Refactored and optimized implementation

CHANGELOG

@@ -1,3 +1,31 @@
+1.4.0
+
+Improved cross thread deallocations by using per-span atomic free list to minimize thread
+contention and localize free list processing to actual span
+
+Change span free list to a linked list, conditionally initialized one memory page at a time
+
+Reduce number of conditionals in the fast path allocation and avoid touching heap structure
+at all in best case
+
+Avoid realigning block in deallocation unless span marked as used by alignment > 32 bytes
+
+Revert block granularity and natural alignment to 16 bytes to reduce memory waste
+
+Bugfix for preserving data when reallocating a previously aligned (>32 bytes) block
+
+Use compile time span size by default for improved performance, added build time RPMALLOC_CONFIGURABLE
+preprocessor directive to reenable configurability of span and page size
+
+More detailed statistics
+
+Disabled adaptive thread cache by default
+
+Fixed an issue where reallocations of large blocks could read outsize of memory page boundaries
+
+Tag mmap requests on macOS with tag 240 for identification with vmmap tool
+
+
 1.3.2
 
 Support for alignment equal or larger than memory page size, up to span size

build/ninja/clang.py

@@ -40,15 +40,15 @@ def initialize(self, project, archs, configs, includepaths, dependlibs, libpaths
 
     #Base flags
     self.cflags = ['-D' + project.upper() + '_COMPILE=1',
-                   '-funit-at-a-time', '-fstrict-aliasing',
-                   '-fno-math-errno','-ffinite-math-only', '-funsafe-math-optimizations',
+                   '-funit-at-a-time', '-fstrict-aliasing', '-fvisibility=hidden', '-fno-stack-protector',
+                   '-fomit-frame-pointer', '-fno-math-errno','-ffinite-math-only', '-funsafe-math-optimizations',
                    '-fno-trapping-math', '-ffast-math']
     self.cwarnflags = ['-W', '-Werror', '-pedantic', '-Wall', '-Weverything',
-                       '-Wno-padded', '-Wno-documentation-unknown-command']
+                       '-Wno-padded', '-Wno-documentation-unknown-command', '-Wno-static-in-inline']
     self.cmoreflags = []
     self.mflags = []
     self.arflags = []
-    self.linkflags = []
+    self.linkflags = ['-fomit-frame-pointer']
     self.oslibs = []
     self.frameworks = []
 
@@ -65,7 +65,6 @@ def initialize(self, project, archs, configs, includepaths, dependlibs, libpaths
     if self.target.is_linux() or self.target.is_bsd() or self.target.is_raspberrypi():
       self.cflags += ['-D_GNU_SOURCE=1']
       self.linkflags += ['-pthread']
-      self.oslibs += ['m']
     if self.target.is_linux() or self.target.is_raspberrypi():
       self.oslibs += ['dl']
     if self.target.is_bsd():
@@ -85,7 +84,7 @@ def initialize(self, project, archs, configs, includepaths, dependlibs, libpaths
       self.cflags += ['-w']
     self.cxxflags = list(self.cflags)
 
-    self.cflags += ['-std=c11']
+    self.cflags += ['-std=gnu11']
     if self.target.is_macos() or self.target.is_ios():
       self.cxxflags += ['-std=c++14', '-stdlib=libc++']
     else:
@@ -311,7 +310,7 @@ def make_carchflags(self, arch, targettype):
     flags = []
     if targettype == 'sharedlib':
       flags += ['-DBUILD_DYNAMIC_LINK=1']
-      if self.target.is_linux():
+      if self.target.is_linux() or self.target.is_bsd():
        flags += ['-fPIC']
     flags += self.make_targetarchflags(arch, targettype)
     return flags
@@ -321,11 +320,11 @@ def make_cconfigflags(self, config, targettype):
     if config == 'debug':
       flags += ['-DBUILD_DEBUG=1', '-g']
     elif config == 'release':
-      flags += ['-DBUILD_RELEASE=1', '-O3', '-g', '-funroll-loops']
+      flags += ['-DBUILD_RELEASE=1', '-DNDEBUG', '-O3', '-g', '-funroll-loops']
     elif config == 'profile':
-      flags += ['-DBUILD_PROFILE=1', '-O3', '-g', '-funroll-loops']
+      flags += ['-DBUILD_PROFILE=1', '-DNDEBUG', '-O3', '-g', '-funroll-loops']
     elif config == 'deploy':
-      flags += ['-DBUILD_DEPLOY=1', '-O3', '-g', '-funroll-loops']
+      flags += ['-DBUILD_DEPLOY=1', '-DNDEBUG', '-O3', '-g', '-funroll-loops']
     return flags
 
