[pdb] Add -type-stats and sort stats by descending size

Summary:
It prints this on chromium browser_tests.exe.pdb:

  Types
           Total: 5647475 entries ( 371,897,512 bytes,   65.85 avg)
  --------------------------------------------------------------------------
        LF_CLASS:  397894 entries ( 119,537,780 bytes,  300.43 avg)
    LF_STRUCTURE:  236351 entries (  83,208,084 bytes,  352.05 avg)
    LF_FIELDLIST:  291003 entries (  66,087,920 bytes,  227.10 avg)
    LF_MFUNCTION: 1884176 entries (  52,756,928 bytes,   28.00 avg)
      LF_POINTER: 1149030 entries (  13,877,344 bytes,   12.08 avg)
      LF_ARGLIST:  789980 entries (  12,436,752 bytes,   15.74 avg)
   LF_METHODLIST:  361498 entries (   8,351,008 bytes,   23.10 avg)
         LF_ENUM:   16069 entries (   6,108,340 bytes,  380.13 avg)
    LF_PROCEDURE:  269374 entries (   4,309,984 bytes,   16.00 avg)
     LF_MODIFIER:  235602 entries (   2,827,224 bytes,   12.00 avg)
        LF_UNION:    9131 entries (   2,072,168 bytes,  226.94 avg)
      LF_VFTABLE:     323 entries (     207,784 bytes,  643.29 avg)
        LF_ARRAY:    6639 entries (     106,380 bytes,   16.02 avg)
      LF_VTSHAPE:     126 entries (       6,472 bytes,   51.37 avg)
     LF_BITFIELD:     278 entries (       3,336 bytes,   12.00 avg)
        LF_LABEL:       1 entries (           8 bytes,    8.00 avg)

The PDB is overall 1.9GB, so the LF_CLASS and LF_STRUCTURE declarations
account for about 10% of the overall file size. I was surprised to find
that on average LF_FIELDLIST records are short. Maybe this is because
there are many more types with short member lists than there are
instantiations with lots of members, like std::vector.

Reviewers: aganea, zturner

Subscribers: llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D59672

llvm-svn: 356813
This commit is contained in:
Reid Kleckner 2019-03-22 21:22:13 +00:00
parent b7ebab3006
commit 1eb494baab
7 changed files with 120 additions and 34 deletions

