server-skynet-source-3rd-je.../doc/jemalloc.xml.in

2868 lines
126 KiB
XML
Raw Normal View History

<?xml version='1.0' encoding='UTF-8'?>
<?xml-stylesheet type="text/xsl"
href="http://docbook.sourceforge.net/release/xsl/current/manpages/docbook.xsl"?>
<!DOCTYPE refentry PUBLIC "-//OASIS//DTD DocBook XML V4.4//EN"
"http://www.oasis-open.org/docbook/xml/4.4/docbookx.dtd" [
]>
<refentry>
<refentryinfo>
<title>User Manual</title>
<productname>jemalloc</productname>
<releaseinfo role="version">@jemalloc_version@</releaseinfo>
<authorgroup>
<author>
<firstname>Jason</firstname>
<surname>Evans</surname>
<personblurb>Author</personblurb>
</author>
</authorgroup>
</refentryinfo>
<refmeta>
<refentrytitle>JEMALLOC</refentrytitle>
<manvolnum>3</manvolnum>
</refmeta>
<refnamediv>
<refdescriptor>jemalloc</refdescriptor>
<refname>jemalloc</refname>
<!-- Each refname causes a man page file to be created. Only if this were
the system malloc(3) implementation would these files be appropriate.
<refname>malloc</refname>
<refname>calloc</refname>
<refname>posix_memalign</refname>
<refname>aligned_alloc</refname>
<refname>realloc</refname>
<refname>free</refname>
<refname>mallocx</refname>
<refname>rallocx</refname>
<refname>xallocx</refname>
<refname>sallocx</refname>
<refname>dallocx</refname>
<refname>sdallocx</refname>
<refname>nallocx</refname>
<refname>mallctl</refname>
<refname>mallctlnametomib</refname>
<refname>mallctlbymib</refname>
<refname>malloc_stats_print</refname>
<refname>malloc_usable_size</refname>
-->
<refpurpose>general purpose memory allocation functions</refpurpose>
</refnamediv>
<refsect1 id="library">
<title>LIBRARY</title>
<para>This manual describes jemalloc @jemalloc_version@. More information
can be found at the <ulink
url="http://www.canonware.com/jemalloc/">jemalloc website</ulink>.</para>
</refsect1>
<refsynopsisdiv>
<title>SYNOPSIS</title>
<funcsynopsis>
<funcsynopsisinfo>#include &lt;<filename class="headerfile">jemalloc/jemalloc.h</filename>&gt;</funcsynopsisinfo>
<refsect2>
<title>Standard API</title>
<funcprototype>
<funcdef>void *<function>malloc</function></funcdef>
<paramdef>size_t <parameter>size</parameter></paramdef>
</funcprototype>
<funcprototype>
<funcdef>void *<function>calloc</function></funcdef>
<paramdef>size_t <parameter>number</parameter></paramdef>
<paramdef>size_t <parameter>size</parameter></paramdef>
</funcprototype>
<funcprototype>
<funcdef>int <function>posix_memalign</function></funcdef>
<paramdef>void **<parameter>ptr</parameter></paramdef>
<paramdef>size_t <parameter>alignment</parameter></paramdef>
<paramdef>size_t <parameter>size</parameter></paramdef>
</funcprototype>
<funcprototype>
<funcdef>void *<function>aligned_alloc</function></funcdef>
<paramdef>size_t <parameter>alignment</parameter></paramdef>
<paramdef>size_t <parameter>size</parameter></paramdef>
</funcprototype>
<funcprototype>
<funcdef>void *<function>realloc</function></funcdef>
<paramdef>void *<parameter>ptr</parameter></paramdef>
<paramdef>size_t <parameter>size</parameter></paramdef>
</funcprototype>
<funcprototype>
<funcdef>void <function>free</function></funcdef>
<paramdef>void *<parameter>ptr</parameter></paramdef>
</funcprototype>
</refsect2>
<refsect2>
<title>Non-standard API</title>
<funcprototype>
<funcdef>void *<function>mallocx</function></funcdef>
<paramdef>size_t <parameter>size</parameter></paramdef>
<paramdef>int <parameter>flags</parameter></paramdef>
</funcprototype>
<funcprototype>
<funcdef>void *<function>rallocx</function></funcdef>
<paramdef>void *<parameter>ptr</parameter></paramdef>
<paramdef>size_t <parameter>size</parameter></paramdef>
<paramdef>int <parameter>flags</parameter></paramdef>
</funcprototype>
<funcprototype>
<funcdef>size_t <function>xallocx</function></funcdef>
<paramdef>void *<parameter>ptr</parameter></paramdef>
<paramdef>size_t <parameter>size</parameter></paramdef>
<paramdef>size_t <parameter>extra</parameter></paramdef>
<paramdef>int <parameter>flags</parameter></paramdef>
</funcprototype>
<funcprototype>
<funcdef>size_t <function>sallocx</function></funcdef>
<paramdef>void *<parameter>ptr</parameter></paramdef>
<paramdef>int <parameter>flags</parameter></paramdef>
</funcprototype>
<funcprototype>
<funcdef>void <function>dallocx</function></funcdef>
<paramdef>void *<parameter>ptr</parameter></paramdef>
<paramdef>int <parameter>flags</parameter></paramdef>
</funcprototype>
<funcprototype>
<funcdef>void <function>sdallocx</function></funcdef>
<paramdef>void *<parameter>ptr</parameter></paramdef>
<paramdef>size_t <parameter>size</parameter></paramdef>
<paramdef>int <parameter>flags</parameter></paramdef>
</funcprototype>
<funcprototype>
<funcdef>size_t <function>nallocx</function></funcdef>
<paramdef>size_t <parameter>size</parameter></paramdef>
<paramdef>int <parameter>flags</parameter></paramdef>
</funcprototype>
<funcprototype>
<funcdef>int <function>mallctl</function></funcdef>
<paramdef>const char *<parameter>name</parameter></paramdef>
<paramdef>void *<parameter>oldp</parameter></paramdef>
<paramdef>size_t *<parameter>oldlenp</parameter></paramdef>
<paramdef>void *<parameter>newp</parameter></paramdef>
<paramdef>size_t <parameter>newlen</parameter></paramdef>
</funcprototype>
<funcprototype>
<funcdef>int <function>mallctlnametomib</function></funcdef>
<paramdef>const char *<parameter>name</parameter></paramdef>
<paramdef>size_t *<parameter>mibp</parameter></paramdef>
<paramdef>size_t *<parameter>miblenp</parameter></paramdef>
</funcprototype>
<funcprototype>
<funcdef>int <function>mallctlbymib</function></funcdef>
<paramdef>const size_t *<parameter>mib</parameter></paramdef>
<paramdef>size_t <parameter>miblen</parameter></paramdef>
<paramdef>void *<parameter>oldp</parameter></paramdef>
<paramdef>size_t *<parameter>oldlenp</parameter></paramdef>
<paramdef>void *<parameter>newp</parameter></paramdef>
<paramdef>size_t <parameter>newlen</parameter></paramdef>
</funcprototype>
<funcprototype>
<funcdef>void <function>malloc_stats_print</function></funcdef>
<paramdef>void <parameter>(*write_cb)</parameter>
<funcparams>void *, const char *</funcparams>
</paramdef>
<paramdef>void *<parameter>cbopaque</parameter></paramdef>
<paramdef>const char *<parameter>opts</parameter></paramdef>
</funcprototype>
<funcprototype>
<funcdef>size_t <function>malloc_usable_size</function></funcdef>
<paramdef>const void *<parameter>ptr</parameter></paramdef>
</funcprototype>
<funcprototype>
<funcdef>void <function>(*malloc_message)</function></funcdef>
<paramdef>void *<parameter>cbopaque</parameter></paramdef>
<paramdef>const char *<parameter>s</parameter></paramdef>
</funcprototype>
<para><type>const char *</type><varname>malloc_conf</varname>;</para>
</refsect2>
</funcsynopsis>
</refsynopsisdiv>
<refsect1 id="description">
<title>DESCRIPTION</title>
<refsect2>
<title>Standard API</title>
<para>The <function>malloc<parameter/></function> function allocates
<parameter>size</parameter> bytes of uninitialized memory. The allocated
space is suitably aligned (after possible pointer coercion) for storage
of any type of object.</para>
<para>The <function>calloc<parameter/></function> function allocates
space for <parameter>number</parameter> objects, each
<parameter>size</parameter> bytes in length. The result is identical to
calling <function>malloc<parameter/></function> with an argument of
<parameter>number</parameter> * <parameter>size</parameter>, with the
exception that the allocated memory is explicitly initialized to zero
bytes.</para>
<para>The <function>posix_memalign<parameter/></function> function
allocates <parameter>size</parameter> bytes of memory such that the
2014-05-16 13:46:24 +08:00
allocation's base address is a multiple of
<parameter>alignment</parameter>, and returns the allocation in the value
pointed to by <parameter>ptr</parameter>. The requested
2014-05-16 13:46:24 +08:00
<parameter>alignment</parameter> must be a power of 2 at least as large as
<code language="C">sizeof(<type>void *</type>)</code>.</para>
<para>The <function>aligned_alloc<parameter/></function> function
allocates <parameter>size</parameter> bytes of memory such that the
2014-05-16 13:46:24 +08:00
allocation's base address is a multiple of
<parameter>alignment</parameter>. The requested
<parameter>alignment</parameter> must be a power of 2. Behavior is
undefined if <parameter>size</parameter> is not an integral multiple of
<parameter>alignment</parameter>.</para>
<para>The <function>realloc<parameter/></function> function changes the
size of the previously allocated memory referenced by
<parameter>ptr</parameter> to <parameter>size</parameter> 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 <parameter>ptr</parameter> is freed and a pointer to the newly
allocated memory is returned. Note that
<function>realloc<parameter/></function> may move the memory allocation,
resulting in a different return value than <parameter>ptr</parameter>.
If <parameter>ptr</parameter> is <constant>NULL</constant>, the
<function>realloc<parameter/></function> function behaves identically to
<function>malloc<parameter/></function> for the specified size.</para>
<para>The <function>free<parameter/></function> function causes the
allocated memory referenced by <parameter>ptr</parameter> to be made
available for future allocations. If <parameter>ptr</parameter> is
<constant>NULL</constant>, no action occurs.</para>
</refsect2>
<refsect2>
<title>Non-standard API</title>
<para>The <function>mallocx<parameter/></function>,
<function>rallocx<parameter/></function>,
<function>xallocx<parameter/></function>,
<function>sallocx<parameter/></function>,
<function>dallocx<parameter/></function>,
<function>sdallocx<parameter/></function>, and
<function>nallocx<parameter/></function> functions all have a
<parameter>flags</parameter> argument that can be used to specify
options. The functions only check the options that are contextually
relevant. Use bitwise or (<code language="C">|</code>) operations to
specify one or more of the following:
<variablelist>
<varlistentry id="MALLOCX_LG_ALIGN">
<term><constant>MALLOCX_LG_ALIGN(<parameter>la</parameter>)
</constant></term>
<listitem><para>Align the memory allocation to start at an address
that is a multiple of <code language="C">(1 &lt;&lt;
<parameter>la</parameter>)</code>. This macro does not validate
that <parameter>la</parameter> is within the valid
range.</para></listitem>
</varlistentry>
<varlistentry id="MALLOCX_ALIGN">
<term><constant>MALLOCX_ALIGN(<parameter>a</parameter>)
</constant></term>
<listitem><para>Align the memory allocation to start at an address
that is a multiple of <parameter>a</parameter>, where
<parameter>a</parameter> is a power of two. This macro does not
validate that <parameter>a</parameter> is a power of 2.
</para></listitem>
</varlistentry>
<varlistentry id="MALLOCX_ZERO">
<term><constant>MALLOCX_ZERO</constant></term>
<listitem><para>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.</para></listitem>
</varlistentry>
<varlistentry id="MALLOCX_TCACHE">
<term><constant>MALLOCX_TCACHE(<parameter>tc</parameter>)
</constant></term>
<listitem><para>Use the thread-specific cache (tcache) specified by
the identifier <parameter>tc</parameter>, which must have been
acquired via the <link
linkend="tcache.create"><mallctl>tcache.create</mallctl></link>
mallctl. This macro does not validate that
<parameter>tc</parameter> specifies a valid
identifier.</para></listitem>
</varlistentry>
<varlistentry id="MALLOC_TCACHE_NONE">
<term><constant>MALLOCX_TCACHE_NONE</constant></term>
<listitem><para>Do not use a thread-specific cache (tcache). Unless
<constant>MALLOCX_TCACHE(<parameter>tc</parameter>)</constant> or
<constant>MALLOCX_TCACHE_NONE</constant> is specified, an
automatically managed tcache will be used under many circumstances.
