summaryrefslogtreecommitdiffstats
path: root/src
Commit message (Collapse)AuthorAgeFilesLines
...
* Update brace style.Jason Evans2017-01-2122-1748/+1670
| | | | | | | Add braces around single-line blocks, and remove line breaks before function-opening braces. This resolves #537.
* Unify the allocation pathsDavid Goldblatt2017-01-201-392/+505
| | | | | | | | | This unifies the allocation paths for malloc, posix_memalign, aligned_alloc, calloc, memalign, valloc, and mallocx, so that they all share common code where they can. There's more work that could be done here, but I think this is the smallest discrete change in this direction.
* Fix --disable-stats support.Jason Evans2017-01-202-164/+200
| | | | | Fix numerous regressions that were exposed by --disable-stats, both in the core library and in the tests.
* Test JSON output of malloc_stats_print() and fix bugs.Jason Evans2017-01-191-28/+37
| | | | | | | | Implement and test a JSON validation parser. Use the parser to validate JSON output from malloc_stats_print(), with a significant subset of supported output options. This resolves #551.
* Added stats about number of bytes cached in tcache currently.Qi Wang2017-01-183-0/+37
|
* Add dummy implementations for most remaining OSX zone allocator functionsMike Hommey2017-01-181-10/+108
| | | | | | | | | | | | | | | | | | | | | | | | | Some system libraries are using malloc_default_zone() and then using some of the malloc_zone_* API. Under normal conditions, those functions check the malloc_zone_t/malloc_introspection_t struct for the values that are allowed to be NULL, so that a NULL deref doesn't happen. As of OSX 10.12, malloc_default_zone() doesn't return the actual default zone anymore, but returns a fake, wrapper zone. The wrapper zone defines all the possible functions in the malloc_zone_t/malloc_introspection_t struct (almost), and calls the function from the registered default zone (jemalloc in our case) on its own. Without checking whether the pointers are NULL. This means that a system library that calls e.g. malloc_zone_batch_malloc(malloc_default_zone(), ...) ends up trying to call jemalloc_zone.batch_malloc, which is NULL, and crash follows. So as of OSX 10.12, the default zone is required to have all the functions available (really, the same as the wrapper zone), even if they do nothing. This is arguably a bug in libsystem_malloc in OSX 10.12, but jemalloc still needs to work in that case.
* Don't rely on OSX SDK malloc/malloc.h for malloc_zone struct definitionsMike Hommey2017-01-181-36/+86
| | | | | | | | | | 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.
* Fix prof_realloc() regression.Jason Evans2017-01-171-40/+123
| | | | | | | | | | | | | | Mostly revert the prof_realloc() changes in 498856f44a30b31fe713a18eb2fc7c6ecf3a9f63 (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 ea8d97b8978a0c0423f0ed64332463a25b787c3d (Fix prof_{malloc,free}_sample_object() call order in prof_realloc().) is not repeated. This resolves #499.
* Formatting/comment fixes.Jason Evans2017-01-172-3/+2
|
* Add nullptr support to sized delete operators.Jason Evans2017-01-171-0/+6
|
* Fix style nits.Jason Evans2017-01-171-19/+18
|
* Remove redundent stats-merging logic when destroying tcache.Qi Wang2017-01-171-11/+4
| | | | The removed stats merging logic is already taken care of by tcache_flush.
* Remove leading blank lines from function bodies.Jason Evans2017-01-1321-257/+0
| | | | This resolves #535.
* Fix indentation.Jason Evans2017-01-132-4/+4
|
* Implement arena.<i>.destroy .Jason Evans2017-01-075-96/+315
| | | | | | | Add MALLCTL_ARENAS_DESTROYED for accessing destroyed arena stats as an analogue to MALLCTL_ARENAS_ALL. This resolves #382.
* Replace the arenas.initialized mallctl with arena.<i>.initialized .Jason Evans2017-01-072-33/+33
|
* Range-check mib[1] --> arena_ind casts.Jason Evans2017-01-071-7/+22
|
* Move static ctl_epoch variable into ctl_stats_t (as epoch).Jason Evans2017-01-071-4/+3
|
* Refactor ctl_stats_t.Jason Evans2017-01-071-58/+91
| | | | | | | 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.
* Rename the arenas.extend mallctl to arenas.create.Jason Evans2017-01-072-4/+4
|
* Add MALLCTL_ARENAS_ALL.Jason Evans2017-01-072-77/+123
| | | | | | | 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).
* Fix locking in arena_dirty_count().Jason Evans2017-01-071-1/+3
| | | | This was a latent bug, since the function is (intentionally) not used.
* Fix allocated_large stats with respect to sampled small allocations.Jason Evans2017-01-071-6/+18
|
* Fix arena_large_reset_stats_cancel().Jason Evans2017-01-051-1/+1
| | | | | Decrement ndalloc_large rather than incrementing, in order to cancel out the increment in arena_large_dalloc_stats_update().
