Commit Graph

469 Commits

Author SHA1 Message Date
Jason Evans
3f2b8d9cfa Add os_unfair_lock support.
OS X 10.12 deprecated OSSpinLock; os_unfair_lock is the recommended
replacement.
2016-11-02 19:35:12 -07:00
Jason Evans
a99e0fa2d2 Fix/refactor zone allocator integration code.
Fix zone_force_unlock() to reinitialize, rather than unlocking mutexes,
since OS X 10.12 cannot tolerate a child unlocking mutexes that were
locked by its parent.

Refactor; this was a side effect of experimenting with zone
{de,re}registration during fork(2).
2016-11-02 19:35:09 -07:00
Jason Evans
4752a54eeb Refactor witness_unlock() to fix undefined test behavior.
This resolves #396.
2016-10-31 11:51:39 -07:00
Jason Evans
1d57c03e33 Use CLOCK_MONOTONIC_COARSE rather than COARSE_MONOTONIC_RAW.
The raw clock variant is slow (even relative to plain CLOCK_MONOTONIC),
whereas the coarse clock variant is faster than CLOCK_MONOTONIC, but
still has resolution (~1ms) that is adequate for our purposes.

This resolves #479.
2016-10-29 22:59:42 -07:00
Dave Watson
ed84764a2a Support static linking of jemalloc with glibc
glibc defines its malloc implementation with several weak and strong
symbols:

strong_alias (__libc_calloc, __calloc) weak_alias (__libc_calloc, calloc)
strong_alias (__libc_free, __cfree) weak_alias (__libc_free, cfree)
strong_alias (__libc_free, __free) strong_alias (__libc_free, free)
strong_alias (__libc_malloc, __malloc) strong_alias (__libc_malloc, malloc)

The issue is not with the weak symbols, but that other parts of glibc
depend on __libc_malloc explicitly.  Defining them in terms of jemalloc
API's allows the linker to drop glibc's malloc.o completely from the link,
and static linking no longer results in symbol collisions.

Another wrinkle: jemalloc during initialization calls sysconf to
get the number of CPU's.  GLIBC allocates for the first time before
setting up isspace (and other related) tables, which are used by
sysconf.  Instead, use the pthread API to get the number of
CPUs with GLIBC, which seems to work.

This resolves #442.
2016-10-28 15:10:19 -07:00
Jason Evans
962a2979e3 Do not (recursively) allocate within tsd_fetch().
Refactor tsd so that tsdn_fetch() does not trigger allocation, since
allocation could cause infinite recursion.

This resolves #458.
2016-10-21 00:27:37 -07:00
Jason Evans
e2bcf037d4 Make dss operations lockless.
Rather than protecting dss operations with a mutex, use atomic
operations.  This has negligible impact on synchronization overhead
during typical dss allocation, but is a substantial improvement for
chunk_in_dss() and the newly added chunk_dss_mergeable(), which can be
called multiple times during chunk deallocations.

This change also has the advantage of avoiding tsd in deallocation paths
associated with purging, which resolves potential deadlocks during
thread exit due to attempted tsd resurrection.

This resolves #425.
2016-10-13 15:33:56 -07:00
Jason Evans
9737685943 Add/use adaptive spinning.
Add spin_t and spin_{init,adaptive}(), which provide a simple
abstraction for adaptive spinning.

Adaptively spin during busy waits in bootstrapping and rtree node
initialization.
2016-10-13 14:58:38 -07:00
Jason Evans
d419bb09ef Fix and simplify decay-based purging.
Simplify decay-based purging attempts to only be triggered when the
epoch is advanced, rather than every time purgeable memory increases.
In a correctly functioning system (not previously the case; see below),
this only causes a behavior difference if during subsequent purge
attempts the least recently used (LRU) purgeable memory extent is
initially too large to be purged, but that memory is reused between
attempts and one or more of the next LRU purgeable memory extents are
small enough to be purged.  In practice this is an arbitrary behavior
change that is within the set of acceptable behaviors.

