Commit 4d5911b4 authored by Yoav Steinberg's avatar Yoav Steinberg
Browse files

Merge commit '220a0f08' as 'deps/jemalloc'

parents 4a884343 220a0f08
dnl Process this file with autoconf to produce a configure script.
AC_PREREQ(2.68)
AC_INIT([Makefile.in])
AC_CONFIG_AUX_DIR([build-aux])
dnl ============================================================================
dnl Custom macro definitions.
dnl JE_CONCAT_VVV(r, a, b)
dnl
dnl Set $r to the concatenation of $a and $b, with a space separating them iff
dnl both $a and $b are non-empty.
AC_DEFUN([JE_CONCAT_VVV],
if test "x[$]{$2}" = "x" -o "x[$]{$3}" = "x" ; then
$1="[$]{$2}[$]{$3}"
else
$1="[$]{$2} [$]{$3}"
fi
)
dnl JE_APPEND_VS(a, b)
dnl
dnl Set $a to the concatenation of $a and b, with a space separating them iff
dnl both $a and b are non-empty.
AC_DEFUN([JE_APPEND_VS],
T_APPEND_V=$2
JE_CONCAT_VVV($1, $1, T_APPEND_V)
)
CONFIGURE_CFLAGS=
SPECIFIED_CFLAGS="${CFLAGS}"
dnl JE_CFLAGS_ADD(cflag)
dnl
dnl CFLAGS is the concatenation of CONFIGURE_CFLAGS and SPECIFIED_CFLAGS
dnl (ignoring EXTRA_CFLAGS, which does not impact configure tests. This macro
dnl appends to CONFIGURE_CFLAGS and regenerates CFLAGS.
AC_DEFUN([JE_CFLAGS_ADD],
[
AC_MSG_CHECKING([whether compiler supports $1])
T_CONFIGURE_CFLAGS="${CONFIGURE_CFLAGS}"
JE_APPEND_VS(CONFIGURE_CFLAGS, $1)
JE_CONCAT_VVV(CFLAGS, CONFIGURE_CFLAGS, SPECIFIED_CFLAGS)
AC_COMPILE_IFELSE([AC_LANG_PROGRAM(
[[
]], [[
return 0;
]])],
[je_cv_cflags_added=$1]
AC_MSG_RESULT([yes]),
[je_cv_cflags_added=]
AC_MSG_RESULT([no])
[CONFIGURE_CFLAGS="${T_CONFIGURE_CFLAGS}"]
)
JE_CONCAT_VVV(CFLAGS, CONFIGURE_CFLAGS, SPECIFIED_CFLAGS)
])
dnl JE_CFLAGS_SAVE()
dnl JE_CFLAGS_RESTORE()
dnl
dnl Save/restore CFLAGS. Nesting is not supported.
AC_DEFUN([JE_CFLAGS_SAVE],
SAVED_CONFIGURE_CFLAGS="${CONFIGURE_CFLAGS}"
)
AC_DEFUN([JE_CFLAGS_RESTORE],
CONFIGURE_CFLAGS="${SAVED_CONFIGURE_CFLAGS}"
JE_CONCAT_VVV(CFLAGS, CONFIGURE_CFLAGS, SPECIFIED_CFLAGS)
)
CONFIGURE_CXXFLAGS=
SPECIFIED_CXXFLAGS="${CXXFLAGS}"
dnl JE_CXXFLAGS_ADD(cxxflag)
AC_DEFUN([JE_CXXFLAGS_ADD],
[
AC_MSG_CHECKING([whether compiler supports $1])
T_CONFIGURE_CXXFLAGS="${CONFIGURE_CXXFLAGS}"
JE_APPEND_VS(CONFIGURE_CXXFLAGS, $1)
JE_CONCAT_VVV(CXXFLAGS, CONFIGURE_CXXFLAGS, SPECIFIED_CXXFLAGS)
AC_LANG_PUSH([C++])
AC_COMPILE_IFELSE([AC_LANG_PROGRAM(
[[
]], [[
return 0;
]])],
[je_cv_cxxflags_added=$1]
AC_MSG_RESULT([yes]),
[je_cv_cxxflags_added=]
AC_MSG_RESULT([no])
[CONFIGURE_CXXFLAGS="${T_CONFIGURE_CXXFLAGS}"]
)
AC_LANG_POP([C++])
JE_CONCAT_VVV(CXXFLAGS, CONFIGURE_CXXFLAGS, SPECIFIED_CXXFLAGS)
])
dnl JE_COMPILABLE(label, hcode, mcode, rvar)
dnl
dnl Use AC_LINK_IFELSE() rather than AC_COMPILE_IFELSE() so that linker errors
dnl cause failure.
AC_DEFUN([JE_COMPILABLE],
[
AC_CACHE_CHECK([whether $1 is compilable],
[$4],
[AC_LINK_IFELSE([AC_LANG_PROGRAM([$2],
[$3])],
[$4=yes],
[$4=no])])
])
dnl ============================================================================
CONFIG=`echo ${ac_configure_args} | sed -e 's#'"'"'\([^ ]*\)'"'"'#\1#g'`
AC_SUBST([CONFIG])
dnl Library revision.
rev=2
AC_SUBST([rev])
srcroot=$srcdir
if test "x${srcroot}" = "x." ; then
srcroot=""
else
srcroot="${srcroot}/"
fi
AC_SUBST([srcroot])
abs_srcroot="`cd \"${srcdir}\"; pwd`/"
AC_SUBST([abs_srcroot])
objroot=""
AC_SUBST([objroot])
abs_objroot="`pwd`/"
AC_SUBST([abs_objroot])
dnl Munge install path variables.
if test "x$prefix" = "xNONE" ; then
prefix="/usr/local"
fi
if test "x$exec_prefix" = "xNONE" ; then
exec_prefix=$prefix
fi
PREFIX=$prefix
AC_SUBST([PREFIX])
BINDIR=`eval echo $bindir`
BINDIR=`eval echo $BINDIR`
AC_SUBST([BINDIR])
INCLUDEDIR=`eval echo $includedir`
INCLUDEDIR=`eval echo $INCLUDEDIR`
AC_SUBST([INCLUDEDIR])
LIBDIR=`eval echo $libdir`
LIBDIR=`eval echo $LIBDIR`
AC_SUBST([LIBDIR])
DATADIR=`eval echo $datadir`
DATADIR=`eval echo $DATADIR`
AC_SUBST([DATADIR])
MANDIR=`eval echo $mandir`
MANDIR=`eval echo $MANDIR`
AC_SUBST([MANDIR])
dnl Support for building documentation.
AC_PATH_PROG([XSLTPROC], [xsltproc], [false], [$PATH])
if test -d "/usr/share/xml/docbook/stylesheet/docbook-xsl" ; then
DEFAULT_XSLROOT="/usr/share/xml/docbook/stylesheet/docbook-xsl"
elif test -d "/usr/share/sgml/docbook/xsl-stylesheets" ; then
DEFAULT_XSLROOT="/usr/share/sgml/docbook/xsl-stylesheets"
else
dnl Documentation building will fail if this default gets used.
DEFAULT_XSLROOT=""
fi
AC_ARG_WITH([xslroot],
[AS_HELP_STRING([--with-xslroot=<path>], [XSL stylesheet root path])], [
if test "x$with_xslroot" = "xno" ; then
XSLROOT="${DEFAULT_XSLROOT}"
else
XSLROOT="${with_xslroot}"
fi
],
XSLROOT="${DEFAULT_XSLROOT}"
)
if test "x$XSLTPROC" = "xfalse" ; then
XSLROOT=""
fi
AC_SUBST([XSLROOT])
dnl If CFLAGS isn't defined, set CFLAGS to something reasonable. Otherwise,
dnl just prevent autoconf from molesting CFLAGS.
CFLAGS=$CFLAGS
AC_PROG_CC
if test "x$GCC" != "xyes" ; then
AC_CACHE_CHECK([whether compiler is MSVC],
[je_cv_msvc],
[AC_COMPILE_IFELSE([AC_LANG_PROGRAM([],
[
#ifndef _MSC_VER
int fail[-1];
#endif
])],
[je_cv_msvc=yes],
[je_cv_msvc=no])])
fi
dnl check if a cray prgenv wrapper compiler is being used
je_cv_cray_prgenv_wrapper=""
if test "x${PE_ENV}" != "x" ; then
case "${CC}" in
CC|cc)
je_cv_cray_prgenv_wrapper="yes"
;;
*)
;;
esac
fi
AC_CACHE_CHECK([whether compiler is cray],
[je_cv_cray],
[AC_COMPILE_IFELSE([AC_LANG_PROGRAM([],
[
#ifndef _CRAYC
int fail[-1];
#endif
])],
[je_cv_cray=yes],
[je_cv_cray=no])])
if test "x${je_cv_cray}" = "xyes" ; then
AC_CACHE_CHECK([whether cray compiler version is 8.4],
[je_cv_cray_84],
[AC_COMPILE_IFELSE([AC_LANG_PROGRAM([],
[
#if !(_RELEASE_MAJOR == 8 && _RELEASE_MINOR == 4)
int fail[-1];
#endif
])],
[je_cv_cray_84=yes],
[je_cv_cray_84=no])])
fi
if test "x$GCC" = "xyes" ; then
JE_CFLAGS_ADD([-std=gnu11])
if test "x$je_cv_cflags_added" = "x-std=gnu11" ; then
AC_DEFINE_UNQUOTED([JEMALLOC_HAS_RESTRICT])
else
JE_CFLAGS_ADD([-std=gnu99])
if test "x$je_cv_cflags_added" = "x-std=gnu99" ; then
AC_DEFINE_UNQUOTED([JEMALLOC_HAS_RESTRICT])
fi
fi
JE_CFLAGS_ADD([-Wall])
JE_CFLAGS_ADD([-Wextra])
JE_CFLAGS_ADD([-Wshorten-64-to-32])
JE_CFLAGS_ADD([-Wsign-compare])
JE_CFLAGS_ADD([-Wundef])
JE_CFLAGS_ADD([-Wno-format-zero-length])
JE_CFLAGS_ADD([-pipe])
JE_CFLAGS_ADD([-g3])
elif test "x$je_cv_msvc" = "xyes" ; then
CC="$CC -nologo"
JE_CFLAGS_ADD([-Zi])
JE_CFLAGS_ADD([-MT])
JE_CFLAGS_ADD([-W3])
JE_CFLAGS_ADD([-FS])
JE_APPEND_VS(CPPFLAGS, -I${srcdir}/include/msvc_compat)
fi
if test "x$je_cv_cray" = "xyes" ; then
dnl cray compiler 8.4 has an inlining bug
if test "x$je_cv_cray_84" = "xyes" ; then
JE_CFLAGS_ADD([-hipa2])
JE_CFLAGS_ADD([-hnognu])
fi
dnl ignore unreachable code warning
JE_CFLAGS_ADD([-hnomessage=128])
dnl ignore redefinition of "malloc", "free", etc warning
JE_CFLAGS_ADD([-hnomessage=1357])
fi
AC_SUBST([CONFIGURE_CFLAGS])
AC_SUBST([SPECIFIED_CFLAGS])
AC_SUBST([EXTRA_CFLAGS])
AC_PROG_CPP
AC_ARG_ENABLE([cxx],
[AS_HELP_STRING([--disable-cxx], [Disable C++ integration])],
if test "x$enable_cxx" = "xno" ; then
enable_cxx="0"
else
enable_cxx="1"
fi
,
enable_cxx="1"
)
if test "x$enable_cxx" = "x1" ; then
dnl Require at least c++14, which is the first version to support sized
dnl deallocation. C++ support is not compiled otherwise.
m4_include([m4/ax_cxx_compile_stdcxx.m4])
AX_CXX_COMPILE_STDCXX([14], [noext], [optional])
if test "x${HAVE_CXX14}" = "x1" ; then
JE_CXXFLAGS_ADD([-Wall])
JE_CXXFLAGS_ADD([-Wextra])
JE_CXXFLAGS_ADD([-g3])
SAVED_LIBS="${LIBS}"
JE_APPEND_VS(LIBS, -lstdc++)
JE_COMPILABLE([libstdc++ linkage], [
#include <stdlib.h>
], [[
int *arr = (int *)malloc(sizeof(int) * 42);
if (arr == NULL)
return 1;
]], [je_cv_libstdcxx])
if test "x${je_cv_libstdcxx}" = "xno" ; then
LIBS="${SAVED_LIBS}"
fi
else
enable_cxx="0"
fi
fi
AC_SUBST([enable_cxx])
AC_SUBST([CONFIGURE_CXXFLAGS])
AC_SUBST([SPECIFIED_CXXFLAGS])
AC_SUBST([EXTRA_CXXFLAGS])
AC_C_BIGENDIAN([ac_cv_big_endian=1], [ac_cv_big_endian=0])
if test "x${ac_cv_big_endian}" = "x1" ; then
AC_DEFINE_UNQUOTED([JEMALLOC_BIG_ENDIAN], [ ])
fi
if test "x${je_cv_msvc}" = "xyes" -a "x${ac_cv_header_inttypes_h}" = "xno"; then
JE_APPEND_VS(CPPFLAGS, -I${srcdir}/include/msvc_compat/C99)
fi
if test "x${je_cv_msvc}" = "xyes" ; then
LG_SIZEOF_PTR=LG_SIZEOF_PTR_WIN
AC_MSG_RESULT([Using a predefined value for sizeof(void *): 4 for 32-bit, 8 for 64-bit])
else
AC_CHECK_SIZEOF([void *])
if test "x${ac_cv_sizeof_void_p}" = "x8" ; then
LG_SIZEOF_PTR=3
elif test "x${ac_cv_sizeof_void_p}" = "x4" ; then
LG_SIZEOF_PTR=2
else
AC_MSG_ERROR([Unsupported pointer size: ${ac_cv_sizeof_void_p}])
fi
fi
AC_DEFINE_UNQUOTED([LG_SIZEOF_PTR], [$LG_SIZEOF_PTR])
AC_CHECK_SIZEOF([int])
if test "x${ac_cv_sizeof_int}" = "x8" ; then
LG_SIZEOF_INT=3
elif test "x${ac_cv_sizeof_int}" = "x4" ; then
LG_SIZEOF_INT=2
else
AC_MSG_ERROR([Unsupported int size: ${ac_cv_sizeof_int}])
fi
AC_DEFINE_UNQUOTED([LG_SIZEOF_INT], [$LG_SIZEOF_INT])
AC_CHECK_SIZEOF([long])
if test "x${ac_cv_sizeof_long}" = "x8" ; then
LG_SIZEOF_LONG=3
elif test "x${ac_cv_sizeof_long}" = "x4" ; then
LG_SIZEOF_LONG=2
else
AC_MSG_ERROR([Unsupported long size: ${ac_cv_sizeof_long}])
fi
AC_DEFINE_UNQUOTED([LG_SIZEOF_LONG], [$LG_SIZEOF_LONG])
AC_CHECK_SIZEOF([long long])
if test "x${ac_cv_sizeof_long_long}" = "x8" ; then
LG_SIZEOF_LONG_LONG=3
elif test "x${ac_cv_sizeof_long_long}" = "x4" ; then
LG_SIZEOF_LONG_LONG=2
else
AC_MSG_ERROR([Unsupported long long size: ${ac_cv_sizeof_long_long}])
fi
AC_DEFINE_UNQUOTED([LG_SIZEOF_LONG_LONG], [$LG_SIZEOF_LONG_LONG])
AC_CHECK_SIZEOF([intmax_t])
if test "x${ac_cv_sizeof_intmax_t}" = "x16" ; then
LG_SIZEOF_INTMAX_T=4
elif test "x${ac_cv_sizeof_intmax_t}" = "x8" ; then
LG_SIZEOF_INTMAX_T=3
elif test "x${ac_cv_sizeof_intmax_t}" = "x4" ; then
LG_SIZEOF_INTMAX_T=2
else
AC_MSG_ERROR([Unsupported intmax_t size: ${ac_cv_sizeof_intmax_t}])
fi
AC_DEFINE_UNQUOTED([LG_SIZEOF_INTMAX_T], [$LG_SIZEOF_INTMAX_T])
AC_CANONICAL_HOST
dnl CPU-specific settings.
CPU_SPINWAIT=""
case "${host_cpu}" in
i686|x86_64)
HAVE_CPU_SPINWAIT=1
if test "x${je_cv_msvc}" = "xyes" ; then
AC_CACHE_VAL([je_cv_pause_msvc],
[JE_COMPILABLE([pause instruction MSVC], [],
[[_mm_pause(); return 0;]],
[je_cv_pause_msvc])])
if test "x${je_cv_pause_msvc}" = "xyes" ; then
CPU_SPINWAIT='_mm_pause()'
fi
else
AC_CACHE_VAL([je_cv_pause],
[JE_COMPILABLE([pause instruction], [],
[[__asm__ volatile("pause"); return 0;]],
[je_cv_pause])])
if test "x${je_cv_pause}" = "xyes" ; then
CPU_SPINWAIT='__asm__ volatile("pause")'
fi
fi
;;
*)
HAVE_CPU_SPINWAIT=0
;;
esac
AC_DEFINE_UNQUOTED([HAVE_CPU_SPINWAIT], [$HAVE_CPU_SPINWAIT])
AC_DEFINE_UNQUOTED([CPU_SPINWAIT], [$CPU_SPINWAIT])
AC_ARG_WITH([lg_vaddr],
[AS_HELP_STRING([--with-lg-vaddr=<lg-vaddr>], [Number of significant virtual address bits])],
[LG_VADDR="$with_lg_vaddr"], [LG_VADDR="detect"])
case "${host_cpu}" in
aarch64)
if test "x$LG_VADDR" = "xdetect"; then
AC_MSG_CHECKING([number of significant virtual address bits])
if test "x${LG_SIZEOF_PTR}" = "x2" ; then
#aarch64 ILP32
LG_VADDR=32
else
#aarch64 LP64
LG_VADDR=48
fi
AC_MSG_RESULT([$LG_VADDR])
fi
;;
x86_64)
if test "x$LG_VADDR" = "xdetect"; then
AC_CACHE_CHECK([number of significant virtual address bits],
[je_cv_lg_vaddr],
AC_RUN_IFELSE([AC_LANG_PROGRAM(
[[
#include <stdio.h>
#ifdef _WIN32
#include <limits.h>
#include <intrin.h>
typedef unsigned __int32 uint32_t;
#else
#include <stdint.h>
#endif
]], [[
uint32_t r[[4]];
uint32_t eax_in = 0x80000008U;
#ifdef _WIN32
__cpuid((int *)r, (int)eax_in);
#else
asm volatile ("cpuid"
: "=a" (r[[0]]), "=b" (r[[1]]), "=c" (r[[2]]), "=d" (r[[3]])
: "a" (eax_in), "c" (0)
);
#endif
uint32_t eax_out = r[[0]];
uint32_t vaddr = ((eax_out & 0x0000ff00U) >> 8);
FILE *f = fopen("conftest.out", "w");
if (f == NULL) {
return 1;
}
if (vaddr > (sizeof(void *) << 3)) {
vaddr = sizeof(void *) << 3;
}
fprintf(f, "%u", vaddr);
fclose(f);
return 0;
]])],
[je_cv_lg_vaddr=`cat conftest.out`],
[je_cv_lg_vaddr=error],
[je_cv_lg_vaddr=57]))
if test "x${je_cv_lg_vaddr}" != "x" ; then
LG_VADDR="${je_cv_lg_vaddr}"
fi
if test "x${LG_VADDR}" != "xerror" ; then
AC_DEFINE_UNQUOTED([LG_VADDR], [$LG_VADDR])
else
AC_MSG_ERROR([cannot determine number of significant virtual address bits])
fi
fi
;;
*)
if test "x$LG_VADDR" = "xdetect"; then
AC_MSG_CHECKING([number of significant virtual address bits])
if test "x${LG_SIZEOF_PTR}" = "x3" ; then
LG_VADDR=64
elif test "x${LG_SIZEOF_PTR}" = "x2" ; then
LG_VADDR=32
elif test "x${LG_SIZEOF_PTR}" = "xLG_SIZEOF_PTR_WIN" ; then
LG_VADDR="(1U << (LG_SIZEOF_PTR_WIN+3))"
else
AC_MSG_ERROR([Unsupported lg(pointer size): ${LG_SIZEOF_PTR}])
fi
AC_MSG_RESULT([$LG_VADDR])
fi
;;
esac
AC_DEFINE_UNQUOTED([LG_VADDR], [$LG_VADDR])
LD_PRELOAD_VAR="LD_PRELOAD"
so="so"
importlib="${so}"
o="$ac_objext"
a="a"
exe="$ac_exeext"
libprefix="lib"
link_whole_archive="0"
DSO_LDFLAGS='-shared -Wl,-soname,$(@F)'
RPATH='-Wl,-rpath,$(1)'
SOREV="${so}.${rev}"
PIC_CFLAGS='-fPIC -DPIC'
CTARGET='-o $@'
LDTARGET='-o $@'
TEST_LD_MODE=
EXTRA_LDFLAGS=
ARFLAGS='crus'
AROUT=' $@'
CC_MM=1
if test "x$je_cv_cray_prgenv_wrapper" = "xyes" ; then
TEST_LD_MODE='-dynamic'
fi
if test "x${je_cv_cray}" = "xyes" ; then
CC_MM=
fi
AN_MAKEVAR([AR], [AC_PROG_AR])
AN_PROGRAM([ar], [AC_PROG_AR])
AC_DEFUN([AC_PROG_AR], [AC_CHECK_TOOL(AR, ar, :)])
AC_PROG_AR
AN_MAKEVAR([NM], [AC_PROG_NM])
AN_PROGRAM([nm], [AC_PROG_NM])
AC_DEFUN([AC_PROG_NM], [AC_CHECK_TOOL(NM, nm, :)])
AC_PROG_NM
AC_PROG_AWK
dnl ============================================================================
dnl jemalloc version.
dnl
AC_ARG_WITH([version],
[AS_HELP_STRING([--with-version=<major>.<minor>.<bugfix>-<nrev>-g<gid>],
[Version string])],
[
echo "${with_version}" | grep ['^[0-9]\+\.[0-9]\+\.[0-9]\+-[0-9]\+-g[0-9a-f]\+$'] 2>&1 1>/dev/null
if test $? -eq 0 ; then
echo "$with_version" > "${objroot}VERSION"
else
echo "${with_version}" | grep ['^VERSION$'] 2>&1 1>/dev/null
if test $? -ne 0 ; then
AC_MSG_ERROR([${with_version} does not match <major>.<minor>.<bugfix>-<nrev>-g<gid> or VERSION])
fi
fi
], [
dnl Set VERSION if source directory is inside a git repository.
if test "x`test ! \"${srcroot}\" && cd \"${srcroot}\"; git rev-parse --is-inside-work-tree 2>/dev/null`" = "xtrue" ; then
dnl Pattern globs aren't powerful enough to match both single- and
dnl double-digit version numbers, so iterate over patterns to support up
dnl to version 99.99.99 without any accidental matches.
for pattern in ['[0-9].[0-9].[0-9]' '[0-9].[0-9].[0-9][0-9]' \
'[0-9].[0-9][0-9].[0-9]' '[0-9].[0-9][0-9].[0-9][0-9]' \
'[0-9][0-9].[0-9].[0-9]' '[0-9][0-9].[0-9].[0-9][0-9]' \
'[0-9][0-9].[0-9][0-9].[0-9]' \
'[0-9][0-9].[0-9][0-9].[0-9][0-9]']; do
(test ! "${srcroot}" && cd "${srcroot}"; git describe --long --abbrev=40 --match="${pattern}") > "${objroot}VERSION.tmp" 2>/dev/null
if test $? -eq 0 ; then
mv "${objroot}VERSION.tmp" "${objroot}VERSION"
break
fi
done
fi
rm -f "${objroot}VERSION.tmp"
])
if test ! -e "${objroot}VERSION" ; then
if test ! -e "${srcroot}VERSION" ; then
AC_MSG_RESULT(
[Missing VERSION file, and unable to generate it; creating bogus VERSION])
echo "0.0.0-0-g0000000000000000000000000000000000000000" > "${objroot}VERSION"
else
cp ${srcroot}VERSION ${objroot}VERSION
fi
fi
jemalloc_version=`cat "${objroot}VERSION"`
jemalloc_version_major=`echo ${jemalloc_version} | tr ".g-" " " | awk '{print [$]1}'`
jemalloc_version_minor=`echo ${jemalloc_version} | tr ".g-" " " | awk '{print [$]2}'`
jemalloc_version_bugfix=`echo ${jemalloc_version} | tr ".g-" " " | awk '{print [$]3}'`
jemalloc_version_nrev=`echo ${jemalloc_version} | tr ".g-" " " | awk '{print [$]4}'`
jemalloc_version_gid=`echo ${jemalloc_version} | tr ".g-" " " | awk '{print [$]5}'`
AC_SUBST([jemalloc_version])
AC_SUBST([jemalloc_version_major])
AC_SUBST([jemalloc_version_minor])
AC_SUBST([jemalloc_version_bugfix])
AC_SUBST([jemalloc_version_nrev])
AC_SUBST([jemalloc_version_gid])
dnl Platform-specific settings. abi and RPATH can probably be determined
dnl programmatically, but doing so is error-prone, which makes it generally
dnl not worth the trouble.
dnl
dnl Define cpp macros in CPPFLAGS, rather than doing AC_DEFINE(macro), since the
dnl definitions need to be seen before any headers are included, which is a pain
dnl to make happen otherwise.
default_retain="0"
maps_coalesce="1"
DUMP_SYMS="${NM} -a"
SYM_PREFIX=""
case "${host}" in
*-*-darwin* | *-*-ios*)
abi="macho"
RPATH=""
LD_PRELOAD_VAR="DYLD_INSERT_LIBRARIES"
so="dylib"
importlib="${so}"
force_tls="0"
DSO_LDFLAGS='-shared -Wl,-install_name,$(LIBDIR)/$(@F)'
SOREV="${rev}.${so}"
sbrk_deprecated="1"
SYM_PREFIX="_"
;;
*-*-freebsd*)
abi="elf"
AC_DEFINE([JEMALLOC_SYSCTL_VM_OVERCOMMIT], [ ])
force_lazy_lock="1"
;;
*-*-dragonfly*)
abi="elf"
;;
*-*-openbsd*)
abi="elf"
force_tls="0"
;;
*-*-bitrig*)
abi="elf"
;;
*-*-linux-android)
dnl syscall(2) and secure_getenv(3) are exposed by _GNU_SOURCE.
JE_APPEND_VS(CPPFLAGS, -D_GNU_SOURCE)
abi="elf"
AC_DEFINE([JEMALLOC_PURGE_MADVISE_DONTNEED_ZEROS], [ ])
AC_DEFINE([JEMALLOC_HAS_ALLOCA_H])
AC_DEFINE([JEMALLOC_PROC_SYS_VM_OVERCOMMIT_MEMORY], [ ])
AC_DEFINE([JEMALLOC_THREADED_INIT], [ ])
AC_DEFINE([JEMALLOC_C11_ATOMICS])
force_tls="0"
if test "${LG_SIZEOF_PTR}" = "3"; then
default_retain="1"
fi
;;
*-*-linux*)
dnl syscall(2) and secure_getenv(3) are exposed by _GNU_SOURCE.
JE_APPEND_VS(CPPFLAGS, -D_GNU_SOURCE)
abi="elf"
AC_DEFINE([JEMALLOC_PURGE_MADVISE_DONTNEED_ZEROS], [ ])
AC_DEFINE([JEMALLOC_HAS_ALLOCA_H])
AC_DEFINE([JEMALLOC_PROC_SYS_VM_OVERCOMMIT_MEMORY], [ ])
AC_DEFINE([JEMALLOC_THREADED_INIT], [ ])
AC_DEFINE([JEMALLOC_USE_CXX_THROW], [ ])
if test "${LG_SIZEOF_PTR}" = "3"; then
default_retain="1"
fi
;;
*-*-kfreebsd*)
dnl syscall(2) and secure_getenv(3) are exposed by _GNU_SOURCE.
JE_APPEND_VS(CPPFLAGS, -D_GNU_SOURCE)
abi="elf"
AC_DEFINE([JEMALLOC_HAS_ALLOCA_H])
AC_DEFINE([JEMALLOC_SYSCTL_VM_OVERCOMMIT], [ ])
AC_DEFINE([JEMALLOC_THREADED_INIT], [ ])
AC_DEFINE([JEMALLOC_USE_CXX_THROW], [ ])
;;
*-*-netbsd*)
AC_MSG_CHECKING([ABI])
AC_COMPILE_IFELSE([AC_LANG_PROGRAM(
[[#ifdef __ELF__
/* ELF */
#else
#error aout
#endif
]])],
[abi="elf"],
[abi="aout"])
AC_MSG_RESULT([$abi])
;;
*-*-solaris2*)
abi="elf"
RPATH='-Wl,-R,$(1)'
dnl Solaris needs this for sigwait().
