Commit 08e1c8e8 authored by antirez's avatar antirez
Browse files

Jemalloc upgraded to version 5.0.1.

parent 8f4e2075
version: '{build}'
environment:
matrix:
- MSYSTEM: MINGW64
CPU: x86_64
MSVC: amd64
- MSYSTEM: MINGW32
CPU: i686
MSVC: x86
- MSYSTEM: MINGW64
CPU: x86_64
- MSYSTEM: MINGW32
CPU: i686
- MSYSTEM: MINGW64
CPU: x86_64
MSVC: amd64
CONFIG_FLAGS: --enable-debug
- MSYSTEM: MINGW32
CPU: i686
MSVC: x86
CONFIG_FLAGS: --enable-debug
- MSYSTEM: MINGW64
CPU: x86_64
CONFIG_FLAGS: --enable-debug
- MSYSTEM: MINGW32
CPU: i686
CONFIG_FLAGS: --enable-debug
install:
- set PATH=c:\msys64\%MSYSTEM%\bin;c:\msys64\usr\bin;%PATH%
- if defined MSVC call "c:\Program Files (x86)\Microsoft Visual Studio 14.0\VC\vcvarsall.bat" %MSVC%
- if defined MSVC pacman --noconfirm -Rsc mingw-w64-%CPU%-gcc gcc
- pacman --noconfirm -Suy mingw-w64-%CPU%-make
build_script:
- bash -c "autoconf"
- bash -c "./configure $CONFIG_FLAGS"
- mingw32-make
- file lib/jemalloc.dll
- mingw32-make tests
- mingw32-make -k check
/*.gcov.*
/bin/jemalloc-config
/bin/jemalloc.sh
/bin/jeprof
......@@ -21,10 +19,14 @@
/Makefile
/include/jemalloc/internal/jemalloc_internal.h
/include/jemalloc/internal/jemalloc_preamble.h
/include/jemalloc/internal/jemalloc_internal_defs.h
/include/jemalloc/internal/private_namespace.gen.h
/include/jemalloc/internal/private_namespace.h
/include/jemalloc/internal/private_unnamespace.h
/include/jemalloc/internal/private_namespace_jet.gen.h
/include/jemalloc/internal/private_namespace_jet.h
/include/jemalloc/internal/private_symbols.awk
/include/jemalloc/internal/private_symbols_jet.awk
/include/jemalloc/internal/public_namespace.h
/include/jemalloc/internal/public_symbols.txt
/include/jemalloc/internal/public_unnamespace.h
......@@ -40,8 +42,9 @@
/include/jemalloc/jemalloc_typedefs.h
/src/*.[od]
/src/*.gcda
/src/*.gcno
/src/*.sym
/run_tests.out/
/test/test.sh
test/include/test/jemalloc_test.h
......@@ -50,26 +53,41 @@ test/include/test/jemalloc_test_defs.h
/test/integration/[A-Za-z]*
!/test/integration/[A-Za-z]*.*
/test/integration/*.[od]
/test/integration/*.gcda
/test/integration/*.gcno
/test/integration/*.out
/test/integration/cpp/[A-Za-z]*
!/test/integration/cpp/[A-Za-z]*.*
/test/integration/cpp/*.[od]
/test/integration/cpp/*.out
/test/src/*.[od]
/test/src/*.gcda
/test/src/*.gcno
/test/stress/[A-Za-z]*
!/test/stress/[A-Za-z]*.*
/test/stress/*.[od]
/test/stress/*.gcda
/test/stress/*.gcno
/test/stress/*.out
/test/unit/[A-Za-z]*
!/test/unit/[A-Za-z]*.*
/test/unit/*.[od]
/test/unit/*.gcda
/test/unit/*.gcno
/test/unit/*.out
/VERSION
*.pdb
*.sdf
*.opendb
*.VC.db
*.opensdf
*.cachefile
*.suo
*.user
*.sln.docstates
*.tmp
.vs/
/msvc/Win32/
/msvc/x64/
/msvc/projects/*/*/Debug*/
/msvc/projects/*/*/Release*/
/msvc/projects/*/*/Win32/
/msvc/projects/*/*/x64/
language: generic
dist: precise
matrix:
include:
- os: linux
env: CC=gcc CXX=g++ COMPILER_FLAGS="" CONFIGURE_FLAGS="" EXTRA_CFLAGS="-Werror -Wno-array-bounds"
- os: osx
env: CC=gcc CXX=g++ COMPILER_FLAGS="" CONFIGURE_FLAGS="" EXTRA_CFLAGS="-Werror -Wno-array-bounds"
- os: linux
env: CC=clang CXX=clang++ COMPILER_FLAGS="" CONFIGURE_FLAGS="" EXTRA_CFLAGS="-Werror -Wno-array-bounds"
- os: linux
env: CC=gcc CXX=g++ COMPILER_FLAGS="-m32" CONFIGURE_FLAGS="" EXTRA_CFLAGS="-Werror -Wno-array-bounds"
addons:
apt:
packages:
- gcc-multilib
- os: linux
env: CC=gcc CXX=g++ COMPILER_FLAGS="" CONFIGURE_FLAGS="--enable-debug" EXTRA_CFLAGS="-Werror -Wno-array-bounds"
- os: linux
env: CC=gcc CXX=g++ COMPILER_FLAGS="" CONFIGURE_FLAGS="--enable-prof" EXTRA_CFLAGS="-Werror -Wno-array-bounds"
- os: linux
env: CC=gcc CXX=g++ COMPILER_FLAGS="" CONFIGURE_FLAGS="--disable-stats" EXTRA_CFLAGS="-Werror -Wno-array-bounds"
- os: linux
env: CC=gcc CXX=g++ COMPILER_FLAGS="" CONFIGURE_FLAGS="--with-malloc-conf=tcache:false" EXTRA_CFLAGS="-Werror -Wno-array-bounds"
- os: linux
env: CC=gcc CXX=g++ COMPILER_FLAGS="" CONFIGURE_FLAGS="--with-malloc-conf=dss:primary" EXTRA_CFLAGS="-Werror -Wno-array-bounds"
- os: linux
env: CC=gcc CXX=g++ COMPILER_FLAGS="" CONFIGURE_FLAGS="--with-malloc-conf=percpu_arena:percpu" EXTRA_CFLAGS="-Werror -Wno-array-bounds"
- os: linux
env: CC=gcc CXX=g++ COMPILER_FLAGS="" CONFIGURE_FLAGS="--with-malloc-conf=background_thread:true" EXTRA_CFLAGS="-Werror -Wno-array-bounds"
- os: osx
env: CC=clang CXX=clang++ COMPILER_FLAGS="" CONFIGURE_FLAGS="" EXTRA_CFLAGS="-Werror -Wno-array-bounds"
- os: osx
env: CC=gcc CXX=g++ COMPILER_FLAGS="-m32" CONFIGURE_FLAGS="" EXTRA_CFLAGS="-Werror -Wno-array-bounds"
- os: osx
env: CC=gcc CXX=g++ COMPILER_FLAGS="" CONFIGURE_FLAGS="--enable-debug" EXTRA_CFLAGS="-Werror -Wno-array-bounds"
- os: osx
env: CC=gcc CXX=g++ COMPILER_FLAGS="" CONFIGURE_FLAGS="--disable-stats" EXTRA_CFLAGS="-Werror -Wno-array-bounds"
- os: osx
env: CC=gcc CXX=g++ COMPILER_FLAGS="" CONFIGURE_FLAGS="--with-malloc-conf=tcache:false" EXTRA_CFLAGS="-Werror -Wno-array-bounds"
- os: linux
env: CC=clang CXX=clang++ COMPILER_FLAGS="-m32" CONFIGURE_FLAGS="" EXTRA_CFLAGS="-Werror -Wno-array-bounds"
addons:
apt:
packages:
- gcc-multilib
- os: linux
env: CC=clang CXX=clang++ COMPILER_FLAGS="" CONFIGURE_FLAGS="--enable-debug" EXTRA_CFLAGS="-Werror -Wno-array-bounds"
- os: linux
env: CC=clang CXX=clang++ COMPILER_FLAGS="" CONFIGURE_FLAGS="--enable-prof" EXTRA_CFLAGS="-Werror -Wno-array-bounds"
- os: linux
env: CC=clang CXX=clang++ COMPILER_FLAGS="" CONFIGURE_FLAGS="--disable-stats" EXTRA_CFLAGS="-Werror -Wno-array-bounds"
- os: linux
env: CC=clang CXX=clang++ COMPILER_FLAGS="" CONFIGURE_FLAGS="--with-malloc-conf=tcache:false" EXTRA_CFLAGS="-Werror -Wno-array-bounds"
- os: linux
env: CC=clang CXX=clang++ COMPILER_FLAGS="" CONFIGURE_FLAGS="--with-malloc-conf=dss:primary" EXTRA_CFLAGS="-Werror -Wno-array-bounds"
- os: linux
env: CC=clang CXX=clang++ COMPILER_FLAGS="" CONFIGURE_FLAGS="--with-malloc-conf=percpu_arena:percpu" EXTRA_CFLAGS="-Werror -Wno-array-bounds"
- os: linux
env: CC=clang CXX=clang++ COMPILER_FLAGS="" CONFIGURE_FLAGS="--with-malloc-conf=background_thread:true" EXTRA_CFLAGS="-Werror -Wno-array-bounds"
- os: linux
env: CC=gcc CXX=g++ COMPILER_FLAGS="-m32" CONFIGURE_FLAGS="--enable-debug" EXTRA_CFLAGS="-Werror -Wno-array-bounds"
addons:
apt:
packages:
- gcc-multilib
- os: linux
env: CC=gcc CXX=g++ COMPILER_FLAGS="-m32" CONFIGURE_FLAGS="--enable-prof" EXTRA_CFLAGS="-Werror -Wno-array-bounds"
addons:
apt:
packages:
- gcc-multilib
- os: linux
env: CC=gcc CXX=g++ COMPILER_FLAGS="-m32" CONFIGURE_FLAGS="--disable-stats" EXTRA_CFLAGS="-Werror -Wno-array-bounds"
addons:
apt:
packages:
- gcc-multilib
- os: linux
env: CC=gcc CXX=g++ COMPILER_FLAGS="-m32" CONFIGURE_FLAGS="--with-malloc-conf=tcache:false" EXTRA_CFLAGS="-Werror -Wno-array-bounds"
addons:
apt:
packages:
- gcc-multilib
- os: linux
env: CC=gcc CXX=g++ COMPILER_FLAGS="-m32" CONFIGURE_FLAGS="--with-malloc-conf=dss:primary" EXTRA_CFLAGS="-Werror -Wno-array-bounds"
addons:
apt:
packages:
- gcc-multilib
- os: linux
env: CC=gcc CXX=g++ COMPILER_FLAGS="-m32" CONFIGURE_FLAGS="--with-malloc-conf=percpu_arena:percpu" EXTRA_CFLAGS="-Werror -Wno-array-bounds"
addons:
apt:
packages:
- gcc-multilib
- os: linux
env: CC=gcc CXX=g++ COMPILER_FLAGS="-m32" CONFIGURE_FLAGS="--with-malloc-conf=background_thread:true" EXTRA_CFLAGS="-Werror -Wno-array-bounds"
addons:
apt:
packages:
- gcc-multilib
- os: linux
env: CC=gcc CXX=g++ COMPILER_FLAGS="" CONFIGURE_FLAGS="--enable-debug --enable-prof" EXTRA_CFLAGS="-Werror -Wno-array-bounds"
- os: linux
env: CC=gcc CXX=g++ COMPILER_FLAGS="" CONFIGURE_FLAGS="--enable-debug --disable-stats" EXTRA_CFLAGS="-Werror -Wno-array-bounds"
- os: linux
env: CC=gcc CXX=g++ COMPILER_FLAGS="" CONFIGURE_FLAGS="--enable-debug --with-malloc-conf=tcache:false" EXTRA_CFLAGS="-Werror -Wno-array-bounds"
- os: linux
env: CC=gcc CXX=g++ COMPILER_FLAGS="" CONFIGURE_FLAGS="--enable-debug --with-malloc-conf=dss:primary" EXTRA_CFLAGS="-Werror -Wno-array-bounds"
- os: linux
env: CC=gcc CXX=g++ COMPILER_FLAGS="" CONFIGURE_FLAGS="--enable-debug --with-malloc-conf=percpu_arena:percpu" EXTRA_CFLAGS="-Werror -Wno-array-bounds"
- os: linux
env: CC=gcc CXX=g++ COMPILER_FLAGS="" CONFIGURE_FLAGS="--enable-debug --with-malloc-conf=background_thread:true" EXTRA_CFLAGS="-Werror -Wno-array-bounds"
- os: linux
env: CC=gcc CXX=g++ COMPILER_FLAGS="" CONFIGURE_FLAGS="--enable-prof --disable-stats" EXTRA_CFLAGS="-Werror -Wno-array-bounds"
- os: linux
env: CC=gcc CXX=g++ COMPILER_FLAGS="" CONFIGURE_FLAGS="--enable-prof --with-malloc-conf=tcache:false" EXTRA_CFLAGS="-Werror -Wno-array-bounds"
- os: linux
env: CC=gcc CXX=g++ COMPILER_FLAGS="" CONFIGURE_FLAGS="--enable-prof --with-malloc-conf=dss:primary" EXTRA_CFLAGS="-Werror -Wno-array-bounds"
- os: linux
env: CC=gcc CXX=g++ COMPILER_FLAGS="" CONFIGURE_FLAGS="--enable-prof --with-malloc-conf=percpu_arena:percpu" EXTRA_CFLAGS="-Werror -Wno-array-bounds"
- os: linux
env: CC=gcc CXX=g++ COMPILER_FLAGS="" CONFIGURE_FLAGS="--enable-prof --with-malloc-conf=background_thread:true" EXTRA_CFLAGS="-Werror -Wno-array-bounds"
- os: linux
env: CC=gcc CXX=g++ COMPILER_FLAGS="" CONFIGURE_FLAGS="--disable-stats --with-malloc-conf=tcache:false" EXTRA_CFLAGS="-Werror -Wno-array-bounds"
- os: linux
env: CC=gcc CXX=g++ COMPILER_FLAGS="" CONFIGURE_FLAGS="--disable-stats --with-malloc-conf=dss:primary" EXTRA_CFLAGS="-Werror -Wno-array-bounds"
- os: linux
env: CC=gcc CXX=g++ COMPILER_FLAGS="" CONFIGURE_FLAGS="--disable-stats --with-malloc-conf=percpu_arena:percpu" EXTRA_CFLAGS="-Werror -Wno-array-bounds"
- os: linux
env: CC=gcc CXX=g++ COMPILER_FLAGS="" CONFIGURE_FLAGS="--disable-stats --with-malloc-conf=background_thread:true" EXTRA_CFLAGS="-Werror -Wno-array-bounds"
- os: linux
env: CC=gcc CXX=g++ COMPILER_FLAGS="" CONFIGURE_FLAGS="--with-malloc-conf=tcache:false,dss:primary" EXTRA_CFLAGS="-Werror -Wno-array-bounds"
- os: linux
env: CC=gcc CXX=g++ COMPILER_FLAGS="" CONFIGURE_FLAGS="--with-malloc-conf=tcache:false,percpu_arena:percpu" EXTRA_CFLAGS="-Werror -Wno-array-bounds"
- os: linux
env: CC=gcc CXX=g++ COMPILER_FLAGS="" CONFIGURE_FLAGS="--with-malloc-conf=tcache:false,background_thread:true" EXTRA_CFLAGS="-Werror -Wno-array-bounds"
- os: linux
env: CC=gcc CXX=g++ COMPILER_FLAGS="" CONFIGURE_FLAGS="--with-malloc-conf=dss:primary,percpu_arena:percpu" EXTRA_CFLAGS="-Werror -Wno-array-bounds"
- os: linux
env: CC=gcc CXX=g++ COMPILER_FLAGS="" CONFIGURE_FLAGS="--with-malloc-conf=dss:primary,background_thread:true" EXTRA_CFLAGS="-Werror -Wno-array-bounds"
- os: linux
env: CC=gcc CXX=g++ COMPILER_FLAGS="" CONFIGURE_FLAGS="--with-malloc-conf=percpu_arena:percpu,background_thread:true" EXTRA_CFLAGS="-Werror -Wno-array-bounds"
before_script:
- autoconf
- ./configure ${COMPILER_FLAGS:+ CC="$CC $COMPILER_FLAGS" CXX="$CXX $COMPILER_FLAGS" } $CONFIGURE_FLAGS
- make -j3
- make -j3 tests
script:
- make check
Unless otherwise specified, files in the jemalloc source distribution are
subject to the following license:
--------------------------------------------------------------------------------
Copyright (C) 2002-2015 Jason Evans <jasone@canonware.com>.
Copyright (C) 2002-2018 Jason Evans <jasone@canonware.com>.
All rights reserved.
Copyright (C) 2007-2012 Mozilla Foundation. All rights reserved.
Copyright (C) 2009-2015 Facebook, Inc. All rights reserved.
Copyright (C) 2009-2018 Facebook, Inc. All rights reserved.
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
......
......@@ -4,6 +4,600 @@ brevity. Much more detail can be found in the git revision history:
https://github.com/jemalloc/jemalloc
* 5.1.0 (May 4th, 2018)
This release is primarily about fine-tuning, ranging from several new features
to numerous notable performance and portability enhancements. The release and
prior dev versions have been running in multiple large scale applications for
months, and the cumulative improvements are substantial in many cases.
Given the long and successful production runs, this release is likely a good
candidate for applications to upgrade, from both jemalloc 5.0 and before. For
performance-critical applications, the newly added TUNING.md provides
guidelines on jemalloc tuning.
New features:
- Implement transparent huge page support for internal metadata. (@interwq)
- Add opt.thp to allow enabling / disabling transparent huge pages for all
mappings. (@interwq)
- Add maximum background thread count option. (@djwatson)
- Allow prof_active to control opt.lg_prof_interval and prof.gdump.
(@interwq)
- Allow arena index lookup based on allocation addresses via mallctl.
(@lionkov)
- Allow disabling initial-exec TLS model. (@davidtgoldblatt, @KenMacD)
- Add opt.lg_extent_max_active_fit to set the max ratio between the size of
the active extent selected (to split off from) and the size of the requested
allocation. (@interwq, @davidtgoldblatt)
- Add retain_grow_limit to set the max size when growing virtual address
space. (@interwq)
- Add mallctl interfaces:
+ arena.<i>.retain_grow_limit (@interwq)
+ arenas.lookup (@lionkov)
+ max_background_threads (@djwatson)
+ opt.lg_extent_max_active_fit (@interwq)
+ opt.max_background_threads (@djwatson)
+ opt.metadata_thp (@interwq)
+ opt.thp (@interwq)
+ stats.metadata_thp (@interwq)
Portability improvements:
- Support GNU/kFreeBSD configuration. (@paravoid)
- Support m68k, nios2 and SH3 architectures. (@paravoid)
- Fall back to FD_CLOEXEC when O_CLOEXEC is unavailable. (@zonyitoo)
- Fix symbol listing for cross-compiling. (@tamird)
- Fix high bits computation on ARM. (@davidtgoldblatt, @paravoid)
- Disable the CPU_SPINWAIT macro for Power. (@davidtgoldblatt, @marxin)
- Fix MSVC 2015 & 2017 builds. (@rustyx)
- Improve RISC-V support. (@EdSchouten)
- Set name mangling script in strict mode. (@nicolov)
- Avoid MADV_HUGEPAGE on ARM. (@marxin)
- Modify configure to determine return value of strerror_r.
(@davidtgoldblatt, @cferris1000)
- Make sure CXXFLAGS is tested with CPP compiler. (@nehaljwani)
- Fix 32-bit build on MSVC. (@rustyx)
- Fix external symbol on MSVC. (@maksqwe)
- Avoid a printf format specifier warning. (@jasone)
- Add configure option --disable-initial-exec-tls which can allow jemalloc to
be dynamically loaded after program startup. (@davidtgoldblatt, @KenMacD)
- AArch64: Add ILP32 support. (@cmuellner)
- Add --with-lg-vaddr configure option to support cross compiling.
(@cmuellner, @davidtgoldblatt)
Optimizations and refactors:
- Improve active extent fit with extent_max_active_fit. This considerably
reduces fragmentation over time and improves virtual memory and metadata
usage. (@davidtgoldblatt, @interwq)
- Eagerly coalesce large extents to reduce fragmentation. (@interwq)
- sdallocx: only read size info when page aligned (i.e. possibly sampled),
which speeds up the sized deallocation path significantly. (@interwq)
- Avoid attempting new mappings for in place expansion with retain, since
it rarely succeeds in practice and causes high overhead. (@interwq)
- Refactor OOM handling in newImpl. (@wqfish)
- Add internal fine-grained logging functionality for debugging use.
(@davidtgoldblatt)
- Refactor arena / tcache interactions. (@davidtgoldblatt)
- Refactor extent management with dumpable flag. (@davidtgoldblatt)
- Add runtime detection of lazy purging. (@interwq)
- Use pairing heap instead of red-black tree for extents_avail. (@djwatson)
- Use sysctl on startup in FreeBSD. (@trasz)
- Use thread local prng state instead of atomic. (@djwatson)
- Make decay to always purge one more extent than before, because in
practice large extents are usually the ones that cross the decay threshold.
Purging the additional extent helps save memory as well as reduce VM
fragmentation. (@interwq)
- Fast division by dynamic values. (@davidtgoldblatt)
- Improve the fit for aligned allocation. (@interwq, @edwinsmith)
- Refactor extent_t bitpacking. (@rkmisra)
- Optimize the generated assembly for ticker operations. (@davidtgoldblatt)
- Convert stats printing to use a structured text emitter. (@davidtgoldblatt)
- Remove preserve_lru feature for extents management. (@djwatson)
- Consolidate two memory loads into one on the fast deallocation path.
(@davidtgoldblatt, @interwq)
Bug fixes (most of the issues are only relevant to jemalloc 5.0):
- Fix deadlock with multithreaded fork in OS X. (@davidtgoldblatt)
- Validate returned file descriptor before use. (@zonyitoo)
- Fix a few background thread initialization and shutdown issues. (@interwq)
- Fix an extent coalesce + decay race by taking both coalescing extents off
the LRU list. (@interwq)
- Fix potentially unbound increase during decay, caused by one thread keep
stashing memory to purge while other threads generating new pages. The
number of pages to purge is checked to prevent this. (@interwq)
- Fix a FreeBSD bootstrap assertion. (@strejda, @interwq)
- Handle 32 bit mutex counters. (@rkmisra)
- Fix a indexing bug when creating background threads. (@davidtgoldblatt,
@binliu19)
- Fix arguments passed to extent_init. (@yuleniwo, @interwq)
- Fix addresses used for ordering mutexes. (@rkmisra)
- Fix abort_conf processing during bootstrap. (@interwq)
- Fix include path order for out-of-tree builds. (@cmuellner)
Incompatible changes:
- Remove --disable-thp. (@interwq)
- Remove mallctl interfaces:
+ config.thp (@interwq)
Documentation:
- Add TUNING.md. (@interwq, @davidtgoldblatt, @djwatson)
* 5.0.1 (July 1, 2017)
This bugfix release fixes several issues, most of which are obscure enough
that typical applications are not impacted.
Bug fixes:
- Update decay->nunpurged before purging, in order to avoid potential update
races and subsequent incorrect purging volume. (@interwq)
- Only abort on dlsym(3) error if the failure impacts an enabled feature (lazy
locking and/or background threads). This mitigates an initialization
failure bug for which we still do not have a clear reproduction test case.
(@interwq)
- Modify tsd management so that it neither crashes nor leaks if a thread's
only allocation activity is to call free() after TLS destructors have been
executed. This behavior was observed when operating with GNU libc, and is
unlikely to be an issue with other libc implementations. (@interwq)
- Mask signals during background thread creation. This prevents signals from
being inadvertently delivered to background threads. (@jasone,
@davidtgoldblatt, @interwq)
- Avoid inactivity checks within background threads, in order to prevent
recursive mutex acquisition. (@interwq)
- Fix extent_grow_retained() to use the specified hooks when the
arena.<i>.extent_hooks mallctl is used to override the default hooks.
(@interwq)
- Add missing reentrancy support for custom extent hooks which allocate.
(@interwq)
- Post-fork(2), re-initialize the list of tcaches associated with each arena
to contain no tcaches except the forking thread's. (@interwq)
- Add missing post-fork(2) mutex reinitialization for extent_grow_mtx. This
fixes potential deadlocks after fork(2). (@interwq)
- Enforce minimum autoconf version (currently 2.68), since 2.63 is known to
generate corrupt configure scripts. (@jasone)
- Ensure that the configured page size (--with-lg-page) is no larger than the
configured huge page size (--with-lg-hugepage). (@jasone)
* 5.0.0 (June 13, 2017)
Unlike all previous jemalloc releases, this release does not use naturally
aligned "chunks" for virtual memory management, and instead uses page-aligned
"extents". This change has few externally visible effects, but the internal
impacts are... extensive. Many other internal changes combine to make this
the most cohesively designed version of jemalloc so far, with ample
opportunity for further enhancements.
Continuous integration is now an integral aspect of development thanks to the
efforts of @davidtgoldblatt, and the dev branch tends to remain reasonably
stable on the tested platforms (Linux, FreeBSD, macOS, and Windows). As a
side effect the official release frequency may decrease over time.
New features:
- Implement optional per-CPU arena support; threads choose which arena to use
based on current CPU rather than on fixed thread-->arena associations.
(@interwq)
- Implement two-phase decay of unused dirty pages. Pages transition from
dirty-->muzzy-->clean, where the first phase transition relies on
madvise(... MADV_FREE) semantics, and the second phase transition discards
pages such that they are replaced with demand-zeroed pages on next access.
(@jasone)
- Increase decay time resolution from seconds to milliseconds. (@jasone)
- Implement opt-in per CPU background threads, and use them for asynchronous
decay-driven unused dirty page purging. (@interwq)
- Add mutex profiling, which collects a variety of statistics useful for
diagnosing overhead/contention issues. (@interwq)
- Add C++ new/delete operator bindings. (@djwatson)
- Support manually created arena destruction, such that all data and metadata
are discarded. Add MALLCTL_ARENAS_DESTROYED for accessing merged stats
associated with destroyed arenas. (@jasone)
- Add MALLCTL_ARENAS_ALL as a fixed index for use in accessing
merged/destroyed arena statistics via mallctl. (@jasone)
- Add opt.abort_conf to optionally abort if invalid configuration options are
detected during initialization. (@interwq)
- Add opt.stats_print_opts, so that e.g. JSON output can be selected for the
stats dumped during exit if opt.stats_print is true. (@jasone)
- Add --with-version=VERSION for use when embedding jemalloc into another
project's git repository. (@jasone)
- Add --disable-thp to support cross compiling. (@jasone)
- Add --with-lg-hugepage to support cross compiling. (@jasone)
- Add mallctl interfaces (various authors):
+ background_thread
+ opt.abort_conf
+ opt.retain
+ opt.percpu_arena
+ opt.background_thread
+ opt.{dirty,muzzy}_decay_ms
+ opt.stats_print_opts
+ arena.<i>.initialized
+ arena.<i>.destroy
+ arena.<i>.{dirty,muzzy}_decay_ms
+ arena.<i>.extent_hooks
+ arenas.{dirty,muzzy}_decay_ms
+ arenas.bin.<i>.slab_size
+ arenas.nlextents
+ arenas.lextent.<i>.size
+ arenas.create
+ stats.background_thread.{num_threads,num_runs,run_interval}
+ stats.mutexes.{ctl,background_thread,prof,reset}.
{num_ops,num_spin_acq,num_wait,max_wait_time,total_wait_time,max_num_thds,
num_owner_switch}
+ stats.arenas.<i>.{dirty,muzzy}_decay_ms
+ stats.arenas.<i>.uptime
+ stats.arenas.<i>.{pmuzzy,base,internal,resident}
+ stats.arenas.<i>.{dirty,muzzy}_{npurge,nmadvise,purged}
+ stats.arenas.<i>.bins.<j>.{nslabs,reslabs,curslabs}
+ stats.arenas.<i>.bins.<j>.mutex.
{num_ops,num_spin_acq,num_wait,max_wait_time,total_wait_time,max_num_thds,
num_owner_switch}
+ stats.arenas.<i>.lextents.<j>.{nmalloc,ndalloc,nrequests,curlextents}
+ stats.arenas.i.mutexes.{large,extent_avail,extents_dirty,extents_muzzy,
extents_retained,decay_dirty,decay_muzzy,base,tcache_list}.
{num_ops,num_spin_acq,num_wait,max_wait_time,total_wait_time,max_num_thds,
num_owner_switch}
Portability improvements:
- Improve reentrant allocation support, such that deadlock is less likely if
e.g. a system library call in turn allocates memory. (@davidtgoldblatt,
@interwq)
- Support static linking of jemalloc with glibc. (@djwatson)
Optimizations and refactors:
- Organize virtual memory as "extents" of virtual memory pages, rather than as
naturally aligned "chunks", and store all metadata in arbitrarily distant
locations. This reduces virtual memory external fragmentation, and will
interact better with huge pages (not yet explicitly supported). (@jasone)
- Fold large and huge size classes together; only small and large size classes
remain. (@jasone)
- Unify the allocation paths, and merge most fast-path branching decisions.
(@davidtgoldblatt, @interwq)
- Embed per thread automatic tcache into thread-specific data, which reduces
conditional branches and dereferences. Also reorganize tcache to increase
fast-path data locality. (@interwq)
- Rewrite atomics to closely model the C11 API, convert various
synchronization from mutex-based to atomic, and use the explicit memory
ordering control to resolve various hypothetical races without increasing
synchronization overhead. (@davidtgoldblatt)
- Extensively optimize rtree via various methods:
+ Add multiple layers of rtree lookup caching, since rtree lookups are now
part of fast-path deallocation. (@interwq)
+ Determine rtree layout at compile time. (@jasone)
+ Make the tree shallower for common configurations. (@jasone)
+ Embed the root node in the top-level rtree data structure, thus avoiding
one level of indirection. (@jasone)
+ Further specialize leaf elements as compared to internal node elements,
and directly embed extent metadata needed for fast-path deallocation.
(@jasone)
+ Ignore leading always-zero address bits (architecture-specific).
(@jasone)
- Reorganize headers (ongoing work) to make them hermetic, and disentangle
various module dependencies. (@davidtgoldblatt)
- Convert various internal data structures such as size class metadata from
boot-time-initialized to compile-time-initialized. Propagate resulting data
structure simplifications, such as making arena metadata fixed-size.
(@jasone)
- Simplify size class lookups when constrained to size classes that are
multiples of the page size. This speeds lookups, but the primary benefit is
complexity reduction in code that was the source of numerous regressions.
(@jasone)
- Lock individual extents when possible for localized extent operations,
rather than relying on a top-level arena lock. (@davidtgoldblatt, @jasone)
- Use first fit layout policy instead of best fit, in order to improve
packing. (@jasone)
- If munmap(2) is not in use, use an exponential series to grow each arena's
virtual memory, so that the number of disjoint virtual memory mappings
remains low. (@jasone)
- Implement per arena base allocators, so that arenas never share any virtual
memory pages. (@jasone)
- Automatically generate private symbol name mangling macros. (@jasone)
Incompatible changes:
- Replace chunk hooks with an expanded/normalized set of extent hooks.
(@jasone)
- Remove ratio-based purging. (@jasone)
- Remove --disable-tcache. (@jasone)
- Remove --disable-tls. (@jasone)
- Remove --enable-ivsalloc. (@jasone)
- Remove --with-lg-size-class-group. (@jasone)
- Remove --with-lg-tiny-min. (@jasone)
- Remove --disable-cc-silence. (@jasone)
- Remove --enable-code-coverage. (@jasone)
- Remove --disable-munmap (replaced by opt.retain). (@jasone)
- Remove Valgrind support. (@jasone)
- Remove quarantine support. (@jasone)
- Remove redzone support. (@jasone)
- Remove mallctl interfaces (various authors):
+ config.munmap
+ config.tcache
+ config.tls
+ config.valgrind
+ opt.lg_chunk
+ opt.purge
+ opt.lg_dirty_mult
+ opt.decay_time
+ opt.quarantine
+ opt.redzone
+ opt.thp
+ arena.<i>.lg_dirty_mult
+ arena.<i>.decay_time
+ arena.<i>.chunk_hooks
+ arenas.initialized
+ arenas.lg_dirty_mult
+ arenas.decay_time
+ arenas.bin.<i>.run_size
+ arenas.nlruns
+ arenas.lrun.<i>.size
+ arenas.nhchunks
+ arenas.hchunk.<i>.size
+ arenas.extend
+ stats.cactive
+ stats.arenas.<i>.lg_dirty_mult
+ stats.arenas.<i>.decay_time
+ stats.arenas.<i>.metadata.{mapped,allocated}
+ stats.arenas.<i>.{npurge,nmadvise,purged}
+ stats.arenas.<i>.huge.{allocated,nmalloc,ndalloc,nrequests}
+ stats.arenas.<i>.bins.<j>.{nruns,reruns,curruns}
+ stats.arenas.<i>.lruns.<j>.{nmalloc,ndalloc,nrequests,curruns}
+ stats.arenas.<i>.hchunks.<j>.{nmalloc,ndalloc,nrequests,curhchunks}
Bug fixes:
- Improve interval-based profile dump triggering to dump only one profile when
a single allocation's size exceeds the interval. (@jasone)
- Use prefixed function names (as controlled by --with-jemalloc-prefix) when
pruning backtrace frames in jeprof. (@jasone)
* 4.5.0 (February 28, 2017)
This is the first release to benefit from much broader continuous integration
testing, thanks to @davidtgoldblatt. Had we had this testing infrastructure
in place for prior releases, it would have caught all of the most serious
regressions fixed by this release.
New features:
- Add --disable-thp and the opt.thp mallctl to provide opt-out mechanisms for
transparent huge page integration. (@jasone)
- Update zone allocator integration to work with macOS 10.12. (@glandium)
- Restructure *CFLAGS configuration, so that CFLAGS behaves typically, and
EXTRA_CFLAGS provides a way to specify e.g. -Werror during building, but not
during configuration. (@jasone, @ronawho)
Bug fixes:
- Fix DSS (sbrk(2)-based) allocation. This regression was first released in
4.3.0. (@jasone)
- Handle race in per size class utilization computation. This functionality
was first released in 4.0.0. (@interwq)
- Fix lock order reversal during gdump. (@jasone)
- Fix/refactor tcache synchronization. This regression was first released in
4.0.0. (@jasone)
- Fix various JSON-formatted malloc_stats_print() bugs. This functionality
was first released in 4.3.0. (@jasone)
- Fix huge-aligned allocation. This regression was first released in 4.4.0.
(@jasone)
- When transparent huge page integration is enabled, detect what state pages
start in according to the kernel's current operating mode, and only convert
arena chunks to non-huge during purging if that is not their initial state.
This functionality was first released in 4.4.0. (@jasone)
- Fix lg_chunk clamping for the --enable-cache-oblivious --disable-fill case.
