Commit Graph

1138 Commits

Author SHA1 Message Date
David Goldblatt
0552aad91b Kill size_classes.sh.
We've moved size class computations to boot time; they were being used only to
check that the computations resulted in equal values.
2018-07-12 20:53:06 -07:00
David Goldblatt
2f07e92adb Add lg_ceil to bit_util.
Also, add the bit_util test back to the Makefile.
2018-07-12 20:53:06 -07:00
David Goldblatt
07b89c7673 Move quantum detection into its own file.
This is logically fairly independent.
2018-07-12 20:53:06 -07:00
David Goldblatt
e904f813b4 Hide size class computation behind a layer of indirection.
This class removes almost all the dependencies on size_classes.h, accessing the
data there only via the new module sc.h, which does not depend on any
configuration options.

In a subsequent commit, we'll remove the configure-time size class computations,
doing them at boot time, instead.
2018-07-12 20:53:06 -07:00
gnzlbg
fb924dd7bf Suppress -Wmissing-field-initializer warning only for compilers with buggy implementation 2018-07-10 13:13:36 -07:00
gnzlbg
3d29d11ac2 Clean compilation -Wextra
Before this commit jemalloc produced many warnings when compiled with -Wextra
with both Clang and GCC. This commit fixes the issues raised by these warnings
or suppresses them if they were spurious at least for the Clang and GCC
versions covered by CI.

This commit:

* adds `JEMALLOC_DIAGNOSTIC` macros: `JEMALLOC_DIAGNOSTIC_{PUSH,POP}` are
  used to modify the stack of enabled diagnostics. The
  `JEMALLOC_DIAGNOSTIC_IGNORE_...` macros are used to ignore a concrete
  diagnostic.

* adds `JEMALLOC_FALLTHROUGH` macro to explicitly state that falling
  through `case` labels in a `switch` statement is intended

* Removes all UNUSED annotations on function parameters. The warning
  -Wunused-parameter is now disabled globally in
  `jemalloc_internal_macros.h` for all translation units that include
  that header. It is never re-enabled since that header cannot be
  included by users.

* locally suppresses some -Wextra diagnostics:

  * `-Wmissing-field-initializer` is buggy in older Clang and GCC versions,
    where it does not understanding that, in C, `= {0}` is a common C idiom
    to initialize a struct to zero

  * `-Wtype-bounds` is suppressed in a particular situation where a generic
    macro, used in multiple different places, compares an unsigned integer for
    smaller than zero, which is always true.

  * `-Walloc-larger-than-size=` diagnostics warn when an allocation function is
    called with a size that is too large (out-of-range). These are suppressed in
    the parts of the tests where `jemalloc` explicitly does this to test that the
    allocation functions fail properly.

* adds a new CI build bot that runs the log unit test on CI.

Closes #1196 .
2018-07-09 21:40:42 -07:00
Qi Wang
79522b2fc2 Refactor arena_is_auto. 2018-06-29 10:35:02 -07:00
Qi Wang
94a88c26f4 Implement huge arena: opt.huge_threshold.
The feature allows using a dedicated arena for huge allocations.  We want the
addtional arena to separate huge allocation because: 1) mixing small extents
with huge ones causes fragmentation over the long run (this feature reduces VM
size significantly); 2) with many arenas, huge extents rarely get reused across
threads; and 3) huge allocations happen way less frequently, therefore no
concerns for lock contention.
2018-06-29 10:35:02 -07:00
Qi Wang
77a71ef2b7 Fall back to the default pthread_create if RTLD_NEXT fails. 2018-06-28 13:18:21 -07:00
David Goldblatt
d1e11d48d4 Move tsd link and in_hook after tcache.
This can lead to better cache utilization down the common paths where we don't
touch the link.
2018-06-27 13:39:02 -07:00
Qi Wang
0ff7ff3ec7 Optimize ixalloc by avoiding a size lookup. 2018-06-05 21:03:51 -07:00
David Goldblatt
a7f749c9af Hooks: Protect against reentrancy.
Previously, we made the user deal with this themselves, but that's not good
enough; if hooks may allocate, we should test the allocation pathways down
hooks.  If we're doing that, we might as well actually implement the protection
for the user.
2018-05-18 11:43:03 -07:00
David Goldblatt
0379235f47 Tests: Shouldn't be able to change global slowness.
This can help ensure that we don't leave slowness changes behind in case of
resource exhaustion.
2018-05-18 11:43:03 -07:00
David Goldblatt
59e371f463 Hooks: Add a hook exhaustion test.
When we run out of space in which to store hooks, we should return EAGAIN from
the mallctl, but not otherwise misbehave.
2018-05-18 11:43:03 -07:00
David Goldblatt
126e9a84a5 Hooks: move the "extra" pointer into the hook_t itself.
This simplifies the mallctl call to install a hook, which should only take a
single argument.
2018-05-18 11:43:03 -07:00
David Goldblatt
cb0707c0fc Hooks: hook the realloc pathways that move/expand. 2018-05-18 11:43:03 -07:00
David Goldblatt
67270040a5 Hooks: hook the realloc paths that act as pure malloc/free. 2018-05-18 11:43:03 -07:00
David Goldblatt
226327cf66 Hooks: hook the pure-allocation functions. 2018-05-18 11:43:03 -07:00
David Goldblatt
5ae6e7cbfa Add "hook" module.
The hook module allows a low-reader-overhead way of finding hooks to invoke and
calling them.

For now, none of the allocation pathways are tied into the hooks; this will come
later.
2018-05-18 11:43:03 -07:00
David Goldblatt
06a8c40b36 Add the Seq module, a simple seqlock implementation.
This allows fast reader-writer concurrency in cases where writers are rare.  The
immediate use case is for the hooking implementaiton.
2018-05-18 11:43:03 -07:00
David Goldblatt
c7a87e0e0b Rename hooks module to test_hooks.
"Hooks" is really the best name for the module that will contain the publicly
exposed hooks.  So lets rename the current "hooks" module (that hook external
dependencies, for reentrancy testing) to "test_hooks".
2018-05-18 11:43:03 -07:00
David Goldblatt
e870829e64 TSD: Add the ability to enter a global slow path.
This gives any thread the ability to send other threads down slow paths the next
time they fetch tsd.
2018-05-18 11:43:03 -07:00
David Goldblatt
feff510b9f TSD: Pull name mangling into a macro. 2018-05-18 11:43:03 -07:00
David Goldblatt
39d6420c0c TSD: Make state atomic.
This will let us change the state of another thread remotely, eventually.
2018-05-18 11:43:03 -07:00
David Goldblatt
982c10de35 TSD: Make all state access happen through a function.
Shortly, tsd state will be atomic and have some complicated enough logic down
the state-setting path that we should be aware of it.
2018-05-18 11:43:03 -07:00
David Goldblatt
e74a1a37c8 Atomics: Add atomic_u8_t, force-inline operations.
We're about to need an atomic uint8_t for state operations.

Unfortunately, we're at the point where things won't get inlined into the key
methods unless they're force-inlined.  This is embarassing and we should do
something about it, but in the meantime we'll force-inline a little more when we
need to.
2018-05-18 11:43:03 -07:00
Qi Wang
312352faa8 Fix background thread index issues with max_background_threads. 2018-05-15 12:25:23 -07:00
Qi Wang
0fadf4a2e3 Add UNUSED to avoid compiler warnings. 2018-04-16 13:50:21 -07:00
Jason Evans
2a80d6f15b Avoid a printf format specifier warning.
This dodges a warning emitted by the FreeBSD system gcc when compiling
libc for architectures which don't use clang as the system compiler.
2018-04-16 11:07:51 -07:00
Dave Watson
8b14f3abc0 background_thread: add max thread count config
Looking at the thread counts in our services, jemalloc's background thread
is useful, but mostly idle.  Add a config option to tune down the number of threads.
2018-04-10 14:01:45 -07:00
Qi Wang
4be74d5112 Consolidate the two memory loads in rtree_szind_slab_read().
szind and slab bits are read on fast path, where compiler generated two memory
loads separately for them before this diff.  Manually operate on the bits to
avoid the extra memory load.
2018-04-10 10:18:46 -07:00
Qi Wang
d3e0976a2c Fix type warning on Windows.
Add cast since read / write has unsigned return type on windows.
2018-04-09 16:50:30 -07:00
Qi Wang
2dccf45640 Control idump and gdump with prof_active. 2018-04-09 16:35:14 -07:00
David Goldblatt
86c61d4a57 Stats printing: Move global mutex stats to use emitter. 2018-03-09 11:47:17 -08:00
David Goldblatt
ebe0b5f828 Emitter: Add support for row-based output in table mode.
This is needed for things like mutex stats in table mode.
2018-03-09 11:47:17 -08:00
David Goldblatt
27a8fe6780 Introduce the emitter module.
The emitter can be used to produce structured json or tabular output.  For now
it has no uses; in subsequent commits, I'll begin transitioning stats printing
code over.
2018-03-09 11:47:17 -08:00
Qi Wang
e4f090e8df Add opt.thp which allows explicit hugepage usage.
"always" marks all user mappings as MADV_HUGEPAGE; while "never" marks all
mappings as MADV_NOHUGEPAGE. The default setting "default" does not change any
settings.  Note that all the madvise calls are part of the default extent hooks
by design, so that customized extent hooks have complete control over the
mappings including hugepage settings.
2018-03-08 13:08:06 -08:00
Qi Wang
efa40532dc Remove config.thp which wasn't in use. 2018-03-08 13:08:06 -08:00
David T. Goldblatt
dd7e283b6f Tweak the ticker paths to help GCC generate better code.
GCC on its own isn't quite able to turn the ticker subtract into a memory
operation followed by a js.
2018-02-21 16:04:23 -08:00
rustyx
83aa9880b7 Make generated headers usable in both x86 and x64 mode in Visual Studio 2018-01-30 13:11:41 -08:00
Christopher Ferris
f78d4ca3fb Modify configure to determine return value of strerror_r.
On glibc and Android's bionic, strerror_r returns char* when
_GNU_SOURCE is defined.

