JEMALLOC(3) | User Manual | JEMALLOC(3) |
NAME
jemalloc - general purpose memory allocation functionsLIBRARY
This manual describes jemalloc 3.4.0-0-g0ed518e5dab789ad2171bb38977a8927e2a26775. More information can be found at the jemalloc website[1].The following configuration options are enabled in libc's built-in jemalloc: --enable-dss, --enable-experimental, --enable-fill, --enable-lazy-lock, --enable-munmap, --enable-stats, --enable-tcache, --enable-tls, --enable-utrace, and --enable-xmalloc. Additionally, --enable-debug is enabled in development versions of FreeBSD (controlled by the MALLOC_PRODUCTION make variable).
SYNOPSIS
#include <stdlib.h>
#include <malloc_np.h>
Standard API
void *malloc(size_t size);
void *calloc(size_t number, size_t size);
int posix_memalign(void **ptr, size_t alignment, size_t size);
void *aligned_alloc(size_t alignment, size_t size);
void *realloc(void *ptr, size_t size);
void free(void *ptr);
Non-standard API
size_t malloc_usable_size(const void *ptr);
void malloc_stats_print(void (*write_cb) (void *, const char *), void *cbopaque, const char *opts);
int mallctl(const char *name, void *oldp, size_t *oldlenp, void *newp, size_t newlen);
int mallctlnametomib(const char *name, size_t *mibp, size_t *miblenp);
int mallctlbymib(const size_t *mib, size_t miblen, void *oldp, size_t *oldlenp, void *newp, size_t newlen);
void (*malloc_message)(void *cbopaque, const char *s);
const char * malloc_conf;
Experimental API
int allocm(void **ptr, size_t *rsize, size_t size, int flags);
int rallocm(void **ptr, size_t *rsize, size_t size, size_t extra, int flags);
int sallocm(const void *ptr, size_t *rsize, int flags);
int dallocm(void *ptr, int flags);
int nallocm(size_t *rsize, size_t size, int flags);
DESCRIPTION
Standard API
The malloc function allocates size bytes of uninitialized memory. The allocated space is suitably aligned (after possible pointer coercion) for storage of any type of object.The calloc function allocates space for number objects, each size bytes in length. The result is identical to calling malloc with an argument of number * size, with the exception that the allocated memory is explicitly initialized to zero bytes.
The posix_memalign function allocates size bytes of memory such that the allocation's base address is an even multiple of alignment, and returns the allocation in the value pointed to by ptr. The requested alignment must be a power of 2 at least as large as sizeof( void *).
The aligned_alloc function allocates size bytes of memory such that the allocation's base address is an even multiple of alignment. The requested alignment must be a power of 2. Behavior is undefined if size is not an integral multiple of alignment.
The realloc function changes the size of the previously allocated memory referenced by ptr to size bytes. The contents of the memory are unchanged up to the lesser of the new and old sizes. If the new size is larger, the contents of the newly allocated portion of the memory are undefined. Upon success, the memory referenced by ptr is freed and a pointer to the newly allocated memory is returned. Note that realloc may move the memory allocation, resulting in a different return value than ptr. If ptr is NULL, the realloc function behaves identically to malloc for the specified size.
The free function causes the allocated memory referenced by ptr to be made available for future allocations. If ptr is NULL, no action occurs.
Non-standard API
The malloc_usable_size function returns the usable size of the allocation pointed to by ptr. The return value may be larger than the size that was requested during allocation. The malloc_usable_size function is not a mechanism for in-place realloc ; rather it is provided solely as a tool for introspection purposes. Any discrepancy between the requested allocation size and the size reported by malloc_usable_size should not be depended on, since such behavior is entirely implementation-dependent.The malloc_stats_print function writes human-readable summary statistics via the write_cb callback function pointer and cbopaque data passed to write_cb, or malloc_message if write_cb is NULL. This function can be called repeatedly. General information that never changes during execution can be omitted by specifying "g" as a character within the opts string. Note that malloc_message uses the mallctl* functions internally, so inconsistent statistics can be reported if multiple threads use these functions simultaneously. If --enable-stats is specified during configuration, “m” and “a” can be specified to omit merged arena and per arena statistics, respectively;“b” and “l” can be specified to omit per size class statistics for bins and large objects, respectively. Unrecognized characters are silently ignored. Note that thread caching may prevent some statistics from being completely up to date, since extra locking would be required to merge counters that track thread cache operations.
