Flush bitcode incrementally for LTO output

Bitcode writer does not flush buffer until the end by default. This is
fine to small bitcode files. When -flto,--plugin-opt=emit-llvm,-gmlt are
used, the final bitcode file is large, for example, >8G. Keeping all
data in memory consumes a lot of memory.

This change allows bitcode writer flush data to disk early when buffered
data size is above some threshold. This is only enabled when lld emits
LLVM bitcode.

One issue to address is backpatching bitcode: subblock length, function
body indexes, meta data indexes need to backfill. If buffer can be
flushed partially, we introduced raw_fd_stream that supports
read/seek/write, and enables backpatching bitcode flushed in disk.

Reviewed-by: tejohnson, MaskRay

Differential Revision: https://reviews.llvm.org/D86905

1 files changed, 8 insertions, 4 deletions

diff --git a/llvm/lib/Bitcode/Writer/BitcodeWriter.cpp b/llvm/lib/Bitcode/Writer/BitcodeWriter.cpp
index 28384bcb354f..26874c9ac364 100644
--- a/llvm/lib/Bitcode/Writer/BitcodeWriter.cpp
+++ b/llvm/lib/Bitcode/Writer/BitcodeWriter.cpp
@@ -86,6 +86,9 @@ static cl::opt<unsigned>
     IndexThreshold("bitcode-mdindex-threshold", cl::Hidden, cl::init(25),
                    cl::desc("Number of metadatas above which we emit an index "
                             "to enable lazy-loading"));
+static cl::opt<uint32_t> FlushThreshold(
+    "bitcode-flush-threshold", cl::Hidden, cl::init(512),
+    cl::desc("The threshold (unit M) for flushing LLVM bitcode."));
 
 static cl::opt<bool> WriteRelBFToSummary(
     "write-relbf-to-summary", cl::Hidden, cl::init(false),
@@ -4453,8 +4456,8 @@ static void writeBitcodeHeader(BitstreamWriter &Stream) {
   Stream.Emit(0xD, 4);
 }
 
-BitcodeWriter::BitcodeWriter(SmallVectorImpl<char> &Buffer)
-    : Buffer(Buffer), Stream(new BitstreamWriter(Buffer)) {
+BitcodeWriter::BitcodeWriter(SmallVectorImpl<char> &Buffer, raw_fd_stream *FS)
+    : Buffer(Buffer), Stream(new BitstreamWriter(Buffer, FS, FlushThreshold)) {
   writeBitcodeHeader(*Stream);
 }
 
@@ -4565,7 +4568,7 @@ void llvm::WriteBitcodeToFile(const Module &M, raw_ostream &Out,
   if (TT.isOSDarwin() || TT.isOSBinFormatMachO())
     Buffer.insert(Buffer.begin(), BWH_HeaderSize, 0);
 
-  BitcodeWriter Writer(Buffer);
+  BitcodeWriter Writer(Buffer, dyn_cast<raw_fd_stream>(&Out));
   Writer.writeModule(M, ShouldPreserveUseListOrder, Index, GenerateHash,
                      ModHash);
   Writer.writeSymtab();
@@ -4575,7 +4578,8 @@ void llvm::WriteBitcodeToFile(const Module &M, raw_ostream &Out,
     emitDarwinBCHeaderAndTrailer(Buffer, TT);
 
   // Write the generated bitstream to "Out".
-  Out.write((char*)&Buffer.front(), Buffer.size());
+  if (!Buffer.empty())
+    Out.write((char *)&Buffer.front(), Buffer.size());
 }
 
 void IndexBitcodeWriter::write() {