This macro cannot be used in the same <parameter>flags</parameter>
argument as
<constant>MALLOCX_TCACHE(<parameter>tc</parameter>)</constant>.</para></listitem>
</varlistentry>
<varlistentry id="MALLOCX_ARENA">
<term><constant>MALLOCX_ARENA(<parameter>a</parameter>)
</constant></term>
<listitem><para>Use the arena specified by the index
<parameter>a</parameter>. This macro has no effect for regions that
were allocated via an arena other than the one specified. This
macro does not validate that <parameter>a</parameter> specifies an
arena index in the valid range.</para></listitem>
</varlistentry>
</variablelist>
</para>
<para>The <function>mallocx<parameter/></function> function allocates at
least <parameter>size</parameter> bytes of memory, and returns a pointer
to the base address of the allocation. Behavior is undefined if
<parameter>size</parameter> is <constant>0</constant>, or if request size
overflows due to size class and/or alignment constraints.</para>
<para>The <function>rallocx<parameter/></function> function resizes the
allocation at <parameter>ptr</parameter> to be at least
<parameter>size</parameter> bytes, and returns a pointer to the base
address of the resulting allocation, which may or may not have moved from
its original location. Behavior is undefined if
<parameter>size</parameter> is <constant>0</constant>, or if request size
overflows due to size class and/or alignment constraints.</para>
<para>The <function>xallocx<parameter/></function> function resizes the
allocation at <parameter>ptr</parameter> in place to be at least
<parameter>size</parameter> bytes, and returns the real size of the
allocation. If <parameter>extra</parameter> is non-zero, an attempt is
made to resize the allocation to be at least <code
language="C">(<parameter>size</parameter> +
<parameter>extra</parameter>)</code> bytes, though inability to allocate
the extra byte(s) will not by itself result in failure to resize.
Behavior is undefined if <parameter>size</parameter> is
<constant>0</constant>, or if <code
language="C">(<parameter>size</parameter> + <parameter>extra</parameter>
&gt; <constant>SIZE_T_MAX</constant>)</code>.</para>
<para>The <function>sallocx<parameter/></function> function returns the
real size of the allocation at <parameter>ptr</parameter>.</para>
<para>The <function>dallocx<parameter/></function> function causes the
memory referenced by <parameter>ptr</parameter> to be made available for
future allocations.</para>
<para>The <function>sdallocx<parameter/></function> function is an
extension of <function>dallocx<parameter/></function> with a
<parameter>size</parameter> 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
<function>nallocx<parameter/></function> or
<function>sallocx<parameter/></function>.</para>
<para>The <function>nallocx<parameter/></function> function allocates no
memory, but it performs the same size computation as the
<function>mallocx<parameter/></function> function, and returns the real
size of the allocation that would result from the equivalent
<function>mallocx<parameter/></function> function call. Behavior is
undefined if <parameter>size</parameter> is <constant>0</constant>, or if
request size overflows due to size class and/or alignment
constraints.</para>
<para>The <function>mallctl<parameter/></function> function provides a
general interface for introspecting the memory allocator, as well as
setting modifiable parameters and triggering actions. The
period-separated <parameter>name</parameter> argument specifies a
location in a tree-structured namespace; see the <xref
linkend="mallctl_namespace" xrefstyle="template:%t"/> section for
documentation on the tree contents. To read a value, pass a pointer via
<parameter>oldp</parameter> to adequate space to contain the value, and a
pointer to its length via <parameter>oldlenp</parameter>; otherwise pass
<constant>NULL</constant> and <constant>NULL</constant>. Similarly, to
write a value, pass a pointer to the value via
<parameter>newp</parameter>, and its length via
<parameter>newlen</parameter>; otherwise pass <constant>NULL</constant>
and <constant>0</constant>.</para>
<para>The <function>mallctlnametomib<parameter/></function> 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 &ldquo;Management Information Base&rdquo; (MIB) that can be passed
repeatedly to <function>mallctlbymib<parameter/></function>. Upon
successful return from <function>mallctlnametomib<parameter/></function>,
<parameter>mibp</parameter> contains an array of
<parameter>*miblenp</parameter> integers, where
<parameter>*miblenp</parameter> is the lesser of the number of components
in <parameter>name</parameter> and the input value of
<parameter>*miblenp</parameter>. Thus it is possible to pass a
<parameter>*miblenp</parameter> 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
<link
linkend="arenas.bin.i.size"><mallctl>arenas.bin.2.size</mallctl></link>),
the corresponding MIB component will always be that integer. Therefore,
it is legitimate to construct code like the following: <programlisting
language="C"><![CDATA[
unsigned nbins, i;
2013-12-19 15:21:42 +08:00
size_t mib[4];
size_t len, miblen;
len = sizeof(nbins);
mallctl("arenas.nbins", &nbins, &len, NULL, 0);
miblen = 4;
2013-12-19 15:21:42 +08:00
mallctlnametomib("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... */
}]]></programlisting></para>
<para>The <function>malloc_stats_print<parameter/></function> function
writes human-readable summary statistics via the
<parameter>write_cb</parameter> callback function pointer and
<parameter>cbopaque</parameter> data passed to
<parameter>write_cb</parameter>, or
<function>malloc_message<parameter/></function> if
<parameter>write_cb</parameter> is <constant>NULL</constant>. This
function can be called repeatedly. General information that never
changes during execution can be omitted by specifying "g" as a character
within the <parameter>opts</parameter> string. Note that
<function>malloc_message<parameter/></function> uses the
<function>mallctl*<parameter/></function> functions internally, so
inconsistent statistics can be reported if multiple threads use these
functions simultaneously. If <option>--enable-stats</option> is
specified during configuration, &ldquo;m&rdquo; and &ldquo;a&rdquo; can
be specified to omit merged arena and per arena statistics, respectively;
&ldquo;b&rdquo;, &ldquo;l&rdquo;, and &ldquo;h&rdquo; 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.
</para>
<para>The <function>malloc_usable_size<parameter/></function> function
returns the usable size of the allocation pointed to by
<parameter>ptr</parameter>. The return value may be larger than the size
that was requested during allocation. The
<function>malloc_usable_size<parameter/></function> function is not a
mechanism for in-place <function>realloc<parameter/></function>; rather
it is provided solely as a tool for introspection purposes. Any
discrepancy between the requested allocation size and the size reported
by <function>malloc_usable_size<parameter/></function> should not be
depended on, since such behavior is entirely implementation-dependent.
</para>
</refsect2>
</refsect1>
<refsect1 id="tuning">
<title>TUNING</title>
<para>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.</para>
<para>The string specified via <option>--with-malloc-conf</option>, the
string pointed to by the global variable <varname>malloc_conf</varname>, the
&ldquo;name&rdquo; of the file referenced by the symbolic link named
<filename class="symlink">/etc/malloc.conf</filename>, and the value of the
environment variable <envar>MALLOC_CONF</envar>, will be interpreted, in
that order, from left to right as options. Note that
<varname>malloc_conf</varname> may be read before
<function>main<parameter/></function> is entered, so the declaration of
<varname>malloc_conf</varname> should specify an initializer that contains
the final value to be read by jemalloc. <option>--with-malloc-conf</option>
and <varname>malloc_conf</varname> are compile-time mechanisms, whereas
<filename class="symlink">/etc/malloc.conf</filename> and
<envar>MALLOC_CONF</envar> can be safely set any time prior to program
invocation.</para>
<para>An options string is a comma-separated list of option:value pairs.
There is one key corresponding to each <link
linkend="opt.abort"><mallctl>opt.*</mallctl></link> mallctl (see the <xref
linkend="mallctl_namespace" xrefstyle="template:%t"/> section for options
documentation). For example, <literal>abort:true,narenas:1</literal> sets
the <link linkend="opt.abort"><mallctl>opt.abort</mallctl></link> and <link
linkend="opt.narenas"><mallctl>opt.narenas</mallctl></link> 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.</para>
</refsect1>
<refsect1 id="implementation_notes">
<title>IMPLEMENTATION NOTES</title>
<para>Traditionally, allocators have used
<citerefentry><refentrytitle>sbrk</refentrytitle>
<manvolnum>2</manvolnum></citerefentry> to obtain memory, which is
suboptimal for several reasons, including race conditions, increased
fragmentation, and artificial limitations on maximum usable memory. If
<citerefentry><refentrytitle>sbrk</refentrytitle>
<manvolnum>2</manvolnum></citerefentry> is supported by the operating
system, this allocator uses both
<citerefentry><refentrytitle>mmap</refentrytitle>
<manvolnum>2</manvolnum></citerefentry> and
<citerefentry><refentrytitle>sbrk</refentrytitle>
<manvolnum>2</manvolnum></citerefentry>, in that order of preference;
otherwise only <citerefentry><refentrytitle>mmap</refentrytitle>
<manvolnum>2</manvolnum></citerefentry> is used.</para>
<para>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.</para>
<para>In addition to multiple arenas, unless
<option>--disable-tcache</option> 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.</para>
<para>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.</para>
<para>User objects are broken into three categories according to size:
2014-10-15 13:19:21 +08:00
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.</para>
<para>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.</para>
<para>Small objects are managed in groups by page runs. Each run maintains
2014-10-15 13:19:21 +08:00
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 <code
language="C">sizeof(<type>double</type>)</code>. 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 <link
linkend="opt.lg_chunk"><mallctl>opt.lg_chunk</mallctl></link> option), and
huge size classes extend from the chunk size up to one size class less than
the full address space size.</para>
<para>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.</para>
<para>The <function>realloc<parameter/></function>,
<function>rallocx<parameter/></function>, and
<function>xallocx<parameter/></function> functions may resize allocations
without moving them under limited circumstances. Unlike the
<function>*allocx<parameter/></function> 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
<function>realloc<parameter/></function> 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 <link
linkend="arena.i.chunk_hooks"><mallctl>arena.&lt;i&gt;.chunk_hooks</mallctl></link>).