JE_APPEND_VS(CPPFLAGS, -D_POSIX_PTHREAD_SEMANTICS)
JE_APPEND_VS(LIBS, -lposix4 -lsocket -lnsl)
;;
*-ibm-aix*)
if test "${LG_SIZEOF_PTR}" = "3"; then
dnl 64bit AIX
LD_PRELOAD_VAR="LDR_PRELOAD64"
else
dnl 32bit AIX
LD_PRELOAD_VAR="LDR_PRELOAD"
fi
abi="xcoff"
;;
*-*-mingw* | *-*-cygwin*)
abi="pecoff"
force_tls="0"
maps_coalesce="0"
RPATH=""
so="dll"
if test "x$je_cv_msvc" = "xyes" ; then
importlib="lib"
DSO_LDFLAGS="-LD"
EXTRA_LDFLAGS="-link -DEBUG"
CTARGET='-Fo$@'
LDTARGET='-Fe$@'
AR='lib'
ARFLAGS='-nologo -out:'
AROUT='$@'
CC_MM=
else
importlib="${so}"
DSO_LDFLAGS="-shared"
link_whole_archive="1"
fi
case "${host}" in
*-*-cygwin*)
DUMP_SYMS="dumpbin /SYMBOLS"
;;
*)
;;
esac
a="lib"
libprefix=""
SOREV="${so}"
PIC_CFLAGS=""
if test "${LG_SIZEOF_PTR}" = "3"; then
default_retain="1"
fi
;;
*)
AC_MSG_RESULT([Unsupported operating system: ${host}])
abi="elf"
;;
esac
JEMALLOC_USABLE_SIZE_CONST=const
AC_CHECK_HEADERS([malloc.h], [
AC_MSG_CHECKING([whether malloc_usable_size definition can use const argument])
AC_COMPILE_IFELSE([AC_LANG_PROGRAM(
[#include <malloc.h>
#include <stddef.h>
size_t malloc_usable_size(const void *ptr);
],
[])],[
AC_MSG_RESULT([yes])
],[
JEMALLOC_USABLE_SIZE_CONST=
AC_MSG_RESULT([no])
])
])
AC_DEFINE_UNQUOTED([JEMALLOC_USABLE_SIZE_CONST], [$JEMALLOC_USABLE_SIZE_CONST])
AC_SUBST([abi])
AC_SUBST([RPATH])
AC_SUBST([LD_PRELOAD_VAR])
AC_SUBST([so])
AC_SUBST([importlib])
AC_SUBST([o])
AC_SUBST([a])
AC_SUBST([exe])
AC_SUBST([libprefix])
AC_SUBST([link_whole_archive])
AC_SUBST([DSO_LDFLAGS])
AC_SUBST([EXTRA_LDFLAGS])
AC_SUBST([SOREV])
AC_SUBST([PIC_CFLAGS])
AC_SUBST([CTARGET])
AC_SUBST([LDTARGET])
AC_SUBST([TEST_LD_MODE])
AC_SUBST([MKLIB])
AC_SUBST([ARFLAGS])
AC_SUBST([AROUT])
AC_SUBST([DUMP_SYMS])
AC_SUBST([CC_MM])
dnl Determine whether libm must be linked to use e.g. log(3).
AC_SEARCH_LIBS([log], [m], , [AC_MSG_ERROR([Missing math functions])])
if test "x$ac_cv_search_log" != "xnone required" ; then
LM="$ac_cv_search_log"
else
LM=
fi
AC_SUBST(LM)
JE_COMPILABLE([__attribute__ syntax],
[static __attribute__((unused)) void foo(void){}],
[],
[je_cv_attribute])
if test "x${je_cv_attribute}" = "xyes" ; then
AC_DEFINE([JEMALLOC_HAVE_ATTR], [ ])
if test "x${GCC}" = "xyes" -a "x${abi}" = "xelf"; then
JE_CFLAGS_ADD([-fvisibility=hidden])
JE_CXXFLAGS_ADD([-fvisibility=hidden])
fi
fi
dnl Check for tls_model attribute support (clang 3.0 still lacks support).
JE_CFLAGS_SAVE()
JE_CFLAGS_ADD([-Werror])
JE_CFLAGS_ADD([-herror_on_warning])
JE_COMPILABLE([tls_model attribute], [],
[static __thread int
__attribute__((tls_model("initial-exec"), unused)) foo;
foo = 0;],
[je_cv_tls_model])
JE_CFLAGS_RESTORE()
dnl (Setting of JEMALLOC_TLS_MODEL is done later, after we've checked for
dnl --disable-initial-exec-tls)
dnl Check for alloc_size attribute support.
JE_CFLAGS_SAVE()
JE_CFLAGS_ADD([-Werror])
JE_CFLAGS_ADD([-herror_on_warning])
JE_COMPILABLE([alloc_size attribute], [#include <stdlib.h>],
[void *foo(size_t size) __attribute__((alloc_size(1)));],
[je_cv_alloc_size])
JE_CFLAGS_RESTORE()
if test "x${je_cv_alloc_size}" = "xyes" ; then
AC_DEFINE([JEMALLOC_HAVE_ATTR_ALLOC_SIZE], [ ])
fi
dnl Check for format(gnu_printf, ...) attribute support.
JE_CFLAGS_SAVE()
JE_CFLAGS_ADD([-Werror])
JE_CFLAGS_ADD([-herror_on_warning])
JE_COMPILABLE([format(gnu_printf, ...) attribute], [#include <stdlib.h>],
[void *foo(const char *format, ...) __attribute__((format(gnu_printf, 1, 2)));],
[je_cv_format_gnu_printf])
JE_CFLAGS_RESTORE()
if test "x${je_cv_format_gnu_printf}" = "xyes" ; then
AC_DEFINE([JEMALLOC_HAVE_ATTR_FORMAT_GNU_PRINTF], [ ])
fi
dnl Check for format(printf, ...) attribute support.
JE_CFLAGS_SAVE()
JE_CFLAGS_ADD([-Werror])
JE_CFLAGS_ADD([-herror_on_warning])
JE_COMPILABLE([format(printf, ...) attribute], [#include <stdlib.h>],
[void *foo(const char *format, ...) __attribute__((format(printf, 1, 2)));],
[je_cv_format_printf])
JE_CFLAGS_RESTORE()
if test "x${je_cv_format_printf}" = "xyes" ; then
AC_DEFINE([JEMALLOC_HAVE_ATTR_FORMAT_PRINTF], [ ])
fi
dnl Check for format_arg(...) attribute support.
JE_CFLAGS_SAVE()
JE_CFLAGS_ADD([-Werror])
JE_CFLAGS_ADD([-herror_on_warning])
JE_COMPILABLE([format(printf, ...) attribute], [#include <stdlib.h>],
[const char * __attribute__((__format_arg__(1))) foo(const char *format);],
[je_cv_format_arg])
JE_CFLAGS_RESTORE()
if test "x${je_cv_format_arg}" = "xyes" ; then
AC_DEFINE([JEMALLOC_HAVE_ATTR_FORMAT_ARG], [ ])
fi
dnl Support optional additions to rpath.
AC_ARG_WITH([rpath],
[AS_HELP_STRING([--with-rpath=<rpath>], [Colon-separated rpath (ELF systems only)])],
if test "x$with_rpath" = "xno" ; then
RPATH_EXTRA=
else
RPATH_EXTRA="`echo $with_rpath | tr \":\" \" \"`"
fi,
RPATH_EXTRA=
)
AC_SUBST([RPATH_EXTRA])
dnl Disable rules that do automatic regeneration of configure output by default.
AC_ARG_ENABLE([autogen],
[AS_HELP_STRING([--enable-autogen], [Automatically regenerate configure output])],
if test "x$enable_autogen" = "xno" ; then
enable_autogen="0"
else
enable_autogen="1"
fi
,
enable_autogen="0"
)
AC_SUBST([enable_autogen])
AC_PROG_INSTALL
AC_PROG_RANLIB
AC_PATH_PROG([LD], [ld], [false], [$PATH])
AC_PATH_PROG([AUTOCONF], [autoconf], [false], [$PATH])
dnl Enable documentation
AC_ARG_ENABLE([doc],
[AS_HELP_STRING([--enable-documentation], [Build documentation])],
if test "x$enable_doc" = "xno" ; then
enable_doc="0"
else
enable_doc="1"
fi
,
enable_doc="1"
)
AC_SUBST([enable_doc])
dnl Enable shared libs
AC_ARG_ENABLE([shared],
[AS_HELP_STRING([--enable-shared], [Build shared libaries])],
if test "x$enable_shared" = "xno" ; then
enable_shared="0"
else
enable_shared="1"
fi
,
enable_shared="1"
)
AC_SUBST([enable_shared])
dnl Enable static libs
AC_ARG_ENABLE([static],
[AS_HELP_STRING([--enable-static], [Build static libaries])],
if test "x$enable_static" = "xno" ; then
enable_static="0"
else
enable_static="1"
fi
,
enable_static="1"
)
AC_SUBST([enable_static])
if test "$enable_shared$enable_static" = "00" ; then
AC_MSG_ERROR([Please enable one of shared or static builds])
fi
dnl Perform no name mangling by default.
AC_ARG_WITH([mangling],
[AS_HELP_STRING([--with-mangling=<map>], [Mangle symbols in <map>])],
[mangling_map="$with_mangling"], [mangling_map=""])
dnl Do not prefix public APIs by default.
AC_ARG_WITH([jemalloc_prefix],
[AS_HELP_STRING([--with-jemalloc-prefix=<prefix>], [Prefix to prepend to all public APIs])],
[JEMALLOC_PREFIX="$with_jemalloc_prefix"],
[if test "x$abi" != "xmacho" -a "x$abi" != "xpecoff"; then
JEMALLOC_PREFIX=""
else
JEMALLOC_PREFIX="je_"
fi]
)
if test "x$JEMALLOC_PREFIX" = "x" ; then
AC_DEFINE([JEMALLOC_IS_MALLOC])
else
JEMALLOC_CPREFIX=`echo ${JEMALLOC_PREFIX} | tr "a-z" "A-Z"`
AC_DEFINE_UNQUOTED([JEMALLOC_PREFIX], ["$JEMALLOC_PREFIX"])
AC_DEFINE_UNQUOTED([JEMALLOC_CPREFIX], ["$JEMALLOC_CPREFIX"])
fi
AC_SUBST([JEMALLOC_PREFIX])
AC_SUBST([JEMALLOC_CPREFIX])
AC_ARG_WITH([export],
[AS_HELP_STRING([--without-export], [disable exporting jemalloc public APIs])],
[if test "x$with_export" = "xno"; then
AC_DEFINE([JEMALLOC_EXPORT],[])
fi]
)
public_syms="aligned_alloc calloc dallocx free mallctl mallctlbymib mallctlnametomib malloc malloc_conf malloc_message malloc_stats_print malloc_usable_size mallocx smallocx_${jemalloc_version_gid} nallocx posix_memalign rallocx realloc sallocx sdallocx xallocx"
dnl Check for additional platform-specific public API functions.
AC_CHECK_FUNC([memalign],
[AC_DEFINE([JEMALLOC_OVERRIDE_MEMALIGN], [ ])
public_syms="${public_syms} memalign"])
AC_CHECK_FUNC([valloc],
[AC_DEFINE([JEMALLOC_OVERRIDE_VALLOC], [ ])
public_syms="${public_syms} valloc"])
dnl Check for allocator-related functions that should be wrapped.
wrap_syms=
if test "x${JEMALLOC_PREFIX}" = "x" ; then
AC_CHECK_FUNC([__libc_calloc],
[AC_DEFINE([JEMALLOC_OVERRIDE___LIBC_CALLOC], [ ])
wrap_syms="${wrap_syms} __libc_calloc"])
AC_CHECK_FUNC([__libc_free],
[AC_DEFINE([JEMALLOC_OVERRIDE___LIBC_FREE], [ ])
wrap_syms="${wrap_syms} __libc_free"])
AC_CHECK_FUNC([__libc_malloc],
[AC_DEFINE([JEMALLOC_OVERRIDE___LIBC_MALLOC], [ ])
wrap_syms="${wrap_syms} __libc_malloc"])
AC_CHECK_FUNC([__libc_memalign],
[AC_DEFINE([JEMALLOC_OVERRIDE___LIBC_MEMALIGN], [ ])
wrap_syms="${wrap_syms} __libc_memalign"])
AC_CHECK_FUNC([__libc_realloc],
[AC_DEFINE([JEMALLOC_OVERRIDE___LIBC_REALLOC], [ ])
wrap_syms="${wrap_syms} __libc_realloc"])
AC_CHECK_FUNC([__libc_valloc],
[AC_DEFINE([JEMALLOC_OVERRIDE___LIBC_VALLOC], [ ])
wrap_syms="${wrap_syms} __libc_valloc"])
AC_CHECK_FUNC([__posix_memalign],
[AC_DEFINE([JEMALLOC_OVERRIDE___POSIX_MEMALIGN], [ ])
wrap_syms="${wrap_syms} __posix_memalign"])
fi
case "${host}" in
*-*-mingw* | *-*-cygwin*)
wrap_syms="${wrap_syms} tls_callback"
;;
*)
;;
esac
dnl Mangle library-private APIs.
AC_ARG_WITH([private_namespace],
[AS_HELP_STRING([--with-private-namespace=<prefix>], [Prefix to prepend to all library-private APIs])],
[JEMALLOC_PRIVATE_NAMESPACE="${with_private_namespace}je_"],
[JEMALLOC_PRIVATE_NAMESPACE="je_"]
)
AC_DEFINE_UNQUOTED([JEMALLOC_PRIVATE_NAMESPACE], [$JEMALLOC_PRIVATE_NAMESPACE])
private_namespace="$JEMALLOC_PRIVATE_NAMESPACE"
AC_SUBST([private_namespace])
dnl Do not add suffix to installed files by default.
AC_ARG_WITH([install_suffix],
[AS_HELP_STRING([--with-install-suffix=<suffix>], [Suffix to append to all installed files])],
[INSTALL_SUFFIX="$with_install_suffix"],
[INSTALL_SUFFIX=]
)
install_suffix="$INSTALL_SUFFIX"
AC_SUBST([install_suffix])
dnl Specify default malloc_conf.
AC_ARG_WITH([malloc_conf],
[AS_HELP_STRING([--with-malloc-conf=<malloc_conf>], [config.malloc_conf options string])],
[JEMALLOC_CONFIG_MALLOC_CONF="$with_malloc_conf"],
[JEMALLOC_CONFIG_MALLOC_CONF=""]
)
config_malloc_conf="$JEMALLOC_CONFIG_MALLOC_CONF"
AC_DEFINE_UNQUOTED([JEMALLOC_CONFIG_MALLOC_CONF], ["$config_malloc_conf"])
dnl Substitute @je_@ in jemalloc_protos.h.in, primarily to make generation of
dnl jemalloc_protos_jet.h easy.
je_="je_"
AC_SUBST([je_])
cfgoutputs_in="Makefile.in"
cfgoutputs_in="${cfgoutputs_in} jemalloc.pc.in"
cfgoutputs_in="${cfgoutputs_in} doc/html.xsl.in"
cfgoutputs_in="${cfgoutputs_in} doc/manpages.xsl.in"
cfgoutputs_in="${cfgoutputs_in} doc/jemalloc.xml.in"
cfgoutputs_in="${cfgoutputs_in} include/jemalloc/jemalloc_macros.h.in"
cfgoutputs_in="${cfgoutputs_in} include/jemalloc/jemalloc_protos.h.in"
cfgoutputs_in="${cfgoutputs_in} include/jemalloc/jemalloc_typedefs.h.in"
cfgoutputs_in="${cfgoutputs_in} include/jemalloc/internal/jemalloc_preamble.h.in"
cfgoutputs_in="${cfgoutputs_in} test/test.sh.in"
cfgoutputs_in="${cfgoutputs_in} test/include/test/jemalloc_test.h.in"
cfgoutputs_out="Makefile"
cfgoutputs_out="${cfgoutputs_out} jemalloc.pc"
cfgoutputs_out="${cfgoutputs_out} doc/html.xsl"
cfgoutputs_out="${cfgoutputs_out} doc/manpages.xsl"
cfgoutputs_out="${cfgoutputs_out} doc/jemalloc.xml"
cfgoutputs_out="${cfgoutputs_out} include/jemalloc/jemalloc_macros.h"
cfgoutputs_out="${cfgoutputs_out} include/jemalloc/jemalloc_protos.h"
cfgoutputs_out="${cfgoutputs_out} include/jemalloc/jemalloc_typedefs.h"
cfgoutputs_out="${cfgoutputs_out} include/jemalloc/internal/jemalloc_preamble.h"
cfgoutputs_out="${cfgoutputs_out} test/test.sh"
cfgoutputs_out="${cfgoutputs_out} test/include/test/jemalloc_test.h"
cfgoutputs_tup="Makefile"
cfgoutputs_tup="${cfgoutputs_tup} jemalloc.pc:jemalloc.pc.in"
cfgoutputs_tup="${cfgoutputs_tup} doc/html.xsl:doc/html.xsl.in"
cfgoutputs_tup="${cfgoutputs_tup} doc/manpages.xsl:doc/manpages.xsl.in"
cfgoutputs_tup="${cfgoutputs_tup} doc/jemalloc.xml:doc/jemalloc.xml.in"
cfgoutputs_tup="${cfgoutputs_tup} include/jemalloc/jemalloc_macros.h:include/jemalloc/jemalloc_macros.h.in"
cfgoutputs_tup="${cfgoutputs_tup} include/jemalloc/jemalloc_protos.h:include/jemalloc/jemalloc_protos.h.in"
cfgoutputs_tup="${cfgoutputs_tup} include/jemalloc/jemalloc_typedefs.h:include/jemalloc/jemalloc_typedefs.h.in"
cfgoutputs_tup="${cfgoutputs_tup} include/jemalloc/internal/jemalloc_preamble.h"
cfgoutputs_tup="${cfgoutputs_tup} test/test.sh:test/test.sh.in"
cfgoutputs_tup="${cfgoutputs_tup} test/include/test/jemalloc_test.h:test/include/test/jemalloc_test.h.in"
cfghdrs_in="include/jemalloc/jemalloc_defs.h.in"
cfghdrs_in="${cfghdrs_in} include/jemalloc/internal/jemalloc_internal_defs.h.in"
cfghdrs_in="${cfghdrs_in} include/jemalloc/internal/private_symbols.sh"
cfghdrs_in="${cfghdrs_in} include/jemalloc/internal/private_namespace.sh"
cfghdrs_in="${cfghdrs_in} include/jemalloc/internal/public_namespace.sh"
cfghdrs_in="${cfghdrs_in} include/jemalloc/internal/public_unnamespace.sh"
cfghdrs_in="${cfghdrs_in} include/jemalloc/jemalloc_rename.sh"
cfghdrs_in="${cfghdrs_in} include/jemalloc/jemalloc_mangle.sh"
cfghdrs_in="${cfghdrs_in} include/jemalloc/jemalloc.sh"
cfghdrs_in="${cfghdrs_in} test/include/test/jemalloc_test_defs.h.in"
cfghdrs_out="include/jemalloc/jemalloc_defs.h"
cfghdrs_out="${cfghdrs_out} include/jemalloc/jemalloc${install_suffix}.h"
cfghdrs_out="${cfghdrs_out} include/jemalloc/internal/private_symbols.awk"
cfghdrs_out="${cfghdrs_out} include/jemalloc/internal/private_symbols_jet.awk"
cfghdrs_out="${cfghdrs_out} include/jemalloc/internal/public_symbols.txt"
cfghdrs_out="${cfghdrs_out} include/jemalloc/internal/public_namespace.h"
cfghdrs_out="${cfghdrs_out} include/jemalloc/internal/public_unnamespace.h"
cfghdrs_out="${cfghdrs_out} include/jemalloc/jemalloc_protos_jet.h"
cfghdrs_out="${cfghdrs_out} include/jemalloc/jemalloc_rename.h"
cfghdrs_out="${cfghdrs_out} include/jemalloc/jemalloc_mangle.h"
cfghdrs_out="${cfghdrs_out} include/jemalloc/jemalloc_mangle_jet.h"
cfghdrs_out="${cfghdrs_out} include/jemalloc/internal/jemalloc_internal_defs.h"
cfghdrs_out="${cfghdrs_out} test/include/test/jemalloc_test_defs.h"
cfghdrs_tup="include/jemalloc/jemalloc_defs.h:include/jemalloc/jemalloc_defs.h.in"
cfghdrs_tup="${cfghdrs_tup} include/jemalloc/internal/jemalloc_internal_defs.h:include/jemalloc/internal/jemalloc_internal_defs.h.in"
cfghdrs_tup="${cfghdrs_tup} test/include/test/jemalloc_test_defs.h:test/include/test/jemalloc_test_defs.h.in"
dnl ============================================================================
dnl jemalloc build options.
dnl
dnl Do not compile with debugging by default.
AC_ARG_ENABLE([debug],
[AS_HELP_STRING([--enable-debug],
[Build debugging code])],
[if test "x$enable_debug" = "xno" ; then
enable_debug="0"
else
enable_debug="1"
fi
],
[enable_debug="0"]
)
if test "x$enable_debug" = "x1" ; then
AC_DEFINE([JEMALLOC_DEBUG], [ ])
fi
if test "x$enable_debug" = "x1" ; then
AC_DEFINE([JEMALLOC_DEBUG], [ ])
fi
AC_SUBST([enable_debug])
dnl Only optimize if not debugging.
if test "x$enable_debug" = "x0" ; then
if test "x$GCC" = "xyes" ; then
JE_CFLAGS_ADD([-O3])
JE_CXXFLAGS_ADD([-O3])
JE_CFLAGS_ADD([-funroll-loops])
elif test "x$je_cv_msvc" = "xyes" ; then
JE_CFLAGS_ADD([-O2])
JE_CXXFLAGS_ADD([-O2])
else
JE_CFLAGS_ADD([-O])
JE_CXXFLAGS_ADD([-O])
fi
fi
dnl Enable statistics calculation by default.
AC_ARG_ENABLE([stats],
[AS_HELP_STRING([--disable-stats],
[Disable statistics calculation/reporting])],
[if test "x$enable_stats" = "xno" ; then
enable_stats="0"
else
enable_stats="1"
fi
],
[enable_stats="1"]
)
if test "x$enable_stats" = "x1" ; then
AC_DEFINE([JEMALLOC_STATS], [ ])
fi
AC_SUBST([enable_stats])
dnl Do not enable smallocx by default.
AC_ARG_ENABLE([experimental_smallocx],
[AS_HELP_STRING([--enable-experimental-smallocx], [Enable experimental smallocx API])],
[if test "x$enable_experimental_smallocx" = "xno" ; then
enable_experimental_smallocx="0"
else
enable_experimental_smallocx="1"
fi
],
[enable_experimental_smallocx="0"]
)
if test "x$enable_experimental_smallocx" = "x1" ; then
AC_DEFINE([JEMALLOC_EXPERIMENTAL_SMALLOCX_API])
fi
AC_SUBST([enable_experimental_smallocx])
dnl Do not enable profiling by default.
AC_ARG_ENABLE([prof],
[AS_HELP_STRING([--enable-prof], [Enable allocation profiling])],
[if test "x$enable_prof" = "xno" ; then
enable_prof="0"
else
enable_prof="1"
fi
],
[enable_prof="0"]
)
if test "x$enable_prof" = "x1" ; then
backtrace_method=""
else
backtrace_method="N/A"
fi
AC_ARG_ENABLE([prof-libunwind],
[AS_HELP_STRING([--enable-prof-libunwind], [Use libunwind for backtracing])],
[if test "x$enable_prof_libunwind" = "xno" ; then
enable_prof_libunwind="0"
else
enable_prof_libunwind="1"
fi
],
[enable_prof_libunwind="0"]
)
AC_ARG_WITH([static_libunwind],
[AS_HELP_STRING([--with-static-libunwind=<libunwind.a>],
[Path to static libunwind library; use rather than dynamically linking])],
if test "x$with_static_libunwind" = "xno" ; then
LUNWIND="-lunwind"
else
if test ! -f "$with_static_libunwind" ; then
AC_MSG_ERROR([Static libunwind not found: $with_static_libunwind])
fi
LUNWIND="$with_static_libunwind"
fi,
LUNWIND="-lunwind"
)
if test "x$backtrace_method" = "x" -a "x$enable_prof_libunwind" = "x1" ; then
AC_CHECK_HEADERS([libunwind.h], , [enable_prof_libunwind="0"])
if test "x$LUNWIND" = "x-lunwind" ; then
AC_CHECK_LIB([unwind], [unw_backtrace], [JE_APPEND_VS(LIBS, $LUNWIND)],
[enable_prof_libunwind="0"])
else
JE_APPEND_VS(LIBS, $LUNWIND)
fi
if test "x${enable_prof_libunwind}" = "x1" ; then
backtrace_method="libunwind"
AC_DEFINE([JEMALLOC_PROF_LIBUNWIND], [ ])
fi
fi
AC_ARG_ENABLE([prof-libgcc],
[AS_HELP_STRING([--disable-prof-libgcc],
[Do not use libgcc for backtracing])],
[if test "x$enable_prof_libgcc" = "xno" ; then
enable_prof_libgcc="0"
else
enable_prof_libgcc="1"
fi
],
[enable_prof_libgcc="1"]
)
if test "x$backtrace_method" = "x" -a "x$enable_prof_libgcc" = "x1" \
-a "x$GCC" = "xyes" ; then
AC_CHECK_HEADERS([unwind.h], , [enable_prof_libgcc="0"])
if test "x${enable_prof_libgcc}" = "x1" ; then
AC_CHECK_LIB([gcc], [_Unwind_Backtrace], [JE_APPEND_VS(LIBS, -lgcc)], [enable_prof_libgcc="0"])
fi
if test "x${enable_prof_libgcc}" = "x1" ; then
backtrace_method="libgcc"
AC_DEFINE([JEMALLOC_PROF_LIBGCC], [ ])
fi
else
enable_prof_libgcc="0"
fi
AC_ARG_ENABLE([prof-gcc],
[AS_HELP_STRING([--disable-prof-gcc],
[Do not use gcc intrinsics for backtracing])],
[if test "x$enable_prof_gcc" = "xno" ; then
enable_prof_gcc="0"
else
enable_prof_gcc="1"
fi
],
[enable_prof_gcc="1"]
)
if test "x$backtrace_method" = "x" -a "x$enable_prof_gcc" = "x1" \
-a "x$GCC" = "xyes" ; then
JE_CFLAGS_ADD([-fno-omit-frame-pointer])
backtrace_method="gcc intrinsics"
AC_DEFINE([JEMALLOC_PROF_GCC], [ ])
else
enable_prof_gcc="0"
fi
if test "x$backtrace_method" = "x" ; then
backtrace_method="none (disabling profiling)"
enable_prof="0"
fi
AC_MSG_CHECKING([configured backtracing method])
AC_MSG_RESULT([$backtrace_method])
if test "x$enable_prof" = "x1" ; then
dnl Heap profiling uses the log(3) function.
JE_APPEND_VS(LIBS, $LM)
AC_DEFINE([JEMALLOC_PROF], [ ])
fi
AC_SUBST([enable_prof])
dnl Indicate whether adjacent virtual memory mappings automatically coalesce
dnl (and fragment on demand).
if test "x${maps_coalesce}" = "x1" ; then
AC_DEFINE([JEMALLOC_MAPS_COALESCE], [ ])
fi
dnl Indicate whether to retain memory (rather than using munmap()) by default.
if test "x$default_retain" = "x1" ; then
AC_DEFINE([JEMALLOC_RETAIN], [ ])
fi
dnl Enable allocation from DSS if supported by the OS.
have_dss="1"
dnl Check whether the BSD/SUSv1 sbrk() exists. If not, disable DSS support.
AC_CHECK_FUNC([sbrk], [have_sbrk="1"], [have_sbrk="0"])
if test "x$have_sbrk" = "x1" ; then
if test "x$sbrk_deprecated" = "x1" ; then
AC_MSG_RESULT([Disabling dss allocation because sbrk is deprecated])
have_dss="0"
fi
else
have_dss="0"
fi
if test "x$have_dss" = "x1" ; then
AC_DEFINE([JEMALLOC_DSS], [ ])
fi
dnl Support the junk/zero filling option by default.
AC_ARG_ENABLE([fill],
[AS_HELP_STRING([--disable-fill], [Disable support for junk/zero filling])],
[if test "x$enable_fill" = "xno" ; then
enable_fill="0"
else
enable_fill="1"
fi
],
[enable_fill="1"]
)
if test "x$enable_fill" = "x1" ; then
AC_DEFINE([JEMALLOC_FILL], [ ])
fi
AC_SUBST([enable_fill])
dnl Disable utrace(2)-based tracing by default.
AC_ARG_ENABLE([utrace],
[AS_HELP_STRING([--enable-utrace], [Enable utrace(2)-based tracing])],
[if test "x$enable_utrace" = "xno" ; then
enable_utrace="0"
else
enable_utrace="1"
fi
],
[enable_utrace="0"]
)
JE_COMPILABLE([utrace(2)], [
#include <sys/types.h>
#include <sys/param.h>
#include <sys/time.h>
#include <sys/uio.h>
#include <sys/ktrace.h>
], [
utrace((void *)0, 0);
], [je_cv_utrace])
if test "x${je_cv_utrace}" = "xno" ; then
enable_utrace="0"
fi
if test "x$enable_utrace" = "x1" ; then
AC_DEFINE([JEMALLOC_UTRACE], [ ])
fi
AC_SUBST([enable_utrace])
dnl Do not support the xmalloc option by default.