This regression was first released in 4.0.0. (@jasone, @428desmo)
- Properly detect sparc64 when building for Linux. (@glaubitz)
* 4.4.0 (December 3, 2016)
New features:
- Add configure support for *-*-linux-android. (@cferris1000, @jasone)
- Add the --disable-syscall configure option, for use on systems that place
security-motivated limitations on syscall(2). (@jasone)
- Add support for Debian GNU/kFreeBSD. (@thesam)
Optimizations:
- Add extent serial numbers and use them where appropriate as a sort key that
is higher priority than address, so that the allocation policy prefers older
extents. This tends to improve locality (decrease fragmentation) when
memory grows downward. (@jasone)
- Refactor madvise(2) configuration so that MADV_FREE is detected and utilized
on Linux 4.5 and newer. (@jasone)
- Mark partially purged arena chunks as non-huge-page. This improves
interaction with Linux's transparent huge page functionality. (@jasone)
Bug fixes:
- Fix size class computations for edge conditions involving extremely large
allocations. This regression was first released in 4.0.0. (@jasone,
@ingvarha)
- Remove overly restrictive assertions related to the cactive statistic. This
regression was first released in 4.1.0. (@jasone)
- Implement a more reliable detection scheme for os_unfair_lock on macOS.
(@jszakmeister)
* 4.3.1 (November 7, 2016)
Bug fixes:
- Fix a severe virtual memory leak. This regression was first released in
4.3.0. (@interwq, @jasone)
- Refactor atomic and prng APIs to restore support for 32-bit platforms that
use pre-C11 toolchains, e.g. FreeBSD's mips. (@jasone)
* 4.3.0 (November 4, 2016)
This is the first release that passes the test suite for multiple Windows
configurations, thanks in large part to @glandium setting up continuous
integration via AppVeyor (and Travis CI for Linux and OS X).
New features:
- Add "J" (JSON) support to malloc_stats_print(). (@jasone)
- Add Cray compiler support. (@ronawho)
Optimizations:
- Add/use adaptive spinning for bootstrapping and radix tree node
initialization. (@jasone)
Bug fixes:
- Fix large allocation to search starting in the optimal size class heap,
which can substantially reduce virtual memory churn and fragmentation. This
regression was first released in 4.0.0. (@mjp41, @jasone)
- Fix stats.arenas.<i>.nthreads accounting. (@interwq)
- Fix and simplify decay-based purging. (@jasone)
- Make DSS (sbrk(2)-related) operations lockless, which resolves potential
deadlocks during thread exit. (@jasone)
- Fix over-sized allocation of radix tree leaf nodes. (@mjp41, @ogaun,
@jasone)
- Fix over-sized allocation of arena_t (plus associated stats) data
structures. (@jasone, @interwq)
- Fix EXTRA_CFLAGS to not affect configuration. (@jasone)
- Fix a Valgrind integration bug. (@ronawho)
- Disallow 0x5a junk filling when running in Valgrind. (@jasone)
- Fix a file descriptor leak on Linux. This regression was first released in
4.2.0. (@vsarunas, @jasone)
- Fix static linking of jemalloc with glibc. (@djwatson)
- Use syscall(2) rather than {open,read,close}(2) during boot on Linux. This
works around other libraries' system call wrappers performing reentrant
allocation. (@kspinka, @Whissi, @jasone)
- Fix OS X default zone replacement to work with OS X 10.12. (@glandium,
@jasone)
- Fix cached memory management to avoid needless commit/decommit operations
during purging, which resolves permanent virtual memory map fragmentation
issues on Windows. (@mjp41, @jasone)
- Fix TSD fetches to avoid (recursive) allocation. This is relevant to
non-TLS and Windows configurations. (@jasone)
- Fix malloc_conf overriding to work on Windows. (@jasone)
- Forcibly disable lazy-lock on Windows (was forcibly *enabled*). (@jasone)
* 4.2.1 (June 8, 2016)
Bug fixes:
- Fix bootstrapping issues for configurations that require allocation during
tsd initialization (e.g. --disable-tls). (@cferris1000, @jasone)
- Fix gettimeofday() version of nstime_update(). (@ronawho)
- Fix Valgrind regressions in calloc() and chunk_alloc_wrapper(). (@ronawho)
- Fix potential VM map fragmentation regression. (@jasone)
- Fix opt_zero-triggered in-place huge reallocation zeroing. (@jasone)
- Fix heap profiling context leaks in reallocation edge cases. (@jasone)
* 4.2.0 (May 12, 2016)
New features:
- Add the arena.<i>.reset mallctl, which makes it possible to discard all of
an arena's allocations in a single operation. (@jasone)
- Add the stats.retained and stats.arenas.<i>.retained statistics. (@jasone)
- Add the --with-version configure option. (@jasone)
- Support --with-lg-page values larger than actual page size. (@jasone)
Optimizations:
- Use pairing heaps rather than red-black trees for various hot data
structures. (@djwatson, @jasone)
- Streamline fast paths of rtree operations. (@jasone)
- Optimize the fast paths of calloc() and [m,d,sd]allocx(). (@jasone)
- Decommit unused virtual memory if the OS does not overcommit. (@jasone)
- Specify MAP_NORESERVE on Linux if [heuristic] overcommit is active, in order
to avoid unfortunate interactions during fork(2). (@jasone)
Bug fixes:
- Fix chunk accounting related to triggering gdump profiles. (@jasone)
- Link against librt for clock_gettime(2) if glibc < 2.17. (@jasone)
- Scale leak report summary according to sampling probability. (@jasone)
* 4.1.1 (May 3, 2016)
This bugfix release resolves a variety of mostly minor issues, though the
bitmap fix is critical for 64-bit Windows.
Bug fixes:
- Fix the linear scan version of bitmap_sfu() to shift by the proper amount
even when sizeof(long) is not the same as sizeof(void *), as on 64-bit
Windows. (@jasone)
- Fix hashing functions to avoid unaligned memory accesses (and resulting
crashes). This is relevant at least to some ARM-based platforms.
(@rkmisra)
- Fix fork()-related lock rank ordering reversals. These reversals were
unlikely to cause deadlocks in practice except when heap profiling was
enabled and active. (@jasone)
- Fix various chunk leaks in OOM code paths. (@jasone)
- Fix malloc_stats_print() to print opt.narenas correctly. (@jasone)
- Fix MSVC-specific build/test issues. (@rustyx, @yuslepukhin)
- Fix a variety of test failures that were due to test fragility rather than
core bugs. (@jasone)
* 4.1.0 (February 28, 2016)
This release is primarily about optimizations, but it also incorporates a lot
of portability-motivated refactoring and enhancements. Many people worked on
this release, to an extent that even with the omission here of minor changes
(see git revision history), and of the people who reported and diagnosed
issues, so much of the work was contributed that starting with this release,
changes are annotated with author credits to help reflect the collaborative
effort involved.
New features:
- Implement decay-based unused dirty page purging, a major optimization with
mallctl API impact. This is an alternative to the existing ratio-based
unused dirty page purging, and is intended to eventually become the sole
purging mechanism. New mallctls:
+ opt.purge
+ opt.decay_time
+ arena.<i>.decay
+ arena.<i>.decay_time
+ arenas.decay_time
+ stats.arenas.<i>.decay_time
(@jasone, @cevans87)
- Add --with-malloc-conf, which makes it possible to embed a default
options string during configuration. This was motivated by the desire to
specify --with-malloc-conf=purge:decay , since the default must remain
purge:ratio until the 5.0.0 release. (@jasone)
- Add MS Visual Studio 2015 support. (@rustyx, @yuslepukhin)
- Make *allocx() size class overflow behavior defined. The maximum
size class is now less than PTRDIFF_MAX to protect applications against
numerical overflow, and all allocation functions are guaranteed to indicate
errors rather than potentially crashing if the request size exceeds the
maximum size class. (@jasone)
- jeprof:
+ Add raw heap profile support. (@jasone)
+ Add --retain and --exclude for backtrace symbol filtering. (@jasone)
Optimizations:
- Optimize the fast path to combine various bootstrapping and configuration
checks and execute more streamlined code in the common case. (@interwq)
- Use linear scan for small bitmaps (used for small object tracking). In
addition to speeding up bitmap operations on 64-bit systems, this reduces
allocator metadata overhead by approximately 0.2%. (@djwatson)
- Separate arena_avail trees, which substantially speeds up run tree
operations. (@djwatson)
- Use memoization (boot-time-computed table) for run quantization. Separate
arena_avail trees reduced the importance of this optimization. (@jasone)
- Attempt mmap-based in-place huge reallocation. This can dramatically speed
up incremental huge reallocation. (@jasone)
Incompatible changes:
- Make opt.narenas unsigned rather than size_t. (@jasone)
Bug fixes:
- Fix stats.cactive accounting regression. (@rustyx, @jasone)
- Handle unaligned keys in hash(). This caused problems for some ARM systems.
(@jasone, @cferris1000)
- Refactor arenas array. In addition to fixing a fork-related deadlock, this
makes arena lookups faster and simpler. (@jasone)
- Move retained memory allocation out of the default chunk allocation
function, to a location that gets executed even if the application installs
a custom chunk allocation function. This resolves a virtual memory leak.
(@buchgr)
- Fix a potential tsd cleanup leak. (@cferris1000, @jasone)
- Fix run quantization. In practice this bug had no impact unless
applications requested memory with alignment exceeding one page.
(@jasone, @djwatson)
- Fix LinuxThreads-specific bootstrapping deadlock. (Cosmin Paraschiv)
- jeprof:
+ Don't discard curl options if timeout is not defined. (@djwatson)
+ Detect failed profile fetches. (@djwatson)
- Fix stats.arenas.<i>.{dss,lg_dirty_mult,decay_time,pactive,pdirty} for
--disable-stats case. (@jasone)
* 4.0.4 (October 24, 2015)
This bugfix release fixes another xallocx() regression. No other regressions
have come to light in over a month, so this is likely a good starting point
for people who prefer to wait for "dot one" releases with all the major issues
shaken out.
Bug fixes:
- Fix xallocx(..., MALLOCX_ZERO to zero the last full trailing page of large
allocations that have been randomly assigned an offset of 0 when
--enable-cache-oblivious configure option is enabled.
* 4.0.3 (September 24, 2015)
This bugfix release continues the trend of xallocx() and heap profiling fixes.
......@@ -38,7 +632,7 @@ brevity. Much more detail can be found in the git revision history:
these fixes, xallocx() now tries harder to partially fulfill requests for
optional extra space. Note that a couple of minor heap profiling
optimizations are included, but these are better thought of as performance
fixes that were integral to disovering most of the other bugs.
fixes that were integral to discovering most of the other bugs.
Optimizations:
- Avoid a chunk metadata read in arena_prof_tctx_set(), since it is in the
......
......@@ -18,16 +18,19 @@ would create a dependency on xsltproc in packaged releases, hence the
requirement to either run 'make dist' or avoid installing docs via the various
install_* targets documented below.
=== Advanced configuration =====================================================
## Advanced configuration
The 'configure' script supports numerous options that allow control of which
functionality is enabled, where jemalloc is installed, etc. Optionally, pass
any of the following arguments (not a definitive list) to 'configure':
--help
* `--help`
Print a definitive list of options.
--prefix=<install-root-dir>
* `--prefix=<install-root-dir>`
Set the base directory in which to install. For example:
./configure --prefix=/usr/local
......@@ -35,11 +38,29 @@ any of the following arguments (not a definitive list) to 'configure':
will cause files to be installed into /usr/local/include, /usr/local/lib,
and /usr/local/man.
--with-rpath=<colon-separated-rpath>
* `--with-version=(<major>.<minor>.<bugfix>-<nrev>-g<gid>|VERSION)`
The VERSION file is mandatory for successful configuration, and the
following steps are taken to assure its presence:
1) If --with-version=<major>.<minor>.<bugfix>-<nrev>-g<gid> is specified,
generate VERSION using the specified value.
2) If --with-version is not specified in either form and the source
directory is inside a git repository, try to generate VERSION via 'git
describe' invocations that pattern-match release tags.
3) If VERSION is missing, generate it with a bogus version:
0.0.0-0-g0000000000000000000000000000000000000000
Note that --with-version=VERSION bypasses (1) and (2), which simplifies
VERSION configuration when embedding a jemalloc release into another
project's git repository.
* `--with-rpath=<colon-separated-rpath>`
Embed one or more library paths, so that libjemalloc can find the libraries
it is linked to. This works only on ELF-based systems.
--with-mangling=<map>
* `--with-mangling=<map>`
Mangle public symbols specified in <map> which is a comma-separated list of
name:mangled pairs.
......@@ -52,7 +73,8 @@ any of the following arguments (not a definitive list) to 'configure':
--with-jemalloc-prefix, and mangled symbols are then ignored when applying
the prefix.
--with-jemalloc-prefix=<prefix>
* `--with-jemalloc-prefix=<prefix>`
Prefix all public APIs with <prefix>. For example, if <prefix> is
"prefix_", API changes like the following occur:
......@@ -68,55 +90,46 @@ any of the following arguments (not a definitive list) to 'configure':
jemalloc overlays the default malloc zone, but makes no attempt to actually
replace the "malloc", "calloc", etc. symbols.
--without-export
* `--without-export`
Don't export public APIs. This can be useful when building jemalloc as a
static library, or to avoid exporting public APIs when using the zone
allocator on OSX.
--with-private-namespace=<prefix>
* `--with-private-namespace=<prefix>`
Prefix all library-private APIs with <prefix>je_. For shared libraries,
symbol visibility mechanisms prevent these symbols from being exported, but
for static libraries, naming collisions are a real possibility. By
default, <prefix> is empty, which results in a symbol prefix of je_ .
--with-install-suffix=<suffix>
* `--with-install-suffix=<suffix>`
Append <suffix> to the base name of all installed files, such that multiple
versions of jemalloc can coexist in the same installation directory. For
example, libjemalloc.so.0 becomes libjemalloc<suffix>.so.0.
--disable-cc-silence
Disable code that silences non-useful compiler warnings. This is mainly
useful during development when auditing the set of warnings that are being
silenced.
* `--with-malloc-conf=<malloc_conf>`
--enable-debug
Enable assertions and validation code. This incurs a substantial
performance hit, but is very useful during application development.
Implies --enable-ivsalloc.
Embed `<malloc_conf>` as a run-time options string that is processed prior to
the malloc_conf global variable, the /etc/malloc.conf symlink, and the
MALLOC_CONF environment variable. For example, to change the default decay
time to 30 seconds:
--with-malloc-conf=decay_ms:30000
--enable-code-coverage
Enable code coverage support, for use during jemalloc test development.
Additional testing targets are available if this option is enabled:
* `--enable-debug`
coverage
coverage_unit
coverage_integration
coverage_stress
Enable assertions and validation code. This incurs a substantial
performance hit, but is very useful during application development.
These targets do not clear code coverage results from previous runs, and
there are interactions between the various coverage targets, so it is
usually advisable to run 'make clean' between repeated code coverage runs.
* `--disable-stats`
--disable-stats
Disable statistics gathering functionality. See the "opt.stats_print"
option documentation for usage details.
--enable-ivsalloc
Enable validation code, which verifies that pointers reside within
jemalloc-owned chunks before dereferencing them. This incurs a minor
performance hit.
* `--enable-prof`
--enable-prof
Enable heap profiling and leak detection functionality. See the "opt.prof"
option documentation for usage details. When enabled, there are several
approaches to backtracing, and the configure script chooses the first one
......@@ -126,66 +139,55 @@ any of the following arguments (not a definitive list) to 'configure':
+ libgcc (unless --disable-prof-libgcc)
+ gcc intrinsics (unless --disable-prof-gcc)
--enable-prof-libunwind
* `--enable-prof-libunwind`
Use the libunwind library (http://www.nongnu.org/libunwind/) for stack
backtracing.
--disable-prof-libgcc
* `--disable-prof-libgcc`
Disable the use of libgcc's backtracing functionality.
--disable-prof-gcc
* `--disable-prof-gcc`
Disable the use of gcc intrinsics for backtracing.
--with-static-libunwind=<libunwind.a>
* `--with-static-libunwind=<libunwind.a>`
Statically link against the specified libunwind.a rather than dynamically
linking with -lunwind.
--disable-tcache
Disable thread-specific caches for small objects. Objects are cached and
released in bulk, thus reducing the total number of mutex operations. See
the "opt.tcache" option for usage details.
* `--disable-fill`
--disable-munmap
Disable virtual memory deallocation via munmap(2); instead keep track of
the virtual memory for later use. munmap() is disabled by default (i.e.
--disable-munmap is implied) on Linux, which has a quirk in its virtual
memory allocation algorithm that causes semi-permanent VM map holes under
normal jemalloc operation.
Disable support for junk/zero filling of memory. See the "opt.junk" and
"opt.zero" option documentation for usage details.
--disable-fill
Disable support for junk/zero filling of memory, quarantine, and redzones.
See the "opt.junk", "opt.zero", "opt.quarantine", and "opt.redzone" option
documentation for usage details.
* `--disable-zone-allocator`
--disable-valgrind
Disable support for Valgrind.
--disable-zone-allocator
Disable zone allocator for Darwin. This means jemalloc won't be hooked as
the default allocator on OSX/iOS.
--enable-utrace
* `--enable-utrace`
Enable utrace(2)-based allocation tracing. This feature is not broadly
portable (FreeBSD has it, but Linux and OS X do not).
--enable-xmalloc
* `--enable-xmalloc`
Enable support for optional immediate termination due to out-of-memory
errors, as is commonly implemented by "xmalloc" wrapper function for malloc.
See the "opt.xmalloc" option documentation for usage details.
--enable-lazy-lock
* `--enable-lazy-lock`
Enable code that wraps pthread_create() to detect when an application
switches from single-threaded to multi-threaded mode, so that it can avoid
mutex locking/unlocking operations while in single-threaded mode. In
practice, this feature usually has little impact on performance unless
thread-specific caching is disabled.
--disable-tls
Disable thread-local storage (TLS), which allows for fast access to
thread-local variables via the __thread keyword. If TLS is available,
jemalloc uses it for several purposes.
* `--disable-cache-oblivious`
--disable-cache-oblivious
Disable cache-oblivious large allocation alignment for large allocation
requests with no alignment constraints. If this feature is disabled, all
large allocations are page-aligned as an implementation artifact, which can
......@@ -194,56 +196,51 @@ any of the following arguments (not a definitive list) to 'configure':
most extreme case increases physical memory usage for the 16 KiB size class
to 20 KiB.
--with-xslroot=<path>
Specify where to find DocBook XSL stylesheets when building the
documentation.
* `--disable-syscall`
--with-lg-page=<lg-page>
Specify the base 2 log of the system page size. This option is only useful
when cross compiling, since the configure script automatically determines
the host's page size by default.
Disable use of syscall(2) rather than {open,read,write,close}(2). This is
intended as a workaround for systems that place security limitations on
syscall(2).
--with-lg-page-sizes=<lg-page-sizes>
Specify the comma-separated base 2 logs of the page sizes to support. This
option may be useful when cross-compiling in combination with
--with-lg-page, but its primary use case is for integration with FreeBSD's
libc, wherein jemalloc is embedded.
* `--disable-cxx`
Disable C++ integration. This will cause new and delete operator
implementations to be omitted.
--with-lg-size-class-group=<lg-size-class-group>
Specify the base 2 log of how many size classes to use for each doubling in
size. By default jemalloc uses <lg-size-class-group>=2, which results in
e.g. the following size classes:
* `--with-xslroot=<path>`
[...], 64,
80, 96, 112, 128,
160, [...]
Specify where to find DocBook XSL stylesheets when building the
documentation.
* `--with-lg-page=<lg-page>`
Specify the base 2 log of the allocator page size, which must in turn be at
least as large as the system page size. By default the configure script
determines the host's page size and sets the allocator page size equal to
the system page size, so this option need not be specified unless the
system page size may change between configuration and execution, e.g. when
cross compiling.
<lg-size-class-group>=3 results in e.g. the following size classes:
* `--with-lg-page-sizes=<lg-page-sizes>`
[...], 64,
72, 80, 88, 96, 104, 112, 120, 128,
144, [...]
Specify the comma-separated base 2 logs of the page sizes to support. This
option may be useful when cross compiling in combination with
`--with-lg-page`, but its primary use case is for integration with FreeBSD's
libc, wherein jemalloc is embedded.
The minimal <lg-size-class-group>=0 causes jemalloc to only provide size
classes that are powers of 2:
* `--with-lg-hugepage=<lg-hugepage>`
[...],
64,
128,
256,
[...]
Specify the base 2 log of the system huge page size. This option is useful
when cross compiling, or when overriding the default for systems that do
not explicitly support huge pages.
An implementation detail currently limits the total number of small size
classes to 255, and a compilation error will result if the
<lg-size-class-group> you specify cannot be supported. The limit is
roughly <lg-size-class-group>=4, depending on page size.
* `--with-lg-quantum=<lg-quantum>`
--with-lg-quantum=<lg-quantum>
Specify the base 2 log of the minimum allocation alignment. jemalloc needs
to know the minimum alignment that meets the following C standard
requirement (quoted from the April 12, 2011 draft of the C11 standard):
The pointer returned if the allocation succeeds is suitably aligned so
> The pointer returned if the allocation succeeds is suitably aligned so
that it may be assigned to a pointer to any type of object with a
fundamental alignment requirement and then used to access such an object
or an array of such objects in the space allocated [...]
......@@ -251,71 +248,82 @@ any of the following arguments (not a definitive list) to 'configure':
This setting is architecture-specific, and although jemalloc includes known
safe values for the most commonly used modern architectures, there is a
wrinkle related to GNU libc (glibc) that may impact your choice of
<lg-quantum>. On most modern architectures, this mandates 16-byte alignment
(<lg-quantum>=4), but the glibc developers chose not to meet this
<lg-quantum>. On most modern architectures, this mandates 16-byte
alignment (<lg-quantum>=4), but the glibc developers chose not to meet this
requirement for performance reasons. An old discussion can be found at
https://sourceware.org/bugzilla/show_bug.cgi?id=206 . Unlike glibc,
<https://sourceware.org/bugzilla/show_bug.cgi?id=206> . Unlike glibc,
jemalloc does follow the C standard by default (caveat: jemalloc
technically cheats if --with-lg-tiny-min is smaller than
--with-lg-quantum), but the fact that Linux systems already work around
this allocator noncompliance means that it is generally safe in practice to
let jemalloc's minimum alignment follow glibc's lead. If you specify
--with-lg-quantum=3 during configuration, jemalloc will provide additional
size classes that are not 16-byte-aligned (24, 40, and 56, assuming
--with-lg-size-class-group=2).
--with-lg-tiny-min=<lg-tiny-min>
Specify the base 2 log of the minimum tiny size class to support. Tiny
size classes are powers of 2 less than the quantum, and are only
incorporated if <lg-tiny-min> is less than <lg-quantum> (see
--with-lg-quantum). Tiny size classes technically violate the C standard
requirement for minimum alignment, and crashes could conceivably result if
the compiler were to generate instructions that made alignment assumptions,
both because illegal instruction traps could result, and because accesses
could straddle page boundaries and cause segmentation faults due to
accessing unmapped addresses.
The default of <lg-tiny-min>=3 works well in practice even on architectures
that technically require 16-byte alignment, probably for the same reason
--with-lg-quantum=3 works. Smaller tiny size classes can, and will, cause
crashes (see https://bugzilla.mozilla.org/show_bug.cgi?id=691003 for an
example).
This option is rarely useful, and is mainly provided as documentation of a
subtle implementation detail. If you do use this option, specify a
value in [3, ..., <lg-quantum>].
technically cheats for size classes smaller than the quantum), but the fact
that Linux systems already work around this allocator noncompliance means
that it is generally safe in practice to let jemalloc's minimum alignment
follow glibc's lead. If you specify `--with-lg-quantum=3` during
configuration, jemalloc will provide additional size classes that are not
16-byte-aligned (24, 40, and 56).
* `--with-lg-vaddr=<lg-vaddr>`
Specify the number of significant virtual address bits. By default, the
configure script attempts to detect virtual address size on those platforms
where it knows how, and picks a default otherwise. This option may be
useful when cross-compiling.
* `--disable-initial-exec-tls`
Disable the initial-exec TLS model for jemalloc's internal thread-local
storage (on those platforms that support explicit settings). This can allow
jemalloc to be dynamically loaded after program startup (e.g. using dlopen).
Note that in this case, there will be two malloc implementations operating
in the same process, which will almost certainly result in confusing runtime
crashes if pointers leak from one implementation to the other.
The following environment variables (not a definitive list) impact configure's
behavior:
CFLAGS="?"
Pass these flags to the compiler. You probably shouldn't define this unless
you know what you are doing. (Use EXTRA_CFLAGS instead.)
* `CFLAGS="?"`
* `CXXFLAGS="?"`
Pass these flags to the C/C++ compiler. Any flags set by the configure
script are prepended, which means explicitly set flags generally take
precedence. Take care when specifying flags such as -Werror, because
configure tests may be affected in undesirable ways.
* `EXTRA_CFLAGS="?"`
* `EXTRA_CXXFLAGS="?"`
EXTRA_CFLAGS="?"
Append these flags to CFLAGS. This makes it possible to add flags such as
-Werror, while allowing the configure script to determine what other flags
are appropriate for the specified configuration.
Append these flags to CFLAGS/CXXFLAGS, without passing them to the
compiler(s) during configuration. This makes it possible to add flags such
as -Werror, while allowing the configure script to determine what other
flags are appropriate for the specified configuration.
The configure script specifically checks whether an optimization flag (-O*)
is specified in EXTRA_CFLAGS, and refrains from specifying an optimization
level if it finds that one has already been specified.
* `CPPFLAGS="?"`
CPPFLAGS="?"
Pass these flags to the C preprocessor. Note that CFLAGS is not passed to
'cpp' when 'configure' is looking for include files, so you must use
CPPFLAGS instead if you need to help 'configure' find header files.
LD_LIBRARY_PATH="?"
* `LD_LIBRARY_PATH="?"`
'ld' uses this colon-separated list to find libraries.
LDFLAGS="?"
* `LDFLAGS="?"`
Pass these flags when linking.
PATH="?"
* `PATH="?"`
'configure' uses this to find programs.
=== Advanced compilation =======================================================
In some cases it may be necessary to work around configuration results that do
not match reality. For example, Linux 4.5 added support for the MADV_FREE flag
to madvise(2), which can cause problems if building on a host with MADV_FREE
support and deploying to a target without. To work around this, use a cache
file to override the relevant configuration variable defined in configure.ac,
e.g.:
echo "je_cv_madv_free=no" > config.cache && ./configure -C
## Advanced compilation
To build only parts of jemalloc, use the following targets:
......@@ -332,6 +340,7 @@ To install only parts of jemalloc, use the following targets:
install_include
install_lib_shared
install_lib_static
install_lib_pc
install_lib
install_doc_html
install_doc_man
......@@ -343,40 +352,51 @@ To clean up build results to varying degrees, use the following make targets:
distclean
relclean
=== Advanced installation ======================================================
## Advanced installation
Optionally, define make variables when invoking make, including (not
exclusively):
INCLUDEDIR="?"
* `INCLUDEDIR="?"`
Use this as the installation prefix for header files.
LIBDIR="?"
* `LIBDIR="?"`
Use this as the installation prefix for libraries.
MANDIR="?"
* `MANDIR="?"`
Use this as the installation prefix for man pages.
DESTDIR="?"
* `DESTDIR="?"`
Prepend DESTDIR to INCLUDEDIR, LIBDIR, DATADIR, and MANDIR. This is useful
when installing to a different path than was specified via --prefix.
CC="?"
* `CC="?"`
Use this to invoke the C compiler.
CFLAGS="?"
* `CFLAGS="?"`
Pass these flags to the compiler.
CPPFLAGS="?"
* `CPPFLAGS="?"`
Pass these flags to the C preprocessor.
LDFLAGS="?"
* `LDFLAGS="?"`
Pass these flags when linking.
PATH="?"
* `PATH="?"`
Use this to search for programs used during configuration and building.
=== Development ================================================================
## Development
If you intend to make non-trivial changes to jemalloc, use the 'autogen.sh'
script rather than 'configure'. This re-generates 'configure', enables
......@@ -393,7 +413,8 @@ directory, issue configuration and build commands:
../configure --enable-autogen
make
=== Documentation ==============================================================
## Documentation
The manual page is generated in both html and roff formats. Any web browser
can be used to view the html manual. The roff manual page can be formatted
......
......@@ -9,6 +9,7 @@ vpath % .
SHELL := /bin/sh
CC := @CC@
CXX := @CXX@
# Configuration parameters.
DESTDIR =
......@@ -23,12 +24,18 @@ abs_srcroot := @abs_srcroot@
abs_objroot := @abs_objroot@
# Build parameters.
CPPFLAGS := @CPPFLAGS@ -I$(srcroot)include -I$(objroot)include
CFLAGS := @CFLAGS@
CPPFLAGS := @CPPFLAGS@ -I$(objroot)include -I$(srcroot)include
CONFIGURE_CFLAGS := @CONFIGURE_CFLAGS@
SPECIFIED_CFLAGS := @SPECIFIED_CFLAGS@
EXTRA_CFLAGS := @EXTRA_CFLAGS@
CFLAGS := $(strip $(CONFIGURE_CFLAGS) $(SPECIFIED_CFLAGS) $(EXTRA_CFLAGS))
CONFIGURE_CXXFLAGS := @CONFIGURE_CXXFLAGS@
SPECIFIED_CXXFLAGS := @SPECIFIED_CXXFLAGS@
EXTRA_CXXFLAGS := @EXTRA_CXXFLAGS@
CXXFLAGS := $(strip $(CONFIGURE_CXXFLAGS) $(SPECIFIED_CXXFLAGS) $(EXTRA_CXXFLAGS))
LDFLAGS := @LDFLAGS@
EXTRA_LDFLAGS := @EXTRA_LDFLAGS@
LIBS := @LIBS@
TESTLIBS := @TESTLIBS@
RPATH_EXTRA := @RPATH_EXTRA@
SO := @so@
IMPORTLIB := @importlib@
......@@ -48,20 +55,24 @@ cfghdrs_out := @cfghdrs_out@
cfgoutputs_in := $(addprefix $(srcroot),@cfgoutputs_in@)
cfgoutputs_out := @cfgoutputs_out@
enable_autogen := @enable_autogen@
enable_code_coverage := @enable_code_coverage@
enable_prof := @enable_prof@
enable_valgrind := @enable_valgrind@
enable_zone_allocator := @enable_zone_allocator@
MALLOC_CONF := @JEMALLOC_CPREFIX@MALLOC_CONF
link_whole_archive := @link_whole_archive@
DSO_LDFLAGS = @DSO_LDFLAGS@
SOREV = @SOREV@
PIC_CFLAGS = @PIC_CFLAGS@
CTARGET = @CTARGET@
LDTARGET = @LDTARGET@
TEST_LD_MODE = @TEST_LD_MODE@
MKLIB = @MKLIB@
AR = @AR@
ARFLAGS = @ARFLAGS@
DUMP_SYMS = @DUMP_SYMS@
AWK := @AWK@
CC_MM = @CC_MM@
LM := @LM@
INSTALL = @INSTALL@
ifeq (macho, $(ABI))
TEST_LIBRARY_PATH := DYLD_FALLBACK_LIBRARY_PATH="$(objroot)lib"
......@@ -78,18 +89,36 @@ LIBJEMALLOC := $(LIBPREFIX)jemalloc$(install_suffix)