Growth only succeeds if the trailing memory is currently available, and
additionally for huge size classes the chunk allocator must support
merging.</para>
<para>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 <xref
linkend="size_classes" xrefstyle="template:Table %n"/>.</para>
<table xml:id="size_classes" frame="all">
<title>Size classes</title>
<tgroup cols="3" colsep="1" rowsep="1">
<colspec colname="c1" align="left"/>
<colspec colname="c2" align="right"/>
<colspec colname="c3" align="left"/>
<thead>
<row>
<entry>Category</entry>
<entry>Spacing</entry>
<entry>Size</entry>
</row>
</thead>
<tbody>
<row>
2014-10-15 13:19:21 +08:00
<entry morerows="8">Small</entry>
<entry>lg</entry>
<entry>[8]</entry>
</row>
<row>
<entry>16</entry>
2014-10-15 13:19:21 +08:00
<entry>[16, 32, 48, 64, 80, 96, 112, 128]</entry>
</row>
<row>
<entry>32</entry>
<entry>[160, 192, 224, 256]</entry>
</row>
<row>
<entry>64</entry>
<entry>[320, 384, 448, 512]</entry>
</row>
<row>
<entry>128</entry>
<entry>[640, 768, 896, 1024]</entry>
</row>
<row>
<entry>256</entry>
<entry>[1280, 1536, 1792, 2048]</entry>
</row>
<row>
<entry>512</entry>
2014-10-15 13:19:21 +08:00
<entry>[2560, 3072, 3584, 4096]</entry>
</row>
<row>
<entry>1 KiB</entry>
<entry>[5 KiB, 6 KiB, 7 KiB, 8 KiB]</entry>
</row>
<row>
<entry>2 KiB</entry>
<entry>[10 KiB, 12 KiB, 14 KiB]</entry>
</row>
<row>
<entry morerows="7">Large</entry>
2014-10-15 13:19:21 +08:00
<entry>2 KiB</entry>
<entry>[16 KiB]</entry>
</row>
<row>
<entry>4 KiB</entry>
2014-10-15 13:19:21 +08:00
<entry>[20 KiB, 24 KiB, 28 KiB, 32 KiB]</entry>
</row>
<row>
<entry>8 KiB</entry>
<entry>[40 KiB, 48 KiB, 54 KiB, 64 KiB]</entry>
</row>
<row>
<entry>16 KiB</entry>
<entry>[80 KiB, 96 KiB, 112 KiB, 128 KiB]</entry>
</row>
<row>
<entry>32 KiB</entry>
<entry>[160 KiB, 192 KiB, 224 KiB, 256 KiB]</entry>
2014-10-15 13:19:21 +08:00
</row>
<row>
<entry>64 KiB</entry>
<entry>[320 KiB, 384 KiB, 448 KiB, 512 KiB]</entry>
</row>
<row>
<entry>128 KiB</entry>
<entry>[640 KiB, 768 KiB, 896 KiB, 1 MiB]</entry>
2014-10-15 13:19:21 +08:00
</row>
<row>
<entry>256 KiB</entry>
<entry>[1280 KiB, 1536 KiB, 1792 KiB]</entry>
</row>
<row>
<entry morerows="6">Huge</entry>
<entry>256 KiB</entry>
<entry>[2 MiB]</entry>
2014-10-15 13:19:21 +08:00
</row>
<row>
<entry>512 KiB</entry>
<entry>[2560 KiB, 3 MiB, 3584 KiB, 4 MiB]</entry>
2014-10-15 13:19:21 +08:00
</row>
<row>
<entry>1 MiB</entry>
<entry>[5 MiB, 6 MiB, 7 MiB, 8 MiB]</entry>
</row>
<row>
<entry>2 MiB</entry>
<entry>[10 MiB, 12 MiB, 14 MiB, 16 MiB]</entry>
</row>
<row>
<entry>4 MiB</entry>
2014-10-15 13:19:21 +08:00
<entry>[20 MiB, 24 MiB, 28 MiB, 32 MiB]</entry>
</row>
<row>
<entry>8 MiB</entry>
<entry>[40 MiB, 48 MiB, 56 MiB, 64 MiB]</entry>
</row>
<row>
<entry>...</entry>
<entry>...</entry>
</row>
</tbody>
</tgroup>
</table>
</refsect1>
<refsect1 id="mallctl_namespace">
<title>MALLCTL NAMESPACE</title>
<para>The following names are defined in the namespace accessible via the
<function>mallctl*<parameter/></function> functions. Value types are
specified in parentheses, their readable/writable statuses are encoded as
<literal>rw</literal>, <literal>r-</literal>, <literal>-w</literal>, or
<literal>--</literal>, and required build configuration flags follow, if
any. A name element encoded as <literal>&lt;i&gt;</literal> or
<literal>&lt;j&gt;</literal> indicates an integer component, where the
integer varies from 0 to some upper value that must be determined via
introspection. In the case of <mallctl>stats.arenas.&lt;i&gt;.*</mallctl>,
<literal>&lt;i&gt;</literal> equal to <link
linkend="arenas.narenas"><mallctl>arenas.narenas</mallctl></link> can be
used to access the summation of statistics from all arenas. Take special
note of the <link linkend="epoch"><mallctl>epoch</mallctl></link> mallctl,
which controls refreshing of cached dynamic statistics.</para>
<variablelist>
<varlistentry id="version">
<term>
<mallctl>version</mallctl>
(<type>const char *</type>)
<literal>r-</literal>
</term>
<listitem><para>Return the jemalloc version string.</para></listitem>
</varlistentry>
<varlistentry id="epoch">
<term>
<mallctl>epoch</mallctl>
(<type>uint64_t</type>)
<literal>rw</literal>
</term>
<listitem><para>If a value is passed in, refresh the data from which
the <function>mallctl*<parameter/></function> functions report values,
and increment the epoch. Return the current epoch. This is useful for
detecting whether another thread caused a refresh.</para></listitem>
</varlistentry>
<varlistentry id="config.cache_oblivious">
<term>
<mallctl>config.cache_oblivious</mallctl>
(<type>bool</type>)
<literal>r-</literal>
</term>
<listitem><para><option>--enable-cache-oblivious</option> was specified
during build configuration.</para></listitem>
</varlistentry>
<varlistentry id="config.debug">
<term>
<mallctl>config.debug</mallctl>
(<type>bool</type>)
<literal>r-</literal>
</term>
<listitem><para><option>--enable-debug</option> was specified during
build configuration.</para></listitem>
</varlistentry>
<varlistentry id="config.fill">
<term>
<mallctl>config.fill</mallctl>
(<type>bool</type>)
<literal>r-</literal>
</term>
<listitem><para><option>--enable-fill</option> was specified during
build configuration.</para></listitem>
</varlistentry>
<varlistentry id="config.lazy_lock">
<term>
<mallctl>config.lazy_lock</mallctl>
(<type>bool</type>)
<literal>r-</literal>
</term>
<listitem><para><option>--enable-lazy-lock</option> was specified
during build configuration.</para></listitem>
</varlistentry>
<varlistentry id="config.malloc_conf">
<term>
<mallctl>config.malloc_conf</mallctl>
(<type>const char *</type>)
<literal>r-</literal>
</term>
<listitem><para>Embedded configure-time-specified run-time options
string, empty unless <option>--with-malloc-conf</option> was specified
during build configuration.</para></listitem>
</varlistentry>
<varlistentry id="config.munmap">
<term>
<mallctl>config.munmap</mallctl>
(<type>bool</type>)
<literal>r-</literal>
</term>
<listitem><para><option>--enable-munmap</option> was specified during
build configuration.</para></listitem>
</varlistentry>
<varlistentry id="config.prof">
<term>
<mallctl>config.prof</mallctl>
(<type>bool</type>)
<literal>r-</literal>
</term>
<listitem><para><option>--enable-prof</option> was specified during
build configuration.</para></listitem>
</varlistentry>
<varlistentry id="config.prof_libgcc">
<term>
<mallctl>config.prof_libgcc</mallctl>
(<type>bool</type>)
<literal>r-</literal>
</term>
<listitem><para><option>--disable-prof-libgcc</option> was not
specified during build configuration.</para></listitem>
</varlistentry>
<varlistentry id="config.prof_libunwind">
<term>
<mallctl>config.prof_libunwind</mallctl>
(<type>bool</type>)
<literal>r-</literal>
</term>
<listitem><para><option>--enable-prof-libunwind</option> was specified
during build configuration.</para></listitem>
</varlistentry>
<varlistentry id="config.stats">
<term>
<mallctl>config.stats</mallctl>
(<type>bool</type>)
<literal>r-</literal>
</term>
<listitem><para><option>--enable-stats</option> was specified during
build configuration.</para></listitem>
</varlistentry>
<varlistentry id="config.tcache">
<term>
<mallctl>config.tcache</mallctl>
(<type>bool</type>)
<literal>r-</literal>
</term>
<listitem><para><option>--disable-tcache</option> was not specified
during build configuration.</para></listitem>
</varlistentry>
<varlistentry id="config.tls">
<term>
<mallctl>config.tls</mallctl>
(<type>bool</type>)
<literal>r-</literal>
</term>
<listitem><para><option>--disable-tls</option> was not specified during
build configuration.</para></listitem>
</varlistentry>
<varlistentry id="config.utrace">
<term>
<mallctl>config.utrace</mallctl>
(<type>bool</type>)
<literal>r-</literal>
</term>
<listitem><para><option>--enable-utrace</option> was specified during
build configuration.</para></listitem>
</varlistentry>
<varlistentry id="config.valgrind">
<term>
<mallctl>config.valgrind</mallctl>
(<type>bool</type>)
<literal>r-</literal>
</term>
<listitem><para><option>--enable-valgrind</option> was specified during
build configuration.</para></listitem>
</varlistentry>
<varlistentry id="config.xmalloc">
<term>
<mallctl>config.xmalloc</mallctl>
(<type>bool</type>)
<literal>r-</literal>
</term>
<listitem><para><option>--enable-xmalloc</option> was specified during
build configuration.</para></listitem>
</varlistentry>
<varlistentry id="opt.abort">
<term>
<mallctl>opt.abort</mallctl>
(<type>bool</type>)
<literal>r-</literal>
</term>
<listitem><para>Abort-on-warning enabled/disabled. If true, most
warnings are fatal. The process will call
<citerefentry><refentrytitle>abort</refentrytitle>
<manvolnum>3</manvolnum></citerefentry> in these cases. This option is
disabled by default unless <option>--enable-debug</option> is
specified during configuration, in which case it is enabled by default.
</para></listitem>
</varlistentry>
<varlistentry id="opt.dss">
<term>
<mallctl>opt.dss</mallctl>
(<type>const char *</type>)
<literal>r-</literal>
</term>
<listitem><para>dss (<citerefentry><refentrytitle>sbrk</refentrytitle>
<manvolnum>2</manvolnum></citerefentry>) allocation precedence as
related to <citerefentry><refentrytitle>mmap</refentrytitle>
<manvolnum>2</manvolnum></citerefentry> allocation. The following
settings are supported if
<citerefentry><refentrytitle>sbrk</refentrytitle>
<manvolnum>2</manvolnum></citerefentry> is supported by the operating
system: &ldquo;disabled&rdquo;, &ldquo;primary&rdquo;, and
&ldquo;secondary&rdquo;; otherwise only &ldquo;disabled&rdquo; is
supported. The default is &ldquo;secondary&rdquo; if
<citerefentry><refentrytitle>sbrk</refentrytitle>
<manvolnum>2</manvolnum></citerefentry> is supported by the operating
system; &ldquo;disabled&rdquo; otherwise.
</para></listitem>
</varlistentry>
<varlistentry id="opt.lg_chunk">
<term>
<mallctl>opt.lg_chunk</mallctl>
(<type>size_t</type>)
<literal>r-</literal>
</term>
<listitem><para>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).
</para></listitem>
</varlistentry>
<varlistentry id="opt.narenas">
<term>
<mallctl>opt.narenas</mallctl>
(<type>size_t</type>)
<literal>r-</literal>
</term>
<listitem><para>Maximum number of arenas to use for automatic
multiplexing of threads and arenas. The default is four times the
number of CPUs, or one if there is a single CPU.</para></listitem>
</varlistentry>
<varlistentry id="opt.purge">
<term>
<mallctl>opt.purge</mallctl>
(<type>const char *</type>)
<literal>r-</literal>
</term>
<listitem><para>Purge mode is &ldquo;ratio&rdquo; (default) or
&ldquo;decay&rdquo;. See <link
linkend="opt.lg_dirty_mult"><mallctl>opt.lg_dirty_mult</mallctl></link>
for details of the ratio mode. See <link
linkend="opt.decay_time"><mallctl>opt.decay_time</mallctl></link> for
details of the decay mode.</para></listitem>
</varlistentry>
<varlistentry id="opt.lg_dirty_mult">
<term>
<mallctl>opt.lg_dirty_mult</mallctl>
(<type>ssize_t</type>)
<literal>r-</literal>
</term>
<listitem><para>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 <citerefentry><refentrytitle>madvise</refentrytitle>
<manvolnum>2</manvolnum></citerefentry> 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 <link
linkend="arenas.lg_dirty_mult"><mallctl>arenas.lg_dirty_mult</mallctl></link>
and <link
linkend="arena.i.lg_dirty_mult"><mallctl>arena.&lt;i&gt;.lg_dirty_mult</mallctl></link>
for related dynamic control options.</para></listitem>
</varlistentry>
<varlistentry id="opt.decay_time">
<term>
<mallctl>opt.decay_time</mallctl>
(<type>ssize_t</type>)
<literal>r-</literal>
</term>
<listitem><para>Approximate time in seconds from the creation of a set
of unused dirty pages until an equivalent set of unused dirty pages is
purged and/or reused. The pages are incrementally purged according to a
sigmoidal decay curve that starts and ends with zero purge rate. A
decay time of 0 causes all unused dirty pages to be purged immediately
upon creation. A decay time of -1 disables purging. The default decay
time is 10 seconds. See <link
linkend="arenas.decay_time"><mallctl>arenas.decay_time</mallctl></link>
and <link
linkend="arena.i.decay_time"><mallctl>arena.&lt;i&gt;.decay_time</mallctl></link>
for related dynamic control options.