The mallctl function provides a general interface for introspecting the memory allocator, as well as setting modifiable parameters and triggering actions. The period-separated name argument specifies a location in a tree-structured namespace; see the MALLCTL NAMESPACE section for documentation on the tree contents. To read a value, pass a pointer via oldp to adequate space to contain the value, and a pointer to its length via oldlenp; otherwise pass NULL and NULL. Similarly, to write a value, pass a pointer to the value via newp, and its length via newlen; otherwise pass NULL and 0.
The mallctlnametomib function provides a way to avoid repeated name lookups for applications that repeatedly query the same portion of the namespace, by translating a name to a “Management Information Base” (MIB) that can be passed repeatedly to mallctlbymib. Upon successful return from mallctlnametomib, mibp contains an array of *miblenp integers, where *miblenp is the lesser of the number of components in name and the input value of *miblenp. Thus it is possible to pass a *miblenp that is smaller than the number of period-separated name components, which results in a partial MIB that can be used as the basis for constructing a complete MIB. For name components that are integers (e.g. the 2 in "arenas.bin.2.size"), the corresponding MIB component will always be that integer. Therefore, it is legitimate to construct code like the following:
unsigned nbins, i;
int mib[4];
size_t len, miblen;
len = sizeof(nbins);
mallctl("arenas.nbins", &nbins, &len, NULL, 0);
miblen = 4;
mallnametomib("arenas.bin.0.size", mib, &miblen);
for (i = 0; i < nbins; i++) {
size_t bin_size;
mib[2] = i;
len = sizeof(bin_size);
mallctlbymib(mib, miblen, &bin_size, &len, NULL, 0);
/* Do something with bin_size... */
}
Experimental API
The experimental API is subject to change or removal without regard for backward compatibility. If --disable-experimental is specified during configuration, the experimental API is omitted.The allocm, rallocm, sallocm, dallocm, and nallocm functions all have a flags argument that can be used to specify options. The functions only check the options that are contextually relevant. Use bitwise or (|) operations to specify one or more of the following:
ALLOCM_LG_ALIGN(la)
ALLOCM_ALIGN(a)
ALLOCM_ZERO
ALLOCM_NO_MOVE
ALLOCM_ARENA(a)
The allocm function allocates at least size bytes of memory, sets *ptr to the base address of the allocation, and sets *rsize to the real size of the allocation if rsize is not NULL. Behavior is undefined if size is 0.
The rallocm function resizes the allocation at *ptr to be at least size bytes, sets *ptr to the base address of the allocation if it moved, and sets *rsize to the real size of the allocation if rsize is not NULL. If extra is non-zero, an attempt is made to resize the allocation to be at least size + extra) bytes, though inability to allocate the extra byte(s) will not by itself result in failure. Behavior is undefined if size is 0, or if ( size + extra > SIZE_T_MAX).
The sallocm function sets *rsize to the real size of the allocation.
The dallocm function causes the memory referenced by ptr to be made available for future allocations.
The nallocm function allocates no memory, but it performs the same size computation as the allocm function, and if rsize is not NULL it sets *rsize to the real size of the allocation that would result from the equivalent allocm function call. Behavior is undefined if size is 0.
TUNING
Once, when the first call is made to one of the memory allocation routines, the allocator initializes its internals based in part on various options that can be specified at compile- or run-time.The string pointed to by the global variable malloc_conf, the “name” of the file referenced by the symbolic link named /etc/malloc.conf, and the value of the environment variable MALLOC_CONF, will be interpreted, in that order, from left to right as options. Note that malloc_conf may be read before main is entered, so the declaration of malloc_conf should specify an initializer that contains the final value to be read by jemalloc. malloc_conf is a compile-time setting, whereas /etc/malloc.conf and MALLOC_CONF can be safely set any time prior to program invocation.
