Total GC time: 15.3 -> 14.1 s (-7.7%)
Bug: 12687968
Change-Id: Idb29c3dcb745b094bcf6abc4db646dac9cbd1f71
|
| 3c448933bea6af7362fb8eb48c24292bb5fba2ef |
|
23-Jan-2016 |
Hiroshi Yamauchi <yamauchi@google.com> |
Disable the CC collector verbose log.
To reduce the amount of buildbot libcore test logs.
Bug: 12687968
Change-Id: Idadca6622c745ef12629ccb26dcbdc9ebc379a00
|
| 763a31ed7a2bfad22a9cb07f5301a71c0f97ca49 |
|
17-Nov-2015 |
Mathieu Chartier <mathieuc@google.com> |
Add immune spaces abstraction
ImmuneSpaces is a set of spaces which are not reclaimable by the GC in
the current collection. This set of spaces does not have requirements
about space adjacency like the old ImmuneRegion. ImmuneSpaces generates
the largest immune region for the GC. Since there is no requirement on
adjacency, it is possible to have multiple non-adjacent applicaton
image files.
For image spaces, we also look at the oat code which is normally after
the application image. In this case, we add the code as part of the
immune region. This is required to have both the boot image and the
zygote space be in the same immune region (for performance reasons).
Bug: 22858531
Change-Id: I5103b31c0e39ad63c594f5557fc848a3b288b43e
|
| 723e6cee35671d2dd9aeb884dd11f6994307c01f |
|
29-Oct-2015 |
Hiroshi Yamauchi <yamauchi@google.com> |
Minor improvements for the CC collector.
- Split Mark() and inline its first part.
- Make sure some other routines are inlined.
- Add some UNLIKELY's.
- Use VisitConcurrentRoots().
Ritz EAAC GC time decreased from 28.9 -> 27.6s (-4.5%) on N5.
Bug: 12687968
Change-Id: I7bd13f162e7daa2a5853000fb22c5fefc318994f
|
| 19eab409b3efab3889885b71db708fbe56594088 |
|
24-Oct-2015 |
Hiroshi Yamauchi <yamauchi@google.com> |
Make the mark stack expandable for the CC collector.
Bug: 12687968
Change-Id: I5d05df5524f54c6adb964901e5a963eb042cb2e1
|
| 00370827646cc21cb370c3e7e93f9c0cff4c30c2 |
|
18-Aug-2015 |
Hiroshi Yamauchi <yamauchi@google.com> |
Use thread-local is_gc_marking flags for the CC collector.
The currently global is_marking flag is used to check if the read
barrier slow path needs to be taken for GC roots access. Changing it
to a thread-local flag simplifies the fast path check and makes it
easier to do it in assembly code. It also solves the issue that we
need to avoid accessing the global flag during startup before the heap
or the collector object isn't allocated and initialized.
Bug: 12687968
Change-Id: Ibf0dca12f400bf3490188b12dfe96c7de30583e0
|
| a4f6af9b1e6380b31674d7ac645b1732c846ac06 |
|
12-Aug-2015 |
Mathieu Chartier <mathieuc@google.com> |
Some heap cleanup
Bug: 19534862
Change-Id: Ia63f489d26ec8813a263ce877bdbbc8c4e8fe5f4
|
| da7c650022a974be10e2f00fa07d5109e3d8826f |
|
24-Jul-2015 |
Mathieu Chartier <mathieuc@google.com> |
Visit class native roots from VisitReferences
Visit class roots when we call Class::VisitReferences instead of in
the class linker. This makes it easier to implement class unloading
since unmarked classes won't have their roots visited by the class
linker.
Bug: 22181835
Change-Id: I63f31e5ebef7b2a0b764b3ba3cb038b3f561b379
|
| 90443477f9a0061581c420775ce3b7eeae7468bc |
|
17-Jul-2015 |
Mathieu Chartier <mathieuc@google.com> |
Move to newer clang annotations
Also enable -Wthread-safety-negative.
Changes:
Switch to capabilities and negative capabilities.
Future work:
Use capabilities to implement uninterruptible annotations to work
with AssertNoThreadSuspension.
