summaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAgeFilesLines
* Purge unused dirty pages in a fragmentation-reducing order.Jason Evans2012-11-064-221/+337
| | | | | | | | | | | | | | | | Purge unused dirty pages in an order that first performs clean/dirty run defragmentation, in order to mitigate available run fragmentation. Remove the limitation that prevented purging unless at least one chunk worth of dirty pages had accumulated in an arena. This limitation was intended to avoid excessive purging for small applications, but the threshold was arbitrary, and the effect of questionable utility. Relax opt_lg_dirty_mult from 5 to 3. This compensates for increased likelihood of allocating clean runs, given the same ratio of clean:dirty runs, and reduces the potential for repeated purging in pathological large malloc/free loops that push the active:dirty page ratio just over the purge threshold.
* Fix deadlock in the arenas.purge mallctl.Jason Evans2012-11-041-26/+22
| | | | | Fix deadlock in the arenas.purge mallctl due to recursive mutex acquisition.
* Fix dss/mmap allocation precedence code.Jason Evans2012-10-172-26/+20
| | | | | Fix dss/mmap allocation precedence code to use recyclable mmap memory only after primary dss allocation fails.
* Update ChangeLog for 3.1.0.Jason Evans2012-10-161-1/+12
|
* Add ctl_mutex proection to arena_i_dss_ctl().Jason Evans2012-10-151-0/+2
| | | | | Add ctl_mutex proection to arena_i_dss_ctl(), since ctl_stats.narenas is accessed.
* Add arena-specific and selective dss allocation.Jason Evans2012-10-1323-240/+905
| | | | | | | | | | | | | | | | | | | Add the "arenas.extend" mallctl, so that it is possible to create new arenas that are outside the set that jemalloc automatically multiplexes threads onto. Add the ALLOCM_ARENA() flag for {,r,d}allocm(), so that it is possible to explicitly allocate from a particular arena. Add the "opt.dss" mallctl, which controls the default precedence of dss allocation relative to mmap allocation. Add the "arena.<i>.dss" mallctl, which makes it possible to set the default dss precedence on a per arena or global basis. Add the "arena.<i>.purge" mallctl, which obsoletes "arenas.purge". Add the "stats.arenas.<i>.dss" mallctl.
* mark _pthread_mutex_init_calloc_cb as public explicitlyJan Beich2012-10-101-1/+1
| | | | | | | Mozilla build hides everything by default using visibility pragma and unhides only explicitly listed headers. But this doesn't work on FreeBSD because _pthread_mutex_init_calloc_cb is neither documented nor exposed via any header.
* Make malloc_usable_size() implementation consistent with prototype.Jason Evans2012-10-091-1/+1
| | | | | Use JEMALLOC_USABLE_SIZE_CONST for the malloc_usable_size() implementation as well as the prototype, for consistency's sake.
* Drop const from malloc_usable_size() argument on Linux.Jason Evans2012-10-093-1/+14
| | | | | Drop const from malloc_usable_size() argument on Linux, in order to match the prototype in Linux's malloc.h.
* Fix fork(2)-related mutex acquisition order.Jason Evans2012-10-091-3/+3
| | | | | | Fix mutex acquisition order inversion for the chunks rtree and the base mutex. Chunks rtree acquisition was introduced by the previous commit, so this bug was short-lived.
* Fix fork(2)-related deadlocks.Jason Evans2012-10-0910-3/+175
| | | | | | | | | | | | | | | | | Add a library constructor for jemalloc that initializes the allocator. This fixes a race that could occur if threads were created by the main thread prior to any memory allocation, followed by fork(2), and then memory allocation in the child process. Fix the prefork/postfork functions to acquire/release the ctl, prof, and rtree mutexes. This fixes various fork() child process deadlocks, but one possible deadlock remains (intentionally) unaddressed: prof backtracing can acquire runtime library mutexes, so deadlock is still possible if heap profiling is enabled during fork(). This deadlock is known to be a real issue in at least the case of libgcc-based backtracing. Reported by tfengjun.
* Fix mlockall()/madvise() interaction.Jason Evans2012-10-095-41/+48
| | | | | | | | mlockall(2) can cause purging via madvise(2) to fail. Fix purging code to check whether madvise() succeeded, and base zeroed page metadata on the result. Reported by Olivier Lecomte.
