Commit Graph

961 Commits

Author SHA1 Message Date
Qi Wang
a3fa597921 Refactor arena_dalloc() / _sdalloc(). 2019-07-24 18:30:54 -07:00
Qi Wang
bc0998a905 Invoke arena_dalloc_promoted() properly w/o tcache.
When tcache was disabled, the dalloc promoted case was missing.
2019-07-24 18:30:54 -07:00
Qi Wang
4e36ce34c1 Track the leaked VM space via the abandoned_vm counter.
The counter is 0 unless metadata allocation failed (indicates OOM), and is
mainly for sanity checking.
2019-07-24 11:24:22 -07:00
Qi Wang
9a86c65abc Implement retain on Windows.
The VirtualAlloc and VirtualFree APIs are different because MEM_DECOMMIT cannot
be used across multiple VirtualAlloc regions.  To properly support decommit,
only allow merge / split within the same region -- this is done by tracking the
"is_head" state of extents and not merging cross-region.

Add a new state is_head (only relevant for retain && !maps_coalesce), which is
true for the first extent in each VirtualAlloc region.  Determine if two extents
can be merged based on the head state, and use serial numbers for sanity checks.
2019-07-23 22:18:55 -07:00
Yinan Zhang
a2a693e722 Remove prof_accumbytes in arena
`prof_accumbytes` was supposed to be replaced by `prof_accum` in
https://github.com/jemalloc/jemalloc/pull/623.
2019-07-16 15:18:52 -07:00
Yinan Zhang
d26636d566 Fix logic in printing
`cbopaque` can now be overriden without overriding `write_cb` in
the first place.  (Otherwise there would be no need to have the
`cbopaque` parameter in `malloc_message`.)
2019-07-16 14:54:23 -07:00
Yinan Zhang
7720b6e385 Fix redzone setting and checking 2019-07-11 20:51:29 -07:00
Yinan Zhang
c92ac30601 Add confirm_conf option
If the confirm_conf option is set, when the program starts, each of
the four malloc_conf strings will be printed, and each option will
be printed when being set.
2019-05-22 09:38:39 -07:00
Qi Wang
07c44847c2 Track nfills and nflushes for arenas.i.small / large.
Small is added purely for convenience.  Large flushes wasn't tracked before and
can be useful in analysis.  Large fill simply reports nmalloc, since there is no
batch fill for large currently.
2019-05-15 10:05:09 -07:00
Doron Roberts-Kedes
7fc4f2a32c Add nonfull_slabs to bin_stats_t.
When config_stats is enabled track the size of bin->slabs_nonfull in
the new nonfull_slabs counter in bin_stats_t. This metric should be
useful for establishing an upper ceiling on the savings possible by
meshing.
2019-04-29 13:35:02 -07:00
Yinan Zhang
ae124b8684 Improve size class header
Mainly fixing typos.  The only non-trivial change is in the
computation for SC_NPSIZES, though the result wouldn't be any
different when SC_NGROUP = 4 as is always the case at the moment.
2019-04-24 10:45:12 -07:00
Qi Wang
1aabab5fdc Enforce TLS_MODEL attribute.
Caught by @zoulasc in #1460.  The attribute needs to be added in the headers as
well.
2019-04-16 11:07:15 -07:00
David Goldblatt
33e1dad680 Safety checks: Add a redzoning feature. 2019-04-15 16:48:12 -07:00
David Goldblatt
b92c9a1a81 Safety checks: Indirect through a function.
This will let us share code on failure pathways.pathways
2019-04-15 16:48:12 -07:00
David Goldblatt
f4d24f05e1 Move extra size checks behind a config flag.
This will let us turn that flag into a generic "turn on runtime checks" flag
that guards other functionality we have planned.
2019-04-15 16:48:12 -07:00
zoulasc
7f7935cf78 Add an autoconf feature test for format_arg and a jemalloc-specific
macro for it.
2019-04-15 15:14:46 -07:00
zoulasc
14e4176758 Fix incorrect macro use.
Compiling with warnings produces missing prototype warnings.
2019-04-15 15:14:46 -07:00
zoulasc
020b5dc7ac Convert the format generator function to an annotated format function,
so that the generated formats can be checked by the compiler.
2019-04-15 15:14:46 -07:00
mgrice
d3d7a8ef09 remove compare and branch in fast path for c++ operator delete[]
Summary: sdallocx is checking a flag that will never be set (at least in the provided C++ destructor implementation).  This branch will probably only rarely be mispredicted however it removes two instructions in sdallocx and one at the callsite (to zero out flags).
