| 95adf1ff81dec324746bef58ba8c45dc1c8f3b50 |
|
22-Aug-2013 |
Mathieu Chartier <mathieuc@google.com> |
Fix native allocation tracking on Dalvik.
Fixed issue where we had inverted logic when checking for
pending exceptions.
Changed the logic to not update the native allocation watermarks
after concurrent GC since the finalizers may not have been run at
this point.
Copied over the test from ART for ensuring that it is working.
Bug: 10444866
Change-Id: Ie26170f9c4703f11e993233cdc9c5f46396fca84
|
| eeb18914e487b4ae8c8702fc390fd1a360c768ae |
|
15-Jul-2013 |
Hiroshi Yamauchi <yamauchi@google.com> |
Show size/alloc/free per Dalvik heap space in dumpsys
Add the heap size/alloc/free stats to the Dalvik heap space breakdown section in dumpsys meminfo.
Also, now the zygote heap has a distict ashmem region name.
Bug: 9532137
Bug: 8266259
(cherry picked from commit 3edfe0b32753309ad7dcccd894239cb0a8aefb85)
Change-Id: I9b32727e4211f571a5205b6b7281958514d245d4
|
| 478976606f43c8095c829a5b78d79ff50b4c43ef |
|
15-Jul-2013 |
Hiroshi Yamauchi <yamauchi@google.com> |
Show size/alloc/free per Dalvik heap space in dumpsys
Add the heap size/alloc/free stats to the Dalvik heap space breakdown section in dumpsys meminfo.
Also, now the zygote heap has a distict ashmem region name.
Bug: 9532137
Bug: 8266259
(cherry picked from commit 3edfe0b32753309ad7dcccd894239cb0a8aefb85)
Change-Id: I9b32727e4211f571a5205b6b7281958514d245d4
|
| 3086ab6a9c0859af3a85d5df73d0aecc2c47ca89 |
|
16-Jul-2013 |
Mathieu Chartier <mathieuc@google.com> |
Backport native allocation tracking.
From:
https://googleplex-android-review.googlesource.com/#/c/328818/
Change-Id: I5a930e629c5a2062f01f870b4a44dcd98cb4ffe9
|
| ebaf918e1bacff53c3dc3f0861c5cee851db23e5 |
|
10-Jul-2013 |
Mathieu Chartier <mathieuc@google.com> |
Add low memory mode option.
Added a low memory mode option which can be enabled by passing the
flag "-XX:LowMemoryMode" to the VM.
Changed dvmHeapSourceAlloc to use mspace_malloc and madvise page
aligned regions of allocations back to the kernel if low
memory mode is enabled. No measurable performance penalty on a
benchmark which does 4 million object allocations. This seems to
reduce the Dalvik total PSS by 10 - 15% on devices with
large bitmaps (such as manta or flo).
Another change is that cards are madvised instead of memset when
cleared if low memory mode is enabled. This saves a minor amount
of memory at the cost of having slightly more page faults.
Change-Id: I0c850bc370ebabf4393bff1c47d3257b2f1518d2
|
| 739bb122cfc866d599338a9def221e0661b54d20 |
|
17-Apr-2013 |
Elliott Hughes <enh@google.com> |
Work around a dalvik JDWP/GC deadlock.
Also add a few missing TEMP_FAILURE_RETRYs that can cause dalvik to
incorrectly decide that the debugger connection has been broken.
Bug: 8191824
(cherry picked from commit b680ae3140a789f182c26abf8df9645f7744113a)
Change-Id: I92736a1ad2f06caba30506d05bfa59fccbeee834
|
| b680ae3140a789f182c26abf8df9645f7744113a |
|
17-Apr-2013 |
Elliott Hughes <enh@google.com> |
Work around a dalvik JDWP/GC deadlock.
Also add a few missing TEMP_FAILURE_RETRYs that can cause dalvik to
incorrectly decide that the debugger connection has been broken.
Bug: 8191824
Change-Id: I791b514c6bec1ca634a65d9f87c5fa06da01b5ed
|
| 485dfb5ccb6d8b2c5d498ff6ee41b14e79103e3c |
|
24-Sep-2012 |
Ian Rogers <irogers@google.com> |
Allow max free size of heap to be configured.
This allows the max free to be larger on devices with more memory and
thereby avoid GCs (that may be more frequent due to larger bitmaps).
b/6606849
Change-Id: I4063a303ea4be3c1f227259d699fb238a806451f
|
| 2f30ef57ceb02ee5d6719d2158bd9bca4723687d |
|
29-Aug-2012 |
Ian Rogers <irogers@google.com> |
Revert "Revert "Trim pre-Zygote fork, fix under-estimate of heap limit.""
