bytes of memory such that the allocation\*(Aqs base address is an even multiple of
bytes of memory such that the allocation\*(Aqs base address is a multiple of
\fIalignment\fR, and returns the allocation in the value pointed to by
\fIalignment\fR, and returns the allocation in the value pointed to by
\fIptr\fR\&. The requested
\fIptr\fR\&. The requested
\fIalignment\fR
\fIalignment\fR
...
@@ -129,7 +119,7 @@ The
...
@@ -129,7 +119,7 @@ The
\fBaligned_alloc\fR\fB\fR
\fBaligned_alloc\fR\fB\fR
function allocates
function allocates
\fIsize\fR
\fIsize\fR
bytes of memory such that the allocation\*(Aqs base address is an even multiple of
bytes of memory such that the allocation\*(Aqs base address is a multiple of
\fIalignment\fR\&. The requested
\fIalignment\fR\&. The requested
\fIalignment\fR
\fIalignment\fR
must be a power of 2\&. Behavior is undefined if
must be a power of 2\&. Behavior is undefined if
...
@@ -172,7 +162,8 @@ The
...
@@ -172,7 +162,8 @@ The
\fBrallocx\fR\fB\fR,
\fBrallocx\fR\fB\fR,
\fBxallocx\fR\fB\fR,
\fBxallocx\fR\fB\fR,
\fBsallocx\fR\fB\fR,
\fBsallocx\fR\fB\fR,
\fBdallocx\fR\fB\fR, and
\fBdallocx\fR\fB\fR,
\fBsdallocx\fR\fB\fR, and
\fBnallocx\fR\fB\fR
\fBnallocx\fR\fB\fR
functions all have a
functions all have a
\fIflags\fR
\fIflags\fR
...
@@ -201,11 +192,32 @@ is a power of 2\&.
...
@@ -201,11 +192,32 @@ is a power of 2\&.
Initialize newly allocated memory to contain zero bytes\&. In the growing reallocation case, the real size prior to reallocation defines the boundary between untouched bytes and those that are initialized to contain zero bytes\&. If this macro is absent, newly allocated memory is uninitialized\&.
Initialize newly allocated memory to contain zero bytes\&. In the growing reallocation case, the real size prior to reallocation defines the boundary between untouched bytes and those that are initialized to contain zero bytes\&. If this macro is absent, newly allocated memory is uninitialized\&.
.RE
.RE
.PP
.PP
\fBMALLOCX_TCACHE(\fR\fB\fItc\fR\fR\fB) \fR
.RS 4
Use the thread\-specific cache (tcache) specified by the identifier
\fItc\fR, which must have been acquired via the
"tcache\&.create"
mallctl\&. This macro does not validate that
\fItc\fR
specifies a valid identifier\&.
.RE
.PP
\fBMALLOCX_TCACHE_NONE\fR
.RS 4
Do not use a thread\-specific cache (tcache)\&. Unless
\fBMALLOCX_TCACHE(\fR\fB\fItc\fR\fR\fB)\fR
or
\fBMALLOCX_TCACHE_NONE\fR
is specified, an automatically managed tcache will be used under many circumstances\&. This macro cannot be used in the same
\fIflags\fR
argument as
\fBMALLOCX_TCACHE(\fR\fB\fItc\fR\fR\fB)\fR\&.
.RE
.PP
\fBMALLOCX_ARENA(\fR\fB\fIa\fR\fR\fB) \fR
\fBMALLOCX_ARENA(\fR\fB\fIa\fR\fR\fB) \fR
.RS 4
.RS 4
Use the arena specified by the index
Use the arena specified by the index
\fIa\fR
\fIa\fR\&. This macro has no effect for regions that were allocated via an arena other than the one specified\&. This macro does not validate that
(and by necessity bypass the thread cache)\&. This macro has no effect for huge regions, nor for regions that were allocated via an arena other than the one specified\&. This macro does not validate that
\fIa\fR
\fIa\fR
specifies an arena index in the valid range\&.
specifies an arena index in the valid range\&.
.RE
.RE
...
@@ -258,6 +270,17 @@ function causes the memory referenced by
...
@@ -258,6 +270,17 @@ function causes the memory referenced by
to be made available for future allocations\&.
to be made available for future allocations\&.
.PP
.PP
The
The
\fBsdallocx\fR\fB\fR
function is an extension of
\fBdallocx\fR\fB\fR
with a
\fIsize\fR
parameter to allow the caller to pass in the allocation size as an optimization\&. The minimum valid input size is the original requested size of the allocation, and the maximum valid input size is the corresponding value returned by
\fBnallocx\fR\fB\fR
or
\fBsallocx\fR\fB\fR\&.
.PP
The
\fBnallocx\fR\fB\fR
\fBnallocx\fR\fB\fR
function allocates no memory, but it performs the same size computation as the
function allocates no memory, but it performs the same size computation as the
\fBmallocx\fR\fB\fR
\fBmallocx\fR\fB\fR
...
@@ -351,7 +374,7 @@ uses the
...
@@ -351,7 +374,7 @@ uses the
\fBmallctl*\fR\fB\fR
\fBmallctl*\fR\fB\fR
functions internally, so inconsistent statistics can be reported if multiple threads use these functions simultaneously\&. If
functions internally, so inconsistent statistics can be reported if multiple threads use these functions simultaneously\&. If
\fB\-\-enable\-stats\fR
\fB\-\-enable\-stats\fR
is specified during configuration, \(lqm\(rq and \(lqa\(rq can be specified to omit merged arena and per arena statistics, respectively; \(lqb\(rq and \(lql\(rq 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\&.
is specified during configuration, \(lqm\(rq and \(lqa\(rq can be specified to omit merged arena and per arena statistics, respectively; \(lqb\(rq, \(lql\(rq, and \(lqh\(rq can be specified to omit per size class statistics for bins, large objects, and huge 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\&.
.PP
.PP
The
The
\fBmalloc_usable_size\fR\fB\fR
\fBmalloc_usable_size\fR\fB\fR
...
@@ -362,126 +385,6 @@ function is not a mechanism for in\-place
...
@@ -362,126 +385,6 @@ function is not a mechanism for in\-place
\fBrealloc\fR\fB\fR; rather it is provided solely as a tool for introspection purposes\&. Any discrepancy between the requested allocation size and the size reported by
\fBrealloc\fR\fB\fR; rather it is provided solely as a tool for introspection purposes\&. Any discrepancy between the requested allocation size and the size reported by
\fBmalloc_usable_size\fR\fB\fR
\fBmalloc_usable_size\fR\fB\fR
should not be depended on, since such behavior is entirely implementation\-dependent\&.
should not be depended on, since such behavior is entirely implementation\-dependent\&.
.SS "Experimental API"
.PP
The experimental API is subject to change or removal without regard for backward compatibility\&. If
\fB\-\-disable\-experimental\fR
is specified during configuration, the experimental API is omitted\&.
.PP
The
\fBallocm\fR\fB\fR,
\fBrallocm\fR\fB\fR,
\fBsallocm\fR\fB\fR,
\fBdallocm\fR\fB\fR, and
\fBnallocm\fR\fB\fR
functions all have a
\fIflags\fR
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:
.PP
\fBALLOCM_LG_ALIGN(\fR\fB\fIla\fR\fR\fB) \fR
.RS 4
Align the memory allocation to start at an address that is a multiple of
(1 << \fIla\fR)\&. This macro does not validate that
\fIla\fR
is within the valid range\&.
.RE
.PP
\fBALLOCM_ALIGN(\fR\fB\fIa\fR\fR\fB) \fR
.RS 4
Align the memory allocation to start at an address that is a multiple of
\fIa\fR, where
\fIa\fR
is a power of two\&. This macro does not validate that
\fIa\fR
is a power of 2\&.
.RE
.PP
\fBALLOCM_ZERO\fR
.RS 4
Initialize newly allocated memory to contain zero bytes\&. In the growing reallocation case, the real size prior to reallocation defines the boundary between untouched bytes and those that are initialized to contain zero bytes\&. If this macro is absent, newly allocated memory is uninitialized\&.
.RE
.PP
\fBALLOCM_NO_MOVE\fR
.RS 4
For reallocation, fail rather than moving the object\&. This constraint can apply to both growth and shrinkage\&.
.RE
.PP
\fBALLOCM_ARENA(\fR\fB\fIa\fR\fR\fB) \fR
.RS 4
Use the arena specified by the index
\fIa\fR
(and by necessity bypass the thread cache)\&. This macro has no effect for huge regions, nor for regions that were allocated via an arena other than the one specified\&. This macro does not validate that
\fIa\fR
specifies an arena index in the valid range\&.
.RE
.PP
The
\fBallocm\fR\fB\fR
function allocates at least
\fIsize\fR
bytes of memory, sets
\fI*ptr\fR
to the base address of the allocation, and sets
\fI*rsize\fR
to the real size of the allocation if
\fIrsize\fR
is not
\fBNULL\fR\&. Behavior is undefined if
\fIsize\fR
is
\fB0\fR, or if request size overflows due to size class and/or alignment constraints\&.
.PP
The
\fBrallocm\fR\fB\fR
function resizes the allocation at
\fI*ptr\fR
to be at least
\fIsize\fR
bytes, sets
\fI*ptr\fR
to the base address of the allocation if it moved, and sets
\fI*rsize\fR
to the real size of the allocation if
\fIrsize\fR
is not
\fBNULL\fR\&. If
\fIextra\fR
is non\-zero, an attempt is made to resize the allocation to be at least
(\fIsize\fR + \fIextra\fR)
bytes, though inability to allocate the extra byte(s) will not by itself result in failure\&. Behavior is undefined if
\fIsize\fR
is
\fB0\fR, if request size overflows due to size class and/or alignment constraints, or if
(\fIsize\fR + \fIextra\fR > \fBSIZE_T_MAX\fR)\&.
.PP
The
\fBsallocm\fR\fB\fR
function sets
\fI*rsize\fR
to the real size of the allocation\&.
.PP
The
\fBdallocm\fR\fB\fR
function causes the memory referenced by
\fIptr\fR
to be made available for future allocations\&.