An options string is a comma-separated list of option:value pairs. There is one key corresponding to each "opt.*" mallctl (see the MALLCTL NAMESPACE section for options documentation). For example, abort:true,narenas:1 sets the "opt.abort" and "opt.narenas" options. Some options have boolean values (true/false), others have integer values (base 8, 10, or 16, depending on prefix), and yet others have raw string values.
IMPLEMENTATION NOTES
Traditionally, allocators have used sbrk(2) to obtain memory, which is suboptimal for several reasons, including race conditions, increased fragmentation, and artificial limitations on maximum usable memory. If --enable-dss is specified during configuration, this allocator uses both mmap(2) and sbrk(2), in that order of preference; otherwise only mmap(2) is used.This allocator uses multiple arenas in order to reduce lock contention for threaded programs on multi-processor systems. This works well with regard to threading scalability, but incurs some costs. There is a small fixed per-arena overhead, and additionally, arenas manage memory completely independently of each other, which means a small fixed increase in overall memory fragmentation. These overheads are not generally an issue, given the number of arenas normally used. Note that using substantially more arenas than the default is not likely to improve performance, mainly due to reduced cache performance. However, it may make sense to reduce the number of arenas if an application does not make much use of the allocation functions.
In addition to multiple arenas, unless --disable-tcache is specified during configuration, this allocator supports thread-specific caching for small and large objects, in order to make it possible to completely avoid synchronization for most allocation requests. Such caching allows very fast allocation in the common case, but it increases memory usage and fragmentation, since a bounded number of objects can remain allocated in each thread cache.
Memory is conceptually broken into equal-sized chunks, where the chunk size is a power of two that is greater than the page size. Chunks are always aligned to multiples of the chunk size. This alignment makes it possible to find metadata for user objects very quickly.
User objects are broken into three categories according to size: small, large, and huge. Small objects are smaller than one page. Large objects are smaller than the chunk size. Huge objects are a multiple of the chunk size. Small and large objects are managed by arenas; huge objects are managed separately in a single data structure that is shared by all threads. Huge objects are used by applications infrequently enough that this single data structure is not a scalability issue.
Each chunk that is managed by an arena tracks its contents as runs of contiguous pages (unused, backing a set of small objects, or backing one large object). The combination of chunk alignment and chunk page maps makes it possible to determine all metadata regarding small and large allocations in constant time.
Small objects are managed in groups by page runs. Each run maintains a frontier and free list to track which regions are in use. Allocation requests that are no more than half the quantum (8 or 16, depending on architecture) are rounded up to the nearest power of two that is at least sizeof( double). All other small object size classes are multiples of the quantum, spaced such that internal fragmentation is limited to approximately 25% for all but the smallest size classes. Allocation requests that are larger than the maximum small size class, but small enough to fit in an arena-managed chunk (see the "opt.lg_chunk" option), are rounded up to the nearest run size. Allocation requests that are too large to fit in an arena-managed chunk are rounded up to the nearest multiple of the chunk size.
Allocations are packed tightly together, which can be an issue for multi-threaded applications. If you need to assure that allocations do not suffer from cacheline sharing, round your allocation requests up to the nearest multiple of the cacheline size, or specify cacheline alignment when allocating.
Assuming 4 MiB chunks, 4 KiB pages, and a 16-byte quantum on a 64-bit system, the size classes in each category are as shown in Table 1.