This reverts commit 4c7e27186d87ccd40646fd4f514dc982ff5b40b1.
|
| 808a7c0e7e39b7ca3c7db1366e6e4089166052bb |
|
29-Aug-2012 |
Ian Rogers <irogers@google.com> |
Revert "Revert "Upgrade to dlmalloc 2.8.5.""
This reverts commit 729eebbb4e4ec5b826b7230b4c02267da341b70b.
|
| 4c7e27186d87ccd40646fd4f514dc982ff5b40b1 |
|
24-Aug-2012 |
Ian Rogers <irogers@google.com> |
Revert "Trim pre-Zygote fork, fix under-estimate of heap limit."
This reverts commit 2f8d5e11f735e9ee8e235c31b3f113f6c90ad63c.
|
| 2f8d5e11f735e9ee8e235c31b3f113f6c90ad63c |
|
23-Aug-2012 |
Ian Rogers <irogers@google.com> |
Trim pre-Zygote fork, fix under-estimate of heap limit.
Card scanning uses dvmHeapSourceGetValue to scan from the heap base to
the total foot print of the heap. Trimming the Zygote may lower the
footprint of the heap by creating a hole in the middle. This hole is
unaccounted for in the card scanning leading to missed dirty cards.
This was a regression introduced by:
https://android-review.googlesource.com/#/c/41728/
as it didn't #define MORECORE_CANNOT_TRIM 1 that was previously defined
here:
https://android-review.googlesource.com/#/c/41731/4/libcutils/mspace.c
Introduce a notion of dvmHeapSourceGetLimit so that card scanning
doesn't rely on footprint. Trim the heap before forking the Zygote. This
change continues to enable morecore trimming of mspaces.
Change-Id: I3f0b12371097f50a1f920cac25846ca08685e7ed
|
| 497b25e87a51b4afd206ba7734971614d00301fb |
|
22-Aug-2012 |
Brian Carlstrom <bdc@google.com> |
Revert "Upgrade to dlmalloc 2.8.5."
This reverts commit bba37bd191843ef29ef9c7a8839e98b73debfffa.
|
| 729eebbb4e4ec5b826b7230b4c02267da341b70b |
|
22-Aug-2012 |
Brian Carlstrom <bdc@google.com> |
Revert "Upgrade to dlmalloc 2.8.5."
This reverts commit bba37bd191843ef29ef9c7a8839e98b73debfffa.
|
| bba37bd191843ef29ef9c7a8839e98b73debfffa |
|
18-Aug-2012 |
Ian Rogers <irogers@google.com> |
Upgrade to dlmalloc 2.8.5.
Switch to using dlmalloc 2.8.5. Define mspace functionality directly
using dlmalloc rather than taking from libcutils.
Remove growth limit check in tryMalloc that only checks initial growth
limit.
Implement trimming at the end of the mspace.
Depends upon: https://android-review.googlesource.com/41717
Change-Id: Ia2c6b50bdb0b0d5aae4b18deefbd1bf50dfa49d5
|
| 9487ab7fa22fc53512b344eeddc6dc866492a880 |
|
11-Jun-2012 |
Elliott Hughes <enh@google.com> |
Revert " Trim after explicit gc."
This reverts commit ea4c6e57a48e08eacbf08520c64133175e7d5da0
|
| ea4c6e57a48e08eacbf08520c64133175e7d5da0 |
|
11-May-2012 |
SangWook Han <swhan@nemustech.com> |
Trim after explicit gc.
On Gingerbread, dvmHeapSourceTrim() is called 5 seconds
after every kind of GC. Current AOSP do trim only for
concurrent GC. That makes OOM killer too busy.
At least explicit GC need trim and in case of explicit
GC, there are no need to delay 5 seconds before trim.
Change-Id: I8fde8f773398bf20c674cfa6f686d7d745d56492
|
| 0cea134bef68f348225178dacf03716d4907bdbe |
|
11-May-2012 |
SangWook Han <swhan@nemustech.com> |
Fix: Issue 26627: Dalvik Heap Trim timer value after GC
dvmRelativeCondWait need millisecods not seconds.
With this fix, trim will begins 5 seconds after concurrent GC
Bug: http://code.google.com/p/android/issues/detail?id=26627
Bug: 6482868
Change-Id: I3802b48e345725fb78e4ef2c999dd243ef30a138
|
| 1ae25c55391a874638f6a6366d2c8359c811b168 |
|
11-May-2012 |
SangWook Han <swhan@nemustech.com> |
Fix: Issue 26627: Dalvik Heap Trim timer value after GC
dvmRelativeCondWait need millisecods not seconds.