As for the purging fix, assure that arena->decay.ndirty is recorded
*after* the epoch advance and associated purging occurs.  Prior to this
fix, it was possible for purging during epoch advance to cause a
substantially underrepresentative (arena->ndirty - arena->decay.ndirty),
i.e. the number of dirty pages attributed to the current epoch was too
low, and a series of unintended purges could result.  This fix is also
relevant in the context of the simplification described above, but the
bug's impact would be limited to over-purging at epoch advances.
2016-10-11 15:50:05 -07:00
Jason Evans
45a5bf6772 Do not advance decay epoch when time goes backwards.
Instead, move the epoch backward in time.  Additionally, add
nstime_monotonic() and use it in debug builds to assert that time only
goes backward if nstime_update() is using a non-monotonic time source.
2016-10-10 22:31:37 -07:00
Jason Evans
94e7ffa979 Refactor arena->decay_* into arena->decay.* (arena_decay_t). 2016-10-10 22:22:59 -07:00
Jason Evans
b732c395b7 Refine nstime_update().
Add missing #include <time.h>.  The critical time facilities appear to
have been transitively included via unistd.h and sys/time.h, but in
principle this omission was capable of having caused
clock_gettime(CLOCK_MONOTONIC, ...) to have been overlooked in favor of
gettimeofday(), which in turn could cause spurious non-monotonic time
updates.

Refactor nstime_get() out of nstime_update() and add configure tests for
all variants.

Add CLOCK_MONOTONIC_RAW support (Linux-specific) and
mach_absolute_time() support (OS X-specific).

Do not fall back to clock_gettime(CLOCK_REALTIME, ...).  This was a
fragile Linux-specific workaround, which we're unlikely to use at all
now that clock_gettime(CLOCK_MONOTONIC_RAW, ...) is supported, and if we
have no choice besides non-monotonic clocks, gettimeofday() is only
incrementally worse.
2016-10-10 11:40:46 -07:00
Jason Evans
5d8db15db9 Simplify run quantization. 2016-10-06 15:58:38 -07:00
Jason Evans
f193fd80cf Refactor runs_avail.
Use pszind_t size classes rather than szind_t size classes, and always
reserve space for NPSIZES elements.  This removes unused heaps that are
not multiples of the page size, and adds (currently) unused heaps for
all huge size classes, with the immediate benefit that the size of
arena_t allocations is constant (no longer dependent on chunk size).
2016-10-04 19:48:50 -07:00
Jason Evans
1abb49f09d Implement pz2ind(), pind2sz(), and psz2u().
These compute size classes and indices similarly to size2index(),
index2size() and s2u(), respectively, but using the subset of size
classes that are multiples of the page size.  Note that pszind_t and
szind_t are not interchangeable.
2016-10-04 16:29:19 -07:00
Jason Evans
bcd5424b1c Use TSDN_NULL rather than NULL as appropriate. 2016-10-04 15:56:56 -07:00
Mike Hommey
af33e9a597 Define 64-bits atomics unconditionally
They are used on all platforms in prng.h.
2016-10-04 12:18:14 -07:00
Eric Le Bihan
b54c0c2925 Fix LG_QUANTUM definition for sparc64
GCC 4.9.3 cross-compiled for sparc64 defines __sparc_v9__, not
__sparc64__ nor __sparcv9. This prevents LG_QUANTUM from being defined
properly. Adding this new value to the check solves the issue.
2016-09-26 15:14:59 -07:00
Elliot Ronaghan
5acef864f2 Don't use compact red-black trees with the pgi compiler
Some bug (either in the red-black tree code, or in the pgi compiler) seems to
cause red-black trees to become unbalanced. This issue seems to go away if we
don't use compact red-black trees. Since red-black trees don't seem to be used
much anymore, I opted for what seems to be an easy fix here instead of digging
in and trying to find the root cause of the bug.

Some context in case it's helpful:

I experienced a ton of segfaults while using pgi as Chapel's target compiler
with jemalloc 4.0.4. The little bit of debugging I did pointed me somewhere
deep in red-black tree manipulation, but I didn't get a chance to investigate
further. It looks like 4.2.0 replaced most uses of red-black trees with
pairing-heaps, which seems to avoid whatever bug I was hitting.