* Fix error return value in thread_tcache_enabled_ctl().Jason Evans2012-10-081-1/+1
| | | | Reported by Corey Richardson.
* If sysconf() fails, the number of CPUs is reported as UINT_MAX, not 1 as it ↵Corey Richardson2012-10-081-3/+4
| | | | should be
* Remove unused variable and branch (reported by clang-analzyer)Corey Richardson2012-10-081-5/+0
|
* Define LG_QUANTUM for hppa.Jason Evans2012-10-081-0/+3
| | | | Submitted by Jory Pratt.
* Remove const from __*_hook variable declarations.Jason Evans2012-05-232-5/+6
| | | | | Remove const from __*_hook variable declarations, so that glibc can modify them during process forking.
* Update a comment.Jason Evans2012-05-161-1/+1
|
* Disable tcache by default if running inside Valgrind.Jason Evans2012-05-163-1/+8
| | | | | Disable tcache by default if running inside Valgrind, in order to avoid making unallocated objects appear reachable to Valgrind.
* Auto-detect whether running inside Valgrind.Jason Evans2012-05-154-30/+31
| | | | | Auto-detect whether running inside Valgrind, thus removing the need to manually specify MALLOC_CONF=valgrind:true.
* Fix heap profiling crash for realloc(p, 0) case.Jason Evans2012-05-152-1/+6
| | | | | Fix prof_realloc() to not call prof_ctx_set() if a sampled object is being freed via realloc(p, 0).
* Update ChangeLog for 3.0.0.Jason Evans2012-05-121-4/+6
|
* Return early in _malloc_{pre,post}fork() if uninitialized.Jason Evans2012-05-121-0/+14
| | | | | | | Avoid mutex operations in _malloc_{pre,post}fork() unless jemalloc has been initialized. Reported by David Xu.
* Fix large calloc() zeroing bugs.Jason Evans2012-05-113-30/+29
| | | | | | | | | Refactor code such that arena_mapbits_{large,small}_set() always preserves the unzeroed flag, and manually manipulate the unzeroed flag in the one case where it actually gets reset (in arena_chunk_purge()). This fixes unzeroed preservation bugs in arena_run_split() and arena_ralloc_large_grow(). These bugs caused large calloc() to return non-zeroed memory under some circumstances.
* Add arena chunk map assertions.Jason Evans2012-05-111-15/+30
|
* Refactor arena_run_alloc().Jason Evans2012-05-111-34/+24
| | | | | Refactor duplicated arena_run_alloc() code into arena_run_alloc_helper().
* Update a comment.Jason Evans2012-05-101-9/+9
|
* Generalize "stats.mapped" documentation.Jason Evans2012-05-101-2/+2
| | | | | | Generalize "stats.mapped" documentation to state that all inactive chunks are omitted, now that it is possible for mmap'ed chunks to be omitted in addition to DSS chunks.
* Export je_memalign and je_vallocMike Hommey2012-05-091-0/+9
| | | | | | da99e31 removed attributes on je_memalign and je_valloc, while they didn't have a definition in the jemalloc.h header, thus making them non-exported. Export them again, by defining them in the jemalloc.h header.
* Remove -fno-common compiler flag for OS X.Mike Hommey2012-05-091-1/+1
| | | | | It doesn't allow the je_malloc_message and je_malloc_conf symbols to be overridden when linking statically.
* Add the --enable-mremap option.Jason Evans2012-05-097-17/+64
| | | | | | Add the --enable-mremap option, and disable the use of mremap(2) by default, for the same reason that freeing chunks via munmap(2) is disabled by default on Linux: semi-permanent VM map fragmentation.
* Fix chunk_recycle() to stop leaking trailing chunks.Jason Evans2012-05-091-40/+38
| | | | | | | Fix chunk_recycle() to correctly compute trailsize and re-insert trailing chunks. This fixes a major virtual memory leak. Simplify chunk_record() to avoid dropping/re-acquiring chunks_mtx.
* Fix chunk_alloc_mmap() bugs.Jason Evans2012-05-092-35/+11
| | | | | | | | | | | | | | | | Simplify chunk_alloc_mmap() to no longer attempt map extension. The extra complexity isn't warranted, because although in the success case it saves one system call as compared to immediately falling back to chunk_alloc_mmap_slow(), it also makes the failure case even more expensive. This simplification removes two bugs: - For Windows platforms, pages_unmap() wasn't being called for unaligned mappings prior to falling back to chunk_alloc_mmap_slow(). This caused permanent virtual memory leaks. - For non-Windows platforms, alignment greater than chunksize caused pages_map() to be called with size 0 when attempting map extension. This always resulted in an mmap() error, and subsequent fallback to chunk_alloc_mmap_slow().