AC_ARG_ENABLE([xmalloc],
[AS_HELP_STRING([--enable-xmalloc], [Support xmalloc option])],
[if test "x$enable_xmalloc" = "xno" ; then
enable_xmalloc="0"
else
enable_xmalloc="1"
fi
],
[enable_xmalloc="0"]
)
if test "x$enable_xmalloc" = "x1" ; then
AC_DEFINE([JEMALLOC_XMALLOC], [ ])
fi
AC_SUBST([enable_xmalloc])
dnl Support cache-oblivious allocation alignment by default.
AC_ARG_ENABLE([cache-oblivious],
[AS_HELP_STRING([--disable-cache-oblivious],
[Disable support for cache-oblivious allocation alignment])],
[if test "x$enable_cache_oblivious" = "xno" ; then
enable_cache_oblivious="0"
else
enable_cache_oblivious="1"
fi
],
[enable_cache_oblivious="1"]
)
if test "x$enable_cache_oblivious" = "x1" ; then
AC_DEFINE([JEMALLOC_CACHE_OBLIVIOUS], [ ])
fi
AC_SUBST([enable_cache_oblivious])
dnl Do not log by default.
AC_ARG_ENABLE([log],
[AS_HELP_STRING([--enable-log], [Support debug logging])],
[if test "x$enable_log" = "xno" ; then
enable_log="0"
else
enable_log="1"
fi
],
[enable_log="0"]
)
if test "x$enable_log" = "x1" ; then
AC_DEFINE([JEMALLOC_LOG], [ ])
fi
AC_SUBST([enable_log])
dnl Do not use readlinkat by default
AC_ARG_ENABLE([readlinkat],
[AS_HELP_STRING([--enable-readlinkat], [Use readlinkat over readlink])],
[if test "x$enable_readlinkat" = "xno" ; then
enable_readlinkat="0"
else
enable_readlinkat="1"
fi
],
[enable_readlinkat="0"]
)
if test "x$enable_readlinkat" = "x1" ; then
AC_DEFINE([JEMALLOC_READLINKAT], [ ])
fi
AC_SUBST([enable_readlinkat])
dnl Avoid extra safety checks by default
AC_ARG_ENABLE([opt-safety-checks],
[AS_HELP_STRING([--enable-opt-safety-checks],
[Perform certain low-overhead checks, even in opt mode])],
[if test "x$enable_opt_safety_checks" = "xno" ; then
enable_opt_safety_checks="0"
else
enable_opt_safety_checks="1"
fi
],
[enable_opt_safety_checks="0"]
)
if test "x$enable_opt_safety_checks" = "x1" ; then
AC_DEFINE([JEMALLOC_OPT_SAFETY_CHECKS], [ ])
fi
AC_SUBST([enable_opt_safety_checks])
JE_COMPILABLE([a program using __builtin_unreachable], [
void foo (void) {
__builtin_unreachable();
}
], [
{
foo();
}
], [je_cv_gcc_builtin_unreachable])
if test "x${je_cv_gcc_builtin_unreachable}" = "xyes" ; then
AC_DEFINE([JEMALLOC_INTERNAL_UNREACHABLE], [__builtin_unreachable])
else
AC_DEFINE([JEMALLOC_INTERNAL_UNREACHABLE], [abort])
fi
dnl ============================================================================
dnl Check for __builtin_ffsl(), then ffsl(3), and fail if neither are found.
dnl One of those two functions should (theoretically) exist on all platforms
dnl that jemalloc currently has a chance of functioning on without modification.
dnl We additionally assume ffs[ll]() or __builtin_ffs[ll]() are defined if
dnl ffsl() or __builtin_ffsl() are defined, respectively.
JE_COMPILABLE([a program using __builtin_ffsl], [
#include <stdio.h>
#include <strings.h>
#include <string.h>
], [
{
int rv = __builtin_ffsl(0x08);
printf("%d\n", rv);
}
], [je_cv_gcc_builtin_ffsl])
if test "x${je_cv_gcc_builtin_ffsl}" = "xyes" ; then
AC_DEFINE([JEMALLOC_INTERNAL_FFSLL], [__builtin_ffsll])
AC_DEFINE([JEMALLOC_INTERNAL_FFSL], [__builtin_ffsl])
AC_DEFINE([JEMALLOC_INTERNAL_FFS], [__builtin_ffs])
else
JE_COMPILABLE([a program using ffsl], [
#include <stdio.h>
#include <strings.h>
#include <string.h>
], [
{
int rv = ffsl(0x08);
printf("%d\n", rv);
}
], [je_cv_function_ffsl])
if test "x${je_cv_function_ffsl}" = "xyes" ; then
AC_DEFINE([JEMALLOC_INTERNAL_FFSLL], [ffsll])
AC_DEFINE([JEMALLOC_INTERNAL_FFSL], [ffsl])
AC_DEFINE([JEMALLOC_INTERNAL_FFS], [ffs])
else
AC_MSG_ERROR([Cannot build without ffsl(3) or __builtin_ffsl()])
fi
fi
JE_COMPILABLE([a program using __builtin_popcountl], [
#include <stdio.h>
#include <strings.h>
#include <string.h>
], [
{
int rv = __builtin_popcountl(0x08);
printf("%d\n", rv);
}
], [je_cv_gcc_builtin_popcountl])
if test "x${je_cv_gcc_builtin_popcountl}" = "xyes" ; then
AC_DEFINE([JEMALLOC_INTERNAL_POPCOUNT], [__builtin_popcount])
AC_DEFINE([JEMALLOC_INTERNAL_POPCOUNTL], [__builtin_popcountl])
fi
AC_ARG_WITH([lg_quantum],
[AS_HELP_STRING([--with-lg-quantum=<lg-quantum>],
[Base 2 log of minimum allocation alignment])],
[LG_QUANTA="$with_lg_quantum"],
[LG_QUANTA="3 4"])
if test "x$with_lg_quantum" != "x" ; then
AC_DEFINE_UNQUOTED([LG_QUANTUM], [$with_lg_quantum])
fi
AC_ARG_WITH([lg_page],
[AS_HELP_STRING([--with-lg-page=<lg-page>], [Base 2 log of system page size])],
[LG_PAGE="$with_lg_page"], [LG_PAGE="detect"])
if test "x$LG_PAGE" = "xdetect"; then
AC_CACHE_CHECK([LG_PAGE],
[je_cv_lg_page],
AC_RUN_IFELSE([AC_LANG_PROGRAM(
[[
#include <strings.h>
#ifdef _WIN32
#include <windows.h>
#else
#include <unistd.h>
#endif
#include <stdio.h>
]],
[[
int result;
FILE *f;
#ifdef _WIN32
SYSTEM_INFO si;
GetSystemInfo(&si);
result = si.dwPageSize;
#else
result = sysconf(_SC_PAGESIZE);
#endif
if (result == -1) {
return 1;
}
result = JEMALLOC_INTERNAL_FFSL(result) - 1;
f = fopen("conftest.out", "w");
if (f == NULL) {
return 1;
}
fprintf(f, "%d", result);
fclose(f);
return 0;
]])],
[je_cv_lg_page=`cat conftest.out`],
[je_cv_lg_page=undefined],
[je_cv_lg_page=12]))
fi
if test "x${je_cv_lg_page}" != "x" ; then
LG_PAGE="${je_cv_lg_page}"
fi
if test "x${LG_PAGE}" != "xundefined" ; then
AC_DEFINE_UNQUOTED([LG_PAGE], [$LG_PAGE])
else
AC_MSG_ERROR([cannot determine value for LG_PAGE])
fi
AC_ARG_WITH([lg_hugepage],
[AS_HELP_STRING([--with-lg-hugepage=<lg-hugepage>],
[Base 2 log of system huge page size])],
[je_cv_lg_hugepage="${with_lg_hugepage}"],
[je_cv_lg_hugepage=""])
if test "x${je_cv_lg_hugepage}" = "x" ; then
dnl Look in /proc/meminfo (Linux-specific) for information on the default huge
dnl page size, if any. The relevant line looks like:
dnl
dnl Hugepagesize: 2048 kB
if test -e "/proc/meminfo" ; then
hpsk=[`cat /proc/meminfo 2>/dev/null | \
grep -e '^Hugepagesize:[[:space:]]\+[0-9]\+[[:space:]]kB$' | \
awk '{print $2}'`]
if test "x${hpsk}" != "x" ; then
je_cv_lg_hugepage=10
while test "${hpsk}" -gt 1 ; do
hpsk="$((hpsk / 2))"
je_cv_lg_hugepage="$((je_cv_lg_hugepage + 1))"
done
fi
fi
dnl Set default if unable to automatically configure.
if test "x${je_cv_lg_hugepage}" = "x" ; then
je_cv_lg_hugepage=21
fi
fi
if test "x${LG_PAGE}" != "xundefined" -a \
"${je_cv_lg_hugepage}" -lt "${LG_PAGE}" ; then
AC_MSG_ERROR([Huge page size (2^${je_cv_lg_hugepage}) must be at least page size (2^${LG_PAGE})])
fi
AC_DEFINE_UNQUOTED([LG_HUGEPAGE], [${je_cv_lg_hugepage}])
dnl ============================================================================
dnl Enable libdl by default.
AC_ARG_ENABLE([libdl],
[AS_HELP_STRING([--disable-libdl],
[Do not use libdl])],
[if test "x$enable_libdl" = "xno" ; then
enable_libdl="0"
else
enable_libdl="1"
fi
],
[enable_libdl="1"]
)
AC_SUBST([libdl])
dnl ============================================================================
dnl Configure pthreads.
if test "x$abi" != "xpecoff" ; then
AC_DEFINE([JEMALLOC_HAVE_PTHREAD], [ ])
AC_CHECK_HEADERS([pthread.h], , [AC_MSG_ERROR([pthread.h is missing])])
dnl Some systems may embed pthreads functionality in libc; check for libpthread
dnl first, but try libc too before failing.
AC_CHECK_LIB([pthread], [pthread_create], [JE_APPEND_VS(LIBS, -pthread)],
[AC_SEARCH_LIBS([pthread_create], , ,
AC_MSG_ERROR([libpthread is missing]))])
wrap_syms="${wrap_syms} pthread_create"
have_pthread="1"
dnl Check if we have dlsym support.
if test "x$enable_libdl" = "x1" ; then
have_dlsym="1"
AC_CHECK_HEADERS([dlfcn.h],
AC_CHECK_FUNC([dlsym], [],
[AC_CHECK_LIB([dl], [dlsym], [LIBS="$LIBS -ldl"], [have_dlsym="0"])]),
[have_dlsym="0"])
if test "x$have_dlsym" = "x1" ; then
AC_DEFINE([JEMALLOC_HAVE_DLSYM], [ ])
fi
else
have_dlsym="0"
fi
JE_COMPILABLE([pthread_atfork(3)], [
#include <pthread.h>
], [
pthread_atfork((void *)0, (void *)0, (void *)0);
], [je_cv_pthread_atfork])
if test "x${je_cv_pthread_atfork}" = "xyes" ; then
AC_DEFINE([JEMALLOC_HAVE_PTHREAD_ATFORK], [ ])
fi
dnl Check if pthread_setname_np is available with the expected API.
JE_COMPILABLE([pthread_setname_np(3)], [
#include <pthread.h>
], [
pthread_setname_np(pthread_self(), "setname_test");
], [je_cv_pthread_setname_np])
if test "x${je_cv_pthread_setname_np}" = "xyes" ; then
AC_DEFINE([JEMALLOC_HAVE_PTHREAD_SETNAME_NP], [ ])
fi
fi
JE_APPEND_VS(CPPFLAGS, -D_REENTRANT)
dnl Check whether clock_gettime(2) is in libc or librt.
AC_SEARCH_LIBS([clock_gettime], [rt])
dnl Cray wrapper compiler often adds `-lrt` when using `-static`. Check with
dnl `-dynamic` as well in case a user tries to dynamically link in jemalloc
if test "x$je_cv_cray_prgenv_wrapper" = "xyes" ; then
if test "$ac_cv_search_clock_gettime" != "-lrt"; then
JE_CFLAGS_SAVE()
unset ac_cv_search_clock_gettime
JE_CFLAGS_ADD([-dynamic])
AC_SEARCH_LIBS([clock_gettime], [rt])
JE_CFLAGS_RESTORE()
fi
fi
dnl check for CLOCK_MONOTONIC_COARSE (Linux-specific).
JE_COMPILABLE([clock_gettime(CLOCK_MONOTONIC_COARSE, ...)], [
#include <time.h>
], [
struct timespec ts;
clock_gettime(CLOCK_MONOTONIC_COARSE, &ts);
], [je_cv_clock_monotonic_coarse])
if test "x${je_cv_clock_monotonic_coarse}" = "xyes" ; then
AC_DEFINE([JEMALLOC_HAVE_CLOCK_MONOTONIC_COARSE])
fi
dnl check for CLOCK_MONOTONIC.
JE_COMPILABLE([clock_gettime(CLOCK_MONOTONIC, ...)], [
#include <unistd.h>
#include <time.h>
], [
struct timespec ts;
clock_gettime(CLOCK_MONOTONIC, &ts);
#if !defined(_POSIX_MONOTONIC_CLOCK) || _POSIX_MONOTONIC_CLOCK < 0
# error _POSIX_MONOTONIC_CLOCK missing/invalid
#endif
], [je_cv_clock_monotonic])
if test "x${je_cv_clock_monotonic}" = "xyes" ; then
AC_DEFINE([JEMALLOC_HAVE_CLOCK_MONOTONIC])
fi
dnl Check for mach_absolute_time().
JE_COMPILABLE([mach_absolute_time()], [
#include <mach/mach_time.h>
], [
mach_absolute_time();
], [je_cv_mach_absolute_time])
if test "x${je_cv_mach_absolute_time}" = "xyes" ; then
AC_DEFINE([JEMALLOC_HAVE_MACH_ABSOLUTE_TIME])
fi
dnl Use syscall(2) (if available) by default.
AC_ARG_ENABLE([syscall],
[AS_HELP_STRING([--disable-syscall], [Disable use of syscall(2)])],
[if test "x$enable_syscall" = "xno" ; then
enable_syscall="0"
else
enable_syscall="1"
fi
],
[enable_syscall="1"]
)
if test "x$enable_syscall" = "x1" ; then
dnl Check if syscall(2) is usable. Treat warnings as errors, so that e.g. OS
dnl X 10.12's deprecation warning prevents use.
JE_CFLAGS_SAVE()
JE_CFLAGS_ADD([-Werror])
JE_COMPILABLE([syscall(2)], [
#include <sys/syscall.h>
#include <unistd.h>
], [
syscall(SYS_write, 2, "hello", 5);
],
[je_cv_syscall])
JE_CFLAGS_RESTORE()
if test "x$je_cv_syscall" = "xyes" ; then
AC_DEFINE([JEMALLOC_USE_SYSCALL], [ ])
fi
fi
dnl Check if the GNU-specific secure_getenv function exists.
AC_CHECK_FUNC([secure_getenv],
[have_secure_getenv="1"],
[have_secure_getenv="0"]
)
if test "x$have_secure_getenv" = "x1" ; then
AC_DEFINE([JEMALLOC_HAVE_SECURE_GETENV], [ ])
fi
dnl Check if the GNU-specific sched_getcpu function exists.
AC_CHECK_FUNC([sched_getcpu],
[have_sched_getcpu="1"],
[have_sched_getcpu="0"]
)
if test "x$have_sched_getcpu" = "x1" ; then
AC_DEFINE([JEMALLOC_HAVE_SCHED_GETCPU], [ ])
fi
dnl Check if the GNU-specific sched_setaffinity function exists.
AC_CHECK_FUNC([sched_setaffinity],
[have_sched_setaffinity="1"],
[have_sched_setaffinity="0"]
)
if test "x$have_sched_setaffinity" = "x1" ; then
AC_DEFINE([JEMALLOC_HAVE_SCHED_SETAFFINITY], [ ])
fi
dnl Check if the Solaris/BSD issetugid function exists.
AC_CHECK_FUNC([issetugid],
[have_issetugid="1"],
[have_issetugid="0"]
)
if test "x$have_issetugid" = "x1" ; then
AC_DEFINE([JEMALLOC_HAVE_ISSETUGID], [ ])
fi
dnl Check whether the BSD-specific _malloc_thread_cleanup() exists. If so, use
dnl it rather than pthreads TSD cleanup functions to support cleanup during
dnl thread exit, in order to avoid pthreads library recursion during
dnl bootstrapping.
AC_CHECK_FUNC([_malloc_thread_cleanup],
[have__malloc_thread_cleanup="1"],
[have__malloc_thread_cleanup="0"]
)
if test "x$have__malloc_thread_cleanup" = "x1" ; then
AC_DEFINE([JEMALLOC_MALLOC_THREAD_CLEANUP], [ ])
wrap_syms="${wrap_syms} _malloc_thread_cleanup"
force_tls="1"
fi
dnl Check whether the BSD-specific _pthread_mutex_init_calloc_cb() exists. If
dnl so, mutex initialization causes allocation, and we need to implement this
dnl callback function in order to prevent recursive allocation.
AC_CHECK_FUNC([_pthread_mutex_init_calloc_cb],
[have__pthread_mutex_init_calloc_cb="1"],
[have__pthread_mutex_init_calloc_cb="0"]
)
if test "x$have__pthread_mutex_init_calloc_cb" = "x1" ; then
AC_DEFINE([JEMALLOC_MUTEX_INIT_CB])
wrap_syms="${wrap_syms} _malloc_prefork _malloc_postfork"
fi
dnl Disable lazy locking by default.
AC_ARG_ENABLE([lazy_lock],
[AS_HELP_STRING([--enable-lazy-lock],
[Enable lazy locking (only lock when multi-threaded)])],
[if test "x$enable_lazy_lock" = "xno" ; then
enable_lazy_lock="0"
else
enable_lazy_lock="1"
fi
],
[enable_lazy_lock=""]
)
if test "x${enable_lazy_lock}" = "x" ; then
if test "x${force_lazy_lock}" = "x1" ; then
AC_MSG_RESULT([Forcing lazy-lock to avoid allocator/threading bootstrap issues])
enable_lazy_lock="1"
else
enable_lazy_lock="0"
fi
fi
if test "x${enable_lazy_lock}" = "x1" -a "x${abi}" = "xpecoff" ; then
AC_MSG_RESULT([Forcing no lazy-lock because thread creation monitoring is unimplemented])
enable_lazy_lock="0"
fi
if test "x$enable_lazy_lock" = "x1" ; then
if test "x$have_dlsym" = "x1" ; then
AC_DEFINE([JEMALLOC_LAZY_LOCK], [ ])
else
AC_MSG_ERROR([Missing dlsym support: lazy-lock cannot be enabled.])
fi
fi
AC_SUBST([enable_lazy_lock])
dnl Automatically configure TLS.
if test "x${force_tls}" = "x1" ; then
enable_tls="1"
elif test "x${force_tls}" = "x0" ; then
enable_tls="0"
else
enable_tls="1"
fi
if test "x${enable_tls}" = "x1" ; then
AC_MSG_CHECKING([for TLS])
AC_COMPILE_IFELSE([AC_LANG_PROGRAM(
[[
__thread int x;
]], [[
x = 42;
return 0;
]])],
AC_MSG_RESULT([yes]),
AC_MSG_RESULT([no])
enable_tls="0")
else
enable_tls="0"
fi
AC_SUBST([enable_tls])
if test "x${enable_tls}" = "x1" ; then
AC_DEFINE_UNQUOTED([JEMALLOC_TLS], [ ])
fi
dnl ============================================================================
dnl Check for C11 atomics.
JE_COMPILABLE([C11 atomics], [
#include <stdint.h>
#if (__STDC_VERSION__ >= 201112L) && !defined(__STDC_NO_ATOMICS__)
#include <stdatomic.h>
#else
#error Atomics not available
#endif
], [
uint64_t *p = (uint64_t *)0;
uint64_t x = 1;
volatile atomic_uint_least64_t *a = (volatile atomic_uint_least64_t *)p;
uint64_t r = atomic_fetch_add(a, x) + x;
return r == 0;
], [je_cv_c11_atomics])
if test "x${je_cv_c11_atomics}" = "xyes" ; then
AC_DEFINE([JEMALLOC_C11_ATOMICS])
fi
dnl ============================================================================
dnl Check for GCC-style __atomic atomics.
JE_COMPILABLE([GCC __atomic atomics], [
], [
int x = 0;
int val = 1;
int y = __atomic_fetch_add(&x, val, __ATOMIC_RELAXED);
int after_add = x;
return after_add == 1;
], [je_cv_gcc_atomic_atomics])
if test "x${je_cv_gcc_atomic_atomics}" = "xyes" ; then
AC_DEFINE([JEMALLOC_GCC_ATOMIC_ATOMICS])
dnl check for 8-bit atomic support
JE_COMPILABLE([GCC 8-bit __atomic atomics], [
], [
unsigned char x = 0;
int val = 1;
int y = __atomic_fetch_add(&x, val, __ATOMIC_RELAXED);
int after_add = (int)x;
return after_add == 1;
], [je_cv_gcc_u8_atomic_atomics])
if test "x${je_cv_gcc_u8_atomic_atomics}" = "xyes" ; then
AC_DEFINE([JEMALLOC_GCC_U8_ATOMIC_ATOMICS])
fi
fi
dnl ============================================================================
dnl Check for GCC-style __sync atomics.
JE_COMPILABLE([GCC __sync atomics], [
], [
int x = 0;
int before_add = __sync_fetch_and_add(&x, 1);
int after_add = x;
return (before_add == 0) && (after_add == 1);
], [je_cv_gcc_sync_atomics])
if test "x${je_cv_gcc_sync_atomics}" = "xyes" ; then
AC_DEFINE([JEMALLOC_GCC_SYNC_ATOMICS])
dnl check for 8-bit atomic support
JE_COMPILABLE([GCC 8-bit __sync atomics], [
], [
unsigned char x = 0;
int before_add = __sync_fetch_and_add(&x, 1);
int after_add = (int)x;
return (before_add == 0) && (after_add == 1);
], [je_cv_gcc_u8_sync_atomics])
if test "x${je_cv_gcc_u8_sync_atomics}" = "xyes" ; then
AC_DEFINE([JEMALLOC_GCC_U8_SYNC_ATOMICS])
fi
fi
dnl ============================================================================
dnl Check for atomic(3) operations as provided on Darwin.
dnl We need this not for the atomic operations (which are provided above), but
dnl rather for the OS_unfair_lock type it exposes.
JE_COMPILABLE([Darwin OSAtomic*()], [
#include <libkern/OSAtomic.h>
#include <inttypes.h>
], [
{
int32_t x32 = 0;
volatile int32_t *x32p = &x32;
OSAtomicAdd32(1, x32p);
}
{
int64_t x64 = 0;
volatile int64_t *x64p = &x64;
OSAtomicAdd64(1, x64p);
}
], [je_cv_osatomic])
if test "x${je_cv_osatomic}" = "xyes" ; then
AC_DEFINE([JEMALLOC_OSATOMIC], [ ])
fi
dnl ============================================================================
dnl Check for madvise(2).
JE_COMPILABLE([madvise(2)], [
#include <sys/mman.h>
], [
madvise((void *)0, 0, 0);
], [je_cv_madvise])
if test "x${je_cv_madvise}" = "xyes" ; then
AC_DEFINE([JEMALLOC_HAVE_MADVISE], [ ])
dnl Check for madvise(..., MADV_FREE).
JE_COMPILABLE([madvise(..., MADV_FREE)], [
#include <sys/mman.h>
], [
madvise((void *)0, 0, MADV_FREE);
], [je_cv_madv_free])
if test "x${je_cv_madv_free}" = "xyes" ; then
AC_DEFINE([JEMALLOC_PURGE_MADVISE_FREE], [ ])
elif test "x${je_cv_madvise}" = "xyes" ; then
case "${host_cpu}" in i686|x86_64)
case "${host}" in *-*-linux*)
AC_DEFINE([JEMALLOC_PURGE_MADVISE_FREE], [ ])
AC_DEFINE([JEMALLOC_DEFINE_MADVISE_FREE], [ ])
;;
esac
;;
esac
fi
dnl Check for madvise(..., MADV_DONTNEED).
JE_COMPILABLE([madvise(..., MADV_DONTNEED)], [
#include <sys/mman.h>
], [
madvise((void *)0, 0, MADV_DONTNEED);
], [je_cv_madv_dontneed])
if test "x${je_cv_madv_dontneed}" = "xyes" ; then
AC_DEFINE([JEMALLOC_PURGE_MADVISE_DONTNEED], [ ])
fi
dnl Check for madvise(..., MADV_DO[NT]DUMP).
JE_COMPILABLE([madvise(..., MADV_DO[[NT]]DUMP)], [
#include <sys/mman.h>
], [
madvise((void *)0, 0, MADV_DONTDUMP);
madvise((void *)0, 0, MADV_DODUMP);
], [je_cv_madv_dontdump])
if test "x${je_cv_madv_dontdump}" = "xyes" ; then
AC_DEFINE([JEMALLOC_MADVISE_DONTDUMP], [ ])
fi
dnl Check for madvise(..., MADV_[NO]HUGEPAGE).
JE_COMPILABLE([madvise(..., MADV_[[NO]]HUGEPAGE)], [
#include <sys/mman.h>
], [
madvise((void *)0, 0, MADV_HUGEPAGE);
madvise((void *)0, 0, MADV_NOHUGEPAGE);
], [je_cv_thp])
case "${host_cpu}" in
arm*)
;;
*)
if test "x${je_cv_thp}" = "xyes" ; then
AC_DEFINE([JEMALLOC_HAVE_MADVISE_HUGE], [ ])
fi
;;
esac
fi
dnl ============================================================================
dnl Check for __builtin_clz() and __builtin_clzl().
AC_CACHE_CHECK([for __builtin_clz],
[je_cv_builtin_clz],
[AC_LINK_IFELSE([AC_LANG_PROGRAM([],
[
{
unsigned x = 0;
int y = __builtin_clz(x);
}
{
unsigned long x = 0;
int y = __builtin_clzl(x);
}
])],
[je_cv_builtin_clz=yes],
[je_cv_builtin_clz=no])])
if test "x${je_cv_builtin_clz}" = "xyes" ; then
AC_DEFINE([JEMALLOC_HAVE_BUILTIN_CLZ], [ ])
fi
dnl ============================================================================
dnl Check for os_unfair_lock operations as provided on Darwin.
JE_COMPILABLE([Darwin os_unfair_lock_*()], [
#include <os/lock.h>
#include <AvailabilityMacros.h>
], [
#if MAC_OS_X_VERSION_MIN_REQUIRED < 101200
#error "os_unfair_lock is not supported"
#else
os_unfair_lock lock = OS_UNFAIR_LOCK_INIT;
os_unfair_lock_lock(&lock);
os_unfair_lock_unlock(&lock);
#endif
], [je_cv_os_unfair_lock])
if test "x${je_cv_os_unfair_lock}" = "xyes" ; then
AC_DEFINE([JEMALLOC_OS_UNFAIR_LOCK], [ ])
fi
dnl ============================================================================
dnl Darwin-related configuration.
AC_ARG_ENABLE([zone-allocator],
[AS_HELP_STRING([--disable-zone-allocator],
[Disable zone allocator for Darwin])],
[if test "x$enable_zone_allocator" = "xno" ; then
enable_zone_allocator="0"
else
enable_zone_allocator="1"
fi
],
[if test "x${abi}" = "xmacho"; then
enable_zone_allocator="1"
fi
]
)
AC_SUBST([enable_zone_allocator])
if test "x${enable_zone_allocator}" = "x1" ; then
if test "x${abi}" != "xmacho"; then
AC_MSG_ERROR([--enable-zone-allocator is only supported on Darwin])
fi
AC_DEFINE([JEMALLOC_ZONE], [ ])
fi
dnl ============================================================================
dnl Use initial-exec TLS by default.
