[PATCH] D39464: Define fs::allocate_file which preallocates disk blocks.

[Rafael Avila de Espindola via llvm-commits]

Why create a new function?

Currently rename is only used in FileOutputBuffer.cpp.

I am OK with renaming rename to allocate_file if you want.

Cheers,
Rafael

Rui Ueyama via Phabricator <reviews at reviews.llvm.org> writes:

> ruiu created this revision.
> Herald added subscribers: hiraditya, mgorny.
>
> Unlike fs::resize_file, the new function guarantees that disk blocks
> for a given size are actually allocated on a file system. In other
> words, it doesn't create a sparse file.
>
> If you want to do mmap IO, you generally want to preallocate disk
> blocks if you can, because if you mmap a sparse file for writing and
> the disk becomes full, your process will be killed by SIGBUS. There's
> no way to gracefully handle that error condition. If you use fallocate(2)
> or equivalent, you can handle that error before calling mmap.
>
> My plan is to use this function in FileOutputBuffer so that we do mmap
> IO only when we can preallocate disk blocks. That prevents LLVM tools
> from crashing with a mysterious bus error when a disk is almost full.
>
>
> https://reviews.llvm.org/D39464
>
> Files:
>   llvm/cmake/config-ix.cmake
>   llvm/include/llvm/Config/config.h.cmake
>   llvm/include/llvm/Support/FileSystem.h
>   llvm/lib/Support/Unix/Path.inc
>   llvm/lib/Support/Windows/Path.inc
>
>
> Index: llvm/lib/Support/Windows/Path.inc
> ===================================================================
> --- llvm/lib/Support/Windows/Path.inc
> +++ llvm/lib/Support/Windows/Path.inc
> @@ -509,6 +509,8 @@
>    return std::error_code(error, std::generic_category());
>  }
>  
> +std::error_code allocate_file(int FD, uint64_t Size) { resize_file(FD, Size); }
> +
>  std::error_code access(const Twine &Path, AccessMode Mode) {
>    SmallVector<wchar_t, 128> PathUtf16;
>  
> Index: llvm/lib/Support/Unix/Path.inc
> ===================================================================
> --- llvm/lib/Support/Unix/Path.inc
> +++ llvm/lib/Support/Unix/Path.inc
> @@ -438,6 +438,23 @@
>    return std::error_code();
>  }
>  
> +std::error_code resize_file(int FD, uint64_t Size) {
> +#ifdef HAVE_FALLOCATE
> +  if (fallocate(FD, 0, 0, Size) == -1)
> +    return std::error_code(errno, std::generic_category());
> +  return std::error_code();
> +#endif HAVE_FALLOCATE
> +
> +#ifdef __APPLE__
> +  fstore_t Store = {F_ALLOCATEALL, F_PEOFPOSMODE, 0, Size};
> +  if (fcntl(fd, F_PREALLOCATE, &Store) == -1)
> +    return std::error_code(errno, std::generic_category());
> +  return std::error_code();
> +#endif
> +
> +  return make_error_code(errc::function_not_supported);
> +}
> +
>  static int convertAccessMode(AccessMode Mode) {
>    switch (Mode) {
>    case AccessMode::Exist:
> Index: llvm/include/llvm/Support/FileSystem.h
> ===================================================================
> --- llvm/include/llvm/Support/FileSystem.h
> +++ llvm/include/llvm/Support/FileSystem.h
> @@ -391,6 +391,14 @@
>  ///          platform-specific error_code.
>  std::error_code resize_file(int FD, uint64_t Size);
>  
> +/// @brief Preallocate disk blocks to a given file.
> +///
> +/// @param FD Input file descriptor.
> +/// @param Size Size to resize to.
> +/// @returns errc::success if \a path has been resized to \a size, otherwise a
> +///          platform-specific error_code.
> +std::error_code allocate_file(int FD, uint64_t Size);
> +
>  /// @brief Compute an MD5 hash of a file's contents.
>  ///
>  /// @param FD Input file descriptor.
> Index: llvm/include/llvm/Config/config.h.cmake
> ===================================================================
> --- llvm/include/llvm/Config/config.h.cmake
> +++ llvm/include/llvm/Config/config.h.cmake
> @@ -59,6 +59,9 @@
>  /* Define to 1 if you have the <errno.h> header file. */
>  #cmakedefine HAVE_ERRNO_H ${HAVE_ERRNO_H}
>  
> +/* Define to 1 if you have the `fallocate' function. */
> +#cmakedefine HAVE_FALLOCATE ${HAVE_FALLOCATE}
> +
>  /* Define to 1 if you have the <fcntl.h> header file. */
>  #cmakedefine HAVE_FCNTL_H ${HAVE_FCNTL_H}
>  
> Index: llvm/cmake/config-ix.cmake