</para></listitem>
</varlistentry>
<varlistentry id="opt.stats_print">
<term>
<mallctl>opt.stats_print</mallctl>
(<type>bool</type>)
<literal>r-</literal>
</term>
<listitem><para>Enable/disable statistics printing at exit. If
enabled, the <function>malloc_stats_print<parameter/></function>
function is called at program exit via an
<citerefentry><refentrytitle>atexit</refentrytitle>
<manvolnum>3</manvolnum></citerefentry> function. If
<option>--enable-stats</option> 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, <function>atexit<parameter/></function> may
allocate memory during application initialization and then deadlock
internally when jemalloc in turn calls
<function>atexit<parameter/></function>, so this option is not
univerally usable (though the application can register its own
<function>atexit<parameter/></function> 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.</para></listitem>
</varlistentry>
<varlistentry id="opt.junk">
<term>
<mallctl>opt.junk</mallctl>
(<type>const char *</type>)
<literal>r-</literal>
[<option>--enable-fill</option>]
</term>
<listitem><para>Junk filling. If set to "alloc", each byte of
uninitialized allocated memory will be initialized to
<literal>0xa5</literal>. If set to "free", all deallocated memory will
be initialized to <literal>0x5a</literal>. 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 <option>--enable-debug</option> is specified
during configuration, in which case it is "true" by default unless
running inside <ulink
url="http://valgrind.org/">Valgrind</ulink>.</para></listitem>
</varlistentry>
<varlistentry id="opt.quarantine">
<term>
<mallctl>opt.quarantine</mallctl>
(<type>size_t</type>)
<literal>r-</literal>
[<option>--enable-fill</option>]
</term>
<listitem><para>Per thread quarantine size in bytes. If non-zero, each
thread maintains a FIFO object quarantine that stores up to the
specified number of bytes of memory. The quarantined memory is not
freed until it is released from quarantine, though it is immediately
junk-filled if the <link
linkend="opt.junk"><mallctl>opt.junk</mallctl></link> option is
enabled. This feature is of particular use in combination with <ulink
url="http://valgrind.org/">Valgrind</ulink>, which can detect attempts
to access quarantined objects. This is intended for debugging and will
impact performance negatively. The default quarantine size is 0 unless
running inside Valgrind, in which case the default is 16
MiB.</para></listitem>
</varlistentry>
<varlistentry id="opt.redzone">
<term>
<mallctl>opt.redzone</mallctl>
(<type>bool</type>)
<literal>r-</literal>
[<option>--enable-fill</option>]
</term>
<listitem><para>Redzones enabled/disabled. If enabled, small
allocations have redzones before and after them. Furthermore, if the
<link linkend="opt.junk"><mallctl>opt.junk</mallctl></link> option is
enabled, the redzones are checked for corruption during deallocation.
However, the primary intended purpose of this feature is to be used in
combination with <ulink url="http://valgrind.org/">Valgrind</ulink>,
which needs redzones in order to do effective buffer overflow/underflow
detection. This option is intended for debugging and will impact
performance negatively. This option is disabled by
default unless running inside Valgrind.</para></listitem>
</varlistentry>
<varlistentry id="opt.zero">
<term>
<mallctl>opt.zero</mallctl>
(<type>bool</type>)
<literal>r-</literal>
[<option>--enable-fill</option>]
</term>
<listitem><para>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
<function>realloc<parameter/></function> and
<function>rallocx<parameter/></function> 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.
</para></listitem>
</varlistentry>
<varlistentry id="opt.utrace">
<term>
<mallctl>opt.utrace</mallctl>
(<type>bool</type>)
<literal>r-</literal>
[<option>--enable-utrace</option>]
</term>
<listitem><para>Allocation tracing based on
<citerefentry><refentrytitle>utrace</refentrytitle>
<manvolnum>2</manvolnum></citerefentry> enabled/disabled. This option
is disabled by default.</para></listitem>
</varlistentry>
<varlistentry id="opt.xmalloc">
<term>
<mallctl>opt.xmalloc</mallctl>
(<type>bool</type>)
<literal>r-</literal>
[<option>--enable-xmalloc</option>]
</term>
<listitem><para>Abort-on-out-of-memory enabled/disabled. If enabled,
rather than returning failure for any allocation function, display a
diagnostic message on <constant>STDERR_FILENO</constant> and cause the
program to drop core (using
<citerefentry><refentrytitle>abort</refentrytitle>
<manvolnum>3</manvolnum></citerefentry>). If an application is
designed to depend on this behavior, set the option at compile time by
including the following in the source code:
<programlisting language="C"><![CDATA[
malloc_conf = "xmalloc:true";]]></programlisting>
This option is disabled by default.</para></listitem>
</varlistentry>
<varlistentry id="opt.tcache">
<term>
<mallctl>opt.tcache</mallctl>
(<type>bool</type>)
<literal>r-</literal>
[<option>--enable-tcache</option>]
</term>
<listitem><para>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 <link
linkend="opt.lg_tcache_max"><mallctl>opt.lg_tcache_max</mallctl></link>
option for related tuning information. This option is enabled by
default unless running inside <ulink
url="http://valgrind.org/">Valgrind</ulink>, in which case it is
forcefully disabled.</para></listitem>
</varlistentry>
<varlistentry id="opt.lg_tcache_max">
<term>
<mallctl>opt.lg_tcache_max</mallctl>
(<type>size_t</type>)
<literal>r-</literal>
[<option>--enable-tcache</option>]
</term>
<listitem><para>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).</para></listitem>
</varlistentry>
<varlistentry id="opt.prof">
<term>
<mallctl>opt.prof</mallctl>
(<type>bool</type>)
<literal>r-</literal>
[<option>--enable-prof</option>]
</term>
<listitem><para>Memory profiling enabled/disabled. If enabled, profile
memory allocation activity. See the <link
linkend="opt.prof_active"><mallctl>opt.prof_active</mallctl></link>
option for on-the-fly activation/deactivation. See the <link
linkend="opt.lg_prof_sample"><mallctl>opt.lg_prof_sample</mallctl></link>
option for probabilistic sampling control. See the <link
linkend="opt.prof_accum"><mallctl>opt.prof_accum</mallctl></link>
option for control of cumulative sample reporting. See the <link
linkend="opt.lg_prof_interval"><mallctl>opt.lg_prof_interval</mallctl></link>
option for information on interval-triggered profile dumping, the <link
linkend="opt.prof_gdump"><mallctl>opt.prof_gdump</mallctl></link>
option for information on high-water-triggered profile dumping, and the
<link linkend="opt.prof_final"><mallctl>opt.prof_final</mallctl></link>
option for final profile dumping. Profile output is compatible with
the <command>jeprof</command> command, which is based on the
<command>pprof</command> that is developed as part of the <ulink
url="http://code.google.com/p/gperftools/">gperftools
package</ulink>.</para></listitem>
</varlistentry>
<varlistentry id="opt.prof_prefix">
<term>
<mallctl>opt.prof_prefix</mallctl>
(<type>const char *</type>)
<literal>r-</literal>
[<option>--enable-prof</option>]
</term>
<listitem><para>Filename prefix for profile dumps. If the prefix is
set to the empty string, no automatic dumps will occur; this is
primarily useful for disabling the automatic final heap dump (which
also disables leak reporting, if enabled). The default prefix is
<filename>jeprof</filename>.</para></listitem>
</varlistentry>
<varlistentry id="opt.prof_active">
<term>
<mallctl>opt.prof_active</mallctl>
(<type>bool</type>)
<literal>r-</literal>
[<option>--enable-prof</option>]
</term>
<listitem><para>Profiling activated/deactivated. This is a secondary
control mechanism that makes it possible to start the application with
profiling enabled (see the <link
linkend="opt.prof"><mallctl>opt.prof</mallctl></link> option) but
inactive, then toggle profiling at any time during program execution
with the <link
linkend="prof.active"><mallctl>prof.active</mallctl></link> mallctl.
This option is enabled by default.</para></listitem>
</varlistentry>
<varlistentry id="opt.prof_thread_active_init">
<term>
<mallctl>opt.prof_thread_active_init</mallctl>
(<type>bool</type>)
<literal>r-</literal>
[<option>--enable-prof</option>]
</term>
<listitem><para>Initial setting for <link
linkend="thread.prof.active"><mallctl>thread.prof.active</mallctl></link>
in newly created threads. The initial setting for newly created threads
can also be changed during execution via the <link
linkend="prof.thread_active_init"><mallctl>prof.thread_active_init</mallctl></link>
mallctl. This option is enabled by default.</para></listitem>
</varlistentry>
<varlistentry id="opt.lg_prof_sample">
<term>
<mallctl>opt.lg_prof_sample</mallctl>
(<type>size_t</type>)
<literal>r-</literal>
[<option>--enable-prof</option>]
</term>
<listitem><para>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).</para></listitem>
</varlistentry>
<varlistentry id="opt.prof_accum">
<term>
<mallctl>opt.prof_accum</mallctl>
(<type>bool</type>)
<literal>r-</literal>
[<option>--enable-prof</option>]
</term>
<listitem><para>Reporting of cumulative object/byte counts in profile
dumps enabled/disabled. If this option is enabled, every unique
backtrace must be stored for the duration of execution. Depending on
the application, this can impose a large memory overhead, and the
cumulative counts are not always of interest. This option is disabled
by default.</para></listitem>
</varlistentry>
<varlistentry id="opt.lg_prof_interval">
<term>
<mallctl>opt.lg_prof_interval</mallctl>
(<type>ssize_t</type>)
<literal>r-</literal>
[<option>--enable-prof</option>]
</term>
<listitem><para>Average interval (log base 2) between memory profile
dumps, as measured in bytes of allocation activity. The actual
interval between dumps may be sporadic because decentralized allocation
counters are used to avoid synchronization bottlenecks. Profiles are
dumped to files named according to the pattern
<filename>&lt;prefix&gt;.&lt;pid&gt;.&lt;seq&gt;.i&lt;iseq&gt;.heap</filename>,
where <literal>&lt;prefix&gt;</literal> is controlled by the
<link
linkend="opt.prof_prefix"><mallctl>opt.prof_prefix</mallctl></link>
option. By default, interval-triggered profile dumping is disabled
(encoded as -1).
