1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-20 11:33:24 +02:00
llvm-mirror/lib/Support/FileOutputBuffer.cpp
Nick Terrell ac02e6927c [LLD][ELF] Support --[no-]mmap-output-file with F_no_mmap
Summary:
Add a flag `F_no_mmap` to `FileOutputBuffer` to support
`--[no-]mmap-output-file` in ELF LLD. LLD currently explicitly ignores
this flag for compatibility with GNU ld and gold.

We need this flag to speed up link time for large binaries in certain
scenarios. When we link some of our larger binaries we find that LLD
takes 50+ GB of memory, which causes memory pressure. The memory
pressure causes the VM to flush dirty pages of the output file to disk.
This is normally okay, since we should be flushing cold pages. However,
when using BtrFS with compression we need to write 128KB at a time when
we flush a page. If any page in that 128KB block is written again, then
it must be flushed a second time, and so on. Since LLD doesn't write
sequentially this causes write amplification. The same 128KB block will
end up being flushed multiple times, causing the linker to many times
more IO than necessary. We've observed 3-5x faster builds with
-no-mmap-output-file when we hit this scenario.

The bad scenario only applies to compressed filesystems, which group
together multiple pages into a single compressed block. I've tested
BtrFS, but the problem will be present for any compressed filesystem
on Linux, since it is caused by the VM.

Silently ignoring --no-mmap-output-file caused a silent regression when
we switched from gold to lld. We pass --no-mmap-output-file to fix this
edge case, but since lld silently ignored the flag we didn't realize it
wasn't being respected.

Benchmark building a 9 GB binary that exposes this edge case. I linked 3
times with --mmap-output-file and 3 times with --no-mmap-output-file and
took the average. The machine has 24 cores @ 2.4 GHz, 112 GB of RAM,
BtrFS mounted with -compress-force=zstd, and an 80% full disk.

| Mode    | Time  |
|---------|-------|
| mmap    | 894 s |
| no mmap | 126 s |

When compression is disabled, BtrFS performs just as well with and
without mmap on this benchmark.

I was unable to reproduce the regression with any binaries in
lld-speed-test.

Reviewed By: ruiu, MaskRay

Differential Revision: https://reviews.llvm.org/D69294
2019-10-29 15:49:08 -07:00

