Commit Graph

84 Commits

Author SHA1 Message Date
Daniel Micay
a62812eacc fix isqalloct (should call isdalloct) 2014-09-08 21:46:17 -04:00
Daniel Micay
4cfe55166e Add support for sized deallocation.
This adds a new `sdallocx` function to the external API, allowing the
size to be passed by the caller.  It avoids some extra reads in the
thread cache fast path.  In the case where stats are enabled, this
avoids the work of calculating the size from the pointer.

An assertion validates the size that's passed in, so enabling debugging
will allow users of the API to debug cases where an incorrect size is
passed in.

The performance win for a contrived microbenchmark doing an allocation
and immediately freeing it is ~10%.  It may have a different impact on a
real workload.

Closes #28
2014-09-08 17:34:24 -07:00
Jason Evans
b718cf77e9 Optimize [nmd]alloc() fast paths.
Optimize [nmd]alloc() fast paths such that the (flags == 0) case is
streamlined, flags decoding only happens to the minimum degree
necessary, and no conditionals are repeated.
2014-09-07 14:40:19 -07:00
Manuel A. Fernandez Montecelo
ffa259841c Add OpenRISC/or1k LG_QUANTUM size definition 2014-07-29 23:11:26 +01:00
Richard Diamond
9c3a10fdf6 Try to use __builtin_ffsl if ffsl is unavailable.
Some platforms (like those using Newlib) don't have ffs/ffsl.  This
commit adds a check to configure.ac for __builtin_ffsl if ffsl isn't
found.  __builtin_ffsl performs the same function as ffsl, and has the
added benefit of being available on any platform utilizing
Gcc-compatible compiler.

This change does not address the used of ffs in the MALLOCX_ARENA()
macro.
2014-06-02 07:44:50 -07:00
Jason Evans
d04047cc29 Add size class computation capability.
Add size class computation capability, currently used only as validation
of the size class lookup tables.  Generalize the size class spacing used
for bins, for eventual use throughout the full range of allocation
sizes.
2014-05-28 21:06:46 -07:00
Mike Hommey
12f74e680c Move platform headers and tricks from jemalloc_internal.h.in to a new jemalloc_internal_decls.h header 2014-05-28 09:38:10 -07:00
Mike Hommey
22bc570fba Move __func__ to jemalloc_internal_macros.h
test/integration/aligned_alloc.c needs it.
2014-05-27 15:52:49 -07:00
Jason Evans
e2deab7a75 Refactor huge allocation to be managed by arenas.
Refactor huge allocation to be managed by arenas (though the global
red-black tree of huge allocations remains for lookup during
deallocation).  This is the logical conclusion of recent changes that 1)
made per arena dss precedence apply to huge allocation, and 2) made it
possible to replace the per arena chunk allocation/deallocation
functions.

Remove the top level huge stats, and replace them with per arena huge
stats.

Normalize function names and types to *dalloc* (some were *dealloc*).

Remove the --enable-mremap option.  As jemalloc currently operates, this
is a performace regression for some applications, but planned work to
logarithmically space huge size classes should provide similar amortized
performance.  The motivation for this change was that mremap-based huge
reallocation forced leaky abstractions that prevented refactoring.
2014-05-15 22:36:41 -07:00
aravind
fb7fe50a88 Add support for user-specified chunk allocators/deallocators.
Add new mallctl endpoints "arena<i>.chunk.alloc" and
"arena<i>.chunk.dealloc" to allow userspace to configure
jemalloc's chunk allocator and deallocator on a per-arena
basis.
2014-05-12 10:46:03 -07:00
Lucian Adrian Grijincu
9d4e13f45a prof_backtrace: use unw_backtrace
unw_backtrace:
- does internal per-thread caching
- doesn't acquire an internal lock
2014-04-22 18:39:47 -07:00
Jason Evans
3541a904d6 Refactor small_size2bin and small_bin2size.
Refactor small_size2bin and small_bin2size to be inline functions rather
than directly accessed arrays.
2014-04-16 17:14:33 -07:00
Jason Evans
3e3caf03af Merge pull request #73 from bmaurer/smallmalloc
Smaller malloc hot path
2014-04-16 16:33:21 -07:00
Ben Maurer
021136ce4d Create a const array with only a small bin to size map 2014-04-16 14:31:24 -07:00
Jason Evans
bd87b01999 Optimize Valgrind integration.
Forcefully disable tcache if running inside Valgrind, and remove
Valgrind calls in tcache-specific code.