Add a configure check for this rather than assume glibc is the
only libc that behaves this way.
2018-01-10 21:01:18 -08:00
Qi Wang
41790f4fa4 Check tsdn_null before reading reentrancy level. 2018-01-05 13:05:17 -08:00
Qi Wang
91b247d311 In iallocztm, check lock rank only when not in reentrancy. 2018-01-05 13:05:17 -08:00
Rajeev Misra
72bdbc35e3 extent_t bitpacking logic refactoring 2018-01-04 11:11:04 -08:00
Rajeev Misra
f47e39d11a handle 32 bit mutex counters 2018-01-04 11:08:17 -08:00
David Goldblatt
21f7c13d0b Add the div module, which allows fast division by dynamic values. 2017-12-21 14:25:43 -08:00
David T. Goldblatt
7f1b02e3fa Split up and standardize naming of stats code.
The arena-associated stats are now all prefixed with arena_stats_, and live in
their own file.  Likewise, malloc_bin_stats_t -> bin_stats_t, also in its own
file.
2017-12-18 16:29:10 -08:00
David T. Goldblatt
901d94a2b0 Rename cache_alloc_easy to cache_bin_alloc_easy.
This lives in the cache_bin module; just a typo.
2017-12-18 16:29:10 -08:00
David T. Goldblatt
8aafa270fd Move bin stats code from arena to bin module. 2017-12-18 16:29:10 -08:00
David T. Goldblatt
48bb4a056b Move bin forking code from arena to bin module. 2017-12-18 16:29:10 -08:00
David T. Goldblatt
a8dd8876fb Move bin initialization from arena module to bin module. 2017-12-18 16:29:10 -08:00
David T. Goldblatt
4bf4a1c4ea Pull out arena_bin_info_t and arena_bin_t into their own file.
In the process, kill arena_bin_index, which is unused.  To follow are several
diffs continuing this separation.
2017-12-18 16:29:10 -08:00
Qi Wang
740bdd68b1 Over purge by 1 extent always.
When purging, large allocations are usually the ones that cross the npages_limit
threshold, simply because they are "large".  This means we often leave the large
extent around for a while, which has the downsides of: 1) high RSS and 2) more
chance of them getting fragmented.  Given that they are not likely to be reused
very soon (LRU), let's over purge by 1 extent (which is often large and not
reused frequently).
2017-12-18 12:57:07 -08:00
Ed Schouten
749caf14ae Also use __riscv to detect builds for RISC-V CPUs.
According to the RISC-V toolchain conventions, __riscv__ is the old
spelling of this definition. __riscv should be used going forward.

https://github.com/riscv/riscv-toolchain-conventions#cc-preprocessor-definitions
2017-12-09 10:10:42 -08:00
Qi Wang
eb1b08daae Fix an extent coalesce bug.
When coalescing, we should take both extents off the LRU list; otherwise decay
can grab the existing outer extent through extents_evict.
2017-11-16 15:32:02 -08:00
Qi Wang
fac706836f Add opt.lg_extent_max_active_fit
When allocating from dirty extents (which we always prefer if available), large
active extents can get split even if the new allocation is much smaller, in
which case the introduced fragmentation causes high long term damage.  This new
option controls the threshold to reuse and split an existing active extent.  We
avoid using a large extent for much smaller sizes, in order to reduce
fragmentation.  In some workload, adding the threshold improves virtual memory
usage by >10x.
2017-11-16 15:32:02 -08:00
Dave Watson
d6feed6e66 Use tsd offset_state instead of atomic
While working on #852, I noticed the prng state is atomic.  This is the only
atomic use of prng in all of jemalloc.  Instead, use a threadlocal prng
state if possible to avoid unnecessary cache line contention.
2017-11-14 08:58:18 -08:00
Qi Wang
cb3b72b975 Fix base allocator THP auto mode locking and stats.
Added proper synchronization for switching to using THP in auto mode.  Also
fixed stats for number of THPs used.
2017-11-09 16:14:12 -08:00
Qi Wang
b5d071c266 Fix unbounded increase in stash_decayed.
Added an upper bound on how many pages we can decay during the current run.
Without this, decay could have unbounded increase in stashed, since other
threads could add new pages into the extents.
2017-11-08 16:33:30 -08:00
Qi Wang
e422fa8e7e Add arena.i.retain_grow_limit
This option controls the max size when grow_retained.  This is useful when we
have customized extent hooks reserving physical memory (e.g. 1G huge pages).
Without this feature, the default increasing sequence could result in fragmented
and wasted physical memory.
2017-11-03 13:53:33 -07:00
Qi Wang
58eba024c0 metadata_thp: auto mode adjustment for a0.
We observed that arena 0 can have much more metadata allocated comparing to
other arenas.  Tune the auto mode to only switch to huge page on the 5th block
(instead of 3 previously) for a0.
2017-11-01 13:52:06 -07:00
David Goldblatt
d14bbf8d81 Add a "dumpable" bit to the extent state.
Currently, this is unused (i.e. all extents are always marked dumpable).  In the
future, we'll begin using this functionality.
2017-10-16 15:35:49 -07:00
David Goldblatt
bbaa72422b Add pages_dontdump and pages_dodump.
This will, eventually, enable us to avoid dumping eden regions.
2017-10-16 15:35:49 -07:00
David Goldblatt
ccd09050aa Add configure-time detection for madvise(..., MADV_DO[NT]DUMP) 2017-10-16 15:35:49 -07:00
Qi Wang
31ab38be5f Define MADV_FREE on our own when needed.
On x86 Linux, we define our own MADV_FREE if madvise(2) is available, but no
MADV_FREE is detected.  This allows the feature to be built in and enabled with
runtime detection.
2017-10-11 15:49:22 -07:00
David Goldblatt
1245faae90 Power: disable the CPU_SPINWAIT macro.
Quoting from https://github.com/jemalloc/jemalloc/issues/761 :

[...] reading the Power ISA documentation[1], the assembly in [the CPU_SPINWAIT
macro] isn't correct anyway (as @marxin points out): the setting of the
program-priority register is "sticky", and we never undo the lowering.

We could do something similar, but given that we don't have testing here in the
first place, I'm inclined to simply not try. I'll put something up reverting the
problematic commit tomorrow.

[1] Book II, chapter 3 of the 2.07B or 3.0B ISA documents.
2017-10-04 18:37:23 -07:00
Dave Watson
7c6c99b829 Use ph instead of rb tree for extents_avail_
There does not seem to be any overlap between usage of
extent_avail and extent_heap, so we can use the same hook.

The only remaining usage of rb trees is in the profiling code,
which has some 'interesting' iteration constraints.

Fixes #888
2017-10-04 12:23:03 -07:00
David Goldblatt
8a7ee3014c Logging: capitalize log macro.
Dodge a name-conflict with the math.h logarithm function. D'oh.
2017-10-02 20:44:43 -07:00
David Goldblatt
7a8bc7172b ARM: Don't extend bit LG_VADDR to compute high address bits.
In userspace ARM on Linux, zero-ing the high bits is the correct way to do this.
This doesn't fix the fact that we currently set LG_VADDR to 48 on ARM, when in
fact larger virtual address sizes are coming soon.  We'll cross that bridge when
we come to it.
2017-10-02 14:54:46 -07:00
Qi Wang
3959a9fe19 Avoid left shift by negative values.
Fix warnings on -Wshift-negative-value.
2017-09-25 15:38:58 -07:00
Qi Wang
56f0e57844 Add "falls through" comment explicitly.
Fix warnings by -Wimplicit-fallthrough.
2017-09-25 15:38:58 -07:00
Qi Wang
d60f3bac12 Add missing field in initializer for rtree cache.
Fix a warning by -Wmissing-field-initializers.
2017-09-21 12:18:10 -07:00
Qi Wang
a315688be0 Relax constraints on reentrancy for extent hooks.
If we guarantee no malloc activity in extent hooks, it's possible to make
customized hooks working on arena 0.  Remove the non-a0 assertion to enable such
use cases.
2017-08-31 11:03:34 -07:00
Qi Wang
e55c3ca267 Add stats for metadata_thp.
Report number of THPs used in arena and aggregated stats.
2017-08-30 16:47:32 -07:00
Qi Wang
47b20bb654 Change opt.metadata_thp to [disabled,auto,always].
To avoid the high RSS caused by THP + low usage arena (i.e. THP becomes a
significant percentage), added a new "auto" option which will only start using
THP after a base allocator used up the first THP region.  Starting from the
second hugepage (in a single arena), "auto" behaves the same as "always",
i.e. madvise hugepage right away.
2017-08-30 16:47:32 -07:00
David Goldblatt
ea91dfa58e Document the ialloc function abbreviations.
In the jemalloc_internal_inlines files, we have a lot of somewhat terse function
names.  This commit adds some documentation to aid in translation.
2017-08-16 17:48:44 -07:00
David Goldblatt
9c0549007d Make arena stats collection go through cache bins.
This eliminates the need for the arena stats code to "know" about tcaches; all
that it needs is a cache_bin_array_descriptor_t to tell it where to find
cache_bins whose stats it should aggregate.
2017-08-16 17:48:44 -07:00
David Goldblatt
f3170baa30 Pull out caching for a bin into its own file.
This is the first step towards breaking up the tcache and arena (since they
interact primarily at the bin level).  It should also make a future arena
caching implementation more straightforward.
2017-08-16 17:48:44 -07:00
Faidon Liambotis
82d1a3fb31 Add support for m68k, nios2, SH3 architectures
Add minimum alignment for three more architectures, as requested by
Debian users or porters (see Debian bugs #807554, #816236, #863424).
2017-08-11 16:35:44 -07:00
Qi Wang
3ec279ba1c Fix test/unit/pages.
As part of the metadata_thp support, We now have a separate swtich
(JEMALLOC_HAVE_MADVISE_HUGE) for MADV_HUGEPAGE availability.  Use that instead
of JEMALLOC_THP (which doesn't guard pages_huge anymore) in tests.
2017-08-11 15:57:12 -07:00
Qi Wang
8fdd9a5797 Implement opt.metadata_thp
This option enables transparent huge page for base allocators (require
MADV_HUGEPAGE support).
2017-08-11 14:51:20 -07:00
Ryan Libby
048c6679cd Remove external linkage for spin_adaptive
The external linkage for spin_adaptive was not used, and the inline
declaration of spin_adaptive that was used caused a probem on FreeBSD
where CPU_SPINWAIT is implemented as a call to a static procedure for
x86 architectures.
2017-08-08 10:30:21 -07:00
David Goldblatt
e6aeceb606 Logging: log using the log var names directly.
Currently we have to log by writing something like:

  static log_var_t log_a_b_c = LOG_VAR_INIT("a.b.c");
  log (log_a_b_c, "msg");