* Implement per arena base allocators.Jason Evans2016-12-279-202/+418
| | | | | | | | | | | | | 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.
* Refactor purging and splitting/merging.Jason Evans2016-12-274-48/+149
| | | | | | | | | | | | | | 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.
* Rename arena_decay_t's ndirty to nunpurged.Jason Evans2016-12-271-4/+4
|
* Use exponential series to size extents.Jason Evans2016-12-272-31/+189
| | | | | | | | | | 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.
* Add huge page configuration and pages_[no}huge().Jason Evans2016-12-271-1/+30
| | | | | | | | 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.
* Fix JSON-mode output for !config_stats and/or !config_prof cases.Jason Evans2016-12-231-10/+11
| | | | | | | These bugs were introduced by 0ba5b9b6189e16a983d8922d8c5cb6ab421906e8 (Add "J" (JSON) support to malloc_stats_print().), which was backported as b599b32280e1142856b0b96293a71e1684b1ccfb (with the same bugs except the inapplicable "metatata" misspelling) and first released in 4.3.0.
* Simplify arena_slab_regind().Jason Evans2016-12-231-59/+26
| | | | | | | | | 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.
* jemalloc cpp new/delete bindingsDave Watson2016-12-131-0/+140
| | | | | | | | | | | | | | | | | | | | | | | | | | | | 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.
* Add --disable-syscall.Jason Evans2016-12-042-4/+4
| | | | This resolves #517.
* Add pthread_atfork(3) feature test.Jason Evans2016-11-171-2/+3
| | | | | | Some versions of Android provide a pthreads library without providing pthread_atfork(), so in practice a separate feature test is necessary for the latter.
* Refactor madvise(2) configuration.Jason Evans2016-11-171-5/+5
| | | | | | | | | 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.
* Avoid gcc type-limits warnings.Jason Evans2016-11-171-12/+30
|
* Remove size_t -> unsigned -> size_t conversion.Maks Naumov2016-11-161-2/+1
|
* Uniformly cast mallctl[bymib]() oldp/newp arguments to (void *).Jason Evans2016-11-151-3/+4
| | | | | This avoids warnings in some cases, and is otherwise generally good hygiene.
* Add extent serial numbers.Jason Evans2016-11-154-28/+42
| | | | | | | | 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.
* Fix arena_reset() crashing bug.Jason Evans2016-11-151-41/+42
| | | | | This regression was caused by 498856f44a30b31fe713a18eb2fc7c6ecf3a9f63 (Move slabs out of chunks.).
* Rename atomic_*_{uint32,uint64,u}() to atomic_*_{u32,u64,zu}().Jason Evans2016-11-072-8/+8
| | | | This change conforms to naming conventions throughout the codebase.
* Refactor prng to not use 64-bit atomics on 32-bit platforms.Jason Evans2016-11-073-8/+8
| | | | This resolves #495.
* Fix/simplify extent_recycle() allocation size computations.Jason Evans2016-11-041-6/+5
| | | | | | | | | | | Do not call s2u() during alloc_size computation, since any necessary ceiling increase is taken care of later by extent_first_best_fit() --> extent_size_quantize_ceil(), and the s2u() call may erroneously cause a higher quantization result. Remove an overly strict overflow check that was added in 4a7852137d8b6598fdb90ea8e1fd3bc8a8b94a3a (Fix extent_recycle()'s cache-oblivious padding support.).
* Fix extent_recycle()'s cache-oblivious padding support.Jason Evans2016-11-041-5/+6
| | | | | | | Add padding *after* computing the size class, so that the optimal size class isn't skipped during search for a usable extent. This regression was caused by b46261d58b449cc4c099ed2384451a2499688f0e (Implement cache-oblivious support for huge size classes.).
* Fix psz/pind edge cases.Jason Evans2016-11-043-13/+13
| | | | | | | | | 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.
* Fix extent_alloc_cache[_locked]() to support decommitted allocation.Jason Evans2016-11-043-18/+17
| | | | | | | | | 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.
* Fix long spinning in rtree_node_initDave Watson2016-11-031-14/+9
| | | | | | | | | | | | | | | | | 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
* Check for existance of CPU_COUNT macro before using it.Dave Watson2016-11-031-1/+7
| | | | This resolves #485.
* Do not use syscall(2) on OS X 10.12 (deprecated).Jason Evans2016-11-032-4/+4
|
* Add os_unfair_lock support.Jason Evans2016-11-031-0/+2
| | | | | OS X 10.12 deprecated OSSpinLock; os_unfair_lock is the recommended replacement.
generated by cgit v0.12 at 2025-03-17 06:51:31 (GMT)