kbobyrev updated this revision to Diff 166266.
kbobyrev retitled this revision from "[clangd] Add a "benchmark" for tracking
memory" to "[clangd] Add building benchmark and memory consumption tracking".
kbobyrev edited the summary of this revision.
kbobyrev added a comment.
Add symbol index building benchmarks, split `loadIndex()` into
`symbolsFromFile()` and actual index build.
https://reviews.llvm.org/D52047
Files:
clang-tools-extra/clangd/benchmarks/IndexBenchmark.cpp
clang-tools-extra/clangd/index/SymbolYAML.cpp
clang-tools-extra/clangd/index/SymbolYAML.h
clang-tools-extra/clangd/index/dex/Dex.cpp
Index: clang-tools-extra/clangd/index/dex/Dex.cpp
===================================================================
--- clang-tools-extra/clangd/index/dex/Dex.cpp
+++ clang-tools-extra/clangd/index/dex/Dex.cpp
@@ -124,9 +124,6 @@
for (const auto &TokenToPostingList : TempInvertedIndex)
InvertedIndex.insert({TokenToPostingList.first,
PostingList(move(TokenToPostingList.second))});
-
- vlog("Built Dex with estimated memory usage {0} bytes.",
- estimateMemoryUsage());
}
/// Constructs iterators over tokens extracted from the query and exhausts it
@@ -239,7 +236,7 @@
Bytes += LookupTable.getMemorySize();
Bytes += InvertedIndex.getMemorySize();
for (const auto &P : InvertedIndex)
- Bytes += P.second.bytes();
+ Bytes += P.first.Data.size() + P.second.bytes();
return Bytes + BackingDataSize;
}
Index: clang-tools-extra/clangd/index/SymbolYAML.h
===================================================================
--- clang-tools-extra/clangd/index/SymbolYAML.h
+++ clang-tools-extra/clangd/index/SymbolYAML.h
@@ -29,6 +29,9 @@
// Read symbols from a YAML-format string.
SymbolSlab symbolsFromYAML(llvm::StringRef YAMLContent);
+// Read symbols from YAML or RIFF file.
+llvm::Optional<SymbolSlab> symbolsFromFile(llvm::StringRef SymbolFilename);
+
// Read one symbol from a YAML-stream.
// The returned symbol is backed by Input.
Symbol SymbolFromYAML(llvm::yaml::Input &Input);
Index: clang-tools-extra/clangd/index/SymbolYAML.cpp
===================================================================
--- clang-tools-extra/clangd/index/SymbolYAML.cpp
+++ clang-tools-extra/clangd/index/SymbolYAML.cpp
@@ -9,6 +9,7 @@
#include "SymbolYAML.h"
#include "Index.h"
+#include "Logger.h"
#include "Serialization.h"
#include "Trace.h"
#include "dex/Dex.h"
@@ -182,6 +183,28 @@
return std::move(Syms).build();
}
+llvm::Optional<SymbolSlab> symbolsFromFile(llvm::StringRef SymbolFilename) {
+ auto Buffer = llvm::MemoryBuffer::getFile(SymbolFilename);
+ if (!Buffer) {
+ llvm::errs() << "Can't open " << SymbolFilename << "\n";
+ return llvm::None;
+ }
+ StringRef Data = Buffer->get()->getBuffer();
+
+ llvm::Optional<SymbolSlab> Slab;
+ if (Data.startswith("RIFF")) { // Magic for binary index file.
+ trace::Span Tracer("ParseRIFF");
+ if (auto RIFF = readIndexFile(Data))
+ Slab = std::move(RIFF->Symbols);
+ else
+ llvm::errs() << "Bad RIFF: " << llvm::toString(RIFF.takeError()) << "\n";
+ } else {
+ trace::Span Tracer("ParseYAML");
+ Slab = symbolsFromYAML(Data);
+ }
+ return Slab;
+}
+
Symbol SymbolFromYAML(llvm::yaml::Input &Input) {
Symbol S;
Input >> S;
@@ -206,30 +229,16 @@
llvm::ArrayRef<std::string> URISchemes,
bool UseDex) {
trace::Span OverallTracer("LoadIndex");
- auto Buffer = llvm::MemoryBuffer::getFile(SymbolFilename);
- if (!Buffer) {
- llvm::errs() << "Can't open " << SymbolFilename << "\n";
- return nullptr;
- }
- StringRef Data = Buffer->get()->getBuffer();
-
- llvm::Optional<SymbolSlab> Slab;
- if (Data.startswith("RIFF")) { // Magic for binary index file.