# Lists of files.
BINS := $(objroot)bin/jemalloc-config $(objroot)bin/jemalloc.sh $(objroot)bin/jeprof
C_HDRS := $(objroot)include/jemalloc/jemalloc$(install_suffix).h
C_SRCS := $(srcroot)src/jemalloc.c $(srcroot)src/arena.c \
$(srcroot)src/atomic.c $(srcroot)src/base.c $(srcroot)src/bitmap.c \
$(srcroot)src/chunk.c $(srcroot)src/chunk_dss.c \
$(srcroot)src/chunk_mmap.c $(srcroot)src/ckh.c $(srcroot)src/ctl.c \
$(srcroot)src/extent.c $(srcroot)src/hash.c $(srcroot)src/huge.c \
$(srcroot)src/mb.c $(srcroot)src/mutex.c $(srcroot)src/pages.c \
$(srcroot)src/prof.c $(srcroot)src/quarantine.c $(srcroot)src/rtree.c \
$(srcroot)src/stats.c $(srcroot)src/tcache.c $(srcroot)src/util.c \
$(srcroot)src/tsd.c
ifeq ($(enable_valgrind), 1)
C_SRCS += $(srcroot)src/valgrind.c
endif
C_SRCS := $(srcroot)src/jemalloc.c \
$(srcroot)src/arena.c \
$(srcroot)src/background_thread.c \
$(srcroot)src/base.c \
$(srcroot)src/bin.c \
$(srcroot)src/bitmap.c \
$(srcroot)src/ckh.c \
$(srcroot)src/ctl.c \
$(srcroot)src/div.c \
$(srcroot)src/extent.c \
$(srcroot)src/extent_dss.c \
$(srcroot)src/extent_mmap.c \
$(srcroot)src/hash.c \
$(srcroot)src/hooks.c \
$(srcroot)src/large.c \
$(srcroot)src/log.c \
$(srcroot)src/malloc_io.c \
$(srcroot)src/mutex.c \
$(srcroot)src/mutex_pool.c \
$(srcroot)src/nstime.c \
$(srcroot)src/pages.c \
$(srcroot)src/prng.c \
$(srcroot)src/prof.c \
$(srcroot)src/rtree.c \
$(srcroot)src/stats.c \
$(srcroot)src/sz.c \
$(srcroot)src/tcache.c \
$(srcroot)src/ticker.c \
$(srcroot)src/tsd.c \
$(srcroot)src/witness.c
ifeq ($(enable_zone_allocator), 1)
C_SRCS += $(srcroot)src/zone.c
endif
......@@ -105,6 +134,11 @@ DSOS := $(objroot)lib/$(LIBJEMALLOC).$(SOREV)
ifneq ($(SOREV),$(SO))
DSOS += $(objroot)lib/$(LIBJEMALLOC).$(SO)
endif
ifeq (1, $(link_whole_archive))
LJEMALLOC := -Wl,--whole-archive -L$(objroot)lib -l$(LIBJEMALLOC) -Wl,--no-whole-archive
else
LJEMALLOC := $(objroot)lib/$(LIBJEMALLOC).$(IMPORTLIB)
endif
PC := $(objroot)jemalloc.pc
MAN3 := $(objroot)doc/jemalloc$(install_suffix).3
DOCS_XML := $(objroot)doc/jemalloc$(install_suffix).xml
......@@ -116,53 +150,103 @@ C_TESTLIB_SRCS := $(srcroot)test/src/btalloc.c $(srcroot)test/src/btalloc_0.c \
$(srcroot)test/src/mtx.c $(srcroot)test/src/mq.c \
$(srcroot)test/src/SFMT.c $(srcroot)test/src/test.c \
$(srcroot)test/src/thd.c $(srcroot)test/src/timer.c
C_UTIL_INTEGRATION_SRCS := $(srcroot)src/util.c
TESTS_UNIT := $(srcroot)test/unit/atomic.c \
ifeq (1, $(link_whole_archive))
C_UTIL_INTEGRATION_SRCS :=
C_UTIL_CPP_SRCS :=
else
C_UTIL_INTEGRATION_SRCS := $(srcroot)src/nstime.c $(srcroot)src/malloc_io.c
C_UTIL_CPP_SRCS := $(srcroot)src/nstime.c $(srcroot)src/malloc_io.c
endif
TESTS_UNIT := \
$(srcroot)test/unit/a0.c \
$(srcroot)test/unit/arena_reset.c \
$(srcroot)test/unit/atomic.c \
$(srcroot)test/unit/background_thread.c \
$(srcroot)test/unit/background_thread_enable.c \
$(srcroot)test/unit/base.c \
$(srcroot)test/unit/bitmap.c \
$(srcroot)test/unit/ckh.c \
$(srcroot)test/unit/decay.c \
$(srcroot)test/unit/div.c \
$(srcroot)test/unit/emitter.c \
$(srcroot)test/unit/extent_quantize.c \
$(srcroot)test/unit/fork.c \
$(srcroot)test/unit/hash.c \
$(srcroot)test/unit/hooks.c \
$(srcroot)test/unit/junk.c \
$(srcroot)test/unit/junk_alloc.c \
$(srcroot)test/unit/junk_free.c \
$(srcroot)test/unit/lg_chunk.c \
$(srcroot)test/unit/log.c \
$(srcroot)test/unit/mallctl.c \
$(srcroot)test/unit/malloc_io.c \
$(srcroot)test/unit/math.c \
$(srcroot)test/unit/mq.c \
$(srcroot)test/unit/mtx.c \
$(srcroot)test/unit/pack.c \
$(srcroot)test/unit/pages.c \
$(srcroot)test/unit/ph.c \
$(srcroot)test/unit/prng.c \
$(srcroot)test/unit/prof_accum.c \
$(srcroot)test/unit/prof_active.c \
$(srcroot)test/unit/prof_gdump.c \
$(srcroot)test/unit/prof_idump.c \
$(srcroot)test/unit/prof_reset.c \
$(srcroot)test/unit/prof_tctx.c \
$(srcroot)test/unit/prof_thread_name.c \
$(srcroot)test/unit/ql.c \
$(srcroot)test/unit/qr.c \
$(srcroot)test/unit/quarantine.c \
$(srcroot)test/unit/rb.c \
$(srcroot)test/unit/retained.c \
$(srcroot)test/unit/rtree.c \
$(srcroot)test/unit/SFMT.c \
$(srcroot)test/unit/size_classes.c \
$(srcroot)test/unit/slab.c \
$(srcroot)test/unit/smoothstep.c \
$(srcroot)test/unit/spin.c \
$(srcroot)test/unit/stats.c \
$(srcroot)test/unit/stats_print.c \
$(srcroot)test/unit/ticker.c \
$(srcroot)test/unit/nstime.c \
$(srcroot)test/unit/tsd.c \
$(srcroot)test/unit/util.c \
$(srcroot)test/unit/witness.c \
$(srcroot)test/unit/zero.c
ifeq (@enable_prof@, 1)
TESTS_UNIT += \
$(srcroot)test/unit/arena_reset_prof.c
endif
TESTS_INTEGRATION := $(srcroot)test/integration/aligned_alloc.c \
$(srcroot)test/integration/allocated.c \
$(srcroot)test/integration/sdallocx.c \
$(srcroot)test/integration/extent.c \
$(srcroot)test/integration/mallocx.c \
$(srcroot)test/integration/MALLOCX_ARENA.c \
$(srcroot)test/integration/overflow.c \
$(srcroot)test/integration/posix_memalign.c \
$(srcroot)test/integration/rallocx.c \
$(srcroot)test/integration/sdallocx.c \
$(srcroot)test/integration/thread_arena.c \
$(srcroot)test/integration/thread_tcache_enabled.c \
$(srcroot)test/integration/xallocx.c \
$(srcroot)test/integration/chunk.c
$(srcroot)test/integration/xallocx.c
ifeq (@enable_cxx@, 1)
CPP_SRCS := $(srcroot)src/jemalloc_cpp.cpp
TESTS_INTEGRATION_CPP := $(srcroot)test/integration/cpp/basic.cpp
else
CPP_SRCS :=
TESTS_INTEGRATION_CPP :=
endif
TESTS_STRESS := $(srcroot)test/stress/microbench.c
TESTS := $(TESTS_UNIT) $(TESTS_INTEGRATION) $(TESTS_STRESS)
TESTS := $(TESTS_UNIT) $(TESTS_INTEGRATION) $(TESTS_INTEGRATION_CPP) $(TESTS_STRESS)
PRIVATE_NAMESPACE_HDRS := $(objroot)include/jemalloc/internal/private_namespace.h $(objroot)include/jemalloc/internal/private_namespace_jet.h
PRIVATE_NAMESPACE_GEN_HDRS := $(PRIVATE_NAMESPACE_HDRS:%.h=%.gen.h)
C_SYM_OBJS := $(C_SRCS:$(srcroot)%.c=$(objroot)%.sym.$(O))
C_SYMS := $(C_SRCS:$(srcroot)%.c=$(objroot)%.sym)
C_OBJS := $(C_SRCS:$(srcroot)%.c=$(objroot)%.$(O))
CPP_OBJS := $(CPP_SRCS:$(srcroot)%.cpp=$(objroot)%.$(O))
C_PIC_OBJS := $(C_SRCS:$(srcroot)%.c=$(objroot)%.pic.$(O))
CPP_PIC_OBJS := $(CPP_SRCS:$(srcroot)%.cpp=$(objroot)%.pic.$(O))
C_JET_SYM_OBJS := $(C_SRCS:$(srcroot)%.c=$(objroot)%.jet.sym.$(O))
C_JET_SYMS := $(C_SRCS:$(srcroot)%.c=$(objroot)%.jet.sym)
C_JET_OBJS := $(C_SRCS:$(srcroot)%.c=$(objroot)%.jet.$(O))
C_TESTLIB_UNIT_OBJS := $(C_TESTLIB_SRCS:$(srcroot)%.c=$(objroot)%.unit.$(O))
C_TESTLIB_INTEGRATION_OBJS := $(C_TESTLIB_SRCS:$(srcroot)%.c=$(objroot)%.integration.$(O))
......@@ -172,15 +256,17 @@ C_TESTLIB_OBJS := $(C_TESTLIB_UNIT_OBJS) $(C_TESTLIB_INTEGRATION_OBJS) $(C_UTIL_
TESTS_UNIT_OBJS := $(TESTS_UNIT:$(srcroot)%.c=$(objroot)%.$(O))
TESTS_INTEGRATION_OBJS := $(TESTS_INTEGRATION:$(srcroot)%.c=$(objroot)%.$(O))
TESTS_INTEGRATION_CPP_OBJS := $(TESTS_INTEGRATION_CPP:$(srcroot)%.cpp=$(objroot)%.$(O))
TESTS_STRESS_OBJS := $(TESTS_STRESS:$(srcroot)%.c=$(objroot)%.$(O))
TESTS_OBJS := $(TESTS_UNIT_OBJS) $(TESTS_INTEGRATION_OBJS) $(TESTS_STRESS_OBJS)
TESTS_CPP_OBJS := $(TESTS_INTEGRATION_CPP_OBJS)
.PHONY: all dist build_doc_html build_doc_man build_doc
.PHONY: install_bin install_include install_lib
.PHONY: install_doc_html install_doc_man install_doc install
.PHONY: tests check clean distclean relclean
.SECONDARY : $(TESTS_OBJS)
.SECONDARY : $(PRIVATE_NAMESPACE_GEN_HDRS) $(TESTS_OBJS) $(TESTS_CPP_OBJS)
# Default target.
all: build_lib
......@@ -201,18 +287,32 @@ build_doc: $(DOCS)
# Include generated dependency files.
#
ifdef CC_MM
-include $(C_SYM_OBJS:%.$(O)=%.d)
-include $(C_OBJS:%.$(O)=%.d)
-include $(CPP_OBJS:%.$(O)=%.d)
-include $(C_PIC_OBJS:%.$(O)=%.d)
-include $(CPP_PIC_OBJS:%.$(O)=%.d)
-include $(C_JET_SYM_OBJS:%.$(O)=%.d)
-include $(C_JET_OBJS:%.$(O)=%.d)
-include $(C_TESTLIB_OBJS:%.$(O)=%.d)
-include $(TESTS_OBJS:%.$(O)=%.d)
-include $(TESTS_CPP_OBJS:%.$(O)=%.d)
endif
$(C_SYM_OBJS): $(objroot)src/%.sym.$(O): $(srcroot)src/%.c
$(C_SYM_OBJS): CPPFLAGS += -DJEMALLOC_NO_PRIVATE_NAMESPACE
$(C_SYMS): $(objroot)src/%.sym: $(objroot)src/%.sym.$(O)
$(C_OBJS): $(objroot)src/%.$(O): $(srcroot)src/%.c
$(CPP_OBJS): $(objroot)src/%.$(O): $(srcroot)src/%.cpp
$(C_PIC_OBJS): $(objroot)src/%.pic.$(O): $(srcroot)src/%.c
$(C_PIC_OBJS): CFLAGS += $(PIC_CFLAGS)
$(CPP_PIC_OBJS): $(objroot)src/%.pic.$(O): $(srcroot)src/%.cpp
$(CPP_PIC_OBJS): CXXFLAGS += $(PIC_CFLAGS)
$(C_JET_SYM_OBJS): $(objroot)src/%.jet.sym.$(O): $(srcroot)src/%.c
$(C_JET_SYM_OBJS): CPPFLAGS += -DJEMALLOC_JET -DJEMALLOC_NO_PRIVATE_NAMESPACE
$(C_JET_SYMS): $(objroot)src/%.jet.sym: $(objroot)src/%.jet.sym.$(O)
$(C_JET_OBJS): $(objroot)src/%.jet.$(O): $(srcroot)src/%.c
$(C_JET_OBJS): CFLAGS += -DJEMALLOC_JET
$(C_JET_OBJS): CPPFLAGS += -DJEMALLOC_JET
$(C_TESTLIB_UNIT_OBJS): $(objroot)test/src/%.unit.$(O): $(srcroot)test/src/%.c
$(C_TESTLIB_UNIT_OBJS): CPPFLAGS += -DJEMALLOC_UNIT_TEST
$(C_TESTLIB_INTEGRATION_OBJS): $(objroot)test/src/%.integration.$(O): $(srcroot)test/src/%.c
......@@ -223,112 +323,146 @@ $(C_TESTLIB_STRESS_OBJS): CPPFLAGS += -DJEMALLOC_STRESS_TEST -DJEMALLOC_STRESS_T
$(C_TESTLIB_OBJS): CPPFLAGS += -I$(srcroot)test/include -I$(objroot)test/include
$(TESTS_UNIT_OBJS): CPPFLAGS += -DJEMALLOC_UNIT_TEST
$(TESTS_INTEGRATION_OBJS): CPPFLAGS += -DJEMALLOC_INTEGRATION_TEST
$(TESTS_INTEGRATION_CPP_OBJS): CPPFLAGS += -DJEMALLOC_INTEGRATION_CPP_TEST
$(TESTS_STRESS_OBJS): CPPFLAGS += -DJEMALLOC_STRESS_TEST
$(TESTS_OBJS): $(objroot)test/%.$(O): $(srcroot)test/%.c
$(TESTS_CPP_OBJS): $(objroot)test/%.$(O): $(srcroot)test/%.cpp
$(TESTS_OBJS): CPPFLAGS += -I$(srcroot)test/include -I$(objroot)test/include
$(TESTS_CPP_OBJS): CPPFLAGS += -I$(srcroot)test/include -I$(objroot)test/include
ifneq ($(IMPORTLIB),$(SO))
$(C_OBJS) $(C_JET_OBJS): CPPFLAGS += -DDLLEXPORT
$(CPP_OBJS) $(C_SYM_OBJS) $(C_OBJS) $(C_JET_SYM_OBJS) $(C_JET_OBJS): CPPFLAGS += -DDLLEXPORT
endif
ifndef CC_MM
# Dependencies.
ifndef CC_MM
HEADER_DIRS = $(srcroot)include/jemalloc/internal \
$(objroot)include/jemalloc $(objroot)include/jemalloc/internal
HEADERS = $(wildcard $(foreach dir,$(HEADER_DIRS),$(dir)/*.h))
$(C_OBJS) $(C_PIC_OBJS) $(C_JET_OBJS) $(C_TESTLIB_OBJS) $(TESTS_OBJS): $(HEADERS)
$(TESTS_OBJS): $(objroot)test/include/test/jemalloc_test.h
HEADERS = $(filter-out $(PRIVATE_NAMESPACE_HDRS),$(wildcard $(foreach dir,$(HEADER_DIRS),$(dir)/*.h)))
$(C_SYM_OBJS) $(C_OBJS) $(CPP_OBJS) $(C_PIC_OBJS) $(CPP_PIC_OBJS) $(C_JET_SYM_OBJS) $(C_JET_OBJS) $(C_TESTLIB_OBJS) $(TESTS_OBJS) $(TESTS_CPP_OBJS): $(HEADERS)
$(TESTS_OBJS) $(TESTS_CPP_OBJS): $(objroot)test/include/test/jemalloc_test.h
endif
$(C_OBJS) $(C_PIC_OBJS) $(C_JET_OBJS) $(C_TESTLIB_OBJS) $(TESTS_OBJS): %.$(O):
$(C_OBJS) $(CPP_OBJS) $(C_PIC_OBJS) $(CPP_PIC_OBJS) $(C_TESTLIB_INTEGRATION_OBJS) $(C_UTIL_INTEGRATION_OBJS) $(TESTS_INTEGRATION_OBJS) $(TESTS_INTEGRATION_CPP_OBJS): $(objroot)include/jemalloc/internal/private_namespace.h
$(C_JET_OBJS) $(C_TESTLIB_UNIT_OBJS) $(C_TESTLIB_STRESS_OBJS) $(TESTS_UNIT_OBJS) $(TESTS_STRESS_OBJS): $(objroot)include/jemalloc/internal/private_namespace_jet.h
$(C_SYM_OBJS) $(C_OBJS) $(C_PIC_OBJS) $(C_JET_SYM_OBJS) $(C_JET_OBJS) $(C_TESTLIB_OBJS) $(TESTS_OBJS): %.$(O):
@mkdir -p $(@D)
$(CC) $(CFLAGS) -c $(CPPFLAGS) $(CTARGET) $<
ifdef CC_MM
@$(CC) -MM $(CPPFLAGS) -MT $@ -o $(@:%.$(O)=%.d) $<
endif
$(C_SYMS): %.sym:
@mkdir -p $(@D)
$(DUMP_SYMS) $< | $(AWK) -f $(objroot)include/jemalloc/internal/private_symbols.awk > $@
$(C_JET_SYMS): %.sym:
@mkdir -p $(@D)
$(DUMP_SYMS) $< | $(AWK) -f $(objroot)include/jemalloc/internal/private_symbols_jet.awk > $@
$(objroot)include/jemalloc/internal/private_namespace.gen.h: $(C_SYMS)
$(SHELL) $(srcroot)include/jemalloc/internal/private_namespace.sh $^ > $@
$(objroot)include/jemalloc/internal/private_namespace_jet.gen.h: $(C_JET_SYMS)
$(SHELL) $(srcroot)include/jemalloc/internal/private_namespace.sh $^ > $@
%.h: %.gen.h
@if ! `cmp -s $< $@` ; then echo "cp $< $<"; cp $< $@ ; fi
$(CPP_OBJS) $(CPP_PIC_OBJS) $(TESTS_CPP_OBJS): %.$(O):
@mkdir -p $(@D)
$(CXX) $(CXXFLAGS) -c $(CPPFLAGS) $(CTARGET) $<
ifdef CC_MM
@$(CXX) -MM $(CPPFLAGS) -MT $@ -o $(@:%.$(O)=%.d) $<
endif
ifneq ($(SOREV),$(SO))
%.$(SO) : %.$(SOREV)
@mkdir -p $(@D)
ln -sf $(<F) $@
endif
$(objroot)lib/$(LIBJEMALLOC).$(SOREV) : $(if $(PIC_CFLAGS),$(C_PIC_OBJS),$(C_OBJS))
$(objroot)lib/$(LIBJEMALLOC).$(SOREV) : $(if $(PIC_CFLAGS),$(C_PIC_OBJS),$(C_OBJS)) $(if $(PIC_CFLAGS),$(CPP_PIC_OBJS),$(CPP_OBJS))
@mkdir -p $(@D)
$(CC) $(DSO_LDFLAGS) $(call RPATH,$(RPATH_EXTRA)) $(LDTARGET) $+ $(LDFLAGS) $(LIBS) $(EXTRA_LDFLAGS)
$(objroot)lib/$(LIBJEMALLOC)_pic.$(A) : $(C_PIC_OBJS)
$(objroot)lib/$(LIBJEMALLOC).$(A) : $(C_OBJS)
$(objroot)lib/$(LIBJEMALLOC)_s.$(A) : $(C_OBJS)
$(objroot)lib/$(LIBJEMALLOC)_pic.$(A) : $(C_PIC_OBJS) $(CPP_PIC_OBJS)
$(objroot)lib/$(LIBJEMALLOC).$(A) : $(C_OBJS) $(CPP_OBJS)
$(objroot)lib/$(LIBJEMALLOC)_s.$(A) : $(C_OBJS) $(CPP_OBJS)
$(STATIC_LIBS):
@mkdir -p $(@D)
$(AR) $(ARFLAGS)@AROUT@ $+
$(objroot)test/unit/%$(EXE): $(objroot)test/unit/%.$(O) $(TESTS_UNIT_LINK_OBJS) $(C_JET_OBJS) $(C_TESTLIB_UNIT_OBJS)
$(objroot)test/unit/%$(EXE): $(objroot)test/unit/%.$(O) $(C_JET_OBJS) $(C_TESTLIB_UNIT_OBJS)
@mkdir -p $(@D)
$(CC) $(LDTARGET) $(filter %.$(O),$^) $(call RPATH,$(objroot)lib) $(LDFLAGS) $(filter-out -lm,$(LIBS)) -lm $(TESTLIBS) $(EXTRA_LDFLAGS)
$(CC) $(LDTARGET) $(filter %.$(O),$^) $(call RPATH,$(objroot)lib) $(LDFLAGS) $(filter-out -lm,$(LIBS)) $(LM) $(EXTRA_LDFLAGS)
$(objroot)test/integration/%$(EXE): $(objroot)test/integration/%.$(O) $(C_TESTLIB_INTEGRATION_OBJS) $(C_UTIL_INTEGRATION_OBJS) $(objroot)lib/$(LIBJEMALLOC).$(IMPORTLIB)
@mkdir -p $(@D)
$(CC) $(LDTARGET) $(filter %.$(O),$^) $(call RPATH,$(objroot)lib) $(objroot)lib/$(LIBJEMALLOC).$(IMPORTLIB) $(LDFLAGS) $(filter-out -lm,$(filter -lpthread,$(LIBS))) -lm $(TESTLIBS) $(EXTRA_LDFLAGS)
$(CC) $(TEST_LD_MODE) $(LDTARGET) $(filter %.$(O),$^) $(call RPATH,$(objroot)lib) $(LJEMALLOC) $(LDFLAGS) $(filter-out -lm,$(filter -lrt -lpthread -lstdc++,$(LIBS))) $(LM) $(EXTRA_LDFLAGS)
$(objroot)test/integration/cpp/%$(EXE): $(objroot)test/integration/cpp/%.$(O) $(C_TESTLIB_INTEGRATION_OBJS) $(C_UTIL_INTEGRATION_OBJS) $(objroot)lib/$(LIBJEMALLOC).$(IMPORTLIB)
@mkdir -p $(@D)
$(CXX) $(LDTARGET) $(filter %.$(O),$^) $(call RPATH,$(objroot)lib) $(objroot)lib/$(LIBJEMALLOC).$(IMPORTLIB) $(LDFLAGS) $(filter-out -lm,$(LIBS)) -lm $(EXTRA_LDFLAGS)
$(objroot)test/stress/%$(EXE): $(objroot)test/stress/%.$(O) $(C_JET_OBJS) $(C_TESTLIB_STRESS_OBJS) $(objroot)lib/$(LIBJEMALLOC).$(IMPORTLIB)
@mkdir -p $(@D)
$(CC) $(LDTARGET) $(filter %.$(O),$^) $(call RPATH,$(objroot)lib) $(objroot)lib/$(LIBJEMALLOC).$(IMPORTLIB) $(LDFLAGS) $(filter-out -lm,$(LIBS)) -lm $(TESTLIBS) $(EXTRA_LDFLAGS)
$(CC) $(TEST_LD_MODE) $(LDTARGET) $(filter %.$(O),$^) $(call RPATH,$(objroot)lib) $(objroot)lib/$(LIBJEMALLOC).$(IMPORTLIB) $(LDFLAGS) $(filter-out -lm,$(LIBS)) $(LM) $(EXTRA_LDFLAGS)
build_lib_shared: $(DSOS)
build_lib_static: $(STATIC_LIBS)
build_lib: build_lib_shared build_lib_static
install_bin:
install -d $(BINDIR)
$(INSTALL) -d $(BINDIR)
@for b in $(BINS); do \
echo "install -m 755 $$b $(BINDIR)"; \
install -m 755 $$b $(BINDIR); \
echo "$(INSTALL) -m 755 $$b $(BINDIR)"; \
$(INSTALL) -m 755 $$b $(BINDIR); \
done
install_include:
install -d $(INCLUDEDIR)/jemalloc
$(INSTALL) -d $(INCLUDEDIR)/jemalloc
@for h in $(C_HDRS); do \
echo "install -m 644 $$h $(INCLUDEDIR)/jemalloc"; \
install -m 644 $$h $(INCLUDEDIR)/jemalloc; \
echo "$(INSTALL) -m 644 $$h $(INCLUDEDIR)/jemalloc"; \
$(INSTALL) -m 644 $$h $(INCLUDEDIR)/jemalloc; \
done
install_lib_shared: $(DSOS)
install -d $(LIBDIR)
install -m 755 $(objroot)lib/$(LIBJEMALLOC).$(SOREV) $(LIBDIR)
$(INSTALL) -d $(LIBDIR)
$(INSTALL) -m 755 $(objroot)lib/$(LIBJEMALLOC).$(SOREV) $(LIBDIR)
ifneq ($(SOREV),$(SO))
ln -sf $(LIBJEMALLOC).$(SOREV) $(LIBDIR)/$(LIBJEMALLOC).$(SO)
endif
install_lib_static: $(STATIC_LIBS)
install -d $(LIBDIR)
$(INSTALL) -d $(LIBDIR)
@for l in $(STATIC_LIBS); do \
echo "install -m 755 $$l $(LIBDIR)"; \
install -m 755 $$l $(LIBDIR); \
echo "$(INSTALL) -m 755 $$l $(LIBDIR)"; \
$(INSTALL) -m 755 $$l $(LIBDIR); \
done
install_lib_pc: $(PC)
install -d $(LIBDIR)/pkgconfig
$(INSTALL) -d $(LIBDIR)/pkgconfig
@for l in $(PC); do \
echo "install -m 644 $$l $(LIBDIR)/pkgconfig"; \
install -m 644 $$l $(LIBDIR)/pkgconfig; \
echo "$(INSTALL) -m 644 $$l $(LIBDIR)/pkgconfig"; \
$(INSTALL) -m 644 $$l $(LIBDIR)/pkgconfig; \
done
install_lib: install_lib_shared install_lib_static install_lib_pc
install_doc_html:
install -d $(DATADIR)/doc/jemalloc$(install_suffix)
$(INSTALL) -d $(DATADIR)/doc/jemalloc$(install_suffix)
@for d in $(DOCS_HTML); do \
echo "install -m 644 $$d $(DATADIR)/doc/jemalloc$(install_suffix)"; \
install -m 644 $$d $(DATADIR)/doc/jemalloc$(install_suffix); \
echo "$(INSTALL) -m 644 $$d $(DATADIR)/doc/jemalloc$(install_suffix)"; \
$(INSTALL) -m 644 $$d $(DATADIR)/doc/jemalloc$(install_suffix); \
done
install_doc_man:
install -d $(MANDIR)/man3
$(INSTALL) -d $(MANDIR)/man3
@for d in $(DOCS_MAN3); do \
echo "install -m 644 $$d $(MANDIR)/man3"; \
install -m 644 $$d $(MANDIR)/man3; \
echo "$(INSTALL) -m 644 $$d $(MANDIR)/man3"; \
$(INSTALL) -m 644 $$d $(MANDIR)/man3; \
done
install_doc: install_doc_html install_doc_man
......@@ -336,7 +470,7 @@ install_doc: install_doc_html install_doc_man
install: install_bin install_include install_lib install_doc
tests_unit: $(TESTS_UNIT:$(srcroot)%.c=$(objroot)%$(EXE))
tests_integration: $(TESTS_INTEGRATION:$(srcroot)%.c=$(objroot)%$(EXE))
tests_integration: $(TESTS_INTEGRATION:$(srcroot)%.c=$(objroot)%$(EXE)) $(TESTS_INTEGRATION_CPP:$(srcroot)%.cpp=$(objroot)%$(EXE))
tests_stress: $(TESTS_STRESS:$(srcroot)%.c=$(objroot)%$(EXE))
tests: tests_unit tests_integration tests_stress
......@@ -352,71 +486,48 @@ check_unit: tests_unit check_unit_dir
$(SHELL) $(objroot)test/test.sh $(TESTS_UNIT:$(srcroot)%.c=$(objroot)%)
check_integration_prof: tests_integration check_integration_dir
ifeq ($(enable_prof), 1)
$(MALLOC_CONF)="prof:true" $(SHELL) $(objroot)test/test.sh $(TESTS_INTEGRATION:$(srcroot)%.c=$(objroot)%)
$(MALLOC_CONF)="prof:true,prof_active:false" $(SHELL) $(objroot)test/test.sh $(TESTS_INTEGRATION:$(srcroot)%.c=$(objroot)%)
$(MALLOC_CONF)="prof:true" $(SHELL) $(objroot)test/test.sh $(TESTS_INTEGRATION:$(srcroot)%.c=$(objroot)%) $(TESTS_INTEGRATION_CPP:$(srcroot)%.cpp=$(objroot)%)
$(MALLOC_CONF)="prof:true,prof_active:false" $(SHELL) $(objroot)test/test.sh $(TESTS_INTEGRATION:$(srcroot)%.c=$(objroot)%) $(TESTS_INTEGRATION_CPP:$(srcroot)%.cpp=$(objroot)%)
endif
check_integration_decay: tests_integration check_integration_dir
$(MALLOC_CONF)="dirty_decay_ms:-1,muzzy_decay_ms:-1" $(SHELL) $(objroot)test/test.sh $(TESTS_INTEGRATION:$(srcroot)%.c=$(objroot)%) $(TESTS_INTEGRATION_CPP:$(srcroot)%.cpp=$(objroot)%)
$(MALLOC_CONF)="dirty_decay_ms:0,muzzy_decay_ms:0" $(SHELL) $(objroot)test/test.sh $(TESTS_INTEGRATION:$(srcroot)%.c=$(objroot)%) $(TESTS_INTEGRATION_CPP:$(srcroot)%.cpp=$(objroot)%)
check_integration: tests_integration check_integration_dir
$(SHELL) $(objroot)test/test.sh $(TESTS_INTEGRATION:$(srcroot)%.c=$(objroot)%)
$(SHELL) $(objroot)test/test.sh $(TESTS_INTEGRATION:$(srcroot)%.c=$(objroot)%) $(TESTS_INTEGRATION_CPP:$(srcroot)%.cpp=$(objroot)%)
stress: tests_stress stress_dir
$(SHELL) $(objroot)test/test.sh $(TESTS_STRESS:$(srcroot)%.c=$(objroot)%)
check: tests check_dir check_integration_prof
$(SHELL) $(objroot)test/test.sh $(TESTS_UNIT:$(srcroot)%.c=$(objroot)%) $(TESTS_INTEGRATION:$(srcroot)%.c=$(objroot)%)
ifeq ($(enable_code_coverage), 1)
coverage_unit: check_unit
$(SHELL) $(srcroot)coverage.sh $(srcroot)src jet $(C_JET_OBJS)
$(SHELL) $(srcroot)coverage.sh $(srcroot)test/src unit $(C_TESTLIB_UNIT_OBJS)
$(SHELL) $(srcroot)coverage.sh $(srcroot)test/unit unit $(TESTS_UNIT_OBJS)
coverage_integration: check_integration
$(SHELL) $(srcroot)coverage.sh $(srcroot)src pic $(C_PIC_OBJS)
$(SHELL) $(srcroot)coverage.sh $(srcroot)src integration $(C_UTIL_INTEGRATION_OBJS)
$(SHELL) $(srcroot)coverage.sh $(srcroot)test/src integration $(C_TESTLIB_INTEGRATION_OBJS)
$(SHELL) $(srcroot)coverage.sh $(srcroot)test/integration integration $(TESTS_INTEGRATION_OBJS)
coverage_stress: stress
$(SHELL) $(srcroot)coverage.sh $(srcroot)src pic $(C_PIC_OBJS)
$(SHELL) $(srcroot)coverage.sh $(srcroot)src jet $(C_JET_OBJS)
$(SHELL) $(srcroot)coverage.sh $(srcroot)test/src stress $(C_TESTLIB_STRESS_OBJS)
$(SHELL) $(srcroot)coverage.sh $(srcroot)test/stress stress $(TESTS_STRESS_OBJS)
coverage: check
$(SHELL) $(srcroot)coverage.sh $(srcroot)src pic $(C_PIC_OBJS)
$(SHELL) $(srcroot)coverage.sh $(srcroot)src jet $(C_JET_OBJS)
$(SHELL) $(srcroot)coverage.sh $(srcroot)src integration $(C_UTIL_INTEGRATION_OBJS)
$(SHELL) $(srcroot)coverage.sh $(srcroot)test/src unit $(C_TESTLIB_UNIT_OBJS)
$(SHELL) $(srcroot)coverage.sh $(srcroot)test/src integration $(C_TESTLIB_INTEGRATION_OBJS)
$(SHELL) $(srcroot)coverage.sh $(srcroot)test/src stress $(C_TESTLIB_STRESS_OBJS)
$(SHELL) $(srcroot)coverage.sh $(srcroot)test/unit unit $(TESTS_UNIT_OBJS) $(TESTS_UNIT_AUX_OBJS)
$(SHELL) $(srcroot)coverage.sh $(srcroot)test/integration integration $(TESTS_INTEGRATION_OBJS)
$(SHELL) $(srcroot)coverage.sh $(srcroot)test/stress integration $(TESTS_STRESS_OBJS)
endif
check: check_unit check_integration check_integration_decay check_integration_prof
clean:
rm -f $(PRIVATE_NAMESPACE_HDRS)
rm -f $(PRIVATE_NAMESPACE_GEN_HDRS)
rm -f $(C_SYM_OBJS)
rm -f $(C_SYMS)
rm -f $(C_OBJS)
rm -f $(CPP_OBJS)
rm -f $(C_PIC_OBJS)
rm -f $(CPP_PIC_OBJS)
rm -f $(C_JET_SYM_OBJS)
rm -f $(C_JET_SYMS)
rm -f $(C_JET_OBJS)
rm -f $(C_TESTLIB_OBJS)
rm -f $(C_SYM_OBJS:%.$(O)=%.d)
rm -f $(C_OBJS:%.$(O)=%.d)
rm -f $(C_OBJS:%.$(O)=%.gcda)
rm -f $(C_OBJS:%.$(O)=%.gcno)
rm -f $(CPP_OBJS:%.$(O)=%.d)
rm -f $(C_PIC_OBJS:%.$(O)=%.d)
rm -f $(C_PIC_OBJS:%.$(O)=%.gcda)
rm -f $(C_PIC_OBJS:%.$(O)=%.gcno)
rm -f $(CPP_PIC_OBJS:%.$(O)=%.d)
rm -f $(C_JET_SYM_OBJS:%.$(O)=%.d)
rm -f $(C_JET_OBJS:%.$(O)=%.d)
rm -f $(C_JET_OBJS:%.$(O)=%.gcda)
rm -f $(C_JET_OBJS:%.$(O)=%.gcno)
rm -f $(C_TESTLIB_OBJS:%.$(O)=%.d)
rm -f $(C_TESTLIB_OBJS:%.$(O)=%.gcda)
rm -f $(C_TESTLIB_OBJS:%.$(O)=%.gcno)
rm -f $(TESTS_OBJS:%.$(O)=%$(EXE))
rm -f $(TESTS_OBJS)
rm -f $(TESTS_OBJS:%.$(O)=%.d)
rm -f $(TESTS_OBJS:%.$(O)=%.gcda)
rm -f $(TESTS_OBJS:%.$(O)=%.gcno)
rm -f $(TESTS_OBJS:%.$(O)=%.out)
rm -f $(TESTS_CPP_OBJS:%.$(O)=%$(EXE))
rm -f $(TESTS_CPP_OBJS)
rm -f $(TESTS_CPP_OBJS:%.$(O)=%.d)
rm -f $(TESTS_CPP_OBJS:%.$(O)=%.out)
rm -f $(DSOS) $(STATIC_LIBS)
rm -f $(objroot)*.gcov.*
distclean: clean
rm -f $(objroot)bin/jemalloc-config
......
......@@ -3,12 +3,12 @@ fragmentation avoidance and scalable concurrency support. jemalloc first came
into use as the FreeBSD libc allocator in 2005, and since then it has found its
way into numerous applications that rely on its predictable behavior. In 2010
jemalloc development efforts broadened to include developer support features
such as heap profiling, Valgrind integration, and extensive monitoring/tuning
hooks. Modern jemalloc releases continue to be integrated back into FreeBSD,
and therefore versatility remains critical. Ongoing development efforts trend
toward making jemalloc among the best allocators for a broad range of demanding
applications, and eliminating/mitigating weaknesses that have practical
repercussions for real world applications.
such as heap profiling and extensive monitoring/tuning hooks. Modern jemalloc
releases continue to be integrated back into FreeBSD, and therefore versatility
remains critical. Ongoing development efforts trend toward making jemalloc
among the best allocators for a broad range of demanding applications, and
eliminating/mitigating weaknesses that have practical repercussions for real
world applications.
The COPYING file contains copyright and licensing information.
......@@ -17,4 +17,4 @@ jemalloc.
The ChangeLog file contains a brief summary of changes for each release.
URL: http://www.canonware.com/jemalloc/
URL: http://jemalloc.net/
This document summarizes the common approaches for performance fine tuning with
jemalloc (as of 5.1.0). The default configuration of jemalloc tends to work
reasonably well in practice, and most applications should not have to tune any
options. However, in order to cover a wide range of applications and avoid
pathological cases, the default setting is sometimes kept conservative and
suboptimal, even for many common workloads. When jemalloc is properly tuned for
a specific application / workload, it is common to improve system level metrics
by a few percent, or make favorable trade-offs.
## Notable runtime options for performance tuning
Runtime options can be set via
[malloc_conf](http://jemalloc.net/jemalloc.3.html#tuning).
* [background_thread](http://jemalloc.net/jemalloc.3.html#background_thread)
Enabling jemalloc background threads generally improves the tail latency for
application threads, since unused memory purging is shifted to the dedicated
background threads. In addition, unintended purging delay caused by
application inactivity is avoided with background threads.
Suggested: `background_thread:true` when jemalloc managed threads can be
allowed.
* [metadata_thp](http://jemalloc.net/jemalloc.3.html#opt.metadata_thp)
Allowing jemalloc to utilize transparent huge pages for its internal
metadata usually reduces TLB misses significantly, especially for programs
with large memory footprint and frequent allocation / deallocation
activities. Metadata memory usage may increase due to the use of huge
pages.
Suggested for allocation intensive programs: `metadata_thp:auto` or
`metadata_thp:always`, which is expected to improve CPU utilization at a
small memory cost.
* [dirty_decay_ms](http://jemalloc.net/jemalloc.3.html#opt.dirty_decay_ms) and
[muzzy_decay_ms](http://jemalloc.net/jemalloc.3.html#opt.muzzy_decay_ms)
Decay time determines how fast jemalloc returns unused pages back to the
operating system, and therefore provides a fairly straightforward trade-off
between CPU and memory usage. Shorter decay time purges unused pages faster
to reduces memory usage (usually at the cost of more CPU cycles spent on
purging), and vice versa.