Bug: 20072211
Change-Id: I42fcbe0300d98a831c89d1eff3ecd5a7e99ebf33
|
| 8118781ebc9659f806716c451bdb3fe9b77ae32b |
|
15-Jul-2015 |
Mathieu Chartier <mathieuc@google.com> |
Address some GC comments
Follow-up from:
https://android-review.googlesource.com/#/c/159650/
Change-Id: Id14f29b4ce5b70b63fcb3e74f8503ae60a3ae444
|
| 97509954404d031594b2ecbda607314d169d512e |
|
13-Jul-2015 |
Mathieu Chartier <mathieuc@google.com> |
Clean up GC callbacks to be virtual methods
Change-Id: Ia08034a4e5931c4fcb329c3bd3c4b1f301135735
|
| 0b71357fb52be9bb06d35396a3042b4381b01041 |
|
17-Jun-2015 |
Hiroshi Yamauchi <yamauchi@google.com> |
Thread-local mark stacks for the CC collector.
Thread-local mark stacks are assigned to mutators where they push
references in read barriers to reduce the (CAS) synchronization cost
in a global mark stack/queue.
We step through three mark stack modes (thread-local, shared,
GC-exclusive) and use per-thread flags to disable/enable system weak
accesses (only for the CC collector) instead of the existing global
one to safely perform the marking phase. The reasons are 1)
thread-local mark stacks for mutators need to be revoked using a
checkpoint to avoid races (incorrectly leaving a reference on mark
stacks) when terminating marking, and 2) we can’t use a checkpoint
while system weak accesses are disabled (or a deadlock would
happen). More details are described in the code comments.
Performance improvements in Ritzperf EAAC: a ~2.8% improvement
(13290->12918) in run time and a ~23% improvement (51.6s->39.8s) in
the total GC time on N5.
Bug: 12687968
Change-Id: I5d234d7e48bf115cd773d38bdb62ad24ce9116c7
|
| 3f64f25151780fdea3511be62b4fe50775f86541 |
|
13-Jun-2015 |
Hiroshi Yamauchi <yamauchi@google.com> |
Print more diagnosis info on to-space invariant violation.
Pass the method/field (in GcRootSource) to the read barrier to print
more info when a to-space invariant violation is detected on a
method/field GC root access.
Refactor ConcurrentCopying::AssertToSpaceInvariant().
Bug: 12687968
Bug: 21564728
Change-Id: I3a5fde1f41969349b0fee6cd9217b948d5241a7c
|
| 414369a2e3f23e1408fc1cbf4f623014bd95cb8f |
|
04-May-2015 |
Mathieu Chartier <mathieuc@google.com> |
Add some more DISALLOW_COPY_AND_ASSIGN
May help prevent bugs maybe.
(cherry picked from commit 3130cdf29eb203be0c38d1107a65d920ec39c106)
Change-Id: Ie73d469dfcd078492ecb3aa28682b42707221202
|
| 3130cdf29eb203be0c38d1107a65d920ec39c106 |
|
04-May-2015 |
Mathieu Chartier <mathieuc@google.com> |
Add some more DISALLOW_COPY_AND_ASSIGN
May help prevent bugs maybe.
Change-Id: Ie73d469dfcd078492ecb3aa28682b42707221202
|
| 65b798ea10dd716c1bb3dda029f9bf255435af72 |
|
06-Apr-2015 |
Andreas Gampe <agampe@google.com> |
ART: Enable more Clang warnings
Change-Id: Ie6aba02f4223b1de02530e1515c63505f37e184c
|
| bb87e0f1a52de656bc77cb01cb887e51a0e5198b |
|
03-Apr-2015 |
Mathieu Chartier <mathieuc@google.com> |
Refactor and improve GC root handling
Changed GcRoot to use compressed references. Changed root visiting to
use virtual functions instead of function pointers. Changed root visting
interface to be an array of roots instead of a single root at a time.
Added buffered root marking helper to avoid dispatch overhead.
Root marking seems a bit faster on EvaluateAndApplyChanges due to batch
marking. Pause times unaffected.
Mips64 is untested but might work, maybe.
