Commit Graph

62 Commits

Author SHA1 Message Date
Jason Evans
9b41ac909f Fix huge allocation statistics. 2014-10-14 22:20:00 -07:00
Jason Evans
3c4d92e82a Add per size class huge allocation statistics.
Add per size class huge allocation statistics, and normalize various
stats:
- Change the arenas.nlruns type from size_t to unsigned.
- Add the arenas.nhchunks and arenas.hchunks.<i>.size mallctl's.
- Replace the stats.arenas.<i>.bins.<j>.allocated mallctl with
  stats.arenas.<i>.bins.<j>.curregs .
- Add the stats.arenas.<i>.hchunks.<j>.nmalloc,
  stats.arenas.<i>.hchunks.<j>.ndalloc,
  stats.arenas.<i>.hchunks.<j>.nrequests, and
  stats.arenas.<i>.hchunks.<j>.curhchunks mallctl's.
2014-10-12 23:02:10 -07:00
Jason Evans
381c23dd9d Remove arena_dalloc_bin_run() clean page preservation.
Remove code in arena_dalloc_bin_run() that preserved the "clean" state
of trailing clean pages by splitting them into a separate run during
deallocation.  This was a useful mechanism for reducing dirty page
churn when bin runs comprised many pages, but bin runs are now quite
small.

Remove the nextind field from arena_run_t now that it is no longer
needed, and change arena_run_t's bin field (arena_bin_t *) to binind
(index_t).  These two changes remove 8 bytes of chunk header overhead
per page, which saves 1/512 of all arena chunk memory.
2014-10-10 23:01:03 -07:00
Jason Evans
fc0b3b7383 Add configure options.
Add:
  --with-lg-page
  --with-lg-page-sizes
  --with-lg-size-class-group
  --with-lg-quantum

Get rid of STATIC_PAGE_SHIFT, in favor of directly setting LG_PAGE.

Fix various edge conditions exposed by the configure options.
2014-10-09 22:44:37 -07:00
Jason Evans
8bb3198f72 Refactor/fix arenas manipulation.
Abstract arenas access to use arena_get() (or a0get() where appropriate)
rather than directly reading e.g. arenas[ind].  Prior to the addition of
the arenas.extend mallctl, the worst possible outcome of directly
accessing arenas was a stale read, but arenas.extend may allocate and
assign a new array to arenas.

Add a tsd-based arenas_cache, which amortizes arenas reads.  This
introduces some subtle bootstrapping issues, with tsd_boot() now being
split into tsd_boot[01]() to support tsd wrapper allocation
bootstrapping, as well as an arenas_cache_bypass tsd variable which
dynamically terminates allocation of arenas_cache itself.

Promote a0malloc(), a0calloc(), and a0free() to be generally useful for
internal allocation, and use them in several places (more may be
appropriate).

Abstract arena->nthreads management and fix a missing decrement during
thread destruction (recent tsd refactoring left arenas_cleanup()
unused).

Change arena_choose() to propagate OOM, and handle OOM in all callers.
This is important for providing consistent allocation behavior when the
MALLOCX_ARENA() flag is being used.  Prior to this fix, it was possible
for an OOM to result in allocation silently allocating from a different
arena than the one specified.
2014-10-07 23:14:57 -07:00
Jason Evans
155bfa7da1 Normalize size classes.
Normalize size classes to use the same number of size classes per size
doubling (currently hard coded to 4), across the intire range of size
classes.  Small size classes already used this spacing, but in order to
support this change, additional small size classes now fill [4 KiB .. 16
KiB).  Large size classes range from [16 KiB .. 4 MiB).  Huge size
classes now support non-multiples of the chunk size in order to fill (4
MiB .. 16 MiB).
2014-10-06 01:45:13 -07:00
Daniel Micay
a95018ee81 Attempt to expand huge allocations in-place.
This adds support for expanding huge allocations in-place by requesting
memory at a specific address from the chunk allocator.

It's currently only implemented for the chunk recycling path, although
in theory it could also be done by optimistically allocating new chunks.
On Linux, it could attempt an in-place mremap. However, that won't work
in practice since the heap is grown downwards and memory is not unmapped
(in a normal build, at least).

Repeated vector reallocation micro-benchmark:

    #include <string.h>
    #include <stdlib.h>

    int main(void) {
        for (size_t i = 0; i < 100; i++) {
            void *ptr = NULL;
            size_t old_size = 0;
            for (size_t size = 4; size < (1 << 30); size *= 2) {
                ptr = realloc(ptr, size);
                if (!ptr) return 1;
                memset(ptr + old_size, 0xff, size - old_size);
                old_size = size;
            }
            free(ptr);
        }
    }

The glibc allocator fails to do any in-place reallocations on this
benchmark once it passes the M_MMAP_THRESHOLD (default 128k) but it
elides the cost of copies via mremap, which is currently not something
that jemalloc can use.

With this improvement, jemalloc still fails to do any in-place huge
reallocations for the first outer loop, but then succeeds 100% of the
time for the remaining 99 iterations. The time spent doing allocations
and copies drops down to under 5%, with nearly all of it spent doing
purging + faulting (when huge pages are disabled) and the array memset.