Suggested: tune the values based on the desired trade-offs.
* [narenas](http://jemalloc.net/jemalloc.3.html#opt.narenas)
By default jemalloc uses multiple arenas to reduce internal lock contention.
However high arena count may also increase overall memory fragmentation,
since arenas manage memory independently. When high degree of parallelism
is not expected at the allocator level, lower number of arenas often
improves memory usage.
Suggested: if low parallelism is expected, try lower arena count while
monitoring CPU and memory usage.
* [percpu_arena](http://jemalloc.net/jemalloc.3.html#opt.percpu_arena)
Enable dynamic thread to arena association based on running CPU. This has
the potential to improve locality, e.g. when thread to CPU affinity is
present.
Suggested: try `percpu_arena:percpu` or `percpu_arena:phycpu` if
thread migration between processors is expected to be infrequent.
Examples:
* High resource consumption application, prioritizing CPU utilization:
`background_thread:true,metadata_thp:auto` combined with relaxed decay time
(increased `dirty_decay_ms` and / or `muzzy_decay_ms`,
e.g. `dirty_decay_ms:30000,muzzy_decay_ms:30000`).
* High resource consumption application, prioritizing memory usage:
`background_thread:true` combined with shorter decay time (decreased
`dirty_decay_ms` and / or `muzzy_decay_ms`,
e.g. `dirty_decay_ms:5000,muzzy_decay_ms:5000`), and lower arena count
(e.g. number of CPUs).
* Low resource consumption application:
`narenas:1,lg_tcache_max:13` combined with shorter decay time (decreased
`dirty_decay_ms` and / or `muzzy_decay_ms`,e.g.
`dirty_decay_ms:1000,muzzy_decay_ms:0`).
* Extremely conservative -- minimize memory usage at all costs, only suitable when
allocation activity is very rare:
`narenas:1,tcache:false,dirty_decay_ms:0,muzzy_decay_ms:0`
Note that it is recommended to combine the options with `abort_conf:true` which
aborts immediately on illegal options.
## Beyond runtime options
In addition to the runtime options, there are a number of programmatic ways to
improve application performance with jemalloc.
* [Explicit arenas](http://jemalloc.net/jemalloc.3.html#arenas.create)
Manually created arenas can help performance in various ways, e.g. by
managing locality and contention for specific usages. For example,
applications can explicitly allocate frequently accessed objects from a
dedicated arena with
[mallocx()](http://jemalloc.net/jemalloc.3.html#MALLOCX_ARENA) to improve
locality. In addition, explicit arenas often benefit from individually
tuned options, e.g. relaxed [decay
time](http://jemalloc.net/jemalloc.3.html#arena.i.dirty_decay_ms) if
frequent reuse is expected.
* [Extent hooks](http://jemalloc.net/jemalloc.3.html#arena.i.extent_hooks)
Extent hooks allow customization for managing underlying memory. One use
case for performance purpose is to utilize huge pages -- for example,
[HHVM](https://github.com/facebook/hhvm/blob/master/hphp/util/alloc.cpp)
uses explicit arenas with customized extent hooks to manage 1GB huge pages
for frequently accessed data, which reduces TLB misses significantly.
* [Explicit thread-to-arena
binding](http://jemalloc.net/jemalloc.3.html#thread.arena)
It is common for some threads in an application to have different memory
access / allocation patterns. Threads with heavy workloads often benefit
from explicit binding, e.g. binding very active threads to dedicated arenas
may reduce contention at the allocator level.
4.0.3-0-ge9192eacf8935e29fc62fddc2701f7942b1cc02c
......@@ -18,6 +18,7 @@ Options:
--cc : Print compiler used to build jemalloc.
--cflags : Print compiler flags used to build jemalloc.
--cppflags : Print preprocessor flags used to build jemalloc.
--cxxflags : Print C++ compiler flags used to build jemalloc.
--ldflags : Print library flags used to build jemalloc.
--libs : Print libraries jemalloc was linked against.
EOF
......@@ -67,6 +68,9 @@ case "$1" in
--cppflags)
echo "@CPPFLAGS@"
;;
--cxxflags)
echo "@CXXFLAGS@"
;;
--ldflags)
echo "@LDFLAGS@ @EXTRA_LDFLAGS@"
;;
......
......@@ -71,6 +71,7 @@
use strict;
use warnings;
use Getopt::Long;
use Cwd;
my $JEPROF_VERSION = "@jemalloc_version@";
my $PPROF_VERSION = "2.0";
......@@ -95,7 +96,7 @@ my @EVINCE = ("evince"); # could also be xpdf or perhaps acroread
my @KCACHEGRIND = ("kcachegrind");
my @PS2PDF = ("ps2pdf");
# These are used for dynamic profiles
my @URL_FETCHER = ("curl", "-s");
my @URL_FETCHER = ("curl", "-s", "--fail");
# These are the web pages that servers need to support for dynamic profiles
my $HEAP_PAGE = "/pprof/heap";
......@@ -223,12 +224,14 @@ Call-graph Options:
--nodefraction=<f> Hide nodes below <f>*total [default=.005]
--edgefraction=<f> Hide edges below <f>*total [default=.001]
--maxdegree=<n> Max incoming/outgoing edges per node [default=8]
--focus=<regexp> Focus on nodes matching <regexp>
--focus=<regexp> Focus on backtraces with nodes matching <regexp>
--thread=<n> Show profile for thread <n>
--ignore=<regexp> Ignore nodes matching <regexp>
--ignore=<regexp> Ignore backtraces with nodes matching <regexp>
--scale=<n> Set GV scaling [default=0]
--heapcheck Make nodes with non-0 object counts
(i.e. direct leak generators) more visible
--retain=<regexp> Retain only nodes that match <regexp>
--exclude=<regexp> Exclude all nodes that match <regexp>
Miscellaneous:
--tools=<prefix or binary:fullpath>[,...] \$PATH for object tool pathnames
......@@ -339,6 +342,8 @@ sub Init() {
$main::opt_ignore = '';
$main::opt_scale = 0;
$main::opt_heapcheck = 0;
$main::opt_retain = '';
$main::opt_exclude = '';
$main::opt_seconds = 30;
$main::opt_lib = "";
......@@ -410,6 +415,8 @@ sub Init() {
"ignore=s" => \$main::opt_ignore,
"scale=i" => \$main::opt_scale,
"heapcheck" => \$main::opt_heapcheck,
"retain=s" => \$main::opt_retain,
"exclude=s" => \$main::opt_exclude,
"inuse_space!" => \$main::opt_inuse_space,
"inuse_objects!" => \$main::opt_inuse_objects,
"alloc_space!" => \$main::opt_alloc_space,
......@@ -1160,8 +1167,21 @@ sub PrintSymbolizedProfile {
}
print '---', "\n";
$PROFILE_PAGE =~ m,[^/]+$,; # matches everything after the last slash
my $profile_marker = $&;
my $profile_marker;
if ($main::profile_type eq 'heap') {
$HEAP_PAGE =~ m,[^/]+$,; # matches everything after the last slash
$profile_marker = $&;
} elsif ($main::profile_type eq 'growth') {
$GROWTH_PAGE =~ m,[^/]+$,; # matches everything after the last slash
$profile_marker = $&;
} elsif ($main::profile_type eq 'contention') {
$CONTENTION_PAGE =~ m,[^/]+$,; # matches everything after the last slash
$profile_marker = $&;
} else { # elsif ($main::profile_type eq 'cpu')
$PROFILE_PAGE =~ m,[^/]+$,; # matches everything after the last slash
$profile_marker = $&;
}
print '--- ', $profile_marker, "\n";
if (defined($main::collected_profile)) {
# if used with remote fetch, simply dump the collected profile to output.
......@@ -1171,6 +1191,12 @@ sub PrintSymbolizedProfile {
}
close(SRC);
} else {
# --raw/http: For everything to work correctly for non-remote profiles, we
# would need to extend PrintProfileData() to handle all possible profile
# types, re-enable the code that is currently disabled in ReadCPUProfile()
# and FixCallerAddresses(), and remove the remote profile dumping code in
# the block above.
die "--raw/http: jeprof can only dump remote profiles for --raw\n";
# dump a cpu-format profile to standard out
PrintProfileData($profile);
}
......@@ -2821,6 +2847,43 @@ sub ExtractCalls {
return $calls;
}
sub FilterFrames {
my $symbols = shift;
my $profile = shift;
if ($main::opt_retain eq '' && $main::opt_exclude eq '') {
return $profile;
}
my $result = {};
foreach my $k (keys(%{$profile})) {
my $count = $profile->{$k};
my @addrs = split(/\n/, $k);
my @path = ();
foreach my $a (@addrs) {
my $sym;
if (exists($symbols->{$a})) {
$sym = $symbols->{$a}->[0];
} else {
$sym = $a;
}
if ($main::opt_retain ne '' && $sym !~ m/$main::opt_retain/) {
next;
}
if ($main::opt_exclude ne '' && $sym =~ m/$main::opt_exclude/) {
next;
}
push(@path, $a);
}
if (scalar(@path) > 0) {
my $reduced_path = join("\n", @path);
AddEntry($result, $reduced_path, $count);
}
}
return $result;
}
sub RemoveUninterestingFrames {
my $symbols = shift;
my $profile = shift;
......@@ -2829,21 +2892,23 @@ sub RemoveUninterestingFrames {
my %skip = ();
my $skip_regexp = 'NOMATCH';
if ($main::profile_type eq 'heap' || $main::profile_type eq 'growth') {
foreach my $name ('calloc',
foreach my $name ('@JEMALLOC_PREFIX@calloc',
'cfree',
'malloc',
'free',
'memalign',
'posix_memalign',
'aligned_alloc',
'@JEMALLOC_PREFIX@malloc',
'newImpl',
'void* newImpl',
'@JEMALLOC_PREFIX@free',
'@JEMALLOC_PREFIX@memalign',
'@JEMALLOC_PREFIX@posix_memalign',
'@JEMALLOC_PREFIX@aligned_alloc',
'pvalloc',
'valloc',
'realloc',
'mallocx', # jemalloc
'rallocx', # jemalloc
'xallocx', # jemalloc
'dallocx', # jemalloc
'sdallocx', # jemalloc
'@JEMALLOC_PREFIX@valloc',
'@JEMALLOC_PREFIX@realloc',
'@JEMALLOC_PREFIX@mallocx',
'@JEMALLOC_PREFIX@rallocx',
'@JEMALLOC_PREFIX@xallocx',
'@JEMALLOC_PREFIX@dallocx',
'@JEMALLOC_PREFIX@sdallocx',
'tc_calloc',
'tc_cfree',
'tc_malloc',
......@@ -2965,6 +3030,9 @@ sub RemoveUninterestingFrames {
my $reduced_path = join("\n", @path);
AddEntry($result, $reduced_path, $count);
}
$result = FilterFrames($symbols, $result);
return $result;
}
......@@ -3274,7 +3342,7 @@ sub ResolveRedirectionForCurl {
# Add a timeout flat to URL_FETCHER. Returns a new list.
sub AddFetchTimeout {
my $timeout = shift;
my @fetcher = shift;
my @fetcher = @_;
if (defined($timeout)) {
if (join(" ", @fetcher) =~ m/\bcurl -s/) {
push(@fetcher, "--max-time", sprintf("%d", $timeout));
......@@ -3320,6 +3388,27 @@ sub ReadSymbols {
return $map;
}
sub URLEncode {
my $str = shift;
$str =~ s/([^A-Za-z0-9\-_.!~*'()])/ sprintf "%%%02x", ord $1 /eg;
return $str;
}
sub AppendSymbolFilterParams {
my $url = shift;
my @params = ();
if ($main::opt_retain ne '') {
push(@params, sprintf("retain=%s", URLEncode($main::opt_retain)));
}
if ($main::opt_exclude ne '') {
push(@params, sprintf("exclude=%s", URLEncode($main::opt_exclude)));
}
if (scalar @params > 0) {
$url = sprintf("%s?%s", $url, join("&", @params));
}
return $url;
}
# Fetches and processes symbols to prepare them for use in the profile output
# code. If the optional 'symbol_map' arg is not given, fetches symbols from
# $SYMBOL_PAGE for all PC values found in profile. Otherwise, the raw symbols
......@@ -3344,9 +3433,11 @@ sub FetchSymbols {
my $command_line;
if (join(" ", @URL_FETCHER) =~ m/\bcurl -s/) {
$url = ResolveRedirectionForCurl($url);
$url = AppendSymbolFilterParams($url);
$command_line = ShellEscape(@URL_FETCHER, "-d", "\@$main::tmpfile_sym",
$url);
} else {
$url = AppendSymbolFilterParams($url);
$command_line = (ShellEscape(@URL_FETCHER, "--post", $url)
. " < " . ShellEscape($main::tmpfile_sym));
}
......@@ -3427,12 +3518,22 @@ sub FetchDynamicProfile {
}
$url .= sprintf("seconds=%d", $main::opt_seconds);
$fetch_timeout = $main::opt_seconds * 1.01 + 60;
# Set $profile_type for consumption by PrintSymbolizedProfile.
$main::profile_type = 'cpu';
} else {
# For non-CPU profiles, we add a type-extension to
# the target profile file name.
my $suffix = $path;
$suffix =~ s,/,.,g;
$profile_file .= $suffix;
# Set $profile_type for consumption by PrintSymbolizedProfile.
if ($path =~ m/$HEAP_PAGE/) {
$main::profile_type = 'heap';
} elsif ($path =~ m/$GROWTH_PAGE/) {
$main::profile_type = 'growth';
} elsif ($path =~ m/$CONTENTION_PAGE/) {
$main::profile_type = 'contention';
}
}
my $profile_dir = $ENV{"JEPROF_TMPDIR"} || ($ENV{HOME} . "/jeprof");
......@@ -3730,6 +3831,8 @@ sub ReadProfile {
my $symbol_marker = $&;
$PROFILE_PAGE =~ m,[^/]+$,; # matches everything after the last slash
my $profile_marker = $&;
$HEAP_PAGE =~ m,[^/]+$,; # matches everything after the last slash
my $heap_marker = $&;
# Look at first line to see if it is a heap or a CPU profile.
# CPU profile may start with no header at all, and just binary data
......@@ -3756,7 +3859,13 @@ sub ReadProfile {
$header = ReadProfileHeader(*PROFILE) || "";
}
if ($header =~ m/^--- *($heap_marker|$growth_marker)/o) {
# Skip "--- ..." line for profile types that have their own headers.
$header = ReadProfileHeader(*PROFILE) || "";
}
$main::profile_type = '';
if ($header =~ m/^heap profile:.*$growth_marker/o) {
$main::profile_type = 'growth';
$result = ReadHeapProfile($prog, *PROFILE, $header);
......@@ -3808,9 +3917,9 @@ sub ReadProfile {
# independent implementation.
sub FixCallerAddresses {
my $stack = shift;
if ($main::use_symbolized_profile) {
return $stack;
} else {
# --raw/http: Always subtract one from pc's, because PrintSymbolizedProfile()
# dumps unadjusted profiles.
{
$stack =~ /(\s)/;
my $delimiter = $1;
my @addrs = split(' ', $stack);
......@@ -3878,12 +3987,7 @@ sub ReadCPUProfile {
for (my $j = 0; $j < $d; $j++) {
my $pc = $slots->get($i+$j);
# Subtract one from caller pc so we map back to call instr.
# However, don't do this if we're reading a symbolized profile
# file, in which case the subtract-one was done when the file
# was written.
if ($j > 0 && !$main::use_symbolized_profile) {
$pc--;
}
$pc--;
$pc = sprintf("%0*x", $address_length, $pc);
$pcs->{$pc} = 1;
push @k, $pc;
......@@ -4469,7 +4573,7 @@ sub ParseTextSectionHeader {
# Split /proc/pid/maps dump into a list of libraries
sub ParseLibraries {
return if $main::use_symbol_page; # We don't need libraries info.
my $prog = shift;
my $prog = Cwd::abs_path(shift);
my $map = shift;
my $pcs = shift;
......@@ -4502,6 +4606,16 @@ sub ParseLibraries {
$finish = HexExtend($2);
$offset = $zero_offset;
$lib = $3;
} elsif (($l =~ /^($h)-($h)\s+..x.\s+($h)\s+\S+:\S+\s+\d+\s+(\S+)$/i) && ($4 eq $prog)) {
# PIEs and address space randomization do not play well with our
# default assumption that main executable is at lowest
# addresses. So we're detecting main executable in
# /proc/self/maps as well.
$start = HexExtend($1);
$finish = HexExtend($2);
$offset = HexExtend($3);
$lib = $4;
$lib =~ s|\\|/|g; # turn windows-style paths into unix-style paths
}
# FreeBSD 10.0 virtual memory map /proc/curproc/map as defined in
# function procfs_doprocmap (sys/fs/procfs/procfs_map.c)
......
#! /bin/sh
# Attempt to guess a canonical system name.
# Copyright 1992-2014 Free Software Foundation, Inc.
# Copyright 1992-2016 Free Software Foundation, Inc.
timestamp='2014-03-23'
timestamp='2016-10-02'
# This file is free software; you can redistribute it and/or modify it
# under the terms of the GNU General Public License as published by
......@@ -24,12 +24,12 @@ timestamp='2014-03-23'
# program. This Exception is an additional permission under section 7
# of the GNU General Public License, version 3 ("GPLv3").
#
# Originally written by Per Bothner.
# Originally written by Per Bothner; maintained since 2000 by Ben Elliston.
#
# You can get the latest version of this script from:
# http://git.savannah.gnu.org/gitweb/?p=config.git;a=blob_plain;f=config.guess;hb=HEAD
# http://git.savannah.gnu.org/gitweb/?p=config.git;a=blob_plain;f=config.guess
#
# Please send patches with a ChangeLog entry to config-patches@gnu.org.
# Please send patches to <config-patches@gnu.org>.
me=`echo "$0" | sed -e 's,.*/,,'`
......@@ -50,7 +50,7 @@ version="\
GNU config.guess ($timestamp)
Originally written by Per Bothner.
Copyright 1992-2014 Free Software Foundation, Inc.
Copyright 1992-2016 Free Software Foundation, Inc.
This is free software; see the source for copying conditions. There is NO
warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE."
......@@ -168,19 +168,29 @@ case "${UNAME_MACHINE}:${UNAME_SYSTEM}:${UNAME_RELEASE}:${UNAME_VERSION}" in
# Note: NetBSD doesn't particularly care about the vendor
# portion of the name. We always set it to "unknown".
sysctl="sysctl -n hw.machine_arch"
UNAME_MACHINE_ARCH=`(/sbin/$sysctl 2>/dev/null || \
/usr/sbin/$sysctl 2>/dev/null || echo unknown)`
UNAME_MACHINE_ARCH=`(uname -p 2>/dev/null || \
/sbin/$sysctl 2>/dev/null || \
/usr/sbin/$sysctl 2>/dev/null || \
echo unknown)`
case "${UNAME_MACHINE_ARCH}" in
armeb) machine=armeb-unknown ;;
arm*) machine=arm-unknown ;;
sh3el) machine=shl-unknown ;;
sh3eb) machine=sh-unknown ;;
sh5el) machine=sh5le-unknown ;;
earmv*)
arch=`echo ${UNAME_MACHINE_ARCH} | sed -e 's,^e\(armv[0-9]\).*$,\1,'`
endian=`echo ${UNAME_MACHINE_ARCH} | sed -ne 's,^.*\(eb\)$,\1,p'`
machine=${arch}${endian}-unknown
;;
*) machine=${UNAME_MACHINE_ARCH}-unknown ;;
esac
# The Operating System including object format, if it has switched
# to ELF recently, or will in the future.
# to ELF recently (or will in the future) and ABI.
case "${UNAME_MACHINE_ARCH}" in
earm*)
os=netbsdelf
;;
arm*|i386|m68k|ns32k|sh3*|sparc|vax)
eval $set_cc_for_build
if echo __ELF__ | $CC_FOR_BUILD -E - 2>/dev/null \
......@@ -197,6 +207,13 @@ case "${UNAME_MACHINE}:${UNAME_SYSTEM}:${UNAME_RELEASE}:${UNAME_VERSION}" in
os=netbsd
;;
esac
# Determine ABI tags.
case "${UNAME_MACHINE_ARCH}" in
earm*)
expr='s/^earmv[0-9]/-eabi/;s/eb$//'
abi=`echo ${UNAME_MACHINE_ARCH} | sed -e "$expr"`
;;
esac
# The OS release
# Debian GNU/NetBSD machines have a different userland, and
# thus, need a distinct triplet. However, they do not need
......@@ -207,13 +224,13 @@ case "${UNAME_MACHINE}:${UNAME_SYSTEM}:${UNAME_RELEASE}:${UNAME_VERSION}" in
release='-gnu'
;;
*)
release=`echo ${UNAME_RELEASE}|sed -e 's/[-_].*/\./'`
release=`echo ${UNAME_RELEASE} | sed -e 's/[-_].*//' | cut -d. -f1,2`
;;
esac
# Since CPU_TYPE-MANUFACTURER-KERNEL-OPERATING_SYSTEM:
# contains redundant information, the shorter form:
# CPU_TYPE-MANUFACTURER-OPERATING_SYSTEM is used.
echo "${machine}-${os}${release}"
echo "${machine}-${os}${release}${abi}"
exit ;;
*:Bitrig:*:*)
UNAME_MACHINE_ARCH=`arch | sed 's/Bitrig.//'`
......@@ -223,6 +240,10 @@ case "${UNAME_MACHINE}:${UNAME_SYSTEM}:${UNAME_RELEASE}:${UNAME_VERSION}" in
UNAME_MACHINE_ARCH=`arch | sed 's/OpenBSD.//'`
echo ${UNAME_MACHINE_ARCH}-unknown-openbsd${UNAME_RELEASE}
exit ;;
*:LibertyBSD:*:*)
UNAME_MACHINE_ARCH=`arch | sed 's/^.*BSD\.//'`
echo ${UNAME_MACHINE_ARCH}-unknown-libertybsd${UNAME_RELEASE}
exit ;;
*:ekkoBSD:*:*)
echo ${UNAME_MACHINE}-unknown-ekkobsd${UNAME_RELEASE}
exit ;;
......@@ -235,6 +256,9 @@ case "${UNAME_MACHINE}:${UNAME_SYSTEM}:${UNAME_RELEASE}:${UNAME_VERSION}" in
*:MirBSD:*:*)
echo ${UNAME_MACHINE}-unknown-mirbsd${UNAME_RELEASE}
exit ;;
*:Sortix:*:*)
echo ${UNAME_MACHINE}-unknown-sortix
exit ;;
alpha:OSF1:*:*)
case $UNAME_RELEASE in
*4.0)
......@@ -251,42 +275,42 @@ case "${UNAME_MACHINE}:${UNAME_SYSTEM}:${UNAME_RELEASE}:${UNAME_VERSION}" in
ALPHA_CPU_TYPE=`/usr/sbin/psrinfo -v | sed -n -e 's/^ The alpha \(.*\) processor.*$/\1/p' | head -n 1`
case "$ALPHA_CPU_TYPE" in
"EV4 (21064)")
UNAME_MACHINE="alpha" ;;
UNAME_MACHINE=alpha ;;
"EV4.5 (21064)")
UNAME_MACHINE="alpha" ;;
UNAME_MACHINE=alpha ;;
"LCA4 (21066/21068)")
UNAME_MACHINE="alpha" ;;
UNAME_MACHINE=alpha ;;
"EV5 (21164)")
UNAME_MACHINE="alphaev5" ;;
UNAME_MACHINE=alphaev5 ;;
"EV5.6 (21164A)")
UNAME_MACHINE="alphaev56" ;;
UNAME_MACHINE=alphaev56 ;;
"EV5.6 (21164PC)")
UNAME_MACHINE="alphapca56" ;;
UNAME_MACHINE=alphapca56 ;;
"EV5.7 (21164PC)")
UNAME_MACHINE="alphapca57" ;;
UNAME_MACHINE=alphapca57 ;;
"EV6 (21264)")
UNAME_MACHINE="alphaev6" ;;
UNAME_MACHINE=alphaev6 ;;
"EV6.7 (21264A)")
UNAME_MACHINE="alphaev67" ;;
UNAME_MACHINE=alphaev67 ;;
"EV6.8CB (21264C)")
UNAME_MACHINE="alphaev68" ;;
UNAME_MACHINE=alphaev68 ;;
"EV6.8AL (21264B)")
UNAME_MACHINE="alphaev68" ;;
UNAME_MACHINE=alphaev68 ;;
"EV6.8CX (21264D)")
UNAME_MACHINE="alphaev68" ;;
UNAME_MACHINE=alphaev68 ;;
"EV6.9A (21264/EV69A)")
UNAME_MACHINE="alphaev69" ;;
UNAME_MACHINE=alphaev69 ;;
"EV7 (21364)")
UNAME_MACHINE="alphaev7" ;;
UNAME_MACHINE=alphaev7 ;;
"EV7.9 (21364A)")
UNAME_MACHINE="alphaev79" ;;
UNAME_MACHINE=alphaev79 ;;
esac
# A Pn.n version is a patched version.
# A Vn.n version is a released version.
# A Tn.n version is a released field test version.
# A Xn.n version is an unreleased experimental baselevel.
# 1.2 uses "1.2" for uname -r.
echo ${UNAME_MACHINE}-dec-osf`echo ${UNAME_RELEASE} | sed -e 's/^[PVTX]//' | tr 'ABCDEFGHIJKLMNOPQRSTUVWXYZ' 'abcdefghijklmnopqrstuvwxyz'`
echo ${UNAME_MACHINE}-dec-osf`echo ${UNAME_RELEASE} | sed -e 's/^[PVTX]//' | tr ABCDEFGHIJKLMNOPQRSTUVWXYZ abcdefghijklmnopqrstuvwxyz`
# Reset EXIT trap before exiting to avoid spurious non-zero exit code.
exitcode=$?
trap '' 0
......@@ -359,16 +383,16 @@ case "${UNAME_MACHINE}:${UNAME_SYSTEM}:${UNAME_RELEASE}:${UNAME_VERSION}" in
exit ;;
i86pc:SunOS:5.*:* | i86xen:SunOS:5.*:*)
eval $set_cc_for_build
SUN_ARCH="i386"
SUN_ARCH=i386
# If there is a compiler, see if it is configured for 64-bit objects.
# Note that the Sun cc does not turn __LP64__ into 1 like gcc does.
# This test works for both compilers.
if [ "$CC_FOR_BUILD" != 'no_compiler_found' ]; then
if [ "$CC_FOR_BUILD" != no_compiler_found ]; then
if (echo '#ifdef __amd64'; echo IS_64BIT_ARCH; echo '#endif') | \
(CCOPTS= $CC_FOR_BUILD -E - 2>/dev/null) | \
(CCOPTS="" $CC_FOR_BUILD -E - 2>/dev/null) | \
grep IS_64BIT_ARCH >/dev/null
then
SUN_ARCH="x86_64"
SUN_ARCH=x86_64
fi
fi
echo ${SUN_ARCH}-pc-solaris2`echo ${UNAME_RELEASE}|sed -e 's/[^.]*//'`
......@@ -393,7 +417,7 @@ case "${UNAME_MACHINE}:${UNAME_SYSTEM}:${UNAME_RELEASE}:${UNAME_VERSION}" in
exit ;;
sun*:*:4.2BSD:*)
UNAME_RELEASE=`(sed 1q /etc/motd | awk '{print substr($5,1,3)}') 2>/dev/null`
test "x${UNAME_RELEASE}" = "x" && UNAME_RELEASE=3
test "x${UNAME_RELEASE}" = x && UNAME_RELEASE=3
case "`/bin/arch`" in
sun3)
echo m68k-sun-sunos${UNAME_RELEASE}
......@@ -579,8 +603,9 @@ EOF
else
IBM_ARCH=powerpc
fi
if [ -x /usr/bin/oslevel ] ; then
IBM_REV=`/usr/bin/oslevel`
if [ -x /usr/bin/lslpp ] ; then
IBM_REV=`/usr/bin/lslpp -Lqc bos.rte.libc |
awk -F: '{ print $3 }' | sed s/[0-9]*$/0/`
else
IBM_REV=${UNAME_VERSION}.${UNAME_RELEASE}
fi
......@@ -617,13 +642,13 @@ EOF
sc_cpu_version=`/usr/bin/getconf SC_CPU_VERSION 2>/dev/null`
sc_kernel_bits=`/usr/bin/getconf SC_KERNEL_BITS 2>/dev/null`
case "${sc_cpu_version}" in
523) HP_ARCH="hppa1.0" ;; # CPU_PA_RISC1_0
528) HP_ARCH="hppa1.1" ;; # CPU_PA_RISC1_1
523) HP_ARCH=hppa1.0 ;; # CPU_PA_RISC1_0
528) HP_ARCH=hppa1.1 ;; # CPU_PA_RISC1_1
532) # CPU_PA_RISC2_0
case "${sc_kernel_bits}" in
32) HP_ARCH="hppa2.0n" ;;
64) HP_ARCH="hppa2.0w" ;;
'') HP_ARCH="hppa2.0" ;; # HP-UX 10.20
32) HP_ARCH=hppa2.0n ;;
64) HP_ARCH=hppa2.0w ;;
'') HP_ARCH=hppa2.0 ;; # HP-UX 10.20
esac ;;
esac
fi
......@@ -662,11 +687,11 @@ EOF
exit (0);
}
EOF
(CCOPTS= $CC_FOR_BUILD -o $dummy $dummy.c 2>/dev/null) && HP_ARCH=`$dummy`
(CCOPTS="" $CC_FOR_BUILD -o $dummy $dummy.c 2>/dev/null) && HP_ARCH=`$dummy`
test -z "$HP_ARCH" && HP_ARCH=hppa
fi ;;
esac
if [ ${HP_ARCH} = "hppa2.0w" ]
if [ ${HP_ARCH} = hppa2.0w ]
then
eval $set_cc_for_build
......@@ -679,12 +704,12 @@ EOF
# $ CC_FOR_BUILD="cc +DA2.0w" ./config.guess
# => hppa64-hp-hpux11.23
if echo __LP64__ | (CCOPTS= $CC_FOR_BUILD -E - 2>/dev/null) |
if echo __LP64__ | (CCOPTS="" $CC_FOR_BUILD -E - 2>/dev/null) |
grep -q __LP64__
then
HP_ARCH="hppa2.0w"
HP_ARCH=hppa2.0w
else
HP_ARCH="hppa64"
HP_ARCH=hppa64
fi
fi
echo ${HP_ARCH}-hp-hpux${HPUX_REV}
......@@ -789,14 +814,14 @@ EOF
echo craynv-cray-unicosmp${UNAME_RELEASE} | sed -e 's/\.[^.]*$/.X/'
exit ;;
F30[01]:UNIX_System_V:*:* | F700:UNIX_System_V:*:*)
FUJITSU_PROC=`uname -m | tr 'ABCDEFGHIJKLMNOPQRSTUVWXYZ' 'abcdefghijklmnopqrstuvwxyz'`
FUJITSU_SYS=`uname -p | tr 'ABCDEFGHIJKLMNOPQRSTUVWXYZ' 'abcdefghijklmnopqrstuvwxyz' | sed -e 's/\///'`
FUJITSU_PROC=`uname -m | tr ABCDEFGHIJKLMNOPQRSTUVWXYZ abcdefghijklmnopqrstuvwxyz`
FUJITSU_SYS=`uname -p | tr ABCDEFGHIJKLMNOPQRSTUVWXYZ abcdefghijklmnopqrstuvwxyz | sed -e 's/\///'`
FUJITSU_REL=`echo ${UNAME_RELEASE} | sed -e 's/ /_/'`
echo "${FUJITSU_PROC}-fujitsu-${FUJITSU_SYS}${FUJITSU_REL}"
exit ;;
5000:UNIX_System_V:4.*:*)
FUJITSU_SYS=`uname -p | tr 'ABCDEFGHIJKLMNOPQRSTUVWXYZ' 'abcdefghijklmnopqrstuvwxyz' | sed -e 's/\///'`
FUJITSU_REL=`echo ${UNAME_RELEASE} | tr 'ABCDEFGHIJKLMNOPQRSTUVWXYZ' 'abcdefghijklmnopqrstuvwxyz' | sed -e 's/ /_/'`
FUJITSU_SYS=`uname -p | tr ABCDEFGHIJKLMNOPQRSTUVWXYZ abcdefghijklmnopqrstuvwxyz | sed -e 's/\///'`
FUJITSU_REL=`echo ${UNAME_RELEASE} | tr ABCDEFGHIJKLMNOPQRSTUVWXYZ abcdefghijklmnopqrstuvwxyz | sed -e 's/ /_/'`
echo "sparc-fujitsu-${FUJITSU_SYS}${FUJITSU_REL}"
exit ;;
i*86:BSD/386:*:* | i*86:BSD/OS:*:* | *:Ascend\ Embedded/OS:*:*)
......@@ -878,7 +903,7 @@ EOF
exit ;;
*:GNU/*:*:*)
# other systems with GNU libc and userland
echo ${UNAME_MACHINE}-unknown-`echo ${UNAME_SYSTEM} | sed 's,^[^/]*/,,' | tr '[A-Z]' '[a-z]'``echo ${UNAME_RELEASE}|sed -e 's/[-(].*//'`-${LIBC}
echo ${UNAME_MACHINE}-unknown-`echo ${UNAME_SYSTEM} | sed 's,^[^/]*/,,' | tr "[:upper:]" "[:lower:]"``echo ${UNAME_RELEASE}|sed -e 's/[-(].*//'`-${LIBC}
exit ;;
i*86:Minix:*:*)
echo ${UNAME_MACHINE}-pc-minix
......@@ -901,7 +926,7 @@ EOF
EV68*) UNAME_MACHINE=alphaev68 ;;
esac
objdump --private-headers /bin/sh | grep -q ld.so.1
if test "$?" = 0 ; then LIBC="gnulibc1" ; fi
if test "$?" = 0 ; then LIBC=gnulibc1 ; fi
echo ${UNAME_MACHINE}-unknown-linux-${LIBC}
exit ;;
arc:Linux:*:* | arceb:Linux:*:*)
......@@ -932,6 +957,9 @@ EOF
crisv32:Linux:*:*)
echo ${UNAME_MACHINE}-axis-linux-${LIBC}
exit ;;
e2k:Linux:*:*)
echo ${UNAME_MACHINE}-unknown-linux-${LIBC}
exit ;;
frv:Linux:*:*)
echo ${UNAME_MACHINE}-unknown-linux-${LIBC}
exit ;;
......@@ -944,6 +972,9 @@ EOF
ia64:Linux:*:*)
echo ${UNAME_MACHINE}-unknown-linux-${LIBC}
exit ;;
k1om:Linux:*:*)
echo ${UNAME_MACHINE}-unknown-linux-${LIBC}
exit ;;
m32r*:Linux:*:*)
echo ${UNAME_MACHINE}-unknown-linux-${LIBC}
exit ;;
......@@ -969,6 +1000,9 @@ EOF
eval `$CC_FOR_BUILD -E $dummy.c 2>/dev/null | grep '^CPU'`
test x"${CPU}" != x && { echo "${CPU}-unknown-linux-${LIBC}"; exit; }
;;
mips64el:Linux:*:*)
echo ${UNAME_MACHINE}-unknown-linux-${LIBC}
exit ;;
openrisc*:Linux:*:*)
echo or1k-unknown-linux-${LIBC}
exit ;;
......@@ -1001,6 +1035,9 @@ EOF
ppcle:Linux:*:*)
echo powerpcle-unknown-linux-${LIBC}
exit ;;
riscv32:Linux:*:* | riscv64:Linux:*:*)
echo ${UNAME_MACHINE}-unknown-linux-${LIBC}
exit ;;
s390:Linux:*:* | s390x:Linux:*:*)
echo ${UNAME_MACHINE}-ibm-linux-${LIBC}
exit ;;
......@@ -1020,7 +1057,7 @@ EOF
echo ${UNAME_MACHINE}-dec-linux-${LIBC}
exit ;;
x86_64:Linux:*:*)
echo ${UNAME_MACHINE}-unknown-linux-${LIBC}
echo ${UNAME_MACHINE}-pc-linux-${LIBC}
exit ;;
xtensa*:Linux:*:*)
echo ${UNAME_MACHINE}-unknown-linux-${LIBC}
......@@ -1099,7 +1136,7 @@ EOF
# uname -m prints for DJGPP always 'pc', but it prints nothing about
# the processor, so we play safe by assuming i586.
# Note: whatever this is, it MUST be the same as what config.sub
# prints for the "djgpp" host, or else GDB configury will decide that
# prints for the "djgpp" host, or else GDB configure will decide that
# this is a cross-build.
echo i586-pc-msdosdjgpp
exit ;;
......@@ -1248,6 +1285,9 @@ EOF
SX-8R:SUPER-UX:*:*)
echo sx8r-nec-superux${UNAME_RELEASE}
exit ;;
SX-ACE:SUPER-UX:*:*)
echo sxace-nec-superux${UNAME_RELEASE}
exit ;;
Power*:Rhapsody:*:*)
echo powerpc-apple-rhapsody${UNAME_RELEASE}
exit ;;
......@@ -1261,9 +1301,9 @@ EOF
UNAME_PROCESSOR=powerpc
fi
if test `echo "$UNAME_RELEASE" | sed -e 's/\..*//'` -le 10 ; then
if [ "$CC_FOR_BUILD" != 'no_compiler_found' ]; then
if [ "$CC_FOR_BUILD" != no_compiler_found ]; then
if (echo '#ifdef __LP64__'; echo IS_64BIT_ARCH; echo '#endif') | \
(CCOPTS= $CC_FOR_BUILD -E - 2>/dev/null) | \
(CCOPTS="" $CC_FOR_BUILD -E - 2>/dev/null) | \
grep IS_64BIT_ARCH >/dev/null
then
case $UNAME_PROCESSOR in
......@@ -1285,7 +1325,7 @@ EOF
exit ;;
*:procnto*:*:* | *:QNX:[0123456789]*:*)
UNAME_PROCESSOR=`uname -p`
if test "$UNAME_PROCESSOR" = "x86"; then
if test "$UNAME_PROCESSOR" = x86; then
UNAME_PROCESSOR=i386
UNAME_MACHINE=pc
fi
......@@ -1316,7 +1356,7 @@ EOF
# "uname -m" is not consistent, so use $cputype instead. 386
# is converted to i386 for consistency with other x86
# operating systems.
if test "$cputype" = "386"; then
if test "$cputype" = 386; then
UNAME_MACHINE=i386
else
UNAME_MACHINE="$cputype"
......@@ -1358,7 +1398,7 @@ EOF
echo i386-pc-xenix
exit ;;
i*86:skyos:*:*)
echo ${UNAME_MACHINE}-pc-skyos`echo ${UNAME_RELEASE}` | sed -e 's/ .*$//'
echo ${UNAME_MACHINE}-pc-skyos`echo ${UNAME_RELEASE} | sed -e 's/ .*$//'`
exit ;;
i*86:rdos:*:*)
echo ${UNAME_MACHINE}-pc-rdos
......@@ -1369,23 +1409,25 @@ EOF
x86_64:VMkernel:*:*)
echo ${UNAME_MACHINE}-unknown-esx
exit ;;
amd64:Isilon\ OneFS:*:*)
echo x86_64-unknown-onefs
exit ;;
esac
cat >&2 <<EOF
$0: unable to guess system type
This script, last modified $timestamp, has failed to recognize
the operating system you are using. It is advised that you
download the most up to date version of the config scripts from
This script (version $timestamp), has failed to recognize the
operating system you are using. If your script is old, overwrite
config.guess and config.sub with the latest versions from:
http://git.savannah.gnu.org/gitweb/?p=config.git;a=blob_plain;f=config.guess;hb=HEAD
http://git.savannah.gnu.org/gitweb/?p=config.git;a=blob_plain;f=config.guess
and
http://git.savannah.gnu.org/gitweb/?p=config.git;a=blob_plain;f=config.sub;hb=HEAD
http://git.savannah.gnu.org/gitweb/?p=config.git;a=blob_plain;f=config.sub
If the version you run ($0) is already up to date, please
send the following data and any information you think might be
pertinent to <config-patches@gnu.org> in order to provide the needed
information to handle your system.