Table 1. Size classes
Category | Spacing | Size |
Small | lg | [8] |
16 | [16, 32, 48, ..., 128] | |
32 | [160, 192, 224, 256] | |
64 | [320, 384, 448, 512] | |
128 | [640, 768, 896, 1024] | |
256 | [1280, 1536, 1792, 2048] | |
512 | [2560, 3072, 3584] | |
Large | 4 KiB | [4 KiB, 8 KiB, 12 KiB, ..., 4072 KiB] |
Huge | 4 MiB | [4 MiB, 8 MiB, 12 MiB, ...] |
MALLCTL NAMESPACE
The following names are defined in the namespace accessible via the mallctl* functions. Value types are specified in parentheses, their readable/writable statuses are encoded as rw, r-, -w, or --, and required build configuration flags follow, if any. A name element encoded as <i> or <j> indicates an integer component, where the integer varies from 0 to some upper value that must be determined via introspection. In the case of "stats.arenas.<i>.*", <i> equal to "arenas.narenas" can be used to access the summation of statistics from all arenas. Take special note of the "epoch" mallctl, which controls refreshing of cached dynamic statistics."version" ( const char *) r-
"epoch" ( uint64_t) rw
"config.debug" ( bool) r-
"config.dss" ( bool) r-
"config.fill" ( bool) r-
"config.lazy_lock" ( bool) r-
"config.mremap" ( bool) r-
"config.munmap" ( bool) r-
"config.prof" ( bool) r-
"config.prof_libgcc" ( bool) r-
"config.prof_libunwind" ( bool) r-
"config.stats" ( bool) r-
"config.tcache" ( bool) r-
"config.tls" ( bool) r-
"config.utrace" ( bool) r-
"config.valgrind" ( bool) r-
"config.xmalloc" ( bool) r-
"opt.abort" ( bool) r-
"opt.lg_chunk" ( size_t) r-
"opt.dss" ( const char *) r-
"opt.narenas" ( size_t) r-
"opt.lg_dirty_mult" ( ssize_t) r-
"opt.stats_print" ( bool) r-
"opt.junk" ( bool) r- [ --enable-fill]
"opt.quarantine" ( size_t) r- [ --enable-fill]
"opt.redzone" ( bool) r- [ --enable-fill]
"opt.zero" ( bool) r- [ --enable-fill]
"opt.utrace" ( bool) r- [ --enable-utrace]
"opt.valgrind" ( bool) r- [ --enable-valgrind]
"opt.xmalloc" ( bool) r- [ --enable-xmalloc]
malloc_conf = "xmalloc:true";
"opt.tcache" ( bool) r- [ --enable-tcache]
"opt.lg_tcache_max" ( size_t) r- [ --enable-tcache]
"opt.prof" ( bool) r- [ --enable-prof]
"opt.prof_prefix" ( const char *) r- [ --enable-prof]
"opt.prof_active" ( bool) r- [ --enable-prof]
"opt.lg_prof_sample" ( ssize_t) r- [ --enable-prof]
"opt.prof_accum" ( bool) r- [ --enable-prof]
"opt.lg_prof_interval" ( ssize_t) r- [ --enable-prof]
"opt.prof_gdump" ( bool) r- [ --enable-prof]
"opt.prof_final" ( bool) r- [ --enable-prof]
"opt.prof_leak" ( bool) r- [ --enable-prof]
"thread.arena" ( unsigned) rw
"thread.allocated" ( uint64_t) r- [ --enable-stats]
"thread.allocatedp" ( uint64_t *) r- [ --enable-stats]
"thread.deallocated" ( uint64_t) r- [ --enable-stats]
"thread.deallocatedp" ( uint64_t *) r- [ --enable-stats]
"thread.tcache.enabled" ( bool) rw [ --enable-tcache]
"thread.tcache.flush" ( void) -- [ --enable-tcache]
"arena.<i>.purge" ( unsigned) --
"arena.<i>.dss" ( const char *) rw
"arenas.narenas" ( unsigned) r-
"arenas.initialized" ( bool *) r-
"arenas.quantum" ( size_t) r-
"arenas.page" ( size_t) r-
"arenas.tcache_max" ( size_t) r- [ --enable-tcache]
"arenas.nbins" ( unsigned) r-
"arenas.nhbins" ( unsigned) r- [ --enable-tcache]
"arenas.bin.<i>.size" ( size_t) r-
"arenas.bin.<i>.nregs" ( uint32_t) r-
"arenas.bin.<i>.run_size" ( size_t) r-
"arenas.nlruns" ( size_t) r-
"arenas.lrun.<i>.size" ( size_t) r-