.PP
The
\fBnallocm\fR\fB\fR
function allocates no memory, but it performs the same size computation as the
\fBallocm\fR\fB\fR
function, and if
\fIrsize\fR
is not
\fBNULL\fR
it sets
\fI*rsize\fR
to the real size of the allocation that would result from the equivalent
\fBallocm\fR\fB\fR
function call\&. Behavior is undefined if
\fIsize\fR
is
\fB0\fR, or if request size overflows due to size class and/or alignment constraints\&.
.SH "TUNING"
.SH "TUNING"
.PP
.PP
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\&.
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\&.
...
@@ -519,8 +422,8 @@ options\&. Some options have boolean values (true/false), others have integer va
...
@@ -519,8 +422,8 @@ options\&. Some options have boolean values (true/false), others have integer va
Traditionally, allocators have used
Traditionally, allocators have used
\fBsbrk\fR(2)
\fBsbrk\fR(2)
to obtain memory, which is suboptimal for several reasons, including race conditions, increased fragmentation, and artificial limitations on maximum usable memory\&. If
to obtain memory, which is suboptimal for several reasons, including race conditions, increased fragmentation, and artificial limitations on maximum usable memory\&. If
\fB\-\-enable\-dss\fR
\fBsbrk\fR(2)
is specified during configuration, this allocator uses both
is supported by the operating system, this allocator uses both
\fBmmap\fR(2)
\fBmmap\fR(2)
and
and
\fBsbrk\fR(2), in that order of preference; otherwise only
\fBsbrk\fR(2), in that order of preference; otherwise only
...
@@ -535,18 +438,29 @@ is specified during configuration, this allocator supports thread\-specific cach
...
@@ -535,18 +438,29 @@ is specified during configuration, this allocator supports thread\-specific cach
.PP
.PP
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\&.
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\&.
.PP
.PP
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\&.
User objects are broken into three categories according to size: small, large, and huge\&. Small and large objects are managed entirely by arenas; huge objects are additionally aggregated in a single data structure that is shared by all threads\&. Huge objects are typically used by applications infrequently enough that this single data structure is not a scalability issue\&.
.PP
.PP
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\&.
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\&.
.PP
.PP
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
Small objects are managed in groups by page runs\&. Each run maintains a bitmap 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(\fBdouble\fR)\&. 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
sizeof(\fBdouble\fR)\&. All other object size classes are multiples of the quantum, spaced such that there are four size classes for each doubling in size, which limits internal fragmentation to approximately 20% for all but the smallest size classes\&. Small size classes are smaller than four times the page size, large size classes are smaller than the chunk size (see the
"opt\&.lg_chunk"
"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\&.
option), and huge size classes extend from the chunk size up to one size class less than the full address space size\&.
.PP
.PP
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\&.
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\&.
.PP
.PP
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
The
\fBrealloc\fR\fB\fR,
\fBrallocx\fR\fB\fR, and
\fBxallocx\fR\fB\fR
functions may resize allocations without moving them under limited circumstances\&. Unlike the
\fB*allocx\fR\fB\fR
API, the standard API does not officially round up the usable size of an allocation to the nearest size class, so technically it is necessary to call
\fBrealloc\fR\fB\fR
to grow e\&.g\&. a 9\-byte allocation to 16 bytes, or shrink a 16\-byte allocation to 9 bytes\&. Growth and shrinkage trivially succeeds in place as long as the pre\-size and post\-size both round up to the same size class\&. No other API guarantees are made regarding in\-place resizing, but the current implementation also tries to resize large and huge allocations in place, as long as the pre\-size and post\-size are both large or both huge\&. In such cases shrinkage always succeeds for large size classes, but for huge size classes the chunk allocator must support splitting (see
"arena\&.<i>\&.chunk_hooks")\&. Growth only succeeds if the trailing memory is currently available, and additionally for huge size classes the chunk allocator must support merging\&.
.PP
Assuming 2 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\&.
.sp
.sp
.it 1 an-trap
.it 1 an-trap
...
@@ -572,8 +486,23 @@ l r l
...
@@ -572,8 +486,23 @@ l r l
^ r l
^ r l
^ r l
^ r l
^ r l
^ r l
^ r l
^ r l
l r l
l r l
l r l.
^ r l
^ r l
^ r l
^ r l
^ r l
^ r l
^ r l
l r l
^ r l
^ r l
^ r l
^ r l
^ r l
^ r l.
T{
T{
Small
Small
T}:T{
T}:T{
...
@@ -584,7 +513,7 @@ T}
...
@@ -584,7 +513,7 @@ T}
:T{
:T{
16
16
T}:T{
T}:T{
[16, 32, 48, \&.\&.\&., 128]
[16, 32, 48, 64, 80, 96, 112, 128]
T}
T}
:T{
:T{
32
32
...
@@ -609,21 +538,96 @@ T}
...
@@ -609,21 +538,96 @@ T}
:T{
:T{
512
512
T}:T{
T}:T{
[2560, 3072, 3584]
[2560, 3072, 3584, 4096]
T}
:T{
1 KiB
T}:T{
[5 KiB, 6 KiB, 7 KiB, 8 KiB]
T}
:T{
2 KiB
T}:T{
[10 KiB, 12 KiB, 14 KiB]
T}
T}
T{
T{
Large
Large
T}:T{
T}:T{
2 KiB
T}:T{
[16 KiB]
T}
:T{
4 KiB
4 KiB
T}:T{
T}:T{
[4 KiB, 8 KiB, 12 KiB, \&.\&.\&., 4072 KiB]
[20 KiB, 24 KiB, 28 KiB, 32 KiB]
T}
:T{
8 KiB
T}:T{
[40 KiB, 48 KiB, 54 KiB, 64 KiB]
T}
:T{
16 KiB
T}:T{
[80 KiB, 96 KiB, 112 KiB, 128 KiB]
T}
:T{
32 KiB
T}:T{
[160 KiB, 192 KiB, 224 KiB, 256 KiB]
T}
:T{
64 KiB
T}:T{
[320 KiB, 384 KiB, 448 KiB, 512 KiB]
T}
:T{
128 KiB
T}:T{
[640 KiB, 768 KiB, 896 KiB, 1 MiB]
T}
:T{
256 KiB
T}:T{
[1280 KiB, 1536 KiB, 1792 KiB]
T}
T}
T{
T{
Huge
Huge
T}:T{
T}:T{
256 KiB
T}:T{
[2 MiB]
T}
:T{
512 KiB
T}:T{
[2560 KiB, 3 MiB, 3584 KiB, 4 MiB]
T}
:T{
1 MiB
T}:T{
[5 MiB, 6 MiB, 7 MiB, 8 MiB]
T}
:T{
2 MiB
T}:T{
[10 MiB, 12 MiB, 14 MiB, 16 MiB]
T}
:T{
4 MiB
4 MiB
T}:T{
T}:T{
[4 MiB, 8 MiB, 12 MiB, \&.\&.\&.]
[20 MiB, 24 MiB, 28 MiB, 32 MiB]
T}
:T{
8 MiB
T}:T{
[40 MiB, 48 MiB, 56 MiB, 64 MiB]
T}
:T{
\&.\&.\&.
T}:T{
\&.\&.\&.
T}
T}
.TE
.TE
.sp 1
.sp 1
...
@@ -660,15 +664,15 @@ If a value is passed in, refresh the data from which the
...
@@ -660,15 +664,15 @@ If a value is passed in, refresh the data from which the
functions report values, and increment the epoch\&. Return the current epoch\&. This is useful for detecting whether another thread caused a refresh\&.
functions report values, and increment the epoch\&. Return the current epoch\&. This is useful for detecting whether another thread caused a refresh\&.
.RE
.RE
.PP
.PP
"config\&.debug" (\fBbool\fR) r\-
"config\&.cache_oblivious" (\fBbool\fR) r\-
.RS 4
.RS 4
\fB\-\-enable\-debug\fR
\fB\-\-enable\-cache\-oblivious\fR
was specified during build configuration\&.
was specified during build configuration\&.
.RE
.RE
.PP
.PP
"config\&.dss" (\fBbool\fR) r\-
"config\&.debug" (\fBbool\fR) r\-
.RS 4
.RS 4
\fB\-\-enable\-dss\fR
\fB\-\-enable\-debug\fR
was specified during build configuration\&.
was specified during build configuration\&.
.RE
.RE
.PP
.PP
...
@@ -684,12 +688,6 @@ was specified during build configuration\&.
...
@@ -684,12 +688,6 @@ was specified during build configuration\&.
was specified during build configuration\&.
was specified during build configuration\&.
.RE
.RE
.PP
.PP
"config\&.mremap" (\fBbool\fR) r\-
.RS 4
\fB\-\-enable\-mremap\fR
was specified during build configuration\&.
.RE
.PP
"config\&.munmap" (\fBbool\fR) r\-
"config\&.munmap" (\fBbool\fR) r\-
.RS 4
.RS 4
\fB\-\-enable\-munmap\fR
\fB\-\-enable\-munmap\fR
...
@@ -763,14 +761,16 @@ is specified during configuration, in which case it is enabled by default\&.
...
@@ -763,14 +761,16 @@ is specified during configuration, in which case it is enabled by default\&.
.RS 4
.RS 4
dss (\fBsbrk\fR(2)) allocation precedence as related to
dss (\fBsbrk\fR(2)) allocation precedence as related to
\fBmmap\fR(2)
\fBmmap\fR(2)
allocation\&. The following settings are supported: \(lqdisabled\(rq, \(lqprimary\(rq, and \(lqsecondary\(rq\&. The default is \(lqsecondary\(rq if
allocation\&. The following settings are supported if
"config\&.dss"
\fBsbrk\fR(2)
is true, \(lqdisabled\(rq otherwise\&.
is supported by the operating system: \(lqdisabled\(rq, \(lqprimary\(rq, and \(lqsecondary\(rq; otherwise only \(lqdisabled\(rq is supported\&. The default is \(lqsecondary\(rq if
\fBsbrk\fR(2)
is supported by the operating system; \(lqdisabled\(rq otherwise\&.
.RE
.RE
.PP
.PP
"opt\&.lg_chunk" (\fBsize_t\fR) r\-
"opt\&.lg_chunk" (\fBsize_t\fR) r\-
.RS 4
.RS 4
Virtual memory chunk size (log base 2)\&. If a chunk size outside the supported size range is specified, the size is silently clipped to the minimum/maximum supported size\&. The default chunk size is 4 MiB (2^22)\&.