This is sort of annoying.  Let's just write:

  log("a.b.c", "msg");
2017-07-24 14:55:54 -07:00
David Goldblatt
a9f7732d45 Logging: allow logging with empty varargs.
Currently, the log macro requires at least one argument after the format string,
because of the way the preprocessor handles varargs macros.  We can hide some of
that irritation by pushing the extra arguments into a varargs function.
2017-07-22 09:38:19 -07:00
David T. Goldblatt
e215a7bc18 Add entry and exit logging to all core functions.
I.e. mallloc, free, the allocx API, the posix extensions.
2017-07-20 17:58:37 -07:00
David T. Goldblatt
9761b449c8 Add a logging facility.
This sets up a hierarchical logging facility, so that we can add logging
statements liberally, and turn them on in a fine-grained manner.
2017-07-20 17:58:37 -07:00
Qi Wang
cb032781bd Add extent_grow_mtx in pre_ / post_fork handlers.
This fixed the issue that could cause the child process to stuck after fork.
2017-06-29 17:01:18 -07:00
Qi Wang
57beeb2fcb Switch ctl to explicitly use tsd instead of tsdn. 2017-06-23 13:27:53 -07:00
Qi Wang
425463a446 Check arena in current context in pre_reentrancy. 2017-06-23 13:27:53 -07:00
Qi Wang
d6eb8ac8f3 Set reentrancy when invoking customized extent hooks.
Customized extent hooks may malloc / free thus trigger reentry.  Support this
behavior by adding reentrancy on hook functions.
2017-06-23 13:27:53 -07:00
Qi Wang
a3f4977217 Add thread name for background threads. 2017-06-23 10:54:54 -07:00
Qi Wang
52fc887b49 Avoid inactivity_check within background threads.
Passing is_background_thread down the decay path, so that background thread
itself won't attempt inactivity_check.  This fixes an issue with background
thread doing trylock on a mutex it already owns.
2017-06-22 16:53:58 -07:00
Jason Evans
37f3fa0941 Mask signals during background thread creation.
This prevents signals from being inadvertently delivered to background
threads.
2017-06-20 17:47:38 -07:00
Qi Wang
9b1befabbb Add minimal initialized TSD.
We use the minimal_initilized tsd (which requires no cleanup) for free()
specifically, if tsd hasn't been initialized yet.

Any other activity will transit the state from minimal to normal.  This is to
workaround the case where a thread has no malloc calls in its lifetime until
during thread termination, free() happens after tls destructors.
2017-06-15 17:55:53 -07:00
Qi Wang
ae93fb08e2 Pass tsd to tcache_flush(). 2017-06-15 17:55:53 -07:00
Qi Wang
a4d6fe73cf Only abort on dlsym when necessary.
If neither background_thread nor lazy_lock is in use, do not abort on dlsym
errors.
2017-06-14 13:27:41 -07:00
Qi Wang
394df9519d Combine background_thread started / paused into state. 2017-06-12 08:56:14 -07:00
Qi Wang
464cb60490 Move background thread creation to background_thread_0.
To avoid complications, avoid invoking pthread_create "internally", instead rely
on thread0 to launch new threads, and also terminating threads when asked.
2017-06-12 08:56:14 -07:00
Jason Evans
13685ab1b7 Normalize background thread configuration.
Also fix a compilation error #ifndef JEMALLOC_PTHREAD_CREATE_WRAPPER.
2017-06-08 23:01:26 -07:00
Jason Evans
faaf458bad Remove redundant typedefs.
Pre-C11 compilers do not support typedef redefinition.
2017-06-08 13:28:57 -07:00
Qi Wang
5642f03cae Add internal tsd for background_thread. 2017-06-08 10:02:18 -07:00
Qi Wang
73713fbb27 Drop high rank locks when creating threads.
Avoid holding arenas_lock and background_thread_lock when creating background
threads, because pthread_create may take internal locks, and potentially cause
deadlock with jemalloc internal locks.
2017-06-08 10:02:18 -07:00
Qi Wang
00869e39a3 Make tsd no-cleanup during tsd reincarnation.
Since tsd cleanup isn't guaranteed when reincarnated, we set up tsd in a way
that needs no cleanup, by making it going through slow path instead.
2017-06-07 11:03:49 -07:00
Qi Wang
3a813946fb Take background thread lock when setting extent hooks. 2017-06-05 10:56:25 -07:00
Qi Wang
340071f0cf Set isthreaded when enabling background_thread. 2017-06-01 17:34:49 -07:00
Jason Evans
b511232fcd Refactor/fix background_thread/percpu_arena bootstrapping.
Refactor bootstrapping such that dlsym() is called during the
bootstrapping phase that can tolerate reentrant allocation.
2017-06-01 08:55:27 -07:00
David Goldblatt
8261e581be Header refactoring: Pull size helpers out of jemalloc module. 2017-05-31 13:08:45 -07:00
David Goldblatt
041e041e1f Header refactoring: unify and de-catchall mutex_pool. 2017-05-31 13:08:45 -07:00
David Goldblatt
98774e64a4 Header refactoring: unify and de-catchall extent_mmap module. 2017-05-31 13:08:45 -07:00
David Goldblatt
93284bb53d Header refactoring: unify and de-catchall extent_dss. 2017-05-31 13:08:45 -07:00
David Goldblatt
44f9bd147a Header refactoring: unify and de-catchall rtree module. 2017-05-31 13:08:45 -07:00
Jason Evans
c606a87d2a Add the --disable-thp option to support cross compiling.
This resolves #669.
2017-05-30 11:30:54 -07:00
Jason Evans
168793a1c1 Fix extent_grow_next management.
Fix management of extent_grow_next to serialize operations that may grow
retained memory.  This assures that the sizes of the newly allocated
extents correspond to the size classes in the intended growth sequence.

Fix management of extent_grow_next to skip size classes if a request is
too large to be satisfied by the next size in the growth sequence.  This
avoids the potential for an arbitrary number of requests to bypass
triggering extent_grow_next increases.

This resolves #858.
2017-05-29 17:27:18 -07:00
Qi Wang
d5ef5ae934 Add opt.stats_print_opts.
The value is passed to atexit(3)-triggered malloc_stats_print() calls.
2017-05-29 11:54:00 -07:00
Qi Wang
b86d271cbf Added opt_abort_conf: abort on invalid config options. 2017-05-26 21:14:28 -07:00
Qi Wang
927239b910 Cleanup smoothstep.sh / .h.
h_step_sum was used to compute moving sum.  Not in use anymore.
2017-05-25 16:52:10 -07:00
David Goldblatt
18ecbfa89e Header refactoring: unify and de-catchall mutex module 2017-05-24 15:27:30 -07:00
David Goldblatt
9f822a1fd7 Header refactoring: unify and de-catchall witness code. 2017-05-24 15:27:30 -07:00
Jason Evans
36195c8f4d Disable percpu_arena by default. 2017-05-23 15:32:50 -07:00
Qi Wang
eeefdf3ce8 Fix # of unpurged pages in decay algorithm.
When # of dirty pages move below npages_limit (e.g. they are reused), we should
not lower number of unpurged pages because that would cause the reused pages to
be double counted in the backlog (as a result, decay happen slower than it
should).  Instead, set number of unpurged to the greater of current npages and
npages_limit.

Added an assertion: the ceiling # of pages should be greater than npages_limit.
2017-05-23 13:48:30 -07:00
Qi Wang
0eae838b0d Check for background thread inactivity on extents_dalloc.
To avoid background threads sleeping forever with idle arenas, we eagerly check
background threads' sleep time after extents_dalloc, and signal the thread if
necessary.
2017-05-23 12:26:20 -07:00
Qi Wang
5f5ed2198e Add profiling for the background thread mutex. 2017-05-23 12:26:20 -07:00
Qi Wang
2bee0c6251 Add background thread related stats. 2017-05-23 12:26:20 -07:00
Qi Wang
b693c7868e Implementing opt.background_thread.
Added opt.background_thread to enable background threads, which handles purging
currently.  When enabled, decay ticks will not trigger purging (which will be
left to the background threads).  We limit the max number of threads to NCPUs.
When percpu arena is enabled, set CPU affinity for the background threads as
well.

The sleep interval of background threads is dynamic and determined by computing
number of pages to purge in the future (based on backlog).
2017-05-23 12:26:20 -07:00
David Goldblatt
3f685e8824 Protect the rtree/extent interactions with a mutex pool.
Instead of embedding a lock bit in rtree leaf elements, we associate extents
with a small set of mutexes.  This gets us two things:

- We can use the system mutexes.  This (hypothetically) protects us from
  priority inversion, and lets us stop doing a backoff/sleep loop, instead
  opting for precise wakeups from the mutex.
- Cuts down on the number of mutex acquisitions we have to do (from 4 in the
  worst case to two).

We end up simplifying most of the rtree code (which no longer has to deal with
locking or concurrency at all), at the cost of additional complexity in the
extent code: since the mutex protecting the rtree leaf elements is determined by
reading the extent out of those elements, the initial read is racy, so that we
may acquire an out of date mutex.  We re-check the extent in the leaf after
acquiring the mutex to protect us from this race.
2017-05-19 14:21:27 -07:00
David Goldblatt
26c792e61a Allow mutexes to take a lock ordering enum at construction.
This lets us specify whether and how mutexes of the same rank are allowed to be
acquired.  Currently, we only allow two polices (only a single mutex at a given
rank at a time, and mutexes acquired in ascending order), but we can plausibly
allow more (e.g. the "release uncontended mutexes before blocking").
2017-05-19 14:21:27 -07:00
Jason Evans
6e62c62862 Refactor *decay_time into *decay_ms.
Support millisecond resolution for decay times.  Among other use cases
this makes it possible to specify a short initial dirty-->muzzy decay
phase, followed by a longer muzzy-->clean decay phase.

This resolves #812.
2017-05-18 11:33:45 -07:00
Qi Wang
baf3e294e0 Add stats: arena uptime. 2017-05-18 10:04:28 -07:00
Jason Evans
18a83681cf Refactor (MALLOCX_ARENA_MAX + 1) to be MALLOCX_ARENA_LIMIT.
This resolves #673.
2017-05-14 10:14:23 -07:00
Jason Evans
909f0482e4 Automatically generate private symbol name mangling macros.
Rather than using a manually maintained list of internal symbols to
drive name mangling, add a compilation phase to automatically extract
the list of internal symbols.