"arenas.purge" ( unsigned) -w
"arenas.extend" ( unsigned) r-
"prof.active" ( bool) rw [ --enable-prof]
"prof.dump" ( const char *) -w [ --enable-prof]
"prof.interval" ( uint64_t) r- [ --enable-prof]
"stats.cactive" ( size_t *) r- [ --enable-stats]
"stats.allocated" ( size_t) r- [ --enable-stats]
"stats.active" ( size_t) r- [ --enable-stats]
"stats.mapped" ( size_t) r- [ --enable-stats]
"stats.chunks.current" ( size_t) r- [ --enable-stats]
"stats.chunks.total" ( uint64_t) r- [ --enable-stats]
"stats.chunks.high" ( size_t) r- [ --enable-stats]
"stats.huge.allocated" ( size_t) r- [ --enable-stats]
"stats.huge.nmalloc" ( uint64_t) r- [ --enable-stats]
"stats.huge.ndalloc" ( uint64_t) r- [ --enable-stats]
"stats.arenas.<i>.dss" ( const char *) r-
"stats.arenas.<i>.nthreads" ( unsigned) r-
"stats.arenas.<i>.pactive" ( size_t) r-
"stats.arenas.<i>.pdirty" ( size_t) r-
"stats.arenas.<i>.mapped" ( size_t) r- [ --enable-stats]
"stats.arenas.<i>.npurge" ( uint64_t) r- [ --enable-stats]
"stats.arenas.<i>.nmadvise" ( uint64_t) r- [ --enable-stats]
"stats.arenas.<i>.npurged" ( uint64_t) r- [ --enable-stats]
"stats.arenas.<i>.small.allocated" ( size_t) r- [ --enable-stats]
"stats.arenas.<i>.small.nmalloc" ( uint64_t) r- [ --enable-stats]
"stats.arenas.<i>.small.ndalloc" ( uint64_t) r- [ --enable-stats]
"stats.arenas.<i>.small.nrequests" ( uint64_t) r- [ --enable-stats]
"stats.arenas.<i>.large.allocated" ( size_t) r- [ --enable-stats]
"stats.arenas.<i>.large.nmalloc" ( uint64_t) r- [ --enable-stats]
"stats.arenas.<i>.large.ndalloc" ( uint64_t) r- [ --enable-stats]
"stats.arenas.<i>.large.nrequests" ( uint64_t) r- [ --enable-stats]
"stats.arenas.<i>.bins.<j>.allocated" ( size_t) r- [ --enable-stats]
"stats.arenas.<i>.bins.<j>.nmalloc" ( uint64_t) r- [ --enable-stats]
"stats.arenas.<i>.bins.<j>.ndalloc" ( uint64_t) r- [ --enable-stats]
"stats.arenas.<i>.bins.<j>.nrequests" ( uint64_t) r- [ --enable-stats]
"stats.arenas.<i>.bins.<j>.nfills" ( uint64_t) r- [ --enable-stats --enable-tcache]
"stats.arenas.<i>.bins.<j>.nflushes" ( uint64_t) r- [ --enable-stats --enable-tcache]
"stats.arenas.<i>.bins.<j>.nruns" ( uint64_t) r- [ --enable-stats]
"stats.arenas.<i>.bins.<j>.nreruns" ( uint64_t) r- [ --enable-stats]
"stats.arenas.<i>.bins.<j>.curruns" ( size_t) r- [ --enable-stats]
"stats.arenas.<i>.lruns.<j>.nmalloc" ( uint64_t) r- [ --enable-stats]
"stats.arenas.<i>.lruns.<j>.ndalloc" ( uint64_t) r- [ --enable-stats]
"stats.arenas.<i>.lruns.<j>.nrequests" ( uint64_t) r- [ --enable-stats]
"stats.arenas.<i>.lruns.<j>.curruns" ( size_t) r- [ --enable-stats]
DEBUGGING MALLOC PROBLEMS
When debugging, it is a good idea to configure/build jemalloc with the --enable-debug and --enable-fill options, and recompile the program with suitable options and symbols for debugger support. When so configured, jemalloc incorporates a wide variety of run-time assertions that catch application errors such as double-free, write-after-free, etc.Programs often accidentally depend on “uninitialized” memory actually being filled with zero bytes. Junk filling (see the "opt.junk" option) tends to expose such bugs in the form of obviously incorrect results and/or coredumps. Conversely, zero filling (see the "opt.zero" option) eliminates the symptoms of such bugs. Between these two options, it is usually possible to quickly detect, diagnose, and eliminate such bugs.