Virtual memory chunk size (log base 2)\&. If a chunk size outside the supported size range is specified, the size is silently clipped to the minimum/maximum supported size\&. The default chunk size is 2 MiB (2^21)\&.
.RE
.RE
.PP
.PP
"opt\&.narenas" (\fBsize_t\fR) r\-
"opt\&.narenas" (\fBsize_t\fR) r\-
...
@@ -782,7 +782,11 @@ Maximum number of arenas to use for automatic multiplexing of threads and arenas
...
@@ -782,7 +782,11 @@ Maximum number of arenas to use for automatic multiplexing of threads and arenas
.RS 4
.RS 4
Per\-arena minimum ratio (log base 2) of active to dirty pages\&. Some dirty unused pages may be allowed to accumulate, within the limit set by the ratio (or one chunk worth of dirty pages, whichever is greater), before informing the kernel about some of those pages via
Per\-arena minimum ratio (log base 2) of active to dirty pages\&. Some dirty unused pages may be allowed to accumulate, within the limit set by the ratio (or one chunk worth of dirty pages, whichever is greater), before informing the kernel about some of those pages via
\fBmadvise\fR(2)
\fBmadvise\fR(2)
or a similar system call\&. This provides the kernel with sufficient information to recycle dirty pages if physical memory becomes scarce and the pages remain unused\&. The default minimum ratio is 8:1 (2^3:1); an option value of \-1 will disable dirty page purging\&.
or a similar system call\&. This provides the kernel with sufficient information to recycle dirty pages if physical memory becomes scarce and the pages remain unused\&. The default minimum ratio is 8:1 (2^3:1); an option value of \-1 will disable dirty page purging\&. See
"arenas\&.lg_dirty_mult"
and
"arena\&.<i>\&.lg_dirty_mult"
for related dynamic control options\&.
.RE
.RE
.PP
.PP
"opt\&.stats_print" (\fBbool\fR) r\-
"opt\&.stats_print" (\fBbool\fR) r\-
...
@@ -793,16 +797,21 @@ function is called at program exit via an
...
@@ -793,16 +797,21 @@ function is called at program exit via an
\fBatexit\fR(3)
\fBatexit\fR(3)
function\&. If
function\&. If
\fB\-\-enable\-stats\fR
\fB\-\-enable\-stats\fR
is specified during configuration, this has the potential to cause deadlock for a multi\-threaded process that exits while one or more threads are executing in the memory allocation functions\&. Therefore, this option should only be used with care; it is primarily intended as a performance tuning aid during application development\&. This option is disabled by default\&.
is specified during configuration, this has the potential to cause deadlock for a multi\-threaded process that exits while one or more threads are executing in the memory allocation functions\&. Furthermore,
\fBatexit\fR\fB\fR
may allocate memory during application initialization and then deadlock internally when jemalloc in turn calls
\fBatexit\fR\fB\fR, so this option is not univerally usable (though the application can register its own
\fBatexit\fR\fB\fR
function with equivalent functionality)\&. Therefore, this option should only be used with care; it is primarily intended as a performance tuning aid during application development\&. This option is disabled by default\&.
Junk filling enabled/disabled\&. If enabled, each byte of uninitialized allocated memory will be initialized to
Junk filling\&. If set to "alloc", each byte of uninitialized allocated memory will be initialized to
0xa5\&. All deallocated memory will be initialized to
0xa5\&. If set to "free", all deallocated memory will be initialized to
0x5a\&. This is intended for debugging and will impact performance negatively\&. This option is disabled by default unless
0x5a\&. If set to "true", both allocated and deallocated memory will be initialized, and if set to "false", junk filling be disabled entirely\&. This is intended for debugging and will impact performance negatively\&. This option is "false" by default unless
\fB\-\-enable\-debug\fR
\fB\-\-enable\-debug\fR
is specified during configuration, in which case it is enabled by default unless running inside
is specified during configuration, in which case it is "true" by default unless running inside
\m[blue]\fBValgrind\fR\m[]\&\s-2\u[2]\d\s+2\&.
\m[blue]\fBValgrind\fR\m[]\&\s-2\u[2]\d\s+2\&.
.RE
.RE
.PP
.PP
...
@@ -825,10 +834,9 @@ option is enabled, the redzones are checked for corruption during deallocation\&
...
@@ -825,10 +834,9 @@ option is enabled, the redzones are checked for corruption during deallocation\&
Zero filling enabled/disabled\&. If enabled, each byte of uninitialized allocated memory will be initialized to 0\&. Note that this initialization only happens once for each byte, so
Zero filling enabled/disabled\&. If enabled, each byte of uninitialized allocated memory will be initialized to 0\&. Note that this initialization only happens once for each byte, so
\fBrealloc\fR\fB\fR,
\fBrealloc\fR\fB\fR
\fBrallocx\fR\fB\fR
and
and
\fBrallocm\fR\fB\fR
\fBrallocx\fR\fB\fR
calls do not zero memory that was previously allocated\&. This is intended for debugging and will impact performance negatively\&. This option is disabled by default\&.
calls do not zero memory that was previously allocated\&. This is intended for debugging and will impact performance negatively\&. This option is disabled by default\&.
.RE
.RE
.PP
.PP
...
@@ -839,12 +847,6 @@ Allocation tracing based on
...
@@ -839,12 +847,6 @@ Allocation tracing based on
enabled/disabled\&. This option is disabled by default\&.
enabled/disabled\&. This option is disabled by default\&.
support enabled/disabled\&. This option is vestigal because jemalloc auto\-detects whether it is running inside Valgrind\&. This option is disabled by default, unless running inside Valgrind\&.
Thread\-specific caching enabled/disabled\&. When there are multiple threads, each thread uses a thread\-specific cache for objects up to a certain size\&. Thread\-specific caching allows many allocations to be satisfied without performing any thread synchronization, at the cost of increased memory use\&. See the
Thread\-specific caching (tcache) enabled/disabled\&. When there are multiple threads, each thread uses a tcache for objects up to a certain size\&. Thread\-specific caching allows many allocations to be satisfied without performing any thread synchronization, at the cost of increased memory use\&. See the
"opt\&.lg_tcache_max"
"opt\&.lg_tcache_max"
option for related tuning information\&. This option is enabled by default unless running inside
option for related tuning information\&. This option is enabled by default unless running inside
\m[blue]\fBValgrind\fR\m[]\&\s-2\u[2]\d\s+2\&.
\m[blue]\fBValgrind\fR\m[]\&\s-2\u[2]\d\s+2, in which case it is forcefully disabled\&.
Maximum size class (log base 2) to cache in the thread\-specific cache\&. At a minimum, all small size classes are cached, and at a maximum all large size classes are cached\&. The default maximum is 32 KiB (2^15)\&.
Maximum size class (log base 2) to cache in the thread\-specific cache (tcache)\&. At a minimum, all small size classes are cached, and at a maximum all large size classes are cached\&. The default maximum is 32 KiB (2^15)\&.
Profiling activated/deactivated\&. This is a secondary control mechanism that makes it possible to start the application with profiling enabled (see the
Profiling activated/deactivated\&. This is a secondary control mechanism that makes it possible to start the application with profiling enabled (see the
"opt\&.prof"
"opt\&.prof"
...
@@ -913,7 +917,16 @@ option) but inactive, then toggle profiling at any time during program execution
...
@@ -913,7 +917,16 @@ option) but inactive, then toggle profiling at any time during program execution
Average interval (log base 2) between allocation samples, as measured in bytes of allocation activity\&. Increasing the sampling interval decreases profile fidelity, but also decreases the computational overhead\&. The default sample interval is 512 KiB (2^19 B)\&.
Average interval (log base 2) between allocation samples, as measured in bytes of allocation activity\&. Increasing the sampling interval decreases profile fidelity, but also decreases the computational overhead\&. The default sample interval is 512 KiB (2^19 B)\&.
.RE
.RE
...
@@ -935,12 +948,8 @@ option\&. By default, interval\-triggered profile dumping is disabled (encoded a
...
@@ -935,12 +948,8 @@ option\&. By default, interval\-triggered profile dumping is disabled (encoded a
Trigger a memory profile dump every time the total virtual memory exceeds the previous maximum\&. Profiles are dumped to files named according to the pattern
Set the initial state of
<prefix>\&.<pid>\&.<seq>\&.u<useq>\&.heap, where
"prof\&.gdump", which when enabled triggers a memory profile dump every time the total virtual memory exceeds the previous maximum\&. This option is disabled by default\&.
Flush calling thread\*(Aqs tcache\&. This interface releases all cached objects and internal data structures associated with the calling thread\*(Aqs thread\-specific cache\&. Ordinarily, this interface need not be called, since automatic periodic incremental garbage collection occurs, and the thread cache is automatically discarded when a thread exits\&. However, garbage collection is triggered by allocation activity, so it is possible for a thread that stops allocating/deallocating to retain its cache indefinitely, in which case the developer may find manual flushing useful\&.
Flush calling thread\*(Aqs thread\-specific cache (tcache)\&. This interface releases all cached objects and internal data structures associated with the calling thread\*(Aqs tcache\&. Ordinarily, this interface need not be called, since automatic periodic incremental garbage collection occurs, and the thread cache is automatically discarded when a thread exits\&. However, garbage collection is triggered by allocation activity, so it is possible for a thread that stops allocating/deallocating to retain its cache indefinitely, in which case the developer may find manual flushing useful\&.
.RE
.PP
"thread\&.prof\&.name" (\fBconst char *\fR) r\- or \-w [\fB\-\-enable\-prof\fR]
.RS 4
Get/set the descriptive name associated with the calling thread in memory profile dumps\&. An internal copy of the name string is created, so the input string need not be maintained after this interface completes execution\&. The output string of this interface should be copied for non\-ephemeral uses, because multiple implementation details can cause asynchronous string deallocation\&. Furthermore, each invocation of this interface can only read or write; simultaneous read/write is not supported due to string lifetime limitations\&. The name string must nil\-terminated and comprised only of characters in the sets recognized by
Create an explicit thread\-specific cache (tcache) and return an identifier that can be passed to the
\fBMALLOCX_TCACHE(\fR\fB\fItc\fR\fR\fB)\fR
macro to explicitly use the specified cache rather than the automatically managed one that is used by default\&. Each explicit cache can be used by only one thread at a time; the application must assure that this constraint holds\&.