</para></listitem>
</varlistentry>
<varlistentry id="opt.prof_gdump">
<term>
<mallctl>opt.prof_gdump</mallctl>
(<type>bool</type>)
<literal>r-</literal>
[<option>--enable-prof</option>]
</term>
<listitem><para>Set the initial state of <link
linkend="prof.gdump"><mallctl>prof.gdump</mallctl></link>, which when
enabled triggers a memory profile dump every time the total virtual
memory exceeds the previous maximum. This option is disabled by
default.</para></listitem>
</varlistentry>
<varlistentry id="opt.prof_final">
<term>
<mallctl>opt.prof_final</mallctl>
(<type>bool</type>)
<literal>r-</literal>
[<option>--enable-prof</option>]
</term>
<listitem><para>Use an
<citerefentry><refentrytitle>atexit</refentrytitle>
<manvolnum>3</manvolnum></citerefentry> function to dump final memory
usage to a file named according to the pattern
<filename>&lt;prefix&gt;.&lt;pid&gt;.&lt;seq&gt;.f.heap</filename>,
where <literal>&lt;prefix&gt;</literal> is controlled by the <link
linkend="opt.prof_prefix"><mallctl>opt.prof_prefix</mallctl></link>
option. Note that <function>atexit<parameter/></function> may allocate
memory during application initialization and then deadlock internally
when jemalloc in turn calls <function>atexit<parameter/></function>, so
this option is not univerally usable (though the application can
register its own <function>atexit<parameter/></function> function with
equivalent functionality). This option is disabled by
default.</para></listitem>
</varlistentry>
<varlistentry id="opt.prof_leak">
<term>
<mallctl>opt.prof_leak</mallctl>
(<type>bool</type>)
<literal>r-</literal>
[<option>--enable-prof</option>]
</term>
<listitem><para>Leak reporting enabled/disabled. If enabled, use an
<citerefentry><refentrytitle>atexit</refentrytitle>
<manvolnum>3</manvolnum></citerefentry> function to report memory leaks
detected by allocation sampling. See the
<link linkend="opt.prof"><mallctl>opt.prof</mallctl></link> option for
information on analyzing heap profile output. This option is disabled
by default.</para></listitem>
</varlistentry>
<varlistentry id="thread.arena">
<term>
<mallctl>thread.arena</mallctl>
(<type>unsigned</type>)
<literal>rw</literal>
</term>
<listitem><para>Get or set the arena associated with the calling
thread. If the specified arena was not initialized beforehand (see the
<link
linkend="arenas.initialized"><mallctl>arenas.initialized</mallctl></link>
mallctl), it will be automatically initialized as a side effect of
calling this interface.</para></listitem>
</varlistentry>
<varlistentry id="thread.allocated">
<term>
<mallctl>thread.allocated</mallctl>
(<type>uint64_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Get the total number of bytes ever allocated by the
calling thread. This counter has the potential to wrap around; it is
up to the application to appropriately interpret the counter in such
cases.</para></listitem>
</varlistentry>
<varlistentry id="thread.allocatedp">
<term>
<mallctl>thread.allocatedp</mallctl>
(<type>uint64_t *</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Get a pointer to the the value that is returned by the
<link
linkend="thread.allocated"><mallctl>thread.allocated</mallctl></link>
mallctl. This is useful for avoiding the overhead of repeated
<function>mallctl*<parameter/></function> calls.</para></listitem>
</varlistentry>
<varlistentry id="thread.deallocated">
<term>
<mallctl>thread.deallocated</mallctl>
(<type>uint64_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Get the total number of bytes ever deallocated by the
calling thread. This counter has the potential to wrap around; it is
up to the application to appropriately interpret the counter in such
cases.</para></listitem>
</varlistentry>
<varlistentry id="thread.deallocatedp">
<term>
<mallctl>thread.deallocatedp</mallctl>
(<type>uint64_t *</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Get a pointer to the the value that is returned by the
<link
linkend="thread.deallocated"><mallctl>thread.deallocated</mallctl></link>
mallctl. This is useful for avoiding the overhead of repeated
<function>mallctl*<parameter/></function> calls.</para></listitem>
</varlistentry>
<varlistentry id="thread.tcache.enabled">
<term>
<mallctl>thread.tcache.enabled</mallctl>
(<type>bool</type>)
<literal>rw</literal>
[<option>--enable-tcache</option>]
</term>
<listitem><para>Enable/disable calling thread's tcache. The tcache is
implicitly flushed as a side effect of becoming
disabled (see <link
linkend="thread.tcache.flush"><mallctl>thread.tcache.flush</mallctl></link>).
</para></listitem>
</varlistentry>
<varlistentry id="thread.tcache.flush">
<term>
<mallctl>thread.tcache.flush</mallctl>
(<type>void</type>)
<literal>--</literal>
[<option>--enable-tcache</option>]
</term>
<listitem><para>Flush calling thread's thread-specific cache (tcache).
This interface releases all cached objects and internal data structures
associated with the calling thread's 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.</para></listitem>
</varlistentry>
<varlistentry id="thread.prof.name">
<term>
<mallctl>thread.prof.name</mallctl>
(<type>const char *</type>)
<literal>r-</literal> or
<literal>-w</literal>
[<option>--enable-prof</option>]
</term>
<listitem><para>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
2015-10-20 04:56:05 +08:00
name string must be nil-terminated and comprised only of characters in
the sets recognized
by <citerefentry><refentrytitle>isgraph</refentrytitle>
<manvolnum>3</manvolnum></citerefentry> and
<citerefentry><refentrytitle>isblank</refentrytitle>
<manvolnum>3</manvolnum></citerefentry>.</para></listitem>
</varlistentry>
<varlistentry id="thread.prof.active">
<term>
<mallctl>thread.prof.active</mallctl>
(<type>bool</type>)
<literal>rw</literal>
[<option>--enable-prof</option>]
</term>
<listitem><para>Control whether sampling is currently active for the
calling thread. This is an activation mechanism in addition to <link
linkend="prof.active"><mallctl>prof.active</mallctl></link>; both must
be active for the calling thread to sample. This flag is enabled by
default.</para></listitem>
</varlistentry>
<varlistentry id="tcache.create">
<term>
<mallctl>tcache.create</mallctl>
(<type>unsigned</type>)
<literal>r-</literal>
[<option>--enable-tcache</option>]
</term>
<listitem><para>Create an explicit thread-specific cache (tcache) and
return an identifier that can be passed to the <link
linkend="MALLOCX_TCACHE"><constant>MALLOCX_TCACHE(<parameter>tc</parameter>)</constant></link>
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.
</para></listitem>
</varlistentry>
<varlistentry id="tcache.flush">
<term>
<mallctl>tcache.flush</mallctl>
(<type>unsigned</type>)
<literal>-w</literal>
[<option>--enable-tcache</option>]
</term>
<listitem><para>Flush the specified thread-specific cache (tcache). The
same considerations apply to this interface as to <link
linkend="thread.tcache.flush"><mallctl>thread.tcache.flush</mallctl></link>,
2016-02-20 04:08:14 +08:00
except that the tcache will never be automatically discarded.
</para></listitem>
</varlistentry>
<varlistentry id="tcache.destroy">
<term>
<mallctl>tcache.destroy</mallctl>
(<type>unsigned</type>)
<literal>-w</literal>
[<option>--enable-tcache</option>]
</term>
<listitem><para>Flush the specified thread-specific cache (tcache) and
make the identifier available for use during a future tcache creation.
</para></listitem>
</varlistentry>
<varlistentry id="arena.i.purge">
<term>
<mallctl>arena.&lt;i&gt;.purge</mallctl>
(<type>void</type>)
<literal>--</literal>
</term>
<listitem><para>Purge all unused dirty pages for arena &lt;i&gt;, or for
all arenas if &lt;i&gt; equals <link
linkend="arenas.narenas"><mallctl>arenas.narenas</mallctl></link>.
</para></listitem>
</varlistentry>
<varlistentry id="arena.i.decay">
<term>
<mallctl>arena.&lt;i&gt;.decay</mallctl>
(<type>void</type>)
<literal>--</literal>
</term>
<listitem><para>Trigger decay-based purging of unused dirty pages for
arena &lt;i&gt;, or for all arenas if &lt;i&gt; equals <link
linkend="arenas.narenas"><mallctl>arenas.narenas</mallctl></link>.
The proportion of unused dirty pages to be purged depends on the current
time; see <link
linkend="opt.decay_time"><mallctl>opt.decay_time</mallctl></link> for
details.</para></listitem>
</varlistentry>
<varlistentry id="arena.i.dss">
<term>
<mallctl>arena.&lt;i&gt;.dss</mallctl>
(<type>const char *</type>)
<literal>rw</literal>
</term>
<listitem><para>Set the precedence of dss allocation as related to mmap
allocation for arena &lt;i&gt;, or for all arenas if &lt;i&gt; equals
<link
linkend="arenas.narenas"><mallctl>arenas.narenas</mallctl></link>. See
<link linkend="opt.dss"><mallctl>opt.dss</mallctl></link> for supported
settings.</para></listitem>
</varlistentry>
<varlistentry id="arena.i.lg_dirty_mult">
<term>
<mallctl>arena.&lt;i&gt;.lg_dirty_mult</mallctl>
(<type>ssize_t</type>)
<literal>rw</literal>
</term>
<listitem><para>Current per-arena minimum ratio (log base 2) of active
to dirty pages for arena &lt;i&gt;. Each time this interface is set and
the ratio is increased, pages are synchronously purged as necessary to
impose the new ratio. See <link
linkend="opt.lg_dirty_mult"><mallctl>opt.lg_dirty_mult</mallctl></link>
for additional information.</para></listitem>
</varlistentry>
<varlistentry id="arena.i.decay_time">
<term>
<mallctl>arena.&lt;i&gt;.decay_time</mallctl>
(<type>ssize_t</type>)
<literal>rw</literal>
</term>
<listitem><para>Current per-arena approximate time in seconds from the
creation of a set of unused dirty pages until an equivalent set of
unused dirty pages is purged and/or reused. Each time this interface is
set, all currently unused dirty pages are considered to have fully
decayed, which causes immediate purging of all unused dirty pages unless
the decay time is set to -1 (i.e. purging disabled). See <link
linkend="opt.decay_time"><mallctl>opt.decay_time</mallctl></link> for
additional information.</para></listitem>
</varlistentry>
<varlistentry id="arena.i.chunk_hooks">
<term>
<mallctl>arena.&lt;i&gt;.chunk_hooks</mallctl>
(<type>chunk_hooks_t</type>)
<literal>rw</literal>
</term>
<listitem><para>Get or set the chunk management hook functions for arena
&lt;i&gt;. The functions must be capable of operating on all extant
chunks associated with arena &lt;i&gt;, usually by passing unknown
chunks to the replaced functions. In practice, it is feasible to
control allocation for arenas created via <link
linkend="arenas.extend"><mallctl>arenas.extend</mallctl></link> 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.</para>
<programlisting language="C"><![CDATA[
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;]]></programlisting>
<para>The <type>chunk_hooks_t</type> 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.</para>
<funcsynopsis><funcprototype>
<funcdef>typedef void *<function>(chunk_alloc_t)</function></funcdef>
Attempt to expand huge allocations in-place. This adds support for expanding huge allocations in-place by requesting memory at a specific address from the chunk allocator. It's currently only implemented for the chunk recycling path, although in theory it could also be done by optimistically allocating new chunks. On Linux, it could attempt an in-place mremap. However, that won't work in practice since the heap is grown downwards and memory is not unmapped (in a normal build, at least). Repeated vector reallocation micro-benchmark: #include <string.h> #include <stdlib.h> int main(void) { for (size_t i = 0; i < 100; i++) { void *ptr = NULL; size_t old_size = 0; for (size_t size = 4; size < (1 << 30); size *= 2) { ptr = realloc(ptr, size); if (!ptr) return 1; memset(ptr + old_size, 0xff, size - old_size); old_size = size; } free(ptr); } } The glibc allocator fails to do any in-place reallocations on this benchmark once it passes the M_MMAP_THRESHOLD (default 128k) but it elides the cost of copies via mremap, which is currently not something that jemalloc can use. With this improvement, jemalloc still fails to do any in-place huge reallocations for the first outer loop, but then succeeds 100% of the time for the remaining 99 iterations. The time spent doing allocations and copies drops down to under 5%, with nearly all of it spent doing purging + faulting (when huge pages are disabled) and the array memset. An improved mremap API (MREMAP_RETAIN - #138) would be far more general but this is a portable optimization and would still be useful on Linux for xallocx. Numbers with transparent huge pages enabled: glibc (copies elided via MREMAP_MAYMOVE): 8.471s jemalloc: 17.816s jemalloc + no-op madvise: 13.236s jemalloc + this commit: 6.787s jemalloc + this commit + no-op madvise: 6.144s Numbers with transparent huge pages disabled: glibc (copies elided via MREMAP_MAYMOVE): 15.403s jemalloc: 39.456s jemalloc + no-op madvise: 12.768s jemalloc + this commit: 15.534s jemalloc + this commit + no-op madvise: 6.354s Closes #137
2014-10-04 13:39:32 +08:00
<paramdef>void *<parameter>chunk</parameter></paramdef>
<paramdef>size_t <parameter>size</parameter></paramdef>
<paramdef>size_t <parameter>alignment</parameter></paramdef>
<paramdef>bool *<parameter>zero</parameter></paramdef>
<paramdef>bool *<parameter>commit</parameter></paramdef>
<paramdef>unsigned <parameter>arena_ind</parameter></paramdef>
</funcprototype></funcsynopsis>
<literallayout></literallayout>
<para>A chunk allocation function conforms to the
<type>chunk_alloc_t</type> type and upon success returns a pointer to
<parameter>size</parameter> bytes of mapped memory on behalf of arena
<parameter>arena_ind</parameter> such that the chunk's base address is a
multiple of <parameter>alignment</parameter>, as well as setting
<parameter>*zero</parameter> to indicate whether the chunk is zeroed and
<parameter>*commit</parameter> to indicate whether the chunk is
committed. Upon error the function returns <constant>NULL</constant>
and leaves <parameter>*zero</parameter> and
<parameter>*commit</parameter> unmodified. The
<parameter>size</parameter> parameter is always a multiple of the chunk
size. The <parameter>alignment</parameter> parameter is always a power
of two at least as large as the chunk size. Zeroing is mandatory if
<parameter>*zero</parameter> is true upon function entry. Committing is
mandatory if <parameter>*commit</parameter> is true upon function entry.