View File

@ -6,28 +6,28 @@ ALL-NEXT: Stream 12, 308 bytes
ALL: Symbols
ALL-NEXT: Total: 6 entries ( 204 bytes)
ALL-NEXT: --------------------------------------------------------------------------
ALL-NEXT: S_COMPILE3: 1 entries ( 60 bytes)
ALL-NEXT: S_OBJNAME: 1 entries ( 56 bytes)
ALL-NEXT: S_GPROC32: 1 entries ( 44 bytes)
ALL-NEXT: S_FRAMEPROC: 1 entries ( 32 bytes)
ALL-NEXT: S_END: 1 entries ( 4 bytes)
ALL-NEXT: S_OBJNAME: 1 entries ( 56 bytes)
ALL-NEXT: S_COMPILE3: 1 entries ( 60 bytes)
ALL-NEXT: S_BUILDINFO: 1 entries ( 8 bytes)
ALL-NEXT: S_END: 1 entries ( 4 bytes)
ALL: Chunks
ALL-NEXT: Total: 2 entries ( 88 bytes)
ALL-NEXT: --------------------------------------------------------------------------
ALL-NEXT: DEBUG_S_FILECHKSMS: 1 entries ( 32 bytes)
ALL-NEXT: DEBUG_S_LINES: 1 entries ( 56 bytes)
ALL-NEXT: DEBUG_S_FILECHKSMS: 1 entries ( 32 bytes)
ALL-NEXT: Mod 0001 | `* Linker *`:
ALL-NEXT: Stream 14, 520 bytes
ALL: Symbols
ALL-NEXT: Total: 13 entries ( 512 bytes)
ALL-NEXT: --------------------------------------------------------------------------
ALL-NEXT: S_SECTION: 4 entries ( 112 bytes)
ALL-NEXT: S_ENVBLOCK: 1 entries ( 172 bytes)
ALL-NEXT: S_COFFGROUP: 5 entries ( 140 bytes)
ALL-NEXT: S_SECTION: 4 entries ( 112 bytes)
ALL-NEXT: S_COMPILE3: 1 entries ( 48 bytes)
ALL-NEXT: S_TRAMPOLINE: 1 entries ( 20 bytes)
ALL-NEXT: S_OBJNAME: 1 entries ( 20 bytes)
ALL-NEXT: S_COMPILE3: 1 entries ( 48 bytes)
ALL-NEXT: S_COFFGROUP: 5 entries ( 140 bytes)
ALL: Chunks
ALL-NEXT: Total: 0 entries ( 0 bytes)
ALL-NEXT: --------------------------------------------------------------------------
@ -35,21 +35,21 @@ ALL-NEXT: Summary |
ALL: Symbols
ALL-NEXT: Total: 19 entries ( 716 bytes)
ALL-NEXT: --------------------------------------------------------------------------
ALL-NEXT: S_SECTION: 4 entries ( 112 bytes)
ALL-NEXT: S_GPROC32: 1 entries ( 44 bytes)
ALL-NEXT: S_ENVBLOCK: 1 entries ( 172 bytes)
ALL-NEXT: S_COFFGROUP: 5 entries ( 140 bytes)
ALL-NEXT: S_SECTION: 4 entries ( 112 bytes)
ALL-NEXT: S_COMPILE3: 2 entries ( 108 bytes)
ALL-NEXT: S_OBJNAME: 2 entries ( 76 bytes)
ALL-NEXT: S_GPROC32: 1 entries ( 44 bytes)
ALL-NEXT: S_FRAMEPROC: 1 entries ( 32 bytes)
ALL-NEXT: S_TRAMPOLINE: 1 entries ( 20 bytes)
ALL-NEXT: S_END: 1 entries ( 4 bytes)
ALL-NEXT: S_OBJNAME: 2 entries ( 76 bytes)
ALL-NEXT: S_COMPILE3: 2 entries ( 108 bytes)
ALL-NEXT: S_COFFGROUP: 5 entries ( 140 bytes)
ALL-NEXT: S_BUILDINFO: 1 entries ( 8 bytes)
ALL-NEXT: S_END: 1 entries ( 4 bytes)
ALL: Chunks
ALL-NEXT: Total: 2 entries ( 88 bytes)
ALL-NEXT: --------------------------------------------------------------------------
ALL-NEXT: DEBUG_S_FILECHKSMS: 1 entries ( 32 bytes)
ALL-NEXT: DEBUG_S_LINES: 1 entries ( 56 bytes)
ALL-NEXT: DEBUG_S_FILECHKSMS: 1 entries ( 32 bytes)
ONE-NOT: Mod 0000
ONE: Mod 0001 | `* Linker *`:
@ -57,12 +57,12 @@ ONE-NEXT: Stream 14, 520 bytes
ONE: Symbols
ONE-NEXT: Total: 13 entries ( 512 bytes)
ONE-NEXT: --------------------------------------------------------------------------
ONE-NEXT: S_SECTION: 4 entries ( 112 bytes)
ONE-NEXT: S_ENVBLOCK: 1 entries ( 172 bytes)
ONE-NEXT: S_COFFGROUP: 5 entries ( 140 bytes)
ONE-NEXT: S_SECTION: 4 entries ( 112 bytes)
ONE-NEXT: S_COMPILE3: 1 entries ( 48 bytes)
ONE-NEXT: S_TRAMPOLINE: 1 entries ( 20 bytes)
ONE-NEXT: S_OBJNAME: 1 entries ( 20 bytes)
ONE-NEXT: S_COMPILE3: 1 entries ( 48 bytes)
ONE-NEXT: S_COFFGROUP: 5 entries ( 140 bytes)
ONE: Chunks
ONE-NEXT: Total: 0 entries ( 0 bytes)
ONE-NEXT: --------------------------------------------------------------------------
@ -70,12 +70,12 @@ ONE-NEXT: Summary |
ONE: Symbols
ONE-NEXT: Total: 13 entries ( 512 bytes)
ONE-NEXT: --------------------------------------------------------------------------
ONE-NEXT: S_SECTION: 4 entries ( 112 bytes)
ONE-NEXT: S_ENVBLOCK: 1 entries ( 172 bytes)
ONE-NEXT: S_COFFGROUP: 5 entries ( 140 bytes)
ONE-NEXT: S_SECTION: 4 entries ( 112 bytes)
ONE-NEXT: S_COMPILE3: 1 entries ( 48 bytes)
ONE-NEXT: S_TRAMPOLINE: 1 entries ( 20 bytes)
ONE-NEXT: S_OBJNAME: 1 entries ( 20 bytes)
ONE-NEXT: S_COMPILE3: 1 entries ( 48 bytes)
ONE-NEXT: S_COFFGROUP: 5 entries ( 140 bytes)
ONE: Chunks
ONE-NEXT: Total: 0 entries ( 0 bytes)
ONE-NEXT: --------------------------------------------------------------------------