Flush the specified thread\-specific cache (tcache) and make the identifier available for use during a future tcache creation\&.
.RE
.PP
"arena\&.<i>\&.purge" (\fBvoid\fR) \-\-
.RS 4
.RS 4
Purge unused dirty pages for arena <i>, or for all arenas if <i> equals
Purge unused dirty pages for arena <i>, or for all arenas if <i> equals
"arenas\&.narenas"\&.
"arenas\&.narenas"\&.
...
@@ -1019,11 +1065,237 @@ Purge unused dirty pages for arena <i>, or for all arenas if <i> equals
...
@@ -1019,11 +1065,237 @@ Purge unused dirty pages for arena <i>, or for all arenas if <i> equals
"arena\&.<i>\&.dss" (\fBconst char *\fR) rw
"arena\&.<i>\&.dss" (\fBconst char *\fR) rw
.RS 4
.RS 4
Set the precedence of dss allocation as related to mmap allocation for arena <i>, or for all arenas if <i> equals
Set the precedence of dss allocation as related to mmap allocation for arena <i>, or for all arenas if <i> equals
"arenas\&.narenas"\&. Note that even during huge allocation this setting is read from the arena that would be chosen for small or large allocation so that applications can depend on consistent dss versus mmap allocation regardless of allocation size\&. See
"arenas\&.narenas"\&. See
"opt\&.dss"
"opt\&.dss"
for supported settings\&.
for supported settings\&.
.RE
.RE
.PP
.PP
"arena\&.<i>\&.lg_dirty_mult" (\fBssize_t\fR) rw
.RS 4
Current per\-arena minimum ratio (log base 2) of active to dirty pages for arena <i>\&. Each time this interface is set and the ratio is increased, pages are synchronously purged as necessary to impose the new ratio\&. See
Get or set the chunk management hook functions for arena <i>\&. The functions must be capable of operating on all extant chunks associated with arena <i>, usually by passing unknown chunks to the replaced functions\&. In practice, it is feasible to control allocation for arenas created via
"arenas\&.extend"
such that all chunks originate from an application\-supplied chunk allocator (by setting custom chunk hook functions just after arena creation), but the automatically created arenas may have already created chunks prior to the application having an opportunity to take over chunk allocation\&.
.sp
.if n \{\
.RS 4
.\}
.nf
typedef struct {
chunk_alloc_t *alloc;
chunk_dalloc_t *dalloc;
chunk_commit_t *commit;
chunk_decommit_t *decommit;
chunk_purge_t *purge;
chunk_split_t *split;
chunk_merge_t *merge;
} chunk_hooks_t;
.fi
.if n \{\
.RE
.\}
.sp
The
\fBchunk_hooks_t\fR
structure comprises function pointers which are described individually below\&. jemalloc uses these functions to manage chunk lifetime, which starts off with allocation of mapped committed memory, in the simplest case followed by deallocation\&. However, there are performance and platform reasons to retain chunks for later reuse\&. Cleanup attempts cascade from deallocation to decommit to purging, which gives the chunk management functions opportunities to reject the most permanent cleanup operations in favor of less permanent (and often less costly) operations\&. The chunk splitting and merging operations can also be opted out of, but this is mainly intended to support platforms on which virtual memory mappings provided by the operating system kernel do not automatically coalesce and split, e\&.g\&. Windows\&.
such that the chunk\*(Aqs base address is a multiple of
\fIalignment\fR, as well as setting
\fI*zero\fR
to indicate whether the chunk is zeroed and
\fI*commit\fR
to indicate whether the chunk is committed\&. Upon error the function returns
\fBNULL\fR
and leaves
\fI*zero\fR
and
\fI*commit\fR
unmodified\&. The
\fIsize\fR
parameter is always a multiple of the chunk size\&. The
\fIalignment\fR
parameter is always a power of two at least as large as the chunk size\&. Zeroing is mandatory if
\fI*zero\fR
is true upon function entry\&. Committing is mandatory if
\fI*commit\fR
is true upon function entry\&. If
\fIchunk\fR
is not
\fBNULL\fR, the returned pointer must be
\fIchunk\fR
on success or
\fBNULL\fR
on error\&. Committed memory may be committed in absolute terms as on a system that does not overcommit, or in implicit terms as on a system that overcommits and satisfies physical memory needs on demand via soft page faults\&. Note that replacing the default chunk allocation function makes the arena\*(Aqs
\fIcommitted\fR/decommited memory as indicated, on behalf of arena
\fIarena_ind\fR, returning false upon success\&. If the function returns true, this indicates opt\-out from deallocation; the virtual memory mapping associated with the chunk remains mapped, in the same commit state, and available for future use, in which case it will be automatically retained for later reuse\&.
type and commits zeroed physical memory to back pages within a
\fIchunk\fR
of given
\fIsize\fR
at
\fIoffset\fR
bytes, extending for
\fIlength\fR
on behalf of arena
\fIarena_ind\fR, returning false upon success\&. Committed memory may be committed in absolute terms as on a system that does not overcommit, or in implicit terms as on a system that overcommits and satisfies physical memory needs on demand via soft page faults\&. If the function returns true, this indicates insufficient physical memory to satisfy the request\&.
type and decommits any physical memory that is backing pages within a
\fIchunk\fR
of given
\fIsize\fR
at
\fIoffset\fR
bytes, extending for
\fIlength\fR
on behalf of arena
\fIarena_ind\fR, returning false upon success, in which case the pages will be committed via the chunk commit function before being reused\&. If the function returns true, this indicates opt\-out from decommit; the memory remains committed and available for future use, in which case it will be automatically retained for later reuse\&.
\fIcommitted\fR/decommitted memory as indicated, on behalf of arena
\fIarena_ind\fR, returning false upon success\&. If the function returns true, this indicates that the chunk remains unsplit and therefore should continue to be operated on as a whole\&.
\fIcommitted\fR/decommitted memory as indicated, on behalf of arena
\fIarena_ind\fR, returning false upon success\&. If the function returns true, this indicates that the chunks remain distinct mappings and therefore should continue to be operated on independently\&.
.RE
.PP
"arenas\&.narenas" (\fBunsigned\fR) r\-
"arenas\&.narenas" (\fBunsigned\fR) r\-
.RS 4
.RS 4
Current limit on number of arenas\&.
Current limit on number of arenas\&.
...
@@ -1036,6 +1308,15 @@ An array of
...
@@ -1036,6 +1308,15 @@ An array of
booleans\&. Each boolean indicates whether the corresponding arena is initialized\&.
booleans\&. Each boolean indicates whether the corresponding arena is initialized\&.
.RE
.RE
.PP
.PP
"arenas\&.lg_dirty_mult" (\fBssize_t\fR) rw
.RS 4
Current default per\-arena minimum ratio (log base 2) of active to dirty pages, used to initialize
"arena\&.<i>\&.lg_dirty_mult"
during arena creation\&. See
"opt\&.lg_dirty_mult"
for additional information\&.
.RE
.PP
"arenas\&.quantum" (\fBsize_t\fR) r\-
"arenas\&.quantum" (\fBsize_t\fR) r\-
.RS 4
.RS 4
Quantum size\&.
Quantum size\&.
...
@@ -1076,7 +1357,7 @@ Number of regions per page run\&.
...
@@ -1076,7 +1357,7 @@ Number of regions per page run\&.
Number of bytes per page run\&.
Number of bytes per page run\&.
.RE
.RE
.PP
.PP
"arenas\&.nlruns" (\fBsize_t\fR) r\-
"arenas\&.nlruns" (\fBunsigned\fR) r\-
.RS 4
.RS 4
Total number of large size classes\&.
Total number of large size classes\&.
.RE
.RE
...
@@ -1086,9 +1367,14 @@ Total number of large size classes\&.
...
@@ -1086,9 +1367,14 @@ Total number of large size classes\&.
Maximum size supported by this large size class\&.
Maximum size supported by this large size class\&.
.RE
.RE
.PP
.PP
"arenas\&.purge" (\fBunsigned\fR) \-w
"arenas\&.nhchunks" (\fBunsigned\fR) r\-
.RS 4
Total number of huge size classes\&.
.RE
.PP
"arenas\&.hchunk\&.<i>\&.size" (\fBsize_t\fR) r\-
.RS 4
.RS 4
Purge unused dirty pages for the specified arena, or for all arenas if none is specified\&.
Maximum size supported by this huge size class\&.
.RE
.RE
.PP
.PP
"arenas\&.extend" (\fBunsigned\fR) r\-
"arenas\&.extend" (\fBunsigned\fR) r\-
...
@@ -1096,11 +1382,22 @@ Purge unused dirty pages for the specified arena, or for all arenas if none is s
...
@@ -1096,11 +1382,22 @@ Purge unused dirty pages for the specified arena, or for all arenas if none is s
Extend the array of arenas by appending a new arena, and returning the new arena index\&.
Extend the array of arenas by appending a new arena, and returning the new arena index\&.
When enabled, trigger a memory profile dump every time the total virtual memory exceeds the previous maximum\&. Profiles are dumped to files named according to the pattern
Pointer to a counter that contains an approximate count of the current number of bytes in active pages\&. The estimate may be high, but never low, because each arena rounds up to the nearest multiple of the chunk size when computing its contribution to the counter\&. Note that the
Pointer to a counter that contains an approximate count of the current number of bytes in active pages\&. The estimate may be high, but never low, because each arena rounds up when computing its contribution to the counter\&. Note that the
"epoch"
"epoch"
mallctl has no bearing on this counter\&. Furthermore, counter consistency is maintained via atomic operations, so it is necessary to use an atomic operation in order to guarantee a consistent read when dereferencing the pointer\&.
mallctl has no bearing on this counter\&. Furthermore, counter consistency is maintained via atomic operations, so it is necessary to use an atomic operation in order to guarantee a consistent read when dereferencing the pointer\&.
.RE
.RE
...
@@ -1136,44 +1457,27 @@ Total number of bytes allocated by the application\&.
...
@@ -1136,44 +1457,27 @@ Total number of bytes allocated by the application\&.
.RS 4
.RS 4
Total number of bytes in active pages allocated by the application\&. This is a multiple of the page size, and greater than or equal to
Total number of bytes in active pages allocated by the application\&. This is a multiple of the page size, and greater than or equal to
"stats\&.allocated"\&. This does not include
"stats\&.allocated"\&. This does not include
"stats\&.arenas\&.<i>\&.pdirty"
"stats\&.arenas\&.<i>\&.pdirty", nor pages entirely devoted to allocator metadata\&.
and pages entirely devoted to allocator metadata\&.