> ===================================================================
> --- llvm/cmake/config-ix.cmake
> +++ llvm/cmake/config-ix.cmake
> @@ -197,6 +197,11 @@
>  check_symbol_exists(futimens sys/stat.h HAVE_FUTIMENS)
>  check_symbol_exists(futimes sys/time.h HAVE_FUTIMES)
>  check_symbol_exists(posix_fallocate fcntl.h HAVE_POSIX_FALLOCATE)
> +
> +set(CMAKE_REQUIRED_DEFINITIONS "-D_GNU_SOURCE")
> +check_symbol_exists(fallocate fcntl.h HAVE_FALLOCATE)
> +set(CMAKE_REQUIRED_DEFINITIONS "")
> +
>  # AddressSanitizer conflicts with lib/Support/Unix/Signals.inc
>  # Avoid sigaltstack on Apple platforms, where backtrace() cannot handle it
>  # (rdar://7089625) and _Unwind_Backtrace is unusable because it cannot unwind
>
>
> Index: llvm/lib/Support/Windows/Path.inc
> ===================================================================
> --- llvm/lib/Support/Windows/Path.inc
> +++ llvm/lib/Support/Windows/Path.inc
> @@ -509,6 +509,8 @@
>    return std::error_code(error, std::generic_category());
>  }
>  
> +std::error_code allocate_file(int FD, uint64_t Size) { resize_file(FD, Size); }
> +
>  std::error_code access(const Twine &Path, AccessMode Mode) {
>    SmallVector<wchar_t, 128> PathUtf16;
>  
> Index: llvm/lib/Support/Unix/Path.inc
> ===================================================================
> --- llvm/lib/Support/Unix/Path.inc
> +++ llvm/lib/Support/Unix/Path.inc
> @@ -438,6 +438,23 @@
>    return std::error_code();
>  }
>  
> +std::error_code resize_file(int FD, uint64_t Size) {
> +#ifdef HAVE_FALLOCATE
> +  if (fallocate(FD, 0, 0, Size) == -1)
> +    return std::error_code(errno, std::generic_category());
> +  return std::error_code();
> +#endif HAVE_FALLOCATE
> +
> +#ifdef __APPLE__
> +  fstore_t Store = {F_ALLOCATEALL, F_PEOFPOSMODE, 0, Size};
> +  if (fcntl(fd, F_PREALLOCATE, &Store) == -1)
> +    return std::error_code(errno, std::generic_category());
> +  return std::error_code();
> +#endif
> +
> +  return make_error_code(errc::function_not_supported);
> +}
> +
>  static int convertAccessMode(AccessMode Mode) {
>    switch (Mode) {
>    case AccessMode::Exist:
> Index: llvm/include/llvm/Support/FileSystem.h
> ===================================================================
> --- llvm/include/llvm/Support/FileSystem.h
> +++ llvm/include/llvm/Support/FileSystem.h
> @@ -391,6 +391,14 @@
>  ///          platform-specific error_code.
>  std::error_code resize_file(int FD, uint64_t Size);
>  
> +/// @brief Preallocate disk blocks to a given file.
> +///
> +/// @param FD Input file descriptor.
> +/// @param Size Size to resize to.
> +/// @returns errc::success if \a path has been resized to \a size, otherwise a
> +///          platform-specific error_code.
> +std::error_code allocate_file(int FD, uint64_t Size);
> +
>  /// @brief Compute an MD5 hash of a file's contents.
>  ///
>  /// @param FD Input file descriptor.
> Index: llvm/include/llvm/Config/config.h.cmake
> ===================================================================
> --- llvm/include/llvm/Config/config.h.cmake
> +++ llvm/include/llvm/Config/config.h.cmake
> @@ -59,6 +59,9 @@
>  /* Define to 1 if you have the <errno.h> header file. */
>  #cmakedefine HAVE_ERRNO_H ${HAVE_ERRNO_H}
>  
> +/* Define to 1 if you have the `fallocate' function. */
> +#cmakedefine HAVE_FALLOCATE ${HAVE_FALLOCATE}
> +
>  /* Define to 1 if you have the <fcntl.h> header file. */
>  #cmakedefine HAVE_FCNTL_H ${HAVE_FCNTL_H}
>  
> Index: llvm/cmake/config-ix.cmake
> ===================================================================
> --- llvm/cmake/config-ix.cmake
> +++ llvm/cmake/config-ix.cmake
> @@ -197,6 +197,11 @@
>  check_symbol_exists(futimens sys/stat.h HAVE_FUTIMENS)
>  check_symbol_exists(futimes sys/time.h HAVE_FUTIMES)
>  check_symbol_exists(posix_fallocate fcntl.h HAVE_POSIX_FALLOCATE)
> +
> +set(CMAKE_REQUIRED_DEFINITIONS "-D_GNU_SOURCE")
> +check_symbol_exists(fallocate fcntl.h HAVE_FALLOCATE)
> +set(CMAKE_REQUIRED_DEFINITIONS "")
> +
>  # AddressSanitizer conflicts with lib/Support/Unix/Signals.inc
>  # Avoid sigaltstack on Apple platforms, where backtrace() cannot handle it
>  # (rdar://7089625) and _Unwind_Backtrace is unusable because it cannot unwind