4460a84be92b5a94ecfb5c650aef4945ab849c93 |
|
09-Mar-2015 |
Hiroshi Yamauchi <yamauchi@google.com> |
Rosalloc thread local allocation path without a cas. Speedup on N4: MemAllocTest 3044 -> 2396 (~21% reduction) BinaryTrees 4101 -> 2929 (~26% reduction) Bug: 9986565 Change-Id: Ia1d1a37b9e001f903c3c056e8ec68fc8c623a78b
|
5c42c29b89286e5efa4a4613132b09051ce5945b |
|
25-Feb-2015 |
Vladimir Marko <vmarko@google.com> |
Add support for .bss section in oat files. Change-Id: I779b80b8139d9afdc28373f8c68edff5df7726ce
|
2cd334ae2d4287216523882f0d298cf3901b7ab1 |
|
09-Jan-2015 |
Hiroshi Yamauchi <yamauchi@google.com> |
More of the concurrent copying collector. Bug: 12687968 Change-Id: I62f70274d47df6d6cab714df95c518b750ce3105
|
277ccbd200ea43590dfc06a93ae184a765327ad0 |
|
04-Nov-2014 |
Andreas Gampe <agampe@google.com> |
ART: More warnings Enable -Wno-conversion-null, -Wredundant-decls and -Wshadow in general, and -Wunused-but-set-parameter for GCC builds. Change-Id: I81bbdd762213444673c65d85edae594a523836e5
|
2c4257be8191c5eefde744e8965fcefc80a0a97d |
|
24-Oct-2014 |
Ian Rogers <irogers@google.com> |
Tidy logging code not using UNIMPLEMENTED. Change-Id: I7a79c1671a6ff8b2040887133b3e0925ef9a3cfe
|
13735955f39b3b304c37d2b2840663c131262c18 |
|
08-Oct-2014 |
Ian Rogers <irogers@google.com> |
stdint types all the way! Change-Id: I4e4ef3a2002fc59ebd9097087f150eaf3f2a7e08
|
38c488bcd41ba632a646d7a1d790ec71a2fcf6fa |
|
16-Jul-2014 |
Mathieu Chartier <mathieuc@google.com> |
Recycle mem-maps for collector transitions. We now create spaces when we need them for collector transitions or homogeneous compaction by recycling mem maps. Change the bump pointer space size to be as large as the heap capacity instead of 1/2 heap capacity like it used to be. For GSS, bump pointer spaces are set to 32MB currently. Changed GSS to have main space == non moving space since we don't need to copy from the main space. Fixes GC stress tests 074, 096. Fixed test 080 oom throw with -Xmx2m for GC stress test, this was broken since it was allocating a 4 MB array before starting the OOM process. Bug: 14059466 Bug: 16406852 (cherry picked from commit b363f666883860d40823d5528df3c98c897f74f4) Change-Id: I62877cfa24ec944a6f34ffac30334f454a8002fd
|
b363f666883860d40823d5528df3c98c897f74f4 |
|
16-Jul-2014 |
Mathieu Chartier <mathieuc@google.com> |
Recycle mem-maps for collector transitions. We now create spaces when we need them for collector transitions or homogeneous compaction by recycling mem maps. Change the bump pointer space size to be as large as the heap capacity instead of 1/2 heap capacity like it used to be. For GSS, bump pointer spaces are set to 32MB currently. Changed GSS to have main space == non moving space since we don't need to copy from the main space. Fixes GC stress tests 074, 096. Fixed test 080 oom throw with -Xmx2m for GC stress test, this was broken since it was allocating a 4 MB array before starting the OOM process. Bug: 14059466 Bug: 16406852 Change-Id: I62877cfa24ec944a6f34ffac30334f454a8002fd
|
c5f17732d8144491c642776b6b48c85dfadf4b52 |
|
06-Jun-2014 |
Ian Rogers <irogers@google.com> |
Remove deprecated WITH_HOST_DALVIK. Bug: 13751317 Fix the Mac build: - disable x86 selector removal that causes OS/X 10.9 kernel panics, - madvise don't need does zero memory on the Mac, factor into MemMap routine, - switch to the elf.h in elfutils to avoid Linux kernel dependencies, - we can't rely on exclusive_owner_ being available from other pthread libraries so maintain our own when futexes aren't available (we can't rely on the OS/X 10.8 hack any more), - fix symbol naming in assembly code, - work around C library differences, - disable backtrace in DumpNativeStack to avoid a broken libbacktrace dependency, - disable main thread signal handling logic, - align the stack in stub_test, - use $(HOST_SHLIB_SUFFIX) rather than .so in host make file variables. Not all host tests are passing on the Mac with this change. dex2oat works as does running HelloWorld. Change-Id: I5a232aedfb2028524d49daa6397a8e60f3ee40d3