If $0 has already been updated, send the following data and any
information you think might be pertinent to config-patches@gnu.org to
provide the necessary information to handle your system.
config.guess timestamp = $timestamp
......
#! /bin/sh
# Configuration validation subroutine script.
# Copyright 1992-2014 Free Software Foundation, Inc.
# Copyright 1992-2016 Free Software Foundation, Inc.
timestamp='2014-05-01'
timestamp='2016-11-04'
# This file is free software; you can redistribute it and/or modify it
# under the terms of the GNU General Public License as published by
......@@ -25,7 +25,7 @@ timestamp='2014-05-01'
# of the GNU General Public License, version 3 ("GPLv3").
# Please send patches with a ChangeLog entry to config-patches@gnu.org.
# Please send patches to <config-patches@gnu.org>.
#
# Configuration subroutine to validate and canonicalize a configuration type.
# Supply the specified configuration type as an argument.
......@@ -33,7 +33,7 @@ timestamp='2014-05-01'
# Otherwise, we print the canonical config type on stdout and succeed.
# You can get the latest version of this script from:
# http://git.savannah.gnu.org/gitweb/?p=config.git;a=blob_plain;f=config.sub;hb=HEAD
# http://git.savannah.gnu.org/gitweb/?p=config.git;a=blob_plain;f=config.sub
# This file is supposed to be the same for all GNU packages
# and recognize all the CPU types, system types and aliases
......@@ -53,8 +53,7 @@ timestamp='2014-05-01'
me=`echo "$0" | sed -e 's,.*/,,'`
usage="\
Usage: $0 [OPTION] CPU-MFR-OPSYS
$0 [OPTION] ALIAS
Usage: $0 [OPTION] CPU-MFR-OPSYS or ALIAS
Canonicalize a configuration name.
......@@ -68,7 +67,7 @@ Report bugs and patches to <config-patches@gnu.org>."
version="\
GNU config.sub ($timestamp)
Copyright 1992-2014 Free Software Foundation, Inc.
Copyright 1992-2016 Free Software Foundation, Inc.
This is free software; see the source for copying conditions. There is NO
warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE."
......@@ -117,8 +116,8 @@ maybe_os=`echo $1 | sed 's/^\(.*\)-\([^-]*-[^-]*\)$/\2/'`
case $maybe_os in
nto-qnx* | linux-gnu* | linux-android* | linux-dietlibc | linux-newlib* | \
linux-musl* | linux-uclibc* | uclinux-uclibc* | uclinux-gnu* | kfreebsd*-gnu* | \
knetbsd*-gnu* | netbsd*-gnu* | \
kopensolaris*-gnu* | \
knetbsd*-gnu* | netbsd*-gnu* | netbsd*-eabi* | \
kopensolaris*-gnu* | cloudabi*-eabi* | \
storm-chaos* | os2-emx* | rtmk-nova*)
os=-$maybe_os
basic_machine=`echo $1 | sed 's/^\(.*\)-\([^-]*-[^-]*\)$/\1/'`
......@@ -255,12 +254,13 @@ case $basic_machine in
| arc | arceb \
| arm | arm[bl]e | arme[lb] | armv[2-8] | armv[3-8][lb] | armv7[arm] \
| avr | avr32 \
| ba \
| be32 | be64 \
| bfin \
| c4x | c8051 | clipper \
| d10v | d30v | dlx | dsp16xx \
| epiphany \
| fido | fr30 | frv \
| e2k | epiphany \
| fido | fr30 | frv | ft32 \
| h8300 | h8500 | hppa | hppa1.[01] | hppa2.0 | hppa2.0[nw] | hppa64 \
| hexagon \
| i370 | i860 | i960 | ia64 \
......@@ -301,10 +301,12 @@ case $basic_machine in
| open8 | or1k | or1knd | or32 \
| pdp10 | pdp11 | pj | pjl \
| powerpc | powerpc64 | powerpc64le | powerpcle \
| pru \
| pyramid \
| riscv32 | riscv64 \
| rl78 | rx \
| score \
| sh | sh[1234] | sh[24]a | sh[24]aeb | sh[23]e | sh[34]eb | sheb | shbe | shle | sh[1234]le | sh3ele \
| sh | sh[1234] | sh[24]a | sh[24]aeb | sh[23]e | sh[234]eb | sheb | shbe | shle | sh[1234]le | sh3ele \
| sh64 | sh64le \
| sparc | sparc64 | sparc64b | sparc64v | sparc86x | sparclet | sparclite \
| sparcv8 | sparcv9 | sparcv9b | sparcv9v \
......@@ -312,6 +314,7 @@ case $basic_machine in
| tahoe | tic4x | tic54x | tic55x | tic6x | tic80 | tron \
| ubicom32 \
| v850 | v850e | v850e1 | v850e2 | v850es | v850e2v3 \
| visium \
| we32k \
| x86 | xc16x | xstormy16 | xtensa \
| z8k | z80)
......@@ -326,6 +329,9 @@ case $basic_machine in
c6x)
basic_machine=tic6x-unknown
;;
leon|leon[3-9])
basic_machine=sparc-$basic_machine
;;
m6811 | m68hc11 | m6812 | m68hc12 | m68hcs12x | nvptx | picochip)
basic_machine=$basic_machine-unknown
os=-none
......@@ -371,12 +377,13 @@ case $basic_machine in
| alphapca5[67]-* | alpha64pca5[67]-* | arc-* | arceb-* \
| arm-* | armbe-* | armle-* | armeb-* | armv*-* \
| avr-* | avr32-* \
| ba-* \
| be32-* | be64-* \
| bfin-* | bs2000-* \
| c[123]* | c30-* | [cjt]90-* | c4x-* \
| c8051-* | clipper-* | craynv-* | cydra-* \
| d10v-* | d30v-* | dlx-* \
| elxsi-* \
| e2k-* | elxsi-* \
| f30[01]-* | f700-* | fido-* | fr30-* | frv-* | fx80-* \
| h8300-* | h8500-* \
| hppa-* | hppa1.[01]-* | hppa2.0-* | hppa2.0[nw]-* | hppa64-* \
......@@ -422,13 +429,15 @@ case $basic_machine in
| orion-* \
| pdp10-* | pdp11-* | pj-* | pjl-* | pn-* | power-* \
| powerpc-* | powerpc64-* | powerpc64le-* | powerpcle-* \
| pru-* \
| pyramid-* \
| riscv32-* | riscv64-* \
| rl78-* | romp-* | rs6000-* | rx-* \
| sh-* | sh[1234]-* | sh[24]a-* | sh[24]aeb-* | sh[23]e-* | sh[34]eb-* | sheb-* | shbe-* \
| shle-* | sh[1234]le-* | sh3ele-* | sh64-* | sh64le-* \
| sparc-* | sparc64-* | sparc64b-* | sparc64v-* | sparc86x-* | sparclet-* \
| sparclite-* \
| sparcv8-* | sparcv9-* | sparcv9b-* | sparcv9v-* | sv1-* | sx?-* \
| sparcv8-* | sparcv9-* | sparcv9b-* | sparcv9v-* | sv1-* | sx*-* \
| tahoe-* \
| tic30-* | tic4x-* | tic54x-* | tic55x-* | tic6x-* | tic80-* \
| tile*-* \
......@@ -436,6 +445,7 @@ case $basic_machine in
| ubicom32-* \
| v850-* | v850e-* | v850e1-* | v850es-* | v850e2-* | v850e2v3-* \
| vax-* \
| visium-* \
| we32k-* \
| x86-* | x86_64-* | xc16x-* | xps100-* \
| xstormy16-* | xtensa*-* \
......@@ -512,6 +522,9 @@ case $basic_machine in
basic_machine=i386-pc
os=-aros
;;
asmjs)
basic_machine=asmjs-unknown
;;
aux)
basic_machine=m68k-apple
os=-aux
......@@ -632,6 +645,14 @@ case $basic_machine in
basic_machine=m68k-bull
os=-sysv3
;;
e500v[12])
basic_machine=powerpc-unknown
os=$os"spe"
;;
e500v[12]-*)
basic_machine=powerpc-`echo $basic_machine | sed 's/^[^-]*-//'`
os=$os"spe"
;;
ebmon29k)
basic_machine=a29k-amd
os=-ebmon
......@@ -773,6 +794,9 @@ case $basic_machine in
basic_machine=m68k-isi
os=-sysv
;;
leon-*|leon[3-9]-*)
basic_machine=sparc-`echo $basic_machine | sed 's/-.*//'`
;;
m68knommu)
basic_machine=m68k-unknown
os=-linux
......@@ -828,6 +852,10 @@ case $basic_machine in
basic_machine=powerpc-unknown
os=-morphos
;;
moxiebox)
basic_machine=moxie-unknown
os=-moxiebox
;;
msdos)
basic_machine=i386-pc
os=-msdos
......@@ -1004,7 +1032,7 @@ case $basic_machine in
ppc-* | ppcbe-*)
basic_machine=powerpc-`echo $basic_machine | sed 's/^[^-]*-//'`
;;
ppcle | powerpclittle | ppc-le | powerpc-little)
ppcle | powerpclittle)
basic_machine=powerpcle-unknown
;;
ppcle-* | powerpclittle-*)
......@@ -1014,7 +1042,7 @@ case $basic_machine in
;;
ppc64-*) basic_machine=powerpc64-`echo $basic_machine | sed 's/^[^-]*-//'`
;;
ppc64le | powerpc64little | ppc64-le | powerpc64-little)
ppc64le | powerpc64little)
basic_machine=powerpc64le-unknown
;;
ppc64le-* | powerpc64little-*)
......@@ -1360,27 +1388,28 @@ case $os in
| -hpux* | -unos* | -osf* | -luna* | -dgux* | -auroraux* | -solaris* \
| -sym* | -kopensolaris* | -plan9* \
| -amigaos* | -amigados* | -msdos* | -newsos* | -unicos* | -aof* \
| -aos* | -aros* \
| -aos* | -aros* | -cloudabi* | -sortix* \
| -nindy* | -vxsim* | -vxworks* | -ebmon* | -hms* | -mvs* \
| -clix* | -riscos* | -uniplus* | -iris* | -rtu* | -xenix* \
| -hiux* | -386bsd* | -knetbsd* | -mirbsd* | -netbsd* \
| -bitrig* | -openbsd* | -solidbsd* \
| -bitrig* | -openbsd* | -solidbsd* | -libertybsd* \
| -ekkobsd* | -kfreebsd* | -freebsd* | -riscix* | -lynxos* \
| -bosx* | -nextstep* | -cxux* | -aout* | -elf* | -oabi* \
| -ptx* | -coff* | -ecoff* | -winnt* | -domain* | -vsta* \
| -udi* | -eabi* | -lites* | -ieee* | -go32* | -aux* \
| -chorusos* | -chorusrdb* | -cegcc* \
| -cygwin* | -msys* | -pe* | -psos* | -moss* | -proelf* | -rtems* \
| -mingw32* | -mingw64* | -linux-gnu* | -linux-android* \
| -midipix* | -mingw32* | -mingw64* | -linux-gnu* | -linux-android* \
| -linux-newlib* | -linux-musl* | -linux-uclibc* \
| -uxpv* | -beos* | -mpeix* | -udk* \
| -uxpv* | -beos* | -mpeix* | -udk* | -moxiebox* \
| -interix* | -uwin* | -mks* | -rhapsody* | -darwin* | -opened* \
| -openstep* | -oskit* | -conix* | -pw32* | -nonstopux* \
| -storm-chaos* | -tops10* | -tenex* | -tops20* | -its* \
| -os2* | -vos* | -palmos* | -uclinux* | -nucleus* \
| -morphos* | -superux* | -rtmk* | -rtmk-nova* | -windiss* \
| -powermax* | -dnix* | -nx6 | -nx7 | -sei* | -dragonfly* \
| -skyos* | -haiku* | -rdos* | -toppers* | -drops* | -es* | -tirtos*)
| -skyos* | -haiku* | -rdos* | -toppers* | -drops* | -es* \
| -onefs* | -tirtos* | -phoenix* | -fuchsia*)
# Remember, each alternative MUST END IN *, to match a version number.
;;
-qnx*)
......@@ -1404,9 +1433,6 @@ case $os in
-mac*)
os=`echo $os | sed -e 's|mac|macos|'`
;;
# Apple iOS
-ios*)
;;
-linux-dietlibc)
os=-linux-dietlibc
;;
......@@ -1515,6 +1541,8 @@ case $os in
;;
-nacl*)
;;
-ios)
;;
-none)
;;
*)
......
This source diff could not be displayed because it is too large. You can view the blob instead.
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_CFLAGS_APPEND(cflag)
AC_DEFUN([JE_CFLAGS_APPEND],
[
AC_MSG_CHECKING([whether compiler supports $1])
TCFLAGS="${CFLAGS}"
if test "x${CFLAGS}" = "x" ; then
CFLAGS="$1"
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
$1="[$]{$2}[$]{$3}"
else
CFLAGS="${CFLAGS} $1"
$1="[$]{$2} [$]{$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_appended=$1]
[je_cv_cflags_added=$1]
AC_MSG_RESULT([yes]),
[je_cv_cflags_appended=]
[je_cv_cflags_added=]
AC_MSG_RESULT([no])
[CFLAGS="${TCFLAGS}"]
[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
dnl Use AC_LINK_IFELSE() rather than AC_COMPILE_IFELSE() so that linker errors
dnl cause failure.
AC_DEFUN([JE_COMPILABLE],
......@@ -116,6 +181,7 @@ 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],
......@@ -129,31 +195,122 @@ if test "x$GCC" != "xyes" ; then
[je_cv_msvc=no])])
fi
if test "x$CFLAGS" = "x" ; then
no_CFLAGS="yes"
if test "x$GCC" = "xyes" ; then
JE_CFLAGS_APPEND([-std=gnu99])
if test "x$je_cv_cflags_appended" = "x-std=gnu99" ; then
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
JE_CFLAGS_APPEND([-Wall])
JE_CFLAGS_APPEND([-Werror=declaration-after-statement])
JE_CFLAGS_APPEND([-pipe])
JE_CFLAGS_APPEND([-g3])
elif test "x$je_cv_msvc" = "xyes" ; then
CC="$CC -nologo"
JE_CFLAGS_APPEND([-Zi])
JE_CFLAGS_APPEND([-MT])
JE_CFLAGS_APPEND([-W3])
JE_CFLAGS_APPEND([-FS])
CPPFLAGS="$CPPFLAGS -I${srcdir}/include/msvc_compat"
fi
JE_CFLAGS_ADD([-Wall])
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
dnl Append EXTRA_CFLAGS to CFLAGS, if defined.
if test "x$EXTRA_CFLAGS" != "x" ; then
JE_CFLAGS_APPEND([$EXTRA_CFLAGS])
,
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([-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="${SAVED_LIBS}"
fi
else
enable_cxx="0"
fi
fi
AC_PROG_CPP
AC_SUBST([enable_cxx])
AC_SUBST([CONFIGURE_CXXFLAGS])
AC_SUBST([SPECIFIED_CXXFLAGS])
AC_SUBST([EXTRA_CXXFLAGS])
AC_C_BIGENDIAN([ac_cv_big_endian=1], [ac_cv_big_endian=0])
if test "x${ac_cv_big_endian}" = "x1" ; then
......@@ -161,16 +318,21 @@ if test "x${ac_cv_big_endian}" = "x1" ; then
fi
if test "x${je_cv_msvc}" = "xyes" -a "x${ac_cv_header_inttypes_h}" = "xno"; then
CPPFLAGS="$CPPFLAGS -I${srcdir}/include/msvc_compat/C99"
JE_APPEND_VS(CPPFLAGS, -I${srcdir}/include/msvc_compat/C99)
fi
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
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_MSG_ERROR([Unsupported pointer size: ${ac_cv_sizeof_void_p}])
AC_CHECK_SIZEOF([void *])
if test "x${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])
......@@ -194,6 +356,16 @@ else
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${ac_cv_sizeof_intmax_t}" = "x16" ; then
LG_SIZEOF_INTMAX_T=4
......@@ -211,22 +383,119 @@ dnl CPU-specific settings.
CPU_SPINWAIT=""
case "${host_cpu}" in
i686|x86_64)
AC_CACHE_VAL([je_cv_pause],
[JE_COMPILABLE([pause instruction], [],
[[__asm__ volatile("pause"); return 0;]],
[je_cv_pause])])
if test "x${je_cv_pause}" = "xyes" ; then
CPU_SPINWAIT='__asm__ volatile("pause")'
HAVE_CPU_SPINWAIT=1
if test "x${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
;;
powerpc)
AC_DEFINE_UNQUOTED([HAVE_ALTIVEC], [ ])
;;
*)
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}"
......@@ -234,36 +503,53 @@ 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${je_cv_cray}" = "xyes" ; then
CC_MM=
fi
AN_MAKEVAR([AR], [AC_PROG_AR])
AN_PROGRAM([ar], [AC_PROG_AR])
AC_DEFUN([AC_PROG_AR], [AC_CHECK_TOOL(AR, ar, :)])
AC_PROG_AR
AN_MAKEVAR([NM], [AC_PROG_NM])
AN_PROGRAM([nm], [AC_PROG_NM])
AC_DEFUN([AC_PROG_NM], [AC_CHECK_TOOL(NM, nm, :)])
AC_PROG_NM
AC_PROG_AWK
dnl Platform-specific settings. abi and RPATH can probably be determined
dnl programmatically, but doing so is error-prone, which makes it generally
dnl not worth the trouble.
dnl
dnl
dnl Define cpp macros in CPPFLAGS, rather than doing AC_DEFINE(macro), since the
dnl definitions need to be seen before any headers are included, which is a pain
dnl to make happen otherwise.
default_munmap="1"
default_retain="0"
maps_coalesce="1"
DUMP_SYMS="${NM} -a"
SYM_PREFIX=""
case "${host}" in
*-*-darwin* | *-*-ios*)
CFLAGS="$CFLAGS"
abi="macho"
AC_DEFINE([JEMALLOC_PURGE_MADVISE_FREE], [ ])
RPATH=""
LD_PRELOAD_VAR="DYLD_INSERT_LIBRARIES"
so="dylib"
......@@ -272,38 +558,58 @@ case "${host}" in
DSO_LDFLAGS='-shared -Wl,-install_name,$(LIBDIR)/$(@F)'
SOREV="${rev}.${so}"
sbrk_deprecated="1"
SYM_PREFIX="_"
;;
*-*-freebsd*)
CFLAGS="$CFLAGS"
abi="elf"
AC_DEFINE([JEMALLOC_PURGE_MADVISE_FREE], [ ])
AC_DEFINE([JEMALLOC_SYSCTL_VM_OVERCOMMIT], [ ])
force_lazy_lock="1"
;;
*-*-dragonfly*)
CFLAGS="$CFLAGS"
abi="elf"
AC_DEFINE([JEMALLOC_PURGE_MADVISE_FREE], [ ])
;;
*-*-openbsd*)
CFLAGS="$CFLAGS"
abi="elf"
AC_DEFINE([JEMALLOC_PURGE_MADVISE_FREE], [ ])
force_tls="0"
;;
*-*-bitrig*)
CFLAGS="$CFLAGS"
abi="elf"
AC_DEFINE([JEMALLOC_PURGE_MADVISE_FREE], [ ])
;;
*-*-linux-android)
dnl syscall(2) and secure_getenv(3) are exposed by _GNU_SOURCE.
JE_APPEND_VS(CPPFLAGS, -D_GNU_SOURCE)
abi="elf"
AC_DEFINE([JEMALLOC_PURGE_MADVISE_DONTNEED_ZEROS], [ ])
AC_DEFINE([JEMALLOC_HAS_ALLOCA_H])
AC_DEFINE([JEMALLOC_PROC_SYS_VM_OVERCOMMIT_MEMORY], [ ])
AC_DEFINE([JEMALLOC_THREADED_INIT], [ ])
AC_DEFINE([JEMALLOC_C11_ATOMICS])
force_tls="0"
if test "${LG_SIZEOF_PTR}" = "3"; then
default_retain="1"
fi
;;
*-*-linux*)
CFLAGS="$CFLAGS"
CPPFLAGS="$CPPFLAGS -D_GNU_SOURCE"
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_PURGE_MADVISE_DONTNEED], [ ])
AC_DEFINE([JEMALLOC_PROC_SYS_VM_OVERCOMMIT_MEMORY], [ ])
AC_DEFINE([JEMALLOC_THREADED_INIT], [ ])
AC_DEFINE([JEMALLOC_USE_CXX_THROW], [ ])
if test "${LG_SIZEOF_PTR}" = "3"; then
default_retain="1"
fi
;;
*-*-kfreebsd*)
dnl syscall(2) and secure_getenv(3) are exposed by _GNU_SOURCE.
JE_APPEND_VS(CPPFLAGS, -D_GNU_SOURCE)
abi="elf"
AC_DEFINE([JEMALLOC_HAS_ALLOCA_H])
AC_DEFINE([JEMALLOC_SYSCTL_VM_OVERCOMMIT], [ ])
AC_DEFINE([JEMALLOC_THREADED_INIT], [ ])
AC_DEFINE([JEMALLOC_USE_CXX_THROW], [ ])
default_munmap="0"
;;
*-*-netbsd*)
AC_MSG_CHECKING([ABI])
......@@ -314,22 +620,19 @@ case "${host}" in
#error aout
#endif
]])],
[CFLAGS="$CFLAGS"; abi="elf"],
[abi="elf"],
[abi="aout"])
AC_MSG_RESULT([$abi])
AC_DEFINE([JEMALLOC_PURGE_MADVISE_FREE], [ ])
;;
*-*-solaris2*)
CFLAGS="$CFLAGS"
abi="elf"
AC_DEFINE([JEMALLOC_PURGE_MADVISE_FREE], [ ])
RPATH='-Wl,-R,$(1)'
dnl Solaris needs this for sigwait().
CPPFLAGS="$CPPFLAGS -D_POSIX_PTHREAD_SEMANTICS"
LIBS="$LIBS -lposix4 -lsocket -lnsl"
JE_APPEND_VS(CPPFLAGS, -D_POSIX_PTHREAD_SEMANTICS)
JE_APPEND_VS(LIBS, -lposix4 -lsocket -lnsl)
;;
*-ibm-aix*)
if "$LG_SIZEOF_PTR" = "8"; then
if test "${LG_SIZEOF_PTR}" = "3"; then
dnl 64bit AIX
LD_PRELOAD_VAR="LDR_PRELOAD64"
else
......@@ -341,7 +644,6 @@ case "${host}" in
*-*-mingw* | *-*-cygwin*)
abi="pecoff"
force_tls="0"
force_lazy_lock="1"
maps_coalesce="0"
RPATH=""
so="dll"
......@@ -358,7 +660,15 @@ case "${host}" in
else
importlib="${so}"
DSO_LDFLAGS="-shared"
link_whole_archive="1"
fi
case "${host}" in
*-*-cygwin*)
DUMP_SYMS="dumpbin /SYMBOLS"
;;
*)
;;
esac
a="lib"
libprefix=""
SOREV="${so}"
......@@ -395,17 +705,29 @@ AC_SUBST([o])
AC_SUBST([a])
AC_SUBST([exe])
AC_SUBST([libprefix])
AC_SUBST([link_whole_archive])
AC_SUBST([DSO_LDFLAGS])
AC_SUBST([EXTRA_LDFLAGS])
AC_SUBST([SOREV])
AC_SUBST([PIC_CFLAGS])
AC_SUBST([CTARGET])
AC_SUBST([LDTARGET])
AC_SUBST([TEST_LD_MODE])
AC_SUBST([MKLIB])
AC_SUBST([ARFLAGS])
AC_SUBST([AROUT])
AC_SUBST([DUMP_SYMS])
AC_SUBST([CC_MM])
dnl Determine whether libm must be linked to use e.g. log(3).
AC_SEARCH_LIBS([log], [m], , [AC_MSG_ERROR([Missing math functions])])
if test "x$ac_cv_search_log" != "xnone required" ; then
LM="$ac_cv_search_log"
else
LM=
fi
AC_SUBST(LM)
JE_COMPILABLE([__attribute__ syntax],
[static __attribute__((unused)) void foo(void){}],
[],
......@@ -413,51 +735,53 @@ JE_COMPILABLE([__attribute__ syntax],
if test "x${je_cv_attribute}" = "xyes" ; then
AC_DEFINE([JEMALLOC_HAVE_ATTR], [ ])
if test "x${GCC}" = "xyes" -a "x${abi}" = "xelf"; then
JE_CFLAGS_APPEND([-fvisibility=hidden])
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).
SAVED_CFLAGS="${CFLAGS}"
JE_CFLAGS_APPEND([-Werror])
JE_CFLAGS_SAVE()
JE_CFLAGS_ADD([-Werror])
JE_CFLAGS_ADD([-herror_on_warning])
JE_COMPILABLE([tls_model attribute], [],
[static __thread int
__attribute__((tls_model("initial-exec"), unused)) foo;
foo = 0;],
[je_cv_tls_model])
CFLAGS="${SAVED_CFLAGS}"
if test "x${je_cv_tls_model}" = "xyes" ; then
AC_DEFINE([JEMALLOC_TLS_MODEL],
[__attribute__((tls_model("initial-exec")))])
else
AC_DEFINE([JEMALLOC_TLS_MODEL], [ ])
fi
JE_CFLAGS_RESTORE()
dnl (Setting of JEMALLOC_TLS_MODEL is done later, after we've checked for
dnl --disable-initial-exec-tls)
dnl Check for alloc_size attribute support.
SAVED_CFLAGS="${CFLAGS}"
JE_CFLAGS_APPEND([-Werror])
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])
CFLAGS="${SAVED_CFLAGS}"
JE_CFLAGS_RESTORE()
if test "x${je_cv_alloc_size}" = "xyes" ; then
AC_DEFINE([JEMALLOC_HAVE_ATTR_ALLOC_SIZE], [ ])
fi
dnl Check for format(gnu_printf, ...) attribute support.
SAVED_CFLAGS="${CFLAGS}"
JE_CFLAGS_APPEND([-Werror])
JE_CFLAGS_SAVE()
JE_CFLAGS_ADD([-Werror])
JE_CFLAGS_ADD([-herror_on_warning])
JE_COMPILABLE([format(gnu_printf, ...) attribute], [#include <stdlib.h>],
[void *foo(const char *format, ...) __attribute__((format(gnu_printf, 1, 2)));],
[je_cv_format_gnu_printf])
CFLAGS="${SAVED_CFLAGS}"
JE_CFLAGS_RESTORE()
if test "x${je_cv_format_gnu_printf}" = "xyes" ; then
AC_DEFINE([JEMALLOC_HAVE_ATTR_FORMAT_GNU_PRINTF], [ ])
fi
dnl Check for format(printf, ...) attribute support.
SAVED_CFLAGS="${CFLAGS}"
JE_CFLAGS_APPEND([-Werror])
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])
CFLAGS="${SAVED_CFLAGS}"
JE_CFLAGS_RESTORE()
if test "x${je_cv_format_printf}" = "xyes" ; then
AC_DEFINE([JEMALLOC_HAVE_ATTR_FORMAT_PRINTF], [ ])
fi
......@@ -492,41 +816,6 @@ AC_PROG_RANLIB
AC_PATH_PROG([LD], [ld], [false], [$PATH])
AC_PATH_PROG([AUTOCONF], [autoconf], [false], [$PATH])
public_syms="malloc_conf malloc_message malloc calloc posix_memalign aligned_alloc realloc free mallocx rallocx xallocx sallocx dallocx sdallocx nallocx mallctl mallctlnametomib mallctlbymib malloc_stats_print malloc_usable_size"
dnl Check for allocator-related functions that should be wrapped.
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 Do not compute test code coverage by default.
GCOV_FLAGS=
AC_ARG_ENABLE([code-coverage],
[AS_HELP_STRING([--enable-code-coverage],
[Enable code coverage])],
[if test "x$enable_code_coverage" = "xno" ; then
enable_code_coverage="0"
else
enable_code_coverage="1"
fi
],
[enable_code_coverage="0"]
)
if test "x$enable_code_coverage" = "x1" ; then
deoptimize="no"
echo "$CFLAGS $EXTRA_CFLAGS" | grep '\-O' >/dev/null || deoptimize="yes"
if test "x${deoptimize}" = "xyes" ; then
JE_CFLAGS_APPEND([-O0])
fi
JE_CFLAGS_APPEND([-fprofile-arcs -ftest-coverage])
EXTRA_LDFLAGS="$EXTRA_LDFLAGS -fprofile-arcs -ftest-coverage"
AC_DEFINE([JEMALLOC_CODE_COVERAGE], [ ])
fi
AC_SUBST([enable_code_coverage])
dnl Perform no name mangling by default.
AC_ARG_WITH([mangling],
[AS_HELP_STRING([--with-mangling=<map>], [Mangle symbols in <map>])],
......@@ -542,11 +831,14 @@ else
JEMALLOC_PREFIX="je_"
fi]
)
if test "x$JEMALLOC_PREFIX" != "x" ; then
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], ["$JEMALLOC_CPREFIX"])
fi
AC_SUBST([JEMALLOC_PREFIX])
AC_SUBST([JEMALLOC_CPREFIX])
AC_ARG_WITH([export],
......@@ -556,6 +848,49 @@ AC_ARG_WITH([export],
fi]
)
public_syms="aligned_alloc calloc dallocx free mallctl mallctlbymib mallctlnametomib malloc malloc_conf malloc_message malloc_stats_print malloc_usable_size mallocx nallocx posix_memalign rallocx realloc sallocx sdallocx xallocx"
dnl Check for additional platform-specific public API functions.
AC_CHECK_FUNC([memalign],
[AC_DEFINE([JEMALLOC_OVERRIDE_MEMALIGN], [ ])
public_syms="${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="${wrap_syms} tls_callback"
;;
*)
;;
esac
dnl Mangle library-private APIs.