This resolves #677.
2017-05-11 23:06:54 -07:00
Jason Evans
a4ae9707da Remove unused private_unnamespace infrastructure. 2017-05-11 23:06:54 -07:00
Jason Evans
a268af5085 Stop depending on JEMALLOC_N() for function interception during testing.
Instead, always define function pointers for interceptable functions,
but mark them const unless testing, so that the compiler can optimize
out the pointer dereferences.
2017-05-11 23:06:54 -07:00
Jason Evans
81ef365622 Avoid compiler warnings on Windows. 2017-05-11 18:06:20 -07:00
Jason Evans
11d2f39d96 Remove mutex_prof_data_t redeclaration.
Redeclaration causes compilations failures with e.g. gcc 4.2.1 on
FreeBSD.  This regression was introduced by
89e2d3c12b (Header refactoring: ctl -
unify and remove from catchall.).
2017-05-11 10:49:43 -07:00
Jason Evans
0798fe6e70 Fix rtree_leaf_elm_szind_slab_update().
Re-read the leaf element when atomic CAS fails due to a race with
another thread that has locked the leaf element, since
atomic_compare_exchange_strong_p() overwrites the expected value with
the actual value on failure.  This regression was introduced by
0ee0e0c155 (Implement compact rtree leaf
element representation.).

This resolves #798.
2017-05-03 08:52:33 -07:00
Jason Evans
344dd342dd rtree_leaf_elm_extent_write() --> rtree_leaf_elm_extent_lock_write()
Refactor rtree_leaf_elm_extent_write() as
rtree_leaf_elm_extent_lock_write(), so that whether the leaf element is
currently acquired is separate from what lock state to write.  This
allows for a relaxed atomic read when releasing the lock.
2017-05-03 08:52:33 -07:00
Qi Wang
fc1aaf13fe Revert "Use trylock in tcache_bin_flush when possible."
This reverts commit 8584adc451.  Production
results not favorable.  Will investigate separately.
2017-05-01 14:49:42 -07:00
David Goldblatt
209f2926b8 Header refactoring: tsd - cleanup and dependency breaking.
This removes the tsd macros (which are used only for tsd_t in real builds).  We
break up the circular dependencies involving tsd.

We also move all tsd access through getters and setters.  This allows us to
assert that we only touch data when tsd is in a valid state.

We simplify the usages of the x macro trick, removing all the customizability
(get/set, init, cleanup), moving the lifetime logic to tsd_init and tsd_cleanup.
This lets us make initialization order independent of order within tsd_t.
2017-05-01 10:49:56 -07:00
Jason Evans
c86c8f4ffb Add extent_destroy_t and use it during arena destruction.
Add the extent_destroy_t extent destruction hook to extent_hooks_t, and
use it during arena destruction.  This hook explicitly communicates to
the callee that the extent must be destroyed or tracked for later reuse,
lest it be permanently leaked.  Prior to this change, retained extents
could unintentionally be leaked if extent retention was enabled.

This resolves #560.
2017-04-29 09:24:12 -07:00
Jason Evans
b9ab04a191 Refactor !opt.munmap to opt.retain. 2017-04-29 09:24:12 -07:00
Qi Wang
d901a37775 Revert "Use try_flush first in tcache_dalloc."
This reverts commit b0c2a28280.  Production
benchmark shows this caused significant regression in both CPU and memory
consumption.  Will investigate separately later on.
2017-04-28 10:59:04 -07:00
Qi Wang
b0c2a28280 Use try_flush first in tcache_dalloc.
Only do must_flush if try_flush didn't manage to free anything.
2017-04-25 17:21:33 -07:00
Qi Wang
8584adc451 Use trylock in tcache_bin_flush when possible.
During tcache gc, use tcache_bin_try_flush_small / _large so that we can skip
items with their bins locked already.
2017-04-25 17:21:33 -07:00
Qi Wang
05775a3736 Avoid prof_dump during reentrancy. 2017-04-25 12:54:36 -07:00
David Goldblatt
268843ac68 Header refactoring: pages.h - unify and remove from catchall. 2017-04-25 09:51:38 -07:00
David Goldblatt
dab4beb277 Header refactoring: hash - unify and remove from catchall. 2017-04-25 09:51:38 -07:00
David Goldblatt
89e2d3c12b Header refactoring: ctl - unify and remove from catchall.
In order to do this, we introduce the mutex_prof module, which breaks a circular
dependency between ctl and prof.
2017-04-25 09:51:38 -07:00
Jason Evans
c67c3e4a63 Replace --disable-munmap with opt.munmap.
Control use of munmap(2) via a run-time option rather than a
compile-time option (with the same per platform default).  The old
behavior of --disable-munmap can be achieved with
--with-malloc-conf=munmap:false.

This partially resolves #580.
2017-04-24 20:37:16 -07:00
Jason Evans
e2cc6280ed Remove --enable-code-coverage.
This option hasn't been particularly useful since the original pre-3.0.0
push to broaden test coverage.

This partially resolves #580.
2017-04-24 16:33:04 -07:00
Jason Evans
0f63396b23 Remove --disable-cc-silence.
The explicit compiler warning suppression controlled by this option is
universally desirable, so remove the ability to disable suppression.

This partially resolves #580.
2017-04-24 15:02:45 -07:00
Qi Wang
f970c497dc Implement malloc_mutex_trylock() w/ proper stats update. 2017-04-24 13:23:55 -07:00
Jason Evans
af76f0e5d2 Remove --with-lg-tiny-min.
This option isn't useful in practice.

This partially resolves #580.
2017-04-24 11:48:28 -07:00
David Goldblatt
120c7a747f Header refactoring: bitmap - unify and remove from catchall. 2017-04-24 10:33:21 -07:00
David Goldblatt
d6b5c7e0f6 Header refactoring: stats - unify and remove from catchall 2017-04-24 10:33:21 -07:00
David Goldblatt
36abf78aa9 Header refactoring: move smoothstep.h out of the catchall. 2017-04-24 10:33:21 -07:00
David Goldblatt
31b43219db Header refactoring: size_classes module - remove from the catchall 2017-04-24 10:33:21 -07:00
David Goldblatt
68da2361d2 Header refactoring: ckh module - remove from the catchall and unify. 2017-04-24 10:33:21 -07:00
David Goldblatt
bf2dc7e678 Header refactoring: ticker module - remove from the catchall and unify. 2017-04-24 10:33:21 -07:00
David Goldblatt
fa3ad730c4 Header refactoring: prng module - remove from the catchall and unify. 2017-04-24 10:33:21 -07:00
David Goldblatt
4d2e4bf5eb Get rid of most of the various inline macros. 2017-04-24 10:33:21 -07:00
David Goldblatt
425253e2cd Enable -Wundef, when supported.
This can catch bugs in which one header defines a numeric constant, and another
uses it without including the defining header. Undefined preprocessor symbols
expand to '0', so that this will compile fine, silently doing the math wrong.
2017-04-21 17:03:56 -07:00
Jason Evans
3823effe12 Remove --enable-ivsalloc.
Continue to use ivsalloc() when --enable-debug is specified (and add
assertions to guard against 0 size), but stop providing a documented
explicit semantics-changing band-aid to dodge undefined behavior in
sallocx() and malloc_usable_size().  ivsalloc() remains compiled in,
unlike when #211 restored --enable-ivsalloc, and if
JEMALLOC_FORCE_IVSALLOC is defined during compilation, sallocx() and
malloc_usable_size() will still use ivsalloc().

This partially resolves #580.
2017-04-21 14:34:35 -07:00
Jim Chen
ae248a2160 Use openat syscall if available
Some architectures like AArch64 may not have the open syscall because it
was superseded by the openat syscall, so check and use SYS_openat if
SYS_open is not available.

Additionally, Android headers for AArch64 define SYS_open to __NR_open,
even though __NR_open is undefined. Undefine SYS_open in that case so
SYS_openat is used.
2017-04-21 10:58:42 -07:00
Jason Evans
4403c9ab44 Remove --disable-tcache.
Simplify configuration by removing the --disable-tcache option, but
replace the testing for that configuration with
--with-malloc-conf=tcache:false.

Fix the thread.arena and thread.tcache.flush mallctls to work correctly
if tcache is disabled.

This partially resolves #580.
2017-04-21 10:06:12 -07:00
Qi Wang
5aa46f027d Bypass extent tracking for auto arenas.
Tracking extents is required by arena_reset.  To support this, the extent
linkage was used for tracking 1) large allocations, and 2) full slabs.  However
modifying the extent linkage could be an expensive operation as it likely incurs
cache misses.  Since we forbid arena_reset on auto arenas, let's bypass the
linkage operations for auto arenas.
2017-04-21 00:29:18 -07:00
Jason Evans
da4cff0279 Support --with-lg-page values larger than system page size.
All mappings continue to be PAGE-aligned, even if the system page size
is smaller.  This change is primarily intended to provide a mechanism
for supporting multiple page sizes with the same binary; smaller page
sizes work better in conjunction with jemalloc's design.

This resolves #467.
2017-04-18 19:01:04 -07:00
Jason Evans
45f087eb03 Revert "Remove BITMAP_USE_TREE."
Some systems use a native 64 KiB page size, which means that the bitmap
for the smallest size class can be 8192 bits, not just 512 bits as when
the page size is 4 KiB.  Linear search in bitmap_{sfu,ffu}() is
unacceptably slow for such large bitmaps.