An improved mremap API (MREMAP_RETAIN - #138) would be far more general
but this is a portable optimization and would still be useful on Linux
for xallocx.

Numbers with transparent huge pages enabled:

glibc (copies elided via MREMAP_MAYMOVE): 8.471s

jemalloc: 17.816s
jemalloc + no-op madvise: 13.236s

jemalloc + this commit: 6.787s
jemalloc + this commit + no-op madvise: 6.144s

Numbers with transparent huge pages disabled:

glibc (copies elided via MREMAP_MAYMOVE): 15.403s

jemalloc: 39.456s
jemalloc + no-op madvise: 12.768s

jemalloc + this commit: 15.534s
jemalloc + this commit + no-op madvise: 6.354s

Closes #137
2014-10-05 14:47:01 -07:00
Jason Evans
551ebc4364 Convert to uniform style: cond == false --> !cond 2014-10-03 10:16:09 -07:00
Jason Evans
0c5dd03e88 Move small run metadata into the arena chunk header.
Move small run metadata into the arena chunk header, with multiple
expected benefits:
- Lower run fragmentation due to reduced run sizes; runs are more likely
  to completely drain when there are fewer total regions.
- Improved cache behavior.  Prior to this change, run headers were
  always page-aligned, which put extra pressure on some CPU cache sets.
  The degree to which this was a problem was hardware dependent, but it
  likely hurt some even for the most advanced modern hardware.
- Buffer overruns/underruns are less likely to corrupt allocator
  metadata.
- Size classes between 4 KiB and 16 KiB become reasonable to support
  without any special handling, and the runs are small enough that dirty
  unused pages aren't a significant concern.
2014-09-29 01:31:39 -07:00
Jason Evans
5460aa6f66 Convert all tsd variables to reside in a single tsd structure. 2014-09-23 02:36:08 -07:00
Jason Evans
9c640bfdd4 Apply likely()/unlikely() to allocation/deallocation fast paths. 2014-09-11 17:01:58 -07:00
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
Qinfan Wu
ff6a31d3b9 Refactor chunk map.
Break the chunk map into two separate arrays, in order to improve cache
locality. This is related to issue #23.
2014-09-04 22:22:52 -07:00
Jason Evans
602c8e0971 Implement per thread heap profiling.
Rename data structures (prof_thr_cnt_t-->prof_tctx_t,
prof_ctx_t-->prof_gctx_t), and convert to storing a prof_tctx_t for
sampled objects.

Convert PROF_ALLOC_PREP() to prof_alloc_prep(), since precise backtrace
depth within jemalloc functions is no longer an issue (pprof prunes
irrelevant frames).

Implement mallctl's:
- prof.reset implements full sample data reset, and optional change of
  sample interval.
- prof.lg_sample reads the current sample interval (opt.lg_prof_sample
  was the permanent source of truth prior to prof.reset).
- thread.prof.name provides naming capability for threads within heap
  profile dumps.
- thread.prof.active makes it possible to activate/deactivate heap
  profiling for individual threads.

Modify the heap dump files to contain per thread heap profile data.
This change is incompatible with the existing pprof, which will require
enhancements to read and process the enriched data.
2014-08-19 21:31:16 -07:00
Jason Evans
070b3c3fbd Fix and refactor runs_dirty-based purging.
Fix runs_dirty-based purging to also purge dirty pages in the spare
chunk.

Refactor runs_dirty manipulation into arena_dirty_{insert,remove}(), and
move the arena->ndirty accounting into those functions.

Remove the u.ql_link field from arena_chunk_map_t, and get rid of the
enclosing union for u.rb_link, since only rb_link remains.

Remove the ndirty field from arena_chunk_t.
2014-08-14 14:45:58 -07:00
Qinfan Wu
e8a2fd83a2 arena->npurgatory is no longer needed since we drop arena's lock
after stashing all the purgeable runs.
2014-08-12 09:50:01 -07:00
Qinfan Wu
90737fcda1 Remove chunks_dirty tree, nruns_avail and nruns_adjac since we no
longer need to maintain the tree for dirty page purging.
2014-08-12 09:50:00 -07:00
Qinfan Wu
04d60a132b Maintain all the dirty runs in a linked list for each arena 2014-08-12 09:50:00 -07:00
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
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
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
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
9b0cbf0850 Remove support for non-prof-promote heap profiling metadata.
Make promotion of sampled small objects to large objects mandatory, so
that profiling metadata can always be stored in the chunk map, rather
than requiring one pointer per small region in each small-region page
run.  In practice the non-prof-promote code was only useful when using
jemalloc to track all objects and report them as leaks at program exit.
However, Valgrind is at least as good a tool for this particular use
case.

Furthermore, the non-prof-promote code is getting in the way of
some optimizations that will make heap profiling much cheaper for the
predominant use case (sampling a small representative proportion of all
allocations).
2014-04-11 14:24:51 -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
Jason Evans
aa5113b1fd Refactor overly large/complex functions.
Refactor overly large functions by breaking out helper functions.