Restructure Valgrind-related code to move most Valgrind calls out of the
fast path functions.

Take advantage of static knowledge to elide some branches in
JEMALLOC_VALGRIND_REALLOC().
2014-04-15 16:49:57 -07:00
Jason Evans
ecd3e59ca3 Remove the "opt.valgrind" mallctl.
Remove the "opt.valgrind" mallctl because it is unnecessary -- jemalloc
automatically detects whether it is running inside valgrind.
2014-04-15 14:33:50 -07:00
Jason Evans
4d434adb14 Make dss non-optional, and fix an "arena.<i>.dss" mallctl bug.
Make dss non-optional on all platforms which support sbrk(2).

Fix the "arena.<i>.dss" mallctl to return an error if "primary" or
"secondary" precedence is specified, but sbrk(2) is not supported.
2014-04-15 12:09:48 -07:00
Jason Evans
9790b9667f Remove the *allocm() API, which is superceded by the *allocx() API. 2014-04-14 22:32:31 -07:00
Ben Maurer
be8e59f5a6 Don't dereference chunk->arena in free() hot path
When you call free() we load chunk->arena even though that
data isn't used on the tcache hot path.

In profiling some FB applications, I found that ~30% of the
dTLB misses in the free() function come from this line. With
4 MB chunks, the arena_chunk_t->map is ~ 32 KB (1024 pages
in the chunk, 4 8 byte pointers in arena_chunk_map_t). This
means there's only a 1/8 chance of the page containing
chunk->arena also comtaining the map bits.
2014-04-05 15:59:08 -07:00
Max Wang
fbb31029a5 Use arena dss prec instead of default for huge allocs.
Pass a dss_prec_t parameter to huge_{m,p,r}alloc instead of defaulting
to the chunk dss prec.
2014-03-28 13:43:58 -07:00
Jason Evans
f234dc51b9 Fix name mangling for stress tests.
Fix stress tests such that testlib code uses the jet_ allocator, but
test code uses libjemalloc.

Generate jemalloc_{rename,mangle}.h, the former because it's needed for
the stress test name mangling fix, and the latter for consistency.  As
an artifact of this change, some (but not all) definitions related to
the experimental API are absent from the headers unless the feature is
enabled at configure time.
2014-01-16 17:38:01 -08:00
Jason Evans
b2c31660be Extract profiling code from [re]allocation functions.
Extract profiling code from malloc(), imemalign(), calloc(), realloc(),
mallocx(), rallocx(), and xallocx().  This slightly reduces the amount
of code compiled into the fast paths, but the primary benefit is the
combinatorial complexity reduction.

Simplify iralloc[t]() by creating a separate ixalloc() that handles the
no-move cases.

Further simplify [mrxn]allocx() (and by implication [mrn]allocm()) to
make request size overflows due to size class and/or alignment
constraints trigger undefined behavior (detected by debug-only
assertions).

Report ENOMEM rather than EINVAL if an OOM occurs during heap profiling
backtrace creation in imemalign().  This bug impacted posix_memalign()
and aligned_alloc().
2014-01-12 15:41:05 -08:00
Jason Evans
b954bc5d3a Convert rtree from (void *) to (uint8_t) storage.
Reduce rtree memory usage by storing booleans (1 byte each) rather than
pointers.  The rtree code is only used to record whether jemalloc manages
a chunk of memory, so there's no need to store pointers in the rtree.

Increase rtree node size to 64 KiB in order to reduce tree depth from 13
to 3 on 64-bit systems.  The conversion to more compact leaf nodes was
enough by itself to make the rtree depth 1 on 32-bit systems; due to the
fact that root nodes are smaller than the specified node size if
possible, the node size change has no impact on 32-bit systems (assuming
default chunk size).
2014-01-02 17:36:38 -08:00
Jason Evans
d82a5e6a34 Implement the *allocx() API.
Implement the *allocx() API, which is a successor to the *allocm() API.
The *allocx() functions are slightly simpler to use because they have
fewer parameters, they directly return the results of primary interest,
and mallocx()/rallocx() avoid the strict aliasing pitfall that
allocm()/rallocx() share with posix_memalign().  The following code
violates strict aliasing rules:

    foo_t *foo;
    allocm((void **)&foo, NULL, 42, 0);

whereas the following is safe:

    foo_t *foo;
    void *p;
    allocm(&p, NULL, 42, 0);
    foo = (foo_t *)p;

mallocx() does not have this problem:

    foo_t *foo = (foo_t *)mallocx(42, 0);
2013-12-12 22:35:52 -08:00
Jason Evans
a4f124f59f Normalize #define whitespace.
Consistently use a tab rather than a space following #define.
2013-12-08 22:28:27 -08:00
Jason Evans
dc1bed6227 Fix more test refactoring issues. 2013-12-05 21:44:25 -08:00
Jason Evans
14990b83d1 Fix test refactoring issues for Linux. 2013-12-05 17:58:32 -08:00
Jason Evans
86abd0dcd8 Refactor to support more varied testing.
Refactor the test harness to support three types of tests:
- unit: White box unit tests.  These tests have full access to all
  internal jemalloc library symbols.  Though in actuality all symbols
  are prefixed by jet_, macro-based name mangling abstracts this away
  from test code.
- integration: Black box integration tests.  These tests link with
  the installable shared jemalloc library, and with the exception of
  some utility code and configure-generated macro definitions, they have
  no access to jemalloc internals.
- stress: Black box stress tests.  These tests link with the installable
  shared jemalloc library, as well as with an internal allocator with
  symbols prefixed by jet_ (same as for unit tests) that can be used to
  allocate data structures that are internal to the test code.

Move existing tests into test/{unit,integration}/ as appropriate.

Split out internal parts of jemalloc_defs.h.in and put them in
jemalloc_internal_defs.h.in.  This reduces internals exposure to
applications that #include <jemalloc/jemalloc.h>.

Refactor jemalloc.h header generation so that a single header file
results, and the prototypes can be used to generate jet_ prototypes for
tests.  Split jemalloc.h.in into multiple parts (jemalloc_defs.h.in,
jemalloc_macros.h.in, jemalloc_protos.h.in, jemalloc_mangle.h.in) and
use a shell script to generate a unified jemalloc.h at configure time.

Change the default private namespace prefix from "" to "je_".

Add missing private namespace mangling.

Remove hard-coded private_namespace.h.  Instead generate it and
private_unnamespace.h from private_symbols.txt.  Use similar logic for
public symbols, which aids in name mangling for jet_ symbols.

Add test_warn() and test_fail().  Replace existing exit(1) calls with
test_fail() calls.
2013-12-03 22:06:59 -08:00
Jason Evans
543abf7e6c Fix inlining warning.
Add the JEMALLOC_ALWAYS_INLINE_C macro and use it for always-inlined
functions declared in .c files.  This fixes a function attribute
inconsistency for debug builds that resulted in (harmless) compiler
warnings about functions not being inlinable.

Reported by Ricardo Nabinger Sanchez.
2013-10-19 17:26:00 -07:00
Riku Voipio
daf6d0446c Add aarch64 LG_QUANTUM size definition
Signed-off-by: Riku Voipio <riku.voipio@linaro.org>
2013-05-07 11:05:01 -07:00
Jason Evans
a491585157 Add no-op bodies to VALGRIND_*() macro stubs.
Add no-op bodies to VALGRIND_*() macro stubs so that they can be used in
contexts like the following without generating a compiler warning about
the 'if' statement having an empty body:

	if (config_valgrind)
		VALGRIND_MAKE_MEM_UNDEFINED(ret, size);
2013-03-06 11:19:31 -08:00
Mike Frysinger
9f9897ad42 fix building for s390 systems
Checking for __s390x__ means you work on s390x, but not s390 (32bit)
systems.  So use __s390__ which works for both.

With this, `make check` passes on s390.

Signed-off-by: Mike Frysinger <vapier@gentoo.org>
2013-03-06 11:03:48 -08:00
Jason Evans
06912756cc Fix Valgrind integration.
Fix Valgrind integration to annotate all internally allocated memory in
a way that keeps Valgrind happy about internal data structure access.
2013-01-31 17:02:53 -08:00
Jason Evans
dd0438ee6b Specify 'inline' in addition to always_inline attribute.
Specify both inline and __attribute__((always_inline)), in order to
avoid warnings when using newer versions of gcc.
2013-01-22 20:43:04 -08:00
Jason Evans
ae03bf6a57 Update hash from MurmurHash2 to MurmurHash3.
Update hash from MurmurHash2 to MurmurHash3, primarily because the
latter generates 128 bits in a single call for no extra cost, which
simplifies integration with cuckoo hashing.
2013-01-22 12:02:08 -08:00
Jason Evans
88393cb0eb Add and use JEMALLOC_ALWAYS_INLINE.
Add JEMALLOC_ALWAYS_INLINE and use it to guarantee that the entire fast
paths of the primary allocation/deallocation functions are inlined.
2013-01-22 08:45:43 -08:00
Garrett Cooper
13e4e24c42 Fix build break on *BSD
Linux uses alloca.h; many other operating systems define alloca(3) in
stdlib.h.