AC_ARG_WITH([private_namespace],
[AS_HELP_STRING([--with-private-namespace=<prefix>], [Prefix to prepend to all library-private APIs])],
......@@ -575,6 +910,15 @@ AC_ARG_WITH([install_suffix],
install_suffix="$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], ["$config_malloc_conf"])
dnl Substitute @je_@ in jemalloc_protos.h.in, primarily to make generation of
dnl jemalloc_protos_jet.h easy.
je_="je_"
......@@ -588,7 +932,7 @@ cfgoutputs_in="${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_internal.h.in"
cfgoutputs_in="${cfgoutputs_in} include/jemalloc/internal/jemalloc_preamble.h.in"
cfgoutputs_in="${cfgoutputs_in} test/test.sh.in"
cfgoutputs_in="${cfgoutputs_in} test/include/test/jemalloc_test.h.in"
......@@ -600,7 +944,7 @@ cfgoutputs_out="${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_internal.h"
cfgoutputs_out="${cfgoutputs_out} include/jemalloc/internal/jemalloc_preamble.h"
cfgoutputs_out="${cfgoutputs_out} test/test.sh"
cfgoutputs_out="${cfgoutputs_out} test/include/test/jemalloc_test.h"
......@@ -612,15 +956,14 @@ cfgoutputs_tup="${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_internal.h"
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="${cfghdrs_in} include/jemalloc/internal/private_unnamespace.sh"
cfghdrs_in="${cfghdrs_in} include/jemalloc/internal/private_symbols.txt"
cfghdrs_in="${cfghdrs_in} include/jemalloc/internal/public_namespace.sh"
cfghdrs_in="${cfghdrs_in} include/jemalloc/internal/public_unnamespace.sh"
cfghdrs_in="${cfghdrs_in} include/jemalloc/internal/size_classes.sh"
......@@ -631,8 +974,8 @@ cfghdrs_in="${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="${cfghdrs_out} include/jemalloc/internal/private_namespace.h"
cfghdrs_out="${cfghdrs_out} include/jemalloc/internal/private_unnamespace.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="${cfghdrs_out} include/jemalloc/internal/public_unnamespace.h"
......@@ -648,26 +991,10 @@ cfghdrs_tup="include/jemalloc/jemalloc_defs.h:include/jemalloc/jemalloc_defs.h.i
cfghdrs_tup="${cfghdrs_tup} include/jemalloc/internal/jemalloc_internal_defs.h:include/jemalloc/internal/jemalloc_internal_defs.h.in"
cfghdrs_tup="${cfghdrs_tup} test/include/test/jemalloc_test_defs.h:test/include/test/jemalloc_test_defs.h.in"
dnl Silence irrelevant compiler warnings by default.
AC_ARG_ENABLE([cc-silence],
[AS_HELP_STRING([--disable-cc-silence],
[Do not silence irrelevant compiler warnings])],
[if test "x$enable_cc_silence" = "xno" ; then
enable_cc_silence="0"
else
enable_cc_silence="1"
fi
],
[enable_cc_silence="1"]
)
if test "x$enable_cc_silence" = "x1" ; then
AC_DEFINE([JEMALLOC_CC_SILENCE], [ ])
fi
dnl Do not compile with debugging by default.
AC_ARG_ENABLE([debug],
[AS_HELP_STRING([--enable-debug],
[Build debugging code (implies --enable-ivsalloc)])],
[Build debugging code])],
[if test "x$enable_debug" = "xno" ; then
enable_debug="0"
else
......@@ -681,40 +1008,21 @@ if test "x$enable_debug" = "x1" ; then
fi
if test "x$enable_debug" = "x1" ; then
AC_DEFINE([JEMALLOC_DEBUG], [ ])
enable_ivsalloc="1"
fi
AC_SUBST([enable_debug])
dnl Do not validate pointers by default.
AC_ARG_ENABLE([ivsalloc],
[AS_HELP_STRING([--enable-ivsalloc],
[Validate pointers passed through the public API])],
[if test "x$enable_ivsalloc" = "xno" ; then
enable_ivsalloc="0"
else
enable_ivsalloc="1"
fi
],
[enable_ivsalloc="0"]
)
if test "x$enable_ivsalloc" = "x1" ; then
AC_DEFINE([JEMALLOC_IVSALLOC], [ ])
fi
dnl Only optimize if not debugging.
if test "x$enable_debug" = "x0" -a "x$no_CFLAGS" = "xyes" ; then
dnl Make sure that an optimization flag was not specified in EXTRA_CFLAGS.
optimize="no"
echo "$CFLAGS $EXTRA_CFLAGS" | grep '\-O' >/dev/null || optimize="yes"
if test "x${optimize}" = "xyes" ; then
if test "x$GCC" = "xyes" ; then
JE_CFLAGS_APPEND([-O3])
JE_CFLAGS_APPEND([-funroll-loops])
elif test "x$je_cv_msvc" = "xyes" ; then
JE_CFLAGS_APPEND([-O2])
else
JE_CFLAGS_APPEND([-O])
fi
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$je_cv_msvc" = "xyes" ; then
JE_CFLAGS_ADD([-O2])
JE_CXXFLAGS_ADD([-O2])
else
JE_CFLAGS_ADD([-O])
JE_CXXFLAGS_ADD([-O])
fi
fi
......@@ -778,10 +1086,10 @@ fi,
if test "x$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], [LIBS="$LIBS $LUNWIND"],
AC_CHECK_LIB([unwind], [unw_backtrace], [JE_APPEND_VS(LIBS, $LUNWIND)],
[enable_prof_libunwind="0"])
else
LIBS="$LIBS $LUNWIND"
JE_APPEND_VS(LIBS, $LUNWIND)
fi
if test "x${enable_prof_libunwind}" = "x1" ; then
backtrace_method="libunwind"
......@@ -803,7 +1111,9 @@ fi
if test "x$backtrace_method" = "x" -a "x$enable_prof_libgcc" = "x1" \
-a "x$GCC" = "xyes" ; then
AC_CHECK_HEADERS([unwind.h], , [enable_prof_libgcc="0"])
AC_CHECK_LIB([gcc], [_Unwind_Backtrace], [LIBS="$LIBS -lgcc"], [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], [ ])
......@@ -825,7 +1135,7 @@ fi
)
if test "x$backtrace_method" = "x" -a "x$enable_prof_gcc" = "x1" \
-a "x$GCC" = "xyes" ; then
JE_CFLAGS_APPEND([-fno-omit-frame-pointer])
JE_CFLAGS_ADD([-fno-omit-frame-pointer])
backtrace_method="gcc intrinsics"
AC_DEFINE([JEMALLOC_PROF_GCC], [ ])
else
......@@ -839,52 +1149,23 @@ fi
AC_MSG_CHECKING([configured backtracing method])
AC_MSG_RESULT([$backtrace_method])
if test "x$enable_prof" = "x1" ; then
if test "x$abi" != "xpecoff"; then
dnl Heap profiling uses the log(3) function.
LIBS="$LIBS -lm"
fi
dnl Heap profiling uses the log(3) function.
JE_APPEND_VS(LIBS, $LM)
AC_DEFINE([JEMALLOC_PROF], [ ])
fi
AC_SUBST([enable_prof])
dnl Enable thread-specific caching by default.
AC_ARG_ENABLE([tcache],
[AS_HELP_STRING([--disable-tcache], [Disable per thread caches])],
[if test "x$enable_tcache" = "xno" ; then
enable_tcache="0"
else
enable_tcache="1"
fi
],
[enable_tcache="1"]
)
if test "x$enable_tcache" = "x1" ; then
AC_DEFINE([JEMALLOC_TCACHE], [ ])
fi
AC_SUBST([enable_tcache])
dnl Indicate whether adjacent virtual memory mappings automatically coalesce
dnl (and fragment on demand).
if test "x${maps_coalesce}" = "x1" ; then
AC_DEFINE([JEMALLOC_MAPS_COALESCE], [ ])
fi
dnl Enable VM deallocation via munmap() by default.
AC_ARG_ENABLE([munmap],
[AS_HELP_STRING([--disable-munmap], [Disable VM deallocation via munmap(2)])],
[if test "x$enable_munmap" = "xno" ; then
enable_munmap="0"
else
enable_munmap="1"
dnl Indicate whether to retain memory (rather than using munmap()) by default.
if test "x$default_retain" = "x1" ; then
AC_DEFINE([JEMALLOC_RETAIN], [ ])
fi
],
[enable_munmap="${default_munmap}"]
)
if test "x$enable_munmap" = "x1" ; then
AC_DEFINE([JEMALLOC_MUNMAP], [ ])
fi
AC_SUBST([enable_munmap])
dnl Enable allocation from DSS if supported by the OS.
have_dss="1"
......@@ -905,8 +1186,7 @@ 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, quarantine, and redzones])],
[AS_HELP_STRING([--disable-fill], [Disable support for junk/zero filling])],
[if test "x$enable_fill" = "xno" ; then
enable_fill="0"
else
......@@ -948,35 +1228,6 @@ if test "x$enable_utrace" = "x1" ; then
fi
AC_SUBST([enable_utrace])
dnl Support Valgrind by default.
AC_ARG_ENABLE([valgrind],
[AS_HELP_STRING([--disable-valgrind], [Disable support for Valgrind])],
[if test "x$enable_valgrind" = "xno" ; then
enable_valgrind="0"
else
enable_valgrind="1"
fi
],
[enable_valgrind="1"]
)
if test "x$enable_valgrind" = "x1" ; then
JE_COMPILABLE([valgrind], [
#include <valgrind/valgrind.h>
#include <valgrind/memcheck.h>
#if !defined(VALGRIND_RESIZEINPLACE_BLOCK)
# error "Incompatible Valgrind version"
#endif
], [], [je_cv_valgrind])
if test "x${je_cv_valgrind}" = "xno" ; then
enable_valgrind="0"
fi
if test "x$enable_valgrind" = "x1" ; then
AC_DEFINE([JEMALLOC_VALGRIND], [ ])
fi
fi
AC_SUBST([enable_valgrind])
dnl Do not support the xmalloc option by default.
AC_ARG_ENABLE([xmalloc],
[AS_HELP_STRING([--enable-xmalloc], [Support xmalloc option])],
......@@ -1010,11 +1261,43 @@ if test "x$enable_cache_oblivious" = "x1" ; then
fi
AC_SUBST([enable_cache_oblivious])
dnl Do not log by default.
AC_ARG_ENABLE([log],
[AS_HELP_STRING([--enable-log], [Support debug logging])],
[if test "x$enable_log" = "xno" ; then
enable_log="0"
else
enable_log="1"
fi
],
[enable_log="0"]
)
if test "x$enable_log" = "x1" ; then
AC_DEFINE([JEMALLOC_LOG], [ ])
fi
AC_SUBST([enable_log])
JE_COMPILABLE([a program using __builtin_unreachable], [
void foo (void) {
__builtin_unreachable();
}
], [
{
foo();
}
], [je_cv_gcc_builtin_unreachable])
if test "x${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() or __builtin_ffs() are defined if
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>
......@@ -1027,6 +1310,7 @@ JE_COMPILABLE([a program using __builtin_ffsl], [
}
], [je_cv_gcc_builtin_ffsl])
if test "x${je_cv_gcc_builtin_ffsl}" = "xyes" ; then
AC_DEFINE([JEMALLOC_INTERNAL_FFSLL], [__builtin_ffsll])
AC_DEFINE([JEMALLOC_INTERNAL_FFSL], [__builtin_ffsl])
AC_DEFINE([JEMALLOC_INTERNAL_FFS], [__builtin_ffs])
else
......@@ -1041,6 +1325,7 @@ else
}
], [je_cv_function_ffsl])
if test "x${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
......@@ -1048,13 +1333,6 @@ else
fi
fi
AC_ARG_WITH([lg_tiny_min],
[AS_HELP_STRING([--with-lg-tiny-min=<lg-tiny-min>],
[Base 2 log of minimum tiny size class to support])],
[LG_TINY_MIN="$with_lg_tiny_min"],
[LG_TINY_MIN="3"])
AC_DEFINE_UNQUOTED([LG_TINY_MIN], [$LG_TINY_MIN])
AC_ARG_WITH([lg_quantum],
[AS_HELP_STRING([--with-lg-quantum=<lg-quantum>],
[Base 2 log of minimum allocation alignment])],
......@@ -1100,7 +1378,7 @@ if test "x$LG_PAGE" = "xdetect"; then
if (f == NULL) {
return 1;
}
fprintf(f, "%d\n", result);
fprintf(f, "%d", result);
fclose(f);
return 0;
......@@ -1118,42 +1396,83 @@ else
AC_MSG_ERROR([cannot determine value for LG_PAGE])
fi
AC_ARG_WITH([lg_hugepage],
[AS_HELP_STRING([--with-lg-hugepage=<lg-hugepage>],
[Base 2 log of system huge page size])],
[je_cv_lg_hugepage="${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}])
AC_ARG_WITH([lg_page_sizes],
[AS_HELP_STRING([--with-lg-page-sizes=<lg-page-sizes>],
[Base 2 logs of system page sizes to support])],
[LG_PAGE_SIZES="$with_lg_page_sizes"], [LG_PAGE_SIZES="$LG_PAGE"])
AC_ARG_WITH([lg_size_class_group],
[AS_HELP_STRING([--with-lg-size-class-group=<lg-size-class-group>],
[Base 2 log of size classes per doubling])],
[LG_SIZE_CLASS_GROUP="$with_lg_size_class_group"],
[LG_SIZE_CLASS_GROUP="2"])
dnl ============================================================================
dnl jemalloc configuration.
dnl
dnl Set VERSION if source directory is inside a git repository.
if test "x`test ! \"${srcroot}\" && cd \"${srcroot}\"; git rev-parse --is-inside-work-tree 2>/dev/null`" = "xtrue" ; then
dnl Pattern globs aren't powerful enough to match both single- and
dnl double-digit version numbers, so iterate over patterns to support up to
dnl version 99.99.99 without any accidental matches.
rm -f "${objroot}VERSION"
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
if test ! -e "${objroot}VERSION" ; then
(test ! "${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" "${objroot}VERSION"
break
dnl
AC_ARG_WITH([version],
[AS_HELP_STRING([--with-version=<major>.<minor>.<bugfix>-<nrev>-g<gid>],
[Version string])],
[
echo "${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
done
fi
rm -f "${objroot}VERSION.tmp"
], [
dnl Set VERSION if source directory is inside a git repository.
if test "x`test ! \"${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(
......@@ -1180,23 +1499,128 @@ dnl ============================================================================
dnl Configure pthreads.
if test "x$abi" != "xpecoff" ; then
AC_DEFINE([JEMALLOC_HAVE_PTHREAD], [ ])
AC_CHECK_HEADERS([pthread.h], , [AC_MSG_ERROR([pthread.h is missing])])
dnl Some systems may embed pthreads functionality in libc; check for libpthread
dnl first, but try libc too before failing.
AC_CHECK_LIB([pthread], [pthread_create], [LIBS="$LIBS -lpthread"],
AC_CHECK_LIB([pthread], [pthread_create], [JE_APPEND_VS(LIBS, -lpthread)],
[AC_SEARCH_LIBS([pthread_create], , ,
AC_MSG_ERROR([libpthread is missing]))])
wrap_syms="${wrap_syms} pthread_create"
have_pthread="1"
dnl Check if we have dlsym support.
have_dlsym="1"
AC_CHECK_HEADERS([dlfcn.h],
AC_CHECK_FUNC([dlsym], [],
[AC_CHECK_LIB([dl], [dlsym], [LIBS="$LIBS -ldl"], [have_dlsym="0"])]),
[have_dlsym="0"])
if test "x$have_dlsym" = "x1" ; then
AC_DEFINE([JEMALLOC_HAVE_DLSYM], [ ])
fi
JE_COMPILABLE([pthread_atfork(3)], [
#include <pthread.h>
], [
pthread_atfork((void *)0, (void *)0, (void *)0);
], [je_cv_pthread_atfork])
if test "x${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${je_cv_clock_monotonic}" = "xyes" ; then
AC_DEFINE([JEMALLOC_HAVE_CLOCK_MONOTONIC])
fi
CPPFLAGS="$CPPFLAGS -D_REENTRANT"
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${je_cv_mach_absolute_time}" = "xyes" ; then
AC_DEFINE([JEMALLOC_HAVE_MACH_ABSOLUTE_TIME])
fi
dnl Check whether clock_gettime(2) is in libc or librt. This function is only
dnl used in test code, so save the result to TESTLIBS to avoid poluting LIBS.
SAVED_LIBS="${LIBS}"
LIBS=
AC_SEARCH_LIBS([clock_gettime], [rt], [TESTLIBS="${LIBS}"])
AC_SUBST([TESTLIBS])
LIBS="${SAVED_LIBS}"
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$je_cv_syscall" = "xyes" ; then
AC_DEFINE([JEMALLOC_USE_SYSCALL], [ ])
fi
fi
dnl Check if the GNU-specific secure_getenv function exists.
AC_CHECK_FUNC([secure_getenv],
......@@ -1207,6 +1631,24 @@ if test "x$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"],
......@@ -1226,6 +1668,7 @@ AC_CHECK_FUNC([_malloc_thread_cleanup],
)
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
......@@ -1238,6 +1681,7 @@ AC_CHECK_FUNC([_pthread_mutex_init_calloc_cb],
)
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.
......@@ -1252,45 +1696,35 @@ fi
],
[enable_lazy_lock=""]
)
if test "x$enable_lazy_lock" = "x" -a "x${force_lazy_lock}" = "x1" ; then
AC_MSG_RESULT([Forcing lazy-lock to avoid allocator/threading bootstrap issues])
enable_lazy_lock="1"
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$enable_lazy_lock" = "x1" ; then
if test "x$abi" != "xpecoff" ; then
AC_CHECK_HEADERS([dlfcn.h], , [AC_MSG_ERROR([dlfcn.h is missing])])
AC_CHECK_FUNC([dlsym], [],
[AC_CHECK_LIB([dl], [dlsym], [LIBS="$LIBS -ldl"],
[AC_MSG_ERROR([libdl is missing])])
])
if test "x$have_dlsym" = "x1" ; then
AC_DEFINE([JEMALLOC_LAZY_LOCK], [ ])
else
AC_MSG_ERROR([Missing dlsym support: lazy-lock cannot be enabled.])
fi
AC_DEFINE([JEMALLOC_LAZY_LOCK], [ ])
else
enable_lazy_lock="0"
fi
AC_SUBST([enable_lazy_lock])
AC_ARG_ENABLE([tls],
[AS_HELP_STRING([--disable-tls], [Disable thread-local storage (__thread keyword)])],
if test "x$enable_tls" = "xno" ; then
dnl Automatically configure TLS.
if test "x${force_tls}" = "x1" ; then
enable_tls="1"
elif test "x${force_tls}" = "x0" ; then
enable_tls="0"
else
enable_tls="1"
fi
,
enable_tls=""
)
if test "x${enable_tls}" = "x" ; then
if test "x${force_tls}" = "x1" ; then
AC_MSG_RESULT([Forcing TLS to avoid allocator/threading bootstrap issues])
enable_tls="1"
elif test "x${force_tls}" = "x0" ; then
AC_MSG_RESULT([Forcing no TLS to avoid allocator/threading bootstrap issues])
enable_tls="0"
else
enable_tls="1"
fi
fi
if test "x${enable_tls}" = "x1" ; then
AC_MSG_CHECKING([for TLS])
AC_COMPILE_IFELSE([AC_LANG_PROGRAM(
......@@ -1309,12 +1743,7 @@ else
fi
AC_SUBST([enable_tls])
if test "x${enable_tls}" = "x1" ; then
if test "x${force_tls}" = "x0" ; then
AC_MSG_WARN([TLS enabled despite being marked unusable on this platform])
fi
AC_DEFINE_UNQUOTED([JEMALLOC_TLS], [ ])
elif test "x${force_tls}" = "x1" ; then
AC_MSG_WARN([TLS disabled despite being marked critical on this platform])
fi
dnl ============================================================================
......@@ -1332,37 +1761,45 @@ JE_COMPILABLE([C11 atomics], [
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_c11atomics])
if test "x${je_cv_c11atomics}" = "xyes" ; then
AC_DEFINE([JEMALLOC_C11ATOMICS])
return r == 0;
], [je_cv_c11_atomics])
if test "x${je_cv_c11_atomics}" = "xyes" ; then
AC_DEFINE([JEMALLOC_C11_ATOMICS])
fi
dnl ============================================================================
dnl Check for atomic(9) operations as provided on FreeBSD.
dnl Check for GCC-style __atomic atomics.
JE_COMPILABLE([atomic(9)], [
#include <sys/types.h>
#include <machine/atomic.h>
#include <inttypes.h>
JE_COMPILABLE([GCC __atomic atomics], [
], [
{
uint32_t x32 = 0;
volatile uint32_t *x32p = &x32;
atomic_fetchadd_32(x32p, 1);
}
{
unsigned long xlong = 0;
volatile unsigned long *xlongp = &xlong;
atomic_fetchadd_long(xlongp, 1);
}
], [je_cv_atomic9])
if test "x${je_cv_atomic9}" = "xyes" ; then
AC_DEFINE([JEMALLOC_ATOMIC9])
int x = 0;
int val = 1;
int y = __atomic_fetch_add(&x, val, __ATOMIC_RELAXED);
int after_add = x;
return after_add == 1;
], [je_cv_gcc_atomic_atomics])
if test "x${je_cv_gcc_atomic_atomics}" = "xyes" ; then
AC_DEFINE([JEMALLOC_GCC_ATOMIC_ATOMICS])
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${je_cv_gcc_sync_atomics}" = "xyes" ; then
AC_DEFINE([JEMALLOC_GCC_SYNC_ATOMICS])
fi
dnl ============================================================================
dnl Check for atomic(3) operations as provided on Darwin.
dnl We need this not for the atomic operations (which are provided above), but
dnl rather for the OSSpinLock type it exposes.
JE_COMPILABLE([Darwin OSAtomic*()], [
#include <libkern/OSAtomic.h>
......@@ -1389,12 +1826,67 @@ dnl Check for madvise(2).
JE_COMPILABLE([madvise(2)], [
#include <sys/mman.h>
], [
{
madvise((void *)0, 0, 0);
}
madvise((void *)0, 0, 0);
], [je_cv_madvise])
if test "x${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 ============================================================================
......@@ -1454,6 +1946,25 @@ 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 Check for spinlock(3) operations as provided on Darwin.
......@@ -1493,37 +2004,38 @@ if test "x${enable_zone_allocator}" = "x1" ; then
AC_MSG_ERROR([--enable-zone-allocator is only supported on Darwin])
fi
AC_DEFINE([JEMALLOC_ZONE], [ ])
fi
dnl The szone version jumped from 3 to 6 between the OS X 10.5.x and 10.6
dnl releases. malloc_zone_t and malloc_introspection_t have new fields in
dnl 10.6, which is the only source-level indication of the change.
AC_MSG_CHECKING([malloc zone version])
AC_DEFUN([JE_ZONE_PROGRAM],
[AC_LANG_PROGRAM(
[#include <malloc/malloc.h>],
[static int foo[[sizeof($1) $2 sizeof(void *) * $3 ? 1 : -1]]]
)])
AC_COMPILE_IFELSE([JE_ZONE_PROGRAM(malloc_zone_t,==,14)],[JEMALLOC_ZONE_VERSION=3],[
AC_COMPILE_IFELSE([JE_ZONE_PROGRAM(malloc_zone_t,==,15)],[JEMALLOC_ZONE_VERSION=5],[
AC_COMPILE_IFELSE([JE_ZONE_PROGRAM(malloc_zone_t,==,16)],[
AC_COMPILE_IFELSE([JE_ZONE_PROGRAM(malloc_introspection_t,==,9)],[JEMALLOC_ZONE_VERSION=6],[
AC_COMPILE_IFELSE([JE_ZONE_PROGRAM(malloc_introspection_t,==,13)],[JEMALLOC_ZONE_VERSION=7],[JEMALLOC_ZONE_VERSION=]
)])],[
AC_COMPILE_IFELSE([JE_ZONE_PROGRAM(malloc_zone_t,==,17)],[JEMALLOC_ZONE_VERSION=8],[
AC_COMPILE_IFELSE([JE_ZONE_PROGRAM(malloc_zone_t,>,17)],[JEMALLOC_ZONE_VERSION=9],[JEMALLOC_ZONE_VERSION=]
)])])])])
if test "x${JEMALLOC_ZONE_VERSION}" = "x"; then
AC_MSG_RESULT([unsupported])
AC_MSG_ERROR([Unsupported malloc zone version])
fi
if test "${JEMALLOC_ZONE_VERSION}" = 9; then
JEMALLOC_ZONE_VERSION=8
AC_MSG_RESULT([> 8])
else
AC_MSG_RESULT([$JEMALLOC_ZONE_VERSION])
fi
AC_DEFINE_UNQUOTED(JEMALLOC_ZONE_VERSION, [$JEMALLOC_ZONE_VERSION])
dnl ============================================================================
dnl Use initial-exec TLS by default.
AC_ARG_ENABLE([initial-exec-tls],
[AS_HELP_STRING([--disable-initial-exec-tls],
[Disable the initial-exec tls model])],
[if test "x$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${have_pthread}" = "x1" -a "x${have_dlsym}" = "x1" \
-a "x${je_cv_os_unfair_lock}" != "xyes" \
-a "x${je_cv_osspin}" != "xyes" ; then
AC_DEFINE([JEMALLOC_BACKGROUND_THREAD])
fi
dnl ============================================================================
......@@ -1542,7 +2054,10 @@ extern void *(* __realloc_hook)(void *ptr, size_t size);
if (__free_hook && ptr) __free_hook(ptr);
], [je_cv_glibc_malloc_hook])
if test "x${je_cv_glibc_malloc_hook}" = "xyes" ; then
AC_DEFINE([JEMALLOC_GLIBC_MALLOC_HOOK], [ ])
if test "x${JEMALLOC_PREFIX}" = "x" ; then
AC_DEFINE([JEMALLOC_GLIBC_MALLOC_HOOK], [ ])
wrap_syms="${wrap_syms} __free_hook __malloc_hook __realloc_hook"
fi
fi
JE_COMPILABLE([glibc memalign hook], [
......@@ -1554,7 +2069,10 @@ extern void *(* __memalign_hook)(size_t alignment, size_t size);
if (__memalign_hook) ptr = __memalign_hook(16, 7);
], [je_cv_glibc_memalign_hook])
if test "x${je_cv_glibc_memalign_hook}" = "xyes" ; then
AC_DEFINE([JEMALLOC_GLIBC_MEMALIGN_HOOK], [ ])
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], [
......@@ -1569,6 +2087,25 @@ 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
......@@ -1576,20 +2113,6 @@ AC_HEADER_STDBOOL
dnl ============================================================================
dnl Define commands that generate output files.
AC_CONFIG_COMMANDS([include/jemalloc/internal/private_namespace.h], [
mkdir -p "${objroot}include/jemalloc/internal"
"${srcdir}/include/jemalloc/internal/private_namespace.sh" "${srcdir}/include/jemalloc/internal/private_symbols.txt" > "${objroot}include/jemalloc/internal/private_namespace.h"
], [
srcdir="${srcdir}"
objroot="${objroot}"
])
AC_CONFIG_COMMANDS([include/jemalloc/internal/private_unnamespace.h], [
mkdir -p "${objroot}include/jemalloc/internal"
"${srcdir}/include/jemalloc/internal/private_unnamespace.sh" "${srcdir}/include/jemalloc/internal/private_symbols.txt" > "${objroot}include/jemalloc/internal/private_unnamespace.h"
], [
srcdir="${srcdir}"
objroot="${objroot}"
])
AC_CONFIG_COMMANDS([include/jemalloc/internal/public_symbols.txt], [
f="${objroot}include/jemalloc/internal/public_symbols.txt"
mkdir -p "${objroot}include/jemalloc/internal"
......@@ -1613,6 +2136,31 @@ AC_CONFIG_COMMANDS([include/jemalloc/internal/public_symbols.txt], [
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" > "${objroot}include/jemalloc/internal/public_namespace.h"
......@@ -1629,15 +2177,13 @@ AC_CONFIG_COMMANDS([include/jemalloc/internal/public_unnamespace.h], [
])
AC_CONFIG_COMMANDS([include/jemalloc/internal/size_classes.h], [
mkdir -p "${objroot}include/jemalloc/internal"
"${SHELL}" "${srcdir}/include/jemalloc/internal/size_classes.sh" "${LG_QUANTA}" ${LG_TINY_MIN} "${LG_PAGE_SIZES}" ${LG_SIZE_CLASS_GROUP} > "${objroot}include/jemalloc/internal/size_classes.h"
"${SHELL}" "${srcdir}/include/jemalloc/internal/size_classes.sh" "${LG_QUANTA}" 3 "${LG_PAGE_SIZES}" 2 > "${objroot}include/jemalloc/internal/size_classes.h"
], [
SHELL="${SHELL}"
srcdir="${srcdir}"
objroot="${objroot}"
LG_QUANTA="${LG_QUANTA}"
LG_TINY_MIN=${LG_TINY_MIN}
LG_PAGE_SIZES="${LG_PAGE_SIZES}"
LG_SIZE_CLASS_GROUP=${LG_SIZE_CLASS_GROUP}
])
AC_CONFIG_COMMANDS([include/jemalloc/jemalloc_protos_jet.h], [
mkdir -p "${objroot}include/jemalloc"
......@@ -1697,12 +2243,18 @@ AC_MSG_RESULT([library revision : ${rev}])
AC_MSG_RESULT([])
AC_MSG_RESULT([CONFIG : ${CONFIG}])
AC_MSG_RESULT([CC : ${CC}])
AC_MSG_RESULT([CFLAGS : ${CFLAGS}])
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([TESTLIBS : ${TESTLIBS}])
AC_MSG_RESULT([RPATH_EXTRA : ${RPATH_EXTRA}])
AC_MSG_RESULT([])
AC_MSG_RESULT([XSLTPROC : ${XSLTPROC}])
......@@ -1724,22 +2276,19 @@ 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([autogen : ${enable_autogen}])
AC_MSG_RESULT([cc-silence : ${enable_cc_silence}])
AC_MSG_RESULT([debug : ${enable_debug}])
AC_MSG_RESULT([code-coverage : ${enable_code_coverage}])
AC_MSG_RESULT([stats : ${enable_stats}])
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([tcache : ${enable_tcache}])
AC_MSG_RESULT([fill : ${enable_fill}])
AC_MSG_RESULT([utrace : ${enable_utrace}])
AC_MSG_RESULT([valgrind : ${enable_valgrind}])
AC_MSG_RESULT([xmalloc : ${enable_xmalloc}])
AC_MSG_RESULT([munmap : ${enable_munmap}])
AC_MSG_RESULT([log : ${enable_log}])
AC_MSG_RESULT([lazy_lock : ${enable_lazy_lock}])
AC_MSG_RESULT([tls : ${enable_tls}])
AC_MSG_RESULT([cache-oblivious : ${enable_cache_oblivious}])
AC_MSG_RESULT([cxx : ${enable_cxx}])
AC_MSG_RESULT([===============================================================================])
#!/bin/sh
set -e
objdir=$1
suffix=$2
shift 2
objs=$@
gcov -b -p -f -o "${objdir}" ${objs}
# Move gcov outputs so that subsequent gcov invocations won't clobber results
# for the same sources with different compilation flags.
for f in `find . -maxdepth 1 -type f -name '*.gcov'` ; do
mv "${f}" "${f}.${suffix}"
done
<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>
'\" t
.\" Title: JEMALLOC
.\" Author: Jason Evans
.\" Generator: DocBook XSL Stylesheets v1.78.1 <http://docbook.sf.net/>
.\" Date: 09/24/2015
.\" Manual: User Manual
.\" Source: jemalloc 4.0.3-0-ge9192eacf8935e29fc62fddc2701f7942b1cc02c
.\" Language: English
.\"
.TH "JEMALLOC" "3" "09/24/2015" "jemalloc 4.0.3-0-ge9192eacf893" "User Manual"
.\" -----------------------------------------------------------------
.\" * Define some portability stuff
.\" -----------------------------------------------------------------
.\" ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.\" http://bugs.debian.org/507673
.\" http://lists.gnu.org/archive/html/groff/2009-02/msg00013.html
.\" ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.ie \n(.g .ds Aq \(aq
.el .ds Aq '
.\" -----------------------------------------------------------------
.\" * set default formatting
.\" -----------------------------------------------------------------
.\" disable hyphenation
.nh
.\" disable justification (adjust text to left margin only)
.ad l
.\" -----------------------------------------------------------------
.\" * MAIN CONTENT STARTS HERE *
.\" -----------------------------------------------------------------
.SH "NAME"
jemalloc \- general purpose memory allocation functions
.SH "LIBRARY"
.PP
This manual describes jemalloc 4\&.0\&.3\-0\-ge9192eacf8935e29fc62fddc2701f7942b1cc02c\&. More information can be found at the
\m[blue]\fBjemalloc website\fR\m[]\&\s-2\u[1]\d\s+2\&.
.SH "SYNOPSIS"
.sp
.ft B
.nf
#include <jemalloc/jemalloc\&.h>
.fi
.ft
.SS "Standard API"
.HP \w'void\ *malloc('u
.BI "void *malloc(size_t\ " "size" ");"
.HP \w'void\ *calloc('u
.BI "void *calloc(size_t\ " "number" ", size_t\ " "size" ");"
.HP \w'int\ posix_memalign('u
.BI "int posix_memalign(void\ **" "ptr" ", size_t\ " "alignment" ", size_t\ " "size" ");"
.HP \w'void\ *aligned_alloc('u
.BI "void *aligned_alloc(size_t\ " "alignment" ", size_t\ " "size" ");"
.HP \w'void\ *realloc('u
.BI "void *realloc(void\ *" "ptr" ", size_t\ " "size" ");"
.HP \w'void\ free('u
.BI "void free(void\ *" "ptr" ");"
.SS "Non\-standard API"
.HP \w'void\ *mallocx('u
.BI "void *mallocx(size_t\ " "size" ", int\ " "flags" ");"
.HP \w'void\ *rallocx('u
.BI "void *rallocx(void\ *" "ptr" ", size_t\ " "size" ", int\ " "flags" ");"
.HP \w'size_t\ xallocx('u
.BI "size_t xallocx(void\ *" "ptr" ", size_t\ " "size" ", size_t\ " "extra" ", int\ " "flags" ");"
.HP \w'size_t\ sallocx('u
.BI "size_t sallocx(void\ *" "ptr" ", int\ " "flags" ");"
.HP \w'void\ dallocx('u
.BI "void dallocx(void\ *" "ptr" ", int\ " "flags" ");"
.HP \w'void\ sdallocx('u
.BI "void sdallocx(void\ *" "ptr" ", size_t\ " "size" ", int\ " "flags" ");"
.HP \w'size_t\ nallocx('u
.BI "size_t nallocx(size_t\ " "size" ", int\ " "flags" ");"
.HP \w'int\ mallctl('u
.BI "int mallctl(const\ char\ *" "name" ", void\ *" "oldp" ", size_t\ *" "oldlenp" ", void\ *" "newp" ", size_t\ " "newlen" ");"
.HP \w'int\ mallctlnametomib('u
.BI "int mallctlnametomib(const\ char\ *" "name" ", size_t\ *" "mibp" ", size_t\ *" "miblenp" ");"
.HP \w'int\ mallctlbymib('u
.BI "int mallctlbymib(const\ size_t\ *" "mib" ", size_t\ " "miblen" ", void\ *" "oldp" ", size_t\ *" "oldlenp" ", void\ *" "newp" ", size_t\ " "newlen" ");"
.HP \w'void\ malloc_stats_print('u
.BI "void malloc_stats_print(void\ " "(*write_cb)" "\ (void\ *,\ const\ char\ *), void\ *" "cbopaque" ", const\ char\ *" "opts" ");"
.HP \w'size_t\ malloc_usable_size('u
.BI "size_t malloc_usable_size(const\ void\ *" "ptr" ");"
.HP \w'void\ (*malloc_message)('u
.BI "void (*malloc_message)(void\ *" "cbopaque" ", const\ char\ *" "s" ");"
.PP
const char *\fImalloc_conf\fR;
.SH "DESCRIPTION"
.SS "Standard API"
.PP
The
\fBmalloc\fR\fB\fR
function allocates
\fIsize\fR
bytes of uninitialized memory\&. The allocated space is suitably aligned (after possible pointer coercion) for storage of any type of object\&.
