Extend per arena unused dirty page purging to manage unused dirty chunks
in aaddtion to unused dirty runs. Rather than immediately unmapping
deallocated chunks (or purging them in the --disable-munmap case), store
them in a separate set of trees, chunks_[sz]ad_dirty. Preferrentially
allocate dirty chunks. When excessive unused dirty pages accumulate,
purge runs and chunks in ingegrated LRU order (and unmap chunks in the
--enable-munmap case).
Refactor extent_node_t to provide accessor functions.
Migrate all centralized data structures related to huge allocations and
recyclable chunks into arena_t, so that each arena can manage huge
allocations and recyclable virtual memory completely independently of
other arenas.
Add chunk node caching to arenas, in order to avoid contention on the
base allocator.
Use chunks_rtree to look up huge allocations rather than a red-black
tree. Maintain a per arena unsorted list of huge allocations (which
will be needed to enumerate huge allocations during arena reset).
Remove the --enable-ivsalloc option, make ivsalloc() always available,
and use it for size queries if --enable-debug is enabled. The only
practical implications to this removal are that 1) ivsalloc() is now
always available during live debugging (and the underlying radix tree is
available during core-based debugging), and 2) size query validation can
no longer be enabled independent of --enable-debug.
Remove the stats.chunks.{current,total,high} mallctls, and replace their
underlying statistics with simpler atomically updated counters used
exclusively for gdump triggering. These statistics are no longer very
useful because each arena manages chunks independently, and per arena
statistics provide similar information.
Simplify chunk synchronization code, now that base chunk allocation
cannot cause recursive lock acquisition.
Add the MALLOCX_TCACHE() and MALLOCX_TCACHE_NONE macros, which can be
used in conjunction with the *allocx() API.
Add the tcache.create, tcache.flush, and tcache.destroy mallctls.
This resolves#145.
The documentation for opt.lg_dirty_mult says:
Per-arena minimum ratio (log base 2) of active to dirty
pages. Some dirty unused pages may be allowed to accumulate,
within the limit set by the ratio (or one chunk worth of dirty
pages, whichever is greater) (...)
The restriction in parentheses currently doesn't happen. This makes
jemalloc aggressively madvise(), which in turns increases the amount
of page faults significantly.
For instance, this resulted in several(!) hundred(!) milliseconds
startup regression on Firefox for Android.
This may require further tweaking, but starting with actually doing
what the documentation says is a good start.
There are three categories of metadata:
- Base allocations are used for bootstrap-sensitive internal allocator
data structures.
- Arena chunk headers comprise pages which track the states of the
non-metadata pages.
- Internal allocations differ from application-originated allocations
in that they are for internal use, and that they are omitted from heap
profiles.
The metadata statistics comprise the metadata categories as follows:
- stats.metadata: All metadata -- base + arena chunk headers + internal
allocations.
- stats.arenas.<i>.metadata.mapped: Arena chunk headers.
- stats.arenas.<i>.metadata.allocated: Internal allocations. This is
reported separately from the other metadata statistics because it
overlaps with the allocated and active statistics, whereas the other
metadata statistics do not.
Base allocations are not reported separately, though their magnitude can
be computed by subtracting the arena-specific metadata.
This resolves#163.
In addition to true/false, opt.junk can now be either "alloc" or "free",
giving applications the possibility of junking memory only on allocation
or deallocation.
This resolves#172.
The size of the source allocation is known at this point, so reading the
chunk header can be avoided for the small size class fast path. This is
not very useful right now, but it provides a significant performance
boost with an alternate ralloc entry point taking the old size.
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.
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.
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.
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.
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).
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
Fix an OOM-related regression in arena_tcache_fill_small() that caused
cache corruption that would almost certainly expose the application to
undefined behavior, usually in the form of an allocation request
returning an already-allocated region, or somewhat less likely, a freed
region that had already been returned to the arena, thus making it
available to the arena for any purpose.
This regression was introduced by
9c43c13a35 (Reverse tcache fill order.),
and was present in all releases from 2.2.0 through 3.6.0.
This resolves#98.
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.
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.
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.
Fix the cactive statistic to decrease (rather than increase) when active
memory decreases. This regression was introduced by
aa5113b1fd (Refactor overly large/complex
functions) and first released in 3.5.0.
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.
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.
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.
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.
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().
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.
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).
This happens when it fails to allocate a new chunk. Which
arena_chunk_alloc then passes into arena_avail_insert without any
checks. This then causes a crash when arena_avail_insert tries
to check chunk->ndirty.
This was introduced by the refactoring of arena_chunk_alloc
which previously would have returned NULL immediately after
calling chunk_alloc. This is now the return from
arena_chunk_init_hard so we need to check that return, and
not continue if it was NULL.
Refactor overly large functions by breaking out helper functions.