If <parameter>chunk</parameter> is not <constant>NULL</constant>, the
returned pointer must be <parameter>chunk</parameter> on success or
<constant>NULL</constant> 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's <link
linkend="arena.i.dss"><mallctl>arena.&lt;i&gt;.dss</mallctl></link>
setting irrelevant.</para>
<funcsynopsis><funcprototype>
<funcdef>typedef bool <function>(chunk_dalloc_t)</function></funcdef>
<paramdef>void *<parameter>chunk</parameter></paramdef>
<paramdef>size_t <parameter>size</parameter></paramdef>
<paramdef>bool <parameter>committed</parameter></paramdef>
<paramdef>unsigned <parameter>arena_ind</parameter></paramdef>
</funcprototype></funcsynopsis>
<literallayout></literallayout>
<para>
A chunk deallocation function conforms to the
<type>chunk_dalloc_t</type> type and deallocates a
<parameter>chunk</parameter> of given <parameter>size</parameter> with
<parameter>committed</parameter>/decommited memory as indicated, on
behalf of arena <parameter>arena_ind</parameter>, 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.</para>
<funcsynopsis><funcprototype>
<funcdef>typedef bool <function>(chunk_commit_t)</function></funcdef>
<paramdef>void *<parameter>chunk</parameter></paramdef>
<paramdef>size_t <parameter>size</parameter></paramdef>
<paramdef>size_t <parameter>offset</parameter></paramdef>
<paramdef>size_t <parameter>length</parameter></paramdef>
<paramdef>unsigned <parameter>arena_ind</parameter></paramdef>
</funcprototype></funcsynopsis>
<literallayout></literallayout>
<para>A chunk commit function conforms to the
<type>chunk_commit_t</type> type and commits zeroed physical memory to
back pages within a <parameter>chunk</parameter> of given
<parameter>size</parameter> at <parameter>offset</parameter> bytes,
extending for <parameter>length</parameter> on behalf of arena
<parameter>arena_ind</parameter>, 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.</para>
<funcsynopsis><funcprototype>
<funcdef>typedef bool <function>(chunk_decommit_t)</function></funcdef>
<paramdef>void *<parameter>chunk</parameter></paramdef>
<paramdef>size_t <parameter>size</parameter></paramdef>
<paramdef>size_t <parameter>offset</parameter></paramdef>
<paramdef>size_t <parameter>length</parameter></paramdef>
<paramdef>unsigned <parameter>arena_ind</parameter></paramdef>
</funcprototype></funcsynopsis>
<literallayout></literallayout>
<para>A chunk decommit function conforms to the
<type>chunk_decommit_t</type> type and decommits any physical memory
that is backing pages within a <parameter>chunk</parameter> of given
<parameter>size</parameter> at <parameter>offset</parameter> bytes,
extending for <parameter>length</parameter> on behalf of arena
<parameter>arena_ind</parameter>, 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.</para>
<funcsynopsis><funcprototype>
<funcdef>typedef bool <function>(chunk_purge_t)</function></funcdef>
<paramdef>void *<parameter>chunk</parameter></paramdef>
<paramdef>size_t<parameter>size</parameter></paramdef>
<paramdef>size_t <parameter>offset</parameter></paramdef>
<paramdef>size_t <parameter>length</parameter></paramdef>
<paramdef>unsigned <parameter>arena_ind</parameter></paramdef>
</funcprototype></funcsynopsis>
<literallayout></literallayout>
<para>A chunk purge function conforms to the <type>chunk_purge_t</type>
type and optionally discards physical pages within the virtual memory
mapping associated with <parameter>chunk</parameter> of given
<parameter>size</parameter> at <parameter>offset</parameter> bytes,
extending for <parameter>length</parameter> on behalf of arena
<parameter>arena_ind</parameter>, returning false if pages within the
purged virtual memory range will be zero-filled the next time they are
accessed.</para>
<funcsynopsis><funcprototype>
<funcdef>typedef bool <function>(chunk_split_t)</function></funcdef>
<paramdef>void *<parameter>chunk</parameter></paramdef>
<paramdef>size_t <parameter>size</parameter></paramdef>
<paramdef>size_t <parameter>size_a</parameter></paramdef>
<paramdef>size_t <parameter>size_b</parameter></paramdef>
<paramdef>bool <parameter>committed</parameter></paramdef>
<paramdef>unsigned <parameter>arena_ind</parameter></paramdef>
</funcprototype></funcsynopsis>
<literallayout></literallayout>
<para>A chunk split function conforms to the <type>chunk_split_t</type>
type and optionally splits <parameter>chunk</parameter> of given
<parameter>size</parameter> into two adjacent chunks, the first of
<parameter>size_a</parameter> bytes, and the second of
<parameter>size_b</parameter> bytes, operating on
<parameter>committed</parameter>/decommitted memory as indicated, on
behalf of arena <parameter>arena_ind</parameter>, 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.</para>
<funcsynopsis><funcprototype>
<funcdef>typedef bool <function>(chunk_merge_t)</function></funcdef>
<paramdef>void *<parameter>chunk_a</parameter></paramdef>
<paramdef>size_t <parameter>size_a</parameter></paramdef>
<paramdef>void *<parameter>chunk_b</parameter></paramdef>
<paramdef>size_t <parameter>size_b</parameter></paramdef>
<paramdef>bool <parameter>committed</parameter></paramdef>
<paramdef>unsigned <parameter>arena_ind</parameter></paramdef>
</funcprototype></funcsynopsis>
<literallayout></literallayout>
<para>A chunk merge function conforms to the <type>chunk_merge_t</type>
type and optionally merges adjacent chunks,
<parameter>chunk_a</parameter> of given <parameter>size_a</parameter>
and <parameter>chunk_b</parameter> of given
<parameter>size_b</parameter> into one contiguous chunk, operating on
<parameter>committed</parameter>/decommitted memory as indicated, on
behalf of arena <parameter>arena_ind</parameter>, 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.</para>
</listitem>
</varlistentry>
<varlistentry id="arenas.narenas">
<term>
<mallctl>arenas.narenas</mallctl>
(<type>unsigned</type>)
<literal>r-</literal>
</term>
<listitem><para>Current limit on number of arenas.</para></listitem>
</varlistentry>
<varlistentry id="arenas.initialized">
<term>
<mallctl>arenas.initialized</mallctl>
(<type>bool *</type>)
<literal>r-</literal>
</term>
<listitem><para>An array of <link
linkend="arenas.narenas"><mallctl>arenas.narenas</mallctl></link>
booleans. Each boolean indicates whether the corresponding arena is
initialized.</para></listitem>
</varlistentry>
<varlistentry id="arenas.lg_dirty_mult">
<term>
<mallctl>arenas.lg_dirty_mult</mallctl>
(<type>ssize_t</type>)
<literal>rw</literal>
</term>
<listitem><para>Current default per-arena minimum ratio (log base 2) of
active to dirty pages, used to initialize <link
linkend="arena.i.lg_dirty_mult"><mallctl>arena.&lt;i&gt;.lg_dirty_mult</mallctl></link>
during arena creation. See <link
linkend="opt.lg_dirty_mult"><mallctl>opt.lg_dirty_mult</mallctl></link>
for additional information.</para></listitem>
</varlistentry>
<varlistentry id="arenas.decay_time">
<term>
<mallctl>arenas.decay_time</mallctl>
(<type>ssize_t</type>)
<literal>rw</literal>
</term>
<listitem><para>Current default per-arena approximate time in seconds
from the creation of a set of unused dirty pages until an equivalent set
of unused dirty pages is purged and/or reused, used to initialize <link
linkend="arena.i.decay_time"><mallctl>arena.&lt;i&gt;.decay_time</mallctl></link>
during arena creation. See <link
linkend="opt.decay_time"><mallctl>opt.decay_time</mallctl></link> for
additional information.</para></listitem>
</varlistentry>
<varlistentry id="arenas.quantum">
<term>
<mallctl>arenas.quantum</mallctl>
(<type>size_t</type>)
<literal>r-</literal>
</term>
<listitem><para>Quantum size.</para></listitem>
</varlistentry>
<varlistentry id="arenas.page">
<term>
<mallctl>arenas.page</mallctl>
(<type>size_t</type>)
<literal>r-</literal>
</term>
<listitem><para>Page size.</para></listitem>
</varlistentry>
<varlistentry id="arenas.tcache_max">
<term>
<mallctl>arenas.tcache_max</mallctl>
(<type>size_t</type>)
<literal>r-</literal>
[<option>--enable-tcache</option>]
</term>
<listitem><para>Maximum thread-cached size class.</para></listitem>
</varlistentry>
<varlistentry id="arenas.nbins">
<term>
<mallctl>arenas.nbins</mallctl>
(<type>unsigned</type>)
<literal>r-</literal>
</term>
<listitem><para>Number of bin size classes.</para></listitem>
</varlistentry>
<varlistentry id="arenas.nhbins">
<term>
<mallctl>arenas.nhbins</mallctl>
(<type>unsigned</type>)
<literal>r-</literal>
[<option>--enable-tcache</option>]
</term>
<listitem><para>Total number of thread cache bin size
classes.</para></listitem>
</varlistentry>
<varlistentry id="arenas.bin.i.size">
<term>
<mallctl>arenas.bin.&lt;i&gt;.size</mallctl>
(<type>size_t</type>)
<literal>r-</literal>
</term>
<listitem><para>Maximum size supported by size class.</para></listitem>
</varlistentry>
<varlistentry id="arenas.bin.i.nregs">
<term>
<mallctl>arenas.bin.&lt;i&gt;.nregs</mallctl>
(<type>uint32_t</type>)
<literal>r-</literal>
</term>
<listitem><para>Number of regions per page run.</para></listitem>
</varlistentry>
<varlistentry id="arenas.bin.i.run_size">
<term>
<mallctl>arenas.bin.&lt;i&gt;.run_size</mallctl>
(<type>size_t</type>)
<literal>r-</literal>
</term>
<listitem><para>Number of bytes per page run.</para></listitem>
</varlistentry>
<varlistentry id="arenas.nlruns">
<term>
<mallctl>arenas.nlruns</mallctl>
(<type>unsigned</type>)
<literal>r-</literal>
</term>
<listitem><para>Total number of large size classes.</para></listitem>
</varlistentry>
<varlistentry id="arenas.lrun.i.size">
<term>
<mallctl>arenas.lrun.&lt;i&gt;.size</mallctl>
(<type>size_t</type>)
<literal>r-</literal>
</term>
<listitem><para>Maximum size supported by this large size
class.</para></listitem>
</varlistentry>
<varlistentry id="arenas.nhchunks">
<term>
<mallctl>arenas.nhchunks</mallctl>
(<type>unsigned</type>)
<literal>r-</literal>
</term>
<listitem><para>Total number of huge size classes.</para></listitem>
</varlistentry>
<varlistentry id="arenas.hchunk.i.size">
<term>
<mallctl>arenas.hchunk.&lt;i&gt;.size</mallctl>
(<type>size_t</type>)
<literal>r-</literal>
</term>
<listitem><para>Maximum size supported by this huge size
class.</para></listitem>
</varlistentry>
<varlistentry id="arenas.extend">
<term>
<mallctl>arenas.extend</mallctl>
(<type>unsigned</type>)
<literal>r-</literal>
</term>
<listitem><para>Extend the array of arenas by appending a new arena,
and returning the new arena index.</para></listitem>
</varlistentry>
<varlistentry id="prof.thread_active_init">
<term>
<mallctl>prof.thread_active_init</mallctl>
(<type>bool</type>)
<literal>rw</literal>
[<option>--enable-prof</option>]
</term>
<listitem><para>Control the initial setting for <link
linkend="thread.prof.active"><mallctl>thread.prof.active</mallctl></link>
in newly created threads. See the <link
linkend="opt.prof_thread_active_init"><mallctl>opt.prof_thread_active_init</mallctl></link>
option for additional information.</para></listitem>
</varlistentry>
<varlistentry id="prof.active">
<term>
<mallctl>prof.active</mallctl>
(<type>bool</type>)
<literal>rw</literal>
[<option>--enable-prof</option>]
</term>
<listitem><para>Control whether sampling is currently active. See the
<link
linkend="opt.prof_active"><mallctl>opt.prof_active</mallctl></link>
option for additional information, as well as the interrelated <link
linkend="thread.prof.active"><mallctl>thread.prof.active</mallctl></link>
mallctl.</para></listitem>
</varlistentry>
<varlistentry id="prof.dump">
<term>
<mallctl>prof.dump</mallctl>
(<type>const char *</type>)
<literal>-w</literal>
[<option>--enable-prof</option>]
</term>
<listitem><para>Dump a memory profile to the specified file, or if NULL
is specified, to a file according to the pattern
<filename>&lt;prefix&gt;.&lt;pid&gt;.&lt;seq&gt;.m&lt;mseq&gt;.heap</filename>,
where <literal>&lt;prefix&gt;</literal> is controlled by the
<link
linkend="opt.prof_prefix"><mallctl>opt.prof_prefix</mallctl></link>
option.</para></listitem>
</varlistentry>
<varlistentry id="prof.gdump">
<term>
<mallctl>prof.gdump</mallctl>
(<type>bool</type>)
<literal>rw</literal>
[<option>--enable-prof</option>]
</term>
<listitem><para>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
<filename>&lt;prefix&gt;.&lt;pid&gt;.&lt;seq&gt;.u&lt;useq&gt;.heap</filename>,
where <literal>&lt;prefix&gt;</literal> is controlled by the <link
linkend="opt.prof_prefix"><mallctl>opt.prof_prefix</mallctl></link>
option.</para></listitem>
</varlistentry>
<varlistentry id="prof.reset">
<term>
<mallctl>prof.reset</mallctl>
(<type>size_t</type>)
<literal>-w</literal>
[<option>--enable-prof</option>]
</term>
<listitem><para>Reset all memory profile statistics, and optionally
update the sample rate (see <link
linkend="opt.lg_prof_sample"><mallctl>opt.lg_prof_sample</mallctl></link>
and <link
linkend="prof.lg_sample"><mallctl>prof.lg_sample</mallctl></link>).