.PP
The
\fBcalloc\fR\fB\fR
function allocates space for
\fInumber\fR
objects, each
\fIsize\fR
bytes in length\&. The result is identical to calling
\fBmalloc\fR\fB\fR
with an argument of
\fInumber\fR
*
\fIsize\fR, with the exception that the allocated memory is explicitly initialized to zero bytes\&.
.PP
The
\fBposix_memalign\fR\fB\fR
function allocates
\fIsize\fR
bytes of memory such that the allocation\*(Aqs base address is a multiple of
\fIalignment\fR, and returns the allocation in the value pointed to by
\fIptr\fR\&. The requested
\fIalignment\fR
must be a power of 2 at least as large as
sizeof(\fBvoid *\fR)\&.
.PP
The
\fBaligned_alloc\fR\fB\fR
function allocates
\fIsize\fR
bytes of memory such that the allocation\*(Aqs base address is a multiple of
\fIalignment\fR\&. The requested
\fIalignment\fR
must be a power of 2\&. Behavior is undefined if
\fIsize\fR
is not an integral multiple of
\fIalignment\fR\&.
.PP
The
\fBrealloc\fR\fB\fR
function changes the size of the previously allocated memory referenced by
\fIptr\fR
to
\fIsize\fR
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
\fIptr\fR
is freed and a pointer to the newly allocated memory is returned\&. Note that
\fBrealloc\fR\fB\fR
may move the memory allocation, resulting in a different return value than
\fIptr\fR\&. If
\fIptr\fR
is
\fBNULL\fR, the
\fBrealloc\fR\fB\fR
function behaves identically to
\fBmalloc\fR\fB\fR
for the specified size\&.
.PP
The
\fBfree\fR\fB\fR
function causes the allocated memory referenced by
\fIptr\fR
to be made available for future allocations\&. If
\fIptr\fR
is
\fBNULL\fR, no action occurs\&.
.SS "Non\-standard API"
.PP
The
\fBmallocx\fR\fB\fR,
\fBrallocx\fR\fB\fR,
\fBxallocx\fR\fB\fR,
\fBsallocx\fR\fB\fR,
\fBdallocx\fR\fB\fR,
\fBsdallocx\fR\fB\fR, and
\fBnallocx\fR\fB\fR
functions all have a
\fIflags\fR
argument that can be used to specify options\&. The functions only check the options that are contextually relevant\&. Use bitwise or (|) operations to specify one or more of the following:
.PP
\fBMALLOCX_LG_ALIGN(\fR\fB\fIla\fR\fR\fB) \fR
.RS 4
Align the memory allocation to start at an address that is a multiple of
(1 << \fIla\fR)\&. This macro does not validate that
\fIla\fR
is within the valid range\&.
.RE
.PP
\fBMALLOCX_ALIGN(\fR\fB\fIa\fR\fR\fB) \fR
.RS 4
Align the memory allocation to start at an address that is a multiple of
\fIa\fR, where
\fIa\fR
is a power of two\&. This macro does not validate that
\fIa\fR
is a power of 2\&.
.RE
.PP
\fBMALLOCX_ZERO\fR
.RS 4
Initialize newly allocated memory to contain zero bytes\&. In the growing reallocation case, the real size prior to reallocation defines the boundary between untouched bytes and those that are initialized to contain zero bytes\&. If this macro is absent, newly allocated memory is uninitialized\&.
.RE
.PP
\fBMALLOCX_TCACHE(\fR\fB\fItc\fR\fR\fB) \fR
.RS 4
Use the thread\-specific cache (tcache) specified by the identifier
\fItc\fR, which must have been acquired via the
"tcache\&.create"
mallctl\&. This macro does not validate that
\fItc\fR
specifies a valid identifier\&.
.RE
.PP
\fBMALLOCX_TCACHE_NONE\fR
.RS 4
Do not use a thread\-specific cache (tcache)\&. Unless
\fBMALLOCX_TCACHE(\fR\fB\fItc\fR\fR\fB)\fR
or
\fBMALLOCX_TCACHE_NONE\fR
is specified, an automatically managed tcache will be used under many circumstances\&. This macro cannot be used in the same
\fIflags\fR
argument as
\fBMALLOCX_TCACHE(\fR\fB\fItc\fR\fR\fB)\fR\&.
.RE
.PP
\fBMALLOCX_ARENA(\fR\fB\fIa\fR\fR\fB) \fR
.RS 4
Use the arena specified by the index
\fIa\fR\&. This macro has no effect for regions that were allocated via an arena other than the one specified\&. This macro does not validate that
\fIa\fR
specifies an arena index in the valid range\&.
.RE
.PP
The
\fBmallocx\fR\fB\fR
function allocates at least
\fIsize\fR
bytes of memory, and returns a pointer to the base address of the allocation\&. Behavior is undefined if
\fIsize\fR
is
\fB0\fR, or if request size overflows due to size class and/or alignment constraints\&.
.PP
The
\fBrallocx\fR\fB\fR
function resizes the allocation at
\fIptr\fR
to be at least
\fIsize\fR
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
\fIsize\fR
is
\fB0\fR, or if request size overflows due to size class and/or alignment constraints\&.
.PP
The
\fBxallocx\fR\fB\fR
function resizes the allocation at
\fIptr\fR
in place to be at least
\fIsize\fR
bytes, and returns the real size of the allocation\&. If
\fIextra\fR
is non\-zero, an attempt is made to resize the allocation to be at least
(\fIsize\fR + \fIextra\fR)
bytes, though inability to allocate the extra byte(s) will not by itself result in failure to resize\&. Behavior is undefined if
\fIsize\fR
is
\fB0\fR, or if
(\fIsize\fR + \fIextra\fR > \fBSIZE_T_MAX\fR)\&.
.PP
The
\fBsallocx\fR\fB\fR
function returns the real size of the allocation at
\fIptr\fR\&.
.PP
The
\fBdallocx\fR\fB\fR
function causes the memory referenced by
\fIptr\fR
to be made available for future allocations\&.
.PP
The
\fBsdallocx\fR\fB\fR
function is an extension of
\fBdallocx\fR\fB\fR
with a
\fIsize\fR
parameter to allow the caller to pass in the allocation size as an optimization\&. The minimum valid input size is the original requested size of the allocation, and the maximum valid input size is the corresponding value returned by
\fBnallocx\fR\fB\fR
or
\fBsallocx\fR\fB\fR\&.
.PP
The
\fBnallocx\fR\fB\fR
function allocates no memory, but it performs the same size computation as the
\fBmallocx\fR\fB\fR
function, and returns the real size of the allocation that would result from the equivalent
\fBmallocx\fR\fB\fR
function call\&. Behavior is undefined if
\fIsize\fR
is
\fB0\fR, or if request size overflows due to size class and/or alignment constraints\&.
.PP
The
\fBmallctl\fR\fB\fR
function provides a general interface for introspecting the memory allocator, as well as setting modifiable parameters and triggering actions\&. The period\-separated
\fIname\fR
argument specifies a location in a tree\-structured namespace; see the
MALLCTL NAMESPACE
section for documentation on the tree contents\&. To read a value, pass a pointer via
\fIoldp\fR
to adequate space to contain the value, and a pointer to its length via
\fIoldlenp\fR; otherwise pass
\fBNULL\fR
and
\fBNULL\fR\&. Similarly, to write a value, pass a pointer to the value via
\fInewp\fR, and its length via
\fInewlen\fR; otherwise pass
\fBNULL\fR
and
\fB0\fR\&.
.PP
The
\fBmallctlnametomib\fR\fB\fR
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 \(lqManagement Information Base\(rq (MIB) that can be passed repeatedly to
\fBmallctlbymib\fR\fB\fR\&. Upon successful return from
\fBmallctlnametomib\fR\fB\fR,
\fImibp\fR
contains an array of
\fI*miblenp\fR
integers, where
\fI*miblenp\fR
is the lesser of the number of components in
\fIname\fR
and the input value of
\fI*miblenp\fR\&. Thus it is possible to pass a
\fI*miblenp\fR
that is smaller than the number of period\-separated name components, which results in a partial MIB that can be used as the basis for constructing a complete MIB\&. For name components that are integers (e\&.g\&. the 2 in
"arenas\&.bin\&.2\&.size"), the corresponding MIB component will always be that integer\&. Therefore, it is legitimate to construct code like the following:
.sp
.if n \{\
.RS 4
.\}
.nf
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, &bin_size, &len, NULL, 0);
/* Do something with bin_size\&.\&.\&. */
}
.fi
.if n \{\
.RE
.\}
.PP
The
\fBmalloc_stats_print\fR\fB\fR
function writes human\-readable summary statistics via the
\fIwrite_cb\fR
callback function pointer and
\fIcbopaque\fR
data passed to
\fIwrite_cb\fR, or
\fBmalloc_message\fR\fB\fR
if
\fIwrite_cb\fR
is
\fBNULL\fR\&. This function can be called repeatedly\&. General information that never changes during execution can be omitted by specifying "g" as a character within the
\fIopts\fR
string\&. Note that
\fBmalloc_message\fR\fB\fR
uses the
\fBmallctl*\fR\fB\fR
functions internally, so inconsistent statistics can be reported if multiple threads use these functions simultaneously\&. If
\fB\-\-enable\-stats\fR
is specified during configuration, \(lqm\(rq and \(lqa\(rq can be specified to omit merged arena and per arena statistics, respectively; \(lqb\(rq, \(lql\(rq, and \(lqh\(rq can be specified to omit per size class statistics for bins, large objects, and huge objects, respectively\&. Unrecognized characters are silently ignored\&. Note that thread caching may prevent some statistics from being completely up to date, since extra locking would be required to merge counters that track thread cache operations\&.
.PP
The
\fBmalloc_usable_size\fR\fB\fR
function returns the usable size of the allocation pointed to by
\fIptr\fR\&. The return value may be larger than the size that was requested during allocation\&. The
\fBmalloc_usable_size\fR\fB\fR
function is not a mechanism for in\-place
\fBrealloc\fR\fB\fR; rather it is provided solely as a tool for introspection purposes\&. Any discrepancy between the requested allocation size and the size reported by
\fBmalloc_usable_size\fR\fB\fR
should not be depended on, since such behavior is entirely implementation\-dependent\&.
.SH "TUNING"
.PP
Once, when the first call is made to one of the memory allocation routines, the allocator initializes its internals based in part on various options that can be specified at compile\- or run\-time\&.
.PP
The string pointed to by the global variable
\fImalloc_conf\fR, the \(lqname\(rq of the file referenced by the symbolic link named
/etc/malloc\&.conf, and the value of the environment variable
\fBMALLOC_CONF\fR, will be interpreted, in that order, from left to right as options\&. Note that
\fImalloc_conf\fR
may be read before
\fBmain\fR\fB\fR
is entered, so the declaration of
\fImalloc_conf\fR
should specify an initializer that contains the final value to be read by jemalloc\&.
\fImalloc_conf\fR
is a compile\-time setting, whereas
/etc/malloc\&.conf
and
\fBMALLOC_CONF\fR
can be safely set any time prior to program invocation\&.
.PP
An options string is a comma\-separated list of option:value pairs\&. There is one key corresponding to each
"opt\&.*"
mallctl (see the
MALLCTL NAMESPACE
section for options documentation)\&. For example,
abort:true,narenas:1
sets the
"opt\&.abort"
and
"opt\&.narenas"
options\&. Some options have boolean values (true/false), others have integer values (base 8, 10, or 16, depending on prefix), and yet others have raw string values\&.
.SH "IMPLEMENTATION NOTES"
.PP
Traditionally, allocators have used
\fBsbrk\fR(2)
to obtain memory, which is suboptimal for several reasons, including race conditions, increased fragmentation, and artificial limitations on maximum usable memory\&. If
\fBsbrk\fR(2)
is supported by the operating system, this allocator uses both
\fBmmap\fR(2)
and
\fBsbrk\fR(2), in that order of preference; otherwise only
\fBmmap\fR(2)
is used\&.
.PP
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\&.
.PP
In addition to multiple arenas, unless
\fB\-\-disable\-tcache\fR
is specified during configuration, this allocator supports thread\-specific caching for small and large objects, in order to make it possible to completely avoid synchronization for most allocation requests\&. Such caching allows very fast allocation in the common case, but it increases memory usage and fragmentation, since a bounded number of objects can remain allocated in each thread cache\&.
.PP
Memory is conceptually broken into equal\-sized chunks, where the chunk size is a power of two that is greater than the page size\&. Chunks are always aligned to multiples of the chunk size\&. This alignment makes it possible to find metadata for user objects very quickly\&.
.PP
User objects are broken into three categories according to size: small, large, and huge\&. Small and large objects are managed entirely by arenas; huge objects are additionally aggregated in a single data structure that is shared by all threads\&. Huge objects are typically used by applications infrequently enough that this single data structure is not a scalability issue\&.
.PP
Each chunk that is managed by an arena tracks its contents as runs of contiguous pages (unused, backing a set of small objects, or backing one large object)\&. The combination of chunk alignment and chunk page maps makes it possible to determine all metadata regarding small and large allocations in constant time\&.
.PP
Small objects are managed in groups by page runs\&. Each run maintains a bitmap to track which regions are in use\&. Allocation requests that are no more than half the quantum (8 or 16, depending on architecture) are rounded up to the nearest power of two that is at least
sizeof(\fBdouble\fR)\&. All other object size classes are multiples of the quantum, spaced such that there are four size classes for each doubling in size, which limits internal fragmentation to approximately 20% for all but the smallest size classes\&. Small size classes are smaller than four times the page size, large size classes are smaller than the chunk size (see the
"opt\&.lg_chunk"
option), and huge size classes extend from the chunk size up to one size class less than the full address space size\&.
.PP
Allocations are packed tightly together, which can be an issue for multi\-threaded applications\&. If you need to assure that allocations do not suffer from cacheline sharing, round your allocation requests up to the nearest multiple of the cacheline size, or specify cacheline alignment when allocating\&.
.PP
The
\fBrealloc\fR\fB\fR,
\fBrallocx\fR\fB\fR, and
\fBxallocx\fR\fB\fR
functions may resize allocations without moving them under limited circumstances\&. Unlike the
\fB*allocx\fR\fB\fR
API, the standard API does not officially round up the usable size of an allocation to the nearest size class, so technically it is necessary to call
\fBrealloc\fR\fB\fR
to grow e\&.g\&. a 9\-byte allocation to 16 bytes, or shrink a 16\-byte allocation to 9 bytes\&. Growth and shrinkage trivially succeeds in place as long as the pre\-size and post\-size both round up to the same size class\&. No other API guarantees are made regarding in\-place resizing, but the current implementation also tries to resize large and huge allocations in place, as long as the pre\-size and post\-size are both large or both huge\&. In such cases shrinkage always succeeds for large size classes, but for huge size classes the chunk allocator must support splitting (see
"arena\&.<i>\&.chunk_hooks")\&. Growth only succeeds if the trailing memory is currently available, and additionally for huge size classes the chunk allocator must support merging\&.
.PP
Assuming 2 MiB chunks, 4 KiB pages, and a 16\-byte quantum on a 64\-bit system, the size classes in each category are as shown in
Table 1\&.
.sp
.it 1 an-trap
.nr an-no-space-flag 1
.nr an-break-flag 1
.br
.B Table\ \&1.\ \&Size classes
.TS
allbox tab(:);
lB rB lB.
T{
Category
T}:T{
Spacing
T}:T{
Size
T}
.T&
l r l
^ r l
^ r l
^ r l
^ r l
^ r l
^ r l
^ r l
^ r l
l r l
^ r l
^ r l
^ r l
^ r l
^ r l
^ r l
^ r l
l r l
^ r l
^ r l
^ r l
^ r l
^ r l
^ r l.
T{
Small
T}:T{
lg
T}:T{
[8]
T}
:T{
16
T}:T{
[16, 32, 48, 64, 80, 96, 112, 128]
T}
:T{
32
T}:T{
[160, 192, 224, 256]
T}
:T{
64
T}:T{
[320, 384, 448, 512]
T}
:T{
128
T}:T{
[640, 768, 896, 1024]
T}
:T{
256
T}:T{
[1280, 1536, 1792, 2048]
T}
:T{
512
T}:T{
[2560, 3072, 3584, 4096]
T}
:T{
1 KiB
T}:T{
[5 KiB, 6 KiB, 7 KiB, 8 KiB]
T}
:T{
2 KiB
T}:T{
[10 KiB, 12 KiB, 14 KiB]
T}
T{
Large
T}:T{
2 KiB
T}:T{
[16 KiB]
T}
:T{
4 KiB
T}:T{
[20 KiB, 24 KiB, 28 KiB, 32 KiB]
T}
:T{
8 KiB
T}:T{
[40 KiB, 48 KiB, 54 KiB, 64 KiB]
T}
:T{
16 KiB
T}:T{
[80 KiB, 96 KiB, 112 KiB, 128 KiB]
T}
:T{
32 KiB
T}:T{
[160 KiB, 192 KiB, 224 KiB, 256 KiB]
T}
:T{
64 KiB
T}:T{
[320 KiB, 384 KiB, 448 KiB, 512 KiB]
T}
:T{
128 KiB
T}:T{
[640 KiB, 768 KiB, 896 KiB, 1 MiB]
T}
:T{
256 KiB
T}:T{
[1280 KiB, 1536 KiB, 1792 KiB]
T}
T{
Huge
T}:T{
256 KiB
T}:T{
[2 MiB]
T}
:T{
512 KiB
T}:T{
[2560 KiB, 3 MiB, 3584 KiB, 4 MiB]
T}
:T{
1 MiB
T}:T{
[5 MiB, 6 MiB, 7 MiB, 8 MiB]
T}
:T{
2 MiB
T}:T{
[10 MiB, 12 MiB, 14 MiB, 16 MiB]
T}
:T{
4 MiB
T}:T{
[20 MiB, 24 MiB, 28 MiB, 32 MiB]
T}
:T{
8 MiB
T}:T{
[40 MiB, 48 MiB, 56 MiB, 64 MiB]
T}
:T{
\&.\&.\&.
T}:T{
\&.\&.\&.
T}
.TE
.sp 1
.SH "MALLCTL NAMESPACE"
.PP
The following names are defined in the namespace accessible via the
\fBmallctl*\fR\fB\fR
functions\&. Value types are specified in parentheses, their readable/writable statuses are encoded as
rw,
r\-,
\-w, or
\-\-, and required build configuration flags follow, if any\&. A name element encoded as
<i>
or
<j>
indicates an integer component, where the integer varies from 0 to some upper value that must be determined via introspection\&. In the case of
"stats\&.arenas\&.<i>\&.*",
<i>
equal to
"arenas\&.narenas"
can be used to access the summation of statistics from all arenas\&. Take special note of the
"epoch"
mallctl, which controls refreshing of cached dynamic statistics\&.
.PP
"version" (\fBconst char *\fR) r\-
.RS 4
Return the jemalloc version string\&.
.RE
.PP
"epoch" (\fBuint64_t\fR) rw
.RS 4
If a value is passed in, refresh the data from which the
\fBmallctl*\fR\fB\fR
functions report values, and increment the epoch\&. Return the current epoch\&. This is useful for detecting whether another thread caused a refresh\&.
.RE
.PP
"config\&.cache_oblivious" (\fBbool\fR) r\-
.RS 4
\fB\-\-enable\-cache\-oblivious\fR
was specified during build configuration\&.
.RE
.PP
"config\&.debug" (\fBbool\fR) r\-
.RS 4
\fB\-\-enable\-debug\fR
was specified during build configuration\&.
.RE
.PP
"config\&.fill" (\fBbool\fR) r\-
.RS 4
\fB\-\-enable\-fill\fR
was specified during build configuration\&.
.RE
.PP
"config\&.lazy_lock" (\fBbool\fR) r\-
.RS 4
\fB\-\-enable\-lazy\-lock\fR
was specified during build configuration\&.
.RE
.PP
"config\&.munmap" (\fBbool\fR) r\-
.RS 4
\fB\-\-enable\-munmap\fR
was specified during build configuration\&.
.RE
.PP
"config\&.prof" (\fBbool\fR) r\-
.RS 4
\fB\-\-enable\-prof\fR
was specified during build configuration\&.
.RE
.PP
"config\&.prof_libgcc" (\fBbool\fR) r\-
.RS 4
\fB\-\-disable\-prof\-libgcc\fR
was not specified during build configuration\&.
.RE
.PP
"config\&.prof_libunwind" (\fBbool\fR) r\-
.RS 4
\fB\-\-enable\-prof\-libunwind\fR
was specified during build configuration\&.
.RE
.PP
"config\&.stats" (\fBbool\fR) r\-
.RS 4
\fB\-\-enable\-stats\fR
was specified during build configuration\&.
.RE
.PP
"config\&.tcache" (\fBbool\fR) r\-
.RS 4
\fB\-\-disable\-tcache\fR
was not specified during build configuration\&.
.RE
.PP
"config\&.tls" (\fBbool\fR) r\-
.RS 4
\fB\-\-disable\-tls\fR
was not specified during build configuration\&.
.RE
.PP
"config\&.utrace" (\fBbool\fR) r\-
.RS 4
\fB\-\-enable\-utrace\fR
was specified during build configuration\&.
.RE
.PP
"config\&.valgrind" (\fBbool\fR) r\-
.RS 4
\fB\-\-enable\-valgrind\fR
was specified during build configuration\&.
.RE
.PP
"config\&.xmalloc" (\fBbool\fR) r\-
.RS 4
\fB\-\-enable\-xmalloc\fR
was specified during build configuration\&.
.RE
.PP
"opt\&.abort" (\fBbool\fR) r\-
.RS 4
Abort\-on\-warning enabled/disabled\&. If true, most warnings are fatal\&. The process will call
\fBabort\fR(3)
in these cases\&. This option is disabled by default unless
\fB\-\-enable\-debug\fR
is specified during configuration, in which case it is enabled by default\&.
.RE
.PP
"opt\&.dss" (\fBconst char *\fR) r\-
.RS 4
dss (\fBsbrk\fR(2)) allocation precedence as related to
\fBmmap\fR(2)
allocation\&. The following settings are supported if
\fBsbrk\fR(2)
is supported by the operating system: \(lqdisabled\(rq, \(lqprimary\(rq, and \(lqsecondary\(rq; otherwise only \(lqdisabled\(rq is supported\&. The default is \(lqsecondary\(rq if
\fBsbrk\fR(2)
is supported by the operating system; \(lqdisabled\(rq otherwise\&.
.RE
.PP
"opt\&.lg_chunk" (\fBsize_t\fR) r\-
.RS 4
Virtual memory chunk size (log base 2)\&. If a chunk size outside the supported size range is specified, the size is silently clipped to the minimum/maximum supported size\&. The default chunk size is 2 MiB (2^21)\&.
.RE
.PP
"opt\&.narenas" (\fBsize_t\fR) r\-
.RS 4
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\&.
.RE
.PP
"opt\&.lg_dirty_mult" (\fBssize_t\fR) r\-
.RS 4
Per\-arena minimum ratio (log base 2) of active to dirty pages\&. Some dirty unused pages may be allowed to accumulate, within the limit set by the ratio (or one chunk worth of dirty pages, whichever is greater), before informing the kernel about some of those pages via
\fBmadvise\fR(2)
or a similar system call\&. This provides the kernel with sufficient information to recycle dirty pages if physical memory becomes scarce and the pages remain unused\&. The default minimum ratio is 8:1 (2^3:1); an option value of \-1 will disable dirty page purging\&. See
"arenas\&.lg_dirty_mult"
and
"arena\&.<i>\&.lg_dirty_mult"
for related dynamic control options\&.
.RE
.PP
"opt\&.stats_print" (\fBbool\fR) r\-
.RS 4
Enable/disable statistics printing at exit\&. If enabled, the
\fBmalloc_stats_print\fR\fB\fR
function is called at program exit via an
\fBatexit\fR(3)
function\&. If
\fB\-\-enable\-stats\fR
is specified during configuration, this has the potential to cause deadlock for a multi\-threaded process that exits while one or more threads are executing in the memory allocation functions\&. Furthermore,
\fBatexit\fR\fB\fR
may allocate memory during application initialization and then deadlock internally when jemalloc in turn calls
\fBatexit\fR\fB\fR, so this option is not univerally usable (though the application can register its own
\fBatexit\fR\fB\fR
function with equivalent functionality)\&. Therefore, this option should only be used with care; it is primarily intended as a performance tuning aid during application development\&. This option is disabled by default\&.
.RE
.PP
"opt\&.junk" (\fBconst char *\fR) r\- [\fB\-\-enable\-fill\fR]
.RS 4
Junk filling\&. If set to "alloc", each byte of uninitialized allocated memory will be initialized to
0xa5\&. If set to "free", all deallocated memory will be initialized to
0x5a\&. If set to "true", both allocated and deallocated memory will be initialized, and if set to "false", junk filling be disabled entirely\&. This is intended for debugging and will impact performance negatively\&. This option is "false" by default unless
\fB\-\-enable\-debug\fR
is specified during configuration, in which case it is "true" by default unless running inside
\m[blue]\fBValgrind\fR\m[]\&\s-2\u[2]\d\s+2\&.
.RE
.PP
"opt\&.quarantine" (\fBsize_t\fR) r\- [\fB\-\-enable\-fill\fR]
.RS 4
Per thread quarantine size in bytes\&. If non\-zero, each thread maintains a FIFO object quarantine that stores up to the specified number of bytes of memory\&. The quarantined memory is not freed until it is released from quarantine, though it is immediately junk\-filled if the
"opt\&.junk"
option is enabled\&. This feature is of particular use in combination with
\m[blue]\fBValgrind\fR\m[]\&\s-2\u[2]\d\s+2, which can detect attempts to access quarantined objects\&. This is intended for debugging and will impact performance negatively\&. The default quarantine size is 0 unless running inside Valgrind, in which case the default is 16 MiB\&.
.RE
.PP
"opt\&.redzone" (\fBbool\fR) r\- [\fB\-\-enable\-fill\fR]
.RS 4
Redzones enabled/disabled\&. If enabled, small allocations have redzones before and after them\&. Furthermore, if the
"opt\&.junk"
option is enabled, the redzones are checked for corruption during deallocation\&. However, the primary intended purpose of this feature is to be used in combination with
\m[blue]\fBValgrind\fR\m[]\&\s-2\u[2]\d\s+2, which needs redzones in order to do effective buffer overflow/underflow detection\&. This option is intended for debugging and will impact performance negatively\&. This option is disabled by default unless running inside Valgrind\&.
.RE
.PP
"opt\&.zero" (\fBbool\fR) r\- [\fB\-\-enable\-fill\fR]
.RS 4
Zero filling enabled/disabled\&. If enabled, each byte of uninitialized allocated memory will be initialized to 0\&. Note that this initialization only happens once for each byte, so
\fBrealloc\fR\fB\fR
and
\fBrallocx\fR\fB\fR
calls do not zero memory that was previously allocated\&. This is intended for debugging and will impact performance negatively\&. This option is disabled by default\&.
.RE
.PP
"opt\&.utrace" (\fBbool\fR) r\- [\fB\-\-enable\-utrace\fR]
.RS 4
Allocation tracing based on
\fButrace\fR(2)
enabled/disabled\&. This option is disabled by default\&.
.RE
.PP
"opt\&.xmalloc" (\fBbool\fR) r\- [\fB\-\-enable\-xmalloc\fR]
.RS 4
Abort\-on\-out\-of\-memory enabled/disabled\&. If enabled, rather than returning failure for any allocation function, display a diagnostic message on
\fBSTDERR_FILENO\fR
and cause the program to drop core (using
\fBabort\fR(3))\&. If an application is designed to depend on this behavior, set the option at compile time by including the following in the source code:
.sp
.if n \{\
.RS 4
.\}
.nf
malloc_conf = "xmalloc:true";
.fi
.if n \{\
.RE
.\}
.sp
This option is disabled by default\&.
.RE
.PP
"opt\&.tcache" (\fBbool\fR) r\- [\fB\-\-enable\-tcache\fR]
.RS 4
Thread\-specific caching (tcache) enabled/disabled\&. When there are multiple threads, each thread uses a tcache for objects up to a certain size\&. Thread\-specific caching allows many allocations to be satisfied without performing any thread synchronization, at the cost of increased memory use\&. See the
"opt\&.lg_tcache_max"
option for related tuning information\&. This option is enabled by default unless running inside
\m[blue]\fBValgrind\fR\m[]\&\s-2\u[2]\d\s+2, in which case it is forcefully disabled\&.
.RE
.PP
"opt\&.lg_tcache_max" (\fBsize_t\fR) r\- [\fB\-\-enable\-tcache\fR]
.RS 4
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)\&.
.RE
.PP
"opt\&.prof" (\fBbool\fR) r\- [\fB\-\-enable\-prof\fR]
.RS 4
Memory profiling enabled/disabled\&. If enabled, profile memory allocation activity\&. See the
"opt\&.prof_active"
option for on\-the\-fly activation/deactivation\&. See the
"opt\&.lg_prof_sample"
option for probabilistic sampling control\&. See the
"opt\&.prof_accum"
option for control of cumulative sample reporting\&. See the
"opt\&.lg_prof_interval"
option for information on interval\-triggered profile dumping, the
"opt\&.prof_gdump"
option for information on high\-water\-triggered profile dumping, and the
"opt\&.prof_final"
option for final profile dumping\&. Profile output is compatible with the
\fBjeprof\fR
command, which is based on the
\fBpprof\fR
that is developed as part of the
\m[blue]\fBgperftools package\fR\m[]\&\s-2\u[3]\d\s+2\&.
.RE
.PP
"opt\&.prof_prefix" (\fBconst char *\fR) r\- [\fB\-\-enable\-prof\fR]
.RS 4
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
jeprof\&.
.RE
.PP
"opt\&.prof_active" (\fBbool\fR) r\- [\fB\-\-enable\-prof\fR]
.RS 4
Profiling activated/deactivated\&. This is a secondary control mechanism that makes it possible to start the application with profiling enabled (see the
"opt\&.prof"
option) but inactive, then toggle profiling at any time during program execution with the
"prof\&.active"
mallctl\&. This option is enabled by default\&.
.RE
.PP
"opt\&.prof_thread_active_init" (\fBbool\fR) r\- [\fB\-\-enable\-prof\fR]
.RS 4
Initial setting for
"thread\&.prof\&.active"
in newly created threads\&. The initial setting for newly created threads can also be changed during execution via the
"prof\&.thread_active_init"
mallctl\&. This option is enabled by default\&.
.RE
.PP
"opt\&.lg_prof_sample" (\fBsize_t\fR) r\- [\fB\-\-enable\-prof\fR]
.RS 4
Average interval (log base 2) between allocation samples, as measured in bytes of allocation activity\&. Increasing the sampling interval decreases profile fidelity, but also decreases the computational overhead\&. The default sample interval is 512 KiB (2^19 B)\&.
.RE
.PP
"opt\&.prof_accum" (\fBbool\fR) r\- [\fB\-\-enable\-prof\fR]
.RS 4
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\&.
.RE
.PP
"opt\&.lg_prof_interval" (\fBssize_t\fR) r\- [\fB\-\-enable\-prof\fR]
.RS 4
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
<prefix>\&.<pid>\&.<seq>\&.i<iseq>\&.heap, where
<prefix>
is controlled by the
"opt\&.prof_prefix"
option\&. By default, interval\-triggered profile dumping is disabled (encoded as \-1)\&.
.RE
.PP
"opt\&.prof_gdump" (\fBbool\fR) r\- [\fB\-\-enable\-prof\fR]
.RS 4
Set the initial state of
"prof\&.gdump", which when enabled triggers a memory profile dump every time the total virtual memory exceeds the previous maximum\&. This option is disabled by default\&.
.RE
.PP
"opt\&.prof_final" (\fBbool\fR) r\- [\fB\-\-enable\-prof\fR]
.RS 4
Use an
\fBatexit\fR(3)
function to dump final memory usage to a file named according to the pattern
<prefix>\&.<pid>\&.<seq>\&.f\&.heap, where
<prefix>
is controlled by the
"opt\&.prof_prefix"
option\&. Note that
\fBatexit\fR\fB\fR
may allocate memory during application initialization and then deadlock internally when jemalloc in turn calls
\fBatexit\fR\fB\fR, so this option is not univerally usable (though the application can register its own
\fBatexit\fR\fB\fR
function with equivalent functionality)\&. This option is disabled by default\&.
.RE
.PP
"opt\&.prof_leak" (\fBbool\fR) r\- [\fB\-\-enable\-prof\fR]
.RS 4
Leak reporting enabled/disabled\&. If enabled, use an
\fBatexit\fR(3)
function to report memory leaks detected by allocation sampling\&. See the
"opt\&.prof"
option for information on analyzing heap profile output\&. This option is disabled by default\&.
.RE
.PP
"thread\&.arena" (\fBunsigned\fR) rw
.RS 4
Get or set the arena associated with the calling thread\&. If the specified arena was not initialized beforehand (see the
"arenas\&.initialized"
mallctl), it will be automatically initialized as a side effect of calling this interface\&.
.RE
.PP
"thread\&.allocated" (\fBuint64_t\fR) r\- [\fB\-\-enable\-stats\fR]
.RS 4
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\&.
.RE
.PP
"thread\&.allocatedp" (\fBuint64_t *\fR) r\- [\fB\-\-enable\-stats\fR]
.RS 4
Get a pointer to the the value that is returned by the
"thread\&.allocated"
mallctl\&. This is useful for avoiding the overhead of repeated
\fBmallctl*\fR\fB\fR
calls\&.
.RE
.PP
"thread\&.deallocated" (\fBuint64_t\fR) r\- [\fB\-\-enable\-stats\fR]
.RS 4
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\&.
.RE
.PP
"thread\&.deallocatedp" (\fBuint64_t *\fR) r\- [\fB\-\-enable\-stats\fR]
.RS 4
Get a pointer to the the value that is returned by the
"thread\&.deallocated"
mallctl\&. This is useful for avoiding the overhead of repeated
\fBmallctl*\fR\fB\fR
calls\&.
.RE
.PP
"thread\&.tcache\&.enabled" (\fBbool\fR) rw [\fB\-\-enable\-tcache\fR]
.RS 4
Enable/disable calling thread\*(Aqs tcache\&. The tcache is implicitly flushed as a side effect of becoming disabled (see
"thread\&.tcache\&.flush")\&.
.RE
.PP
"thread\&.tcache\&.flush" (\fBvoid\fR) \-\- [\fB\-\-enable\-tcache\fR]
.RS 4
Flush calling thread\*(Aqs thread\-specific cache (tcache)\&. This interface releases all cached objects and internal data structures associated with the calling thread\*(Aqs tcache\&. Ordinarily, this interface need not be called, since automatic periodic incremental garbage collection occurs, and the thread cache is automatically discarded when a thread exits\&. However, garbage collection is triggered by allocation activity, so it is possible for a thread that stops allocating/deallocating to retain its cache indefinitely, in which case the developer may find manual flushing useful\&.
.RE
.PP
"thread\&.prof\&.name" (\fBconst char *\fR) r\- or \-w [\fB\-\-enable\-prof\fR]
.RS 4
Get/set the descriptive name associated with the calling thread in memory profile dumps\&. An internal copy of the name string is created, so the input string need not be maintained after this interface completes execution\&. The output string of this interface should be copied for non\-ephemeral uses, because multiple implementation details can cause asynchronous string deallocation\&. Furthermore, each invocation of this interface can only read or write; simultaneous read/write is not supported due to string lifetime limitations\&. The name string must nil\-terminated and comprised only of characters in the sets recognized by
\fBisgraph\fR(3)
and
\fBisblank\fR(3)\&.