However, `make check_unit` was still failing on the rb test, so I figured the
core issue was just being masked. Here's the `make check_unit` failure:

```sh
=== test/unit/rb ===
test_rb_empty: pass
tree_recurse:test/unit/rb.c:90: Failed assertion: (((_Bool) (((uintptr_t) (left_node)->link.rbn_right_red) & ((size_t)1)))) == (false) --> true != false: Node should be black
test_rb_random:test/unit/rb.c:274: Failed assertion: (imbalances) == (0) --> 1 != 0: Tree is unbalanced
tree_recurse:test/unit/rb.c:90: Failed assertion: (((_Bool) (((uintptr_t) (left_node)->link.rbn_right_red) & ((size_t)1)))) == (false) --> true != false: Node should be black
test_rb_random:test/unit/rb.c:274: Failed assertion: (imbalances) == (0) --> 1 != 0: Tree is unbalanced
node_remove:test/unit/rb.c:190: Failed assertion: (imbalances) == (0) --> 2 != 0: Tree is unbalanced
<jemalloc>: test/unit/rb.c:43: Failed assertion: "pathp[-1].cmp < 0"
test/test.sh: line 22: 12926 Aborted
Test harness error
```

While starting to debug I saw the RB_COMPACT option and decided to check if
turning that off resolved the bug. It seems to have fixed it (`make check_unit`
passes and the segfaults under Chapel are gone) so it seems like on okay
work-around. I'd imagine this has performance implications for red-black trees
under pgi, but if they're not going to be used much anymore it's probably not a
big deal.
2016-09-26 11:08:45 -07:00
Elliot Ronaghan
d1207f0d37 Check for __builtin_unreachable at configure time
Add a configure check for __builtin_unreachable instead of basing its
availability on the __GNUC__ version. On OS X using gcc (a real gcc, not the
bundled version that's just a gcc front-end) leads to a linker assertion:

    https://github.com/jemalloc/jemalloc/issues/266

It turns out that this is caused by a gcc bug resulting from the use of
__builtin_unreachable():

    https://gcc.gnu.org/bugzilla/show_bug.cgi?id=57438

To work around this bug, check that __builtin_unreachable() actually works at
configure time, and if it doesn't use abort() instead. The check is based on
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=57438#c21.

With this `make check` passes with a homebrew installed gcc-5 and gcc-6.
2016-09-26 10:44:37 -07:00
Jason Evans
20cd2de5ef Add a missing prof_alloc_rollback() call.
In the case where prof_alloc_prep() is called with an over-estimate of
allocation size, and sampling doesn't end up being triggered, the tctx
must be discarded.
2016-06-08 10:12:38 -07:00
Jason Evans
05a9e4ac65 Fix potential VM map fragmentation regression.
Revert 245ae6036c (Support --with-lg-page
values larger than actual page size.), because it could cause VM map
fragmentation if the kernel grows mmap()ed memory downward.

This resolves #391.
2016-06-07 14:21:21 -07:00
Jason Evans
73d3d58dc2 Optimize witness fast path.
Short-circuit commonly called witness functions so that they only
execute in debug builds, and remove equivalent guards from mutex
functions.  This avoids pointless code execution in
witness_assert_lockless(), which is typically called twice per
allocation/deallocation function invocation.