With this fix, trim will begins 5 seconds after concurrent GC
Bug: http://code.google.com/p/android/issues/detail?id=26627
Change-Id: I3802b48e345725fb78e4ef2c999dd243ef30a138
|
| b74e7190e86d559712747e5cdb31a0d390b7af7d |
|
16-Feb-2012 |
Iliyan Malchev <malchev@google.com> |
Replace malloc() followed by memset() to zero with calloc()
Bionic's calloc() is smart enough to not zero out memory if it gets that memory
from an anonyous mmap. Thus, if we use malloc for large allocations, we cause
unnecessary memory duplication by following the malloc() with a memset().
An even better approach would be to replace the known large calloc() calls with
dvmAllocRegion() allocation.
Change-Id: Id308f541c9a040d5929bf991b6c2bfdefb823c3c
|
| c1a4ab9c313d8a3d12007f2dbef7b5a6fa4ac2ef |
|
06-Jan-2012 |
Steve Block <steveblock@google.com> |
Rename (IF_)LOGE(_IF) to (IF_)ALOGE(_IF) DO NOT MERGE
See https://android-git.corp.google.com/g/#/c/157220
Also fix an occurrence of LOGW missed in an earlier change.
Bug: 5449033
Change-Id: I2e3b23839e6dcd09015d6402280e9300c75e3406
|
| af6cf54652d1b27885b99e216bee29b955052630 |
|
04-Nov-2011 |
Andy McFadden <fadden@android.com> |
Reduce Dalvik card table overhead
The VM has a "growth limit" (e.g. 48MB) that is used to cap normal
apps, and a "max heap" (e.g. 128MB) that is used for apps with unusual
high-memory requirements. The Dalvik GC uses a 128:1 "card table"
that spans the entire managed heap, out to the "max heap" limit.
The table is erased during every concurrent GC. The first time
we do that post-zygote, the copy-on-write behavior causes physical
pages to be allocated. We're currently clearing out to the heap max,
not the growth limit, which means we have a bunch of physical memory
allocated for pages that will never be used.
This changes it so we only clear out to the growth limit. If the
growth limit is removed by the app, we clear out to the heap max.
On devices with a 128MB max heap, this reduces the private/dirty
usage for most apps by 640KB.
Bug 5567332
Change-Id: Iac633017c128d63b284d48016e47d40cc46df1de
|
| 92c1f6f1b4249e4e379452ee7b49f027052bf4ce |
|
20-Oct-2011 |
Steve Block <steveblock@google.com> |
Rename (IF_)LOGV(_IF) to (IF_)ALOGV(_IF) DO NOT MERGE
See https://android-git.corp.google.com/g/#/c/143865
Bug: 5449033
Change-Id: I8bd96961e369a08e86ff78b82d90f20f42787eb1
|
| b2714082bad44fde247920b9280c1b40c4979c3a |
|
10-Oct-2011 |
Ben Cheng <bccheng@android.com> |
Revert "Use the card table to scan the immune region of the heap."
This reverts commit 6c355e53332502314c3d82a7afcf898d66118f27.
Conflicts are resolved in:
vm/alloc/CardTable.cpp
vm/alloc/HeapBitmap.cpp
vm/alloc/HeapInternal.h
vm/alloc/HeapSource.cpp
vm/alloc/MarkSweep.cpp
Tested with overnight monkey runs + Delaunay.
Bug: 5037417
Change-Id: I400eff8542d0bddd865ce570a479f7750c1ba484
|
| fe9052edaf6bebbccaac5a9fb607012778d0dd74 |
|
20-Jul-2011 |
Jeff Brown <jeffbrown@google.com> |
Trim the heap when idle after concurrent GC's.
Bug: 4984352
When applied system-wide, trimming the heap can help recover
multiple megabytes worth of pages that are no longer used.
This is especially useful for applications that periodically
allocate large objects during initialization that they then
discard when running in the background.
Change-Id: Iafffd65a70ae62022f0c74f836a84a7afbe23c3c
|
| fd31cc071c83bdbe45e6f9db41fd76375e7ac310 |
|
10-Jun-2011 |
Carl Shapiro <cshapiro@google.com> |
Do not initiate a concurrent collection if one is already running.
It is possible to cause a recursive garbage collection by writing a
program that triggers a concurrent garbage collection and initiates a
concurrent garbage collection before the garbage collection thread is
scheduled. For example
for (;;) { new byte[16 << 20]; System.gc(); }
When this condition occurs a warning is logged although such warnings
ought to be upgraded to fatal errors. With this change, when the
garbage collection thread is scheduled it first checks to see if there
is a running collection before calling down to start the collection.
Change-Id: Ia7baf5eba245bbf3fe053d3bad3f90876cad2459
|
| 0c13923b0616dc79fcfc41b63119268273bdc8be |
|
10-Jun-2011 |
Carl Shapiro <cshapiro@google.com> |
Always grow the limit address of the a heap along with its size.