.RE
.PP
"thread\&.prof\&.active" (\fBbool\fR) rw [\fB\-\-enable\-prof\fR]
.RS 4
Control whether sampling is currently active for the calling thread\&. This is an activation mechanism in addition to
"prof\&.active"; both must be active for the calling thread to sample\&. This flag is enabled by default\&.
.RE
.PP
"tcache\&.create" (\fBunsigned\fR) r\- [\fB\-\-enable\-tcache\fR]
.RS 4
Create an explicit thread\-specific cache (tcache) and return an identifier that can be passed to the
\fBMALLOCX_TCACHE(\fR\fB\fItc\fR\fR\fB)\fR
macro to explicitly use the specified cache rather than the automatically managed one that is used by default\&. Each explicit cache can be used by only one thread at a time; the application must assure that this constraint holds\&.
.RE
.PP
"tcache\&.flush" (\fBunsigned\fR) \-w [\fB\-\-enable\-tcache\fR]
.RS 4
Flush the specified thread\-specific cache (tcache)\&. The same considerations apply to this interface as to
"thread\&.tcache\&.flush", except that the tcache will never be automatically be discarded\&.
.RE
.PP
"tcache\&.destroy" (\fBunsigned\fR) \-w [\fB\-\-enable\-tcache\fR]
.RS 4
Flush the specified thread\-specific cache (tcache) and make the identifier available for use during a future tcache creation\&.
.RE
.PP
"arena\&.<i>\&.purge" (\fBvoid\fR) \-\-
.RS 4
Purge unused dirty pages for arena <i>, or for all arenas if <i> equals
"arenas\&.narenas"\&.
.RE
.PP
"arena\&.<i>\&.dss" (\fBconst char *\fR) rw
.RS 4
Set the precedence of dss allocation as related to mmap allocation for arena <i>, or for all arenas if <i> equals
"arenas\&.narenas"\&. See
"opt\&.dss"
for supported settings\&.
.RE
.PP
"arena\&.<i>\&.lg_dirty_mult" (\fBssize_t\fR) rw
.RS 4
Current per\-arena minimum ratio (log base 2) of active to dirty pages for arena <i>\&. Each time this interface is set and the ratio is increased, pages are synchronously purged as necessary to impose the new ratio\&. See
"opt\&.lg_dirty_mult"
for additional information\&.
.RE
.PP
"arena\&.<i>\&.chunk_hooks" (\fBchunk_hooks_t\fR) rw
.RS 4
Get or set the chunk management hook functions for arena <i>\&. The functions must be capable of operating on all extant chunks associated with arena <i>, usually by passing unknown chunks to the replaced functions\&. In practice, it is feasible to control allocation for arenas created via
"arenas\&.extend"
such that all chunks originate from an application\-supplied chunk allocator (by setting custom chunk hook functions just after arena creation), but the automatically created arenas may have already created chunks prior to the application having an opportunity to take over chunk allocation\&.
.sp
.if n \{\
.RS 4
.\}
.nf
typedef struct {
chunk_alloc_t *alloc;
chunk_dalloc_t *dalloc;
chunk_commit_t *commit;
chunk_decommit_t *decommit;
chunk_purge_t *purge;
chunk_split_t *split;
chunk_merge_t *merge;
} chunk_hooks_t;
.fi
.if n \{\
.RE
.\}
.sp
The
\fBchunk_hooks_t\fR
structure comprises function pointers which are described individually below\&. jemalloc uses these functions to manage chunk lifetime, which starts off with allocation of mapped committed memory, in the simplest case followed by deallocation\&. However, there are performance and platform reasons to retain chunks for later reuse\&. Cleanup attempts cascade from deallocation to decommit to purging, which gives the chunk management functions opportunities to reject the most permanent cleanup operations in favor of less permanent (and often less costly) operations\&. The chunk splitting and merging operations can also be opted out of, but this is mainly intended to support platforms on which virtual memory mappings provided by the operating system kernel do not automatically coalesce and split, e\&.g\&. Windows\&.
.HP \w'typedef\ void\ *(chunk_alloc_t)('u
.BI "typedef void *(chunk_alloc_t)(void\ *" "chunk" ", size_t\ " "size" ", size_t\ " "alignment" ", bool\ *" "zero" ", bool\ *" "commit" ", unsigned\ " "arena_ind" ");"
.sp
.if n \{\
.RS 4
.\}
.nf
.fi
.if n \{\
.RE
.\}
.sp
A chunk allocation function conforms to the
\fBchunk_alloc_t\fR
type and upon success returns a pointer to
\fIsize\fR
bytes of mapped memory on behalf of arena
\fIarena_ind\fR
such that the chunk\*(Aqs base address is a multiple of
\fIalignment\fR, as well as setting
\fI*zero\fR
to indicate whether the chunk is zeroed and
\fI*commit\fR
to indicate whether the chunk is committed\&. Upon error the function returns
\fBNULL\fR
and leaves
\fI*zero\fR
and
\fI*commit\fR
unmodified\&. The
\fIsize\fR
parameter is always a multiple of the chunk size\&. The
\fIalignment\fR
parameter is always a power of two at least as large as the chunk size\&. Zeroing is mandatory if
\fI*zero\fR
is true upon function entry\&. Committing is mandatory if
\fI*commit\fR
is true upon function entry\&. If
\fIchunk\fR
is not
\fBNULL\fR, the returned pointer must be
\fIchunk\fR
on success or
\fBNULL\fR
on error\&. Committed memory may be committed in absolute terms as on a system that does not overcommit, or in implicit terms as on a system that overcommits and satisfies physical memory needs on demand via soft page faults\&. Note that replacing the default chunk allocation function makes the arena\*(Aqs
"arena\&.<i>\&.dss"
setting irrelevant\&.
.HP \w'typedef\ bool\ (chunk_dalloc_t)('u
.BI "typedef bool (chunk_dalloc_t)(void\ *" "chunk" ", size_t\ " "size" ", bool\ " "committed" ", unsigned\ " "arena_ind" ");"
.sp
.if n \{\
.RS 4
.\}
.nf
.fi
.if n \{\
.RE
.\}
.sp
A chunk deallocation function conforms to the
\fBchunk_dalloc_t\fR
type and deallocates a
\fIchunk\fR
of given
\fIsize\fR
with
\fIcommitted\fR/decommited memory as indicated, on behalf of arena
\fIarena_ind\fR, returning false upon success\&. If the function returns true, this indicates opt\-out from deallocation; the virtual memory mapping associated with the chunk remains mapped, in the same commit state, and available for future use, in which case it will be automatically retained for later reuse\&.
.HP \w'typedef\ bool\ (chunk_commit_t)('u
.BI "typedef bool (chunk_commit_t)(void\ *" "chunk" ", size_t\ " "size" ", size_t\ " "offset" ", size_t\ " "length" ", unsigned\ " "arena_ind" ");"
.sp
.if n \{\
.RS 4
.\}
.nf
.fi
.if n \{\
.RE
.\}
.sp
A chunk commit function conforms to the
\fBchunk_commit_t\fR
type and commits zeroed physical memory to back pages within a
\fIchunk\fR
of given
\fIsize\fR
at
\fIoffset\fR
bytes, extending for
\fIlength\fR
on behalf of arena
\fIarena_ind\fR, returning false upon success\&. Committed memory may be committed in absolute terms as on a system that does not overcommit, or in implicit terms as on a system that overcommits and satisfies physical memory needs on demand via soft page faults\&. If the function returns true, this indicates insufficient physical memory to satisfy the request\&.
.HP \w'typedef\ bool\ (chunk_decommit_t)('u
.BI "typedef bool (chunk_decommit_t)(void\ *" "chunk" ", size_t\ " "size" ", size_t\ " "offset" ", size_t\ " "length" ", unsigned\ " "arena_ind" ");"
.sp
.if n \{\
.RS 4
.\}
.nf
.fi
.if n \{\
.RE
.\}
.sp
A chunk decommit function conforms to the
\fBchunk_decommit_t\fR
type and decommits any physical memory that is backing pages within a
\fIchunk\fR
of given
\fIsize\fR
at
\fIoffset\fR
bytes, extending for
\fIlength\fR
on behalf of arena
\fIarena_ind\fR, returning false upon success, in which case the pages will be committed via the chunk commit function before being reused\&. If the function returns true, this indicates opt\-out from decommit; the memory remains committed and available for future use, in which case it will be automatically retained for later reuse\&.
.HP \w'typedef\ bool\ (chunk_purge_t)('u
.BI "typedef bool (chunk_purge_t)(void\ *" "chunk" ", size_t" "size" ", size_t\ " "offset" ", size_t\ " "length" ", unsigned\ " "arena_ind" ");"
.sp
.if n \{\
.RS 4
.\}
.nf
.fi
.if n \{\
.RE
.\}
.sp
A chunk purge function conforms to the
\fBchunk_purge_t\fR
type and optionally discards physical pages within the virtual memory mapping associated with
\fIchunk\fR
of given
\fIsize\fR
at
\fIoffset\fR
bytes, extending for
\fIlength\fR
on behalf of arena
\fIarena_ind\fR, returning false if pages within the purged virtual memory range will be zero\-filled the next time they are accessed\&.
.HP \w'typedef\ bool\ (chunk_split_t)('u
.BI "typedef bool (chunk_split_t)(void\ *" "chunk" ", size_t\ " "size" ", size_t\ " "size_a" ", size_t\ " "size_b" ", bool\ " "committed" ", unsigned\ " "arena_ind" ");"
.sp
.if n \{\
.RS 4
.\}
.nf
.fi
.if n \{\
.RE
.\}
.sp
A chunk split function conforms to the
\fBchunk_split_t\fR
type and optionally splits
\fIchunk\fR
of given
\fIsize\fR
into two adjacent chunks, the first of
\fIsize_a\fR
bytes, and the second of
\fIsize_b\fR
bytes, operating on
\fIcommitted\fR/decommitted memory as indicated, on behalf of arena
\fIarena_ind\fR, returning false upon success\&. If the function returns true, this indicates that the chunk remains unsplit and therefore should continue to be operated on as a whole\&.
.HP \w'typedef\ bool\ (chunk_merge_t)('u
.BI "typedef bool (chunk_merge_t)(void\ *" "chunk_a" ", size_t\ " "size_a" ", void\ *" "chunk_b" ", size_t\ " "size_b" ", bool\ " "committed" ", unsigned\ " "arena_ind" ");"
.sp
.if n \{\
.RS 4
.\}
.nf
.fi
.if n \{\
.RE
.\}
.sp
A chunk merge function conforms to the
\fBchunk_merge_t\fR
type and optionally merges adjacent chunks,
\fIchunk_a\fR
of given
\fIsize_a\fR
and
\fIchunk_b\fR
of given
\fIsize_b\fR
into one contiguous chunk, operating on
\fIcommitted\fR/decommitted memory as indicated, on behalf of arena
\fIarena_ind\fR, returning false upon success\&. If the function returns true, this indicates that the chunks remain distinct mappings and therefore should continue to be operated on independently\&.
.RE
.PP
"arenas\&.narenas" (\fBunsigned\fR) r\-
.RS 4
Current limit on number of arenas\&.
.RE
.PP
"arenas\&.initialized" (\fBbool *\fR) r\-
.RS 4
An array of
"arenas\&.narenas"
booleans\&. Each boolean indicates whether the corresponding arena is initialized\&.
.RE
.PP
"arenas\&.lg_dirty_mult" (\fBssize_t\fR) rw
.RS 4
Current default per\-arena minimum ratio (log base 2) of active to dirty pages, used to initialize
"arena\&.<i>\&.lg_dirty_mult"
during arena creation\&. See
"opt\&.lg_dirty_mult"
for additional information\&.
.RE
.PP
"arenas\&.quantum" (\fBsize_t\fR) r\-
.RS 4
Quantum size\&.
.RE
.PP
"arenas\&.page" (\fBsize_t\fR) r\-
.RS 4
Page size\&.
.RE
.PP
"arenas\&.tcache_max" (\fBsize_t\fR) r\- [\fB\-\-enable\-tcache\fR]
.RS 4
Maximum thread\-cached size class\&.
.RE
.PP
"arenas\&.nbins" (\fBunsigned\fR) r\-
.RS 4
Number of bin size classes\&.
.RE
.PP
"arenas\&.nhbins" (\fBunsigned\fR) r\- [\fB\-\-enable\-tcache\fR]
.RS 4
Total number of thread cache bin size classes\&.
.RE
.PP
"arenas\&.bin\&.<i>\&.size" (\fBsize_t\fR) r\-
.RS 4
Maximum size supported by size class\&.
.RE
.PP
"arenas\&.bin\&.<i>\&.nregs" (\fBuint32_t\fR) r\-
.RS 4
Number of regions per page run\&.
.RE
.PP
"arenas\&.bin\&.<i>\&.run_size" (\fBsize_t\fR) r\-
.RS 4
Number of bytes per page run\&.
.RE
.PP
"arenas\&.nlruns" (\fBunsigned\fR) r\-
.RS 4
Total number of large size classes\&.
.RE
.PP
"arenas\&.lrun\&.<i>\&.size" (\fBsize_t\fR) r\-
.RS 4
Maximum size supported by this large size class\&.
.RE
.PP
"arenas\&.nhchunks" (\fBunsigned\fR) r\-
.RS 4
Total number of huge size classes\&.
.RE
.PP
"arenas\&.hchunk\&.<i>\&.size" (\fBsize_t\fR) r\-
.RS 4
Maximum size supported by this huge size class\&.
.RE
.PP
"arenas\&.extend" (\fBunsigned\fR) r\-
.RS 4
Extend the array of arenas by appending a new arena, and returning the new arena index\&.
.RE
.PP
"prof\&.thread_active_init" (\fBbool\fR) rw [\fB\-\-enable\-prof\fR]
.RS 4
Control the initial setting for
"thread\&.prof\&.active"
in newly created threads\&. See the
"opt\&.prof_thread_active_init"
option for additional information\&.
.RE
.PP
"prof\&.active" (\fBbool\fR) rw [\fB\-\-enable\-prof\fR]
.RS 4
Control whether sampling is currently active\&. See the
"opt\&.prof_active"
option for additional information, as well as the interrelated
"thread\&.prof\&.active"
mallctl\&.
.RE
.PP
"prof\&.dump" (\fBconst char *\fR) \-w [\fB\-\-enable\-prof\fR]
.RS 4
Dump a memory profile to the specified file, or if NULL is specified, to a file according to the pattern
<prefix>\&.<pid>\&.<seq>\&.m<mseq>\&.heap, where
<prefix>
is controlled by the
"opt\&.prof_prefix"
option\&.
.RE
.PP
"prof\&.gdump" (\fBbool\fR) rw [\fB\-\-enable\-prof\fR]
.RS 4
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
<prefix>\&.<pid>\&.<seq>\&.u<useq>\&.heap, where
<prefix>
is controlled by the
"opt\&.prof_prefix"
option\&.
.RE
.PP
"prof\&.reset" (\fBsize_t\fR) \-w [\fB\-\-enable\-prof\fR]
.RS 4
Reset all memory profile statistics, and optionally update the sample rate (see
"opt\&.lg_prof_sample"
and
"prof\&.lg_sample")\&.
.RE
.PP
"prof\&.lg_sample" (\fBsize_t\fR) r\- [\fB\-\-enable\-prof\fR]
.RS 4
Get the current sample rate (see
"opt\&.lg_prof_sample")\&.
.RE
.PP
"prof\&.interval" (\fBuint64_t\fR) r\- [\fB\-\-enable\-prof\fR]
.RS 4
Average number of bytes allocated between inverval\-based profile dumps\&. See the
"opt\&.lg_prof_interval"
option for additional information\&.
.RE
.PP
"stats\&.cactive" (\fBsize_t *\fR) r\- [\fB\-\-enable\-stats\fR]
.RS 4
Pointer to a counter that contains an approximate count of the current number of bytes in active pages\&. The estimate may be high, but never low, because each arena rounds up when computing its contribution to the counter\&. Note that the
"epoch"
mallctl has no bearing on this counter\&. Furthermore, counter consistency is maintained via atomic operations, so it is necessary to use an atomic operation in order to guarantee a consistent read when dereferencing the pointer\&.
.RE
.PP
"stats\&.allocated" (\fBsize_t\fR) r\- [\fB\-\-enable\-stats\fR]
.RS 4
Total number of bytes allocated by the application\&.
.RE
.PP
"stats\&.active" (\fBsize_t\fR) r\- [\fB\-\-enable\-stats\fR]
.RS 4
Total number of bytes in active pages allocated by the application\&. This is a multiple of the page size, and greater than or equal to
"stats\&.allocated"\&. This does not include
"stats\&.arenas\&.<i>\&.pdirty", nor pages entirely devoted to allocator metadata\&.
.RE
.PP
"stats\&.metadata" (\fBsize_t\fR) r\- [\fB\-\-enable\-stats\fR]
.RS 4
Total number of bytes dedicated to metadata, which comprise base allocations used for bootstrap\-sensitive internal allocator data structures, arena chunk headers (see
"stats\&.arenas\&.<i>\&.metadata\&.mapped"), and internal allocations (see
"stats\&.arenas\&.<i>\&.metadata\&.allocated")\&.
.RE
.PP
"stats\&.resident" (\fBsize_t\fR) r\- [\fB\-\-enable\-stats\fR]
.RS 4
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
"stats\&.active"\&.
.RE
.PP
"stats\&.mapped" (\fBsize_t\fR) r\- [\fB\-\-enable\-stats\fR]
.RS 4
Total number of bytes in active chunks mapped by the allocator\&. This is a multiple of the chunk size, and is larger than
"stats\&.active"\&. This does not include inactive chunks, even those that contain unused dirty pages, which means that there is no strict ordering between this and
"stats\&.resident"\&.
.RE
.PP
"stats\&.arenas\&.<i>\&.dss" (\fBconst char *\fR) r\-
.RS 4
dss (\fBsbrk\fR(2)) allocation precedence as related to
\fBmmap\fR(2)
allocation\&. See
"opt\&.dss"
for details\&.
.RE
.PP
"stats\&.arenas\&.<i>\&.lg_dirty_mult" (\fBssize_t\fR) r\-
.RS 4
Minimum ratio (log base 2) of active to dirty pages\&. See
"opt\&.lg_dirty_mult"
for details\&.
.RE
.PP
"stats\&.arenas\&.<i>\&.nthreads" (\fBunsigned\fR) r\-
.RS 4
Number of threads currently assigned to arena\&.
.RE
.PP
"stats\&.arenas\&.<i>\&.pactive" (\fBsize_t\fR) r\-
.RS 4
Number of pages in active runs\&.
.RE
.PP
"stats\&.arenas\&.<i>\&.pdirty" (\fBsize_t\fR) r\-
.RS 4
Number of pages within unused runs that are potentially dirty, and for which
\fBmadvise\fR\fB\fI\&.\&.\&.\fR\fR\fB \fR\fB\fI\fBMADV_DONTNEED\fR\fR\fR
or similar has not been called\&.
.RE
.PP
"stats\&.arenas\&.<i>\&.mapped" (\fBsize_t\fR) r\- [\fB\-\-enable\-stats\fR]
.RS 4
Number of mapped bytes\&.
.RE
.PP
"stats\&.arenas\&.<i>\&.metadata\&.mapped" (\fBsize_t\fR) r\- [\fB\-\-enable\-stats\fR]
.RS 4
Number of mapped bytes in arena chunk headers, which track the states of the non\-metadata pages\&.
.RE
.PP
"stats\&.arenas\&.<i>\&.metadata\&.allocated" (\fBsize_t\fR) r\- [\fB\-\-enable\-stats\fR]
.RS 4
Number of bytes dedicated to internal allocations\&. Internal allocations differ from application\-originated allocations in that they are for internal use, and that they are omitted from heap profiles\&. This statistic is reported separately from
"stats\&.metadata"
and
"stats\&.arenas\&.<i>\&.metadata\&.mapped"
because it overlaps with e\&.g\&. the
"stats\&.allocated"
and
"stats\&.active"
statistics, whereas the other metadata statistics do not\&.
.RE
.PP
"stats\&.arenas\&.<i>\&.npurge" (\fBuint64_t\fR) r\- [\fB\-\-enable\-stats\fR]
.RS 4
Number of dirty page purge sweeps performed\&.
.RE
.PP
"stats\&.arenas\&.<i>\&.nmadvise" (\fBuint64_t\fR) r\- [\fB\-\-enable\-stats\fR]
.RS 4
Number of
\fBmadvise\fR\fB\fI\&.\&.\&.\fR\fR\fB \fR\fB\fI\fBMADV_DONTNEED\fR\fR\fR
or similar calls made to purge dirty pages\&.
.RE
.PP
"stats\&.arenas\&.<i>\&.purged" (\fBuint64_t\fR) r\- [\fB\-\-enable\-stats\fR]
.RS 4
Number of pages purged\&.
.RE
.PP
"stats\&.arenas\&.<i>\&.small\&.allocated" (\fBsize_t\fR) r\- [\fB\-\-enable\-stats\fR]
.RS 4
Number of bytes currently allocated by small objects\&.
.RE
.PP
"stats\&.arenas\&.<i>\&.small\&.nmalloc" (\fBuint64_t\fR) r\- [\fB\-\-enable\-stats\fR]
.RS 4
Cumulative number of allocation requests served by small bins\&.
.RE
.PP
"stats\&.arenas\&.<i>\&.small\&.ndalloc" (\fBuint64_t\fR) r\- [\fB\-\-enable\-stats\fR]
.RS 4
Cumulative number of small objects returned to bins\&.
.RE
.PP
"stats\&.arenas\&.<i>\&.small\&.nrequests" (\fBuint64_t\fR) r\- [\fB\-\-enable\-stats\fR]
.RS 4
Cumulative number of small allocation requests\&.
.RE
.PP
"stats\&.arenas\&.<i>\&.large\&.allocated" (\fBsize_t\fR) r\- [\fB\-\-enable\-stats\fR]
.RS 4
Number of bytes currently allocated by large objects\&.
.RE
.PP
"stats\&.arenas\&.<i>\&.large\&.nmalloc" (\fBuint64_t\fR) r\- [\fB\-\-enable\-stats\fR]
.RS 4
Cumulative number of large allocation requests served directly by the arena\&.
.RE
.PP
"stats\&.arenas\&.<i>\&.large\&.ndalloc" (\fBuint64_t\fR) r\- [\fB\-\-enable\-stats\fR]
.RS 4
Cumulative number of large deallocation requests served directly by the arena\&.
.RE
.PP
"stats\&.arenas\&.<i>\&.large\&.nrequests" (\fBuint64_t\fR) r\- [\fB\-\-enable\-stats\fR]
.RS 4
Cumulative number of large allocation requests\&.
.RE
.PP
"stats\&.arenas\&.<i>\&.huge\&.allocated" (\fBsize_t\fR) r\- [\fB\-\-enable\-stats\fR]
.RS 4
Number of bytes currently allocated by huge objects\&.
.RE
.PP
"stats\&.arenas\&.<i>\&.huge\&.nmalloc" (\fBuint64_t\fR) r\- [\fB\-\-enable\-stats\fR]
.RS 4
Cumulative number of huge allocation requests served directly by the arena\&.
.RE
.PP
"stats\&.arenas\&.<i>\&.huge\&.ndalloc" (\fBuint64_t\fR) r\- [\fB\-\-enable\-stats\fR]
.RS 4
Cumulative number of huge deallocation requests served directly by the arena\&.
.RE
.PP
"stats\&.arenas\&.<i>\&.huge\&.nrequests" (\fBuint64_t\fR) r\- [\fB\-\-enable\-stats\fR]
.RS 4
Cumulative number of huge allocation requests\&.
.RE
.PP
"stats\&.arenas\&.<i>\&.bins\&.<j>\&.nmalloc" (\fBuint64_t\fR) r\- [\fB\-\-enable\-stats\fR]
.RS 4
Cumulative number of allocations served by bin\&.
.RE
.PP
"stats\&.arenas\&.<i>\&.bins\&.<j>\&.ndalloc" (\fBuint64_t\fR) r\- [\fB\-\-enable\-stats\fR]
.RS 4
Cumulative number of allocations returned to bin\&.
.RE
.PP
"stats\&.arenas\&.<i>\&.bins\&.<j>\&.nrequests" (\fBuint64_t\fR) r\- [\fB\-\-enable\-stats\fR]
.RS 4
Cumulative number of allocation requests\&.
.RE
.PP
"stats\&.arenas\&.<i>\&.bins\&.<j>\&.curregs" (\fBsize_t\fR) r\- [\fB\-\-enable\-stats\fR]
.RS 4
Current number of regions for this size class\&.
.RE
.PP
"stats\&.arenas\&.<i>\&.bins\&.<j>\&.nfills" (\fBuint64_t\fR) r\- [\fB\-\-enable\-stats\fR \fB\-\-enable\-tcache\fR]
.RS 4
Cumulative number of tcache fills\&.
.RE
.PP
"stats\&.arenas\&.<i>\&.bins\&.<j>\&.nflushes" (\fBuint64_t\fR) r\- [\fB\-\-enable\-stats\fR \fB\-\-enable\-tcache\fR]
.RS 4
Cumulative number of tcache flushes\&.
.RE
.PP
"stats\&.arenas\&.<i>\&.bins\&.<j>\&.nruns" (\fBuint64_t\fR) r\- [\fB\-\-enable\-stats\fR]
.RS 4
Cumulative number of runs created\&.
.RE
.PP
"stats\&.arenas\&.<i>\&.bins\&.<j>\&.nreruns" (\fBuint64_t\fR) r\- [\fB\-\-enable\-stats\fR]
.RS 4
Cumulative number of times the current run from which to allocate changed\&.
.RE
.PP
"stats\&.arenas\&.<i>\&.bins\&.<j>\&.curruns" (\fBsize_t\fR) r\- [\fB\-\-enable\-stats\fR]
.RS 4
Current number of runs\&.
.RE
.PP
"stats\&.arenas\&.<i>\&.lruns\&.<j>\&.nmalloc" (\fBuint64_t\fR) r\- [\fB\-\-enable\-stats\fR]
.RS 4
Cumulative number of allocation requests for this size class served directly by the arena\&.
.RE
.PP
"stats\&.arenas\&.<i>\&.lruns\&.<j>\&.ndalloc" (\fBuint64_t\fR) r\- [\fB\-\-enable\-stats\fR]
.RS 4
Cumulative number of deallocation requests for this size class served directly by the arena\&.
.RE
.PP
"stats\&.arenas\&.<i>\&.lruns\&.<j>\&.nrequests" (\fBuint64_t\fR) r\- [\fB\-\-enable\-stats\fR]
.RS 4
Cumulative number of allocation requests for this size class\&.
.RE
.PP
"stats\&.arenas\&.<i>\&.lruns\&.<j>\&.curruns" (\fBsize_t\fR) r\- [\fB\-\-enable\-stats\fR]
.RS 4
Current number of runs for this size class\&.
.RE
.PP
"stats\&.arenas\&.<i>\&.hchunks\&.<j>\&.nmalloc" (\fBuint64_t\fR) r\- [\fB\-\-enable\-stats\fR]
.RS 4
Cumulative number of allocation requests for this size class served directly by the arena\&.
.RE
.PP
"stats\&.arenas\&.<i>\&.hchunks\&.<j>\&.ndalloc" (\fBuint64_t\fR) r\- [\fB\-\-enable\-stats\fR]
.RS 4
Cumulative number of deallocation requests for this size class served directly by the arena\&.
.RE
.PP
"stats\&.arenas\&.<i>\&.hchunks\&.<j>\&.nrequests" (\fBuint64_t\fR) r\- [\fB\-\-enable\-stats\fR]
.RS 4
Cumulative number of allocation requests for this size class\&.
.RE
.PP
"stats\&.arenas\&.<i>\&.hchunks\&.<j>\&.curhchunks" (\fBsize_t\fR) r\- [\fB\-\-enable\-stats\fR]
.RS 4
Current number of huge allocations for this size class\&.
.RE
.SH "DEBUGGING MALLOC PROBLEMS"
.PP
When debugging, it is a good idea to configure/build jemalloc with the
\fB\-\-enable\-debug\fR
and
\fB\-\-enable\-fill\fR
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\&.
.PP
Programs often accidentally depend on \(lquninitialized\(rq memory actually being filled with zero bytes\&. Junk filling (see the
"opt\&.junk"
option) tends to expose such bugs in the form of obviously incorrect results and/or coredumps\&. Conversely, zero filling (see the
"opt\&.zero"
option) eliminates the symptoms of such bugs\&. Between these two options, it is usually possible to quickly detect, diagnose, and eliminate such bugs\&.
.PP
This implementation does not provide much detail about the problems it detects, because the performance impact for storing such information would be prohibitive\&. However, jemalloc does integrate with the most excellent
\m[blue]\fBValgrind\fR\m[]\&\s-2\u[2]\d\s+2
tool if the
\fB\-\-enable\-valgrind\fR
configuration option is enabled\&.
.SH "DIAGNOSTIC MESSAGES"
.PP
If any of the memory allocation/deallocation functions detect an error or warning condition, a message will be printed to file descriptor
\fBSTDERR_FILENO\fR\&. Errors will result in the process dumping core\&. If the
"opt\&.abort"
option is set, most warnings are treated as errors\&.
.PP
The
\fImalloc_message\fR
variable allows the programmer to override the function which emits the text strings forming the errors and warnings if for some reason the
\fBSTDERR_FILENO\fR
file descriptor is not suitable for this\&.
\fBmalloc_message\fR\fB\fR
takes the
\fIcbopaque\fR
pointer argument that is
\fBNULL\fR
unless overridden by the arguments in a call to
\fBmalloc_stats_print\fR\fB\fR, 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\&.
.PP
All messages are prefixed by \(lq<jemalloc>:\(rq\&.
.SH "RETURN VALUES"
.SS "Standard API"
.PP
The
\fBmalloc\fR\fB\fR
and
\fBcalloc\fR\fB\fR
functions return a pointer to the allocated memory if successful; otherwise a
\fBNULL\fR
pointer is returned and
\fIerrno\fR
is set to
ENOMEM\&.
.PP
The
\fBposix_memalign\fR\fB\fR
function returns the value 0 if successful; otherwise it returns an error value\&. The
\fBposix_memalign\fR\fB\fR
function will fail if:
.PP
EINVAL
.RS 4
The
\fIalignment\fR
parameter is not a power of 2 at least as large as
sizeof(\fBvoid *\fR)\&.
.RE
.PP
ENOMEM
.RS 4
Memory allocation error\&.
.RE
.PP
The
\fBaligned_alloc\fR\fB\fR
function returns a pointer to the allocated memory if successful; otherwise a
\fBNULL\fR
pointer is returned and
\fIerrno\fR
is set\&. The
\fBaligned_alloc\fR\fB\fR
function will fail if:
.PP
EINVAL
.RS 4
The
\fIalignment\fR
parameter is not a power of 2\&.
.RE
.PP
ENOMEM
.RS 4
Memory allocation error\&.
.RE
.PP
The
\fBrealloc\fR\fB\fR
function returns a pointer, possibly identical to
\fIptr\fR, to the allocated memory if successful; otherwise a
\fBNULL\fR
pointer is returned, and
\fIerrno\fR
is set to
ENOMEM
if the error was the result of an allocation failure\&. The
\fBrealloc\fR\fB\fR
function always leaves the original buffer intact when an error occurs\&.
.PP
The
\fBfree\fR\fB\fR
function returns no value\&.
.SS "Non\-standard API"
.PP
The
\fBmallocx\fR\fB\fR
and
\fBrallocx\fR\fB\fR
functions return a pointer to the allocated memory if successful; otherwise a
\fBNULL\fR
pointer is returned to indicate insufficient contiguous memory was available to service the allocation request\&.
.PP
The
\fBxallocx\fR\fB\fR
function returns the real size of the resulting resized allocation pointed to by
\fIptr\fR, which is a value less than
\fIsize\fR
if the allocation could not be adequately grown in place\&.
.PP
The
\fBsallocx\fR\fB\fR
function returns the real size of the allocation pointed to by
\fIptr\fR\&.
.PP
The
\fBnallocx\fR\fB\fR
returns the real size that would result from a successful equivalent
\fBmallocx\fR\fB\fR
function call, or zero if insufficient memory is available to perform the size computation\&.
.PP
The
\fBmallctl\fR\fB\fR,
\fBmallctlnametomib\fR\fB\fR, and
\fBmallctlbymib\fR\fB\fR
functions return 0 on success; otherwise they return an error value\&. The functions will fail if:
.PP
EINVAL
.RS 4
\fInewp\fR
is not
\fBNULL\fR, and
\fInewlen\fR
is too large or too small\&. Alternatively,
\fI*oldlenp\fR
is too large or too small; in this case as much data as possible are read despite the error\&.
.RE
.PP
ENOENT
.RS 4
\fIname\fR
or
\fImib\fR
specifies an unknown/invalid value\&.
.RE
.PP
EPERM
.RS 4
Attempt to read or write void value, or attempt to write read\-only value\&.
.RE
.PP
EAGAIN
.RS 4
A memory allocation failure occurred\&.
.RE
.PP
EFAULT
.RS 4
An interface with side effects failed in some way not directly related to
\fBmallctl*\fR\fB\fR
read/write processing\&.
.RE
.PP
The
\fBmalloc_usable_size\fR\fB\fR
function returns the usable size of the allocation pointed to by
\fIptr\fR\&.
.SH "ENVIRONMENT"
.PP
The following environment variable affects the execution of the allocation functions:
.PP
\fBMALLOC_CONF\fR
.RS 4
If the environment variable
\fBMALLOC_CONF\fR
is set, the characters it contains will be interpreted as options\&.
.RE
.SH "EXAMPLES"
.PP
To dump core whenever a problem occurs:
.sp
.if n \{\
.RS 4
.\}
.nf
ln \-s \*(Aqabort:true\*(Aq /etc/malloc\&.conf
.fi
.if n \{\
.RE
.\}
.PP
To specify in the source a chunk size that is 16 MiB:
.sp
.if n \{\
.RS 4
.\}
.nf
malloc_conf = "lg_chunk:24";
.fi
.if n \{\
.RE
.\}
.SH "SEE ALSO"
.PP
\fBmadvise\fR(2),
\fBmmap\fR(2),
\fBsbrk\fR(2),
\fButrace\fR(2),
\fBalloca\fR(3),
\fBatexit\fR(3),
\fBgetpagesize\fR(3)
.SH "STANDARDS"
.PP
The
\fBmalloc\fR\fB\fR,
\fBcalloc\fR\fB\fR,
\fBrealloc\fR\fB\fR, and
\fBfree\fR\fB\fR
functions conform to ISO/IEC 9899:1990 (\(lqISO C90\(rq)\&.
.PP
The
\fBposix_memalign\fR\fB\fR
function conforms to IEEE Std 1003\&.1\-2001 (\(lqPOSIX\&.1\(rq)\&.
.SH "AUTHOR"
.PP
\fBJason Evans\fR
.RS 4
.RE
.SH "NOTES"
.IP " 1." 4
jemalloc website
.RS 4
\%http://www.canonware.com/jemalloc/
.RE
.IP " 2." 4
Valgrind
.RS 4
\%http://valgrind.org/
.RE
.IP " 3." 4
gperftools package
.RS 4
\%http://code.google.com/p/gperftools/
.RE
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