This reverts commit 7c00f04ff4.
2017-04-18 19:01:04 -07:00
David Goldblatt
38e847c1c5 Header refactoring: unify spin.h and move it out of the catch-all. 2017-04-18 18:35:03 -07:00
David Goldblatt
418d96a86c Header refactoring: unify nstime.h and move it out of the catch-all 2017-04-18 18:35:03 -07:00
David Goldblatt
7ebc83894f Header refactoring: move jemalloc_internal_types.h out of the catch-all 2017-04-18 18:35:03 -07:00
David Goldblatt
d9ec36e22d Header refactoring: move assert.h out of the catch-all 2017-04-18 18:35:03 -07:00
David Goldblatt
f692e6c214 Header refactoring: move util.h out of the catchall 2017-04-18 18:35:03 -07:00
David Goldblatt
54373be084 Header refactoring: move malloc_io.h out of the catchall 2017-04-18 18:35:03 -07:00
David Goldblatt
0b00ffe55f Header refactoring: move bit_util.h out of the catchall 2017-04-18 18:35:03 -07:00
David Goldblatt
22366518b7 Move CPP_PROLOGUE and CPP_EPILOGUE to the .cpp
This lets us avoid having to specify them in every C file.
2017-04-18 18:35:03 -07:00
Jason Evans
881fbf762f Prefer old/low extent_t structures during reuse.
Rather than using a LIFO queue to track available extent_t structures,
use a red-black tree, and always choose the oldest/lowest available
during reuse.
2017-04-17 14:47:45 -07:00
Jason Evans
76b35f4b2f Track extent structure serial number (esn) in extent_t.
This enables stable sorting of extent_t structures.
2017-04-17 14:47:45 -07:00
Jason Evans
69aa552809 Allocate increasingly large base blocks.
Limit the total number of base block by leveraging the exponential
size class sequence, similarly to extent_grow_retained().
2017-04-17 14:47:45 -07:00
Qi Wang
3c9c41edb2 Improve rtree cache with a two-level cache design.
Two levels of rcache is implemented: a direct mapped cache as L1, combined with
a LRU cache as L2.  The L1 cache offers low cost on cache hit, but could suffer
collision under circumstances.  This is complemented by the L2 LRU cache, which
is slower on cache access (overhead from linear search + reordering), but solves
collison of L1 rather well.
2017-04-17 12:05:23 -07:00
Qi Wang
d16f1e53df Skip percpu arena when choosing iarena. 2017-04-16 21:34:44 -07:00
Qi Wang
c2fcf9c2cf Switch to fine-grained reentrancy support.
Previously we had a general detection and support of reentrancy, at the cost of
having branches and inc / dec operations on fast paths.  To avoid taxing fast
paths, we move the reentrancy operations onto tsd slow state, and only modify
reentrancy level around external calls (that might trigger reentrancy).
2017-04-14 19:48:06 -07:00
Qi Wang
b348ba29bb Bundle 3 branches on fast path into tsd_state.
Added tsd_state_nominal_slow, which on fast path malloc() incorporates
tcache_enabled check, and on fast path free() bundles both malloc_slow and
tcache_enabled branches.
2017-04-14 16:58:08 -07:00
Qi Wang
ccfe68a916 Pass alloc_ctx down profiling path.
With this change, when profiling is enabled, we avoid doing redundant rtree
lookups. Also changed dalloc_atx_t to alloc_atx_t, as it's now used on
allocation path as well (to speed up profiling).
2017-04-12 13:55:39 -07:00
Qi Wang
f35213bae4 Pass dalloc_ctx down the sdalloc path.
This avoids redundant rtree lookups.
2017-04-12 13:55:39 -07:00
David Goldblatt
e709fae1d7 Header refactoring: move atomic.h out of the catch-all 2017-04-11 11:52:30 -07:00
David Goldblatt
743d940dc3 Header refactoring: Split up jemalloc_internal.h
This is a biggy.  jemalloc_internal.h has been doing multiple jobs for a while
now:
- The source of system-wide definitions.
- The catch-all include file.
- The module header file for jemalloc.c

This commit splits up this functionality.  The system-wide definitions
responsibility has moved to jemalloc_preamble.h.  The catch-all include file is
now jemalloc_internal_includes.h.  The module headers for jemalloc.c are now in
jemalloc_internal_[externs|inlines|types].h, just as they are for the other
modules.
2017-04-11 11:52:30 -07:00
David Goldblatt
0237870c60 Header refactoring: break out ql.h dependencies 2017-04-11 11:52:30 -07:00
David Goldblatt
610cb83419 Header refactoring: break out qr.h dependencies 2017-04-11 11:52:30 -07:00
David Goldblatt
63a5cd4cc2 Header refactoring: break out rb.h dependencies 2017-04-11 11:52:30 -07:00
David Goldblatt
2f00ce4da7 Header refactoring: break out ph.h dependencies 2017-04-11 11:52:30 -07:00
David Goldblatt
57e36e1a12 Header refactoring: Add CPP_PROLOGUE and CPP_EPILOGUE macros 2017-04-11 11:52:30 -07:00
Qi Wang
bfa530b75b Pass dealloc_ctx down free() fast path.
This gets rid of the redundent rtree lookup down fast path.
2017-04-11 09:58:12 -07:00
Qi Wang
04ef218d87 Move reentrancy_level to the beginning of TSD. 2017-04-07 16:25:43 -07:00
David Goldblatt
b407a65401 Add basic reentrancy-checking support, and allow arena_new to reenter.
This checks whether or not we're reentrant using thread-local data, and, if we
are, moves certain internal allocations to use arena 0 (which should be properly
initialized after bootstrapping).

The immediate thing this allows is spinning up threads in arena_new, which will
enable spinning up background threads there.
2017-04-07 14:10:27 -07:00
David Goldblatt
0a0fcd3e6a Add hooking functionality
This allows us to hook chosen functions and do interesting things there (in
particular: reentrancy checking).
2017-04-07 14:10:27 -07:00
Qi Wang
36bd90b962 Optimizing TSD and thread cache layout.
1) Re-organize TSD so that frequently accessed fields are closer to the
beginning and more compact.  Assuming 64-bit, the first 2.5 cachelines now
contains everything needed on tcache fast path, expect the tcache struct itself.

2) Re-organize tcache and tbins.  Take lg_fill_div out of tbin, and reduce tbin
to 24 bytes (down from 32). Split tbins into tbins_small and tbins_large, and
place tbins_small close to the beginning.
2017-04-07 14:06:17 -07:00
Qi Wang
0fba57e579 Get rid of tcache_enabled_t as we have runtime init support. 2017-04-07 10:42:29 -07:00
Qi Wang
fde3e20cc0 Integrate auto tcache into TSD.
The embedded tcache is initialized upon tsd initialization.  The avail arrays
for the tbins will be allocated / deallocated accordingly during init / cleanup.

With this change, the pointer to the auto tcache will always be available, as
long as we have access to the TSD.  tcache_available() (called in tcache_get())
is provided to check if we should use tcache.
2017-04-07 09:55:14 -07:00
David Goldblatt
eeabdd2466 Remove the pre-C11-atomics API, which is now unused 2017-04-05 16:25:37 -07:00
David Goldblatt
5dcc13b342 Make the mutex n_waiting_thds field a C11-style atomic 2017-04-05 16:25:37 -07:00
David Goldblatt
30d74db08e Convert accumbytes in prof_accum_t to C11 atomics, when possible 2017-04-05 16:25:37 -07:00
David Goldblatt
92aafb0efe Make base_t's extent_hooks field C11-atomic 2017-04-05 16:25:37 -07:00
David Goldblatt
56b72c7b17 Transition arena struct fields to C11 atomics 2017-04-05 16:25:37 -07:00
David Goldblatt
bc32ec3503 Move arena-tracking atomics in jemalloc.c to C11-style 2017-04-05 16:25:37 -07:00
David Goldblatt
864adb7f42 Transition e_prof_tctx in struct extent to C11 atomics 2017-04-04 16:46:04 -07:00
David Goldblatt
7da04a6b09 Convert prng module to use C11-style atomics 2017-04-04 16:45:52 -07:00
Qi Wang
492e9f301e Make the tsd member init functions to take tsd_t * type. 2017-04-04 14:06:07 -07:00
Qi Wang
d3cda3423c Do proper cleanup for tsd_state_reincarnated.
Also enable arena_bind under non-nominal state, as the cleanup will be handled
correctly now.
2017-04-04 00:34:49 -07:00
Qi Wang
51d3682950 Remove the leafkey NULL check in leaf_elm_lookup. 2017-04-04 00:27:35 -07:00
Qi Wang
9ed84b0d45 Add init function support to tsd members.
This will facilitate embedding tcache into tsd, which will require proper
initialization cannot be done via the static initializer.  Make tsd->rtree_ctx
to be initialized via rtree_ctx_data_init().
2017-04-04 00:19:21 -07:00
Jason Evans
07f4f93434 Move arena_slab_data_t's nfree into extent_t's e_bits.
Compact extent_t to 128 bytes on 64-bit systems by moving
arena_slab_data_t's nfree into extent_t's e_bits.

Cacheline-align extent_t structures so that they always cross the
minimum number of cacheline boundaries.

Re-order extent_t fields such that all fields except the slab bitmap
(and overlaid heap profiling context pointer) are in the first
cacheline.

