Commit Graph

1466 Commits

Author SHA1 Message Date
Jason Evans
ea9961acdb Fix psz/pind edge cases.
Add an "over-size" extent heap in which to store extents which exceed
the maximum size class (plus cache-oblivious padding, if enabled).
Remove psz2ind_clamp() and use psz2ind() instead so that trying to
allocate the maximum size class can in principle succeed.  In practice,
this allows assertions to hold so that OOM errors can be successfully
generated.
2016-11-03 22:33:34 -07:00
Jason Evans
8dd5ea87ca Fix extent_alloc_cache[_locked]() to support decommitted allocation.
Fix extent_alloc_cache[_locked]() to support decommitted allocation, and
use this ability in arena_stash_dirty(), so that decommitted extents are
not needlessly committed during purging.  In practice this does not
happen on any currently supported systems, because both extent merging
and decommit must be implemented; all supported systems implement one
xor the other.
2016-11-03 22:33:23 -07:00
Jason Evans
4f7d8c2dee Update symbol mangling. 2016-11-03 15:00:02 -07:00
Jason Evans
04e1328ef1 Update ChangeLog for 4.3.0. 2016-11-02 21:39:24 -07:00
Samuel Moritz
69f027b855 Support Debian GNU/kFreeBSD.
Treat it exactly like Linux since they both use GNU libc.
2016-11-02 20:36:37 -07:00
Dave Watson
25f7bbcf28 Fix long spinning in rtree_node_init
rtree_node_init spinlocks the node, allocates, and then sets the node.
This is under heavy contention at the top of the tree if many threads
start to allocate at the same time.

Instead, take a per-rtree sleeping mutex to reduce spinning.  Tested
both pthreads and osx OSSpinLock, and both reduce spinning adequately

Previous benchmark time:
./ttest1 500 100
~15s

New benchmark time:
./ttest1 500 100
.57s
2016-11-02 20:30:53 -07:00
Dave Watson
712fde79fd Check for existance of CPU_COUNT macro before using it.
This resolves #485.
2016-11-02 20:05:40 -07:00
Jason Evans
83ebf2fda5 Fix sycall(2) configure test for Linux. 2016-11-02 19:50:44 -07:00
Jason Evans
d82f2b3473 Do not use syscall(2) on OS X 10.12 (deprecated). 2016-11-02 19:18:33 -07:00
Jason Evans
795f6689de Add os_unfair_lock support.
OS X 10.12 deprecated OSSpinLock; os_unfair_lock is the recommended
replacement.
2016-11-02 18:09:45 -07:00
Jason Evans
d9f7b2a430 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 18:06:40 -07:00
Jason Evans
b54072dfee Call _exit(2) rather than exit(3) in forked child.
_exit(2) is async-signal-safe, whereas exit(3) is not.
2016-11-02 18:05:19 -07:00
Jason Evans
eee1ca655e Force no lazy-lock on Windows.
Monitoring thread creation is unimplemented for Windows, which means
lazy-lock cannot function correctly.

This resolves #310.
2016-11-02 09:14:47 -07:00
Jason Evans
7b0a8b74f0 malloc_stats_print() fixes/cleanups.
Fix and clean up various malloc_stats_print() issues caused by
0ba5b9b618 (Add "J" (JSON) support to
malloc_stats_print().).
2016-11-01 15:26:35 -07:00
Jason Evans
2a2d1b6e86 Use <quote>...</quote> rather than &ldquo;...&rdquo; or "..." in XML. 2016-11-01 13:25:42 -07:00
Jason Evans
0ba5b9b618 Add "J" (JSON) support to malloc_stats_print().
This resolves #474.
2016-10-31 22:30:49 -07:00
Jason Evans
b93f63b3eb Fix extent_rtree acquire() to release element on error.
This resolves #480.
2016-10-31 16:32:33 -07:00
Jason Evans
90b60eeae4 Add an assertion in witness_owner(). 2016-10-31 15:28:22 -07:00
Jason Evans
6a834d94bb Refactor witness_unlock() to fix undefined test behavior.
This resolves #396.
2016-10-31 11:49:12 -07:00
Jason Evans
6c80321aed 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 22:58:18 -07:00
Jason Evans
d87037a62c Use syscall(2) rather than {open,read,close}(2) during boot.
Some applications wrap various system calls, and if they call the
allocator in their wrappers, unexpected reentry can result.  This is not
a general solution (many other syscalls are spread throughout the code),
but this resolves a bootstrapping issue that is apparently common.

This resolves #443.
2016-10-29 22:41:04 -07:00
Jason Evans
af0e28fd94 Fix EXTRA_CFLAGS to not affect configuration. 2016-10-29 22:14:55 -07:00
Jason Evans
1dcd0aa07f Do not mark malloc_conf as weak on Windows.
This works around malloc_conf not being properly initialized by at least
the cygwin toolchain.  Prior build system changes to use
-Wl,--[no-]whole-archive may be necessary for malloc_conf resolution to
work properly as a non-weak symbol (not tested).
2016-10-29 00:13:11 -07:00
Jason Evans
6ec2d8e279 Do not mark malloc_conf as weak for unit tests.
This is generally correct (no need for weak symbols since no jemalloc
library is involved in the link phase), and avoids linking problems
(apparently unininitialized non-NULL malloc_conf) when using cygwin with
gcc.
2016-10-28 23:03:25 -07:00
Dave Watson
8309388408 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 15:08:19 -07:00
Jason Evans
bde815dc40 Reduce memory requirements for regression tests.
This is intended to drop memory usage to a level that AppVeyor test
instances can handle.