Number of bytes currently allocated by huge objects\&.
Total number of bytes dedicated to metadata, which comprise base allocations used for bootstrap\-sensitive internal allocator data structures, arena chunk headers (see
"stats\&.arenas\&.<i>\&.metadata\&.mapped"), and internal allocations (see
Maximum number of bytes in physically resident data pages mapped by the allocator, comprising all pages dedicated to allocator metadata, pages backing active allocations, and unused dirty pages\&. This is a maximum rather than precise because pages may not actually be physically resident if they correspond to demand\-zeroed virtual memory that has not yet been touched\&. This is a multiple of the page size, and is larger than
Cumulative number of huge deallocation requests\&.
Total number of bytes in active chunks mapped by the allocator\&. This is a multiple of the chunk size, and is larger than
"stats\&.active"\&. This does not include inactive chunks, even those that contain unused dirty pages, which means that there is no strict ordering between this and
Number of bytes dedicated to internal allocations\&. Internal allocations differ from application\-originated allocations in that they are for internal use, and that they are omitted from heap profiles\&. This statistic is reported separately from
"stats\&.metadata"
and
"stats\&.arenas\&.<i>\&.metadata\&.mapped"
because it overlaps with e\&.g\&. the
"stats\&.allocated"
and
"stats\&.active"
statistics, whereas the other metadata statistics do not\&.
<html><head><metahttp-equiv="Content-Type"content="text/html; charset=ISO-8859-1"><title>JEMALLOC</title><metaname="generator"content="DocBook XSL Stylesheets V1.78.1"></head><bodybgcolor="white"text="black"link="#0000FF"vlink="#840084"alink="#0000FF"><divclass="refentry"><aname="idm316394519664"></a><divclass="titlepage"></div><divclass="refnamediv"><h2>Name</h2><p>jemalloc — general purpose memory allocation functions</p></div><divclass="refsect1"><aname="library"></a><h2>LIBRARY</h2><p>This manual describes jemalloc 3.6.0-0-g46c0af68bd248b04df75e4f92d5fb804c3d75340. More information
<html><head><metahttp-equiv="Content-Type"content="text/html; charset=ISO-8859-1"><title>JEMALLOC</title><metaname="generator"content="DocBook XSL Stylesheets V1.78.1"></head><bodybgcolor="white"text="black"link="#0000FF"vlink="#840084"alink="#0000FF"><divclass="refentry"><aname="idp45223136"></a><divclass="titlepage"></div><divclass="refnamediv"><h2>Name</h2><p>jemalloc — general purpose memory allocation functions</p></div><divclass="refsect1"><aname="library"></a><h2>LIBRARY</h2><p>This manual describes jemalloc 4.0.3-0-ge9192eacf8935e29fc62fddc2701f7942b1cc02c. More information
can be found at the <aclass="ulink"href="http://www.canonware.com/jemalloc/"target="_top">jemalloc website</a>.</p></div><divclass="refsynopsisdiv"><h2>SYNOPSIS</h2><divclass="funcsynopsis"><preclass="funcsynopsisinfo">#include <<codeclass="filename">stdlib.h</code>>
<emclass="parameter"><code>size</code></em> bytes of uninitialized memory. The allocated
<emclass="parameter"><code>size</code></em> bytes of uninitialized memory. The allocated
space is suitably aligned (after possible pointer coercion) for storage
space is suitably aligned (after possible pointer coercion) for storage
of any type of object.</p><p>The <codeclass="function">calloc</code>(<emclass="parameter"><code></code></em>) function allocates
of any type of object.</p><p>The <codeclass="function">calloc</code>(<emclass="parameter"><code></code></em>) function allocates
...
@@ -13,13 +12,13 @@
...
@@ -13,13 +12,13 @@
exception that the allocated memory is explicitly initialized to zero
exception that the allocated memory is explicitly initialized to zero
bytes.</p><p>The <codeclass="function">posix_memalign</code>(<emclass="parameter"><code></code></em>) function
bytes.</p><p>The <codeclass="function">posix_memalign</code>(<emclass="parameter"><code></code></em>) function
allocates <emclass="parameter"><code>size</code></em> bytes of memory such that the
allocates <emclass="parameter"><code>size</code></em> bytes of memory such that the
allocation's base address is an even multiple of
allocation's base address is a multiple of
<emclass="parameter"><code>alignment</code></em>, and returns the allocation in the value
<emclass="parameter"><code>alignment</code></em>, and returns the allocation in the value
pointed to by <emclass="parameter"><code>ptr</code></em>. The requested
pointed to by <emclass="parameter"><code>ptr</code></em>. The requested
<emclass="parameter"><code>alignment</code></em> must be a power of 2 at least as large
<emclass="parameter"><code>alignment</code></em> must be a power of 2 at least as large as
as <codeclass="code">sizeof(<spanclass="type">void *</span>)</code>.</p><p>The <codeclass="function">aligned_alloc</code>(<emclass="parameter"><code></code></em>) function
<codeclass="code">sizeof(<spanclass="type">void *</span>)</code>.</p><p>The <codeclass="function">aligned_alloc</code>(<emclass="parameter"><code></code></em>) function
allocates <emclass="parameter"><code>size</code></em> bytes of memory such that the
allocates <emclass="parameter"><code>size</code></em> bytes of memory such that the
allocation's base address is an even multiple of
allocation's base address is a multiple of
<emclass="parameter"><code>alignment</code></em>. The requested
<emclass="parameter"><code>alignment</code></em>. The requested
<emclass="parameter"><code>alignment</code></em> must be a power of 2. Behavior is
<emclass="parameter"><code>alignment</code></em> must be a power of 2. Behavior is
undefined if <emclass="parameter"><code>size</code></em> is not an integral multiple of
undefined if <emclass="parameter"><code>size</code></em> is not an integral multiple of
...
@@ -38,37 +37,51 @@
...
@@ -38,37 +37,51 @@
<codeclass="function">malloc</code>(<emclass="parameter"><code></code></em>) for the specified size.</p><p>The <codeclass="function">free</code>(<emclass="parameter"><code></code></em>) function causes the
<codeclass="function">malloc</code>(<emclass="parameter"><code></code></em>) for the specified size.</p><p>The <codeclass="function">free</code>(<emclass="parameter"><code></code></em>) function causes the
allocated memory referenced by <emclass="parameter"><code>ptr</code></em> to be made
allocated memory referenced by <emclass="parameter"><code>ptr</code></em> to be made
available for future allocations. If <emclass="parameter"><code>ptr</code></em> is
available for future allocations. If <emclass="parameter"><code>ptr</code></em> is
<codeclass="constant">NULL</code>, no action occurs.</p></div><divclass="refsect2"><aname="idm316388639904"></a><h3>Non-standard API</h3><p>The <codeclass="function">mallocx</code>(<emclass="parameter"><code></code></em>),
<codeclass="constant">NULL</code>, no action occurs.</p></div><divclass="refsect2"><aname="idp46144704"></a><h3>Non-standard API</h3><p>The <codeclass="function">mallocx</code>(<emclass="parameter"><code></code></em>),
</code></span></dt><dd><p>Align the memory allocation to start at an address
</code></span></dt><dd><p>Align the memory allocation to start at an address
that is a multiple of <emclass="parameter"><code>a</code></em>, where
that is a multiple of <emclass="parameter"><code>a</code></em>, where
<emclass="parameter"><code>a</code></em> is a power of two. This macro does not
<emclass="parameter"><code>a</code></em> is a power of two. This macro does not
validate that <emclass="parameter"><code>a</code></em> is a power of 2.
validate that <emclass="parameter"><code>a</code></em> is a power of 2.
</p></dd><dt><spanclass="term"><codeclass="constant">MALLOCX_ZERO</code></span></dt><dd><p>Initialize newly allocated memory to contain zero
</p></dd><dt><aname="MALLOCX_ZERO"></a><spanclass="term"><codeclass="constant">MALLOCX_ZERO</code></span></dt><dd><p>Initialize newly allocated memory to contain zero
bytes. In the growing reallocation case, the real size prior to
bytes. In the growing reallocation case, the real size prior to
reallocation defines the boundary between untouched bytes and those
reallocation defines the boundary between untouched bytes and those
that are initialized to contain zero bytes. If this macro is
that are initialized to contain zero bytes. If this macro is
absent, newly allocated memory is uninitialized.</p></dd><dt><spanclass="term"><codeclass="constant">MALLOCX_ARENA(<emclass="parameter"><code>a</code></em>)
absent, newly allocated memory is uninitialized.</p></dd><dt><aname="MALLOCX_TCACHE"></a><spanclass="term"><codeclass="constant">MALLOCX_TCACHE(<emclass="parameter"><code>tc</code></em>)
</code></span></dt><dd><p>Use the thread-specific cache (tcache) specified by
the identifier <emclass="parameter"><code>tc</code></em>, which must have been
acquired via the <aclass="link"href="#tcache.create">
"<codeclass="mallctl">tcache.create</code>"
</a>
mallctl. This macro does not validate that
<emclass="parameter"><code>tc</code></em> specifies a valid
identifier.</p></dd><dt><aname="MALLOC_TCACHE_NONE"></a><spanclass="term"><codeclass="constant">MALLOCX_TCACHE_NONE</code></span></dt><dd><p>Do not use a thread-specific cache (tcache). Unless
<codeclass="constant">MALLOCX_TCACHE(<emclass="parameter"><code>tc</code></em>)</code> or
<codeclass="constant">MALLOCX_TCACHE_NONE</code> is specified, an
automatically managed tcache will be used under many circumstances.