</para></listitem>
</varlistentry>
<varlistentry id="prof.lg_sample">
<term>
<mallctl>prof.lg_sample</mallctl>
(<type>size_t</type>)
<literal>r-</literal>
[<option>--enable-prof</option>]
</term>
<listitem><para>Get the current sample rate (see <link
linkend="opt.lg_prof_sample"><mallctl>opt.lg_prof_sample</mallctl></link>).
</para></listitem>
</varlistentry>
<varlistentry id="prof.interval">
<term>
<mallctl>prof.interval</mallctl>
(<type>uint64_t</type>)
<literal>r-</literal>
[<option>--enable-prof</option>]
</term>
<listitem><para>Average number of bytes allocated between
inverval-based profile dumps. See the
<link
linkend="opt.lg_prof_interval"><mallctl>opt.lg_prof_interval</mallctl></link>
option for additional information.</para></listitem>
</varlistentry>
<varlistentry id="stats.cactive">
<term>
<mallctl>stats.cactive</mallctl>
(<type>size_t *</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Pointer to a counter that contains an approximate count
of the current number of bytes in active pages. The estimate may be
2014-10-15 13:20:00 +08:00
high, but never low, because each arena rounds up when computing its
contribution to the counter. Note that the <link
linkend="epoch"><mallctl>epoch</mallctl></link> 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.
</para></listitem>
</varlistentry>
<varlistentry id="stats.allocated">
<term>
<mallctl>stats.allocated</mallctl>
(<type>size_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Total number of bytes allocated by the
application.</para></listitem>
</varlistentry>
<varlistentry id="stats.active">
<term>
<mallctl>stats.active</mallctl>
(<type>size_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>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 <link
linkend="stats.allocated"><mallctl>stats.allocated</mallctl></link>.
This does not include <link linkend="stats.arenas.i.pdirty">
<mallctl>stats.arenas.&lt;i&gt;.pdirty</mallctl></link>, nor pages
entirely devoted to allocator metadata.</para></listitem>
</varlistentry>
<varlistentry id="stats.metadata">
<term>
<mallctl>stats.metadata</mallctl>
(<type>size_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Total number of bytes dedicated to metadata, which
comprise base allocations used for bootstrap-sensitive internal
allocator data structures, arena chunk headers (see <link
linkend="stats.arenas.i.metadata.mapped"><mallctl>stats.arenas.&lt;i&gt;.metadata.mapped</mallctl></link>),
and internal allocations (see <link
linkend="stats.arenas.i.metadata.allocated"><mallctl>stats.arenas.&lt;i&gt;.metadata.allocated</mallctl></link>).</para></listitem>
</varlistentry>
2015-03-24 08:25:57 +08:00
<varlistentry id="stats.resident">
<term>
<mallctl>stats.resident</mallctl>
(<type>size_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>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 <link
linkend="stats.active"><mallctl>stats.active</mallctl></link>.</para></listitem>
</varlistentry>
<varlistentry id="stats.mapped">
<term>
<mallctl>stats.mapped</mallctl>
(<type>size_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
2015-03-24 08:25:57 +08:00
<listitem><para>Total number of bytes in active chunks mapped by the
allocator. This is a multiple of the chunk size, and is larger than
<link linkend="stats.active"><mallctl>stats.active</mallctl></link>.
This does not include inactive chunks, even those that contain unused
dirty pages, which means that there is no strict ordering between this
and <link
linkend="stats.resident"><mallctl>stats.resident</mallctl></link>.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.dss">
<term>
<mallctl>stats.arenas.&lt;i&gt;.dss</mallctl>
(<type>const char *</type>)
<literal>r-</literal>
</term>
<listitem><para>dss (<citerefentry><refentrytitle>sbrk</refentrytitle>
<manvolnum>2</manvolnum></citerefentry>) allocation precedence as
related to <citerefentry><refentrytitle>mmap</refentrytitle>
<manvolnum>2</manvolnum></citerefentry> allocation. See <link
linkend="opt.dss"><mallctl>opt.dss</mallctl></link> for details.
</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.lg_dirty_mult">
<term>
<mallctl>stats.arenas.&lt;i&gt;.lg_dirty_mult</mallctl>
(<type>ssize_t</type>)
<literal>r-</literal>
</term>
<listitem><para>Minimum ratio (log base 2) of active to dirty pages.
See <link
linkend="opt.lg_dirty_mult"><mallctl>opt.lg_dirty_mult</mallctl></link>
for details.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.decay_time">
<term>
<mallctl>stats.arenas.&lt;i&gt;.decay_time</mallctl>
(<type>ssize_t</type>)
<literal>r-</literal>
</term>
<listitem><para>Approximate time in seconds from the creation of a set
of unused dirty pages until an equivalent set of unused dirty pages is
purged and/or reused. See <link
linkend="opt.decay_time"><mallctl>opt.decay_time</mallctl></link>
for details.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.nthreads">
<term>
<mallctl>stats.arenas.&lt;i&gt;.nthreads</mallctl>
(<type>unsigned</type>)
<literal>r-</literal>
</term>
<listitem><para>Number of threads currently assigned to
arena.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.pactive">
<term>
<mallctl>stats.arenas.&lt;i&gt;.pactive</mallctl>
(<type>size_t</type>)
<literal>r-</literal>
</term>
<listitem><para>Number of pages in active runs.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.pdirty">
<term>
<mallctl>stats.arenas.&lt;i&gt;.pdirty</mallctl>
(<type>size_t</type>)
<literal>r-</literal>
</term>
<listitem><para>Number of pages within unused runs that are potentially
dirty, and for which <function>madvise<parameter>...</parameter>
<parameter><constant>MADV_DONTNEED</constant></parameter></function> or
similar has not been called.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.mapped">
<term>
<mallctl>stats.arenas.&lt;i&gt;.mapped</mallctl>
(<type>size_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Number of mapped bytes.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.metadata.mapped">
<term>
<mallctl>stats.arenas.&lt;i&gt;.metadata.mapped</mallctl>
(<type>size_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Number of mapped bytes in arena chunk headers, which
track the states of the non-metadata pages.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.metadata.allocated">
<term>
<mallctl>stats.arenas.&lt;i&gt;.metadata.allocated</mallctl>
(<type>size_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>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 <link
linkend="stats.metadata"><mallctl>stats.metadata</mallctl></link> and
<link
linkend="stats.arenas.i.metadata.mapped"><mallctl>stats.arenas.&lt;i&gt;.metadata.mapped</mallctl></link>
because it overlaps with e.g. the <link
linkend="stats.allocated"><mallctl>stats.allocated</mallctl></link> and
<link linkend="stats.active"><mallctl>stats.active</mallctl></link>
statistics, whereas the other metadata statistics do
not.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.npurge">
<term>
<mallctl>stats.arenas.&lt;i&gt;.npurge</mallctl>
(<type>uint64_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Number of dirty page purge sweeps performed.
</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.nmadvise">
<term>
<mallctl>stats.arenas.&lt;i&gt;.nmadvise</mallctl>
(<type>uint64_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Number of <function>madvise<parameter>...</parameter>
<parameter><constant>MADV_DONTNEED</constant></parameter></function> or
similar calls made to purge dirty pages.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.purged">
<term>
<mallctl>stats.arenas.&lt;i&gt;.purged</mallctl>
(<type>uint64_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Number of pages purged.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.small.allocated">
<term>
<mallctl>stats.arenas.&lt;i&gt;.small.allocated</mallctl>
(<type>size_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Number of bytes currently allocated by small objects.
</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.small.nmalloc">
<term>
<mallctl>stats.arenas.&lt;i&gt;.small.nmalloc</mallctl>
(<type>uint64_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Cumulative number of allocation requests served by
small bins.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.small.ndalloc">
<term>
<mallctl>stats.arenas.&lt;i&gt;.small.ndalloc</mallctl>
(<type>uint64_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Cumulative number of small objects returned to bins.
</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.small.nrequests">
<term>
<mallctl>stats.arenas.&lt;i&gt;.small.nrequests</mallctl>
(<type>uint64_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Cumulative number of small allocation requests.
</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.large.allocated">
<term>
<mallctl>stats.arenas.&lt;i&gt;.large.allocated</mallctl>
(<type>size_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Number of bytes currently allocated by large objects.
</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.large.nmalloc">
<term>
<mallctl>stats.arenas.&lt;i&gt;.large.nmalloc</mallctl>
(<type>uint64_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Cumulative number of large allocation requests served
directly by the arena.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.large.ndalloc">
<term>
<mallctl>stats.arenas.&lt;i&gt;.large.ndalloc</mallctl>
(<type>uint64_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Cumulative number of large deallocation requests served
directly by the arena.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.large.nrequests">
<term>
<mallctl>stats.arenas.&lt;i&gt;.large.nrequests</mallctl>
(<type>uint64_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Cumulative number of large allocation requests.
</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.huge.allocated">
<term>
<mallctl>stats.arenas.&lt;i&gt;.huge.allocated</mallctl>
(<type>size_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Number of bytes currently allocated by huge objects.
</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.huge.nmalloc">
<term>
<mallctl>stats.arenas.&lt;i&gt;.huge.nmalloc</mallctl>
(<type>uint64_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Cumulative number of huge allocation requests served
directly by the arena.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.huge.ndalloc">
<term>
<mallctl>stats.arenas.&lt;i&gt;.huge.ndalloc</mallctl>
(<type>uint64_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Cumulative number of huge deallocation requests served
directly by the arena.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.huge.nrequests">
<term>
<mallctl>stats.arenas.&lt;i&gt;.huge.nrequests</mallctl>
(<type>uint64_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Cumulative number of huge allocation requests.
</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.bins.j.nmalloc">
<term>
<mallctl>stats.arenas.&lt;i&gt;.bins.&lt;j&gt;.nmalloc</mallctl>
(<type>uint64_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Cumulative number of allocations served by bin.
</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.bins.j.ndalloc">
<term>
<mallctl>stats.arenas.&lt;i&gt;.bins.&lt;j&gt;.ndalloc</mallctl>
(<type>uint64_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Cumulative number of allocations returned to bin.