AC_ARG_ENABLE([initial-exec-tls],
[AS_HELP_STRING([--disable-initial-exec-tls],
[Disable the initial-exec tls model])],
[if test "x$enable_initial_exec_tls" = "xno" ; then
enable_initial_exec_tls="0"
else
enable_initial_exec_tls="1"
fi
],
[enable_initial_exec_tls="1"]
)
AC_SUBST([enable_initial_exec_tls])
if test "x${je_cv_tls_model}" = "xyes" -a \
"x${enable_initial_exec_tls}" = "x1" ; then
AC_DEFINE([JEMALLOC_TLS_MODEL],
[__attribute__((tls_model("initial-exec")))])
else
AC_DEFINE([JEMALLOC_TLS_MODEL], [ ])
fi
dnl ============================================================================
dnl Enable background threads if possible.
if test "x${have_pthread}" = "x1" -a "x${je_cv_os_unfair_lock}" != "xyes" ; then
AC_DEFINE([JEMALLOC_BACKGROUND_THREAD])
fi
dnl ============================================================================
dnl Check for glibc malloc hooks
JE_COMPILABLE([glibc malloc hook], [
#include <stddef.h>
extern void (* __free_hook)(void *ptr);
extern void *(* __malloc_hook)(size_t size);
extern void *(* __realloc_hook)(void *ptr, size_t size);
], [
void *ptr = 0L;
if (__malloc_hook) ptr = __malloc_hook(1);
if (__realloc_hook) ptr = __realloc_hook(ptr, 2);
if (__free_hook && ptr) __free_hook(ptr);
], [je_cv_glibc_malloc_hook])
if test "x${je_cv_glibc_malloc_hook}" = "xyes" ; then
if test "x${JEMALLOC_PREFIX}" = "x" ; then
AC_DEFINE([JEMALLOC_GLIBC_MALLOC_HOOK], [ ])
wrap_syms="${wrap_syms} __free_hook __malloc_hook __realloc_hook"
fi
fi
JE_COMPILABLE([glibc memalign hook], [
#include <stddef.h>
extern void *(* __memalign_hook)(size_t alignment, size_t size);
], [
void *ptr = 0L;
if (__memalign_hook) ptr = __memalign_hook(16, 7);
], [je_cv_glibc_memalign_hook])
if test "x${je_cv_glibc_memalign_hook}" = "xyes" ; then
if test "x${JEMALLOC_PREFIX}" = "x" ; then
AC_DEFINE([JEMALLOC_GLIBC_MEMALIGN_HOOK], [ ])
wrap_syms="${wrap_syms} __memalign_hook"
fi
fi
JE_COMPILABLE([pthreads adaptive mutexes], [
#include <pthread.h>
], [
pthread_mutexattr_t attr;
pthread_mutexattr_init(&attr);
pthread_mutexattr_settype(&attr, PTHREAD_MUTEX_ADAPTIVE_NP);
pthread_mutexattr_destroy(&attr);
], [je_cv_pthread_mutex_adaptive_np])
if test "x${je_cv_pthread_mutex_adaptive_np}" = "xyes" ; then
AC_DEFINE([JEMALLOC_HAVE_PTHREAD_MUTEX_ADAPTIVE_NP], [ ])
fi
JE_CFLAGS_SAVE()
JE_CFLAGS_ADD([-D_GNU_SOURCE])
JE_CFLAGS_ADD([-Werror])
JE_CFLAGS_ADD([-herror_on_warning])
JE_COMPILABLE([strerror_r returns char with gnu source], [
#include <errno.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
], [
char *buffer = (char *) malloc(100);
char *error = strerror_r(EINVAL, buffer, 100);
printf("%s\n", error);
], [je_cv_strerror_r_returns_char_with_gnu_source])
JE_CFLAGS_RESTORE()
if test "x${je_cv_strerror_r_returns_char_with_gnu_source}" = "xyes" ; then
AC_DEFINE([JEMALLOC_STRERROR_R_RETURNS_CHAR_WITH_GNU_SOURCE], [ ])
fi
dnl ============================================================================
dnl Check for typedefs, structures, and compiler characteristics.
AC_HEADER_STDBOOL
dnl ============================================================================
dnl Define commands that generate output files.
AC_CONFIG_COMMANDS([include/jemalloc/internal/public_symbols.txt], [
f="${objroot}include/jemalloc/internal/public_symbols.txt"
mkdir -p "${objroot}include/jemalloc/internal"
cp /dev/null "${f}"
for nm in `echo ${mangling_map} |tr ',' ' '` ; do
n=`echo ${nm} |tr ':' ' ' |awk '{print $[]1}'`
m=`echo ${nm} |tr ':' ' ' |awk '{print $[]2}'`
echo "${n}:${m}" >> "${f}"
dnl Remove name from public_syms so that it isn't redefined later.
public_syms=`for sym in ${public_syms}; do echo "${sym}"; done |grep -v "^${n}\$" |tr '\n' ' '`
done
for sym in ${public_syms} ; do
n="${sym}"
m="${JEMALLOC_PREFIX}${sym}"
echo "${n}:${m}" >> "${f}"
done
], [
srcdir="${srcdir}"
objroot="${objroot}"
mangling_map="${mangling_map}"
public_syms="${public_syms}"
JEMALLOC_PREFIX="${JEMALLOC_PREFIX}"
])
AC_CONFIG_COMMANDS([include/jemalloc/internal/private_symbols.awk], [
f="${objroot}include/jemalloc/internal/private_symbols.awk"
mkdir -p "${objroot}include/jemalloc/internal"
export_syms=`for sym in ${public_syms}; do echo "${JEMALLOC_PREFIX}${sym}"; done; for sym in ${wrap_syms}; do echo "${sym}"; done;`
"${srcdir}/include/jemalloc/internal/private_symbols.sh" "${SYM_PREFIX}" ${export_syms} > "${objroot}include/jemalloc/internal/private_symbols.awk"
], [
srcdir="${srcdir}"
objroot="${objroot}"
public_syms="${public_syms}"
wrap_syms="${wrap_syms}"
SYM_PREFIX="${SYM_PREFIX}"
JEMALLOC_PREFIX="${JEMALLOC_PREFIX}"
])
AC_CONFIG_COMMANDS([include/jemalloc/internal/private_symbols_jet.awk], [
f="${objroot}include/jemalloc/internal/private_symbols_jet.awk"
mkdir -p "${objroot}include/jemalloc/internal"
export_syms=`for sym in ${public_syms}; do echo "jet_${sym}"; done; for sym in ${wrap_syms}; do echo "${sym}"; done;`
"${srcdir}/include/jemalloc/internal/private_symbols.sh" "${SYM_PREFIX}" ${export_syms} > "${objroot}include/jemalloc/internal/private_symbols_jet.awk"
], [
srcdir="${srcdir}"
objroot="${objroot}"
public_syms="${public_syms}"
wrap_syms="${wrap_syms}"
SYM_PREFIX="${SYM_PREFIX}"
])
AC_CONFIG_COMMANDS([include/jemalloc/internal/public_namespace.h], [
mkdir -p "${objroot}include/jemalloc/internal"
"${srcdir}/include/jemalloc/internal/public_namespace.sh" "${objroot}include/jemalloc/internal/public_symbols.txt" > "${objroot}include/jemalloc/internal/public_namespace.h"
], [
srcdir="${srcdir}"
objroot="${objroot}"
])
AC_CONFIG_COMMANDS([include/jemalloc/internal/public_unnamespace.h], [
mkdir -p "${objroot}include/jemalloc/internal"
"${srcdir}/include/jemalloc/internal/public_unnamespace.sh" "${objroot}include/jemalloc/internal/public_symbols.txt" > "${objroot}include/jemalloc/internal/public_unnamespace.h"
], [
srcdir="${srcdir}"
objroot="${objroot}"
])
AC_CONFIG_COMMANDS([include/jemalloc/jemalloc_protos_jet.h], [
mkdir -p "${objroot}include/jemalloc"
cat "${srcdir}/include/jemalloc/jemalloc_protos.h.in" | sed -e 's/@je_@/jet_/g' > "${objroot}include/jemalloc/jemalloc_protos_jet.h"
], [
srcdir="${srcdir}"
objroot="${objroot}"
])
AC_CONFIG_COMMANDS([include/jemalloc/jemalloc_rename.h], [
mkdir -p "${objroot}include/jemalloc"
"${srcdir}/include/jemalloc/jemalloc_rename.sh" "${objroot}include/jemalloc/internal/public_symbols.txt" > "${objroot}include/jemalloc/jemalloc_rename.h"
], [
srcdir="${srcdir}"
objroot="${objroot}"
])
AC_CONFIG_COMMANDS([include/jemalloc/jemalloc_mangle.h], [
mkdir -p "${objroot}include/jemalloc"
"${srcdir}/include/jemalloc/jemalloc_mangle.sh" "${objroot}include/jemalloc/internal/public_symbols.txt" je_ > "${objroot}include/jemalloc/jemalloc_mangle.h"
], [
srcdir="${srcdir}"
objroot="${objroot}"
])
AC_CONFIG_COMMANDS([include/jemalloc/jemalloc_mangle_jet.h], [
mkdir -p "${objroot}include/jemalloc"
"${srcdir}/include/jemalloc/jemalloc_mangle.sh" "${objroot}include/jemalloc/internal/public_symbols.txt" jet_ > "${objroot}include/jemalloc/jemalloc_mangle_jet.h"
], [
srcdir="${srcdir}"
objroot="${objroot}"
])
AC_CONFIG_COMMANDS([include/jemalloc/jemalloc.h], [
mkdir -p "${objroot}include/jemalloc"
"${srcdir}/include/jemalloc/jemalloc.sh" "${objroot}" > "${objroot}include/jemalloc/jemalloc${install_suffix}.h"
], [
srcdir="${srcdir}"
objroot="${objroot}"
install_suffix="${install_suffix}"
])
dnl Process .in files.
AC_SUBST([cfghdrs_in])
AC_SUBST([cfghdrs_out])
AC_CONFIG_HEADERS([$cfghdrs_tup])
dnl ============================================================================
dnl Generate outputs.
AC_CONFIG_FILES([$cfgoutputs_tup config.stamp bin/jemalloc-config bin/jemalloc.sh bin/jeprof])
AC_SUBST([cfgoutputs_in])
AC_SUBST([cfgoutputs_out])
AC_OUTPUT
dnl ============================================================================
dnl Print out the results of configuration.
AC_MSG_RESULT([===============================================================================])
AC_MSG_RESULT([jemalloc version : ${jemalloc_version}])
AC_MSG_RESULT([library revision : ${rev}])
AC_MSG_RESULT([])
AC_MSG_RESULT([CONFIG : ${CONFIG}])
AC_MSG_RESULT([CC : ${CC}])
AC_MSG_RESULT([CONFIGURE_CFLAGS : ${CONFIGURE_CFLAGS}])
AC_MSG_RESULT([SPECIFIED_CFLAGS : ${SPECIFIED_CFLAGS}])
AC_MSG_RESULT([EXTRA_CFLAGS : ${EXTRA_CFLAGS}])
AC_MSG_RESULT([CPPFLAGS : ${CPPFLAGS}])
AC_MSG_RESULT([CXX : ${CXX}])
AC_MSG_RESULT([CONFIGURE_CXXFLAGS : ${CONFIGURE_CXXFLAGS}])
AC_MSG_RESULT([SPECIFIED_CXXFLAGS : ${SPECIFIED_CXXFLAGS}])
AC_MSG_RESULT([EXTRA_CXXFLAGS : ${EXTRA_CXXFLAGS}])
AC_MSG_RESULT([LDFLAGS : ${LDFLAGS}])
AC_MSG_RESULT([EXTRA_LDFLAGS : ${EXTRA_LDFLAGS}])
AC_MSG_RESULT([DSO_LDFLAGS : ${DSO_LDFLAGS}])
AC_MSG_RESULT([LIBS : ${LIBS}])
AC_MSG_RESULT([RPATH_EXTRA : ${RPATH_EXTRA}])
AC_MSG_RESULT([])
AC_MSG_RESULT([XSLTPROC : ${XSLTPROC}])
AC_MSG_RESULT([XSLROOT : ${XSLROOT}])
AC_MSG_RESULT([])
AC_MSG_RESULT([PREFIX : ${PREFIX}])
AC_MSG_RESULT([BINDIR : ${BINDIR}])
AC_MSG_RESULT([DATADIR : ${DATADIR}])
AC_MSG_RESULT([INCLUDEDIR : ${INCLUDEDIR}])
AC_MSG_RESULT([LIBDIR : ${LIBDIR}])
AC_MSG_RESULT([MANDIR : ${MANDIR}])
AC_MSG_RESULT([])
AC_MSG_RESULT([srcroot : ${srcroot}])
AC_MSG_RESULT([abs_srcroot : ${abs_srcroot}])
AC_MSG_RESULT([objroot : ${objroot}])
AC_MSG_RESULT([abs_objroot : ${abs_objroot}])
AC_MSG_RESULT([])
AC_MSG_RESULT([JEMALLOC_PREFIX : ${JEMALLOC_PREFIX}])
AC_MSG_RESULT([JEMALLOC_PRIVATE_NAMESPACE])
AC_MSG_RESULT([ : ${JEMALLOC_PRIVATE_NAMESPACE}])
AC_MSG_RESULT([install_suffix : ${install_suffix}])
AC_MSG_RESULT([malloc_conf : ${config_malloc_conf}])
AC_MSG_RESULT([documentation : ${enable_doc}])
AC_MSG_RESULT([shared libs : ${enable_shared}])
AC_MSG_RESULT([static libs : ${enable_static}])
AC_MSG_RESULT([autogen : ${enable_autogen}])
AC_MSG_RESULT([debug : ${enable_debug}])
AC_MSG_RESULT([stats : ${enable_stats}])
AC_MSG_RESULT([experimetal_smallocx : ${enable_experimental_smallocx}])
AC_MSG_RESULT([prof : ${enable_prof}])
AC_MSG_RESULT([prof-libunwind : ${enable_prof_libunwind}])
AC_MSG_RESULT([prof-libgcc : ${enable_prof_libgcc}])
AC_MSG_RESULT([prof-gcc : ${enable_prof_gcc}])
AC_MSG_RESULT([fill : ${enable_fill}])
AC_MSG_RESULT([utrace : ${enable_utrace}])
AC_MSG_RESULT([xmalloc : ${enable_xmalloc}])
AC_MSG_RESULT([log : ${enable_log}])
AC_MSG_RESULT([lazy_lock : ${enable_lazy_lock}])
AC_MSG_RESULT([cache-oblivious : ${enable_cache_oblivious}])
AC_MSG_RESULT([cxx : ${enable_cxx}])
AC_MSG_RESULT([===============================================================================])
<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" version="1.0">
<xsl:import href="@XSLROOT@/html/docbook.xsl"/>
<xsl:import href="@abs_srcroot@doc/stylesheet.xsl"/>
<xsl:output method="xml" encoding="utf-8"/>
</xsl:stylesheet>
<?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://jemalloc.net/">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()</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()</function> function allocates
space for <parameter>number</parameter> objects, each
<parameter>size</parameter> bytes in length. The result is identical to
calling <function>malloc()</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()</function> function
allocates <parameter>size</parameter> bytes of memory such that the
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
<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()</function> function
allocates <parameter>size</parameter> bytes of memory such that the
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()</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()</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()</function> function behaves identically to
<function>malloc()</function> for the specified size.</para>
<para>The <function>free()</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()</function>,
<function>rallocx()</function>,
<function>xallocx()</function>,
<function>sallocx()</function>,
<function>dallocx()</function>,
<function>sdallocx()</function>, and
<function>nallocx()</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()</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>.</para>
<para>The <function>rallocx()</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>.</para>
<para>The <function>xallocx()</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()</function> function returns the
real size of the allocation at <parameter>ptr</parameter>.</para>
<para>The <function>dallocx()</function> function causes the
memory referenced by <parameter>ptr</parameter> to be made available for
future allocations.</para>
<para>The <function>sdallocx()</function> function is an
extension of <function>dallocx()</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()</function> or
<function>sallocx()</function>.</para>
<para>The <function>nallocx()</function> function allocates no
memory, but it performs the same size computation as the
<function>mallocx()</function> function, and returns the real
size of the allocation that would result from the equivalent
<function>mallocx()</function> function call, or
<constant>0</constant> if the inputs exceed the maximum supported size
class and/or alignment. Behavior is undefined if
<parameter>size</parameter> is <constant>0</constant>.</para>
<para>The <function>mallctl()</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()</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 <quote>Management Information Base</quote> (MIB) that can be passed
repeatedly to <function>mallctlbymib()</function>. Upon
successful return from <function>mallctlnametomib()</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;
size_t mib[4];
size_t len, miblen;
len = sizeof(nbins);
mallctl("arenas.nbins", &nbins, &len, NULL, 0);
miblen = 4;
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, (void *)&bin_size, &len, NULL, 0);
/* Do something with bin_size... */
}]]></programlisting></para>
<varlistentry id="malloc_stats_print_opts">
</varlistentry>
<para>The <function>malloc_stats_print()</function> function writes
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()</function>
if <parameter>write_cb</parameter> is <constant>NULL</constant>. The
statistics are presented in human-readable form unless <quote>J</quote> is
specified as a character within the <parameter>opts</parameter> string, in
which case the statistics are presented in <ulink
url="http://www.json.org/">JSON format</ulink>. This function can be
called repeatedly. General information that never changes during
execution can be omitted by specifying <quote>g</quote> as a character
within the <parameter>opts</parameter> string. Note that
<function>malloc_stats_print()</function> uses the
<function>mallctl*()</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, <quote>m</quote>, <quote>d</quote>, and <quote>a</quote>
can be specified to omit merged arena, destroyed merged arena, and per
arena statistics, respectively; <quote>b</quote> and <quote>l</quote> can
be specified to omit per size class statistics for bins and large objects,
respectively; <quote>x</quote> can be specified to omit all mutex
statistics; <quote>e</quote> can be used to omit extent statistics.
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()</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()</function> function is not a
mechanism for in-place <function>realloc()</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()</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
<quote>name</quote> 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()</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, this allocator supports
thread-specific caching, 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 extents. Extents are always
aligned to multiples of the page size. This alignment makes it possible to
find metadata for user objects quickly. User objects are broken into two
categories according to size: small and large. Contiguous small objects
comprise a slab, which resides within a single extent, whereas large objects
each have their own extents backing them.</para>
<para>Small objects are managed in groups by slabs. Each slab maintains
a bitmap to track which regions are in use. Allocation requests that are no
more than half the quantum (8 or 16, depending on architecture) are rounded
up to the nearest power of two that is at least <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, and large size classes extend
from four times the page size up to the largest size class that does not
exceed <constant>PTRDIFF_MAX</constant>.</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()</function>,
<function>rallocx()</function>, and
<function>xallocx()</function> functions may resize allocations
without moving them under limited circumstances. Unlike the
<function>*allocx()</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()</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
allocations in place, as long as the pre-size and post-size are both large.
For shrinkage to succeed, the extent allocator must support splitting (see
<link
linkend="arena.i.extent_hooks"><mallctl>arena.&lt;i&gt;.extent_hooks</mallctl></link>).
Growth only succeeds if the trailing memory is currently available, and the
extent allocator supports merging.</para>
<para>Assuming 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>
<entry morerows="8">Small</entry>
<entry>lg</entry>
<entry>[8]</entry>
</row>
<row>
<entry>16</entry>
<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>
<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="15">Large</entry>
<entry>2 KiB</entry>
<entry>[16 KiB]</entry>
</row>
<row>
<entry>4 KiB</entry>
<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>
</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>
</row>
<row>
<entry>256 KiB</entry>
<entry>[1280 KiB, 1536 KiB, 1792 KiB, 2 MiB]</entry>
</row>
<row>
<entry>512 KiB</entry>
<entry>[2560 KiB, 3 MiB, 3584 KiB, 4 MiB]</entry>
</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>
<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>
<row>
<entry>512 PiB</entry>
<entry>[2560 PiB, 3 EiB, 3584 PiB, 4 EiB]</entry>
</row>
<row>
<entry>1 EiB</entry>
<entry>[5 EiB, 6 EiB, 7 EiB]</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*()</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>
and <mallctl>arena.&lt;i&gt;.{initialized,purge,decay,dss}</mallctl>,
<literal>&lt;i&gt;</literal> equal to
<constant>MALLCTL_ARENAS_ALL</constant> can be used to operate on all arenas
or access the summation of statistics from all arenas; similarly
<literal>&lt;i&gt;</literal> equal to
<constant>MALLCTL_ARENAS_DESTROYED</constant> can be used to access the
summation of statistics from all destroyed arenas. These constants can be
utilized either via <function>mallctlnametomib()</function> followed by
<function>mallctlbymib()</function>, or via code such as the following:
<programlisting language="C"><![CDATA[
#define STRINGIFY_HELPER(x) #x
#define STRINGIFY(x) STRINGIFY_HELPER(x)
mallctl("arena." STRINGIFY(MALLCTL_ARENAS_ALL) ".decay",
NULL, NULL, NULL, 0);]]></programlisting>
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*()</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="background_thread">
<term>
<mallctl>background_thread</mallctl>
(<type>bool</type>)
<literal>rw</literal>
</term>
<listitem><para>Enable/disable internal background worker threads. When
set to true, background threads are created on demand (the number of
background threads will be no more than the number of CPUs or active
arenas). Threads run periodically, and handle <link
linkend="arena.i.decay">purging</link> asynchronously. When switching
off, background threads are terminated synchronously. Note that after
<citerefentry><refentrytitle>fork</refentrytitle><manvolnum>2</manvolnum></citerefentry>
function, the state in the child process will be disabled regardless
the state in parent process. See <link
linkend="stats.background_thread.num_threads"><mallctl>stats.background_thread</mallctl></link>
for related stats. <link
linkend="opt.background_thread"><mallctl>opt.background_thread</mallctl></link>
can be used to set the default option. This option is only available on
selected pthread-based platforms.</para></listitem>
</varlistentry>
<varlistentry id="max_background_threads">
<term>
<mallctl>max_background_threads</mallctl>
(<type>size_t</type>)
<literal>rw</literal>
</term>
<listitem><para>Maximum number of background worker threads that will
be created. This value is capped at <link
linkend="opt.max_background_threads"><mallctl>opt.max_background_threads</mallctl></link> at
startup.</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.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.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.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. Note that runtime option warnings are not included
(see <link
linkend="opt.abort_conf"><mallctl>opt.abort_conf</mallctl></link> for
that). 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.confirm_conf">
<term>
<mallctl>opt.confirm_conf</mallctl>
(<type>bool</type>)
<literal>r-</literal>
</term>
<listitem><para>Confirm-runtime-options-when-program-starts
enabled/disabled. If true, the string specified via
<option>--with-malloc-conf</option>, the string pointed to by the
global variable <varname>malloc_conf</varname>, the <quote>name</quote>
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 printed in
order. Then, each option being set will be individually printed. This
option is disabled by default.</para></listitem>
</varlistentry>
<varlistentry id="opt.abort_conf">
<term>
<mallctl>opt.abort_conf</mallctl>
(<type>bool</type>)
<literal>r-</literal>
</term>
<listitem><para>Abort-on-invalid-configuration enabled/disabled. If
true, invalid runtime options 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.metadata_thp">
<term>
<mallctl>opt.metadata_thp</mallctl>
(<type>const char *</type>)
<literal>r-</literal>
</term>
<listitem><para>Controls whether to allow jemalloc to use transparent
huge page (THP) for internal metadata (see <link
linkend="stats.metadata">stats.metadata</link>). <quote>always</quote>
allows such usage. <quote>auto</quote> uses no THP initially, but may
begin to do so when metadata usage reaches certain level. The default
is <quote>disabled</quote>.</para></listitem>
</varlistentry>
<varlistentry id="opt.retain">
<term>
<mallctl>opt.retain</mallctl>
(<type>bool</type>)
<literal>r-</literal>
</term>
<listitem><para>If true, retain unused virtual memory for later reuse
rather than discarding it by calling
<citerefentry><refentrytitle>munmap</refentrytitle>
<manvolnum>2</manvolnum></citerefentry> or equivalent (see <link
linkend="stats.retained">stats.retained</link> for related details).
It also makes jemalloc use <citerefentry>
<refentrytitle>mmap</refentrytitle><manvolnum>2</manvolnum>
</citerefentry> or equivalent in a more greedy way, mapping larger
chunks in one go. This option is disabled by default unless discarding
virtual memory is known to trigger platform-specific performance
problems, namely 1) for [64-bit] Linux, which has a quirk in its virtual
memory allocation algorithm that causes semi-permanent VM map holes
under normal jemalloc operation; and 2) for [64-bit] Windows, which
disallows split / merged regions with
<parameter><constant>MEM_RELEASE</constant></parameter>. Although the
same issues may present on 32-bit platforms as well, retaining virtual
memory for 32-bit Linux and Windows is disabled by default due to the
practical possibility of address space exhaustion. </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: <quote>disabled</quote>, <quote>primary</quote>, and
<quote>secondary</quote>; otherwise only <quote>disabled</quote> is
supported. The default is <quote>secondary</quote> if
<citerefentry><refentrytitle>sbrk</refentrytitle>
<manvolnum>2</manvolnum></citerefentry> is supported by the operating
system; <quote>disabled</quote> otherwise.
</para></listitem>
</varlistentry>
<varlistentry id="opt.narenas">
<term>
<mallctl>opt.narenas</mallctl>
(<type>unsigned</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.oversize_threshold">
<term>
<mallctl>opt.oversize_threshold</mallctl>
(<type>size_t</type>)
<literal>r-</literal>
</term>
<listitem><para>The threshold in bytes of which requests are considered
oversize. Allocation requests with greater sizes are fulfilled from a
dedicated arena (automatically managed, however not within
<literal>narenas</literal>), in order to reduce fragmentation by not
mixing huge allocations with small ones. In addition, the decay API
guarantees on the extents greater than the specified threshold may be
overridden. Note that requests with arena index specified via
<constant>MALLOCX_ARENA</constant>, or threads associated with explicit
arenas will not be considered. The default threshold is 8MiB. Values
not within large size classes disables this feature.</para></listitem>
</varlistentry>
<varlistentry id="opt.percpu_arena">
<term>
<mallctl>opt.percpu_arena</mallctl>
(<type>const char *</type>)
<literal>r-</literal>
</term>
<listitem><para>Per CPU arena mode. Use the <quote>percpu</quote>
setting to enable this feature, which uses number of CPUs to determine
number of arenas, and bind threads to arenas dynamically based on the
CPU the thread runs on currently. <quote>phycpu</quote> setting uses
one arena per physical CPU, which means the two hyper threads on the
same CPU share one arena. Note that no runtime checking regarding the
availability of hyper threading is done at the moment. When set to
<quote>disabled</quote>, narenas and thread to arena association will
not be impacted by this option. The default is <quote>disabled</quote>.
</para></listitem>
</varlistentry>
<varlistentry id="opt.background_thread">
<term>
<mallctl>opt.background_thread</mallctl>
(<type>bool</type>)
<literal>r-</literal>
</term>
<listitem><para>Internal background worker threads enabled/disabled.
Because of potential circular dependencies, enabling background thread
using this option may cause crash or deadlock during initialization. For
a reliable way to use this feature, see <link
linkend="background_thread">background_thread</link> for dynamic control
options and details. This option is disabled by
default.</para></listitem>
</varlistentry>
<varlistentry id="opt.max_background_threads">
<term>
<mallctl>opt.max_background_threads</mallctl>
(<type>size_t</type>)
<literal>r-</literal>
</term>
<listitem><para>Maximum number of background threads that will be created
if <link linkend="background_thread">background_thread</link> is set.
Defaults to number of cpus.</para></listitem>
</varlistentry>
<varlistentry id="opt.dirty_decay_ms">
<term>
<mallctl>opt.dirty_decay_ms</mallctl>
(<type>ssize_t</type>)
<literal>r-</literal>
</term>
<listitem><para>Approximate time in milliseconds from the creation of a
set of unused dirty pages until an equivalent set of unused dirty pages
is purged (i.e. converted to muzzy via e.g.
<function>madvise(<parameter>...</parameter><parameter><constant>MADV_FREE</constant></parameter>)</function>
if supported by the operating system, or converted to clean otherwise)
and/or reused. Dirty pages are defined as previously having been
potentially written to by the application, and therefore consuming
physical memory, yet having no current use. 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.dirty_decay_ms"><mallctl>arenas.dirty_decay_ms</mallctl></link>
and <link
linkend="arena.i.dirty_decay_ms"><mallctl>arena.&lt;i&gt;.dirty_decay_ms</mallctl></link>
for related dynamic control options. See <link
linkend="opt.muzzy_decay_ms"><mallctl>opt.muzzy_decay_ms</mallctl></link>
for a description of muzzy pages.for a description of muzzy pages. Note
that when the <link
linkend="opt.oversize_threshold"><mallctl>oversize_threshold</mallctl></link>
feature is enabled, the arenas reserved for oversize requests may have
its own default decay settings.</para></listitem>
</varlistentry>
<varlistentry id="opt.muzzy_decay_ms">
<term>
<mallctl>opt.muzzy_decay_ms</mallctl>
(<type>ssize_t</type>)
<literal>r-</literal>
</term>
<listitem><para>Approximate time in milliseconds from the creation of a
set of unused muzzy pages until an equivalent set of unused muzzy pages
is purged (i.e. converted to clean) and/or reused. Muzzy pages are
defined as previously having been unused dirty pages that were
subsequently purged in a manner that left them subject to the
reclamation whims of the operating system (e.g.
<function>madvise(<parameter>...</parameter><parameter><constant>MADV_FREE</constant></parameter>)</function>),
and therefore in an indeterminate state. 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 muzzy 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.muzzy_decay_ms"><mallctl>arenas.muzzy_decay_ms</mallctl></link>
and <link
linkend="arena.i.muzzy_decay_ms"><mallctl>arena.&lt;i&gt;.muzzy_decay_ms</mallctl></link>
for related dynamic control options.</para></listitem>
</varlistentry>
<varlistentry id="opt.lg_extent_max_active_fit">
<term>
<mallctl>opt.lg_extent_max_active_fit</mallctl>
(<type>size_t</type>)
<literal>r-</literal>
</term>
<listitem><para>When reusing dirty extents, this determines the (log
base 2 of the) maximum ratio between the size of the active extent
selected (to split off from) and the size of the requested allocation.