This resolves #461.
2017-03-27 22:43:39 -07:00
Qi Wang
af3d737a9a Simplify rtree cache replacement policy.
To avoid memmove on free() fast path, simplify the cache replacement policy to
only bubble up the cache hit element by 1.
2017-03-27 13:42:31 -07:00
Jason Evans
c6d1819e48 Simplify rtree_clear() to avoid locking. 2017-03-27 13:22:52 -07:00
Jason Evans
4020523f67 Fix a race in rtree_szind_slab_update() for RTREE_LEAF_COMPACT. 2017-03-27 13:22:36 -07:00
Jason Evans
7c00f04ff4 Remove BITMAP_USE_TREE.
Remove tree-structured bitmap support, in order to reduce complexity and
ease maintenance.  No bitmaps larger than 512 bits have been necessary
since before 4.0.0, and there is no current plan that would increase
maximum bitmap size.  Although tree-structured bitmaps were used on
32-bit platforms prior to this change, the overall benefits were
questionable (higher metadata overhead, higher bitmap modification cost,
marginally lower search cost).
2017-03-27 12:18:40 -07:00
Jason Evans
6258176c87 Fix bitmap_ffu() to work with 3+ levels. 2017-03-27 12:18:40 -07:00
Jason Evans
735ad8210c Pack various extent_t fields into a bitfield.
This reduces sizeof(extent_t) from 160 to 136 on x64.
2017-03-25 23:30:13 -07:00
Jason Evans
0591c204b4 Store arena index rather than (arena_t *) in extent_t. 2017-03-25 23:30:13 -07:00
Jason Evans
5e12223925 Fix BITMAP_USE_TREE version of bitmap_ffu().
This fixes an extent searching regression on 32-bit systems, caused by
the initial bitmap_ffu() implementation in
c8021d01f6 (Implement bitmap_ffu(), which
finds the first unset bit.), as first used in
5d33233a5e (Use a bitmap in extents_t to
speed up search.).
2017-03-25 23:29:32 -07:00
Jason Evans
5d33233a5e Use a bitmap in extents_t to speed up search.
Rather than iteratively checking all sufficiently large heaps during
search, maintain and use a bitmap in order to skip empty heaps.
2017-03-24 17:52:46 -07:00
Jason Evans
57e353163f Implement BITMAP_GROUPS(). 2017-03-24 17:52:46 -07:00
Jason Evans
c8021d01f6 Implement bitmap_ffu(), which finds the first unset bit. 2017-03-24 17:52:46 -07:00
Qi Wang
362e356675 Profile per arena base mutex, instead of just a0. 2017-03-23 00:03:28 -07:00
Qi Wang
d3fde1c124 Refactor mutex profiling code with x-macros. 2017-03-23 00:03:28 -07:00
Qi Wang
f6698ec1e6 Switch to nstime_t for the time related fields in mutex profiling. 2017-03-23 00:03:28 -07:00
Qi Wang
74f78cafda Added custom mutex spin.
A fixed max spin count is used -- with benchmark results showing it
solves almost all problems. As the benchmark used was rather intense,
the upper bound could be a little bit high. However it should offer a
good tradeoff between spinning and blocking.
2017-03-23 00:03:28 -07:00
Qi Wang
20b8c70e9f Added extents_dirty / _muzzy mutexes, as well as decay_dirty / _muzzy. 2017-03-23 00:03:28 -07:00
Qi Wang
64c5f5c174 Added "stats.mutexes.reset" mallctl to reset all mutex stats.
Also switched from the term "lock" to "mutex".
2017-03-23 00:03:28 -07:00
Qi Wang
ca9074deff Added lock profiling and output for global locks (ctl, prof and base). 2017-03-23 00:03:28 -07:00
Qi Wang
0fb5c0e853 Add arena lock stats output. 2017-03-23 00:03:28 -07:00
Qi Wang
a4f176af57 Output bin lock profiling results to malloc_stats.
Two counters are included for the small bins: lock contention rate, and
max lock waiting time.
2017-03-23 00:03:28 -07:00
Qi Wang
6309df628f First stage of mutex profiling.
Switched to trylock and update counters based on state.
2017-03-23 00:03:28 -07:00
Jason Evans
32e7cf51cd Further specialize arena_[s]dalloc() tcache fast path.
Use tsd_rtree_ctx() rather than tsdn_rtree_ctx() when tcache is
non-NULL, in order to avoid an extra branch (and potentially extra stack
space) in the fast path.
2017-03-22 18:33:32 -07:00
Jason Evans
5e67fbc367 Push down iealloc() calls.
Call iealloc() as deep into call chains as possible without causing
redundant calls.
2017-03-22 18:33:32 -07:00
Jason Evans
51a2ec92a1 Remove extent dereferences from the deallocation fast paths. 2017-03-22 18:33:32 -07:00
Jason Evans
4f341412e5 Remove extent arg from isalloc() and arena_salloc(). 2017-03-22 18:33:32 -07:00
Jason Evans
0ee0e0c155 Implement compact rtree leaf element representation.
If a single virtual adddress pointer has enough unused bits to pack
{szind_t, extent_t *, bool, bool}, use a single pointer-sized field in
each rtree leaf element, rather than using three separate fields.  This
has little impact on access speed (fewer loads/stores, but more bit
twiddling), except that denser representation increases TLB
effectiveness.
2017-03-22 18:33:32 -07:00
Jason Evans
ce41ab0c57 Embed root node into rtree_t.
This avoids one atomic operation per tree access.
2017-03-22 18:33:32 -07:00
Jason Evans
99d68445ef Incorporate szind/slab into rtree leaves.
Expand and restructure the rtree API such that all common operations can
be achieved with minimal work, regardless of whether the rtree leaf
fields are independent versus packed into a single atomic pointer.
2017-03-22 18:33:32 -07:00
Jason Evans
944c8a3383 Split rtree_elm_t into rtree_{node,leaf}_elm_t.
This allows leaf elements to differ in size from internal node elements.

In principle it would be more correct to use a different type for each
level of the tree, but due to implementation details related to atomic
operations, we use casts anyway, thus counteracting the value of
additional type correctness.  Furthermore, such a scheme would require
function code generation (via cpp macros), as well as either unwieldy
type names for leaves or type aliases, e.g.

  typedef struct rtree_elm_d2_s rtree_leaf_elm_t;

This alternate strategy would be more correct, and with less code
duplication, but probably not worth the complexity.
2017-03-22 18:33:32 -07:00
Jason Evans
f50d6009fe Remove binind field from arena_slab_data_t.
binind is now redundant; the containing extent_t's szind field always
provides the same value.
2017-03-22 18:33:32 -07:00
Jason Evans
e8921cf2eb Convert extent_t's usize to szind.
Rather than storing usize only for large (and prof-promoted)
allocations, store the size class index for allocations that reside
within the extent, such that the size class index is valid for all
extents that contain extant allocations, and invalid otherwise (mainly
to make debugging simpler).
2017-03-22 18:33:32 -07:00
Jason Evans
64e458f5cd Implement two-phase decay-based purging.
Split decay-based purging into two phases, the first of which uses lazy
purging to convert dirty pages to "muzzy", and the second of which uses
forced purging, decommit, or unmapping to convert pages to clean or
destroy them altogether.  Not all operating systems support lazy
purging, yet the application may provide extent hooks that implement
lazy purging, so care must be taken to dynamically omit the first phase
when necessary.

The mallctl interfaces change as follows:
- opt.decay_time --> opt.{dirty,muzzy}_decay_time
- arena.<i>.decay_time --> arena.<i>.{dirty,muzzy}_decay_time
- arenas.decay_time --> arenas.{dirty,muzzy}_decay_time
- stats.arenas.<i>.pdirty --> stats.arenas.<i>.p{dirty,muzzy}
- stats.arenas.<i>.{npurge,nmadvise,purged} -->
  stats.arenas.<i>.{dirty,muzzy}_{npurge,nmadvise,purged}

This resolves #521.
2017-03-15 13:13:47 -07:00
Jason Evans
38a5bfc816 Move arena_t's purging field into arena_decay_t. 2017-03-15 13:13:47 -07:00
Jason Evans
765edd67b4 Refactor decay-related function parametrization.
Refactor most of the decay-related functions to take as parameters the
decay_t and associated extents_t structures to operate on.  This
prepares for supporting both lazy and forced purging on different decay
schedules.
2017-03-15 13:13:47 -07:00
David Goldblatt
ee202efc79 Convert remaining arena_stats_t fields to atomics
These were all size_ts, so we have atomics support for them on all platforms, so
the conversion is straightforward.

Left non-atomic is curlextents, which AFAICT is not used atomically anywhere.
2017-03-13 18:22:33 -07:00
David Goldblatt
4fc2acf5ae Switch atomic uint64_ts in arena_stats_t to C11 atomics
I expect this to be the trickiest conversion we will see, since we want atomics
on 64-bit platforms, but are also always able to piggyback on some sort of
external synchronization on non-64 bit platforms.
2017-03-13 18:22:33 -07:00
Jason Evans
7cbcd2e2b7 Fix pages_purge_forced() to discard pages on non-Linux systems.
madvise(..., MADV_DONTNEED) only causes demand-zeroing on Linux, so fall
back to overlaying a new mapping.
2017-03-13 18:19:57 -07:00
David Goldblatt
21a68e2d22 Convert rtree code to use C11 atomics
In the process, I changed the implementation of rtree_elm_acquire so that it
won't even try to CAS if its initial read (getting the extent + lock bit)
indicates that the CAS is doomed to fail.  This can significantly improve
performance under contention.
2017-03-13 12:05:27 -07:00
Jason Evans
3a2b183d5f Convert arena_t's purging field to non-atomic bool.
The decay mutex already protects all accesses.
2017-03-10 10:14:30 -08:00
Jason Evans
75fddc786c Fix ATOMIC_{ACQUIRE,RELEASE,ACQ_REL} definitions. 2017-03-09 00:57:37 -08:00
Qi Wang
ec532e2c5c Implement per-CPU arena.
The new feature, opt.percpu_arena, determines thread-arena association
dynamically based CPU id. Three modes are supported: "percpu", "phycpu"
and disabled.

"percpu" uses the current core id (with help from sched_getcpu())
directly as the arena index, while "phycpu" will assign threads on the
same physical CPU to the same arena. In other words, "percpu" means # of
arenas == # of CPUs, while "phycpu" has # of arenas == 1/2 * (# of
CPUs). Note that no runtime check on whether hyper threading is enabled
is added yet.

When enabled, threads will be migrated between arenas when a CPU change
is detected. In the current design, to reduce overhead from reading CPU
id, each arena tracks the thread accessed most recently. When a new
thread comes in, we will read CPU id and update arena if necessary.
2017-03-08 23:19:01 -08:00
Qi Wang
8721e19c04 Fix arena_prefork lock rank order for witness.
When witness is enabled, lock rank order needs to be preserved during
prefork, not only for each arena, but also across arenas. This change
breaks arena_prefork into further stages to ensure valid rank order
across arenas. Also changed test/unit/fork to use a manual arena to
catch this case.
2017-03-08 23:07:27 -08:00
David Goldblatt
8adab26972 Convert extents_t's npages field to use C11-style atomics
In the process, we can do some strength reduction, changing the fetch-adds and
fetch-subs to be simple loads followed by stores, since the modifications all
occur while holding the mutex.
2017-03-08 21:27:09 -08:00
David Goldblatt
dafadce622 Reintroduce JEMALLOC_ATOMIC_U64
The C11 atomics backport removed this #define, which degraded atomic 64-bit
reads to require a lock even on platforms that support them.  This commit fixes
that.
2017-03-08 21:26:37 -08:00
Qi Wang
01f47f11a6 Store associated arena in tcache.
This fixes tcache_flush for manual tcaches, which wasn't able to find
the correct arena it associated with. Also changed the decay test to
cover this case (by using manually created arenas).
2017-03-07 12:58:11 -08:00
Jason Evans
cc75c35db5 Add any() and remove_any() to ph.
These functions select the easiest-to-remove element in the heap, which
is either the most recently inserted aux list element or the root.  If
no calls are made to first() or remove_first(), the behavior (and time
complexity) is the same as for a LIFO queue.
2017-03-07 10:25:33 -08:00
Jason Evans
e201e24904 Perform delayed coalescing prior to purging.
Rather than purging uncoalesced extents, perform just enough incremental
coalescing to purge only fully coalesced extents.  In the absence of
cached extent reuse, the immediate versus delayed incremental purging
algorithms result in the same purge order.