</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.bins.j.nrequests">
<term>
<mallctl>stats.arenas.&lt;i&gt;.bins.&lt;j&gt;.nrequests</mallctl>
(<type>uint64_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Cumulative number of allocation
requests.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.bins.j.curregs">
<term>
<mallctl>stats.arenas.&lt;i&gt;.bins.&lt;j&gt;.curregs</mallctl>
(<type>size_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Current number of regions for this size
class.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.bins.j.nfills">
<term>
<mallctl>stats.arenas.&lt;i&gt;.bins.&lt;j&gt;.nfills</mallctl>
(<type>uint64_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option> <option>--enable-tcache</option>]
</term>
<listitem><para>Cumulative number of tcache fills.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.bins.j.nflushes">
<term>
<mallctl>stats.arenas.&lt;i&gt;.bins.&lt;j&gt;.nflushes</mallctl>
(<type>uint64_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option> <option>--enable-tcache</option>]
</term>
<listitem><para>Cumulative number of tcache flushes.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.bins.j.nruns">
<term>
<mallctl>stats.arenas.&lt;i&gt;.bins.&lt;j&gt;.nruns</mallctl>
(<type>uint64_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Cumulative number of runs created.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.bins.j.nreruns">
<term>
<mallctl>stats.arenas.&lt;i&gt;.bins.&lt;j&gt;.nreruns</mallctl>
(<type>uint64_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Cumulative number of times the current run from which
to allocate changed.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.bins.j.curruns">
<term>
<mallctl>stats.arenas.&lt;i&gt;.bins.&lt;j&gt;.curruns</mallctl>
(<type>size_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Current number of runs.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.lruns.j.nmalloc">
<term>
<mallctl>stats.arenas.&lt;i&gt;.lruns.&lt;j&gt;.nmalloc</mallctl>
(<type>uint64_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Cumulative number of allocation requests for this size
class served directly by the arena.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.lruns.j.ndalloc">
<term>
<mallctl>stats.arenas.&lt;i&gt;.lruns.&lt;j&gt;.ndalloc</mallctl>
(<type>uint64_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Cumulative number of deallocation requests for this
size class served directly by the arena.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.lruns.j.nrequests">
<term>
<mallctl>stats.arenas.&lt;i&gt;.lruns.&lt;j&gt;.nrequests</mallctl>
(<type>uint64_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Cumulative number of allocation requests for this size
class.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.lruns.j.curruns">
<term>
<mallctl>stats.arenas.&lt;i&gt;.lruns.&lt;j&gt;.curruns</mallctl>
(<type>size_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Current number of runs for this size class.
</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.hchunks.j.nmalloc">
<term>
<mallctl>stats.arenas.&lt;i&gt;.hchunks.&lt;j&gt;.nmalloc</mallctl>
(<type>uint64_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Cumulative number of allocation requests for this size
class served directly by the arena.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.hchunks.j.ndalloc">
<term>
<mallctl>stats.arenas.&lt;i&gt;.hchunks.&lt;j&gt;.ndalloc</mallctl>
(<type>uint64_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Cumulative number of deallocation requests for this
size class served directly by the arena.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.hchunks.j.nrequests">
<term>
<mallctl>stats.arenas.&lt;i&gt;.hchunks.&lt;j&gt;.nrequests</mallctl>
(<type>uint64_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Cumulative number of allocation requests for this size
class.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.hchunks.j.curhchunks">
<term>
<mallctl>stats.arenas.&lt;i&gt;.hchunks.&lt;j&gt;.curhchunks</mallctl>
(<type>size_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Current number of huge allocations for this size class.
</para></listitem>
</varlistentry>
</variablelist>
</refsect1>
<refsect1 id="debugging_malloc_problems">
<title>DEBUGGING MALLOC PROBLEMS</title>
<para>When debugging, it is a good idea to configure/build jemalloc with
the <option>--enable-debug</option> and <option>--enable-fill</option>
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.</para>
<para>Programs often accidentally depend on &ldquo;uninitialized&rdquo;
memory actually being filled with zero bytes. Junk filling
(see the <link linkend="opt.junk"><mallctl>opt.junk</mallctl></link>
option) tends to expose such bugs in the form of obviously incorrect
results and/or coredumps. Conversely, zero
filling (see the <link
linkend="opt.zero"><mallctl>opt.zero</mallctl></link> option) eliminates
the symptoms of such bugs. Between these two options, it is usually
possible to quickly detect, diagnose, and eliminate such bugs.</para>
<para>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 <ulink url="http://valgrind.org/">Valgrind</ulink> tool if the
<option>--enable-valgrind</option> configuration option is enabled.</para>
</refsect1>
<refsect1 id="diagnostic_messages">
<title>DIAGNOSTIC MESSAGES</title>
<para>If any of the memory allocation/deallocation functions detect an
error or warning condition, a message will be printed to file descriptor
<constant>STDERR_FILENO</constant>. Errors will result in the process
dumping core. If the <link
linkend="opt.abort"><mallctl>opt.abort</mallctl></link> option is set, most
warnings are treated as errors.</para>
<para>The <varname>malloc_message</varname> variable allows the programmer
to override the function which emits the text strings forming the errors
and warnings if for some reason the <constant>STDERR_FILENO</constant> file
descriptor is not suitable for this.
<function>malloc_message<parameter/></function> takes the
<parameter>cbopaque</parameter> pointer argument that is
<constant>NULL</constant> unless overridden by the arguments in a call to
<function>malloc_stats_print<parameter/></function>, 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.</para>
<para>All messages are prefixed by
&ldquo;<computeroutput>&lt;jemalloc&gt;: </computeroutput>&rdquo;.</para>
</refsect1>
<refsect1 id="return_values">
<title>RETURN VALUES</title>
<refsect2>
<title>Standard API</title>
<para>The <function>malloc<parameter/></function> and
<function>calloc<parameter/></function> functions return a pointer to the
allocated memory if successful; otherwise a <constant>NULL</constant>
pointer is returned and <varname>errno</varname> is set to
<errorname>ENOMEM</errorname>.</para>
<para>The <function>posix_memalign<parameter/></function> function
returns the value 0 if successful; otherwise it returns an error value.
The <function>posix_memalign<parameter/></function> function will fail
if:
<variablelist>
<varlistentry>
<term><errorname>EINVAL</errorname></term>
<listitem><para>The <parameter>alignment</parameter> parameter is
not a power of 2 at least as large as
<code language="C">sizeof(<type>void *</type>)</code>.
</para></listitem>
</varlistentry>
<varlistentry>
<term><errorname>ENOMEM</errorname></term>
<listitem><para>Memory allocation error.</para></listitem>
</varlistentry>
</variablelist>
</para>
<para>The <function>aligned_alloc<parameter/></function> function returns
a pointer to the allocated memory if successful; otherwise a
<constant>NULL</constant> pointer is returned and
<varname>errno</varname> is set. The
<function>aligned_alloc<parameter/></function> function will fail if:
<variablelist>
<varlistentry>
<term><errorname>EINVAL</errorname></term>
<listitem><para>The <parameter>alignment</parameter> parameter is
not a power of 2.
</para></listitem>
</varlistentry>
<varlistentry>
<term><errorname>ENOMEM</errorname></term>
<listitem><para>Memory allocation error.</para></listitem>
</varlistentry>
</variablelist>
</para>
<para>The <function>realloc<parameter/></function> function returns a
pointer, possibly identical to <parameter>ptr</parameter>, to the
allocated memory if successful; otherwise a <constant>NULL</constant>
pointer is returned, and <varname>errno</varname> is set to
<errorname>ENOMEM</errorname> if the error was the result of an
allocation failure. The <function>realloc<parameter/></function>
function always leaves the original buffer intact when an error occurs.
</para>
<para>The <function>free<parameter/></function> function returns no
value.</para>
</refsect2>
<refsect2>
<title>Non-standard API</title>
<para>The <function>mallocx<parameter/></function> and
<function>rallocx<parameter/></function> functions return a pointer to
the allocated memory if successful; otherwise a <constant>NULL</constant>
pointer is returned to indicate insufficient contiguous memory was
available to service the allocation request. </para>
<para>The <function>xallocx<parameter/></function> function returns the
real size of the resulting resized allocation pointed to by
<parameter>ptr</parameter>, which is a value less than
<parameter>size</parameter> if the allocation could not be adequately
grown in place. </para>
<para>The <function>sallocx<parameter/></function> function returns the
real size of the allocation pointed to by <parameter>ptr</parameter>.
</para>
<para>The <function>nallocx<parameter/></function> returns the real size
that would result from a successful equivalent
<function>mallocx<parameter/></function> function call, or zero if
insufficient memory is available to perform the size computation. </para>
<para>The <function>mallctl<parameter/></function>,
<function>mallctlnametomib<parameter/></function>, and
<function>mallctlbymib<parameter/></function> functions return 0 on
success; otherwise they return an error value. The functions will fail
if:
<variablelist>
<varlistentry>
<term><errorname>EINVAL</errorname></term>
<listitem><para><parameter>newp</parameter> is not
<constant>NULL</constant>, and <parameter>newlen</parameter> is too
large or too small. Alternatively, <parameter>*oldlenp</parameter>
is too large or too small; in this case as much data as possible
are read despite the error.</para></listitem>
</varlistentry>
<varlistentry>
<term><errorname>ENOENT</errorname></term>
<listitem><para><parameter>name</parameter> or
<parameter>mib</parameter> specifies an unknown/invalid
value.</para></listitem>
</varlistentry>
<varlistentry>
<term><errorname>EPERM</errorname></term>
<listitem><para>Attempt to read or write void value, or attempt to
write read-only value.</para></listitem>
</varlistentry>
<varlistentry>
<term><errorname>EAGAIN</errorname></term>
<listitem><para>A memory allocation failure
occurred.</para></listitem>
</varlistentry>
<varlistentry>
<term><errorname>EFAULT</errorname></term>
<listitem><para>An interface with side effects failed in some way
not directly related to <function>mallctl*<parameter/></function>
read/write processing.</para></listitem>
</varlistentry>
</variablelist>
</para>
<para>The <function>malloc_usable_size<parameter/></function> function
returns the usable size of the allocation pointed to by
<parameter>ptr</parameter>. </para>
</refsect2>
</refsect1>
<refsect1 id="environment">
<title>ENVIRONMENT</title>
<para>The following environment variable affects the execution of the
allocation functions:
<variablelist>
<varlistentry>
<term><envar>MALLOC_CONF</envar></term>
<listitem><para>If the environment variable
<envar>MALLOC_CONF</envar> is set, the characters it contains
will be interpreted as options.</para></listitem>
</varlistentry>
</variablelist>
</para>
</refsect1>
<refsect1 id="examples">
<title>EXAMPLES</title>
<para>To dump core whenever a problem occurs:
<screen>ln -s 'abort:true' /etc/malloc.conf</screen>
</para>
<para>To specify in the source a chunk size that is 16 MiB:
<programlisting language="C"><![CDATA[
malloc_conf = "lg_chunk:24";]]></programlisting></para>
</refsect1>
<refsect1 id="see_also">
<title>SEE ALSO</title>
<para><citerefentry><refentrytitle>madvise</refentrytitle>
<manvolnum>2</manvolnum></citerefentry>,
<citerefentry><refentrytitle>mmap</refentrytitle>
<manvolnum>2</manvolnum></citerefentry>,
<citerefentry><refentrytitle>sbrk</refentrytitle>
<manvolnum>2</manvolnum></citerefentry>,
<citerefentry><refentrytitle>utrace</refentrytitle>
<manvolnum>2</manvolnum></citerefentry>,
<citerefentry><refentrytitle>alloca</refentrytitle>
<manvolnum>3</manvolnum></citerefentry>,
<citerefentry><refentrytitle>atexit</refentrytitle>
<manvolnum>3</manvolnum></citerefentry>,
<citerefentry><refentrytitle>getpagesize</refentrytitle>
<manvolnum>3</manvolnum></citerefentry></para>
</refsect1>
<refsect1 id="standards">
<title>STANDARDS</title>
<para>The <function>malloc<parameter/></function>,
<function>calloc<parameter/></function>,
<function>realloc<parameter/></function>, and
<function>free<parameter/></function> functions conform to ISO/IEC
9899:1990 (&ldquo;ISO C90&rdquo;).</para>
<para>The <function>posix_memalign<parameter/></function> function conforms
to IEEE Std 1003.1-2001 (&ldquo;POSIX.1&rdquo;).</para>
</refsect1>
</refentry>