Refactor overly complex multi-purpose functions into separate more
specific 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().
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.
Don't junk fill reallocations for which the request size is less than
the current usable size, but not enough smaller to cause a size class
change. Unlike malloc()/calloc()/realloc(), *allocx() contractually
treats the full usize as the allocation, so a caller can ask for zeroed
memory via mallocx() and a series of rallocx() calls that all specify
MALLOCX_ZERO, and be assured that all newly allocated bytes will be
zeroed and made available to the application without danger of allocator
mutation until the size class decreases enough to cause usize reduction.
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);
Fix a Valgrind integration flaw that caused Valgrind warnings about
reads of uninitialized memory in internal zero-initialized data
structures (relevant to tcache and prof code).
Tighten valgrind integration such that immediately after memory is
validated or zeroed, valgrind is told to forget the memory's 'defined'
state. The only place newly allocated memory should be left marked as
'defined' is in the public functions (e.g. calloc() and realloc()).
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.
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.
mlockall(2) can cause purging via madvise(2) to fail. Fix purging code
to check whether madvise() succeeded, and base zeroed page metadata on
the result.
Reported by Olivier Lecomte.
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.
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).
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).
Theses newly added macros will be used to implement the equivalent under
MSVC. Also, move the definitions to headers, where they make more sense,
and for some, are even more useful there (e.g. malloc).
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.
Clean up a few config-related conditionals to avoid unnecessary
dependencies on prof symbols. Use cassert() rather than assert()
everywhere that it's appropriate.
Add a configure test to determine whether common mmap()/munmap()
patterns cause VM map holes, and only use munmap() to discard unused
chunks if the problem does not exist.
Unify the chunk caching for mmap and dss.
Fix options processing to limit lg_chunk to be large enough that
redzones will always fit.
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()).
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.
s/PAGE_SHIFT/LG_PAGE/g and s/PAGE_SIZE/PAGE/g.
Remove remnants of the dynamic-page-shift code.
Rename the "arenas.pagesize" mallctl to "arenas.page".
Remove the "arenas.chunksize" mallctl, which is redundant with
"opt.lg_chunk".
Acquire/release arena bin locks as part of the prefork/postfork. This
bug made deadlock in the child between fork and exec a possibility.
Split jemalloc_postfork() into jemalloc_postfork_{parent,child}() so
that the child can reinitialize mutexes rather than unlocking them. In
practice, this bug tended not to cause problems.
Program-generate small size class tables for all valid combinations of
LG_TINY_MIN, LG_QUANTUM, and PAGE_SHIFT. Use the appropriate table to generate
all relevant data structures, and remove the distinction between
tiny/quantum/cacheline/subpage bins.
Remove --enable-dynamic-page-shift. This option didn't prove useful in
practice, and it prevented optimizations.
Add Tilera architecture support.
Fix an interaction between arena_dissociate_bin_run() and
arena_bin_lower_run() that made it possible for bin->runcur to point to
a run other than the lowest non-full run. This bug violated jemalloc's
layout policy, but did not affect correctness.
When tiny size class support was first added, it was intended to support
truly tiny size classes (even 2 bytes). However, this wasn't very
useful in practice, so the minimum tiny size class has been limited to
sizeof(void *) for a long time now. This is too small to be standards
compliant, but other commonly used malloc implementations do not even
bother using a 16-byte quantum on systems with vector units (SSE2+,
AltiVEC, etc.). As such, it is safe in practice to support an 8-byte
tiny size class on 64-bit systems that support 16-byte types.
tcache_get() is inlined, so do the config_tcache check inside
tcache_get() and simplify its callers.
Make arena_malloc() an inline function, since it is part of the malloc()
fast path.
Remove conditional logic that cause build issues if --disable-tcache was
specified.
Remove structure magic, because 1) it is no longer conditional, and 2)
it stopped being very effective at detecting memory corruption several
years ago.
Convert configuration-related cpp conditional logic to use static
constant variables, e.g.:
#ifdef JEMALLOC_DEBUG
[...]
#endif
becomes:
if (config_debug) {
[...]
}
The advantage is clearer, more concise code. The main disadvantage is
that data structures no longer have conditionally defined fields, so
they pay the cost of all fields regardless of whether they are used. In
practice, this is only a minor concern; config_stats will go away in an
upcoming change, and config_prof is the only other major feature that
depends on more than a few special-purpose fields.
Properly handle boundary conditions for sampled region promotion in
rallocm(). Prior to this fix, some combinations of 'size' and 'extra'
values could cause erroneous behavior. Additionally, size class
recording for promoted regions was incorrect.
Fix assertions in arena_purge() to accurately reflect the constraints in
arena_maybe_purge(). There were two bugs here, one of which merely
weakened the assertion, and the other of which referred to an
uninitialized variable (typo; used npurgatory instead of
arena->npurgatory).
