GitLab

Teo Camarasu pushed to branch wip/hugepages at Glasgow Haskell Compiler / GHC

Commits:

c8210d78

by Teo Camarasu at 2026-07-20T18:09:44+01:00

rts: Implement support for 2MB hugepages

We enable/disable it through a runtime flag (-xH).

When enabled we ensure we only (de)allocate in aligned multiples of 2MB.

This is only available under x86_64 Linux.
It isn't available under wasm and i386.

Relates to #24760

Co-authored-by: Matthew Pickering <matthewtpickering@gmail.com>
Co-authored-by: Ben Gamari <bgamari.foss@gmail.com>

76c19dd0
by Teo Camarasu at 2026-07-20T18:10:41+01:00
```
DROP ME: enable hugepages in default flavour
```

12 changed files:

docs/users_guide/runtime_control.rst
hadrian/doc/flavours.md
hadrian/src/Flavour.hs
hadrian/src/Settings/Default.hs
rts/RtsFlags.c
rts/configure.ac
rts/include/rts/Constants.h
rts/include/rts/Flags.h
rts/posix/OSMem.c
rts/sm/OSMem.h
testsuite/tests/rts/all.T
+ testsuite/tests/rts/testhugepagesmblockalloc.c

Changes:

docs/users_guide/runtime_control.rst

@@ -378,6 +378,16 @@ Miscellaneous RTS options
      If given, instruct the runtime linker to try to continue linking in the
      presence of an unresolved symbol.
 +.. rts-flag:: -xH
++
 +    This option enables using huge pages to back memory allocations.
 +    Use of huge pages can make memory lookups more efficient for applications
 +    with high memory usage.
 +    Currently we only support 2MB hugepages on Linux.
++
 +    If huge pages aren't available to back allocations, then we fall back to
 +    regular pages.
++
  .. _rts-options-gc:
  RTS options to control the garbage collector

hadrian/doc/flavours.md

@@ -321,6 +321,10 @@ The supported transformers are listed below:
          <td><code>hie_files</code></td>
          <td>Produce hie files for stage1 libraries</td>
      </tr>
 +    <tr>
 +        <td><code>hugepages</code></td>
 +        <td>Enable support for hugepages in the RTS.</td>
 +    </tr>
  </table>
  ## Ways

hadrian/src/Flavour.hs

@@ -25,6 +25,7 @@ module Flavour
    , enableTextWithSIMDUTF
    , enableHieFiles
    , omitPragmas
 +  , enableHugepages
    , completeSetting
    , applySettings
@@ -86,6 +87,7 @@ flavourTransformers = M.fromList
      , "dump_stg"         =: enableDumpStg
      , "hash_unit_ids"    =: enableHashUnitIds
      , "hie_files"        =: enableHieFiles
 +    , "hugepages"        =: enableHugepages
+     ]
    where (=:) = (,)
@@ -316,6 +318,14 @@ enableUBSan =
            builder Testsuite ? arg "--config=have_ubsan=True"
+         ]
 +enableHugepages :: Flavour -> Flavour
 +enableHugepages =
 +  addArgs $
 +    mconcat [package rts
 +            ? builder (Cabal Setup)
 +            ? arg "--configure-option=--enable-hugepages"
 +            ]
++
  -- | Use the LLVM backend in target stages
  viaLlvmBackend :: Flavour -> Flavour
  viaLlvmBackend = addArgs $ staged buildingForTarget ? builder Ghc ? arg "-fllvm"

hadrian/src/Settings/Default.hs

@@ -20,6 +20,7 @@ import qualified Hadrian.Builder.Tar
  import CommandLine
  import Expression
 +import Flavour
  import Flavour.Type
  import Oracles.Flag
  import Oracles.Setting
@@ -286,7 +287,7 @@ defaultSourceArgs = SourceArgs
  -- | Default build flavour. Other build flavours are defined in modules
  -- @Settings.Flavours.*@. Users can add new build flavours in "UserSettings".
  defaultFlavour :: Flavour
 -defaultFlavour = Flavour
 +defaultFlavour = enableHugepages $ Flavour
      { name               = "default"
      , extraArgs          = defaultExtraArgs
      , packages           = defaultPackages