Before:
MarkConcurrentRoots: Sum: 67.678ms 99% C.I. 2us-664.999us Avg: 161.138us Max: 671us
After:
MarkConcurrentRoots: Sum: 54.806ms 99% C.I. 2us-499.986us Avg: 136.333us Max: 602us
Bug: 19264997
Change-Id: I0a71ebb5928f205b9b3f7945b25db6489d5657ca
|
| e15ea086439b41a805d164d2beb07b4ba96aaa97 |
|
10-Feb-2015 |
Hiroshi Yamauchi <yamauchi@google.com> |
Reserve bits in the lock word for read barriers.
This prepares for the CC collector to use the standard object header
model by storing the read barrier state in the lock word.
Bug: 19355854
Bug: 12687968
Change-Id: Ia7585662dd2cebf0479a3e74f734afe5059fb70f
|
| cb535da36915f9d10bec3880b46f1de1f7a69f22 |
|
23-Jan-2015 |
Mathieu Chartier <mathieuc@google.com> |
Change AtomicStack to use StackReference
Previously used Object*, using StackReference saves memory on 64 bit
devices.
Bug: 12935052
Bug: 17643507
Change-Id: I035878690054eeeb24d655a900b8f26c837703ff
|
| 6c08a453c7fac58388bcf4cd521b4075ef5840d9 |
|
24-Jan-2015 |
Andreas Gampe <agampe@google.com> |
ART: Fix new[] / delete mismatch
The type of the unique_ptr in MarkQueue should be an array type,
as it is holding an array, actually.
Change-Id: If1d05a1d52cd58a373f240f7156fc69b70324298
|
| 2cd334ae2d4287216523882f0d298cf3901b7ab1 |
|
09-Jan-2015 |
Hiroshi Yamauchi <yamauchi@google.com> |
More of the concurrent copying collector.
Bug: 12687968
Change-Id: I62f70274d47df6d6cab714df95c518b750ce3105
|
| 6a3c1fcb4ba42ad4d5d142c17a3712a6ddd3866f |
|
31-Oct-2014 |
Ian Rogers <irogers@google.com> |
Remove -Wno-unused-parameter and -Wno-sign-promo from base cflags.
Fix associated errors about unused paramenters and implict sign conversions.
For sign conversion this was largely in the area of enums, so add ostream
operators for the effected enums and fix tools/generate-operator-out.py.
Tidy arena allocation code and arena allocated data types, rather than fixing
new and delete operators.
Remove dead code.
Change-Id: I5b433e722d2f75baacfacae4d32aef4a828bfe1b
|
| 6f365cc033654a5a3b45eaa1379d4b5f156b0cee |
|
23-Apr-2014 |
Mathieu Chartier <mathieuc@google.com> |
Enable concurrent sweeping for non-concurrent GC.
Refactored the GarbageCollector to let all of the phases be run by
the collector's RunPhases virtual method. This lets the GC decide
which phases should be concurrent and reduces how much baked in GC
logic resides in GarbageCollector.
Enabled concurrent sweeping in the semi space and non concurrent
mark sweep GCs. Changed the semi-space collector to have a swap semi
spaces boolean which can be changed with a setter.
Fixed tests to pass with GSS collector, there was an error related to
the large object space limit.
Before (EvaluateAndApplyChanges):
GSS paused GC time 7.81s/7.81s, score: 3920
After (EvaluateAndApplyChanges):
GSS paused GC time 6.94s/7.71s, score: 3900
Benchmark score doesn't go up since the GC happens in the allocating
thread. There is a slight reduction in pause times experienced by
other threads (0.8s total).
Added options for pre sweeping GC heap verification and pre sweeping
rosalloc verification.
Bug: 14226004
Bug: 14250892
Bug: 14386356
Change-Id: Ib557d0590c1ed82a639d0f0281ba67cf8cae938c
|
| d5307ec41c8344be0c32273ec4f574064036187d |
|
28-Mar-2014 |
Hiroshi Yamauchi <yamauchi@google.com> |
An empty collector skeleton for a read barrier-based collector.
Bug: 12687968
Change-Id: Ic2a3a7b9943ca64e7f60f4d6ed552a316ea4a6f3
|