200 lines
6.5 KiB
C++

//===- FileOutputBuffer.cpp - File Output Buffer ----------------*- C++ -*-===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
// Utility for creating a in-memory buffer that will be written to a file.
//
//===----------------------------------------------------------------------===//
#include "llvm/Support/FileOutputBuffer.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/ADT/SmallString.h"
#include "llvm/Support/Errc.h"
#include "llvm/Support/Memory.h"
#include "llvm/Support/Path.h"
#include <system_error>
#if !defined(_MSC_VER) && !defined(__MINGW32__)
#include <unistd.h>
#else
#include <io.h>
#endif
using namespace llvm;
using namespace llvm::sys;
namespace {
// A FileOutputBuffer which creates a temporary file in the same directory
// as the final output file. The final output file is atomically replaced
// with the temporary file on commit().
class OnDiskBuffer : public FileOutputBuffer {
public:
OnDiskBuffer(StringRef Path, fs::TempFile Temp,
std::unique_ptr<fs::mapped_file_region> Buf)
: FileOutputBuffer(Path), Buffer(std::move(Buf)), Temp(std::move(Temp)) {}
uint8_t *getBufferStart() const override { return (uint8_t *)Buffer->data(); }
uint8_t *getBufferEnd() const override {
return (uint8_t *)Buffer->data() + Buffer->size();
}
size_t getBufferSize() const override { return Buffer->size(); }
Error commit() override {
// Unmap buffer, letting OS flush dirty pages to file on disk.
Buffer.reset();
// Atomically replace the existing file with the new one.
return Temp.keep(FinalPath);
}
~OnDiskBuffer() override {
// Close the mapping before deleting the temp file, so that the removal
// succeeds.
Buffer.reset();
consumeError(Temp.discard());
}
void discard() override {
// Delete the temp file if it still was open, but keeping the mapping
// active.
consumeError(Temp.discard());
}
private:
std::unique_ptr<fs::mapped_file_region> Buffer;
fs::TempFile Temp;
};
// A FileOutputBuffer which keeps data in memory and writes to the final
// output file on commit(). This is used only when we cannot use OnDiskBuffer.
class InMemoryBuffer : public FileOutputBuffer {
public:
InMemoryBuffer(StringRef Path, MemoryBlock Buf, std::size_t BufSize,
unsigned Mode)
: FileOutputBuffer(Path), Buffer(Buf), BufferSize(BufSize),
Mode(Mode) {}
uint8_t *getBufferStart() const override { return (uint8_t *)Buffer.base(); }
uint8_t *getBufferEnd() const override {
return (uint8_t *)Buffer.base() + BufferSize;
}
size_t getBufferSize() const override { return BufferSize; }
Error commit() override {
if (FinalPath == "-") {
llvm::outs() << StringRef((const char *)Buffer.base(), BufferSize);
llvm::outs().flush();
return Error::success();
}
using namespace sys::fs;
int FD;
std::error_code EC;
if (auto EC =
openFileForWrite(FinalPath, FD, CD_CreateAlways, OF_None, Mode))
return errorCodeToError(EC);
raw_fd_ostream OS(FD, /*shouldClose=*/true, /*unbuffered=*/true);
OS << StringRef((const char *)Buffer.base(), BufferSize);
return Error::success();
}
private:
// Buffer may actually contain a larger memory block than BufferSize
OwningMemoryBlock Buffer;
size_t BufferSize;
unsigned Mode;
};
} // namespace
static Expected<std::unique_ptr<InMemoryBuffer>>
createInMemoryBuffer(StringRef Path, size_t Size, unsigned Mode) {
std::error_code EC;
MemoryBlock MB = Memory::allocateMappedMemory(
Size, nullptr, sys::Memory::MF_READ | sys::Memory::MF_WRITE, EC);
if (EC)
return errorCodeToError(EC);
return std::make_unique<InMemoryBuffer>(Path, MB, Size, Mode);
}
static Expected<std::unique_ptr<FileOutputBuffer>>
createOnDiskBuffer(StringRef Path, size_t Size, unsigned Mode) {
Expected<fs::TempFile> FileOrErr =
fs::TempFile::create(Path + ".tmp%%%%%%%", Mode);
if (!FileOrErr)
return FileOrErr.takeError();
fs::TempFile File = std::move(*FileOrErr);
#ifndef _WIN32
// On Windows, CreateFileMapping (the mmap function on Windows)
// automatically extends the underlying file. We don't need to
// extend the file beforehand. _chsize (ftruncate on Windows) is
// pretty slow just like it writes specified amount of bytes,
// so we should avoid calling that function.
if (auto EC = fs::resize_file(File.FD, Size)) {
consumeError(File.discard());
return errorCodeToError(EC);
}
#endif
// Mmap it.
std::error_code EC;
auto MappedFile = std::make_unique<fs::mapped_file_region>(
fs::convertFDToNativeFile(File.FD), fs::mapped_file_region::readwrite,
Size, 0, EC);
// mmap(2) can fail if the underlying filesystem does not support it.
// If that happens, we fall back to in-memory buffer as the last resort.
if (EC) {
consumeError(File.discard());
return createInMemoryBuffer(Path, Size, Mode);
}
return std::make_unique<OnDiskBuffer>(Path, std::move(File),
std::move(MappedFile));
}
// Create an instance of FileOutputBuffer.
Expected<std::unique_ptr<FileOutputBuffer>>
FileOutputBuffer::create(StringRef Path, size_t Size, unsigned Flags) {
// Handle "-" as stdout just like llvm::raw_ostream does.
if (Path == "-")
return createInMemoryBuffer("-", Size, /*Mode=*/0);
unsigned Mode = fs::all_read | fs::all_write;
if (Flags & F_executable)
Mode |= fs::all_exe;
fs::file_status Stat;
fs::status(Path, Stat);
// Usually, we want to create OnDiskBuffer to create a temporary file in
// the same directory as the destination file and atomically replaces it
// by rename(2).
//
// However, if the destination file is a special file, we don't want to
// use rename (e.g. we don't want to replace /dev/null with a regular
// file.) If that's the case, we create an in-memory buffer, open the
// destination file and write to it on commit().
switch (Stat.type()) {
case fs::file_type::directory_file:
return errorCodeToError(errc::is_a_directory);
case fs::file_type::regular_file:
case fs::file_type::file_not_found:
case fs::file_type::status_error:
if (Flags & F_no_mmap)
return createInMemoryBuffer(Path, Size, Mode);
else
return createOnDiskBuffer(Path, Size, Mode);
default:
return createInMemoryBuffer(Path, Size, Mode);
}
}