This resolves #655.
2017-03-07 10:25:12 -08:00
David Goldblatt
4f1e94658a Change arena to use the atomic functions for ssize_t instead of the union strategy 2017-03-06 18:49:19 -08:00
David Goldblatt
438efede78 Add atomic types for ssize_t 2017-03-06 18:49:19 -08:00
David Goldblatt
424e3428b1 Make type abbreviations consistent: ssize_t is zd everywhere 2017-03-06 18:49:19 -08:00
David Goldblatt
84326c566a Insert not_reached after an exhaustive switch
In the C11 atomics backport, we couldn't use not_reached() in
atomic_enum_to_builtin (in atomic_gcc_atomic.h), since atomic.h was hermetic and
assert.h wasn't; there was a dependency issue.  assert.h is hermetic now, so we
can include it.
2017-03-06 15:08:43 -08:00
David Goldblatt
e9852b5776 Disentangle assert and util
This is the first header refactoring diff, #533.  It splits the assert and util
components into separate, hermetic, header files.  In the process, it splits out
two of the large sub-components of util (the stdio.h replacement, and bit
manipulation routines) into their own components (malloc_io.h and bit_util.h).
This is mostly to break up cyclic dependencies, but it also breaks off a good
chunk of the catch-all-ness of util, which is nice.
2017-03-06 15:08:43 -08:00
Jason Evans
04d8fcb745 Optimize malloc_large_stats_t maintenance.
Convert the nrequests field to be partially derived, and the curlextents
to be fully derived, in order to reduce the number of stats updates
needed during common operations.

This change affects ndalloc stats during arena reset, because it is no
longer possible to cancel out ndalloc effects (curlextents would become
negative).
2017-03-04 08:18:31 -08:00
David Goldblatt
d4ac7582f3 Introduce a backport of C11 atomics
This introduces a backport of C11 atomics.  It has four implementations; ranked
in order of preference, they are:
- GCC/Clang __atomic builtins
- GCC/Clang __sync builtins
- MSVC _Interlocked builtins
- C11 atomics, from <stdatomic.h>

The primary advantages are:
- Close adherence to the standard API gives us a defined memory model.
- Type safety: atomic objects are now separate types from non-atomic ones, so
  that it's impossible to mix up atomic and non-atomic updates (which is
  undefined behavior that compilers are starting to take advantage of).
- Efficiency: we can specify ordering for operations, avoiding fences and
  atomic operations on strongly ordered architectures (example:
  `atomic_write_u32(ptr, val);` involves a CAS loop, whereas
  `atomic_store(ptr, val, ATOMIC_RELEASE);` is a plain store.

This diff leaves in the current atomics API (implementing them in terms of the
backport).  This lets us transition uses over piecemeal.

Testing:
This is by nature hard to test. I've manually tested the first three options on
Linux on gcc by futzing with the #defines manually, on freebsd with gcc and
clang, on MSVC, and on OS X with clang.  All of these were x86 machines though,
and we don't have any test infrastructure set up for non-x86 platforms.
2017-03-03 13:40:59 -08:00
David Goldblatt
957b8c5f21 Stop #define-ining away 'inline'
In the long term, we'll transition to C99-style inline semantics.  In the
short-term, this will allow both styles to coexist without breaking one another.
2017-03-03 13:40:59 -08:00
Jason Evans
fd058f572b Immediately purge cached extents if decay_time is 0.
This fixes a regression caused by
54269dc0ed (Remove obsolete
arena_maybe_purge() call.), as well as providing a general fix.

This resolves #665.
2017-03-02 19:43:06 -08:00
Jason Evans
d61a5f76b2 Convert arena_decay_t's time to be atomically synchronized. 2017-03-02 19:43:06 -08:00
Jason Evans
472fef2e12 Fix {allocated,nmalloc,ndalloc,nrequests}_large stats regression.
This fixes a regression introduced by
d433471f58 (Derive
{allocated,nmalloc,ndalloc,nrequests}_large stats.).
2017-02-27 11:18:07 -08:00
Jason Evans
079b8bee37 Tidy up extent quantization.
Remove obsolete unit test scaffolding for extent quantization.  Remove
redundant assertions.  Add an assertion to
extents_first_best_fit_locked() that should help prevent aligned
allocation regressions.
2017-02-27 11:17:47 -08:00
Jason Evans
d727596bcb Update a comment. 2017-02-26 11:05:27 -08:00
Qi Wang
c2323e13a5 Get rid of witness in malloc_mutex_t when !(configured w/ debug).
We don't touch witness at all when config_debug == false.  Let's only pay the
memory cost in malloc_mutex_s when needed. Note that when !config_debug, we keep
the field in a union so that we don't have to do #ifdefs in multiple places.
2017-02-24 09:41:29 -08:00
Jason Evans
8ac7937eb5 Remove remainder of mb (memory barrier).
This complements 94c5d22a4d (Remove mb.h,
which is unused).
2017-02-22 00:24:14 -08:00
Jason Evans
003ca8717f Move arena_basic_stats_merge() prototype (hygienic cleanup). 2017-02-21 12:46:20 -08:00
Jason Evans
2dfc5b5aac Disable coalescing of cached extents.
Extent splitting and coalescing is a major component of large allocation
overhead, and disabling coalescing of cached extents provides a simple
and effective hysteresis mechanism.  Once two-phase purging is
implemented, it will probably make sense to leave coalescing disabled
for the first phase, but coalesce during the second phase.
2017-02-16 20:11:50 -08:00
Jason Evans
b0654b95ed Fix arena->stats.mapped accounting.
Mapped memory increases when extent_alloc_wrapper() succeeds, and
decreases when extent_dalloc_wrapper() is called (during purging).
2017-02-16 15:52:11 -08:00
Jason Evans
f8fee6908d Synchronize arena->decay with arena->decay.mtx.
This removes the last use of arena->lock.
2017-02-16 09:39:46 -08:00
Jason Evans
d433471f58 Derive {allocated,nmalloc,ndalloc,nrequests}_large stats.
This mildly reduces stats update overhead during normal operation.
2017-02-16 09:39:46 -08:00
Jason Evans
ab25d3c987 Synchronize arena->tcache_ql with arena->tcache_ql_mtx.
This replaces arena->lock synchronization.
2017-02-16 09:39:46 -08:00
Jason Evans
6b5cba4191 Convert arena->stats synchronization to atomics. 2017-02-16 09:39:46 -08:00
Jason Evans
fa2d64c94b Convert arena->prof_accumbytes synchronization to atomics. 2017-02-16 09:39:46 -08:00
Jason Evans
b779522b9b Convert arena->dss_prec synchronization to atomics. 2017-02-16 09:39:46 -08:00
Jason Evans
0721b895ff Do not generate unused tsd_*_[gs]et() functions.
This avoids a gcc diagnostic note:
    note: The ABI for passing parameters with 64-byte alignment has
    changed in GCC 4.6
This note related to the cacheline alignment of rtree_ctx_t, which was
introduced by 4a346f5593 (Replace rtree
path cache with LRU cache.).
2017-02-13 10:47:16 -08:00
Jason Evans
6b8ef771a9 Fix rtree_subkey() regression.
Fix rtree_subkey() to use uintptr_t rather than unsigned for key
bitmasking.  This regression was introduced by
4a346f5593 (Replace rtree path cache with
LRU cache.).
2017-02-10 09:05:02 -08:00
Jason Evans
7f55dbef9b Enable mutex witnesses even when !isthreaded.
This fixes interactions with witness_assert_depth[_to_rank](), which was
added in d0e93ada51 (Add
witness_assert_depth[_to_rank]().).
2017-02-09 17:05:47 -08:00
Jason Evans
db7da56359 Spin adaptively in rtree_elm_acquire(). 2017-02-08 18:50:03 -08:00
Jason Evans
de8a68e853 Enhance spin_adaptive() to yield after several iterations.
This avoids worst case behavior if e.g. another thread is preempted
while owning the resource the spinning thread is waiting for.
2017-02-08 18:50:03 -08:00
Jason Evans
5f11830754 Replace spin_init() with SPIN_INITIALIZER. 2017-02-08 18:50:03 -08:00
Jason Evans
650c070e10 Remove rtree support for 0 (NULL) keys.
NULL can never actually be inserted in practice, and removing support
allows a branch to be removed from the fast path.
2017-02-08 18:50:03 -08:00
Jason Evans
f5cf9b19c8 Determine rtree levels at compile time.
Rather than dynamically building a table to aid per level computations,
define a constant table at compile time.  Omit both high and low
insignificant bits.  Use one to three tree levels, depending on the
number of significant bits.
2017-02-08 18:50:03 -08:00
Jason Evans
ff4db5014e Remove rtree leading 0 bit optimization.
A subsequent change instead ignores insignificant high bits.
2017-02-08 18:50:03 -08:00
Jason Evans
cdc240d501 Make non-essential inline rtree functions static functions. 2017-02-08 18:50:03 -08:00
Jason Evans
c511a44e99 Split rtree_elm_lookup_hard() out of rtree_elm_lookup().
Anything but a hit in the first element of the lookup cache is
expensive enough to negate the benefits of inlining.
2017-02-08 18:50:03 -08:00
Jason Evans
4a346f5593 Replace rtree path cache with LRU cache.
Rework rtree_ctx_t to encapsulate an rtree leaf LRU lookup cache rather
than a single-path element lookup cache.  The replacement is logically
much simpler, as well as slightly faster in the fast path case and less
prone to degraded performance during non-trivial sequences of lookups.
2017-02-08 18:50:03 -08:00
Jason Evans
0ecf692726 Optimize a branch out of rtree_read() if !dependent. 2017-02-08 18:50:03 -08:00
Jason Evans
d27f29b468 Disentangle arena and extent locking.
Refactor arena and extent locking protocols such that arena and
extent locks are never held when calling into the extent_*_wrapper()
API.  This requires extra care during purging since the arena lock no
longer protects the inner purging logic.  It also requires extra care to
protect extents from being merged with adjacent extents.

Convert extent_t's 'active' flag to an enumerated 'state', so that
retained extents are explicitly marked as such, rather than depending on
ring linkage state.

Refactor the extent collections (and their synchronization) for cached
and retained extents into extents_t.  Incorporate LRU functionality to
support purging.  Incorporate page count accounting, which replaces
arena->ndirty and arena->stats.retained.

Assert that no core locks are held when entering any internal
[de]allocation functions.  This is in addition to existing assertions
that no locks are held when entering external [de]allocation functions.

Audit and document synchronization protocols for all arena_t fields.