Inline commonly called witness functions so that optimized builds can
completely remove calls as dead code.
2016-05-11 15:38:06 -07:00
Jason Evans
c1e00ef2a6 Resolve bootstrapping issues when embedded in FreeBSD libc.
b2c0d6322d (Add witness, a simple online
locking validator.) caused a broad propagation of tsd throughout the
internal API, but tsd_fetch() was designed to fail prior to tsd
bootstrapping.  Fix this by splitting tsd_t into non-nullable tsd_t and
nullable tsdn_t, and modifying all internal APIs that do not critically
rely on tsd to take nullable pointers.  Furthermore, add the
tsd_booted_get() function so that tsdn_fetch() can probe whether tsd
bootstrapping is complete and return NULL if not.  All dangerous
conversions of nullable pointers are tsdn_tsd() calls that assert-fail
on invalid conversion.
2016-05-10 22:51:33 -07:00
Jason Evans
919e4a0ea9 Add LG_QUANTUM definition for the RISC-V architecture. 2016-05-06 17:15:32 -07:00
Jason Evans
1326010cf4 Update private_symbols.txt. 2016-05-06 14:50:58 -07:00
Jason Evans
3ef51d7f73 Optimize the fast paths of calloc() and [m,d,sd]allocx().
This is a broader application of optimizations to malloc() and free() in
f4a0f32d34 (Fast-path improvement:
reduce # of branches and unnecessary operations.).

This resolves #321.
2016-05-06 14:37:39 -07:00
Jason Evans
c2f970c32b Modify pages_map() to support mapping uncommitted virtual memory.
If the OS overcommits:
- Commit all mappings in pages_map() regardless of whether the caller
  requested committed memory.
- Linux-specific: Specify MAP_NORESERVE to avoid
  unfortunate interactions with heuristic overcommit mode during
  fork(2).

This resolves #193.
2016-05-05 18:56:17 -07:00
Jason Evans
04c3c0f9a0 Add the stats.retained and stats.arenas.<i>.retained statistics.
This resolves #367.
2016-05-03 22:11:35 -07:00
Jason Evans
90827a3f3e Fix huge_palloc() regression.
Split arena_choose() into arena_[i]choose() and use arena_ichoose() for
arena lookup during internal allocation.  This fixes huge_palloc() so
that it always succeeds during extent node allocation.

This regression was introduced by
66cd953514 (Do not allocate metadata via
non-auto arenas, nor tcaches.).
2016-05-03 17:19:15 -07:00
Jason Evans
108c4a11e9 Fix witness/fork() interactions.
Fix witness to clear its list of owned mutexes in the child if
platform-specific malloc_mutex code re-initializes mutexes rather than
unlocking them.
2016-04-26 10:47:22 -07:00
Jason Evans
174c0c3a9c Fix fork()-related lock rank ordering reversals. 2016-04-25 23:16:20 -07:00
Jason Evans
71d94828a2 Fix degenerate mb_write() compilation error.
This resolves #375.
2016-04-22 21:27:17 -07:00
Jason Evans
19ff2cefba Implement the arena.<i>.reset mallctl.
This makes it possible to discard all of an arena's allocations in a
single operation.

This resolves #146.
2016-04-22 15:20:06 -07:00
Jason Evans
66cd953514 Do not allocate metadata via non-auto arenas, nor tcaches.
This assures that all internally allocated metadata come from the
first opt_narenas arenas, i.e. the automatically multiplexed arenas.
2016-04-22 15:19:59 -07:00
Jason Evans
b6e07d2389 Fix malloc_mutex_assert_[not_]owner() for --enable-lazy-lock case. 2016-04-18 15:42:09 -07:00
Jason Evans
ab0cfe01fa Update private_symbols.txt.
Change test-related mangling to simplify symbol filtering.

The following commands can be used to detect missing/obsolete symbol
mangling, with the caveat that the full set of symbols is based on the
union of symbols generated by all configurations, some of which are
platform-specific:

./autogen.sh --enable-debug --enable-prof --enable-lazy-lock
make all tests
nm -a lib/libjemalloc.a src/*.jet.o \
  |grep " [TDBCR] " \
  |awk '{print $3}' \
  |sed -e 's/^\(je_\|jet_\(n_\)\?\)\([a-zA-Z0-9_]*\)/\3/g' \
  |LC_COLLATE=C sort -u \
  |grep -v \
   -e '^\(malloc\|calloc\|posix_memalign\|aligned_alloc\|realloc\|free\)$' \
   -e '^\(m\|r\|x\|s\|d\|sd\|n\)allocx$' \
   -e '^mallctl\(\|nametomib\|bymib\)$' \
   -e '^malloc_\(stats_print\|usable_size\|message\)$' \
   -e '^\(memalign\|valloc\)$' \
   -e '^__\(malloc\|memalign\|realloc\|free\)_hook$' \
   -e '^pthread_create$' \
  > /tmp/private_symbols.txt
2016-04-18 15:23:35 -07:00
Rajat Goel
a0c632c9d5 Update private_symbols.txt
Add 4 missing symbols
2016-04-18 11:54:09 -07:00
Jason Evans
1423ee9016 Fix style nits. 2016-04-17 13:44:59 -07:00
Jason Evans
1b5830178f Fix malloc_mutex_[un]lock() to conditionally check witness.
Also remove tautological cassert(config_debug) calls.
2016-04-17 13:44:59 -07:00
Jason Evans
2288424325 s/MALLOC_MUTEX_RANK_OMIT/WITNESS_RANK_OMIT/
This fixes a compilation error caused by
b2c0d6322d (Add witness, a simple online
locking validator.).

This resolves #375.
2016-04-14 12:18:55 -07:00
Jason Evans
a15841cc7d Fix a compilation error.
Fix a compilation error that occurs if Valgrind is not enabled.  This
regression was caused by b2c0d6322d (Add
witness, a simple online locking validator.).
2016-04-14 02:12:33 -07:00
Jason Evans
b2c0d6322d Add witness, a simple online locking validator.
This resolves #358.
2016-04-14 02:09:28 -07:00
Jason Evans
8413463f3a Fix a style nit. 2016-04-12 23:18:25 -07:00
Jason Evans
667eca2ac2 Simplify RTREE_HEIGHT_MAX definition.
Use 1U rather than ZU(1) in macro definitions, so that the preprocessor
can evaluate the resulting expressions.
2016-04-11 02:35:00 -07:00
Jason Evans
245ae6036c Support --with-lg-page values larger than actual page size.
During over-allocation in preparation for creating aligned mappings,
allocate one more page than necessary if PAGE is the actual page size,
so that trimming still succeeds even if the system returns a mapping
that has less than PAGE alignment.  This allows compiling with e.g. 64
KiB "pages" on systems that actually use 4 KiB pages.

Note that for e.g. --with-lg-page=21, it is also necessary to increase
the chunk size (e.g. --with-malloc-conf=lg_chunk:22) so that there are
at least two "pages" per chunk.  In practice this isn't a particularly
compelling configuration because so much (unusable) virtual memory is
dedicated to chunk headers.
2016-04-11 02:35:00 -07:00
Jason Evans
96aa67aca8 Clean up char vs. uint8_t in junk filling code.
Consistently use uint8_t rather than char for junk filling code.
2016-04-11 02:26:35 -07:00
Jason Evans
c6a2c39404 Refactor/fix ph.
Refactor ph to support configurable comparison functions.  Use a cpp
macro code generation form equivalent to the rb macros so that pairing
heaps can be used for both run heaps and chunk heaps.

Remove per node parent pointers, and instead use leftmost siblings' prev
pointers to track parents.

Fix multi-pass sibling merging to iterate over intermediate results
using a FIFO, rather than a LIFO.  Use this fixed sibling merging
implementation for both merge phases of the auxiliary twopass algorithm
(first merging the aux list, then replacing the root with its merged
children).  This fixes both degenerate merge behavior and the potential
for deep recursion.

This regression was introduced by
6bafa6678f (Pairing heap).

This resolves #371.
2016-04-11 02:15:42 -07:00
Jason Evans
2ee2f1ec57 Reduce differences between alternative bitmap implementations. 2016-04-06 10:38:47 -07:00
Jason Evans
4a8abbb400 Fix bitmap_sfu() regression.
Fix bitmap_sfu() to shift by LG_BITMAP_GROUP_NBITS rather than
hard-coded 6 when using linear (non-USE_TREE) bitmap search.  In
practice this affects only 64-bit systems for which sizeof(long) is not
8 (i.e. Windows), since USE_TREE is defined for 32-bit systems.

This regression was caused by b8823ab026
(Use linear scan for small bitmaps).

This resolves #368.
2016-04-06 10:32:06 -07:00