This macro cannot be used in the same <emclass="parameter"><code>flags</code></em>
</code></span></dt><dd><p>Use the arena specified by the index
</code></span></dt><dd><p>Use the arena specified by the index
<emclass="parameter"><code>a</code></em> (and by necessity bypass the thread
<emclass="parameter"><code>a</code></em>. This macro has no effect for regions that
cache). This macro has no effect for huge regions, nor for regions
were allocated via an arena other than the one specified. This
that were allocated via an arena other than the one specified.
macro does not validate that <emclass="parameter"><code>a</code></em> specifies an
This macro does not validate that <emclass="parameter"><code>a</code></em>
arena index in the valid range.</p></dd></dl></div><p>
specifies an arena index in the valid range.</p></dd></dl></div><p>
</p><p>The <codeclass="function">mallocx</code>(<emclass="parameter"><code></code></em>) function allocates at
</p><p>The <codeclass="function">mallocx</code>(<emclass="parameter"><code></code></em>) function allocates at
least <emclass="parameter"><code>size</code></em> bytes of memory, and returns a pointer
least <emclass="parameter"><code>size</code></em> bytes of memory, and returns a pointer
to the base address of the allocation. Behavior is undefined if
to the base address of the allocation. Behavior is undefined if
...
@@ -91,7 +104,14 @@
...
@@ -91,7 +104,14 @@
><codeclass="constant">SIZE_T_MAX</code>)</code>.</p><p>The <codeclass="function">sallocx</code>(<emclass="parameter"><code></code></em>) function returns the
><codeclass="constant">SIZE_T_MAX</code>)</code>.</p><p>The <codeclass="function">sallocx</code>(<emclass="parameter"><code></code></em>) function returns the
real size of the allocation at <emclass="parameter"><code>ptr</code></em>.</p><p>The <codeclass="function">dallocx</code>(<emclass="parameter"><code></code></em>) function causes the
real size of the allocation at <emclass="parameter"><code>ptr</code></em>.</p><p>The <codeclass="function">dallocx</code>(<emclass="parameter"><code></code></em>) function causes the
memory referenced by <emclass="parameter"><code>ptr</code></em> to be made available for
memory referenced by <emclass="parameter"><code>ptr</code></em> to be made available for
future allocations.</p><p>The <codeclass="function">nallocx</code>(<emclass="parameter"><code></code></em>) function allocates no
future allocations.</p><p>The <codeclass="function">sdallocx</code>(<emclass="parameter"><code></code></em>) function is an
extension of <codeclass="function">dallocx</code>(<emclass="parameter"><code></code></em>) with a
<emclass="parameter"><code>size</code></em> parameter to allow the caller to pass in the
allocation size as an optimization. The minimum valid input size is the
original requested size of the allocation, and the maximum valid input
size is the corresponding value returned by
<codeclass="function">nallocx</code>(<emclass="parameter"><code></code></em>) or
<codeclass="function">sallocx</code>(<emclass="parameter"><code></code></em>).</p><p>The <codeclass="function">nallocx</code>(<emclass="parameter"><code></code></em>) function allocates no
memory, but it performs the same size computation as the
memory, but it performs the same size computation as the
<codeclass="function">mallocx</code>(<emclass="parameter"><code></code></em>) function, and returns the real
<codeclass="function">mallocx</code>(<emclass="parameter"><code></code></em>) function, and returns the real
size of the allocation that would result from the equivalent
size of the allocation that would result from the equivalent
...
@@ -162,11 +182,12 @@ for (i = 0; i < nbins; i++) {
...
@@ -162,11 +182,12 @@ for (i = 0; i < nbins; i++) {
functions simultaneously. If <codeclass="option">--enable-stats</code> is
functions simultaneously. If <codeclass="option">--enable-stats</code> is
specified during configuration, “m” and “a” can
specified during configuration, “m” and “a” can
be specified to omit merged arena and per arena statistics, respectively;
be specified to omit merged arena and per arena statistics, respectively;
“b” and “l” can be specified to omit per size
“b”, “l”, and “h” can be specified to
class statistics for bins and large objects, respectively. Unrecognized
omit per size class statistics for bins, large objects, and huge objects,
characters are silently ignored. Note that thread caching may prevent
respectively. Unrecognized characters are silently ignored. Note that
some statistics from being completely up to date, since extra locking
thread caching may prevent some statistics from being completely up to
would be required to merge counters that track thread cache operations.
date, since extra locking would be required to merge counters that track
thread cache operations.
</p><p>The <codeclass="function">malloc_usable_size</code>(<emclass="parameter"><code></code></em>) function
</p><p>The <codeclass="function">malloc_usable_size</code>(<emclass="parameter"><code></code></em>) function
returns the usable size of the allocation pointed to by
returns the usable size of the allocation pointed to by
<emclass="parameter"><code>ptr</code></em>. The return value may be larger than the size
<emclass="parameter"><code>ptr</code></em>. The return value may be larger than the size
...
@@ -177,74 +198,7 @@ for (i = 0; i < nbins; i++) {
...
@@ -177,74 +198,7 @@ for (i = 0; i < nbins; i++) {
discrepancy between the requested allocation size and the size reported
discrepancy between the requested allocation size and the size reported
by <codeclass="function">malloc_usable_size</code>(<emclass="parameter"><code></code></em>) should not be
by <codeclass="function">malloc_usable_size</code>(<emclass="parameter"><code></code></em>) should not be
depended on, since such behavior is entirely implementation-dependent.
depended on, since such behavior is entirely implementation-dependent.
</p></div><divclass="refsect2"><aname="idm316388574208"></a><h3>Experimental API</h3><p>The experimental API is subject to change or removal without regard
</p></div></div><divclass="refsect1"><aname="tuning"></a><h2>TUNING</h2><p>Once, when the first call is made to one of the memory allocation
for backward compatibility. If <codeclass="option">--disable-experimental</code>
is specified during configuration, the experimental API is
</code></span></dt><dd><p>Align the memory allocation to start at an address
that is a multiple of <emclass="parameter"><code>a</code></em>, where
<emclass="parameter"><code>a</code></em> is a power of two. This macro does not
validate that <emclass="parameter"><code>a</code></em> is a power of 2.
</p></dd><dt><spanclass="term"><codeclass="constant">ALLOCM_ZERO</code></span></dt><dd><p>Initialize newly allocated memory to contain zero
bytes. In the growing reallocation case, the real size prior to
reallocation defines the boundary between untouched bytes and those
that are initialized to contain zero bytes. If this macro is
absent, newly allocated memory is uninitialized.</p></dd><dt><spanclass="term"><codeclass="constant">ALLOCM_NO_MOVE</code></span></dt><dd><p>For reallocation, fail rather than moving the
object. This constraint can apply to both growth and
</code></span></dt><dd><p>Use the arena specified by the index
<emclass="parameter"><code>a</code></em> (and by necessity bypass the thread
cache). This macro has no effect for huge regions, nor for regions
that were allocated via an arena other than the one specified.
This macro does not validate that <emclass="parameter"><code>a</code></em>
specifies an arena index in the valid range.</p></dd></dl></div><p>
</p><p>The <codeclass="function">allocm</code>(<emclass="parameter"><code></code></em>) function allocates at
least <emclass="parameter"><code>size</code></em> bytes of memory, sets
<emclass="parameter"><code>*ptr</code></em> to the base address of the allocation, and
sets <emclass="parameter"><code>*rsize</code></em> to the real size of the allocation if
<emclass="parameter"><code>rsize</code></em> is not <codeclass="constant">NULL</code>. Behavior
is undefined if <emclass="parameter"><code>size</code></em> is <codeclass="constant">0</code>, or
if request size overflows due to size class and/or alignment
constraints.</p><p>The <codeclass="function">rallocm</code>(<emclass="parameter"><code></code></em>) function resizes the
allocation at <emclass="parameter"><code>*ptr</code></em> to be at least
<emclass="parameter"><code>size</code></em> bytes, sets <emclass="parameter"><code>*ptr</code></em> to
the base address of the allocation if it moved, and sets
<emclass="parameter"><code>*rsize</code></em> to the real size of the allocation if
<emclass="parameter"><code>rsize</code></em> is not <codeclass="constant">NULL</code>. If
<emclass="parameter"><code>extra</code></em> is non-zero, an attempt is made to resize
the allocation to be at least <codeclass="code">(<emclass="parameter"><code>size</code></em> +
<emclass="parameter"><code>extra</code></em>)</code> bytes, though inability to allocate
the extra byte(s) will not by itself result in failure. Behavior is
undefined if <emclass="parameter"><code>size</code></em> is <codeclass="constant">0</code>, if
request size overflows due to size class and/or alignment constraints, or
if <codeclass="code">(<emclass="parameter"><code>size</code></em> +
<emclass="parameter"><code>extra</code></em>>
<codeclass="constant">SIZE_T_MAX</code>)</code>.</p><p>The <codeclass="function">sallocm</code>(<emclass="parameter"><code></code></em>) function sets
<emclass="parameter"><code>*rsize</code></em> to the real size of the allocation.</p><p>The <codeclass="function">dallocm</code>(<emclass="parameter"><code></code></em>) function causes the
memory referenced by <emclass="parameter"><code>ptr</code></em> to be made available for
future allocations.</p><p>The <codeclass="function">nallocm</code>(<emclass="parameter"><code></code></em>) function allocates no
memory, but it performs the same size computation as the
<codeclass="function">allocm</code>(<emclass="parameter"><code></code></em>) function, and if
<emclass="parameter"><code>rsize</code></em> is not <codeclass="constant">NULL</code> it sets
<emclass="parameter"><code>*rsize</code></em> to the real size of the allocation that
would result from the equivalent <codeclass="function">allocm</code>(<emclass="parameter"><code></code></em>)
function call. Behavior is undefined if <emclass="parameter"><code>size</code></em> is
<codeclass="constant">0</code>, or if request size overflows due to size class
and/or alignment constraints.</p></div></div><divclass="refsect1"><aname="tuning"></a><h2>TUNING</h2><p>Once, when the first call is made to one of the memory allocation
routines, the allocator initializes its internals based in part on various
routines, the allocator initializes its internals based in part on various
options that can be specified at compile- or run-time.</p><p>The string pointed to by the global variable
options that can be specified at compile- or run-time.</p><p>The string pointed to by the global variable
<codeclass="varname">malloc_conf</code>, the “name” of the file
<codeclass="varname">malloc_conf</code>, the “name” of the file
...
@@ -272,8 +226,9 @@ for (i = 0; i < nbins; i++) {
...