|
3e5cf305db800b2989ad57b7cde8fb3cc9fa1b9e |
|
21-May-2014 |
Ian Rogers <irogers@google.com> |
Begin migration of art::Atomic to std::atomic. Change-Id: I4858d9cbed95e5ca560956b9dabd976cebe68333
|
700a402244a1a423da4f3ba8032459f4b65fa18f |
|
20-May-2014 |
Ian Rogers <irogers@google.com> |
Now we have a proper C++ library, use std::unique_ptr. Also remove the Android.libcxx.mk and other bits of stlport compatibility mechanics. Change-Id: Icdf7188ba3c79cdf5617672c1cfd0a68ae596a61
|
a8e8f9c0a8e259a807d7b99a148d14104c24209d |
|
09-Apr-2014 |
Mathieu Chartier <mathieuc@google.com> |
Refactor space bitmap to support different alignments. Required for: Using space bitmaps instead of std::set in mod union table + remembered set. Using a bitmap instead of set for large object marking. Bug: 13571028 Change-Id: Id024e9563d4ca4278f79607cdb2f81895121b113
|
31f441464c0c8f840aba37e236ad133f30308d70 |
|
08-Apr-2014 |
Mathieu Chartier <mathieuc@google.com> |
Clean-up heap spaces. We now use the CMS collector instead of the semispace collector when the phone is booting. We still perform compaction during the zygote space creation. This reduces time spent in GC by ~2s during boot and doesn't affect zygote space size. Changed the space creation logic to create the temp space when a background transition occurs. Added a flag to each space which is true if you are allowed to move objects that are within this space. Removed SwapSemiSpaces call from the semi space collector, it is now the job of the caller to do this with threads suspended. This simplifies the logic in the zygote compaction / heap transition code since these do not copy from one semispace to another. Added Space::Clear to RosAllocSpace and DlMallocSpace. This greatly simplifies the code used for collector transitions. Time spent in GC creating zygote space: Before: 3.4s, After: 1.28s No change in zygote space size. Bug: 13878055 Change-Id: I700348ab7d5bf3aa537c0cd70c0fed09aa4b0623
|
dd7624d2b9e599d57762d12031b10b89defc9807 |
|
15-Mar-2014 |
Ian Rogers <irogers@google.com> |
Allow mixing of thread offsets between 32 and 64bit architectures. Begin a more full implementation x86-64 REX prefixes. Doesn't implement 64bit thread offset support for the JNI compiler. Change-Id: If9af2f08a1833c21ddb4b4077f9b03add1a05147
|
c93c530efc175954160c3834c93961a1a946a35a |
|
21-Mar-2014 |
Hiroshi Yamauchi <yamauchi@google.com> |
Revoke rosalloc thread-local buffers at the checkpoint. In the mark sweep collector, rosalloc thread-local buffers were revoked during the pause. Now, they are revoked at the thread checkpoint, as opposed to during the pause, which appears to help reduce the pause time. In Ritz MemAllocTest, the average sticky pause time went down ~20% (925 us -> 724 us). Bug: 13394464 Bug: 9986565 Change-Id: I104992a11b46d59264c0b9aa2db82b1ccf2826bc
|
15d3402bbf8265eb1165694da2e4117eb128f3bc |
|
27-Feb-2014 |
Mathieu Chartier <mathieuc@google.com> |
Add custom SIGSEGV handler to help find heap corruption. The new signal handler prints heap diagnostics when you get a SIGSEGV. Added a fault message member in runtime which is modifiable by Runtime::SetFaultMessage. When you get a SIGSEGV it will print out whatever is stored in this string as well as the normal information. This is useful for debugging heap corruption since it lets you see which threads were in which methods when the last GC occured. Added some smarter object dumping logic when the faulting address is in the heap. Bug: 12934910 Change-Id: Ia72be2c39f70ad711cbd746d66fad2b617d5d29f
|
6fac447555dc94a935b78198479cce645c837b89 |
|
26-Feb-2014 |
Ian Rogers <irogers@google.com> |