This prevents the splitting of large active extents for smaller
allocations, which can reduce fragmentation over the long run
(especially for non-active extents). Lower value may reduce
fragmentation, at the cost of extra active extents. The default value
is 6, which gives a maximum ratio of 64 (2^6).</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()</function>
function is called at program exit via an
<citerefentry><refentrytitle>atexit</refentrytitle>
<manvolnum>3</manvolnum></citerefentry> function. <link
linkend="opt.stats_print_opts"><mallctl>opt.stats_print_opts</mallctl></link>
can be combined to specify output options. 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()</function> may
allocate memory during application initialization and then deadlock
internally when jemalloc in turn calls
<function>atexit()</function>, so this option is not
universally usable (though the application can register its own
<function>atexit()</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.stats_print_opts">
<term>
<mallctl>opt.stats_print_opts</mallctl>
(<type>const char *</type>)
<literal>r-</literal>
</term>
<listitem><para>Options (the <parameter>opts</parameter> string) to pass
to the <function>malloc_stats_print()</function> at exit (enabled
through <link
linkend="opt.stats_print"><mallctl>opt.stats_print</mallctl></link>). See
available options in <link
linkend="malloc_stats_print_opts"><function>malloc_stats_print()</function></link>.
Has no effect unless <link
linkend="opt.stats_print"><mallctl>opt.stats_print</mallctl></link> is
enabled. The default is <quote></quote>.</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 <quote>alloc</quote>, each byte
of uninitialized allocated memory will be initialized to
<literal>0xa5</literal>. If set to <quote>free</quote>, all deallocated
memory will be initialized to <literal>0x5a</literal>. If set to
<quote>true</quote>, both allocated and deallocated memory will be
initialized, and if set to <quote>false</quote>, junk filling be
disabled entirely. This is intended for debugging and will impact
performance negatively. This option is <quote>false</quote> by default
unless <option>--enable-debug</option> is specified during
configuration, in which case it is <quote>true</quote> by
default.</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()</function> and
<function>rallocx()</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>
</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.</para></listitem>
</varlistentry>
<varlistentry id="opt.lg_tcache_max">
<term>
<mallctl>opt.lg_tcache_max</mallctl>
(<type>size_t</type>)
<literal>r-</literal>
</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.thp">
<term>
<mallctl>opt.thp</mallctl>
(<type>const char *</type>)
<literal>r-</literal>
</term>
<listitem><para>Transparent hugepage (THP) mode. Settings "always",
"never" and "default" are available if THP is supported by the operating
system. The "always" setting enables transparent hugepage for all user
memory mappings with
<parameter><constant>MADV_HUGEPAGE</constant></parameter>; "never"
ensures no transparent hugepage with
<parameter><constant>MADV_NOHUGEPAGE</constant></parameter>; the default
setting "default" makes no changes. Note that: this option does not
affect THP for jemalloc internal metadata (see <link
linkend="opt.metadata_thp"><mallctl>opt.metadata_thp</mallctl></link>);
in addition, for arenas with customized <link
linkend="arena.i.extent_hooks"><mallctl>extent_hooks</mallctl></link>,
this option is bypassed as it is implemented as part of the default
extent hooks.</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>. See <link linkend="heap_profile_format">HEAP PROFILE
FORMAT</link> for heap profile format documentation.</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()</function> may allocate
memory during application initialization and then deadlock internally
when jemalloc in turn calls <function>atexit()</function>, so
this option is not universally usable (though the application can
register its own <function>atexit()</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="arena.i.initialized"><mallctl>arena.i.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*()</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*()</function> calls.</para></listitem>
</varlistentry>
<varlistentry id="thread.tcache.enabled">
<term>
<mallctl>thread.tcache.enabled</mallctl>
(<type>bool</type>)
<literal>rw</literal>
</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>
</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
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>
</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>
</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>,
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>
</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.initialized">
<term>
<mallctl>arena.&lt;i&gt;.initialized</mallctl>
(<type>bool</type>)
<literal>r-</literal>
</term>
<listitem><para>Get whether the specified arena's statistics are
initialized (i.e. the arena was initialized prior to the current epoch).
This interface can also be nominally used to query whether the merged
statistics corresponding to <constant>MALLCTL_ARENAS_ALL</constant> are
initialized (always true).</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/muzzy pages
for arena &lt;i&gt;, or for all arenas if &lt;i&gt; equals
<constant>MALLCTL_ARENAS_ALL</constant>. The proportion of unused
dirty/muzzy pages to be purged depends on the current time; see <link
linkend="opt.dirty_decay_ms"><mallctl>opt.dirty_decay_ms</mallctl></link>
and <link
linkend="opt.muzzy_decay_ms"><mallctl>opt.muzy_decay_ms</mallctl></link>
for details.</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 <constant>MALLCTL_ARENAS_ALL</constant>.
</para></listitem>
</varlistentry>
<varlistentry id="arena.i.reset">
<term>
<mallctl>arena.&lt;i&gt;.reset</mallctl>
(<type>void</type>)
<literal>--</literal>
</term>
<listitem><para>Discard all of the arena's extant allocations. This
interface can only be used with arenas explicitly created via <link
linkend="arenas.create"><mallctl>arenas.create</mallctl></link>. None
of the arena's discarded/cached allocations may accessed afterward. As
part of this requirement, all thread caches which were used to
allocate/deallocate in conjunction with the arena must be flushed
beforehand.</para></listitem>
</varlistentry>
<varlistentry id="arena.i.destroy">
<term>
<mallctl>arena.&lt;i&gt;.destroy</mallctl>
(<type>void</type>)
<literal>--</literal>
</term>
<listitem><para>Destroy the arena. Discard all of the arena's extant
allocations using the same mechanism as for <link
linkend="arena.i.reset"><mallctl>arena.&lt;i&gt;.reset</mallctl></link>
(with all the same constraints and side effects), merge the arena stats
into those accessible at arena index
<constant>MALLCTL_ARENAS_DESTROYED</constant>, and then completely
discard all metadata associated with the arena. Future calls to <link
linkend="arenas.create"><mallctl>arenas.create</mallctl></link> may
recycle the arena index. Destruction will fail if any threads are
currently associated with the arena as a result of calls to <link
linkend="thread.arena"><mallctl>thread.arena</mallctl></link>.</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
<constant>MALLCTL_ARENAS_ALL</constant>. See <link
linkend="opt.dss"><mallctl>opt.dss</mallctl></link> for supported
settings.</para></listitem>
</varlistentry>
<varlistentry id="arena.i.dirty_decay_ms">
<term>
<mallctl>arena.&lt;i&gt;.dirty_decay_ms</mallctl>
(<type>ssize_t</type>)
<literal>rw</literal>
</term>
<listitem><para>Current per-arena approximate time in milliseconds 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.dirty_decay_ms"><mallctl>opt.dirty_decay_ms</mallctl></link>
for additional information.</para></listitem>
</varlistentry>
<varlistentry id="arena.i.muzzy_decay_ms">
<term>
<mallctl>arena.&lt;i&gt;.muzzy_decay_ms</mallctl>
(<type>ssize_t</type>)
<literal>rw</literal>
</term>
<listitem><para>Current per-arena approximate time in milliseconds from
the creation of a set of unused muzzy pages until an equivalent set of
unused muzzy pages is purged and/or reused. Each time this interface is
set, all currently unused muzzy pages are considered to have fully
decayed, which causes immediate purging of all unused muzzy pages unless
the decay time is set to -1 (i.e. purging disabled). See <link
linkend="opt.muzzy_decay_ms"><mallctl>opt.muzzy_decay_ms</mallctl></link>
for additional information.</para></listitem>
</varlistentry>
<varlistentry id="arena.i.retain_grow_limit">
<term>
<mallctl>arena.&lt;i&gt;.retain_grow_limit</mallctl>
(<type>size_t</type>)
<literal>rw</literal>
</term>
<listitem><para>Maximum size to grow retained region (only relevant when
<link linkend="opt.retain"><mallctl>opt.retain</mallctl></link> is
enabled). This controls the maximum increment to expand virtual memory,
or allocation through <link
linkend="arena.i.extent_hooks"><mallctl>arena.&lt;i&gt;extent_hooks</mallctl></link>.
In particular, if customized extent hooks reserve physical memory
(e.g. 1G huge pages), this is useful to control the allocation hook's
input size. The default is no limit.</para></listitem>
</varlistentry>
<varlistentry id="arena.i.extent_hooks">
<term>
<mallctl>arena.&lt;i&gt;.extent_hooks</mallctl>
(<type>extent_hooks_t *</type>)
<literal>rw</literal>
</term>
<listitem><para>Get or set the extent management hook functions for
arena &lt;i&gt;. The functions must be capable of operating on all
extant extents associated with arena &lt;i&gt;, usually by passing
unknown extents to the replaced functions. In practice, it is feasible
to control allocation for arenas explicitly created via <link
linkend="arenas.create"><mallctl>arenas.create</mallctl></link> such
that all extents originate from an application-supplied extent allocator
(by specifying the custom extent hook functions during arena creation).
However, the API guarantees for the automatically created arenas may be
relaxed -- hooks set there may be called in a "best effort" fashion; in
addition there may be extents created prior to the application having an
opportunity to take over extent allocation.</para>
<programlisting language="C"><![CDATA[
typedef extent_hooks_s extent_hooks_t;
struct extent_hooks_s {
extent_alloc_t *alloc;
extent_dalloc_t *dalloc;
extent_destroy_t *destroy;
extent_commit_t *commit;
extent_decommit_t *decommit;
extent_purge_t *purge_lazy;
extent_purge_t *purge_forced;
extent_split_t *split;
extent_merge_t *merge;
};]]></programlisting>
<para>The <type>extent_hooks_t</type> structure comprises function
pointers which are described individually below. jemalloc uses these
functions to manage extent 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 extents
for later reuse. Cleanup attempts cascade from deallocation to decommit
to forced purging to lazy purging, which gives the extent management
functions opportunities to reject the most permanent cleanup operations
in favor of less permanent (and often less costly) operations. All
operations except allocation can be universally opted out of by setting
the hook pointers to <constant>NULL</constant>, or selectively opted out
of by returning failure. Note that once the extent hook is set, the
structure is accessed directly by the associated arenas, so it must
remain valid for the entire lifetime of the arenas.</para>
<funcsynopsis><funcprototype>
<funcdef>typedef void *<function>(extent_alloc_t)</function></funcdef>
<paramdef>extent_hooks_t *<parameter>extent_hooks</parameter></paramdef>
<paramdef>void *<parameter>new_addr</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>An extent allocation function conforms to the
<type>extent_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 extent's base address is
a multiple of <parameter>alignment</parameter>, as well as setting
<parameter>*zero</parameter> to indicate whether the extent is zeroed
and <parameter>*commit</parameter> to indicate whether the extent 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 page
size. The <parameter>alignment</parameter> parameter is always a power
of two at least as large as the page 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>new_addr</parameter> is not <constant>NULL</constant>, the
returned pointer must be <parameter>new_addr</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 extent 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>(extent_dalloc_t)</function></funcdef>
<paramdef>extent_hooks_t *<parameter>extent_hooks</parameter></paramdef>
<paramdef>void *<parameter>addr</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>
An extent deallocation function conforms to the
<type>extent_dalloc_t</type> type and deallocates an extent at given
<parameter>addr</parameter> and <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 extent
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 void <function>(extent_destroy_t)</function></funcdef>
<paramdef>extent_hooks_t *<parameter>extent_hooks</parameter></paramdef>
<paramdef>void *<parameter>addr</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>
An extent destruction function conforms to the
<type>extent_destroy_t</type> type and unconditionally destroys an
extent at given <parameter>addr</parameter> and
<parameter>size</parameter> with
<parameter>committed</parameter>/decommited memory as indicated, on
behalf of arena <parameter>arena_ind</parameter>. This function may be
called to destroy retained extents during arena destruction (see <link
linkend="arena.i.destroy"><mallctl>arena.&lt;i&gt;.destroy</mallctl></link>).</para>
<funcsynopsis><funcprototype>
<funcdef>typedef bool <function>(extent_commit_t)</function></funcdef>
<paramdef>extent_hooks_t *<parameter>extent_hooks</parameter></paramdef>
<paramdef>void *<parameter>addr</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>An extent commit function conforms to the
<type>extent_commit_t</type> type and commits zeroed physical memory to
back pages within an extent at given <parameter>addr</parameter> and
<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>(extent_decommit_t)</function></funcdef>
<paramdef>extent_hooks_t *<parameter>extent_hooks</parameter></paramdef>
<paramdef>void *<parameter>addr</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>An extent decommit function conforms to the
<type>extent_decommit_t</type> type and decommits any physical memory
that is backing pages within an extent at given
<parameter>addr</parameter> and <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 extent 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>(extent_purge_t)</function></funcdef>
<paramdef>extent_hooks_t *<parameter>extent_hooks</parameter></paramdef>
<paramdef>void *<parameter>addr</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>An extent purge function conforms to the
<type>extent_purge_t</type> type and discards physical pages
within the virtual memory mapping associated with an extent at given
<parameter>addr</parameter> and <parameter>size</parameter> at
<parameter>offset</parameter> bytes, extending for
<parameter>length</parameter> on behalf of arena
<parameter>arena_ind</parameter>. A lazy extent purge function (e.g.
implemented via
<function>madvise(<parameter>...</parameter><parameter><constant>MADV_FREE</constant></parameter>)</function>)
can delay purging indefinitely and leave the pages within the purged
virtual memory range in an indeterminite state, whereas a forced extent
purge function immediately purges, and the pages within the virtual
memory range will be zero-filled the next time they are accessed. If
the function returns true, this indicates failure to purge.</para>
<funcsynopsis><funcprototype>
<funcdef>typedef bool <function>(extent_split_t)</function></funcdef>
<paramdef>extent_hooks_t *<parameter>extent_hooks</parameter></paramdef>
<paramdef>void *<parameter>addr</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>An extent split function conforms to the
<type>extent_split_t</type> type and optionally splits an extent at
given <parameter>addr</parameter> and <parameter>size</parameter> into
two adjacent extents, 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 extent
remains unsplit and therefore should continue to be operated on as a
whole.</para>
<funcsynopsis><funcprototype>
<funcdef>typedef bool <function>(extent_merge_t)</function></funcdef>
<paramdef>extent_hooks_t *<parameter>extent_hooks</parameter></paramdef>
<paramdef>void *<parameter>addr_a</parameter></paramdef>
<paramdef>size_t <parameter>size_a</parameter></paramdef>
<paramdef>void *<parameter>addr_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>An extent merge function conforms to the
<type>extent_merge_t</type> type and optionally merges adjacent extents,
at given <parameter>addr_a</parameter> and <parameter>size_a</parameter>
with given <parameter>addr_b</parameter> and
<parameter>size_b</parameter> into one contiguous extent, 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 extents
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.dirty_decay_ms">
<term>
<mallctl>arenas.dirty_decay_ms</mallctl>
(<type>ssize_t</type>)
<literal>rw</literal>
</term>
<listitem><para>Current default per-arena approximate time in
milliseconds 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.dirty_decay_ms"><mallctl>arena.&lt;i&gt;.dirty_decay_ms</mallctl></link>
during arena creation. See <link
linkend="opt.dirty_decay_ms"><mallctl>opt.dirty_decay_ms</mallctl></link>
for additional information.</para></listitem>
</varlistentry>
<varlistentry id="arenas.muzzy_decay_ms">
<term>
<mallctl>arenas.muzzy_decay_ms</mallctl>
(<type>ssize_t</type>)
<literal>rw</literal>
</term>
<listitem><para>Current default per-arena approximate time in
milliseconds from the creation of a set of unused muzzy pages until an
equivalent set of unused muzzy pages is purged and/or reused, used to
initialize <link
linkend="arena.i.muzzy_decay_ms"><mallctl>arena.&lt;i&gt;.muzzy_decay_ms</mallctl></link>
during arena creation. See <link
linkend="opt.muzzy_decay_ms"><mallctl>opt.muzzy_decay_ms</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>
</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>
</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 slab.</para></listitem>
</varlistentry>
<varlistentry id="arenas.bin.i.slab_size">
<term>
<mallctl>arenas.bin.&lt;i&gt;.slab_size</mallctl>
(<type>size_t</type>)
<literal>r-</literal>
</term>
<listitem><para>Number of bytes per slab.</para></listitem>
</varlistentry>
<varlistentry id="arenas.nlextents">
<term>
<mallctl>arenas.nlextents</mallctl>
(<type>unsigned</type>)
<literal>r-</literal>
</term>
<listitem><para>Total number of large size classes.</para></listitem>
</varlistentry>
<varlistentry id="arenas.lextent.i.size">
<term>
<mallctl>arenas.lextent.&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.create">
<term>
<mallctl>arenas.create</mallctl>
(<type>unsigned</type>, <type>extent_hooks_t *</type>)
<literal>rw</literal>
</term>
<listitem><para>Explicitly create a new arena outside the range of
automatically managed arenas, with optionally specified extent hooks,
and return the new arena index.</para></listitem>
</varlistentry>
<varlistentry id="arenas.lookup">
<term>
<mallctl>arenas.lookup</mallctl>
(<type>unsigned</type>, <type>void*</type>)
<literal>rw</literal>
</term>
<listitem><para>Index of the arena to which an allocation belongs to.</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
interval-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.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>,
<link linkend="stats.arenas.i.pmuzzy">
<mallctl>stats.arenas.&lt;i&gt;.pmuzzy</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 allocator
metadata structures (see <link
linkend="stats.arenas.i.base"><mallctl>stats.arenas.&lt;i&gt;.base</mallctl></link>)
and internal allocations (see <link
linkend="stats.arenas.i.internal"><mallctl>stats.arenas.&lt;i&gt;.internal</mallctl></link>).
Transparent huge page (enabled with <link
linkend="opt.metadata_thp">opt.metadata_thp</link>) usage is not
considered.</para></listitem>
</varlistentry>
<varlistentry id="stats.metadata_thp">
<term>
<mallctl>stats.metadata_thp</mallctl>
(<type>size_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Number of transparent huge pages (THP) used for
metadata. See <link
linkend="stats.metadata"><mallctl>stats.metadata</mallctl></link> and
<link linkend="opt.metadata_thp">opt.metadata_thp</link>) for
details.</para></listitem>
</varlistentry>
<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>
<listitem><para>Total number of bytes in active extents mapped by the
allocator. This is larger than <link
linkend="stats.active"><mallctl>stats.active</mallctl></link>. This
does not include inactive extents, 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.retained">
<term>
<mallctl>stats.retained</mallctl>
(<type>size_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Total number of bytes in virtual memory mappings that
were retained rather than being returned to the operating system via
e.g. <citerefentry><refentrytitle>munmap</refentrytitle>
<manvolnum>2</manvolnum></citerefentry> or similar. Retained virtual
memory is typically untouched, decommitted, or purged, so it has no
strongly associated physical memory (see <link
linkend="arena.i.extent_hooks">extent hooks</link> for details).
Retained memory is excluded from mapped memory statistics, e.g. <link
linkend="stats.mapped"><mallctl>stats.mapped</mallctl></link>.
</para></listitem>
</varlistentry>
<varlistentry id="stats.background_thread.num_threads">
<term>
<mallctl>stats.background_thread.num_threads</mallctl>
(<type>size_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para> Number of <link linkend="background_thread">background
threads</link> running currently.</para></listitem>
</varlistentry>
<varlistentry id="stats.background_thread.num_runs">
<term>
<mallctl>stats.background_thread.num_runs</mallctl>
(<type>uint64_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para> Total number of runs from all <link
linkend="background_thread">background threads</link>.</para></listitem>
</varlistentry>
<varlistentry id="stats.background_thread.run_interval">
<term>
<mallctl>stats.background_thread.run_interval</mallctl>
(<type>uint64_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para> Average run interval in nanoseconds of <link
linkend="background_thread">background threads</link>.</para></listitem>
</varlistentry>
<varlistentry id="stats.mutexes.ctl">
<term>
<mallctl>stats.mutexes.ctl.{counter};</mallctl>
(<type>counter specific type</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Statistics on <varname>ctl</varname> mutex (global
scope; mallctl related). <mallctl>{counter}</mallctl> is one of the
counters below:</para>
<varlistentry id="mutex_counters">
<listitem><para><varname>num_ops</varname> (<type>uint64_t</type>):
Total number of lock acquisition operations on this mutex.</para>
<para><varname>num_spin_acq</varname> (<type>uint64_t</type>): Number
of times the mutex was spin-acquired. When the mutex is currently
locked and cannot be acquired immediately, a short period of
spin-retry within jemalloc will be performed. Acquired through spin
generally means the contention was lightweight and not causing context
switches.</para>
<para><varname>num_wait</varname> (<type>uint64_t</type>): Number of
times the mutex was wait-acquired, which means the mutex contention
was not solved by spin-retry, and blocking operation was likely
involved in order to acquire the mutex. This event generally implies
higher cost / longer delay, and should be investigated if it happens
often.</para>
<para><varname>max_wait_time</varname> (<type>uint64_t</type>):
Maximum length of time in nanoseconds spent on a single wait-acquired
lock operation. Note that to avoid profiling overhead on the common
path, this does not consider spin-acquired cases.</para>
<para><varname>total_wait_time</varname> (<type>uint64_t</type>):
Cumulative time in nanoseconds spent on wait-acquired lock operations.
Similarly, spin-acquired cases are not considered.</para>
<para><varname>max_num_thds</varname> (<type>uint32_t</type>): Maximum
number of threads waiting on this mutex simultaneously. Similarly,
spin-acquired cases are not considered.</para>
<para><varname>num_owner_switch</varname> (<type>uint64_t</type>):
Number of times the current mutex owner is different from the previous
one. This event does not generally imply an issue; rather it is an
indicator of how often the protected data are accessed by different
threads.
</para>
</listitem>
</varlistentry>
</listitem>
</varlistentry>
<varlistentry id="stats.mutexes.background_thread">
<term>
<mallctl>stats.mutexes.background_thread.{counter}</mallctl>
(<type>counter specific type</type>) <literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Statistics on <varname>background_thread</varname> mutex
(global scope; <link
linkend="background_thread"><mallctl>background_thread</mallctl></link>
related). <mallctl>{counter}</mallctl> is one of the counters in <link
linkend="mutex_counters">mutex profiling
counters</link>.</para></listitem>
</varlistentry>
<varlistentry id="stats.mutexes.prof">
<term>
<mallctl>stats.mutexes.prof.{counter}</mallctl>
(<type>counter specific type</type>) <literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Statistics on <varname>prof</varname> mutex (global
scope; profiling related). <mallctl>{counter}</mallctl> is one of the
counters in <link linkend="mutex_counters">mutex profiling
counters</link>.</para></listitem>
</varlistentry>
<varlistentry id="stats.mutexes.reset">
<term>
<mallctl>stats.mutexes.reset</mallctl>
(<type>void</type>) <literal>--</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Reset all mutex profile statistics, including global
mutexes, arena mutexes and bin mutexes.</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.dirty_decay_ms">
<term>
<mallctl>stats.arenas.&lt;i&gt;.dirty_decay_ms</mallctl>
(<type>ssize_t</type>)
<literal>r-</literal>
</term>
<listitem><para>Approximate time in milliseconds 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.dirty_decay_ms"><mallctl>opt.dirty_decay_ms</mallctl></link>
for details.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.muzzy_decay_ms">
<term>
<mallctl>stats.arenas.&lt;i&gt;.muzzy_decay_ms</mallctl>
(<type>ssize_t</type>)
<literal>r-</literal>
</term>
<listitem><para>Approximate time in milliseconds from the creation of a
set of unused muzzy pages until an equivalent set of unused muzzy pages
is purged and/or reused. See <link
linkend="opt.muzzy_decay_ms"><mallctl>opt.muzzy_decay_ms</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.uptime">
<term>
<mallctl>stats.arenas.&lt;i&gt;.uptime</mallctl>
(<type>uint64_t</type>)
<literal>r-</literal>
</term>
<listitem><para>Time elapsed (in nanoseconds) since the arena was
created. If &lt;i&gt; equals <constant>0</constant> or
<constant>MALLCTL_ARENAS_ALL</constant>, this is the uptime since malloc
initialization.</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 extents.</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 extents that are
potentially dirty, and for which <function>madvise()</function> or
similar has not been called. See <link
linkend="opt.dirty_decay_ms"><mallctl>opt.dirty_decay_ms</mallctl></link>
for a description of dirty pages.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.pmuzzy">
<term>
<mallctl>stats.arenas.&lt;i&gt;.pmuzzy</mallctl>
(<type>size_t</type>)
<literal>r-</literal>
</term>
<listitem><para>Number of pages within unused extents that are muzzy.
See <link
linkend="opt.muzzy_decay_ms"><mallctl>opt.muzzy_decay_ms</mallctl></link>
for a description of muzzy pages.</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.retained">
<term>
<mallctl>stats.arenas.&lt;i&gt;.retained</mallctl>
(<type>size_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Number of retained bytes. See <link
linkend="stats.retained"><mallctl>stats.retained</mallctl></link> for
details.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.extent_avail">
<term>
<mallctl>stats.arenas.&lt;i&gt;.extent_avail</mallctl>
(<type>size_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Number of allocated (but unused) extent structs in this
arena.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.base">
<term>
<mallctl>stats.arenas.&lt;i&gt;.base</mallctl>
(<type>size_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>
Number of bytes dedicated to bootstrap-sensitive allocator metadata
structures.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.internal">
<term>
<mallctl>stats.arenas.&lt;i&gt;.internal</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.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.metadata_thp">
<term>
<mallctl>stats.arenas.&lt;i&gt;.metadata_thp</mallctl>
(<type>size_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Number of transparent huge pages (THP) used for
metadata. See <link linkend="opt.metadata_thp">opt.metadata_thp</link>
for details.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.resident">
<term>
<mallctl>stats.arenas.&lt;i&gt;.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 arena, 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.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.dirty_npurge">
<term>
<mallctl>stats.arenas.&lt;i&gt;.dirty_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.dirty_nmadvise">
<term>
<mallctl>stats.arenas.&lt;i&gt;.dirty_nmadvise</mallctl>
(<type>uint64_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Number of <function>madvise()</function> or similar
calls made to purge dirty pages.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.dirty_purged">
<term>
<mallctl>stats.arenas.&lt;i&gt;.dirty_purged</mallctl>
(<type>uint64_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Number of dirty pages purged.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.muzzy_npurge">
<term>
<mallctl>stats.arenas.&lt;i&gt;.muzzy_npurge</mallctl>
(<type>uint64_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Number of muzzy page purge sweeps performed.