Previously, clearing the growth limit only updated the maximumSize of
the unlimited heap without updating the limit value. This caused any
operations iterated over the extent of the heap to ignore allocations
beyond the original heap size. With this change the limit is always
kept in agreement with the maximumSize.
Bug: 4539441
Change-Id: I08c8004e724549d196e1fd5d6ad22efc85b0c8d2
|
| 60fc806b679a3655c228b4093058c59941a49cfe |
|
26-May-2011 |
Dan Bornstein <danfuzz@android.com> |
Further conservation of newlines.
Friends don't let friends end LOG() strings with newlines.
Change-Id: I5a18c766c90c4ab5f03caa6acd601d34d91beb00
|
| d537d4840fcdf0e279b6a7c91a27306e0544aeaa |
|
26-May-2011 |
Carl Shapiro <cshapiro@google.com> |
Eliminate the dvmHeapSourceGetPtrFlag interface.
This routine served answering questions about object addresses. While
it was private to the garbage collector, its remaining use was inside
the heap profiler. Within the heap profiler, a single path was
executed to tested a pointer for containment within the zygote. In
its place, a new function, dvmIsZygoteObject, has been added to the GC
interface superseding the only use of dvmHeapSourceGetPtrFlag.
Change-Id: I347c9adb293bd6c196bbac3765015453133dc492
|
| 7e46af2973841f63b9301e5515f8381478b806ae |
|
12-May-2011 |
Carl Shapiro <cshapiro@google.com> |
Various code clean-ups.
* Combine definitions with initialization. This had to be foregone in
two instances where that would have otherwise caused an unused variable
warning.
* Move the HS_BOILERPLATE macro to the top of the calling function. This
macro checks that certain globals are initialized. It should be removed
after the callers become members functions of a class.
* A few cases of inconsistent function declaration styles have been brought
in line with the rest of the file. These were overlooked in a previous
clean-up.
* The unused heap source debugging macros and tracing code have been
removed.
* One stale comments has been removed and another has been updated.
Change-Id: I20bf4b78161096310b79d7dd294d7636e6bb6f48
|
| 06f120f6092185003bc9b70e06eb44866e9676f8 |
|
11-May-2011 |
Carl Shapiro <cshapiro@google.com> |
Normalize declaration style.
Change-Id: Iae4e3d22bc185060b3a0b4c080eafaa2ec824ac2
|
| d862faa2ceae186da5518607505eb942d634ced9 |
|
28-Apr-2011 |
Carl Shapiro <cshapiro@google.com> |
Get rid of uneeded extern, enum, typedef and struct qualifiers.
Change-Id: I236c5a1553a51f82c9bc3eaaab042046c854d3b4
|
| 5cdd4a3f91d3fc25c8eeca8f58e35bb6c4e908ca |
|
28-Apr-2011 |
Carl Shapiro <cshapiro@google.com> |
Normalize some enumerations.
This change pulls a few enumeration types to the top of their header
file alongside other types. It also eliminates the use of the now
redundant enum qualifier.
Change-Id: I6f853bed09176cde9a83faccea7a76f595f60f2b
|
| 50e5fd5984c9b0a6f0927ed5ddf13bde40e338c7 |
|
27-Apr-2011 |
Carl Shapiro <cshapiro@google.com> |
Use C++ linkage in GC headers and remove unneeded typedefs.
Some interfaces in Alloc.h had to be left with C linkage as they are
referenced by the interpreter assembler code. That dependency will be
addressed in a future commit.
Change-Id: I6b2097a2139ddf6b4b13e592710e241442e08488
|
| 1e1433e78f560a01744e870c19c162ab88df9dc1 |
|
21-Apr-2011 |
Carl Shapiro <cshapiro@google.com> |
Remove unneeded void argument list declarations.
Change-Id: Ica749f6defa890363ec531b29e25bc415dc2cbb9
|
| f9fa8c14c7ef87b4318d606bfc5132df7b77b17c |
|
09-Apr-2011 |
Carl Shapiro <cshapiro@google.com> |
Fix for loops and eliminate some other undesirable idioms.
Previously, we were using a non-standard C dialect which did not permit
the nicer variable scoping in loops. Now that we are using C++ in the
collector we can guarantee that feature is available. This change also
rearranges some of the surrounding code to take advantage of the more
flexible scoping rules.
Change-Id: I9be35794cc12bcbc0d5299fe387d4bc406481075
|
| ae188c676c681e47a93ade7fdf0144099b470e03 |
|
08-Apr-2011 |
Carl Shapiro <cshapiro@google.com> |
Compile the garbage collector and heap profiler as C++.
Change-Id: I25d8fa821987a3dd6d7109d07fd42dbf2fe0e589
|