2019-04-08 10:59:05 -07:00
Yinan Zhang
9aab3f2be0 Add memory utilization analytics to mallctl
The analytics tool is put under experimental.utilization namespace in
mallctl.  Input is one pointer or an array of pointers and the output
is a list of memory utilization statistics.
2019-04-04 13:48:39 -07:00
Qi Wang
fb56766ca9 Eagerly purge oversized merged extents.
This change improves memory usage slightly, at virtually no CPU cost.
2019-03-14 17:34:55 -07:00
Qi Wang
f6c30cbafa Remove some unused comments. 2019-03-14 17:34:55 -07:00
Qi Wang
b804d0f019 Fallback to 32-bit when 8-bit atomics are missing for TSD.
When it happens, this might cause a slowdown on the fast path operations.
However such case is very rare.
2019-03-09 12:52:06 -08:00
Qi Wang
06f0850427 Detect if 8-bit atomics are available.
In some rare cases (older compiler, e.g. gcc 4.2 w/ MIPS), 8-bit atomics might
be unavailable.  Detect such cases so that we can workaround.
2019-03-09 12:52:06 -08:00
Jason Evans
14d3686c9f Do not use #pragma GCC diagnostic with gcc < 4.6.
This regression was introduced by
3d29d11ac2 (Clean compilation -Wextra).
2019-03-09 12:10:30 -08:00
Jason Evans
775fe302a7 Remove JE_FORCE_SYNC_COMPARE_AND_SWAP_[48].
These macros have been unused since
d4ac7582f3 (Introduce a backport of C11
atomics).
2019-02-22 14:22:16 -08:00
Jason Evans
dca7060d5e Avoid redefining tsd_t.
This fixes a build failure when integrating with FreeBSD's libc.  This
regression was introduced by d1e11d48d4
(Move tsd link and in_hook after tcache.).
2019-02-20 20:27:55 -08:00
Qi Wang
8e9a613122 Disable muzzy decay by default. 2019-02-04 14:38:54 -08:00
Qi Wang
e13400c919 Sanity check szind on tcache flush.
This adds some overhead to the tcache flush path (which is one of the
popular paths).  Guard it behind a config option.
2019-02-01 12:31:34 -08:00
Qi Wang
e3db480f6f Rename huge_threshold to oversize_threshold.
The keyword huge tend to remind people of huge pages which is not relevent to
the feature.
2019-01-25 13:15:45 -08:00
Qi Wang
350809dc5d Set huge_threshold to 8M by default.
This feature uses an dedicated arena to handle huge requests, which
significantly improves VM fragmentation.  In production workload we tested it
often reduces VM size by >30%.
2019-01-24 13:29:23 -08:00
Qi Wang
bbe8e6a909 Avoid creating bg thds for huge arena lone.
For low arena count settings, the huge threshold feature may trigger an unwanted
bg thd creation.  Given that the huge arena does eager purging by default,
bypass bg thd creation when initializing the huge arena.
2019-01-15 16:00:34 -08:00
Qi Wang
f459454afe Avoid potential issues on extent zero-out.
When custom extent_hooks or transparent huge pages are in use, the purging
semantics may change, which means we may not get zeroed pages on repopulating.
Fixing the issue by manually memset for such cases.
2019-01-11 19:16:12 -08:00
Leonardo Santagada
daa0e436ba implement malloc_getcpu for windows 2019-01-08 14:34:45 -08:00
Qi Wang
7241bf5b74 Only read arena index from extent on the tcache flush path.
Add exten_arena_ind_get() to avoid loading the actual arena ptr in case we just
need to check arena matching.
2018-12-18 15:19:30 -08:00
Alexander Zinoviev
36de5189c7 Add rate counters to stats 2018-12-18 09:59:41 -08:00
Qi Wang
98b56ab23d Store the bin shard selection in TSD.
This avoids having to choose bin shard on the fly, also will allow flexible bin
binding for each thread.
2018-12-03 17:17:03 -08:00
Qi Wang
3f9f2833f6 Add opt.bin_shards to specify number of bin shards.
The option uses the same format as "slab_sizes" to specify number of shards for
each bin size.
2018-12-03 17:17:03 -08:00
Qi Wang
37b8913925 Add support for sharded bins within an arena.
This makes it possible to have multiple set of bins in an arena, which improves
arena scalability because the bins (especially the small ones) are always the
limiting factor in production workload.

