Commit Graph

1100 Commits

Author SHA1 Message Date
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
5112d9e5fd Add MALLOC_CONF parsing for dynamic slab sizes.
This actually enables us to change the values.
2018-07-12 20:53:06 -07:00
David T. Goldblatt
4610ffa942 Bootstrapping: Parse MALLOC_CONF before using slab sizes.
I.e., parse before booting the bin module or sz module.  This lets us tweak size
class settings before committing to them by letting them leak into other
modules.

This commit does not actually do any tweaking of the size classes; it *just*
chanchanges bootstrapping order; this may help bisecting any bootstrapping
failures on poorly-tested architectures.
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 T. Goldblatt
017dca198c SC module: Add a note on style. 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
4f55c0ec22 Translate size class computation from bash shell into C.
This is the last big step in making size classes a runtime computation rather
than a configure-time one.

The compile-time computation has been left in, for now, to allow assertion
checking that the results are identical.
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
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
cdf15b458a Rename huge_threshold to experimental, and tweak documentation. 2018-06-29 10:35:02 -07:00
Qi Wang
1302af4c43 Add ctl and stats for opt.huge_threshold. 2018-06-29 10:35:02 -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
fec1ef7c91 Fix arena locking in tcache_bin_flush_large().
This regression was introduced in c834912 (incorrect arena used).
2018-06-26 23:13:15 -07:00
Qi Wang
0ff7ff3ec7 Optimize ixalloc by avoiding a size lookup. 2018-06-05 21:03:51 -07:00
Qi Wang
c834912aa9 Avoid taking large_mtx for auto arenas.
On tcache flush path, we can avoid touching the large_mtx for auto arenas, since
it was only needed for manual arenas where arena_reset is allowed.
2018-06-05 15:16:03 -07:00
Qi Wang
9bd8deb260 Fix stats output for opt.lg_extent_max_active_fit. 2018-06-05 10:23:28 -07:00
Qi Wang
d22e150320 Avoid taking extents_muzzy mutex when muzzy is disabled.
When muzzy decay is disabled, no need to allocate from extents_muzzy.  This
saves us a couple of mutex operations down the extents_alloc path.
2018-05-24 14:40:56 -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
bb071db92e Mallctl: Add experimental.hooks.[install|remove]. 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
83e516154c Hooks: hook the pure-expand function. 2018-05-18 11:43:03 -07:00
David Goldblatt
c154f5881b Hooks: hook the pure-deallocation functions. 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
fe0e399385 Hooks: add an early-exit path for the common no-hook case. 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
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
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
Qi Wang
09edea3f5c Tweak the format of the per arena summary section.
Increase the width to ensure enough space for long running programs.
2018-05-17 12:58:56 -07:00
Qi Wang
312352faa8 Fix background thread index issues with max_background_threads. 2018-05-15 12:25:23 -07:00
Qi Wang
e8a63b87c3 Fix an incorrect assertion.
When configured with --with-lg-page, it's possible for the configured page size
to be greater than the system page size, in which case the page address may only
be aligned with the system page size.
2018-05-09 23:52:56 -07:00
Latchesar Ionkov
a32b7bd567 Mallctl: Add arenas.lookup
Implement a new mallctl operation that allows looking up the arena a
region of memory belongs to.
2018-05-01 13:14:36 -07:00
Qi Wang
b8f4c730ef Remove an incorrect assertion.
Background threads are created without holding the global background_thread
lock, which mean paused state is possible (and fine).
2018-04-18 14:17:08 -07:00
Qi Wang
dedfeecc4e Invoke dlsym() on demand.
If no lazy lock or background thread is enabled, avoid dlsym pthread_create on
boot.
2018-04-18 11:20:21 -07:00
David Goldblatt
c95284df1a Avoid a resource leak down extent split failure paths.
Previously, we would leak the extent and memory associated with a salvageable
portion of an extent that we were trying to split in three, in the case where
the first split attempt succeeded and the second failed.
2018-04-18 08:19:41 -07:00
Qi Wang
e40b2f75bd Fix abort_conf processing.
When abort_conf is set, make sure we always error out at the end of the options
processing loop.
2018-04-17 18:23:53 -07:00
Qi Wang
0fadf4a2e3 Add UNUSED to avoid compiler warnings. 2018-04-16 13:50:21 -07:00
Qi Wang
3f0dc64c6b Allow setting extent hooks on uninitialized auto arenas.
Setting extent hooks can result in initializing an unused auto arena.  This is
useful to install extent hooks on auto arenas from the beginning.
2018-04-11 21:21:54 -07:00
Jason Evans
4937309620 Silence a compiler warning. 2018-04-10 17:59:00 -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
Rajeev Misra
5f51882a0a Stack address should not be used for ordering mutexes 2018-04-10 10:16:57 -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
4df483f0fd Fix arguments passed to extent_init. 2018-04-09 16:35:58 -07:00
Qi Wang
2dccf45640 Control idump and gdump with prof_active. 2018-04-09 16:35:14 -07:00
Dave Watson
6d02421730 extents: Remove preserve_lru feature.
preserve_lru feature adds lots of complication, for little value.
Removing it means merged extents are re-added to the lru list, and may
take longer to madvise away than they otherwise would.