Signed-off-by: Garrett Cooper <yanegomi@gmail.com>
2012-12-24 10:32:16 -08:00
Jason Evans
609ae595f0 Add arena-specific and selective dss allocation.
Add the "arenas.extend" mallctl, so that it is possible to create new
arenas that are outside the set that jemalloc automatically multiplexes
threads onto.

Add the ALLOCM_ARENA() flag for {,r,d}allocm(), so that it is possible
to explicitly allocate from a particular arena.

Add the "opt.dss" mallctl, which controls the default precedence of dss
allocation relative to mmap allocation.

Add the "arena.<i>.dss" mallctl, which makes it possible to set the
default dss precedence on a per arena or global basis.

Add the "arena.<i>.purge" mallctl, which obsoletes "arenas.purge".

Add the "stats.arenas.<i>.dss" mallctl.
2012-10-12 18:26:16 -07:00
Jason Evans
dd03a2e377 Define LG_QUANTUM for hppa.
Submitted by Jory Pratt.
2012-10-08 15:41:06 -07:00
Jason Evans
781fe75e0a Auto-detect whether running inside Valgrind.
Auto-detect whether running inside Valgrind, thus removing the need to
manually specify MALLOC_CONF=valgrind:true.
2012-05-15 14:48:14 -07:00
Jason Evans
2e671ffbad Add the --enable-mremap option.
Add the --enable-mremap option, and disable the use of mremap(2) by
default, for the same reason that freeing chunks via munmap(2) is
disabled by default on Linux: semi-permanent VM map fragmentation.
2012-05-09 16:12:00 -07:00
Jason Evans
8d5865eb57 Make CACHELINE a raw constant.
Make CACHELINE a raw constant in order to work around a
__declspec(align()) limitation.

Submitted by Mike Hommey.
2012-05-02 01:22:16 -07:00
Jason Evans
203484e2ea Optimize malloc() and free() fast paths.
Embed the bin index for small page runs into the chunk page map, in
order to omit [...] in the following dependent load sequence:
  ptr-->mapelm-->[run-->bin-->]bin_info

Move various non-critcal code out of the inlined function chain into
helper functions (tcache_event_hard(), arena_dalloc_small(), and
locking).
2012-05-02 00:30:36 -07:00
Mike Hommey
fd97b1dfc7 Add support for MSVC
Tested with MSVC 8 32 and 64 bits.
2012-05-01 11:32:11 -07:00
Mike Hommey
a14bce85e8 Use Get/SetLastError on Win32
Using errno on win32 doesn't quite work, because the value set in a shared
library can't be read from e.g. an executable calling the function setting
errno.

At the same time, since buferror always uses errno/GetLastError, don't pass
it.
2012-04-30 16:50:55 -07:00
Mike Hommey
8b49971d0c Avoid variable length arrays and remove declarations within code
MSVC doesn't support C99, and building as C++ to be able to use them is
dangerous, as C++ and C99 are incompatible.

Introduce a VARIABLE_ARRAY macro that either uses VLA when supported,
or alloca() otherwise. Note that using alloca() inside loops doesn't
quite work like VLAs, thus the use of VARIABLE_ARRAY there is discouraged.
It might be worth investigating ways to check whether VARIABLE_ARRAY is
used in such context at runtime in debug builds and bail out if that
happens.
2012-04-29 00:25:34 -07:00
Mike Hommey
a5288ca934 Remove unused #includes 2012-04-21 21:32:09 -07:00
Mike Hommey
a19e87fbad Add support for Mingw 2012-04-21 21:27:46 -07:00
Jason Evans
f7088e6c99 Make arena_salloc() an inline function. 2012-04-19 18:28:03 -07:00
Jason Evans
b57d3ec571 Add atomic(9) implementations of atomic operations.
Add atomic(9) implementations of atomic operations.  These are used on
FreeBSD for non-x86 architectures.
2012-04-17 13:27:39 -07:00