</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.muzzy_nmadvise">
<term>
<mallctl>stats.arenas.&lt;i&gt;.muzzy_nmadvise</mallctl>
(<type>uint64_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Number of <function>madvise()</function> or similar
calls made to purge muzzy pages.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.muzzy_purged">
<term>
<mallctl>stats.arenas.&lt;i&gt;.muzzy_purged</mallctl>
(<type>uint64_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Number of muzzy 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 times a small allocation was
requested from the arena's bins, whether to fill the relevant tcache if
<link linkend="opt.tcache"><mallctl>opt.tcache</mallctl></link> is
enabled, or to directly satisfy an allocation request
otherwise.</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 times a small allocation was
returned to the arena's bins, whether to flush the relevant tcache if
<link linkend="opt.tcache"><mallctl>opt.tcache</mallctl></link> is
enabled, or to directly deallocate an allocation
otherwise.</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 allocation requests satisfied by
all bin size classes.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.small.nfills">
<term>
<mallctl>stats.arenas.&lt;i&gt;.small.nfills</mallctl>
(<type>uint64_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Cumulative number of tcache fills by all small size
classes.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.small.nflushes">
<term>
<mallctl>stats.arenas.&lt;i&gt;.small.nflushes</mallctl>
(<type>uint64_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Cumulative number of tcache flushes by all small size
classes.</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 times a large extent was allocated
from the arena, whether to fill the relevant tcache if <link
linkend="opt.tcache"><mallctl>opt.tcache</mallctl></link> is enabled and
the size class is within the range being cached, or to directly satisfy
an allocation request otherwise.</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 times a large extent was returned
to the arena, whether to flush the relevant tcache if <link
linkend="opt.tcache"><mallctl>opt.tcache</mallctl></link> is enabled and
the size class is within the range being cached, or to directly
deallocate an allocation otherwise.</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 allocation requests satisfied by
all large size classes.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.large.nfills">
<term>
<mallctl>stats.arenas.&lt;i&gt;.large.nfills</mallctl>
(<type>uint64_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Cumulative number of tcache fills by all large size
classes.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.large.nflushes">
<term>
<mallctl>stats.arenas.&lt;i&gt;.large.nflushes</mallctl>
(<type>uint64_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Cumulative number of tcache flushes by all large size
classes.</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 times a bin region of the
corresponding size class was allocated from the arena, whether to fill
the relevant tcache if <link
linkend="opt.tcache"><mallctl>opt.tcache</mallctl></link> is enabled, or
to directly satisfy an allocation request otherwise.</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 times a bin region of the
corresponding size class was returned to the arena, whether to flush the
relevant tcache if <link
linkend="opt.tcache"><mallctl>opt.tcache</mallctl></link> is enabled, or
to directly deallocate an allocation otherwise.</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 satisfied by
bin regions of the corresponding size class.</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>
</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>
</term>
<listitem><para>Cumulative number of tcache flushes.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.bins.j.nslabs">
<term>
<mallctl>stats.arenas.&lt;i&gt;.bins.&lt;j&gt;.nslabs</mallctl>
(<type>uint64_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Cumulative number of slabs created.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.bins.j.nreslabs">
<term>
<mallctl>stats.arenas.&lt;i&gt;.bins.&lt;j&gt;.nreslabs</mallctl>
(<type>uint64_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Cumulative number of times the current slab from which
to allocate changed.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.bins.j.curslabs">
<term>
<mallctl>stats.arenas.&lt;i&gt;.bins.&lt;j&gt;.curslabs</mallctl>
(<type>size_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Current number of slabs.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.bins.j.nonfull_slabs">
<term>
<mallctl>stats.arenas.&lt;i&gt;.bins.&lt;j&gt;.nonfull_slabs</mallctl>
(<type>size_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Current number of nonfull slabs.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.bins.mutex">
<term>
<mallctl>stats.arenas.&lt;i&gt;.bins.&lt;j&gt;.mutex.{counter}</mallctl>
(<type>counter specific type</type>) <literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Statistics on
<varname>arena.&lt;i&gt;.bins.&lt;j&gt;</varname> mutex (arena bin
scope; bin operation related). <mallctl>{counter}</mallctl> is one of
the counters in <link linkend="mutex_counters">mutex profiling
counters</link>.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.extents.n">
<term>
<mallctl>stats.arenas.&lt;i&gt;.extents.&lt;j&gt;.n{extent_type}</mallctl>
(<type>size_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para> Number of extents of the given type in this arena in
the bucket corresponding to page size index &lt;j&gt;. The extent type
is one of dirty, muzzy, or retained.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.extents.bytes">
<term>
<mallctl>stats.arenas.&lt;i&gt;.extents.&lt;j&gt;.{extent_type}_bytes</mallctl>
(<type>size_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para> Sum of the bytes managed by extents of the given type
in this arena in the bucket corresponding to page size index &lt;j&gt;.
The extent type is one of dirty, muzzy, or retained.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.lextents.j.nmalloc">
<term>
<mallctl>stats.arenas.&lt;i&gt;.lextents.&lt;j&gt;.nmalloc</mallctl>
(<type>uint64_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Cumulative number of times a large extent of the
corresponding size class was allocated from the arena, whether to fill
the relevant tcache if <link
linkend="opt.tcache"><mallctl>opt.tcache</mallctl></link> is enabled and
the size class is within the range being cached, or to directly satisfy
an allocation request otherwise.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.lextents.j.ndalloc">
<term>
<mallctl>stats.arenas.&lt;i&gt;.lextents.&lt;j&gt;.ndalloc</mallctl>
(<type>uint64_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Cumulative number of times a large extent of the
corresponding size class was returned to the arena, whether to flush the
relevant tcache if <link
linkend="opt.tcache"><mallctl>opt.tcache</mallctl></link> is enabled and
the size class is within the range being cached, or to directly
deallocate an allocation otherwise.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.lextents.j.nrequests">
<term>
<mallctl>stats.arenas.&lt;i&gt;.lextents.&lt;j&gt;.nrequests</mallctl>
(<type>uint64_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Cumulative number of allocation requests satisfied by
large extents of the corresponding size class.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.lextents.j.curlextents">
<term>
<mallctl>stats.arenas.&lt;i&gt;.lextents.&lt;j&gt;.curlextents</mallctl>
(<type>size_t</type>)
<literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Current number of large allocations for this size class.
</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.mutexes.large">
<term>
<mallctl>stats.arenas.&lt;i&gt;.mutexes.large.{counter}</mallctl>
(<type>counter specific type</type>) <literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Statistics on <varname>arena.&lt;i&gt;.large</varname>
mutex (arena scope; large allocation related).
<mallctl>{counter}</mallctl> is one of the counters in <link
linkend="mutex_counters">mutex profiling
counters</link>.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.mutexes.extent_avail">
<term>
<mallctl>stats.arenas.&lt;i&gt;.mutexes.extent_avail.{counter}</mallctl>
(<type>counter specific type</type>) <literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Statistics on <varname>arena.&lt;i&gt;.extent_avail
</varname> mutex (arena scope; extent avail related).
<mallctl>{counter}</mallctl> is one of the counters in <link
linkend="mutex_counters">mutex profiling
counters</link>.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.mutexes.extents_dirty">
<term>
<mallctl>stats.arenas.&lt;i&gt;.mutexes.extents_dirty.{counter}</mallctl>
(<type>counter specific type</type>) <literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Statistics on <varname>arena.&lt;i&gt;.extents_dirty
</varname> mutex (arena scope; dirty extents related).
<mallctl>{counter}</mallctl> is one of the counters in <link
linkend="mutex_counters">mutex profiling
counters</link>.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.mutexes.extents_muzzy">
<term>
<mallctl>stats.arenas.&lt;i&gt;.mutexes.extents_muzzy.{counter}</mallctl>
(<type>counter specific type</type>) <literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Statistics on <varname>arena.&lt;i&gt;.extents_muzzy
</varname> mutex (arena scope; muzzy extents related).
<mallctl>{counter}</mallctl> is one of the counters in <link
linkend="mutex_counters">mutex profiling
counters</link>.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.mutexes.extents_retained">
<term>
<mallctl>stats.arenas.&lt;i&gt;.mutexes.extents_retained.{counter}</mallctl>
(<type>counter specific type</type>) <literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Statistics on <varname>arena.&lt;i&gt;.extents_retained
</varname> mutex (arena scope; retained extents related).
<mallctl>{counter}</mallctl> is one of the counters in <link
linkend="mutex_counters">mutex profiling
counters</link>.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.mutexes.decay_dirty">
<term>
<mallctl>stats.arenas.&lt;i&gt;.mutexes.decay_dirty.{counter}</mallctl>
(<type>counter specific type</type>) <literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Statistics on <varname>arena.&lt;i&gt;.decay_dirty
</varname> mutex (arena scope; decay for dirty pages related).
<mallctl>{counter}</mallctl> is one of the counters in <link
linkend="mutex_counters">mutex profiling
counters</link>.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.mutexes.decay_muzzy">
<term>
<mallctl>stats.arenas.&lt;i&gt;.mutexes.decay_muzzy.{counter}</mallctl>
(<type>counter specific type</type>) <literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Statistics on <varname>arena.&lt;i&gt;.decay_muzzy
</varname> mutex (arena scope; decay for muzzy pages related).
<mallctl>{counter}</mallctl> is one of the counters in <link
linkend="mutex_counters">mutex profiling
counters</link>.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.mutexes.base">
<term>
<mallctl>stats.arenas.&lt;i&gt;.mutexes.base.{counter}</mallctl>
(<type>counter specific type</type>) <literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Statistics on <varname>arena.&lt;i&gt;.base</varname>
mutex (arena scope; base allocator related).
<mallctl>{counter}</mallctl> is one of the counters in <link
linkend="mutex_counters">mutex profiling
counters</link>.</para></listitem>
</varlistentry>
<varlistentry id="stats.arenas.i.mutexes.tcache_list">
<term>
<mallctl>stats.arenas.&lt;i&gt;.mutexes.tcache_list.{counter}</mallctl>
(<type>counter specific type</type>) <literal>r-</literal>
[<option>--enable-stats</option>]
</term>
<listitem><para>Statistics on
<varname>arena.&lt;i&gt;.tcache_list</varname> mutex (arena scope;
tcache to arena association related). This mutex is expected to be
accessed less often. <mallctl>{counter}</mallctl> is one of the
counters in <link linkend="mutex_counters">mutex profiling
counters</link>.</para></listitem>
</varlistentry>
</variablelist>
</refsect1>
<refsect1 id="heap_profile_format">
<title>HEAP PROFILE FORMAT</title>
<para>Although the heap profiling functionality was originally designed to
be compatible with the
<command>pprof</command> command that is developed as part of the <ulink
url="http://code.google.com/p/gperftools/">gperftools
package</ulink>, the addition of per thread heap profiling functionality
required a different heap profile format. The <command>jeprof</command>
command is derived from <command>pprof</command>, with enhancements to
support the heap profile format described here.</para>
<para>In the following hypothetical heap profile, <constant>[...]</constant>
indicates elision for the sake of compactness. <programlisting><![CDATA[
heap_v2/524288
t*: 28106: 56637512 [0: 0]
[...]
t3: 352: 16777344 [0: 0]
[...]
t99: 17754: 29341640 [0: 0]
[...]
@ 0x5f86da8 0x5f5a1dc [...] 0x29e4d4e 0xa200316 0xabb2988 [...]
t*: 13: 6688 [0: 0]
t3: 12: 6496 [0: ]
t99: 1: 192 [0: 0]
[...]
MAPPED_LIBRARIES:
[...]]]></programlisting> The following matches the above heap profile, but most
tokens are replaced with <constant>&lt;description&gt;</constant> to indicate
descriptions of the corresponding fields. <programlisting><![CDATA[
<heap_profile_format_version>/<mean_sample_interval>
<aggregate>: <curobjs>: <curbytes> [<cumobjs>: <cumbytes>]
[...]
<thread_3_aggregate>: <curobjs>: <curbytes>[<cumobjs>: <cumbytes>]
[...]
<thread_99_aggregate>: <curobjs>: <curbytes>[<cumobjs>: <cumbytes>]
[...]
@ <top_frame> <frame> [...] <frame> <frame> <frame> [...]
<backtrace_aggregate>: <curobjs>: <curbytes> [<cumobjs>: <cumbytes>]
<backtrace_thread_3>: <curobjs>: <curbytes> [<cumobjs>: <cumbytes>]
<backtrace_thread_99>: <curobjs>: <curbytes> [<cumobjs>: <cumbytes>]
[...]
MAPPED_LIBRARIES:
</proc/<pid>/maps>]]></programlisting></para>
</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 <quote>uninitialized</quote>
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.</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()</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()</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
<quote><computeroutput>&lt;jemalloc&gt;: </computeroutput></quote>.</para>
</refsect1>
<refsect1 id="return_values">
<title>RETURN VALUES</title>
<refsect2>
<title>Standard API</title>
<para>The <function>malloc()</function> and
<function>calloc()</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()</function> function
returns the value 0 if successful; otherwise it returns an error value.
The <function>posix_memalign()</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()</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()</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()</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()</function>
function always leaves the original buffer intact when an error occurs.
</para>
<para>The <function>free()</function> function returns no
value.</para>
</refsect2>
<refsect2>
<title>Non-standard API</title>
<para>The <function>mallocx()</function> and
<function>rallocx()</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()</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()</function> function returns the
real size of the allocation pointed to by <parameter>ptr</parameter>.
</para>
<para>The <function>nallocx()</function> returns the real size
that would result from a successful equivalent
<function>mallocx()</function> function call, or zero if
insufficient memory is available to perform the size computation. </para>
<para>The <function>mallctl()</function>,
<function>mallctlnametomib()</function>, and
<function>mallctlbymib()</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*()</function>
read/write processing.</para></listitem>
</varlistentry>
</variablelist>
</para>
<para>The <function>malloc_usable_size()</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 that only one arena should be automatically
created:
<programlisting language="C"><![CDATA[
malloc_conf = "narenas:1";]]></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()</function>,
<function>calloc()</function>,
<function>realloc()</function>, and
<function>free()</function> functions conform to ISO/IEC
9899:1990 (<quote>ISO C90</quote>).</para>
<para>The <function>posix_memalign()</function> function conforms
to IEEE Std 1003.1-2001 (<quote>POSIX.1</quote>).</para>
</refsect1>
</refentry>
<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" version="1.0">
<xsl:import href="@XSLROOT@/manpages/docbook.xsl"/>
<xsl:import href="@abs_srcroot@doc/stylesheet.xsl"/>
</xsl:stylesheet>
<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" version="1.0">
<xsl:param name="funcsynopsis.style">ansi</xsl:param>
<xsl:param name="function.parens" select="0"/>
<xsl:template match="function">
<xsl:call-template name="inline.monoseq"/>
</xsl:template>
<xsl:template match="mallctl">
<quote><xsl:call-template name="inline.monoseq"/></quote>
</xsl:template>
</xsl:stylesheet>
#ifndef JEMALLOC_INTERNAL_ARENA_EXTERNS_H
#define JEMALLOC_INTERNAL_ARENA_EXTERNS_H
#include "jemalloc/internal/bin.h"
#include "jemalloc/internal/extent_dss.h"
#include "jemalloc/internal/hook.h"
#include "jemalloc/internal/pages.h"
#include "jemalloc/internal/stats.h"
extern ssize_t opt_dirty_decay_ms;
extern ssize_t opt_muzzy_decay_ms;
extern percpu_arena_mode_t opt_percpu_arena;
extern const char *percpu_arena_mode_names[];
extern const uint64_t h_steps[SMOOTHSTEP_NSTEPS];
extern malloc_mutex_t arenas_lock;
extern size_t opt_oversize_threshold;
extern size_t oversize_threshold;
void arena_basic_stats_merge(tsdn_t *tsdn, arena_t *arena,
unsigned *nthreads, const char **dss, ssize_t *dirty_decay_ms,
ssize_t *muzzy_decay_ms, size_t *nactive, size_t *ndirty, size_t *nmuzzy);
void arena_stats_merge(tsdn_t *tsdn, arena_t *arena, unsigned *nthreads,
const char **dss, ssize_t *dirty_decay_ms, ssize_t *muzzy_decay_ms,
size_t *nactive, size_t *ndirty, size_t *nmuzzy, arena_stats_t *astats,
bin_stats_t *bstats, arena_stats_large_t *lstats,
arena_stats_extents_t *estats);
void arena_extents_dirty_dalloc(tsdn_t *tsdn, arena_t *arena,
extent_hooks_t **r_extent_hooks, extent_t *extent);
#ifdef JEMALLOC_JET
size_t arena_slab_regind(extent_t *slab, szind_t binind, const void *ptr);
#endif
extent_t *arena_extent_alloc_large(tsdn_t *tsdn, arena_t *arena,
size_t usize, size_t alignment, bool *zero);
void arena_extent_dalloc_large_prep(tsdn_t *tsdn, arena_t *arena,
extent_t *extent);
void arena_extent_ralloc_large_shrink(tsdn_t *tsdn, arena_t *arena,
extent_t *extent, size_t oldsize);
void arena_extent_ralloc_large_expand(tsdn_t *tsdn, arena_t *arena,
extent_t *extent, size_t oldsize);
ssize_t arena_dirty_decay_ms_get(arena_t *arena);
bool arena_dirty_decay_ms_set(tsdn_t *tsdn, arena_t *arena, ssize_t decay_ms);
ssize_t arena_muzzy_decay_ms_get(arena_t *arena);
bool arena_muzzy_decay_ms_set(tsdn_t *tsdn, arena_t *arena, ssize_t decay_ms);
void arena_decay(tsdn_t *tsdn, arena_t *arena, bool is_background_thread,
bool all);
void arena_reset(tsd_t *tsd, arena_t *arena);
void arena_destroy(tsd_t *tsd, arena_t *arena);
void arena_tcache_fill_small(tsdn_t *tsdn, arena_t *arena, tcache_t *tcache,
cache_bin_t *tbin, szind_t binind, uint64_t prof_accumbytes);
void arena_alloc_junk_small(void *ptr, const bin_info_t *bin_info,
bool zero);
typedef void (arena_dalloc_junk_small_t)(void *, const bin_info_t *);
extern arena_dalloc_junk_small_t *JET_MUTABLE arena_dalloc_junk_small;
void *arena_malloc_hard(tsdn_t *tsdn, arena_t *arena, size_t size,
szind_t ind, bool zero);
void *arena_palloc(tsdn_t *tsdn, arena_t *arena, size_t usize,
size_t alignment, bool zero, tcache_t *tcache);
void arena_prof_promote(tsdn_t *tsdn, void *ptr, size_t usize);
void arena_dalloc_promoted(tsdn_t *tsdn, void *ptr, tcache_t *tcache,
bool slow_path);
void arena_dalloc_bin_junked_locked(tsdn_t *tsdn, arena_t *arena, bin_t *bin,
szind_t binind, extent_t *extent, void *ptr);
void arena_dalloc_small(tsdn_t *tsdn, void *ptr);
bool arena_ralloc_no_move(tsdn_t *tsdn, void *ptr, size_t oldsize, size_t size,
size_t extra, bool zero, size_t *newsize);
void *arena_ralloc(tsdn_t *tsdn, arena_t *arena, void *ptr, size_t oldsize,
size_t size, size_t alignment, bool zero, tcache_t *tcache,
hook_ralloc_args_t *hook_args);
dss_prec_t arena_dss_prec_get(arena_t *arena);
bool arena_dss_prec_set(arena_t *arena, dss_prec_t dss_prec);
ssize_t arena_dirty_decay_ms_default_get(void);
bool arena_dirty_decay_ms_default_set(ssize_t decay_ms);
ssize_t arena_muzzy_decay_ms_default_get(void);
bool arena_muzzy_decay_ms_default_set(ssize_t decay_ms);
bool arena_retain_grow_limit_get_set(tsd_t *tsd, arena_t *arena,
size_t *old_limit, size_t *new_limit);
unsigned arena_nthreads_get(arena_t *arena, bool internal);
void arena_nthreads_inc(arena_t *arena, bool internal);
void arena_nthreads_dec(arena_t *arena, bool internal);
size_t arena_extent_sn_next(arena_t *arena);
arena_t *arena_new(tsdn_t *tsdn, unsigned ind, extent_hooks_t *extent_hooks);
bool arena_init_huge(void);
bool arena_is_huge(unsigned arena_ind);
arena_t *arena_choose_huge(tsd_t *tsd);
bin_t *arena_bin_choose_lock(tsdn_t *tsdn, arena_t *arena, szind_t binind,
unsigned *binshard);
void arena_boot(sc_data_t *sc_data);
void arena_prefork0(tsdn_t *tsdn, arena_t *arena);
void arena_prefork1(tsdn_t *tsdn, arena_t *arena);
void arena_prefork2(tsdn_t *tsdn, arena_t *arena);
void arena_prefork3(tsdn_t *tsdn, arena_t *arena);
void arena_prefork4(tsdn_t *tsdn, arena_t *arena);
void arena_prefork5(tsdn_t *tsdn, arena_t *arena);
void arena_prefork6(tsdn_t *tsdn, arena_t *arena);
void arena_prefork7(tsdn_t *tsdn, arena_t *arena);
void arena_postfork_parent(tsdn_t *tsdn, arena_t *arena);
void arena_postfork_child(tsdn_t *tsdn, arena_t *arena);
#endif /* JEMALLOC_INTERNAL_ARENA_EXTERNS_H */
#ifndef JEMALLOC_INTERNAL_ARENA_INLINES_A_H
#define JEMALLOC_INTERNAL_ARENA_INLINES_A_H
static inline unsigned
arena_ind_get(const arena_t *arena) {
return base_ind_get(arena->base);
}
static inline void
arena_internal_add(arena_t *arena, size_t size) {
atomic_fetch_add_zu(&arena->stats.internal, size, ATOMIC_RELAXED);
}
static inline void
arena_internal_sub(arena_t *arena, size_t size) {
atomic_fetch_sub_zu(&arena->stats.internal, size, ATOMIC_RELAXED);
}
static inline size_t
arena_internal_get(arena_t *arena) {
return atomic_load_zu(&arena->stats.internal, ATOMIC_RELAXED);
}
static inline bool
arena_prof_accum(tsdn_t *tsdn, arena_t *arena, uint64_t accumbytes) {
cassert(config_prof);
if (likely(prof_interval == 0 || !prof_active_get_unlocked())) {
return false;
}
return prof_accum_add(tsdn, &arena->prof_accum, accumbytes);
}
static inline void
percpu_arena_update(tsd_t *tsd, unsigned cpu) {
assert(have_percpu_arena);
arena_t *oldarena = tsd_arena_get(tsd);
assert(oldarena != NULL);
unsigned oldind = arena_ind_get(oldarena);
if (oldind != cpu) {
unsigned newind = cpu;
arena_t *newarena = arena_get(tsd_tsdn(tsd), newind, true);
assert(newarena != NULL);
/* Set new arena/tcache associations. */
arena_migrate(tsd, oldind, newind);
tcache_t *tcache = tcache_get(tsd);
if (tcache != NULL) {
tcache_arena_reassociate(tsd_tsdn(tsd), tcache,
newarena);
}
}
}
#endif /* JEMALLOC_INTERNAL_ARENA_INLINES_A_H */
#ifndef JEMALLOC_INTERNAL_ARENA_INLINES_B_H
#define JEMALLOC_INTERNAL_ARENA_INLINES_B_H
#include "jemalloc/internal/jemalloc_internal_types.h"
#include "jemalloc/internal/mutex.h"
#include "jemalloc/internal/rtree.h"
#include "jemalloc/internal/sc.h"
#include "jemalloc/internal/sz.h"
#include "jemalloc/internal/ticker.h"
JEMALLOC_ALWAYS_INLINE bool
arena_has_default_hooks(arena_t *arena) {
return (extent_hooks_get(arena) == &extent_hooks_default);
}
JEMALLOC_ALWAYS_INLINE arena_t *
arena_choose_maybe_huge(tsd_t *tsd, arena_t *arena, size_t size) {
if (arena != NULL) {
return arena;
}
/*
* For huge allocations, use the dedicated huge arena if both are true:
* 1) is using auto arena selection (i.e. arena == NULL), and 2) the
* thread is not assigned to a manual arena.
*/
if (unlikely(size >= oversize_threshold)) {
arena_t *tsd_arena = tsd_arena_get(tsd);
if (tsd_arena == NULL || arena_is_auto(tsd_arena)) {
return arena_choose_huge(tsd);
}
}
return arena_choose(tsd, NULL);
}
JEMALLOC_ALWAYS_INLINE prof_tctx_t *
arena_prof_tctx_get(tsdn_t *tsdn, const void *ptr, alloc_ctx_t *alloc_ctx) {
cassert(config_prof);
assert(ptr != NULL);
/* Static check. */
if (alloc_ctx == NULL) {
const extent_t *extent = iealloc(tsdn, ptr);
if (unlikely(!extent_slab_get(extent))) {
return large_prof_tctx_get(tsdn, extent);
}
} else {
if (unlikely(!alloc_ctx->slab)) {
return large_prof_tctx_get(tsdn, iealloc(tsdn, ptr));
}
}
return (prof_tctx_t *)(uintptr_t)1U;
}
JEMALLOC_ALWAYS_INLINE void
arena_prof_tctx_set(tsdn_t *tsdn, const void *ptr, size_t usize,
alloc_ctx_t *alloc_ctx, prof_tctx_t *tctx) {
cassert(config_prof);
assert(ptr != NULL);
/* Static check. */
if (alloc_ctx == NULL) {
extent_t *extent = iealloc(tsdn, ptr);
if (unlikely(!extent_slab_get(extent))) {
large_prof_tctx_set(tsdn, extent, tctx);
}
} else {
if (unlikely(!alloc_ctx->slab)) {
large_prof_tctx_set(tsdn, iealloc(tsdn, ptr), tctx);
}
}
}
static inline void
arena_prof_tctx_reset(tsdn_t *tsdn, const void *ptr, prof_tctx_t *tctx) {
cassert(config_prof);
assert(ptr != NULL);
extent_t *extent = iealloc(tsdn, ptr);
assert(!extent_slab_get(extent));
large_prof_tctx_reset(tsdn, extent);
}
JEMALLOC_ALWAYS_INLINE nstime_t
arena_prof_alloc_time_get(tsdn_t *tsdn, const void *ptr,
alloc_ctx_t *alloc_ctx) {
cassert(config_prof);
assert(ptr != NULL);
extent_t *extent = iealloc(tsdn, ptr);
/*
* Unlike arena_prof_prof_tctx_{get, set}, we only call this once we're
* sure we have a sampled allocation.
*/
assert(!extent_slab_get(extent));
return large_prof_alloc_time_get(extent);
}
JEMALLOC_ALWAYS_INLINE void
arena_prof_alloc_time_set(tsdn_t *tsdn, const void *ptr, alloc_ctx_t *alloc_ctx,
nstime_t t) {
cassert(config_prof);
assert(ptr != NULL);
extent_t *extent = iealloc(tsdn, ptr);
assert(!extent_slab_get(extent));
large_prof_alloc_time_set(extent, t);
}
JEMALLOC_ALWAYS_INLINE void
arena_decay_ticks(tsdn_t *tsdn, arena_t *arena, unsigned nticks) {
tsd_t *tsd;
ticker_t *decay_ticker;
if (unlikely(tsdn_null(tsdn))) {
return;
}
tsd = tsdn_tsd(tsdn);
decay_ticker = decay_ticker_get(tsd, arena_ind_get(arena));
if (unlikely(decay_ticker == NULL)) {
return;
}
if (unlikely(ticker_ticks(decay_ticker, nticks))) {
arena_decay(tsdn, arena, false, false);
}
}
JEMALLOC_ALWAYS_INLINE void
arena_decay_tick(tsdn_t *tsdn, arena_t *arena) {
malloc_mutex_assert_not_owner(tsdn, &arena->decay_dirty.mtx);
malloc_mutex_assert_not_owner(tsdn, &arena->decay_muzzy.mtx);
arena_decay_ticks(tsdn, arena, 1);
}
/* Purge a single extent to retained / unmapped directly. */
JEMALLOC_ALWAYS_INLINE void
arena_decay_extent(tsdn_t *tsdn,arena_t *arena, extent_hooks_t **r_extent_hooks,
extent_t *extent) {
size_t extent_size = extent_size_get(extent);
extent_dalloc_wrapper(tsdn, arena,
r_extent_hooks, extent);
if (config_stats) {
/* Update stats accordingly. */
arena_stats_lock(tsdn, &arena->stats);
arena_stats_add_u64(tsdn, &arena->stats,
&arena->decay_dirty.stats->nmadvise, 1);
arena_stats_add_u64(tsdn, &arena->stats,
&arena->decay_dirty.stats->purged, extent_size >> LG_PAGE);
arena_stats_sub_zu(tsdn, &arena->stats, &arena->stats.mapped,
extent_size);
arena_stats_unlock(tsdn, &arena->stats);
}
}
JEMALLOC_ALWAYS_INLINE void *
arena_malloc(tsdn_t *tsdn, arena_t *arena, size_t size, szind_t ind, bool zero,
tcache_t *tcache, bool slow_path) {
assert(!tsdn_null(tsdn) || tcache == NULL);
if (likely(tcache != NULL)) {
if (likely(size <= SC_SMALL_MAXCLASS)) {
return tcache_alloc_small(tsdn_tsd(tsdn), arena,
tcache, size, ind, zero, slow_path);
}
if (likely(size <= tcache_maxclass)) {
return tcache_alloc_large(tsdn_tsd(tsdn), arena,
tcache, size, ind, zero, slow_path);
}
/* (size > tcache_maxclass) case falls through. */
assert(size > tcache_maxclass);
}
return arena_malloc_hard(tsdn, arena, size, ind, zero);
}
JEMALLOC_ALWAYS_INLINE arena_t *
arena_aalloc(tsdn_t *tsdn, const void *ptr) {
return extent_arena_get(iealloc(tsdn, ptr));
}
JEMALLOC_ALWAYS_INLINE size_t
arena_salloc(tsdn_t *tsdn, const void *ptr) {
assert(ptr != NULL);
rtree_ctx_t rtree_ctx_fallback;
rtree_ctx_t *rtree_ctx = tsdn_rtree_ctx(tsdn, &rtree_ctx_fallback);
szind_t szind = rtree_szind_read(tsdn, &extents_rtree, rtree_ctx,
(uintptr_t)ptr, true);
assert(szind != SC_NSIZES);
return sz_index2size(szind);
}
JEMALLOC_ALWAYS_INLINE size_t
arena_vsalloc(tsdn_t *tsdn, const void *ptr) {
/*
* Return 0 if ptr is not within an extent managed by jemalloc. This
* function has two extra costs relative to isalloc():
* - The rtree calls cannot claim to be dependent lookups, which induces
* rtree lookup load dependencies.
* - The lookup may fail, so there is an extra branch to check for
* failure.