@@ -272,8 +226,9 @@ for (i = 0; i < nbins; i++) {
<spanclass="citerefentry"><spanclass="refentrytitle">sbrk</span>(2)</span> to obtain memory, which is
<spanclass="citerefentry"><spanclass="refentrytitle">sbrk</span>(2)</span> to obtain memory, which is
suboptimal for several reasons, including race conditions, increased
suboptimal for several reasons, including race conditions, increased
fragmentation, and artificial limitations on maximum usable memory. If
fragmentation, and artificial limitations on maximum usable memory. If
<codeclass="option">--enable-dss</code> is specified during configuration, this
<spanclass="citerefentry"><spanclass="refentrytitle">sbrk</span>(2)</span> is supported by the operating
allocator uses both <spanclass="citerefentry"><spanclass="refentrytitle">mmap</span>(2)</span> and
system, this allocator uses both
<spanclass="citerefentry"><spanclass="refentrytitle">mmap</span>(2)</span> and
<spanclass="citerefentry"><spanclass="refentrytitle">sbrk</span>(2)</span>, in that order of preference;
<spanclass="citerefentry"><spanclass="refentrytitle">sbrk</span>(2)</span>, in that order of preference;
otherwise only <spanclass="citerefentry"><spanclass="refentrytitle">mmap</span>(2)</span> is used.</p><p>This allocator uses multiple arenas in order to reduce lock
otherwise only <spanclass="citerefentry"><spanclass="refentrytitle">mmap</span>(2)</span> is used.</p><p>This allocator uses multiple arenas in order to reduce lock
contention for threaded programs on multi-processor systems. This works
contention for threaded programs on multi-processor systems. This works
...
@@ -295,34 +250,52 @@ for (i = 0; i < nbins; i++) {
...
@@ -295,34 +250,52 @@ for (i = 0; i < nbins; i++) {
chunk size is a power of two that is greater than the page size. Chunks
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
are always aligned to multiples of the chunk size. This alignment makes it
possible to find metadata for user objects very quickly.</p><p>User objects are broken into three categories according to size:
possible to find metadata for user objects very quickly.</p><p>User objects are broken into three categories according to size:
small, large, and huge. Small objects are smaller than one page. Large
small, large, and huge. Small and large objects are managed entirely by
objects are smaller than the chunk size. Huge objects are a multiple of
arenas; huge objects are additionally aggregated in a single data structure
the chunk size. Small and large objects are managed by arenas; huge
that is shared by all threads. Huge objects are typically used by
objects are managed separately in a single data structure that is shared by
applications infrequently enough that this single data structure is not a
all threads. Huge objects are used by applications infrequently enough
scalability issue.</p><p>Each chunk that is managed by an arena tracks its contents as runs of
that this single data structure is not a scalability issue.</p><p>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
contiguous pages (unused, backing a set of small objects, or backing one
large object). The combination of chunk alignment and chunk page maps
large object). The combination of chunk alignment and chunk page maps
makes it possible to determine all metadata regarding small and large
makes it possible to determine all metadata regarding small and large
allocations in constant time.</p><p>Small objects are managed in groups by page runs. Each run maintains
allocations in constant time.</p><p>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
a bitmap to track which regions are in use. Allocation requests that are no
requests that are no more than half the quantum (8 or 16, depending on
more than half the quantum (8 or 16, depending on architecture) are rounded
architecture) are rounded up to the nearest power of two that is at least
up to the nearest power of two that is at least<codeclass="code">sizeof(<spanclass="type">double</span>)</code>. All other object size
<codeclass="code">sizeof(<spanclass="type">double</span>)</code>. All other small
classes are multiples of the quantum, spaced such that there are four size
object size classes are multiples of the quantum, spaced such that internal
classes for each doubling in size, which limits internal fragmentation to
fragmentation is limited to approximately 25% for all but the smallest size
approximately 20% for all but the smallest size classes. Small size classes
classes. Allocation requests that are larger than the maximum small size
are smaller than four times the page size, large size classes are smaller
class, but small enough to fit in an arena-managed chunk (see the <aclass="link"href="#opt.lg_chunk">
than the chunk size (see the <aclass="link"href="#opt.lg_chunk">
"<codeclass="mallctl">opt.lg_chunk</code>"
"<codeclass="mallctl">opt.lg_chunk</code>"
</a> option), are
</a> option), and
rounded up to the nearest run size. Allocation requests that are too large
huge size classes extend from the chunk size up to one size class less than
to fit in an arena-managed chunk are rounded up to the nearest multiple of
the full address space size.</p><p>Allocations are packed tightly together, which can be an issue for
the chunk size.</p><p>Allocations are packed tightly together, which can be an issue for
multi-threaded applications. If you need to assure that allocations do not
multi-threaded applications. If you need to assure that allocations do not
suffer from cacheline sharing, round your allocation requests up to the
suffer from cacheline sharing, round your allocation requests up to the
nearest multiple of the cacheline size, or specify cacheline alignment when
nearest multiple of the cacheline size, or specify cacheline alignment when
allocating.</p><p>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 <aclass="xref"href="#size_classes"title="Table1.Size classes">Table 1</a>.</p><divclass="table"><aname="size_classes"></a><pclass="title"><b>Table1.Size classes</b></p><divclass="table-contents"><tablesummary="Size classes"border="1"><colgroup><colalign="left"class="c1"><colalign="right"class="c2"><colalign="left"class="c3"></colgroup><thead><tr><thalign="left">Category</th><thalign="right">Spacing</th><thalign="left">Size</th></tr></thead><tbody><tr><tdrowspan="7"align="left">Small</td><tdalign="right">lg</td><tdalign="left">[8]</td></tr><tr><tdalign="right">16</td><tdalign="left">[16, 32, 48, ..., 128]</td></tr><tr><tdalign="right">32</td><tdalign="left">[160, 192, 224, 256]</td></tr><tr><tdalign="right">64</td><tdalign="left">[320, 384, 448, 512]</td></tr><tr><tdalign="right">128</td><tdalign="left">[640, 768, 896, 1024]</td></tr><tr><tdalign="right">256</td><tdalign="left">[1280, 1536, 1792, 2048]</td></tr><tr><tdalign="right">512</td><tdalign="left">[2560, 3072, 3584]</td></tr><tr><tdalign="left">Large</td><tdalign="right">4 KiB</td><tdalign="left">[4 KiB, 8 KiB, 12 KiB, ..., 4072 KiB]</td></tr><tr><tdalign="left">Huge</td><tdalign="right">4 MiB</td><tdalign="left">[4 MiB, 8 MiB, 12 MiB, ...]</td></tr></tbody></table></div></div><brclass="table-break"></div><divclass="refsect1"><aname="mallctl_namespace"></a><h2>MALLCTL NAMESPACE</h2><p>The following names are defined in the namespace accessible via the
<codeclass="function">rallocx</code>(<emclass="parameter"><code></code></em>), and
<codeclass="function">xallocx</code>(<emclass="parameter"><code></code></em>) functions may resize allocations
without moving them under limited circumstances. Unlike the
<codeclass="function">*allocx</code>(<emclass="parameter"><code></code></em>) API, the standard API does not
officially round up the usable size of an allocation to the nearest size
class, so technically it is necessary to call
<codeclass="function">realloc</code>(<emclass="parameter"><code></code></em>) to grow e.g. a 9-byte allocation to
16 bytes, or shrink a 16-byte allocation to 9 bytes. Growth and shrinkage
trivially succeeds in place as long as the pre-size and post-size both round
up to the same size class. No other API guarantees are made regarding
in-place resizing, but the current implementation also tries to resize large
and huge allocations in place, as long as the pre-size and post-size are
both large or both huge. In such cases shrinkage always succeeds for large
size classes, but for huge size classes the chunk allocator must support
splitting (see <aclass="link"href="#arena.i.chunk_hooks">
option for final profile dumping. Profile output is compatible with
option for final profile dumping. Profile output is compatible with
the included <spanclass="command"><strong>pprof</strong></span>Perl script, which originates
the <spanclass="command"><strong>jeprof</strong></span>command, which is based on the
from the <aclass="ulink"href="http://code.google.com/p/gperftools/"target="_top">gperftools
<spanclass="command"><strong>pprof</strong></span> that is developed as part of the <aclass="ulink"href="http://code.google.com/p/gperftools/"target="_top">gperftools
</span></dt><dd><p>Create an explicit thread-specific cache (tcache) and
return an identifier that can be passed to the <aclass="link"href="#MALLOCX_TCACHE"><codeclass="constant">MALLOCX_TCACHE(<emclass="parameter"><code>tc</code></em>)</code></a>
macro to explicitly use the specified cache rather than the
automatically managed one that is used by default. Each explicit cache
can be used by only one thread at a time; the application must assure
<spanclass="type">chunk_dalloc_t</span> type and deallocates a
<emclass="parameter"><code>chunk</code></em> of given <emclass="parameter"><code>size</code></em> with
<emclass="parameter"><code>committed</code></em>/decommited memory as indicated, on
behalf of arena <emclass="parameter"><code>arena_ind</code></em>, returning false upon
success. If the function returns true, this indicates opt-out from
deallocation; the virtual memory mapping associated with the chunk
remains mapped, in the same commit state, and available for future use,
in which case it will be automatically retained for later reuse.</p><divclass="funcsynopsis"><tableborder="0"class="funcprototype-table"summary="Function synopsis"style="cellspacing: 0; cellpadding: 0;"><tr><td><codeclass="funcdef">typedef bool <bclass="fsfunc">(chunk_commit_t)</b>(</code></td><td>void *<varclass="pdparam">chunk</var>, </td></tr><tr><td></td><td>size_t <varclass="pdparam">size</var>, </td></tr><tr><td></td><td>size_t <varclass="pdparam">offset</var>, </td></tr><tr><td></td><td>size_t <varclass="pdparam">length</var>, </td></tr><tr><td></td><td>unsigned <varclass="pdparam">arena_ind</var><code>)</code>;</td></tr></table><divclass="funcprototype-spacer"></div></div><divclass="literallayout"><p></p></div><p>A chunk commit function conforms to the
<spanclass="type">chunk_commit_t</span> type and commits zeroed physical memory to
back pages within a <emclass="parameter"><code>chunk</code></em> of given
<emclass="parameter"><code>size</code></em> at <emclass="parameter"><code>offset</code></em> bytes,
extending for <emclass="parameter"><code>length</code></em> on behalf of arena
<emclass="parameter"><code>arena_ind</code></em>, returning false upon success.