- trace::Span Tracer("ParseRIFF");
- if (auto RIFF = readIndexFile(Data))
- Slab = std::move(RIFF->Symbols);
- else
- llvm::errs() << "Bad RIFF: " << llvm::toString(RIFF.takeError()) << "\n";
- } else {
- trace::Span Tracer("ParseYAML");
- Slab = symbolsFromYAML(Data);
- }
-
+ auto Slab = symbolsFromFile(SymbolFilename);
if (!Slab)
return nullptr;
trace::Span Tracer("BuildIndex");
- return UseDex ? dex::Dex::build(std::move(*Slab), URISchemes)
- : MemIndex::build(std::move(*Slab), RefSlab());
+ auto Index = UseDex ? dex::Dex::build(std::move(*Slab), URISchemes)
+ : MemIndex::build(std::move(*Slab), RefSlab());
+ vlog("Loaded {0} from {1} with estimated memory usage {2}",
+ UseDex ? "Dex" : "MemIndex", SymbolFilename,
+ Index->estimateMemoryUsage());
+ return Index;
}
} // namespace clangd
Index: clang-tools-extra/clangd/benchmarks/IndexBenchmark.cpp
===================================================================
--- clang-tools-extra/clangd/benchmarks/IndexBenchmark.cpp
+++ clang-tools-extra/clangd/benchmarks/IndexBenchmark.cpp
@@ -33,6 +33,16 @@
return loadIndex(IndexFilename, {}, true);
}
+SymbolSlab loadSlab() {
+ auto Slab = symbolsFromFile(IndexFilename);
+ if (!Slab) {
+ llvm::errs() << "Error when loading SymbolSlab from file: " << IndexFilename
+ << '\n';
+ exit(1);
+ }
+ return std::move(*Slab);
+}
+
// Reads JSON array of serialized FuzzyFindRequest's from user-provided file.
std::vector<FuzzyFindRequest> extractQueriesFromLogs() {
std::ifstream InputStream(RequestsFilename);
@@ -66,31 +76,65 @@
return Requests;
}
+// This is not a *real* benchmark: it shows size of built MemIndex (in bytes).
+// Same for the next "benchmark".
+// FIXME(kbobyrev): Should this be separated into the BackingMemorySize
+// (underlying SymbolSlab size) and Symbol Index (MemIndex/Dex) overhead?
+static void MemSize(benchmark::State &State) {
+ const auto Mem = buildMem();
+ for (auto _ : State)
+ // Divide size of Mem by 1000 so that it will be correctly displayed in the
+ // benchmark report (possible options for time units are ms, ns and us).
+ State.SetIterationTime(/*double Seconds=*/Mem->estimateMemoryUsage() /
+ 1000);
+ State.counters["Memory Usage (bytes)"] = Mem->estimateMemoryUsage();
+}
+BENCHMARK(MemSize)->UseManualTime()->Unit(benchmark::kMillisecond);
+
+static void DexSize(benchmark::State &State) {
+ const auto Dex = buildDex();
+ for (auto _ : State)
+ State.SetIterationTime(Dex->estimateMemoryUsage() / 1000);
+ State.counters["Memory Usage (bytes)"] = Dex->estimateMemoryUsage();
+}
+BENCHMARK(DexSize)->UseManualTime()->Unit(benchmark::kMillisecond);
+
+static void MemBuild(benchmark::State &State) {
+ auto Slab = loadSlab();
+ for (auto _ : State)
+ benchmark::DoNotOptimize(MemIndex::build(std::move(Slab), RefSlab()));
+}
+BENCHMARK(MemBuild)->Unit(benchmark::kMillisecond);
+
+static void DexBuild(benchmark::State &State) {
+ auto Slab = loadSlab();
+ for (auto _ : State)
+ benchmark::DoNotOptimize(dex::Dex::build(std::move(Slab), {}));
+}
+BENCHMARK(DexBuild)->Unit(benchmark::kMillisecond);
+
static void MemQueries(benchmark::State &State) {
const auto Mem = buildMem();
const auto Requests = extractQueriesFromLogs();
for (auto _ : State)
for (const auto &Request : Requests)
Mem->fuzzyFind(Request, [](const Symbol &S) {});
}
-BENCHMARK(MemQueries);
+BENCHMARK(MemQueries)->Unit(benchmark::kMillisecond);
static void DexQueries(benchmark::State &State) {
const auto Dex = buildDex();
const auto Requests = extractQueriesFromLogs();
for (auto _ : State)
for (const auto &Request : Requests)
Dex->fuzzyFind(Request, [](const Symbol &S) {});
}
-BENCHMARK(DexQueries);
+BENCHMARK(DexQueries)->Unit(benchmark::kMillisecond);
} // namespace
} // namespace clangd
} // namespace clang
-// FIXME(kbobyrev): Add index building time benchmarks.
-// FIXME(kbobyrev): Add memory consumption "benchmarks" by manually measuring
-// in-memory index size and reporting it as time.
// FIXME(kbobyrev): Create a logger wrapper to suppress debugging info printer.
int main(int argc, char *argv[]) {
if (argc < 3) {
@@ -108,4 +152,5 @@
argc -= 2;
::benchmark::Initialize(&argc, argv);
::benchmark::RunSpecifiedBenchmarks();
+ return 0;
}
_______________________________________________
cfe-commits mailing list
[email protected]
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