*/
rtree_ctx_t rtree_ctx_fallback;
rtree_ctx_t *rtree_ctx = tsdn_rtree_ctx(tsdn, &rtree_ctx_fallback);
extent_t *extent;
szind_t szind;
if (rtree_extent_szind_read(tsdn, &extents_rtree, rtree_ctx,
(uintptr_t)ptr, false, &extent, &szind)) {
return 0;
}
if (extent == NULL) {
return 0;
}
assert(extent_state_get(extent) == extent_state_active);
/* Only slab members should be looked up via interior pointers. */
assert(extent_addr_get(extent) == ptr || extent_slab_get(extent));
assert(szind != SC_NSIZES);
return sz_index2size(szind);
}
static inline void
arena_dalloc_large_no_tcache(tsdn_t *tsdn, void *ptr, szind_t szind) {
if (config_prof && unlikely(szind < SC_NBINS)) {
arena_dalloc_promoted(tsdn, ptr, NULL, true);
} else {
extent_t *extent = iealloc(tsdn, ptr);
large_dalloc(tsdn, extent);
}
}
static inline void
arena_dalloc_no_tcache(tsdn_t *tsdn, void *ptr) {
assert(ptr != NULL);
rtree_ctx_t rtree_ctx_fallback;
rtree_ctx_t *rtree_ctx = tsdn_rtree_ctx(tsdn, &rtree_ctx_fallback);
szind_t szind;
bool slab;
rtree_szind_slab_read(tsdn, &extents_rtree, rtree_ctx, (uintptr_t)ptr,
true, &szind, &slab);
if (config_debug) {
extent_t *extent = rtree_extent_read(tsdn, &extents_rtree,
rtree_ctx, (uintptr_t)ptr, true);
assert(szind == extent_szind_get(extent));
assert(szind < SC_NSIZES);
assert(slab == extent_slab_get(extent));
}
if (likely(slab)) {
/* Small allocation. */
arena_dalloc_small(tsdn, ptr);
} else {
arena_dalloc_large_no_tcache(tsdn, ptr, szind);
}
}
JEMALLOC_ALWAYS_INLINE void
arena_dalloc_large(tsdn_t *tsdn, void *ptr, tcache_t *tcache, szind_t szind,
bool slow_path) {
if (szind < nhbins) {
if (config_prof && unlikely(szind < SC_NBINS)) {
arena_dalloc_promoted(tsdn, ptr, tcache, slow_path);
} else {
tcache_dalloc_large(tsdn_tsd(tsdn), tcache, ptr, szind,
slow_path);
}
} else {
extent_t *extent = iealloc(tsdn, ptr);
large_dalloc(tsdn, extent);
}
}
JEMALLOC_ALWAYS_INLINE void
arena_dalloc(tsdn_t *tsdn, void *ptr, tcache_t *tcache,
alloc_ctx_t *alloc_ctx, bool slow_path) {
assert(!tsdn_null(tsdn) || tcache == NULL);
assert(ptr != NULL);
if (unlikely(tcache == NULL)) {
arena_dalloc_no_tcache(tsdn, ptr);
return;
}
szind_t szind;
bool slab;
rtree_ctx_t *rtree_ctx;
if (alloc_ctx != NULL) {
szind = alloc_ctx->szind;
slab = alloc_ctx->slab;
assert(szind != SC_NSIZES);
} else {
rtree_ctx = tsd_rtree_ctx(tsdn_tsd(tsdn));
rtree_szind_slab_read(tsdn, &extents_rtree, rtree_ctx,
(uintptr_t)ptr, true, &szind, &slab);
}
if (config_debug) {
rtree_ctx = tsd_rtree_ctx(tsdn_tsd(tsdn));
extent_t *extent = rtree_extent_read(tsdn, &extents_rtree,
rtree_ctx, (uintptr_t)ptr, true);
assert(szind == extent_szind_get(extent));
assert(szind < SC_NSIZES);
assert(slab == extent_slab_get(extent));
}
if (likely(slab)) {
/* Small allocation. */
tcache_dalloc_small(tsdn_tsd(tsdn), tcache, ptr, szind,
slow_path);
} else {
arena_dalloc_large(tsdn, ptr, tcache, szind, slow_path);
}
}
static inline void
arena_sdalloc_no_tcache(tsdn_t *tsdn, void *ptr, size_t size) {
assert(ptr != NULL);
assert(size <= SC_LARGE_MAXCLASS);
szind_t szind;
bool slab;
if (!config_prof || !opt_prof) {
/*
* There is no risk of being confused by a promoted sampled
* object, so base szind and slab on the given size.
*/
szind = sz_size2index(size);
slab = (szind < SC_NBINS);
}
if ((config_prof && opt_prof) || config_debug) {
rtree_ctx_t rtree_ctx_fallback;
rtree_ctx_t *rtree_ctx = tsdn_rtree_ctx(tsdn,
&rtree_ctx_fallback);
rtree_szind_slab_read(tsdn, &extents_rtree, rtree_ctx,
(uintptr_t)ptr, true, &szind, &slab);
assert(szind == sz_size2index(size));
assert((config_prof && opt_prof) || slab == (szind < SC_NBINS));
if (config_debug) {
extent_t *extent = rtree_extent_read(tsdn,
&extents_rtree, rtree_ctx, (uintptr_t)ptr, true);
assert(szind == extent_szind_get(extent));
assert(slab == extent_slab_get(extent));
}
}
if (likely(slab)) {
/* Small allocation. */
arena_dalloc_small(tsdn, ptr);
} else {
arena_dalloc_large_no_tcache(tsdn, ptr, szind);
}
}
JEMALLOC_ALWAYS_INLINE void
arena_sdalloc(tsdn_t *tsdn, void *ptr, size_t size, tcache_t *tcache,
alloc_ctx_t *alloc_ctx, bool slow_path) {
assert(!tsdn_null(tsdn) || tcache == NULL);
assert(ptr != NULL);
assert(size <= SC_LARGE_MAXCLASS);
if (unlikely(tcache == NULL)) {
arena_sdalloc_no_tcache(tsdn, ptr, size);
return;
}
szind_t szind;
bool slab;
alloc_ctx_t local_ctx;
if (config_prof && opt_prof) {
if (alloc_ctx == NULL) {
/* Uncommon case and should be a static check. */
rtree_ctx_t rtree_ctx_fallback;
rtree_ctx_t *rtree_ctx = tsdn_rtree_ctx(tsdn,
&rtree_ctx_fallback);
rtree_szind_slab_read(tsdn, &extents_rtree, rtree_ctx,
(uintptr_t)ptr, true, &local_ctx.szind,
&local_ctx.slab);
assert(local_ctx.szind == sz_size2index(size));
alloc_ctx = &local_ctx;
}
slab = alloc_ctx->slab;
szind = alloc_ctx->szind;
} else {
/*
* There is no risk of being confused by a promoted sampled
* object, so base szind and slab on the given size.
*/
szind = sz_size2index(size);
slab = (szind < SC_NBINS);
}
if (config_debug) {
rtree_ctx_t *rtree_ctx = tsd_rtree_ctx(tsdn_tsd(tsdn));
rtree_szind_slab_read(tsdn, &extents_rtree, rtree_ctx,
(uintptr_t)ptr, true, &szind, &slab);
extent_t *extent = rtree_extent_read(tsdn,
&extents_rtree, rtree_ctx, (uintptr_t)ptr, true);
assert(szind == extent_szind_get(extent));
assert(slab == extent_slab_get(extent));
}
if (likely(slab)) {
/* Small allocation. */
tcache_dalloc_small(tsdn_tsd(tsdn), tcache, ptr, szind,
slow_path);
} else {
arena_dalloc_large(tsdn, ptr, tcache, szind, slow_path);
}
}
#endif /* JEMALLOC_INTERNAL_ARENA_INLINES_B_H */
#ifndef JEMALLOC_INTERNAL_ARENA_STATS_H
#define JEMALLOC_INTERNAL_ARENA_STATS_H
#include "jemalloc/internal/atomic.h"
#include "jemalloc/internal/mutex.h"
#include "jemalloc/internal/mutex_prof.h"
#include "jemalloc/internal/sc.h"
JEMALLOC_DIAGNOSTIC_DISABLE_SPURIOUS
/*
* In those architectures that support 64-bit atomics, we use atomic updates for
* our 64-bit values. Otherwise, we use a plain uint64_t and synchronize
* externally.
*/
#ifdef JEMALLOC_ATOMIC_U64
typedef atomic_u64_t arena_stats_u64_t;
#else
/* Must hold the arena stats mutex while reading atomically. */
typedef uint64_t arena_stats_u64_t;
#endif
typedef struct arena_stats_large_s arena_stats_large_t;
struct arena_stats_large_s {
/*
* Total number of allocation/deallocation requests served directly by
* the arena.
*/
arena_stats_u64_t nmalloc;
arena_stats_u64_t ndalloc;
/*
* Number of allocation requests that correspond to this size class.
* This includes requests served by tcache, though tcache only
* periodically merges into this counter.
*/
arena_stats_u64_t nrequests; /* Partially derived. */
/*
* Number of tcache fills / flushes for large (similarly, periodically
* merged). Note that there is no large tcache batch-fill currently
* (i.e. only fill 1 at a time); however flush may be batched.
*/
arena_stats_u64_t nfills; /* Partially derived. */
arena_stats_u64_t nflushes; /* Partially derived. */
/* Current number of allocations of this size class. */
size_t curlextents; /* Derived. */
};
typedef struct arena_stats_decay_s arena_stats_decay_t;
struct arena_stats_decay_s {
/* Total number of purge sweeps. */
arena_stats_u64_t npurge;
/* Total number of madvise calls made. */
arena_stats_u64_t nmadvise;
/* Total number of pages purged. */
arena_stats_u64_t purged;
};
typedef struct arena_stats_extents_s arena_stats_extents_t;
struct arena_stats_extents_s {
/*
* Stats for a given index in the range [0, SC_NPSIZES] in an extents_t.
* We track both bytes and # of extents: two extents in the same bucket
* may have different sizes if adjacent size classes differ by more than
* a page, so bytes cannot always be derived from # of extents.
*/
atomic_zu_t ndirty;
atomic_zu_t dirty_bytes;
atomic_zu_t nmuzzy;
atomic_zu_t muzzy_bytes;
atomic_zu_t nretained;
atomic_zu_t retained_bytes;
};
/*
* Arena stats. Note that fields marked "derived" are not directly maintained
* within the arena code; rather their values are derived during stats merge
* requests.
*/
typedef struct arena_stats_s arena_stats_t;
struct arena_stats_s {
#ifndef JEMALLOC_ATOMIC_U64
malloc_mutex_t mtx;
#endif
/* Number of bytes currently mapped, excluding retained memory. */
atomic_zu_t mapped; /* Partially derived. */
/*
* Number of unused virtual memory bytes currently retained. Retained
* bytes are technically mapped (though always decommitted or purged),
* but they are excluded from the mapped statistic (above).
*/
atomic_zu_t retained; /* Derived. */
/* Number of extent_t structs allocated by base, but not being used. */
atomic_zu_t extent_avail;
arena_stats_decay_t decay_dirty;
arena_stats_decay_t decay_muzzy;
atomic_zu_t base; /* Derived. */
atomic_zu_t internal;
atomic_zu_t resident; /* Derived. */
atomic_zu_t metadata_thp;
atomic_zu_t allocated_large; /* Derived. */
arena_stats_u64_t nmalloc_large; /* Derived. */
arena_stats_u64_t ndalloc_large; /* Derived. */
arena_stats_u64_t nfills_large; /* Derived. */
arena_stats_u64_t nflushes_large; /* Derived. */
arena_stats_u64_t nrequests_large; /* Derived. */
/* VM space had to be leaked (undocumented). Normally 0. */
atomic_zu_t abandoned_vm;
/* Number of bytes cached in tcache associated with this arena. */
atomic_zu_t tcache_bytes; /* Derived. */
mutex_prof_data_t mutex_prof_data[mutex_prof_num_arena_mutexes];
/* One element for each large size class. */
arena_stats_large_t lstats[SC_NSIZES - SC_NBINS];
/* Arena uptime. */
nstime_t uptime;
};
static inline bool
arena_stats_init(tsdn_t *tsdn, arena_stats_t *arena_stats) {
if (config_debug) {
for (size_t i = 0; i < sizeof(arena_stats_t); i++) {
assert(((char *)arena_stats)[i] == 0);
}
}
#ifndef JEMALLOC_ATOMIC_U64
if (malloc_mutex_init(&arena_stats->mtx, "arena_stats",
WITNESS_RANK_ARENA_STATS, malloc_mutex_rank_exclusive)) {
return true;
}
#endif
/* Memory is zeroed, so there is no need to clear stats. */
return false;
}
static inline void
arena_stats_lock(tsdn_t *tsdn, arena_stats_t *arena_stats) {
#ifndef JEMALLOC_ATOMIC_U64
malloc_mutex_lock(tsdn, &arena_stats->mtx);
#endif
}
static inline void
arena_stats_unlock(tsdn_t *tsdn, arena_stats_t *arena_stats) {
#ifndef JEMALLOC_ATOMIC_U64
malloc_mutex_unlock(tsdn, &arena_stats->mtx);
#endif
}
static inline uint64_t
arena_stats_read_u64(tsdn_t *tsdn, arena_stats_t *arena_stats,
arena_stats_u64_t *p) {
#ifdef JEMALLOC_ATOMIC_U64
return atomic_load_u64(p, ATOMIC_RELAXED);
#else
malloc_mutex_assert_owner(tsdn, &arena_stats->mtx);
return *p;
#endif
}
static inline void
arena_stats_add_u64(tsdn_t *tsdn, arena_stats_t *arena_stats,
arena_stats_u64_t *p, uint64_t x) {
#ifdef JEMALLOC_ATOMIC_U64
atomic_fetch_add_u64(p, x, ATOMIC_RELAXED);
#else
malloc_mutex_assert_owner(tsdn, &arena_stats->mtx);
*p += x;
#endif
}
static inline void
arena_stats_sub_u64(tsdn_t *tsdn, arena_stats_t *arena_stats,
arena_stats_u64_t *p, uint64_t x) {
#ifdef JEMALLOC_ATOMIC_U64
uint64_t r = atomic_fetch_sub_u64(p, x, ATOMIC_RELAXED);
assert(r - x <= r);
#else
malloc_mutex_assert_owner(tsdn, &arena_stats->mtx);
*p -= x;
assert(*p + x >= *p);
#endif
}
/*
* Non-atomically sets *dst += src. *dst needs external synchronization.
* This lets us avoid the cost of a fetch_add when its unnecessary (note that
* the types here are atomic).
*/
static inline void
arena_stats_accum_u64(arena_stats_u64_t *dst, uint64_t src) {
#ifdef JEMALLOC_ATOMIC_U64
uint64_t cur_dst = atomic_load_u64(dst, ATOMIC_RELAXED);
atomic_store_u64(dst, src + cur_dst, ATOMIC_RELAXED);
#else
*dst += src;
#endif
}
static inline size_t
arena_stats_read_zu(tsdn_t *tsdn, arena_stats_t *arena_stats,
atomic_zu_t *p) {
#ifdef JEMALLOC_ATOMIC_U64
return atomic_load_zu(p, ATOMIC_RELAXED);
#else
malloc_mutex_assert_owner(tsdn, &arena_stats->mtx);
return atomic_load_zu(p, ATOMIC_RELAXED);
#endif
}
static inline void
arena_stats_add_zu(tsdn_t *tsdn, arena_stats_t *arena_stats,
atomic_zu_t *p, size_t x) {
#ifdef JEMALLOC_ATOMIC_U64
atomic_fetch_add_zu(p, x, ATOMIC_RELAXED);
#else
malloc_mutex_assert_owner(tsdn, &arena_stats->mtx);
size_t cur = atomic_load_zu(p, ATOMIC_RELAXED);
atomic_store_zu(p, cur + x, ATOMIC_RELAXED);
#endif
}
static inline void
arena_stats_sub_zu(tsdn_t *tsdn, arena_stats_t *arena_stats,
atomic_zu_t *p, size_t x) {
#ifdef JEMALLOC_ATOMIC_U64
size_t r = atomic_fetch_sub_zu(p, x, ATOMIC_RELAXED);
assert(r - x <= r);
#else
malloc_mutex_assert_owner(tsdn, &arena_stats->mtx);
size_t cur = atomic_load_zu(p, ATOMIC_RELAXED);
atomic_store_zu(p, cur - x, ATOMIC_RELAXED);
#endif
}
/* Like the _u64 variant, needs an externally synchronized *dst. */
static inline void
arena_stats_accum_zu(atomic_zu_t *dst, size_t src) {
size_t cur_dst = atomic_load_zu(dst, ATOMIC_RELAXED);
atomic_store_zu(dst, src + cur_dst, ATOMIC_RELAXED);
}
static inline void
arena_stats_large_flush_nrequests_add(tsdn_t *tsdn, arena_stats_t *arena_stats,
szind_t szind, uint64_t nrequests) {
arena_stats_lock(tsdn, arena_stats);
arena_stats_large_t *lstats = &arena_stats->lstats[szind - SC_NBINS];
arena_stats_add_u64(tsdn, arena_stats, &lstats->nrequests, nrequests);
arena_stats_add_u64(tsdn, arena_stats, &lstats->nflushes, 1);
arena_stats_unlock(tsdn, arena_stats);
}
static inline void
arena_stats_mapped_add(tsdn_t *tsdn, arena_stats_t *arena_stats, size_t size) {
arena_stats_lock(tsdn, arena_stats);
arena_stats_add_zu(tsdn, arena_stats, &arena_stats->mapped, size);
arena_stats_unlock(tsdn, arena_stats);
}
#endif /* JEMALLOC_INTERNAL_ARENA_STATS_H */
#ifndef JEMALLOC_INTERNAL_ARENA_STRUCTS_A_H
#define JEMALLOC_INTERNAL_ARENA_STRUCTS_A_H
#include "jemalloc/internal/bitmap.h"
struct arena_slab_data_s {
/* Per region allocated/deallocated bitmap. */
bitmap_t bitmap[BITMAP_GROUPS_MAX];
};
#endif /* JEMALLOC_INTERNAL_ARENA_STRUCTS_A_H */
#ifndef JEMALLOC_INTERNAL_ARENA_STRUCTS_B_H
#define JEMALLOC_INTERNAL_ARENA_STRUCTS_B_H
#include "jemalloc/internal/arena_stats.h"
#include "jemalloc/internal/atomic.h"
#include "jemalloc/internal/bin.h"
#include "jemalloc/internal/bitmap.h"
#include "jemalloc/internal/extent_dss.h"
#include "jemalloc/internal/jemalloc_internal_types.h"
#include "jemalloc/internal/mutex.h"
#include "jemalloc/internal/nstime.h"
#include "jemalloc/internal/ql.h"
#include "jemalloc/internal/sc.h"
#include "jemalloc/internal/smoothstep.h"
#include "jemalloc/internal/ticker.h"
struct arena_decay_s {
/* Synchronizes all non-atomic fields. */
malloc_mutex_t mtx;
/*
* True if a thread is currently purging the extents associated with
* this decay structure.
*/
bool purging;
/*
* Approximate time in milliseconds from the creation of a set of unused
* dirty pages until an equivalent set of unused dirty pages is purged
* and/or reused.
*/
atomic_zd_t time_ms;
/* time / SMOOTHSTEP_NSTEPS. */
nstime_t interval;
/*
* Time at which the current decay interval logically started. We do
* not actually advance to a new epoch until sometime after it starts
* because of scheduling and computation delays, and it is even possible
* to completely skip epochs. In all cases, during epoch advancement we
* merge all relevant activity into the most recently recorded epoch.
*/
nstime_t epoch;
/* Deadline randomness generator. */
uint64_t jitter_state;
/*
* Deadline for current epoch. This is the sum of interval and per
* epoch jitter which is a uniform random variable in [0..interval).
* Epochs always advance by precise multiples of interval, but we
* randomize the deadline to reduce the likelihood of arenas purging in
* lockstep.
*/
nstime_t deadline;
/*
* Number of unpurged pages at beginning of current epoch. During epoch
* advancement we use the delta between arena->decay_*.nunpurged and
* extents_npages_get(&arena->extents_*) to determine how many dirty
* pages, if any, were generated.
*/
size_t nunpurged;
/*
* Trailing log of how many unused dirty pages were generated during
* each of the past SMOOTHSTEP_NSTEPS decay epochs, where the last
* element is the most recent epoch. Corresponding epoch times are
* relative to epoch.
*/
size_t backlog[SMOOTHSTEP_NSTEPS];
/*
* Pointer to associated stats. These stats are embedded directly in
* the arena's stats due to how stats structures are shared between the
* arena and ctl code.
*
* Synchronization: Same as associated arena's stats field. */
arena_stats_decay_t *stats;
/* Peak number of pages in associated extents. Used for debug only. */
uint64_t ceil_npages;
};
struct arena_s {
/*
* Number of threads currently assigned to this arena. Each thread has
* two distinct assignments, one for application-serving allocation, and
* the other for internal metadata allocation. Internal metadata must
* not be allocated from arenas explicitly created via the arenas.create
* mallctl, because the arena.<i>.reset mallctl indiscriminately
* discards all allocations for the affected arena.
*
* 0: Application allocation.
* 1: Internal metadata allocation.
*
* Synchronization: atomic.
*/
atomic_u_t nthreads[2];
/* Next bin shard for binding new threads. Synchronization: atomic. */
atomic_u_t binshard_next;
/*
* When percpu_arena is enabled, to amortize the cost of reading /
* updating the current CPU id, track the most recent thread accessing
* this arena, and only read CPU if there is a mismatch.
*/
tsdn_t *last_thd;
/* Synchronization: internal. */
arena_stats_t stats;
/*
* Lists of tcaches and cache_bin_array_descriptors for extant threads
* associated with this arena. Stats from these are merged
* incrementally, and at exit if opt_stats_print is enabled.
*
* Synchronization: tcache_ql_mtx.
*/
ql_head(tcache_t) tcache_ql;
ql_head(cache_bin_array_descriptor_t) cache_bin_array_descriptor_ql;
malloc_mutex_t tcache_ql_mtx;
/* Synchronization: internal. */
prof_accum_t prof_accum;
/*
* PRNG state for cache index randomization of large allocation base
* pointers.
*
* Synchronization: atomic.
*/
atomic_zu_t offset_state;
/*
* Extent serial number generator state.
*
* Synchronization: atomic.
*/
atomic_zu_t extent_sn_next;
/*
* Represents a dss_prec_t, but atomically.
*
* Synchronization: atomic.
*/
atomic_u_t dss_prec;
/*
* Number of pages in active extents.
*
* Synchronization: atomic.
*/
atomic_zu_t nactive;
/*
* Extant large allocations.
*
* Synchronization: large_mtx.
*/
extent_list_t large;
/* Synchronizes all large allocation/update/deallocation. */
malloc_mutex_t large_mtx;
/*
* Collections of extents that were previously allocated. These are
* used when allocating extents, in an attempt to re-use address space.
*
* Synchronization: internal.
*/
extents_t extents_dirty;
extents_t extents_muzzy;
extents_t extents_retained;
/*
* Decay-based purging state, responsible for scheduling extent state
* transitions.
*
* Synchronization: internal.
*/
arena_decay_t decay_dirty; /* dirty --> muzzy */
arena_decay_t decay_muzzy; /* muzzy --> retained */
/*
* Next extent size class in a growing series to use when satisfying a
* request via the extent hooks (only if opt_retain). This limits the
* number of disjoint virtual memory ranges so that extent merging can
* be effective even if multiple arenas' extent allocation requests are
* highly interleaved.
*
* retain_grow_limit is the max allowed size ind to expand (unless the
* required size is greater). Default is no limit, and controlled
* through mallctl only.
*
* Synchronization: extent_grow_mtx
*/
pszind_t extent_grow_next;
pszind_t retain_grow_limit;
malloc_mutex_t extent_grow_mtx;
/*
* Available extent structures that were allocated via
* base_alloc_extent().
*
* Synchronization: extent_avail_mtx.
*/
extent_tree_t extent_avail;
atomic_zu_t extent_avail_cnt;
malloc_mutex_t extent_avail_mtx;
/*
* bins is used to store heaps of free regions.
*
* Synchronization: internal.
*/
bins_t bins[SC_NBINS];
/*
* Base allocator, from which arena metadata are allocated.
*
* Synchronization: internal.
*/
base_t *base;
/* Used to determine uptime. Read-only after initialization. */
nstime_t create_time;
};
/* Used in conjunction with tsd for fast arena-related context lookup. */
struct arena_tdata_s {
ticker_t decay_ticker;
};
/* Used to pass rtree lookup context down the path. */
struct alloc_ctx_s {
szind_t szind;
bool slab;
};
#endif /* JEMALLOC_INTERNAL_ARENA_STRUCTS_B_H */
#ifndef JEMALLOC_INTERNAL_ARENA_TYPES_H
#define JEMALLOC_INTERNAL_ARENA_TYPES_H
#include "jemalloc/internal/sc.h"
/* Maximum number of regions in one slab. */
#define LG_SLAB_MAXREGS (LG_PAGE - SC_LG_TINY_MIN)
#define SLAB_MAXREGS (1U << LG_SLAB_MAXREGS)
/* Default decay times in milliseconds. */
#define DIRTY_DECAY_MS_DEFAULT ZD(10 * 1000)
#define MUZZY_DECAY_MS_DEFAULT (0)
/* Number of event ticks between time checks. */
#define DECAY_NTICKS_PER_UPDATE 1000
typedef struct arena_slab_data_s arena_slab_data_t;
typedef struct arena_decay_s arena_decay_t;
typedef struct arena_s arena_t;
typedef struct arena_tdata_s arena_tdata_t;
typedef struct alloc_ctx_s alloc_ctx_t;
typedef enum {
percpu_arena_mode_names_base = 0, /* Used for options processing. */
/*
* *_uninit are used only during bootstrapping, and must correspond
* to initialized variant plus percpu_arena_mode_enabled_base.
*/
percpu_arena_uninit = 0,
per_phycpu_arena_uninit = 1,
/* All non-disabled modes must come after percpu_arena_disabled. */
percpu_arena_disabled = 2,
percpu_arena_mode_names_limit = 3, /* Used for options processing. */
percpu_arena_mode_enabled_base = 3,
percpu_arena = 3,
per_phycpu_arena = 4 /* Hyper threads share arena. */
} percpu_arena_mode_t;
#define PERCPU_ARENA_ENABLED(m) ((m) >= percpu_arena_mode_enabled_base)
#define PERCPU_ARENA_DEFAULT percpu_arena_disabled
/*
* When allocation_size >= oversize_threshold, use the dedicated huge arena
* (unless have explicitly spicified arena index). 0 disables the feature.
*/
#define OVERSIZE_THRESHOLD_DEFAULT (8 << 20)
#endif /* JEMALLOC_INTERNAL_ARENA_TYPES_H */
#include "jemalloc/internal/malloc_io.h"
#include "jemalloc/internal/util.h"
/*
* Define a custom assert() in order to reduce the chances of deadlock during
* assertion failure.
*/
#ifndef assert
#define assert(e) do { \
if (unlikely(config_debug && !(e))) { \
malloc_printf( \
"<jemalloc>: %s:%d: Failed assertion: \"%s\"\n", \
__FILE__, __LINE__, #e); \
abort(); \
} \
} while (0)
#endif
#ifndef not_reached
#define not_reached() do { \
if (config_debug) { \
malloc_printf( \
"<jemalloc>: %s:%d: Unreachable code reached\n", \
__FILE__, __LINE__); \
abort(); \
} \
unreachable(); \
} while (0)
#endif
#ifndef not_implemented
#define not_implemented() do { \
if (config_debug) { \
malloc_printf("<jemalloc>: %s:%d: Not implemented\n", \
__FILE__, __LINE__); \
abort(); \
} \
} while (0)
#endif
#ifndef assert_not_implemented
#define assert_not_implemented(e) do { \
if (unlikely(config_debug && !(e))) { \
not_implemented(); \
} \
} while (0)
#endif
/* Use to assert a particular configuration, e.g., cassert(config_debug). */
#ifndef cassert
#define cassert(c) do { \
if (unlikely(!(c))) { \
not_reached(); \
} \
} while (0)
#endif
#ifndef JEMALLOC_INTERNAL_ATOMIC_H
#define JEMALLOC_INTERNAL_ATOMIC_H
#define ATOMIC_INLINE JEMALLOC_ALWAYS_INLINE
#define JEMALLOC_U8_ATOMICS
#if defined(JEMALLOC_GCC_ATOMIC_ATOMICS)
# include "jemalloc/internal/atomic_gcc_atomic.h"
# if !defined(JEMALLOC_GCC_U8_ATOMIC_ATOMICS)
# undef JEMALLOC_U8_ATOMICS
# endif
#elif defined(JEMALLOC_GCC_SYNC_ATOMICS)
# include "jemalloc/internal/atomic_gcc_sync.h"
# if !defined(JEMALLOC_GCC_U8_SYNC_ATOMICS)
# undef JEMALLOC_U8_ATOMICS
# endif
#elif defined(_MSC_VER)
# include "jemalloc/internal/atomic_msvc.h"
#elif defined(JEMALLOC_C11_ATOMICS)
# include "jemalloc/internal/atomic_c11.h"
#else
# error "Don't have atomics implemented on this platform."
#endif
/*
* This header gives more or less a backport of C11 atomics. The user can write
* JEMALLOC_GENERATE_ATOMICS(type, short_type, lg_sizeof_type); to generate
* counterparts of the C11 atomic functions for type, as so:
* JEMALLOC_GENERATE_ATOMICS(int *, pi, 3);
* and then write things like:
* int *some_ptr;
* atomic_pi_t atomic_ptr_to_int;
* atomic_store_pi(&atomic_ptr_to_int, some_ptr, ATOMIC_RELAXED);
* int *prev_value = atomic_exchange_pi(&ptr_to_int, NULL, ATOMIC_ACQ_REL);
* assert(some_ptr == prev_value);
* and expect things to work in the obvious way.