Refactor overly complex multi-purpose functions into separate more
specific functions.
2014-01-14 16:23:03 -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
6b694c4d47 Add junk/zero filling unit tests, and fix discovered bugs.
Fix growing large reallocation to junk fill new space.

Fix huge deallocation to junk fill when munmap is disabled.
2014-01-07 16:54:17 -08:00
Jason Evans
0d6c5d8bd0 Add quarantine unit tests.
Verify that freed regions are quarantined, and that redzone corruption
is detected.

Introduce a testing idiom for intercepting/replacing internal functions.
In this case the replaced function is ordinarily a static function, but
the idiom should work similarly for library-private functions.
2013-12-17 15:19:12 -08:00
Jason Evans
5fbad0902b Finish arena_prof_ctx_set() optimization.
Delay reading the mapbits until it's unavoidable.
2013-12-15 22:08:44 -08:00
Jason Evans
665769357c Optimize arena_prof_ctx_set().
Refactor such that arena_prof_ctx_set() receives usize as an argument,
and use it to determine whether to handle ptr as a small region, rather
than reading the chunk page map.
2013-12-15 21:57:02 -08:00
Jason Evans
c368f8c8a2 Remove unnecessary zeroing in arena_palloc(). 2013-10-29 18:31:17 -07:00
Jason Evans
87a02d2bb1 Fix a Valgrind integration flaw.
Fix a Valgrind integration flaw that caused Valgrind warnings about
reads of uninitialized memory in arena chunk headers.
2013-10-19 21:40:20 -07:00
Jason Evans
88c222c8e9 Fix a prof-related locking order bug.
Fix a locking order bug that could cause deadlock during fork if heap
profiling were enabled.
2013-02-06 11:59:30 -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
Jason Evans
a3b3386ddd Avoid arena_prof_accum()-related locking when possible.
Refactor arena_prof_accum() and its callers to avoid arena locking when
prof_interval is 0 (as when profiling is disabled).

Reported by Ben Maurer.
2012-11-13 13:47:53 -08:00
Jason Evans
e3d13060c8 Purge unused dirty pages in a fragmentation-reducing order.
Purge unused dirty pages in an order that first performs clean/dirty run
defragmentation, in order to mitigate available run fragmentation.

Remove the limitation that prevented purging unless at least one chunk
worth of dirty pages had accumulated in an arena.  This limitation was
intended to avoid excessive purging for small applications, but the
threshold was arbitrary, and the effect of questionable utility.

Relax opt_lg_dirty_mult from 5 to 3.  This compensates for increased
likelihood of allocating clean runs, given the same ratio of clean:dirty
runs, and reduces the potential for repeated purging in pathological
large malloc/free loops that push the active:dirty page ratio just over
the purge threshold.
2012-11-06 00:59:53 -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
d8ceef6c55 Fix large calloc() zeroing bugs.
Refactor code such that arena_mapbits_{large,small}_set() always
preserves the unzeroed flag, and manually manipulate the unzeroed flag
in the one case where it actually gets reset (in arena_chunk_purge()).
This fixes unzeroed preservation bugs in arena_run_split() and
arena_ralloc_large_grow().  These bugs caused large calloc() to return
non-zeroed memory under some circumstances.
2012-05-10 21:49:43 -07:00
Jason Evans
53bd42c1fe Update a comment. 2012-05-10 00:18:46 -07:00
Jason Evans
80737c3323 Further optimize and harden arena_salloc().
Further optimize arena_salloc() to only look at the binind chunk map
bits in the common case.

Add more sanity checks to arena_salloc() that detect chunk map
inconsistencies for large allocations (whether due to allocator bugs or
application bugs).
2012-05-02 16:11:03 -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
Jason Evans
f7088e6c99 Make arena_salloc() an inline function. 2012-04-19 18:28:03 -07:00
Jason Evans
5ff709c264 Normalize aligned allocation algorithms.
Normalize arena_palloc(), chunk_alloc_mmap_slow(), and
chunk_recycle_dss() to use the same algorithm for trimming
over-allocation.

Add the ALIGNMENT_ADDR2BASE(), ALIGNMENT_ADDR2OFFSET(), and
ALIGNMENT_CEILING() macros, and use them where appropriate.

Remove the run_size_p parameter from sa2u().

Fix a potential deadlock in chunk_recycle_dss() that was introduced by
eae269036c (Add alignment support to
chunk_alloc()).
2012-04-11 18:13:45 -07:00
Jason Evans
122449b073 Implement Valgrind support, redzones, and quarantine.
Implement Valgrind support, as well as the redzone and quarantine
features, which help Valgrind detect memory errors.  Redzones are only
implemented for small objects because the changes necessary to support
redzones around large and huge objects are complicated by in-place
reallocation, to the point that it isn't clear that the maintenance
burden is worth the incremental improvement to Valgrind support.

Merge arena_salloc() and arena_salloc_demote().

Refactor i[v]salloc() to expose the 'demote' option.
2012-04-11 11:46:18 -07:00
Jason Evans
fad100bc35 Remove arena_malloc_prechosen().
Remove arena_malloc_prechosen(), now that arena_malloc() can be invoked
in a way that is semantically equivalent.
2012-04-06 12:24:46 -07:00