   def make_ararchflags(self, arch, targettype):
@@ -363,7 +362,9 @@ def make_linkconfigflags(self, config, targettype, variables):
         flags += ['-dynamiclib']
     else:
       if targettype == 'sharedlib':
-        flags += ['-shared']
+        flags += ['-shared', '-fPIC']
+    if config == 'release':
+      flags += ['-DNDEBUG', '-O3']
     return flags
 
   def make_linkarchlibs(self, arch, targettype):

build/ninja/gcc.py

@@ -52,7 +52,6 @@ def initialize(self, project, archs, configs, includepaths, dependlibs, libpaths
     if self.target.is_linux() or self.target.is_bsd() or self.target.is_raspberrypi():
       self.cflags += ['-D_GNU_SOURCE=1']
       self.linkflags += ['-pthread']
-      self.oslibs += ['m']
     if self.target.is_linux() or self.target.is_raspberrypi():
       self.oslibs += ['dl']
     if self.target.is_bsd():
@@ -183,7 +182,7 @@ def make_carchflags(self, arch, targettype):
     flags = []
     if targettype == 'sharedlib':
       flags += ['-DBUILD_DYNAMIC_LINK=1']
-      if self.target.is_linux():
+      if self.target.is_linux() or self.target.is_bsd():
         flags += ['-fPIC']
     flags += self.make_targetarchflags(arch, targettype)
     return flags

build/ninja/msvc.py

@@ -22,7 +22,7 @@ def initialize(self, project, archs, configs, includepaths, dependlibs, libpaths
     self.linker = 'link'
     self.dller = 'dll'
 
-    #Command definitions
+    #Command definitions (to generate assembly, add "/FAs /Fa$out.asm")
     self.cccmd = '$toolchain$cc /showIncludes /I. $includepaths $moreincludepaths $cflags $carchflags $cconfigflags $cmoreflags /c $in /Fo$out /Fd$pdbpath /FS /nologo'
     self.cxxcmd = '$toolchain$cxx /showIncludes /I. $includepaths $moreincludepaths $cxxflags $carchflags $cconfigflags $cmoreflags /c $in /Fo$out /Fd$pdbpath /FS /nologo'
     self.ccdepfile = None

configure.py

@@ -10,21 +10,14 @@
 import generator
 
 generator = generator.Generator(project = 'rpmalloc', variables = [('bundleidentifier', 'com.rampantpixels.rpmalloc.$(binname)')])
-target = generator.target
-writer = generator.writer
-toolchain = generator.toolchain
 
 rpmalloc_lib = generator.lib(module = 'rpmalloc', libname = 'rpmalloc', sources = ['rpmalloc.c'])
 
-if not target.is_android() and not target.is_ios():
+if not generator.target.is_android() and not generator.target.is_ios():
 	rpmalloc_so = generator.sharedlib(module = 'rpmalloc', libname = 'rpmalloc', sources = ['rpmalloc.c'])
 
-if not target.is_windows():
-	if not target.is_android() and not target.is_ios():
-		rpmallocwrap_lib = generator.lib(module = 'rpmalloc', libname = 'rpmallocwrap', sources = ['rpmalloc.c', 'malloc.c', 'new.cc'], variables = {'defines': ['ENABLE_PRELOAD=1']})
+	rpmallocwrap_so = generator.sharedlib(module = 'rpmalloc', libname = 'rpmallocwrap', sources = ['rpmalloc.c'], variables = {'defines': ['ENABLE_PRELOAD=1', 'ENABLE_OVERRIDE=1']})
+	rpmallocwrap_lib = generator.lib(module = 'rpmalloc', libname = 'rpmallocwrap', sources = ['rpmalloc.c'], variables = {'defines': ['ENABLE_PRELOAD=1', 'ENABLE_OVERRIDE=1']})
 
-	if not target.is_windows() and not target.is_android() and not target.is_ios():
-		rpmallocwrap_so = generator.sharedlib(module = 'rpmalloc', libname = 'rpmallocwrap', sources = ['rpmalloc.c', 'malloc.c', 'new.cc'], variables = {'runtime': 'c++', 'defines': ['ENABLE_PRELOAD=1']})
-
-if not target.is_ios() and not target.is_android():
 	generator.bin(module = 'test', sources = ['thread.c', 'main.c'], binname = 'rpmalloc-test', implicit_deps = [rpmalloc_lib], libs = ['rpmalloc'], includepaths = ['rpmalloc', 'test'], variables = {'defines': ['ENABLE_ASSERTS=1', 'ENABLE_STATISTICS=1']})
+	generator.bin(module = 'test', sources = ['thread.c', 'main-override.cc'], binname = 'rpmallocwrap-test', implicit_deps = [rpmallocwrap_lib], libs = ['rpmallocwrap'], includepaths = ['rpmalloc', 'test'], variables = {'runtime': 'c++', 'defines': ['ENABLE_ASSERTS=1', 'ENABLE_STATISTICS=1']})