Committed memory may be committed in absolute terms as on a system that
does not overcommit, or in implicit terms as on a system that
overcommits and satisfies physical memory needs on demand via soft page
faults. If the function returns true, this indicates insufficient
physical memory to satisfy the request.</p><divclass="funcsynopsis"><tableborder="0"class="funcprototype-table"summary="Function synopsis"style="cellspacing: 0; cellpadding: 0;"><tr><td><codeclass="funcdef">typedef bool <bclass="fsfunc">(chunk_decommit_t)</b>(</code></td><td>void *<varclass="pdparam">chunk</var>, </td></tr><tr><td></td><td>size_t <varclass="pdparam">size</var>, </td></tr><tr><td></td><td>size_t <varclass="pdparam">offset</var>, </td></tr><tr><td></td><td>size_t <varclass="pdparam">length</var>, </td></tr><tr><td></td><td>unsigned <varclass="pdparam">arena_ind</var><code>)</code>;</td></tr></table><divclass="funcprototype-spacer"></div></div><divclass="literallayout"><p></p></div><p>A chunk decommit function conforms to the
<spanclass="type">chunk_decommit_t</span> type and decommits any physical memory
that is backing pages within a <emclass="parameter"><code>chunk</code></em> of given
<emclass="parameter"><code>size</code></em> at <emclass="parameter"><code>offset</code></em> bytes,
extending for <emclass="parameter"><code>length</code></em> on behalf of arena
<emclass="parameter"><code>arena_ind</code></em>, returning false upon success, in which
case the pages will be committed via the chunk commit function before
being reused. If the function returns true, this indicates opt-out from
decommit; the memory remains committed and available for future use, in
which case it will be automatically retained for later reuse.</p><divclass="funcsynopsis"><tableborder="0"class="funcprototype-table"summary="Function synopsis"style="cellspacing: 0; cellpadding: 0;"><tr><td><codeclass="funcdef">typedef bool <bclass="fsfunc">(chunk_purge_t)</b>(</code></td><td>void *<varclass="pdparam">chunk</var>, </td></tr><tr><td></td><td>size_t<varclass="pdparam">size</var>, </td></tr><tr><td></td><td>size_t <varclass="pdparam">offset</var>, </td></tr><tr><td></td><td>size_t <varclass="pdparam">length</var>, </td></tr><tr><td></td><td>unsigned <varclass="pdparam">arena_ind</var><code>)</code>;</td></tr></table><divclass="funcprototype-spacer"></div></div><divclass="literallayout"><p></p></div><p>A chunk purge function conforms to the <spanclass="type">chunk_purge_t</span>
type and optionally discards physical pages within the virtual memory
mapping associated with <emclass="parameter"><code>chunk</code></em> of given
<emclass="parameter"><code>size</code></em> at <emclass="parameter"><code>offset</code></em> bytes,
extending for <emclass="parameter"><code>length</code></em> on behalf of arena
<emclass="parameter"><code>arena_ind</code></em>, returning false if pages within the
purged virtual memory range will be zero-filled the next time they are
accessed.</p><divclass="funcsynopsis"><tableborder="0"class="funcprototype-table"summary="Function synopsis"style="cellspacing: 0; cellpadding: 0;"><tr><td><codeclass="funcdef">typedef bool <bclass="fsfunc">(chunk_split_t)</b>(</code></td><td>void *<varclass="pdparam">chunk</var>, </td></tr><tr><td></td><td>size_t <varclass="pdparam">size</var>, </td></tr><tr><td></td><td>size_t <varclass="pdparam">size_a</var>, </td></tr><tr><td></td><td>size_t <varclass="pdparam">size_b</var>, </td></tr><tr><td></td><td>bool <varclass="pdparam">committed</var>, </td></tr><tr><td></td><td>unsigned <varclass="pdparam">arena_ind</var><code>)</code>;</td></tr></table><divclass="funcprototype-spacer"></div></div><divclass="literallayout"><p></p></div><p>A chunk split function conforms to the <spanclass="type">chunk_split_t</span>
type and optionally splits <emclass="parameter"><code>chunk</code></em> of given
<emclass="parameter"><code>size</code></em> into two adjacent chunks, the first of
<emclass="parameter"><code>size_a</code></em> bytes, and the second of
<emclass="parameter"><code>size_b</code></em> bytes, operating on
<emclass="parameter"><code>committed</code></em>/decommitted memory as indicated, on
behalf of arena <emclass="parameter"><code>arena_ind</code></em>, returning false upon
success. If the function returns true, this indicates that the chunk
remains unsplit and therefore should continue to be operated on as a
whole.</p><divclass="funcsynopsis"><tableborder="0"class="funcprototype-table"summary="Function synopsis"style="cellspacing: 0; cellpadding: 0;"><tr><td><codeclass="funcdef">typedef bool <bclass="fsfunc">(chunk_merge_t)</b>(</code></td><td>void *<varclass="pdparam">chunk_a</var>, </td></tr><tr><td></td><td>size_t <varclass="pdparam">size_a</var>, </td></tr><tr><td></td><td>void *<varclass="pdparam">chunk_b</var>, </td></tr><tr><td></td><td>size_t <varclass="pdparam">size_b</var>, </td></tr><tr><td></td><td>bool <varclass="pdparam">committed</var>, </td></tr><tr><td></td><td>unsigned <varclass="pdparam">arena_ind</var><code>)</code>;</td></tr></table><divclass="funcprototype-spacer"></div></div><divclass="literallayout"><p></p></div><p>A chunk merge function conforms to the <spanclass="type">chunk_merge_t</span>
type and optionally merges adjacent chunks,
<emclass="parameter"><code>chunk_a</code></em> of given <emclass="parameter"><code>size_a</code></em>
and <emclass="parameter"><code>chunk_b</code></em> of given
<emclass="parameter"><code>size_b</code></em> into one contiguous chunk, operating on
<emclass="parameter"><code>committed</code></em>/decommitted memory as indicated, on
behalf of arena <emclass="parameter"><code>arena_ind</code></em>, returning false upon
success. If the function returns true, this indicates that the chunks
remain distinct mappings and therefore should continue to be operated on
</span></dt><dd><p>Current number of huge allocations for this size class.
</p></dd></dl></div></div><divclass="refsect1"><aname="debugging_malloc_problems"></a><h2>DEBUGGING MALLOC PROBLEMS</h2><p>When debugging, it is a good idea to configure/build jemalloc with
</p></dd></dl></div></div><divclass="refsect1"><aname="debugging_malloc_problems"></a><h2>DEBUGGING MALLOC PROBLEMS</h2><p>When debugging, it is a good idea to configure/build jemalloc with
the <codeclass="option">--enable-debug</code> and <codeclass="option">--enable-fill</code>
the <codeclass="option">--enable-debug</code> and <codeclass="option">--enable-fill</code>
options, and recompile the program with suitable options and symbols for
options, and recompile the program with suitable options and symbols for
allocation failure. The <codeclass="function">realloc</code>(<emclass="parameter"><code></code></em>)
allocation failure. The <codeclass="function">realloc</code>(<emclass="parameter"><code></code></em>)
function always leaves the original buffer intact when an error occurs.
function always leaves the original buffer intact when an error occurs.
</p><p>The <codeclass="function">free</code>(<emclass="parameter"><code></code></em>) function returns no
</p><p>The <codeclass="function">free</code>(<emclass="parameter"><code></code></em>) function returns no
value.</p></div><divclass="refsect2"><aname="idm316388003104"></a><h3>Non-standard API</h3><p>The <codeclass="function">mallocx</code>(<emclass="parameter"><code></code></em>) and
value.</p></div><divclass="refsect2"><aname="idp46974576"></a><h3>Non-standard API</h3><p>The <codeclass="function">mallocx</code>(<emclass="parameter"><code></code></em>) and
<codeclass="function">rallocx</code>(<emclass="parameter"><code></code></em>) functions return a pointer to
<codeclass="function">rallocx</code>(<emclass="parameter"><code></code></em>) functions return a pointer to
the allocated memory if successful; otherwise a <codeclass="constant">NULL</code>
the allocated memory if successful; otherwise a <codeclass="constant">NULL</code>
pointer is returned to indicate insufficient contiguous memory was
pointer is returned to indicate insufficient contiguous memory was
<emclass="parameter"><code>ptr</code></em>. </p></div></div><divclass="refsect1"><aname="environment"></a><h2>ENVIRONMENT</h2><p>The following environment variable affects the execution of the
<codeclass="constant">ALLOCM_SUCCESS</code> on success; otherwise they return an
error value. The <codeclass="function">allocm</code>(<emclass="parameter"><code></code></em>),
<codeclass="function">rallocm</code>(<emclass="parameter"><code></code></em>), and
<codeclass="function">nallocm</code>(<emclass="parameter"><code></code></em>) functions will fail if:
</p><divclass="variablelist"><dlclass="variablelist"><dt><spanclass="term"><spanclass="errorname">ALLOCM_ERR_OOM</span></span></dt><dd><p>Out of memory. Insufficient contiguous memory was
available to service the allocation request. The
<codeclass="function">allocm</code>(<emclass="parameter"><code></code></em>) function additionally sets
<emclass="parameter"><code>*ptr</code></em> to <codeclass="constant">NULL</code>, whereas
the <codeclass="function">rallocm</code>(<emclass="parameter"><code></code></em>) function leaves
The <codeclass="function">rallocm</code>(<emclass="parameter"><code></code></em>) function will also
fail if:
</p><divclass="variablelist"><dlclass="variablelist"><dt><spanclass="term"><spanclass="errorname">ALLOCM_ERR_NOT_MOVED</span></span></dt><dd><p><codeclass="constant">ALLOCM_NO_MOVE</code> was specified,
but the reallocation request could not be serviced without moving
the object.</p></dd></dl></div><p>
</p></div></div><divclass="refsect1"><aname="environment"></a><h2>ENVIRONMENT</h2><p>The following environment variable affects the execution of the
allocation functions:
allocation functions:
</p><divclass="variablelist"><dlclass="variablelist"><dt><spanclass="term"><codeclass="envar">MALLOC_CONF</code></span></dt><dd><p>If the environment variable
</p><divclass="variablelist"><dlclass="variablelist"><dt><spanclass="term"><codeclass="envar">MALLOC_CONF</code></span></dt><dd><p>If the environment variable
<codeclass="envar">MALLOC_CONF</code> is set, the characters it contains
<codeclass="envar">MALLOC_CONF</code> is set, the characters it contains