Make allocations report usable size. Work-in-progress to allow arrays to fill usable size. Bug: 13028925. Use C++11's override keyword on GCC >= 2.7 to ensure that we override GC and allocator methods. Move initial mirror::Class set up into a Functor so that all allocated objects have non-zero sizes. Use this property to assert that all objects are never larger than their usable size. Other bits of GC related clean-up, missing initialization, missing use of const, hot methods in .cc files, "unimplemented" functions that fail at runtime in header files, reducing header file includes, move valgrind's space into its own files, reduce number of array allocation routines. Change-Id: Id5760041a2d7f94dcaf17ec760f6095ec75dadaa
|
8544b462b524a502d2a18efb5a790ef98fa5eb51 |
|
13-Feb-2014 |
Mathieu Chartier <mathieuc@google.com> |
Fix race condition in BumpPointerSpace::Walk. There was a race where we would incorrectly tread part of the main block as other blocks. This was caused by a thread allocating into the bump pointer space when another thread was walking it. The new solution is to ignore objects allocated since we started the walk. Bug: 12966354 Change-Id: I49abd4de97609e9c9a3fae40b9c159abfdbbd07c
|
fc4c27e4d68707271bd7578ae5c8bef93a3ea66b |
|
11-Feb-2014 |
Mathieu Chartier <mathieuc@google.com> |
Change BumpPointerSpace main block header to not be in space data. Changed the bump pointer space main block to be in the space and not the space data. This lets us access the main block header when the space is protected and lets us walk a protected space as long as it is empty. Bug: 12966354 Change-Id: Id53bf59224926718af7356dd9fc1205ff91cc5d1
|
83c8ee000d525017ead8753fce6bc1020249b96a |
|
28-Jan-2014 |
Mathieu Chartier <mathieuc@google.com> |
Add root types and thread id to root visiting. Enables us to pass the root type and thread id to hprof. Bug: 12680863 Change-Id: I6a0f1f9e3aa8f9b4033d695818ae7ca3460d67cb
|
ef7d42fca18c16fbaf103822ad16f23246e2905d |
|
06-Jan-2014 |
Ian Rogers <irogers@google.com> |
Object model changes to support 64bit. Modify mirror objects so that references between them use an ObjectReference value type rather than an Object* so that functionality to compress larger references can be captured in the ObjectRefererence implementation. ObjectReferences are 32bit and all other aspects of object layout remain as they are currently. Expand fields in objects holding pointers so they can hold 64bit pointers. Its expected the size of these will come down by improving where we hold compiler meta-data. Stub out x86_64 architecture specific runtime implementation. Modify OutputStream so that reads and writes are of unsigned quantities. Make the use of portable or quick code more explicit. Templatize AtomicInteger to support more than just int32_t as a type. Add missing, and fix issues relating to, missing annotalysis information on the mutator lock. Refactor and share implementations for array copy between System and uses elsewhere in the runtime. Fix numerous 64bit build issues. Change-Id: I1a5694c251a42c9eff71084dfdd4b51fff716822
|
e6da9af8dfe0a3e3fbc2be700554f6478380e7b9 |
|
16-Dec-2013 |
Mathieu Chartier <mathieuc@google.com> |
Background compaction support. When the process state changes to a state which does not perceives jank, we copy from the main free-list backed allocation space to the bump pointer space and enable the semispace allocator. When we transition back to foreground, we copy back to a free-list backed space. Create a seperate non-moving space which only holds non-movable objects. This enables us to quickly wipe the current alloc space (DlMalloc / RosAlloc) when we transition to background. Added multiple alloc space support to the sticky mark sweep GC. Added a -XX:BackgroundGC option which lets you specify which GC to use for background apps. Passing in -XX:BackgroundGC=SS makes the heap compact the heap for apps which do not perceive jank. Results: Simple background foreground test: 0. Reboot phone, unlock. 