rts/RtsFlags.c

@@ -182,6 +182,7 @@ void initRtsFlagsDefaults(void)
      RtsFlags.GcFlags.allocLimitGrace    = (100*1024) / BLOCK_SIZE;
      RtsFlags.GcFlags.numa               = false;
      RtsFlags.GcFlags.numaMask           = 1;
 +    RtsFlags.GcFlags.hugepages          = false;
      RtsFlags.GcFlags.ringBell           = false;
      RtsFlags.GcFlags.longGCSync         = 0; /* detection turned off */
@@ -572,7 +573,10 @@ usage_text[] = {
  #endif
  "  -xq        The allocation limit given to a thread after it receives",
  "             an AllocationLimitExceeded exception. (default: 100k)",
 +#if defined(HUGEPAGE_FLAGS)
 +"  -xH        Try to use hugepages to allocate memory.",
  "",
 +#endif
  #if defined(USE_LARGE_ADDRESS_SPACE)
  "  -xr        The size of virtual memory address space reserved by the",
  "             two step allocator (default: 1T)",
@@ -1850,11 +1854,11 @@ error = true;
                     */
                  case 'q':
 -                  OPTION_UNSAFE;
 -                  RtsFlags.GcFlags.allocLimitGrace
 -                      = decodeSize(rts_argv[arg], 3, BLOCK_SIZE, HS_INT_MAX)
 -                          / BLOCK_SIZE;
 -                  break;
 +                    OPTION_UNSAFE;
 +                    RtsFlags.GcFlags.allocLimitGrace
 +                        = decodeSize(rts_argv[arg], 3, BLOCK_SIZE, HS_INT_MAX)
 +                            / BLOCK_SIZE;
 +                    break;
                  case 'r':
                      OPTION_UNSAFE;
@@ -1862,7 +1866,16 @@ error = true;
                        = decodeSize(rts_argv[arg], 3, MBLOCK_SIZE, HS_WORD64_MAX);
                      break;
 -                  default:
 +                case 'H':
 +                    OPTION_UNSAFE;
 +#if defined(HUGEPAGE_FLAGS)
 +                    RtsFlags.GcFlags.hugepages = true;
 +#else
 +                    errorBelch("Program not compiled with hugepages support.");
 +#endif
 +                    break;
++
 +                default:
                      OPTION_SAFE;
                      errorBelch("unknown RTS option: %s",rts_argv[arg]);
                      error = true;

rts/configure.ac

@@ -37,6 +37,17 @@ if test "$enable_asserts_all_ways" = "yes" ; then
     AC_DEFINE([USE_ASSERTS_ALL_WAYS], [1], [Compile-in ASSERTs in all ways.])
  fi
 +AC_ARG_ENABLE(hugepages,
 +[AS_HELP_STRING([--enable-hugepages],
 +                [Enable hugepages and set the MBlock size to 2MB.])],
 +  [FP_CAPITALIZE_YES_NO(["$enableval"], [EnableHugepages])],
 +  [EnableHugepages=NO]
 +)
 +if test "$enable_hugepages" = "yes" ; then
 +   AC_DEFINE([USE_HUGEPAGES], [1], [Enable support for hugepages and set MBlock size to 2MB.])
 +fi
++
++
  # We have to run these unconditionally, but we may discard their
  # results in the following code
  AC_CANONICAL_BUILD
@@ -96,7 +107,7 @@ dnl    off_t, because it will affect the result of that test.
  AC_SYS_LARGEFILE
  dnl ** check for specific header (.h) files that we are interested in
 -AC_CHECK_HEADERS([ctype.h dlfcn.h errno.h fcntl.h limits.h locale.h nlist.h pthread.h signal.h sys/param.h sys/mman.h sys/resource.h sys/select.h sys/time.h sys/timeb.h sys/timerfd.h sys/timers.h sys/times.h sys/utsname.h sys/wait.h termios.h utime.h windows.h winsock.h sched.h])
 +AC_CHECK_HEADERS([ctype.h dlfcn.h errno.h fcntl.h limits.h locale.h nlist.h pthread.h signal.h sys/param.h sys/mman.h linux/mman.h sys/resource.h sys/select.h sys/time.h sys/timeb.h sys/timerfd.h sys/timers.h sys/times.h sys/utsname.h sys/wait.h termios.h utime.h windows.h winsock.h sched.h])
  dnl sys/cpuset.h needs sys/param.h to be included first on FreeBSD 9.1; #7708
  AC_CHECK_HEADERS([sys/cpuset.h], [], [],

rts/include/rts/Constants.h

@@ -171,6 +171,8 @@
  /* The size of a megablock (2^MBLOCK_SHIFT bytes) */
  #if defined(wasm32_HOST_ARCH)
  #define MBLOCK_SHIFT   16
 +#elif defined(USE_HUGEPAGES)
 +#define MBLOCK_SHIFT   21
  #else
  #define MBLOCK_SHIFT   20
  #endif

rts/include/rts/Flags.h

@@ -91,6 +91,7 @@ typedef struct _GC_FLAGS {
      StgWord numaMask;
      StgWord64 addressSpaceSize;  /* large address space size in bytes */
 +    bool hugepages;              /* Enable hugepages support */
  } GC_FLAGS;
  /* See Note [Synchronization of flags and base APIs] */