*
* Also included (with naming differences to avoid conflicts with the standard
* library):
* atomic_fence(atomic_memory_order_t) (mimics C11's atomic_thread_fence).
* ATOMIC_INIT (mimics C11's ATOMIC_VAR_INIT).
*/
/*
* Pure convenience, so that we don't have to type "atomic_memory_order_"
* quite so often.
*/
#define ATOMIC_RELAXED atomic_memory_order_relaxed
#define ATOMIC_ACQUIRE atomic_memory_order_acquire
#define ATOMIC_RELEASE atomic_memory_order_release
#define ATOMIC_ACQ_REL atomic_memory_order_acq_rel
#define ATOMIC_SEQ_CST atomic_memory_order_seq_cst
/*
* Not all platforms have 64-bit atomics. If we do, this #define exposes that
* fact.
*/
#if (LG_SIZEOF_PTR == 3 || LG_SIZEOF_INT == 3)
# define JEMALLOC_ATOMIC_U64
#endif
JEMALLOC_GENERATE_ATOMICS(void *, p, LG_SIZEOF_PTR)
/*
* There's no actual guarantee that sizeof(bool) == 1, but it's true on the only
* platform that actually needs to know the size, MSVC.
*/
JEMALLOC_GENERATE_ATOMICS(bool, b, 0)
JEMALLOC_GENERATE_INT_ATOMICS(unsigned, u, LG_SIZEOF_INT)
JEMALLOC_GENERATE_INT_ATOMICS(size_t, zu, LG_SIZEOF_PTR)
JEMALLOC_GENERATE_INT_ATOMICS(ssize_t, zd, LG_SIZEOF_PTR)
JEMALLOC_GENERATE_INT_ATOMICS(uint8_t, u8, 0)
JEMALLOC_GENERATE_INT_ATOMICS(uint32_t, u32, 2)
#ifdef JEMALLOC_ATOMIC_U64
JEMALLOC_GENERATE_INT_ATOMICS(uint64_t, u64, 3)
#endif
#undef ATOMIC_INLINE
#endif /* JEMALLOC_INTERNAL_ATOMIC_H */
#ifndef JEMALLOC_INTERNAL_ATOMIC_C11_H
#define JEMALLOC_INTERNAL_ATOMIC_C11_H
#include <stdatomic.h>
#define ATOMIC_INIT(...) ATOMIC_VAR_INIT(__VA_ARGS__)
#define atomic_memory_order_t memory_order
#define atomic_memory_order_relaxed memory_order_relaxed
#define atomic_memory_order_acquire memory_order_acquire
#define atomic_memory_order_release memory_order_release
#define atomic_memory_order_acq_rel memory_order_acq_rel
#define atomic_memory_order_seq_cst memory_order_seq_cst
#define atomic_fence atomic_thread_fence
#define JEMALLOC_GENERATE_ATOMICS(type, short_type, \
/* unused */ lg_size) \
typedef _Atomic(type) atomic_##short_type##_t; \
\
ATOMIC_INLINE type \
atomic_load_##short_type(const atomic_##short_type##_t *a, \
atomic_memory_order_t mo) { \
/* \
* A strict interpretation of the C standard prevents \
* atomic_load from taking a const argument, but it's \
* convenient for our purposes. This cast is a workaround. \
*/ \
atomic_##short_type##_t* a_nonconst = \
(atomic_##short_type##_t*)a; \
return atomic_load_explicit(a_nonconst, mo); \
} \
\
ATOMIC_INLINE void \
atomic_store_##short_type(atomic_##short_type##_t *a, \
type val, atomic_memory_order_t mo) { \
atomic_store_explicit(a, val, mo); \
} \
\
ATOMIC_INLINE type \
atomic_exchange_##short_type(atomic_##short_type##_t *a, type val, \
atomic_memory_order_t mo) { \
return atomic_exchange_explicit(a, val, mo); \
} \
\
ATOMIC_INLINE bool \
atomic_compare_exchange_weak_##short_type(atomic_##short_type##_t *a, \
type *expected, type desired, atomic_memory_order_t success_mo, \
atomic_memory_order_t failure_mo) { \
return atomic_compare_exchange_weak_explicit(a, expected, \
desired, success_mo, failure_mo); \
} \
\
ATOMIC_INLINE bool \
atomic_compare_exchange_strong_##short_type(atomic_##short_type##_t *a, \
type *expected, type desired, atomic_memory_order_t success_mo, \
atomic_memory_order_t failure_mo) { \
return atomic_compare_exchange_strong_explicit(a, expected, \
desired, success_mo, failure_mo); \
}
/*
* Integral types have some special operations available that non-integral ones
* lack.
*/
#define JEMALLOC_GENERATE_INT_ATOMICS(type, short_type, \
/* unused */ lg_size) \
JEMALLOC_GENERATE_ATOMICS(type, short_type, /* unused */ lg_size) \
\
ATOMIC_INLINE type \
atomic_fetch_add_##short_type(atomic_##short_type##_t *a, \
type val, atomic_memory_order_t mo) { \
return atomic_fetch_add_explicit(a, val, mo); \
} \
\
ATOMIC_INLINE type \
atomic_fetch_sub_##short_type(atomic_##short_type##_t *a, \
type val, atomic_memory_order_t mo) { \
return atomic_fetch_sub_explicit(a, val, mo); \
} \
ATOMIC_INLINE type \
atomic_fetch_and_##short_type(atomic_##short_type##_t *a, \
type val, atomic_memory_order_t mo) { \
return atomic_fetch_and_explicit(a, val, mo); \
} \
ATOMIC_INLINE type \
atomic_fetch_or_##short_type(atomic_##short_type##_t *a, \
type val, atomic_memory_order_t mo) { \
return atomic_fetch_or_explicit(a, val, mo); \
} \
ATOMIC_INLINE type \
atomic_fetch_xor_##short_type(atomic_##short_type##_t *a, \
type val, atomic_memory_order_t mo) { \
return atomic_fetch_xor_explicit(a, val, mo); \
}
#endif /* JEMALLOC_INTERNAL_ATOMIC_C11_H */
#ifndef JEMALLOC_INTERNAL_ATOMIC_GCC_ATOMIC_H
#define JEMALLOC_INTERNAL_ATOMIC_GCC_ATOMIC_H
#include "jemalloc/internal/assert.h"
#define ATOMIC_INIT(...) {__VA_ARGS__}
typedef enum {
atomic_memory_order_relaxed,
atomic_memory_order_acquire,
atomic_memory_order_release,
atomic_memory_order_acq_rel,
atomic_memory_order_seq_cst
} atomic_memory_order_t;
ATOMIC_INLINE int
atomic_enum_to_builtin(atomic_memory_order_t mo) {
switch (mo) {
case atomic_memory_order_relaxed:
return __ATOMIC_RELAXED;
case atomic_memory_order_acquire:
return __ATOMIC_ACQUIRE;
case atomic_memory_order_release:
return __ATOMIC_RELEASE;
case atomic_memory_order_acq_rel:
return __ATOMIC_ACQ_REL;
case atomic_memory_order_seq_cst:
return __ATOMIC_SEQ_CST;
}
/* Can't happen; the switch is exhaustive. */
not_reached();
}
ATOMIC_INLINE void
atomic_fence(atomic_memory_order_t mo) {
__atomic_thread_fence(atomic_enum_to_builtin(mo));
}
#define JEMALLOC_GENERATE_ATOMICS(type, short_type, \
/* unused */ lg_size) \
typedef struct { \
type repr; \
} atomic_##short_type##_t; \
\
ATOMIC_INLINE type \
atomic_load_##short_type(const atomic_##short_type##_t *a, \
atomic_memory_order_t mo) { \
type result; \
__atomic_load(&a->repr, &result, atomic_enum_to_builtin(mo)); \
return result; \
} \
\
ATOMIC_INLINE void \
atomic_store_##short_type(atomic_##short_type##_t *a, type val, \
atomic_memory_order_t mo) { \
__atomic_store(&a->repr, &val, atomic_enum_to_builtin(mo)); \
} \
\
ATOMIC_INLINE type \
atomic_exchange_##short_type(atomic_##short_type##_t *a, type val, \
atomic_memory_order_t mo) { \
type result; \
__atomic_exchange(&a->repr, &val, &result, \
atomic_enum_to_builtin(mo)); \
return result; \
} \
\
ATOMIC_INLINE bool \
atomic_compare_exchange_weak_##short_type(atomic_##short_type##_t *a, \
UNUSED type *expected, type desired, \
atomic_memory_order_t success_mo, \
atomic_memory_order_t failure_mo) { \
return __atomic_compare_exchange(&a->repr, expected, &desired, \
true, atomic_enum_to_builtin(success_mo), \
atomic_enum_to_builtin(failure_mo)); \
} \
\
ATOMIC_INLINE bool \
atomic_compare_exchange_strong_##short_type(atomic_##short_type##_t *a, \
UNUSED type *expected, type desired, \
atomic_memory_order_t success_mo, \
atomic_memory_order_t failure_mo) { \
return __atomic_compare_exchange(&a->repr, expected, &desired, \
false, \
atomic_enum_to_builtin(success_mo), \
atomic_enum_to_builtin(failure_mo)); \
}
#define JEMALLOC_GENERATE_INT_ATOMICS(type, short_type, \
/* unused */ lg_size) \
JEMALLOC_GENERATE_ATOMICS(type, short_type, /* unused */ lg_size) \
\
ATOMIC_INLINE type \
atomic_fetch_add_##short_type(atomic_##short_type##_t *a, type val, \
atomic_memory_order_t mo) { \
return __atomic_fetch_add(&a->repr, val, \
atomic_enum_to_builtin(mo)); \
} \
\
ATOMIC_INLINE type \
atomic_fetch_sub_##short_type(atomic_##short_type##_t *a, type val, \
atomic_memory_order_t mo) { \
return __atomic_fetch_sub(&a->repr, val, \
atomic_enum_to_builtin(mo)); \
} \
\
ATOMIC_INLINE type \
atomic_fetch_and_##short_type(atomic_##short_type##_t *a, type val, \
atomic_memory_order_t mo) { \
return __atomic_fetch_and(&a->repr, val, \
atomic_enum_to_builtin(mo)); \
} \
\
ATOMIC_INLINE type \
atomic_fetch_or_##short_type(atomic_##short_type##_t *a, type val, \
atomic_memory_order_t mo) { \
return __atomic_fetch_or(&a->repr, val, \
atomic_enum_to_builtin(mo)); \
} \
\
ATOMIC_INLINE type \
atomic_fetch_xor_##short_type(atomic_##short_type##_t *a, type val, \
atomic_memory_order_t mo) { \
return __atomic_fetch_xor(&a->repr, val, \
atomic_enum_to_builtin(mo)); \
}
#endif /* JEMALLOC_INTERNAL_ATOMIC_GCC_ATOMIC_H */
#ifndef JEMALLOC_INTERNAL_ATOMIC_GCC_SYNC_H
#define JEMALLOC_INTERNAL_ATOMIC_GCC_SYNC_H
#define ATOMIC_INIT(...) {__VA_ARGS__}
typedef enum {
atomic_memory_order_relaxed,
atomic_memory_order_acquire,
atomic_memory_order_release,
atomic_memory_order_acq_rel,
atomic_memory_order_seq_cst
} atomic_memory_order_t;
ATOMIC_INLINE void
atomic_fence(atomic_memory_order_t mo) {
/* Easy cases first: no barrier, and full barrier. */
if (mo == atomic_memory_order_relaxed) {
asm volatile("" ::: "memory");
return;
}
if (mo == atomic_memory_order_seq_cst) {
asm volatile("" ::: "memory");
__sync_synchronize();
asm volatile("" ::: "memory");
return;
}
asm volatile("" ::: "memory");
# if defined(__i386__) || defined(__x86_64__)
/* This is implicit on x86. */
# elif defined(__ppc64__)
asm volatile("lwsync");
# elif defined(__ppc__)
asm volatile("sync");
# elif defined(__sparc__) && defined(__arch64__)
if (mo == atomic_memory_order_acquire) {
asm volatile("membar #LoadLoad | #LoadStore");
} else if (mo == atomic_memory_order_release) {
asm volatile("membar #LoadStore | #StoreStore");
} else {
asm volatile("membar #LoadLoad | #LoadStore | #StoreStore");
}
# else
__sync_synchronize();
# endif
asm volatile("" ::: "memory");
}
/*
* A correct implementation of seq_cst loads and stores on weakly ordered
* architectures could do either of the following:
* 1. store() is weak-fence -> store -> strong fence, load() is load ->
* strong-fence.
* 2. store() is strong-fence -> store, load() is strong-fence -> load ->
* weak-fence.
* The tricky thing is, load() and store() above can be the load or store
* portions of a gcc __sync builtin, so we have to follow GCC's lead, which
* means going with strategy 2.
* On strongly ordered architectures, the natural strategy is to stick a strong
* fence after seq_cst stores, and have naked loads. So we want the strong
* fences in different places on different architectures.
* atomic_pre_sc_load_fence and atomic_post_sc_store_fence allow us to
* accomplish this.
*/
ATOMIC_INLINE void
atomic_pre_sc_load_fence() {
# if defined(__i386__) || defined(__x86_64__) || \
(defined(__sparc__) && defined(__arch64__))
atomic_fence(atomic_memory_order_relaxed);
# else
atomic_fence(atomic_memory_order_seq_cst);
# endif
}
ATOMIC_INLINE void
atomic_post_sc_store_fence() {
# if defined(__i386__) || defined(__x86_64__) || \
(defined(__sparc__) && defined(__arch64__))
atomic_fence(atomic_memory_order_seq_cst);
# else
atomic_fence(atomic_memory_order_relaxed);
# endif
}
#define JEMALLOC_GENERATE_ATOMICS(type, short_type, \
/* unused */ lg_size) \
typedef struct { \
type volatile repr; \
} atomic_##short_type##_t; \
\
ATOMIC_INLINE type \
atomic_load_##short_type(const atomic_##short_type##_t *a, \
atomic_memory_order_t mo) { \
if (mo == atomic_memory_order_seq_cst) { \
atomic_pre_sc_load_fence(); \
} \
type result = a->repr; \
if (mo != atomic_memory_order_relaxed) { \
atomic_fence(atomic_memory_order_acquire); \
} \
return result; \
} \
\
ATOMIC_INLINE void \
atomic_store_##short_type(atomic_##short_type##_t *a, \
type val, atomic_memory_order_t mo) { \
if (mo != atomic_memory_order_relaxed) { \
atomic_fence(atomic_memory_order_release); \
} \
a->repr = val; \
if (mo == atomic_memory_order_seq_cst) { \
atomic_post_sc_store_fence(); \
} \
} \
\
ATOMIC_INLINE type \
atomic_exchange_##short_type(atomic_##short_type##_t *a, type val, \
atomic_memory_order_t mo) { \
/* \
* Because of FreeBSD, we care about gcc 4.2, which doesn't have\
* an atomic exchange builtin. We fake it with a CAS loop. \
*/ \
while (true) { \
type old = a->repr; \
if (__sync_bool_compare_and_swap(&a->repr, old, val)) { \
return old; \
} \
} \
} \
\
ATOMIC_INLINE bool \
atomic_compare_exchange_weak_##short_type(atomic_##short_type##_t *a, \
type *expected, type desired, \
atomic_memory_order_t success_mo, \
atomic_memory_order_t failure_mo) { \
type prev = __sync_val_compare_and_swap(&a->repr, *expected, \
desired); \
if (prev == *expected) { \
return true; \
} else { \
*expected = prev; \
return false; \
} \
} \
ATOMIC_INLINE bool \
atomic_compare_exchange_strong_##short_type(atomic_##short_type##_t *a, \
type *expected, type desired, \
atomic_memory_order_t success_mo, \
atomic_memory_order_t failure_mo) { \
type prev = __sync_val_compare_and_swap(&a->repr, *expected, \
desired); \
if (prev == *expected) { \
return true; \
} else { \
*expected = prev; \
return false; \
} \
}
#define JEMALLOC_GENERATE_INT_ATOMICS(type, short_type, \
/* unused */ lg_size) \
JEMALLOC_GENERATE_ATOMICS(type, short_type, /* unused */ lg_size) \
\
ATOMIC_INLINE type \
atomic_fetch_add_##short_type(atomic_##short_type##_t *a, type val, \
atomic_memory_order_t mo) { \
return __sync_fetch_and_add(&a->repr, val); \
} \
\
ATOMIC_INLINE type \
atomic_fetch_sub_##short_type(atomic_##short_type##_t *a, type val, \
atomic_memory_order_t mo) { \
return __sync_fetch_and_sub(&a->repr, val); \
} \
\
ATOMIC_INLINE type \
atomic_fetch_and_##short_type(atomic_##short_type##_t *a, type val, \
atomic_memory_order_t mo) { \
return __sync_fetch_and_and(&a->repr, val); \
} \
\
ATOMIC_INLINE type \
atomic_fetch_or_##short_type(atomic_##short_type##_t *a, type val, \
atomic_memory_order_t mo) { \
return __sync_fetch_and_or(&a->repr, val); \
} \
\
ATOMIC_INLINE type \
atomic_fetch_xor_##short_type(atomic_##short_type##_t *a, type val, \
atomic_memory_order_t mo) { \
return __sync_fetch_and_xor(&a->repr, val); \
}
#endif /* JEMALLOC_INTERNAL_ATOMIC_GCC_SYNC_H */
#ifndef JEMALLOC_INTERNAL_ATOMIC_MSVC_H
#define JEMALLOC_INTERNAL_ATOMIC_MSVC_H
#define ATOMIC_INIT(...) {__VA_ARGS__}
typedef enum {
atomic_memory_order_relaxed,
atomic_memory_order_acquire,
atomic_memory_order_release,
atomic_memory_order_acq_rel,
atomic_memory_order_seq_cst
} atomic_memory_order_t;
typedef char atomic_repr_0_t;
typedef short atomic_repr_1_t;
typedef long atomic_repr_2_t;
typedef __int64 atomic_repr_3_t;
ATOMIC_INLINE void
atomic_fence(atomic_memory_order_t mo) {
_ReadWriteBarrier();
# if defined(_M_ARM) || defined(_M_ARM64)
/* ARM needs a barrier for everything but relaxed. */
if (mo != atomic_memory_order_relaxed) {
MemoryBarrier();
}
# elif defined(_M_IX86) || defined (_M_X64)
/* x86 needs a barrier only for seq_cst. */
if (mo == atomic_memory_order_seq_cst) {
MemoryBarrier();
}
# else
# error "Don't know how to create atomics for this platform for MSVC."
# endif
_ReadWriteBarrier();
}
#define ATOMIC_INTERLOCKED_REPR(lg_size) atomic_repr_ ## lg_size ## _t
#define ATOMIC_CONCAT(a, b) ATOMIC_RAW_CONCAT(a, b)
#define ATOMIC_RAW_CONCAT(a, b) a ## b
#define ATOMIC_INTERLOCKED_NAME(base_name, lg_size) ATOMIC_CONCAT( \
base_name, ATOMIC_INTERLOCKED_SUFFIX(lg_size))
#define ATOMIC_INTERLOCKED_SUFFIX(lg_size) \
ATOMIC_CONCAT(ATOMIC_INTERLOCKED_SUFFIX_, lg_size)
#define ATOMIC_INTERLOCKED_SUFFIX_0 8
#define ATOMIC_INTERLOCKED_SUFFIX_1 16
#define ATOMIC_INTERLOCKED_SUFFIX_2
#define ATOMIC_INTERLOCKED_SUFFIX_3 64
#define JEMALLOC_GENERATE_ATOMICS(type, short_type, lg_size) \
typedef struct { \
ATOMIC_INTERLOCKED_REPR(lg_size) repr; \
} atomic_##short_type##_t; \
\
ATOMIC_INLINE type \
atomic_load_##short_type(const atomic_##short_type##_t *a, \
atomic_memory_order_t mo) { \
ATOMIC_INTERLOCKED_REPR(lg_size) ret = a->repr; \
if (mo != atomic_memory_order_relaxed) { \
atomic_fence(atomic_memory_order_acquire); \
} \
return (type) ret; \
} \
\
ATOMIC_INLINE void \
atomic_store_##short_type(atomic_##short_type##_t *a, \
type val, atomic_memory_order_t mo) { \
if (mo != atomic_memory_order_relaxed) { \
atomic_fence(atomic_memory_order_release); \
} \
a->repr = (ATOMIC_INTERLOCKED_REPR(lg_size)) val; \
if (mo == atomic_memory_order_seq_cst) { \
atomic_fence(atomic_memory_order_seq_cst); \
} \
} \
\
ATOMIC_INLINE type \
atomic_exchange_##short_type(atomic_##short_type##_t *a, type val, \
atomic_memory_order_t mo) { \
return (type)ATOMIC_INTERLOCKED_NAME(_InterlockedExchange, \
lg_size)(&a->repr, (ATOMIC_INTERLOCKED_REPR(lg_size))val); \
} \
\
ATOMIC_INLINE bool \
atomic_compare_exchange_weak_##short_type(atomic_##short_type##_t *a, \
type *expected, type desired, atomic_memory_order_t success_mo, \
atomic_memory_order_t failure_mo) { \
ATOMIC_INTERLOCKED_REPR(lg_size) e = \
(ATOMIC_INTERLOCKED_REPR(lg_size))*expected; \
ATOMIC_INTERLOCKED_REPR(lg_size) d = \
(ATOMIC_INTERLOCKED_REPR(lg_size))desired; \
ATOMIC_INTERLOCKED_REPR(lg_size) old = \
ATOMIC_INTERLOCKED_NAME(_InterlockedCompareExchange, \
lg_size)(&a->repr, d, e); \
if (old == e) { \
return true; \
} else { \
*expected = (type)old; \
return false; \
} \
} \
\
ATOMIC_INLINE bool \
atomic_compare_exchange_strong_##short_type(atomic_##short_type##_t *a, \
type *expected, type desired, atomic_memory_order_t success_mo, \
atomic_memory_order_t failure_mo) { \
/* We implement the weak version with strong semantics. */ \
return atomic_compare_exchange_weak_##short_type(a, expected, \
desired, success_mo, failure_mo); \
}
#define JEMALLOC_GENERATE_INT_ATOMICS(type, short_type, lg_size) \
JEMALLOC_GENERATE_ATOMICS(type, short_type, lg_size) \
\
ATOMIC_INLINE type \
atomic_fetch_add_##short_type(atomic_##short_type##_t *a, \
type val, atomic_memory_order_t mo) { \
return (type)ATOMIC_INTERLOCKED_NAME(_InterlockedExchangeAdd, \
lg_size)(&a->repr, (ATOMIC_INTERLOCKED_REPR(lg_size))val); \
} \
\
ATOMIC_INLINE type \
atomic_fetch_sub_##short_type(atomic_##short_type##_t *a, \
type val, atomic_memory_order_t mo) { \
/* \
* MSVC warns on negation of unsigned operands, but for us it \
* gives exactly the right semantics (MAX_TYPE + 1 - operand). \
*/ \
__pragma(warning(push)) \
__pragma(warning(disable: 4146)) \
return atomic_fetch_add_##short_type(a, -val, mo); \
__pragma(warning(pop)) \
} \
ATOMIC_INLINE type \
atomic_fetch_and_##short_type(atomic_##short_type##_t *a, \
type val, atomic_memory_order_t mo) { \
return (type)ATOMIC_INTERLOCKED_NAME(_InterlockedAnd, lg_size)( \
&a->repr, (ATOMIC_INTERLOCKED_REPR(lg_size))val); \
} \
ATOMIC_INLINE type \
atomic_fetch_or_##short_type(atomic_##short_type##_t *a, \
type val, atomic_memory_order_t mo) { \
return (type)ATOMIC_INTERLOCKED_NAME(_InterlockedOr, lg_size)( \
&a->repr, (ATOMIC_INTERLOCKED_REPR(lg_size))val); \
} \
ATOMIC_INLINE type \
atomic_fetch_xor_##short_type(atomic_##short_type##_t *a, \
type val, atomic_memory_order_t mo) { \
return (type)ATOMIC_INTERLOCKED_NAME(_InterlockedXor, lg_size)( \
&a->repr, (ATOMIC_INTERLOCKED_REPR(lg_size))val); \
}
#endif /* JEMALLOC_INTERNAL_ATOMIC_MSVC_H */
#ifndef JEMALLOC_INTERNAL_BACKGROUND_THREAD_EXTERNS_H
#define JEMALLOC_INTERNAL_BACKGROUND_THREAD_EXTERNS_H
extern bool opt_background_thread;
extern size_t opt_max_background_threads;
extern malloc_mutex_t background_thread_lock;
extern atomic_b_t background_thread_enabled_state;
extern size_t n_background_threads;
extern size_t max_background_threads;
extern background_thread_info_t *background_thread_info;
bool background_thread_create(tsd_t *tsd, unsigned arena_ind);
bool background_threads_enable(tsd_t *tsd);
bool background_threads_disable(tsd_t *tsd);
void background_thread_interval_check(tsdn_t *tsdn, arena_t *arena,
arena_decay_t *decay, size_t npages_new);
void background_thread_prefork0(tsdn_t *tsdn);
void background_thread_prefork1(tsdn_t *tsdn);
void background_thread_postfork_parent(tsdn_t *tsdn);
void background_thread_postfork_child(tsdn_t *tsdn);
bool background_thread_stats_read(tsdn_t *tsdn,
background_thread_stats_t *stats);
void background_thread_ctl_init(tsdn_t *tsdn);
#ifdef JEMALLOC_PTHREAD_CREATE_WRAPPER
extern int pthread_create_wrapper(pthread_t *__restrict, const pthread_attr_t *,
void *(*)(void *), void *__restrict);
#endif
bool background_thread_boot0(void);
bool background_thread_boot1(tsdn_t *tsdn);
#endif /* JEMALLOC_INTERNAL_BACKGROUND_THREAD_EXTERNS_H */
#ifndef JEMALLOC_INTERNAL_BACKGROUND_THREAD_INLINES_H
#define JEMALLOC_INTERNAL_BACKGROUND_THREAD_INLINES_H
JEMALLOC_ALWAYS_INLINE bool
background_thread_enabled(void) {
return atomic_load_b(&background_thread_enabled_state, ATOMIC_RELAXED);
}
JEMALLOC_ALWAYS_INLINE void
background_thread_enabled_set(tsdn_t *tsdn, bool state) {
malloc_mutex_assert_owner(tsdn, &background_thread_lock);
atomic_store_b(&background_thread_enabled_state, state, ATOMIC_RELAXED);
}
JEMALLOC_ALWAYS_INLINE background_thread_info_t *
arena_background_thread_info_get(arena_t *arena) {
unsigned arena_ind = arena_ind_get(arena);
return &background_thread_info[arena_ind % max_background_threads];
}
JEMALLOC_ALWAYS_INLINE background_thread_info_t *
background_thread_info_get(size_t ind) {
return &background_thread_info[ind % max_background_threads];
}
JEMALLOC_ALWAYS_INLINE uint64_t
background_thread_wakeup_time_get(background_thread_info_t *info) {
uint64_t next_wakeup = nstime_ns(&info->next_wakeup);
assert(atomic_load_b(&info->indefinite_sleep, ATOMIC_ACQUIRE) ==
(next_wakeup == BACKGROUND_THREAD_INDEFINITE_SLEEP));
return next_wakeup;
}
JEMALLOC_ALWAYS_INLINE void
background_thread_wakeup_time_set(tsdn_t *tsdn, background_thread_info_t *info,
uint64_t wakeup_time) {
malloc_mutex_assert_owner(tsdn, &info->mtx);
atomic_store_b(&info->indefinite_sleep,
wakeup_time == BACKGROUND_THREAD_INDEFINITE_SLEEP, ATOMIC_RELEASE);
nstime_init(&info->next_wakeup, wakeup_time);
}
JEMALLOC_ALWAYS_INLINE bool
background_thread_indefinite_sleep(background_thread_info_t *info) {
return atomic_load_b(&info->indefinite_sleep, ATOMIC_ACQUIRE);
}
JEMALLOC_ALWAYS_INLINE void
arena_background_thread_inactivity_check(tsdn_t *tsdn, arena_t *arena,
bool is_background_thread) {
if (!background_thread_enabled() || is_background_thread) {
return;
}
background_thread_info_t *info =
arena_background_thread_info_get(arena);
if (background_thread_indefinite_sleep(info)) {
background_thread_interval_check(tsdn, arena,
&arena->decay_dirty, 0);
}
}
#endif /* JEMALLOC_INTERNAL_BACKGROUND_THREAD_INLINES_H */
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment