[llvm] r271953 - Retry^2 "[llvm-profdata] Add option to ingest filepaths from a file"
Vedant Kumar via llvm-commits
llvm-commits at lists.llvm.org
Mon Jun 6 16:17:25 PDT 2016
Author: vedantk
Date: Mon Jun 6 18:17:22 2016
New Revision: 271953
URL: http://llvm.org/viewvc/llvm-project?rev=271953&view=rev
Log:
Retry^2 "[llvm-profdata] Add option to ingest filepaths from a file"
Changes since the initial commit:
- Normalize file paths read from the file to prevent Windows path
separators from escaping parts of the path.
- Since we need to store the normalized file paths in WeightedFile,
don't do tricky things to keep the source MemoryBuffer alive.
- Don't use list-initialization for a std::string in WeightedFile.
Differential Revision: http://reviews.llvm.org/D20980
Added:
llvm/trunk/test/tools/llvm-profdata/input-filenames.test
Modified:
llvm/trunk/docs/CommandGuide/llvm-profdata.rst
llvm/trunk/tools/llvm-profdata/llvm-profdata.cpp
Modified: llvm/trunk/docs/CommandGuide/llvm-profdata.rst
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/docs/CommandGuide/llvm-profdata.rst?rev=271953&r1=271952&r2=271953&view=diff
==============================================================================
--- llvm/trunk/docs/CommandGuide/llvm-profdata.rst (original)
+++ llvm/trunk/docs/CommandGuide/llvm-profdata.rst Mon Jun 6 18:17:22 2016
@@ -44,6 +44,9 @@ interpreted as relatively more important
nature of the training runs it may be useful to adjust the weight given to each
input file by using the ``-weighted-input`` option.
+Profiles passed in via ``-weighted-input``, ``-input-files``, or via positional
+arguments are processed once for each time they are seen.
+
OPTIONS
^^^^^^^
@@ -65,6 +68,12 @@ OPTIONS
Input files specified without using this option are assigned a default
weight of 1. Examples are shown below.
+.. option:: -input-files=path, -f=path
+
+ Specify a file which contains a list of files to merge. The entries in this
+ file are newline-separated. Lines starting with '#' are skipped. Entries may
+ be of the form <filename> or <weight>,<filename>.
+
.. option:: -instr (default)
Specify that the input profile is an instrumentation-based profile.
Added: llvm/trunk/test/tools/llvm-profdata/input-filenames.test
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/tools/llvm-profdata/input-filenames.test?rev=271953&view=auto
==============================================================================
--- llvm/trunk/test/tools/llvm-profdata/input-filenames.test (added)
+++ llvm/trunk/test/tools/llvm-profdata/input-filenames.test Mon Jun 6 18:17:22 2016
@@ -0,0 +1,16 @@
+RUN: printf '# comment 1\n' > %t
+RUN: printf ' # comment 2\n' >> %t
+
+RUN: printf 'bar\n' >> %t
+RUN: printf ' baz\n' >> %t
+
+RUN: printf '2,%t.weighted\n' >> %t
+RUN: printf ' ' > %t.weighted
+
+RUN: llvm-profdata merge -input-files %t -dump-input-file-list foo -o /dev/null | FileCheck %s
+RUN: llvm-profdata merge -f %t -dump-input-file-list foo -o /dev/null | FileCheck %s
+
+CHECK: 1,foo
+CHECK-NEXT: 1,bar
+CHECK-NEXT: 1,baz
+CHECK-NEXT: 2,{{.*}}.weighted
Modified: llvm/trunk/tools/llvm-profdata/llvm-profdata.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/tools/llvm-profdata/llvm-profdata.cpp?rev=271953&r1=271952&r2=271953&view=diff
==============================================================================
--- llvm/trunk/tools/llvm-profdata/llvm-profdata.cpp (original)
+++ llvm/trunk/tools/llvm-profdata/llvm-profdata.cpp Mon Jun 6 18:17:22 2016
@@ -108,12 +108,12 @@ static void handleMergeWriterError(Error
}
struct WeightedFile {
- StringRef Filename;
+ std::string Filename;
uint64_t Weight;
WeightedFile() {}
- WeightedFile(StringRef F, uint64_t W) : Filename{F}, Weight{W} {}
+ WeightedFile(std::string F, uint64_t W) : Filename(F), Weight(W) {}
};
typedef SmallVector<WeightedFile, 5> WeightedFileVector;
@@ -208,19 +208,53 @@ static void mergeSampleProfile(const Wei
Writer->write(ProfileMap);
}
+static std::string canonicalizeFilePath(StringRef Filename) {
+ SmallString<256> CanonicalFilename;
+ sys::path::native(Filename, CanonicalFilename);
+ return StringRef(CanonicalFilename).str();
+}
+
static WeightedFile parseWeightedFile(const StringRef &WeightedFilename) {
- StringRef WeightStr, FileName;
- std::tie(WeightStr, FileName) = WeightedFilename.split(',');
+ StringRef WeightStr, FilenameStr;
+ std::tie(WeightStr, FilenameStr) = WeightedFilename.split(',');
uint64_t Weight;
if (WeightStr.getAsInteger(10, Weight) || Weight < 1)
exitWithError("Input weight must be a positive integer.");
- if (!sys::fs::exists(FileName))
+ std::string CanonicalFilename = canonicalizeFilePath(FilenameStr);
+
+ if (!sys::fs::exists(CanonicalFilename))
exitWithErrorCode(make_error_code(errc::no_such_file_or_directory),
- FileName);
+ CanonicalFilename);
- return WeightedFile(FileName, Weight);
+ return WeightedFile(StringRef(CanonicalFilename).str(), Weight);
+}
+
+static void parseInputFilenamesFile(const StringRef &InputFilenamesFile,
+ WeightedFileVector &WFV) {
+ if (InputFilenamesFile == "")
+ return;
+
+ auto BufOrError = MemoryBuffer::getFileOrSTDIN(InputFilenamesFile);
+ if (!BufOrError)
+ exitWithErrorCode(BufOrError.getError(), InputFilenamesFile);
+
+ auto Buffer = std::move(*BufOrError);
+ StringRef Data = Buffer->getBuffer();
+ SmallVector<StringRef, 8> Entries;
+ Data.split(Entries, '\n', /*MaxSplit=*/-1, /*KeepEmpty=*/false);
+ for (const StringRef &FileWeightEntry : Entries) {
+ StringRef SanitizedEntry = FileWeightEntry.trim(" \t\v\f\r");
+ // Skip comments.
+ if (SanitizedEntry.startswith("#"))
+ continue;
+ // If there's no comma, it's an unweighted profile.
+ else if (SanitizedEntry.find(',') == StringRef::npos)
+ WFV.emplace_back(canonicalizeFilePath(SanitizedEntry), 1);
+ else
+ WFV.emplace_back(parseWeightedFile(SanitizedEntry));
+ }
}
static int merge_main(int argc, const char *argv[]) {
@@ -228,6 +262,15 @@ static int merge_main(int argc, const ch
cl::desc("<filename...>"));
cl::list<std::string> WeightedInputFilenames("weighted-input",
cl::desc("<weight>,<filename>"));
+ cl::opt<std::string> InputFilenamesFile(
+ "input-files", cl::init(""),
+ cl::desc("Path to file containing newline-separated "
+ "[<weight>,]<filename> entries"));
+ cl::alias InputFilenamesFileA("f", cl::desc("Alias for --input-files"),
+ cl::aliasopt(InputFilenamesFile));
+ cl::opt<bool> DumpInputFileList(
+ "dump-input-file-list", cl::init(false), cl::Hidden,
+ cl::desc("Dump the list of input files and their weights, then exit"));
cl::opt<std::string> OutputFilename("output", cl::value_desc("output"),
cl::init("-"), cl::Required,
cl::desc("Output file"));
@@ -249,15 +292,22 @@ static int merge_main(int argc, const ch
cl::ParseCommandLineOptions(argc, argv, "LLVM profile data merger\n");
- if (InputFilenames.empty() && WeightedInputFilenames.empty())
- exitWithError("No input files specified. See " +
- sys::path::filename(argv[0]) + " -help");
-
WeightedFileVector WeightedInputs;
for (StringRef Filename : InputFilenames)
- WeightedInputs.push_back(WeightedFile(Filename, 1));
+ WeightedInputs.emplace_back(canonicalizeFilePath(Filename), 1);
for (StringRef WeightedFilename : WeightedInputFilenames)
- WeightedInputs.push_back(parseWeightedFile(WeightedFilename));
+ WeightedInputs.emplace_back(parseWeightedFile(WeightedFilename));
+ parseInputFilenamesFile(InputFilenamesFile, WeightedInputs);
+
+ if (WeightedInputs.empty())
+ exitWithError("No input files specified. See " +
+ sys::path::filename(argv[0]) + " -help");
+
+ if (DumpInputFileList) {
+ for (auto &WF : WeightedInputs)
+ outs() << WF.Weight << "," << WF.Filename << "\n";
+ return 0;
+ }
if (ProfileKind == instr)
mergeInstrProfile(WeightedInputs, OutputFilename, OutputFormat,
More information about the llvm-commits
mailing list