This resolves #393.
2016-10-28 11:23:24 -07:00
Jason Evans
970d293257 Periodically purge in memory-intensive integration tests.
This resolves #393.
2016-10-28 11:00:36 -07:00
Jason Evans
963289df13 Periodically purge in memory-intensive integration tests.
This resolves #393.
2016-10-28 10:44:39 -07:00
Jason Evans
68e14c9884 Fix over-sized allocation of rtree leaf nodes.
Use the correct level metadata when allocating child nodes so that leaf
nodes don't end up over-sized (2^16 elements vs 2^4 elements).
2016-10-28 00:16:55 -07:00
Jason Evans
977103c897 Uniformly cast mallctl[bymib]() oldp/newp arguments to (void *).
This avoids warnings in some cases, and is otherwise generally good
hygiene.
2016-10-27 21:31:25 -07:00
Jason Evans
44df4a45cf Explicitly cast negative constants meant for use as unsigned. 2016-10-27 21:29:59 -07:00
Jason Evans
17aa187f6b Add cast to silence (harmless) conversion warning. 2016-10-27 21:29:00 -07:00
Jason Evans
48d4adfbeb Avoid negation of unsigned numbers.
Rather than relying on two's complement negation for alignment mask
generation, use bitwise not and addition.  This dodges warnings from
MSVC, and should be strength-reduced by compiler optimization anyway.
2016-10-27 21:26:33 -07:00
Jason Evans
d76cfec319 Only link with libm (-lm) if necessary.
This fixes warnings when building with MSVC.
2016-10-27 21:23:48 -07:00
Jason Evans
c44fa92db5 Only use --whole-archive with gcc.
Conditionalize use of --whole-archive on the platform plus compiler,
rather than on the ABI.  This fixes a regression caused by
7b24c6e557 (Use --whole-archive when
linking integration tests on MinGW.).
2016-10-27 17:10:56 -07:00
Jason Evans
583c32c305 Do not force lazy lock on Windows.
This reverts 13473c7c66, which was
intended to work around bootstrapping issues when linking statically.
However, this actually causes problems in various other configurations,
so this reversion may force a future fix for the underlying problem, if
it still exists.
2016-10-27 15:41:43 -07:00
Jason Evans
7b24c6e557 Use --whole-archive when linking integration tests on MinGW.
Prior to this change, the malloc_conf weak symbol provided by the
jemalloc dynamic library is always used, even if the application
provides a malloc_conf symbol.  Use the --whole-archive linker option
to allow the weak symbol to be overridden.
2016-10-25 22:03:14 -07:00
Jason Evans
b54d160dc4 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.
2016-10-20 23:59:12 -07:00
Jason Evans
577d4572b0 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
extent_in_dss() and the newly added extent_dss_mergeable(), which can be
called multiple times during extent 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 15:37:00 -07:00
Jason Evans
e5effef428 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 14:55:39 -07:00
Jason Evans
9acd5cf178 Remove all vestiges of chunks.
Remove mallctls:
- opt.lg_chunk
- stats.cactive

This resolves #464.
2016-10-12 11:55:43 -07:00
Jason Evans
63b5657aa5 Remove ratio-based purging.
Make decay-based purging the default (and only) mode.

Remove associated mallctls:
- opt.purge
- opt.lg_dirty_mult
- arena.<i>.lg_dirty_mult
- arenas.lg_dirty_mult
- stats.arenas.<i>.lg_dirty_mult

This resolves #385.
2016-10-12 10:40:27 -07:00
Jason Evans
b4b4a77848 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 15:30:01 -07:00
Jason Evans
48993ed536 Fix decay tests to all adapt to nstime_monotonic(). 2016-10-11 15:28:43 -07:00
Jason Evans
5f11fb7d43 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 22:15:10 -07:00
Jason Evans
ee0c74b77a Refactor arena->decay_* into arena->decay.* (arena_decay_t). 2016-10-10 20:32:19 -07:00
Jason Evans
e0164bc63c 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 10:33:59 -07:00
Jason Evans
b6c0867142 Reduce "thread.arena" mallctl contention.
This resolves #460.
2016-10-04 09:54:18 -07:00
Jason Evans
a5a8d7ae8d Remove a size class assertion from extent_size_quantize_floor().
Extent coalescence can result in legitimate calls to
extent_size_quantize_floor() with size larger than LARGE_MAXCLASS.
2016-10-03 14:45:27 -07:00
Jason Evans
871a9498e1 Fix size class overflow bugs.
Avoid calling s2u() on raw extent sizes in extent_recycle().

Clamp psz2ind() (implemented as psz2ind_clamp()) when inserting/removing
into/from size-segregated extent heaps.
2016-10-03 14:18:55 -07:00