This fixes a potential deadlock due to recursive allocation during
gdump, in a similar fashion to b49c649bc1
(Fix lock order reversal during gdump.), but with a necessarily much
broader code impact.
2017-02-01 16:43:46 -08:00
Jason Evans
1b6e43507e Fix/refactor tcaches synchronization.
Synchronize tcaches with tcaches_mtx rather than ctl_mtx.  Add missing
synchronization for tcache flushing.  This bug was introduced by
1cb181ed63 (Implement explicit tcache
support.), which was first released in 4.0.0.
2017-02-01 16:43:46 -08:00
Jason Evans
d0e93ada51 Add witness_assert_depth[_to_rank]().
This makes it possible to make lock state assertions about precisely
which locks are held.
2017-02-01 16:43:46 -08:00
Jason Evans
c0cc5db871 Replace tabs following #define with spaces.
This resolves #564.
2017-01-20 21:45:53 -08:00
Jason Evans
f408643a4c Remove extraneous parens around return arguments.
This resolves #540.
2017-01-20 21:43:07 -08:00
Jason Evans
c4c2592c83 Update brace style.
Add braces around single-line blocks, and remove line breaks before
function-opening braces.

This resolves #537.
2017-01-20 21:43:07 -08:00
Jason Evans
9eb1b1c881 Fix --disable-stats support.
Fix numerous regressions that were exposed by --disable-stats, both in
the core library and in the tests.
2017-01-19 18:31:07 -08:00
Qi Wang
58424e679d Added stats about number of bytes cached in tcache currently. 2017-01-18 10:55:21 -08:00
Mike Hommey
0f7376eb62 Don't rely on OSX SDK malloc/malloc.h for malloc_zone struct definitions
The SDK jemalloc is built against might be not be the latest for various
reasons, but the resulting binary ought to work on newer versions of
OSX.

In order to ensure this, we need the fullest definitions possible, so
copy what we need from the latest version of malloc/malloc.h available
on opensource.apple.com.
2017-01-17 20:13:28 -08:00
Jason Evans
1ff09534b5 Fix prof_realloc() regression.
Mostly revert the prof_realloc() changes in
498856f44a (Move slabs out of chunks.) so
that prof_free_sampled_object() is called when appropriate.  Leave the
prof_tctx_[re]set() optimization in place, but add an assertion to
verify that all eight cases are correctly handled.  Add a comment to
make clear the code ordering, so that the regression originally fixed by
ea8d97b897 (Fix
prof_{malloc,free}_sample_object() call order in prof_realloc().) is not
repeated.

This resolves #499.
2017-01-17 15:16:37 -08:00
Jason Evans
ffbb7dac3d Remove leading blank lines from function bodies.
This resolves #535.
2017-01-13 14:49:24 -08:00
David Goldblatt
77cccac8cd Break up headers into constituent parts
This is part of a broader change to make header files better represent the
dependencies between one another (see
https://github.com/jemalloc/jemalloc/issues/533). It breaks up component headers
into smaller parts that can be made to have a simpler dependency graph.

For the autogenerated headers (smoothstep.h and size_classes.h), no splitting
was necessary, so I didn't add support to emit multiple headers.
2017-01-12 15:43:51 -08:00
David Goldblatt
94c5d22a4d Remove mb.h, which is unused 2017-01-11 13:24:30 -08:00
John Paul Adrian Glaubitz
77de5f27d8 Use better pre-processor defines for sparc64
Currently, jemalloc detects sparc64 targets by checking whether
__sparc64__ is defined. However, this definition is used on BSD
targets only. Linux targets define both __sparc__ and __arch64__
for sparc64. Since this also works on BSD, rather use __sparc__
and __arch64__ instead of __sparc64__ to detect sparc64 targets.
2017-01-10 17:39:54 -08:00
Jason Evans
edf1bafb2b Implement arena.<i>.destroy .
Add MALLCTL_ARENAS_DESTROYED for accessing destroyed arena stats as an
analogue to MALLCTL_ARENAS_ALL.

This resolves #382.
2017-01-06 18:58:46 -08:00
Jason Evans
6edbedd916 Range-check mib[1] --> arena_ind casts. 2017-01-06 18:58:46 -08:00
Jason Evans
c0a05e6aba Move static ctl_epoch variable into ctl_stats_t (as epoch). 2017-01-06 18:58:45 -08:00
Jason Evans
d778dd2afc Refactor ctl_stats_t.
Refactor ctl_stats_t to be a demand-zeroed non-growing data structure.
To keep the size from being onerous (~60 MiB) on 32-bit systems, convert
the arenas field to contain pointers rather than directly embedded
ctl_arena_stats_t elements.
2017-01-06 18:58:45 -08:00
Jason Evans
0f04bb1d6f Rename the arenas.extend mallctl to arenas.create. 2017-01-06 18:58:45 -08:00
Jason Evans
3dc4e83ccb Add MALLCTL_ARENAS_ALL.
Add the MALLCTL_ARENAS_ALL cpp macro as a fixed index for use
in accessing the arena.<i>.{purge,decay,dss} and stats.arenas.<i>.*
mallctls, and deprecate access via the arenas.narenas index (to be
removed in 6.0.0).
2017-01-06 18:58:45 -08:00
Jason Evans
a0dd3a4483 Implement per arena base allocators.
Add/rename related mallctls:
- Add stats.arenas.<i>.base .
- Rename stats.arenas.<i>.metadata to stats.arenas.<i>.internal .
- Add stats.arenas.<i>.resident .

Modify the arenas.extend mallctl to take an optional (extent_hooks_t *)
argument so that it is possible for all base allocations to be serviced
by the specified extent hooks.

This resolves #463.
2016-12-26 18:08:28 -08:00
Jason Evans
a6e86810d8 Refactor purging and splitting/merging.
Split purging into lazy and forced variants.  Use the forced variant for
zeroing dss.

Add support for NULL function pointers as an opt-out mechanism for the
dalloc, commit, decommit, purge_lazy, purge_forced, split, and merge
fields of extent_hooks_t.

Add short-circuiting checks in large_ralloc_no_move_{shrink,expand}() so
that no attempt is made if splitting/merging is not supported.

This resolves #268.
2016-12-26 18:08:16 -08:00
Jason Evans
884fa22b8c Rename arena_decay_t's ndirty to nunpurged. 2016-12-26 17:59:43 -08:00
Jason Evans
411697adcd Use exponential series to size extents.
If virtual memory is retained, allocate extents such that their sizes
form an exponentially growing series.  This limits the number of
disjoint virtual memory ranges so that extent merging can be effective
even if multiple arenas' extent allocation requests are highly
interleaved.

This resolves #462.
2016-12-26 17:59:42 -08:00
Jason Evans
c1baa0a9b7 Add huge page configuration and pages_[no}huge().
Add the --with-lg-hugepage configure option, but automatically configure
LG_HUGEPAGE even if it isn't specified.

Add the pages_[no]huge() functions, which toggle huge page state via
madvise(..., MADV_[NO]HUGEPAGE) calls.
2016-12-26 17:59:34 -08:00
Jason Evans
bacb6afc6c Simplify arena_slab_regind().
Rewrite arena_slab_regind() to provide sufficient constant data for
the compiler to perform division strength reduction.  This replaces
more general manual strength reduction that was implemented before
arena_bin_info was compile-time-constant.  It would be possible to
slightly improve on the compiler-generated division code by taking
advantage of range limits that the compiler doesn't know about.
2016-12-23 10:34:34 -08:00
Jason Evans
69c26cdb01 Add some missing explicit casts. 2016-12-13 13:38:11 -08:00
Dave Watson
2319152d9f jemalloc cpp new/delete bindings
Adds cpp bindings for jemalloc, along with necessary autoconf settings.
This is mostly to add sized deallocation support, which can't be added
from C directly.  Sized deallocation is ~10% microbench improvement.

* Import ax_cxx_compile_stdcxx.m4 from the autoconf repo, seems like the
  easiest way to get c++14 detection.
* Adds various other changes, like CXXFLAGS, to configure.ac.
* Adds new rules to Makefile.in for src/jemalloc-cpp.cpp, and a basic
  unittest.
* Both new and delete are overridden, to ensure jemalloc is used for
  both.
* TODO future enhancement of avoiding extra PLT thunks for new and
  delete - sdallocx and malloc are publicly exported jemalloc symbols,
  using an alias would link them directly.  Unfortunately, was having
  trouble getting it to play nice with jemalloc's namespace support.

Testing:
Tested gcc 4.8, gcc 5, gcc 5.2, clang 4.0.  Only gcc >= 5 has sized
deallocation support, verified that the rest build correctly.

Tested mac osx and Centos.

Tested --with-jemalloc-prefix and --without-export.

This resolves #202.
2016-12-12 18:36:06 -08:00
Jason Evans
d4c5aceb7c Add a_type parameter to qr_{meld,split}(). 2016-12-12 18:16:51 -08:00
Jason Evans
acb7b1f53e Add --disable-syscall.
This resolves #517.
2016-12-03 16:50:58 -08:00
Jason Evans
32127949a3 Enable overriding JEMALLOC_{ALLOC,FREE}_JUNK.
This resolves #509.
2016-11-22 10:58:58 -08:00
Jason Evans
c3b85f2585 Style fixes. 2016-11-22 10:58:23 -08:00
Jason Evans
5234be2133 Add pthread_atfork(3) feature test.
Some versions of Android provide a pthreads library without providing
pthread_atfork(), so in practice a separate feature test is necessary
for the latter.
2016-11-17 15:14:57 -08:00
Jason Evans
fda60be799 Update a comment. 2016-11-17 11:50:52 -08:00
Jason Evans
a64123ce13 Refactor madvise(2) configuration.
Add feature tests for the MADV_FREE and MADV_DONTNEED flags to
madvise(2), so that MADV_FREE is detected and used for Linux kernel
versions 4.5 and newer.  Refactor pages_purge() so that on systems which
support both flags, MADV_FREE is preferred over MADV_DONTNEED.

This resolves #387.
2016-11-17 10:31:57 -08:00
Jason Evans
a38acf716e Add extent serial numbers.
Add extent serial numbers and use them where appropriate as a sort key
that is higher priority than address, so that the allocation policy
prefers older extents.

This resolves #147.
2016-11-15 13:08:33 -08:00
Jason Evans
cda59f9970 Rename atomic_*_{uint32,uint64,u}() to atomic_*_{u32,u64,zu}().
This change conforms to naming conventions throughout the codebase.
2016-11-07 11:27:48 -08:00
Jason Evans
2e46b13ad5 Revert "Define 64-bits atomics unconditionally"
This reverts commit c2942e2c0e.

This resolves #495.
2016-11-07 10:53:35 -08:00
Jason Evans
04b463546e Refactor prng to not use 64-bit atomics on 32-bit platforms.
This resolves #495.
2016-11-07 10:52:44 -08:00
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
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
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
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
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
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
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