A bin shard is picked on allocation; each extent tracks the bin shard id for
deallocation.  The shard size will be determined using runtime options.
2018-12-03 17:17:03 -08:00
Dave Watson
b23336af96 mutex: fix trylock spin wait contention
If there are 3 or more threads spin-waiting on the same mutex,
there will be excessive exclusive cacheline contention because
pthread_trylock() immediately tries to CAS in a new value, instead
of first checking if the lock is locked.

This diff adds a 'locked' hint flag, and we will only spin wait
without trylock()ing while set.  I don't know of any other portable
way to get the same behavior as pthread_mutex_lock().

This is pretty easy to test via ttest, e.g.

./ttest1 500 3 10000 1 100

Throughput is nearly 3x as fast.

This blames to the mutex profiling changes, however, we almost never
have 3 or more threads contending in properly configured production
workloads, but still worth fixing.
2018-11-28 15:17:02 -08:00
Qi Wang
c4063ce439 Set the default number of background threads to 4.
The setting has been tested in production for a while.  No negative effect while
we were able to reduce number of threads per process.
2018-11-16 09:35:12 -08:00
Qi Wang
43f3b1ad0c Deprecate OSSpinLock. 2018-11-14 08:44:05 -08:00
Dave Watson
13c237c7ef Add a fastpath for arena_slab_reg_alloc_batch
Also adds a configure.ac check for __builtin_popcount, which is used
in the new fastpath.
2018-11-14 07:09:11 -08:00
Dave Watson
17aa470760 add extent_nfree_sub 2018-11-14 07:09:11 -08:00
Qi Wang
1f56115704 Fix tcache_flush (follow up cd2931a).
Also catch invalid tcache id.
2018-11-13 08:54:09 -08:00
Dave Watson
e2ab215324 refactor tcache_dalloc_small
Add a cache_bin_dalloc_easy (to match the alloc_easy function),
and use it in tcache_dalloc_small.  It will also be used in the
new free fastpath.
2018-11-12 13:20:37 -08:00
Dave Watson
5e795297b3 rtree: add rtree_szind_slab_read_fast
For a free fastpath, we want something that will not make additional
calls.  Assume most free() calls will hit the L1 cache, and use
a custom rtree function for this.

Additionally, roll the ptr=NULL check in to the rtree cache check.
2018-11-12 13:20:37 -08:00
Justin Hibbits
be0749f591 Restrict lwsync to powerpc64 only
Nearly all 32-bit powerpc hardware treats lwsync as sync, and some cores
(Freescale e500) trap lwsync as an illegal instruction, which then gets
emulated in the kernel.  To avoid unnecessary traps on the e500, use
sync on all 32-bit powerpc.  This pessimizes 32-bit software running on
64-bit hardware, but those numbers should be slim.
2018-10-24 11:18:55 -07:00
Edward Tomasz Napierala
ceba1dde27 Make use of pthread_set_name_np(3) on FreeBSD. 2018-10-24 10:06:37 -07:00
Dave Watson
936bc2aa15 prof: Fix memory regression
The diff 'refactor prof accum...' moved the bytes_until_sample
subtraction before the load of tdata.  If tdata is null,
tdata_get(true) will overwrite bytes_until_sample, but we
still sample the current allocation.   Instead, do the subtraction
and check logic again, to keep the previous behavior.

blame-rev: 0ac524308d
2018-10-23 12:39:57 -07:00
Dave Watson
0ec656eb71 ticker: add ticker_trytick
For the fastpath, we want to tick, but undo the tick and jump to the
slowpath if ticker would fire.
2018-10-18 08:32:19 -07:00
Dave Watson
ac34afb403 drop bump_empty_alloc option. Size class lookup support used instead. 2018-10-17 08:50:58 -07:00
Dave Watson
4edbb7c64c sz: Support 0 size in size2index lookup/compute 2018-10-17 08:50:58 -07:00
gnzlbg
08260a6b94 Add experimental API: smallocx_return_t smallocx(size, flags)
---

Motivation:

This new experimental memory-allocaction API returns a pointer to
the allocation as well as the usable size of the allocated memory
region.

The `s` in `smallocx` stands for `sized`-`mallocx`, attempting to
convey that this API returns the size of the allocated memory region.

It should allow C++ P0901r0 [0] and Rust Alloc::alloc_excess to make
use of it.

The main purpose of these APIs is to improve telemetry. It is more accurate
to register `smallocx(size, flags)` than `smallocx(nallocx(size), flags)`,
for example. The latter will always line up perfectly with the existing
size classes, causing a loss of telemetry information about the internal
fragmentation induced by potentially poor size-classes choices.