1. Open browser, click on home. 2. Open calculator, click on home. 3. Open calendar, click on home. 4. Open camera, click on home. 5. Open clock, click on home. 6. adb shell dumpsys meminfo PSS Normal ART: Sample 1: 88468 kB: Dalvik 3188 kB: Dalvik Other Sample 2: 81125 kB: Dalvik 3080 kB: Dalvik Other PSS Dalvik: Total PSS by category: Sample 1: 81033 kB: Dalvik 27787 kB: Dalvik Other Sample 2: 81901 kB: Dalvik 28869 kB: Dalvik Other PSS ART + Background Compaction: Sample 1: 71014 kB: Dalvik 1412 kB: Dalvik Other Sample 2: 73859 kB: Dalvik 1400 kB: Dalvik Other Dalvik other reduction can be explained by less deep allocation stacks / less live bitmaps / less dirty cards. TODO improvements: Recycle mem-maps which are unused in the current state. Not hardcode 64 MB capacity of non movable space (avoid returning linear alloc nightmares). Figure out ways to deal with low virtual address memory problems. Bug: 8981901 Change-Id: Ib235d03f45548ffc08a06b8ae57bf5bada49d6f3
|
b122a4bbed34ab22b4c1541ee25e5cf22f12a926 |
|
20-Nov-2013 |
Ian Rogers <irogers@google.com> |
Tidy up memory barriers. Change-Id: I937ea93e6df1835ecfe2d4bb7d84c24fe7fc097b
|
692fafd9778141fa6ef0048c9569abd7ee0253bf |
|
30-Nov-2013 |
Mathieu Chartier <mathieuc@google.com> |
Thread local bump pointer allocator. Added a thread local allocator to the heap, each thread has three pointers which specify the thread local buffer: start, cur, and end. When the remaining space in the thread local buffer isn't large enough for the allocation, the allocator allocates a new thread local buffer using the bump pointer allocator. The bump pointer space had to be modified to accomodate thread local buffers. These buffers are called "blocks", where a block is a buffer which contains a set of adjacent objects. Blocks aren't necessarily full and may have wasted memory towards the end. Blocks have an 8 byte header which specifies their size and is required for traversing bump pointer spaces. Memory usage is in between full bump pointer and ROSAlloc since madvised memory limits wasted ram to an average of 1/2 page per block. Added a runtime option -XX:UseTLAB which specifies whether or not to use the thread local allocator. Its a NOP if the garbage collector is not the semispace collector. TODO: Smarter block accounting to prevent us reading objects until we either hit the end of the block or GetClass() == null which signifies that the block isn't 100% full. This would provide a slight speedup to BumpPointerSpace::Walk. Timings: -XX:HeapMinFree=4m -XX:HeapMaxFree=8m -Xmx48m ritzperf memalloc: Dalvik -Xgc:concurrent: 11678 Dalvik -Xgc:noconcurrent: 6697 -Xgc:MS: 5978 -Xgc:SS: 4271 -Xgc:CMS: 4150 -Xgc:SS -XX:UseTLAB: 3255 Bug: 9986565 Bug: 12042213 Change-Id: Ib7e1d4b199a8199f3b1de94b0a7b6e1730689cad
|
590fee9e8972f872301c2d16a575d579ee564bee |
|
13-Sep-2013 |
Mathieu Chartier <mathieuc@google.com> |
Compacting collector. The compacting collector is currently similar to semispace. It works by copying objects back and forth between two bump pointer spaces. There are types of objects which are "non-movable" due to current runtime limitations. These are Classes, Methods, and Fields. Bump pointer spaces are a new type of continuous alloc space which have no lock in the allocation code path. When you allocate from these it uses atomic operations to increase an index. Traversing the objects in the bump pointer space relies on Object::SizeOf matching the allocated size exactly. Runtime changes: JNI::GetArrayElements returns copies objects if you attempt to get the backing data of a movable array. For GetArrayElementsCritical, we return direct backing storage for any types of arrays, but temporarily disable the GC until the critical region is completed. Added a new runtime call called VisitObjects, this is used in place of the old pattern which was flushing the allocation stack and walking the bitmaps. Changed image writer to be compaction safe and use object monitor word for forwarding addresses. Added a bunch of added SIRTs to ClassLinker, MethodLinker, etc.. TODO: Enable switching allocators, compacting on background, etc.. Bug: 8981901 Change-Id: I3c886fd322a6eef2b99388d19a765042ec26ab99
|