Canaries after removal seem flat for several services (no change).
2018-04-02 12:40:28 -07:00
Qi Wang
21eb0d15a6 Fix a background_thread shutdown issue.
1) make sure background thread 0 is always created; and 2) fix synchronization
between thread 0 and the control thread.
2018-04-02 10:03:47 -07:00
Qi Wang
956c4ad6b5 Change mutable option output in stats to avoid stringify issues. 2018-03-15 14:42:48 -07:00
Qi Wang
baffeb1d0a Fix a typo in stats. 2018-03-15 14:42:48 -07:00
David Goldblatt
4c36cd2cc5 Stats printing: Convert arena large stats to use emitter.
This completes the conversion; we now have only structured text output.
2018-03-09 11:47:17 -08:00
David Goldblatt
4eed989bbf Stats printing: convert arena bin stats to use emitter. 2018-03-09 11:47:17 -08:00
David Goldblatt
a9f3cedc6e Stats printing: remove a spurious newline.
This was left over from a previous emitter conversion.  It didn't affect the
correctness of the output.
2018-03-09 11:47:17 -08:00
David Goldblatt
a1738f4efd Stats printing: Make arena mutex stats use the emitter. 2018-03-09 11:47:17 -08:00
David Goldblatt
07fb707623 Stats printing: convert most per-arena stats to use the emitter. 2018-03-09 11:47:17 -08:00
David Goldblatt
8fc850695d Stats printing: convert paging and alloc counts to use the emitter. 2018-03-09 11:47:17 -08:00
David Goldblatt
bc6620f73e Stats printing: convert decay stats to use the emitter. 2018-03-09 11:47:17 -08:00
David Goldblatt
a6ef061c43 Stats printing: Move emitter cutoff point into stats_arena_print. 2018-03-09 11:47:17 -08:00
David Goldblatt
cbde666d9a Stats printing: move stats_print_helper to use emitter. 2018-03-09 11:47:17 -08:00
David Goldblatt
86c61d4a57 Stats printing: Move global mutex stats to use emitter. 2018-03-09 11:47:17 -08:00
David Goldblatt
9e1846b004 Stats printing: move non-mutex arena stats to the emitter.
Another step in the conversion process.  The mutex is a little different,
because we we want to emit it as an array.
2018-03-09 11:47:17 -08:00
David Goldblatt
8076b28721 Stats printing: Remove explicit callback passing to stats_print_helper.
This makes the emitter the only source of callback information, which is a step
towards where we want to be.
2018-03-09 11:47:17 -08:00
David Goldblatt
0d20eda127 Stats printing: Move emitter -> manual cutoff point.
This makes it so that the "general" portion of the stats code is completely
agnostic to emitter type.
2018-03-09 11:47:17 -08:00
David Goldblatt
ec31d476ff Stats printing: Convert profiling stats to use the emitter.
While we're at it, print them in table form, too.
2018-03-09 11:47:17 -08:00
David Goldblatt
e5acc35400 Stats printing: Convert general arena stats to use the emitter. 2018-03-09 11:47:17 -08:00
David Goldblatt
4a335e0c6f Stats printing: convert config and opt output to use emitter.
This is a step along the path towards using the emitter for all stats output.
2018-03-09 11:47:17 -08:00
David Goldblatt
b646f89173 Stats printing: Convert header and footer to use emitter. 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 Goldblatt
26b1c13982 Background threads: fix an indexing bug.
We have a buffer overrun that manifests in the case where arena indices higher
than the number of CPUs are accessed before arena indices lower than the number
of CPUs.  This fixes the bug and adds a test.
2018-02-27 19:43:05 -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
ba5992fe9a Improve the fit for aligned allocation.
We compute the max size required to satisfy an alignment.  However this can be
quite pessimistic, especially with frequent reuse (and combined with state-based
fragmentation).  This commit adds one more fit step specific to aligned
allocations, searching in all potential fit size classes.
2018-01-05 14:27:58 -08:00
Rajeev Misra
f47e39d11a handle 32 bit mutex counters 2018-01-04 11:08:17 -08:00
David Goldblatt
d41b19f9c7 Implement arena regind computation using div_info_t.
This eliminates the need to generate an enormous switch statement in
arena_slab_regind.
2017-12-21 14:25:43 -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
Qi Wang
5e0332890f Output opt.lg_extent_max_active_fit in stats. 2017-12-14 15:49:15 -08:00
Qi Wang
955b1d9cc5 Fix extent deregister on the leak path.
On leak path we should not adjust gdump when deregister.
2017-12-08 22:22:03 -08:00
Qi Wang
6e841f618a Add more tests for extent hooks failure paths. 2017-11-28 21:52:49 -08:00
Qi Wang
26a8f82c48 Add missing deregister before extents_leak.
This fixes an regression introduced by 211b1f3 (refactor extent split).
2017-11-19 21:12:40 -08:00
Qi Wang
e475d03752 Avoid setting zero and commit if split fails in extent_recycle. 2017-11-19 21:12:27 -08:00
Qi Wang
3e64dae802 Eagerly coalesce large extents.
Coalescing is a small price to pay for large allocations since they happen less
frequently.  This reduces fragmentation while also potentially improving
locality.
2017-11-16 15:32:02 -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
Qi Wang
282a3faa17 Use extent_heap_first for best fit.
extent_heap_any makes the layout less predictable and as a result incurs more
fragmentation.
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
6dd5681ab7 Use hugepage alignment for base allocator.
This gives us an easier way to tell if the allocation is for metadata in the
extent hooks.
2017-11-03 19:37:13 -07:00