Instrumenting `nallocx` does not help much since user code can cache its
result and use it repeatedly.

---

Implementation:

The implementation adds a new `usize` option to `static_opts_s` and an `usize`
variable to `dynamic_opts_s`. These are then used to cache the result of
`sz_index2size` and similar functions in the code paths in which they are
unconditionally invoked. In the code-paths in which these functions are not
unconditionally invoked, `smallocx` calls, as opposed to `mallocx`, these
functions explicitly.

---

[0]: http://www.open-std.org/jtc1/sc22/wg21/docs/papers/2018/p0901r0.html
2018-10-17 07:12:28 -07:00
Dave Watson
325e3305fc remove malloc_init() off the fastpath 2018-10-15 10:11:08 -07:00
Dave Watson
997d86acc6 restrict bytes_until_sample to int64_t. This allows optimal asm
generation of sub bytes_until_sample, usize; je; for x86 arch.
Subtraction is unconditional, and only flags are checked for the jump,
no extra compare is necessary.  This also reduces register pressure.
2018-10-15 08:24:12 -07:00
Dave Watson
0ac524308d refactor prof accum, so that tdata is not loaded if we aren't going to sample. 2018-10-15 08:24:12 -07:00
Dave Watson
9ed3bdc848 move bytes until sample to tsd. Fastpath allocation does not need
to load tdata now, avoiding several branches.
2018-10-15 08:24:12 -07:00
Dave Watson
09adf18f1a Remove a branch from cache_bin_alloc_easy
Combine the branches for checking for an empty cache_bin, and
checking for the low watermark.
2018-10-15 08:18:15 -07:00
Rajeev Misra
115ce93562 bit_util: Don't use __builtin_clz on s390x
There's an optimizer bug upstream that results in test failures; reported at
https://bugzilla.redhat.com/show_bug.cgi?id=1619354.  This works around the
failure reported at https://github.com/jemalloc/jemalloc/issues/1307.
2018-09-20 11:25:17 -07:00
Rajeev Misra
4c548a61c8 Bit_util: Use intrinsics for pow2_ceil, where available. 2018-08-15 19:38:31 -07:00
David Carlier
0771ff2cea FreeBSD build changes and allow to run the tests. 2018-08-09 10:41:20 -07:00
David Goldblatt
e8ec9528ab Allow the use of readlinkat over readlink.
This can be useful in situations where readlink is disallowed.
2018-08-03 14:04:32 -07:00
Tyler Etzel
126252a7e6 Add stats for the size of extent_avail heap 2018-08-02 10:16:06 -07:00
Tyler Etzel
c14e6c0819 Add extents information to mallocstats output
- Show number/bytes of extents of each size that are dirty, muzzy, retained.
2018-08-02 10:16:06 -07:00
Tyler Etzel
33f1aa5bad Fix comment on SC_NPSIZES. 2018-08-02 10:16:06 -07:00
Tyler Etzel
5e23f96dd4 Add unit tests for logging 2018-08-01 13:27:11 -07:00
Tyler Etzel
b664bd7935 Add logging for sampled allocations
- prof_opt_log flag starts logging automatically at runtime
- prof_log_{start,stop} mallctl for manual control
2018-08-01 13:27:11 -07:00
Tyler Etzel
eb261e53a6 Small refactoring of emitter
- Make API more clear for using as standalone json emitter
- Support cases that weren't possible before, e.g.
	- emitting primitive values in an array
	- emitting nested arrays
2018-08-01 13:27:11 -07:00
David Goldblatt
41b7372ead TSD: Add fork support to tsd_nominal_tsds.
In case of multithreaded fork, we want to leave the child in a reasonable state,
in which tsd_nominal_tsds is either empty or contains only the forking thread.
2018-07-26 17:22:25 -07:00
David Goldblatt
3aba072cef SC: Remove global data.
The global data is mostly only used at initialization, or for easy access to
values we could compute statically.  Instead of consuming that space (and
risking TLB misses), we can just pass around a pointer to stack data during
bootstrapping.
2018-07-23 13:37:08 -07:00
David Goldblatt
55e5cc1341 SC: Make some key size classes static.
The largest small class, smallest large class, and largest large class may all
be needed down fast paths; to avoid the risk of touching another cache line, we
can make them available as constants.
2018-07-12 20:53:06 -07:00
David T. Goldblatt
a7f68aed3e SC: Add page customization functionality. 2018-07-12 20:53:06 -07:00
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