Recommit [SampleFDO] Expose an interface to return the size of a section

or the size of the profile for profile in ExtBinary format.

Fix a test failure on Mac.

[SampleFDO] Expose an interface to return the size of a section or the
size of the profile for profile in ExtBinary format.

Sometimes we want to limit the size of the profile by stripping some functions
with low sample count or by stripping some function names with small text size
from profile symbol list. That requires the profile reader to have the
interfaces returning the size of a section or the size of total profile. The
patch add those interfaces.

At the same time, add some dump facility to show the size of each section.

Differential revision: https://reviews.llvm.org/D67726

llvm-svn: 372478

Author: wmi-11

llvm/include/llvm/ProfileData/SampleProf.h

@@ -125,6 +125,22 @@ enum SecType {
   SecLBRProfile = SecFuncProfileFirst
 };
 
+static inline std::string getSecName(SecType Type) {
+  switch (Type) {
+  case SecInValid:
+    return "InvalidSection";
+  case SecProfSummary:
+    return "ProfileSummarySection";
+  case SecNameTable:
+    return "NameTableSection";
+  case SecProfileSymbolList:
+    return "ProfileSymbolListSection";
+  case SecLBRProfile:
+    return "LBRProfileSection";
+  }
+  llvm_unreachable("A SecType has no name for output");
+}
+
 // Entry type of section header table used by SampleProfileExtBinaryBaseReader
 // and SampleProfileExtBinaryBaseWriter.
 struct SecHdrTableEntry {

llvm/include/llvm/ProfileData/SampleProfReader.h

@@ -333,6 +333,7 @@ class SampleProfileReader {
   /// It includes all the names that have samples either in outline instance
   /// or inline instance.
   virtual std::vector<StringRef> *getNameTable() { return nullptr; }
+  virtual bool dumpSectionInfo(raw_ostream &OS = dbgs()) { return false; };
 
 protected:
   /// Map every function to its associated profile.
@@ -504,6 +505,12 @@ class SampleProfileReaderExtBinaryBase : public SampleProfileReaderBinary {
 
   /// Read sample profiles in extensible format from the associated file.
   std::error_code read() override;
+
+  /// Get the total size of all \p Type sections.
+  uint64_t getSectionSize(SecType Type);
+  /// Get the total size of header and all sections.
+  uint64_t getFileSize();
+  virtual bool dumpSectionInfo(raw_ostream &OS = dbgs()) override;
 };
 
 class SampleProfileReaderExtBinary : public SampleProfileReaderExtBinaryBase {

llvm/lib/ProfileData/SampleProfReader.cpp

@@ -667,6 +667,36 @@ std::error_code SampleProfileReaderExtBinaryBase::readHeader() {
   return sampleprof_error::success;
 }
 
+uint64_t SampleProfileReaderExtBinaryBase::getSectionSize(SecType Type) {
+  for (auto &Entry : SecHdrTable) {
+    if (Entry.Type == Type)
+      return Entry.Size;
+  }
+  return 0;
+}
+
+uint64_t SampleProfileReaderExtBinaryBase::getFileSize() {
+  auto &LastEntry = SecHdrTable.back();
+  return LastEntry.Offset + LastEntry.Size;
+}
+
+bool SampleProfileReaderExtBinaryBase::dumpSectionInfo(raw_ostream &OS) {
+  uint64_t TotalSecsSize = 0;
+  for (auto &Entry : SecHdrTable) {
+    OS << getSecName(Entry.Type) << " - Offset: " << Entry.Offset
+       << ", Size: " << Entry.Size << "\n";
+    TotalSecsSize += getSectionSize(Entry.Type);
+  }
+  uint64_t HeaderSize = SecHdrTable.front().Offset;
+  assert(HeaderSize + TotalSecsSize == getFileSize() &&
+         "Size of 'header + sections' doesn't match the total size of profile");
+
+  OS << "Header Size: " << HeaderSize << "\n";
+  OS << "Total Sections Size: " << TotalSecsSize << "\n";
+  OS << "File Size: " << getFileSize() << "\n";
+  return true;
+}
+
 std::error_code SampleProfileReaderBinary::readMagicIdent() {
   // Read and check the magic identifier.
   auto Magic = readNumber<uint64_t>();

llvm/test/tools/llvm-profdata/show-prof-size.test

@@ -0,0 +1,7 @@
+; RUN: llvm-profdata merge -sample -extbinary -prof-sym-list=%S/Inputs/profile-symbol-list-1.text %S/Inputs/sample-profile.proftext -o %t.1.output
+; RUN: ls -l %t.1.output |tr -s ' ' |cut -f5 -d ' ' > %t.txt
+; RUN: llvm-profdata show -sample -show-sec-info-only %t.1.output >> %t.txt
+; RUN: FileCheck %s --input-file=%t.txt
+; Check llvm-profdata shows the correct file size.
+; CHECK: [[FILESIZE:.*]]
+; CHECK: [[FILESIZE]]

llvm/tools/llvm-profdata/llvm-profdata.cpp

@@ -982,17 +982,34 @@ static int showInstrProfile(const std::string &Filename, bool ShowCounts,
   return 0;
 }
 
+static void showSectionInfo(sampleprof::SampleProfileReader *Reader,
+                            raw_fd_ostream &OS) {
+  if (!Reader->dumpSectionInfo(OS)) {
+    WithColor::warning() << "-show-sec-info-only is only supported for "
+                         << "sample profile in extbinary format and is "
+                         << "ignored for other formats.\n";
+    return;
+  }
+}
+
 static int showSampleProfile(const std::string &Filename, bool ShowCounts,
                              bool ShowAllFunctions,
                              const std::string &ShowFunction,
-                             bool ShowProfileSymbolList, raw_fd_ostream &OS) {
+                             bool ShowProfileSymbolList,
+                             bool ShowSectionInfoOnly, raw_fd_ostream &OS) {
   using namespace sampleprof;
   LLVMContext Context;
   auto ReaderOrErr = SampleProfileReader::create(Filename, Context);
   if (std::error_code EC = ReaderOrErr.getError())
     exitWithErrorCode(EC, Filename);
 
   auto Reader = std::move(ReaderOrErr.get());
+
+  if (ShowSectionInfoOnly) {
+    showSectionInfo(Reader.get(), OS);
+    return 0;
+  }
+
   if (std::error_code EC = Reader->read())
     exitWithErrorCode(EC, Filename);
 
@@ -1062,6 +1079,11 @@ static int show_main(int argc, const char *argv[]) {
   cl::opt<bool> ShowProfileSymbolList(
       "show-prof-sym-list", cl::init(false),
       cl::desc("Show profile symbol list if it exists in the profile. "));
+  cl::opt<bool> ShowSectionInfoOnly(
+      "show-sec-info-only", cl::init(false),
+      cl::desc("Show the information of each section in the sample profile. "
+               "The flag is only usable when the sample profile is in "
+               "extbinary format"));
 
   cl::ParseCommandLineOptions(argc, argv, "LLVM profile data summary\n");
 
@@ -1090,7 +1112,8 @@ static int show_main(int argc, const char *argv[]) {
                             OnlyListBelow, ShowFunction, TextFormat, OS);
   else
     return showSampleProfile(Filename, ShowCounts, ShowAllFunctions,
-                             ShowFunction, ShowProfileSymbolList, OS);
+                             ShowFunction, ShowProfileSymbolList,
+                             ShowSectionInfoOnly, OS);
 }
 
 int main(int argc, const char *argv[]) {