* Fix a base allocator deadlock.Jason Evans2012-05-031-3/+14
| | | | | Fix a base allocator deadlock due to chunk_recycle() calling back into the base allocator.
* Don't use sizeof() on a VARIABLE_ARRAYMike Hommey2012-05-021-2/+2
| | | | In the alloca() case, this fails to be the right size.
* Use "standard" printf prefixes instead of MSVC ones in inttypes.hMike Hommey2012-05-021-51/+59
| | | | | We don't use MSVC's printf, but ours, and it doesn't support the I32 and I64 prefixes.
* Use "hardcoded" dependencies when compiler doesn't support -MMMike Hommey2012-05-022-0/+17
|
* Allow je_malloc_message to be overridden when linking staticallyMike Hommey2012-05-022-19/+14
| | | | | | | | | | | | | If an application wants to override je_malloc_message, it is better to define the symbol locally than to change its value in main(), which might be too late for various reasons. Due to je_malloc_message being initialized in util.c, statically linking jemalloc with an application defining je_malloc_message fails due to "multiple definition of" the symbol. Defining it without a value (like je_malloc_conf) makes it more easily overridable.
* Further optimize and harden arena_salloc().Jason Evans2012-05-023-38/+74
| | | | | | | | | Further optimize arena_salloc() to only look at the binind chunk map bits in the common case. Add more sanity checks to arena_salloc() that detect chunk map inconsistencies for large allocations (whether due to allocator bugs or application bugs).
* Check for VALGRIND_RESIZEINPLACE_BLOCK supportMike Hommey2012-05-021-4/+1
| | | | | VALGRIND_RESIZEINPLACE_BLOCK was added in valgrind 3.7. Unfortunately, the __VALGRIND_MINOR__ macro still says 6 in 3.7 :(
* Fix partial rename of s/EXPORT/JEMALLOC_EXPORT/g.Jason Evans2012-05-021-5/+5
|
* Update private namespace mangling.Jason Evans2012-05-021-12/+11
|
* Make malloc_write() non-inline.Jason Evans2012-05-022-11/+12
| | | | | Make malloc_write() non-inline, in order to resolve its dependency on je_malloc_write().
* Make CACHELINE a raw constant.Jason Evans2012-05-021-1/+4
| | | | | | | Make CACHELINE a raw constant in order to work around a __declspec(align()) limitation. Submitted by Mike Hommey.
* Optimize malloc() and free() fast paths.Jason Evans2012-05-027-388/+614
| | | | | | | | | | Embed the bin index for small page runs into the chunk page map, in order to omit [...] in the following dependent load sequence: ptr-->mapelm-->[run-->bin-->]bin_info Move various non-critcal code out of the inlined function chain into helper functions (tcache_event_hard(), arena_dalloc_small(), and locking).
* Add support for MSVCMike Hommey2012-05-0111-15/+177
| | | | Tested with MSVC 8 32 and 64 bits.
* Import msinttypesMike Hommey2012-05-012-0/+552
| | | | http://code.google.com/p/msinttypes/
* Replace JEMALLOC_ATTR with various different macros when it makes senseMike Hommey2012-05-018-82/+56
| | | | | | Theses newly added macros will be used to implement the equivalent under MSVC. Also, move the definitions to headers, where they make more sense, and for some, are even more useful there (e.g. malloc).
* Few configure.ac adjustmentsMike Hommey2012-05-013-15/+9
| | | | | | - Use the extensions autoconf finds for object and executable files. - Remove the sorev variable, and replace SOREV definition with sorev's. - Default to je_ prefix on win32.
* Use Get/SetLastError on Win32Mike Hommey2012-04-307-33/+71
| | | | | | | | | Using errno on win32 doesn't quite work, because the value set in a shared library can't be read from e.g. an executable calling the function setting errno. At the same time, since buferror always uses errno/GetLastError, don't pass it.
generated by cgit v0.12 at 2025-04-11 06:05:25 (GMT)