This implementation does not provide much detail about the problems it detects, because the performance impact for storing such information would be prohibitive. However, jemalloc does integrate with the most excellent Valgrind[2] tool if the --enable-valgrind configuration option is enabled.
DIAGNOSTIC MESSAGES
If any of the memory allocation/deallocation functions detect an error or warning condition, a message will be printed to file descriptor STDERR_FILENO. Errors will result in the process dumping core. If the "opt.abort" option is set, most warnings are treated as errors.The malloc_message variable allows the programmer to override the function which emits the text strings forming the errors and warnings if for some reason the STDERR_FILENO file descriptor is not suitable for this. malloc_message takes the cbopaque pointer argument that is NULL unless overridden by the arguments in a call to malloc_stats_print, followed by a string pointer. Please note that doing anything which tries to allocate memory in this function is likely to result in a crash or deadlock.
All messages are prefixed by “<jemalloc>:”.
RETURN VALUES
Standard API
The malloc and calloc functions return a pointer to the allocated memory if successful; otherwise a NULL pointer is returned and errno is set to ENOMEM.The posix_memalign function returns the value 0 if successful; otherwise it returns an error value. The posix_memalign function will fail if:
EINVAL
ENOMEM
The aligned_alloc function returns a pointer to the allocated memory if successful; otherwise a NULL pointer is returned and errno is set. The aligned_alloc function will fail if:
EINVAL
ENOMEM
The realloc function returns a pointer, possibly identical to ptr, to the allocated memory if successful; otherwise a NULL pointer is returned, and errno is set to ENOMEM if the error was the result of an allocation failure. The realloc function always leaves the original buffer intact when an error occurs.
The free function returns no value.
Non-standard API
The malloc_usable_size function returns the usable size of the allocation pointed to by ptr.The mallctl, mallctlnametomib, and mallctlbymib functions return 0 on success; otherwise they return an error value. The functions will fail if:
EINVAL
ENOMEM
ENOENT
EPERM
EAGAIN
EFAULT
Experimental API
The allocm , rallocm , sallocm , dallocm , and nallocm functions return ALLOCM_SUCCESS on success; otherwise they return an error value. The allocm , rallocm , and nallocm functions will fail if:ALLOCM_ERR_OOM
The rallocm function will also fail if:
ALLOCM_ERR_NOT_MOVED
ENVIRONMENT
The following environment variable affects the execution of the allocation functions:MALLOC_CONF
EXAMPLES
To dump core whenever a problem occurs:ln -s 'abort:true' /etc/malloc.conf
To specify in the source a chunk size that is 16 MiB:
malloc_conf = "lg_chunk:24";
SEE ALSO
madvise(2), mmap(2), sbrk(2), utrace(2), alloca(3), atexit(3), getpagesize(3)STANDARDS
The malloc , calloc , realloc , and free functions conform to ISO/IEC 9899:1990 (“ISO C90”).The posix_memalign function conforms to IEEE Std 1003.1-2001 (“POSIX.1”).
HISTORY
The malloc_usable_size and posix_memalign functions first appeared in FreeBSD 7.0.The aligned_alloc, malloc_stats_print, mallctl*, and *allocm functions first appeared in FreeBSD 10.0.
AUTHOR
Jason EvansNOTES
- 1.
- jemalloc website
- 2.
- Valgrind
- 3.
- gperftools package
06/02/2013 | jemalloc 3.4.0-0-g0ed518e5dab7 |