rts/posix/OSMem.c

@@ -73,6 +73,11 @@
  # endif
  #endif
 +#if defined(HUGEPAGE_FLAGS)
 +static int huge_tried = 0;
 +static int huge_failed = 0;
 +#endif
++
  static void *next_request = 0;
  void osMemInit(void)
@@ -233,12 +238,28 @@ my_mmap (void *addr, W_ size, int operation)
          errorBelch("my_mmap(,,MEM_RESERVE) not supported on this platform");
  # endif
      } else if (operation == MEM_COMMIT) {
 -        flags = MAP_FIXED | MAP_ANON | MAP_PRIVATE;
 +        flags = MAP_FIXED | MAP_ANONYMOUS | MAP_PRIVATE;
 +#if defined(HUGEPAGE_FLAGS)
 +        if ( RtsFlags.GcFlags.hugepages &&
 +            (size & (HUGEPAGE_SIZE - 1)) == 0) {
 +          huge_tried += 1;
 +          flags |= HUGEPAGE_FLAGS;
 +        }
 +#endif /* defined(HUGEPAGE_FLAGS) */
      } else {
          flags = MAP_ANON | MAP_PRIVATE;
+     }
      ret = mmap(addr, size, prot, flags, -1, 0);
 +#if defined(HUGEPAGE_FLAGS)
 +    // If the mmap failed, and we tried with HUGEPAGE_FLAGS
 +    // then retry without.
 +    if (ret == MAP_FAILED && flags & HUGEPAGE_FLAGS){
 +      huge_failed += 1;
 +      flags &= ~HUGEPAGE_FLAGS;
 +      ret = mmap(addr, size, prot, flags, -1, 0);
 +    }
 +#endif
  # if defined(linux_HOST_OS)
      if (ret == MAP_FAILED && errno == EPERM) {
          // Linux may return EPERM if it tried to give us

rts/sm/OSMem.h

@@ -8,6 +8,12 @@
  #pragma once
 +#if defined(HAVE_LINUX_MMAN_H) && defined(USE_HUGEPAGES)
 +#include <linux/mman.h>
 +#define HUGEPAGE_FLAGS (MAP_HUGETLB | MAP_HUGE_2MB)
 +#define HUGEPAGE_SIZE MBLOCK_SIZE
 +#endif
++
  #include "BeginPrivate.h"
  void osMemInit(void);

testsuite/tests/rts/all.T

@@ -15,6 +15,15 @@ test('testmblockalloc',
  # which will crash because the mblocks we allocate are not in a state
  # the leak detector is expecting.
 +# A variant of the above that tries to use hugepages
 +test('testhugepagesmblockalloc',
 +     [c_src, only_ways(['normal','threaded1']), extra_run_opts('+RTS -I0 -xr0.125T -xH'),
 +      unless(opsys('linux'), skip), # Huge pages are only currently supported on Linux
 +      when(arch('wasm32'), skip), # MBlocks can't be freed on wasm32, see Note [Megablock allocator on wasm] in rts
 +      when(arch('i386'), skip), # Not available under i386
 +      ],
 +     compile_and_run, [''])
++
  # See bug #101, test requires +RTS -c (or equivalently +RTS -M<something>)
  # only GHCi triggers the bug, but we run the test all ways for completeness.

testsuite/tests/rts/testhugepagesmblockalloc.c

 +#include "Rts.h"
++
 +#include <stdio.h>
++
 +// 16 * 64 == max 1GB
 +const int MAXALLOC = 16;
 +const int ARRSIZE  = 64;
++
 +const int LOOPS    = 1000;
 +const int SEED     = 0xf00f00;
++
 +extern StgWord mblocks_allocated;
++
 +int main (int argc, char *argv[])
 +{
 +    int i, j, b;
++
 +    void *a[ARRSIZE];
 +    uint32_t sizes[ARRSIZE];
++
 +    srand(SEED);
++
 +    {
 +        RtsConfig conf = defaultRtsConfig;
 +        conf.rts_opts_enabled = RtsOptsAll;
 +        hs_init_ghc(&argc, &argv, conf);
 +    }
++
 +   // repeatedly sweep though the array, allocating new random-sized
 +   // objects and deallocating the old ones.
 +   for (i=0; i < LOOPS; i++)
 +   {
 +       for (j=0; j < ARRSIZE; j++)
 +       {
 +           if (i > 0)
 +           {
 +               freeMBlocks(a[j], sizes[j]);
 +           }
 +           b = (rand() % MAXALLOC) + 1;
 +           a[j] = getMBlocks(b);
 +           sizes[j] = b;
 +       }
 +   }
++
 +   releaseFreeMemory();
++
 +   for (j=0; j < ARRSIZE; j++)
 +   {
 +       freeMBlocks(a[j], sizes[j]);
 +   }
++
 +   releaseFreeMemory();
++
 +    // this time, sweep forwards allocating new blocks, and then
 +    // backwards deallocating them.
 +    for (i=0; i < LOOPS; i++)
 +    {
 +        for (j=0; j < ARRSIZE; j++)
 +        {
 +            b = (rand() % MAXALLOC) + 1;
 +            a[j] = getMBlocks(b);
 +            sizes[j] = b;
 +        }
 +        for (j=ARRSIZE-1; j >= 0; j--)
 +        {
 +            freeMBlocks(a[j], sizes[j]);
 +        }
 +    }
++
 +    releaseFreeMemory();
++
 +    hs_exit(); // will do a memory leak test
++
 +    exit(0);
 +}