View File

@ -0,0 +1,17 @@
; RUN: llvm-pdbutil dump -type-stats %p/Inputs/empty.pdb | FileCheck --check-prefix=ALL %s
ALL: Type Record Stats
ALL-NEXT: ============================================================
ALL: Types
ALL-NEXT: Total: 75 entries ( 5,336 bytes, 71.15 avg)
ALL-NEXT: --------------------------------------------------------------------------
ALL-NEXT: LF_FIELDLIST: 14 entries ( 1,956 bytes, 139.71 avg)
ALL-NEXT: LF_STRUCTURE: 14 entries ( 1,584 bytes, 113.14 avg)
ALL-NEXT: LF_ENUM: 8 entries ( 988 bytes, 123.50 avg)
ALL-NEXT: LF_MFUNCTION: 14 entries ( 392 bytes, 28.00 avg)
ALL-NEXT: LF_ARGLIST: 10 entries ( 176 bytes, 17.60 avg)
ALL-NEXT: LF_METHODLIST: 5 entries ( 116 bytes, 23.20 avg)
ALL-NEXT: LF_POINTER: 8 entries ( 96 bytes, 12.00 avg)
ALL-NEXT: LF_PROCEDURE: 1 entries ( 16 bytes, 16.00 avg)
ALL-NEXT: LF_MODIFIER: 1 entries ( 12 bytes, 12.00 avg)

View File

@ -4,12 +4,12 @@ CHECK: S_UDT Record Stats
CHECK-NEXT: ============================================================
CHECK: Record Kind | Count Size
CHECK-NEXT: -----------------------------
CHECK-NEXT: LF_ENUM | 3 188
CHECK-NEXT: LF_POINTER | 39 468
CHECK-NEXT: LF_UNION | 1 52
CHECK-NEXT: <simple type> | 43 0
CHECK-NEXT: LF_PROCEDURE | 1 16
CHECK-NEXT: LF_STRUCTURE | 27 1,788
CHECK-NEXT: LF_POINTER | 39 468
CHECK-NEXT: LF_ENUM | 3 188
CHECK-NEXT: LF_UNION | 1 52
CHECK-NEXT: LF_PROCEDURE | 1 16
CHECK-NEXT: <simple type> | 43 0
CHECK-NEXT: -----------------------------
CHECK-NEXT: Total (S_UDT) | 114 2,604
CHECK-NEXT: -----------------------------

View File

@ -110,6 +110,12 @@ Error DumpOutputStyle::dump() {
P.NewLine();
}
if (opts::dump::DumpTypeStats) {
if (auto EC = dumpTypeStats())
return EC;
P.NewLine();
}
if (opts::dump::DumpNamedStreams) {
if (auto EC = dumpNamedStreams())
return EC;
@ -307,18 +313,30 @@ static inline std::string formatModuleDetailKind(SymbolKind K) {
return formatSymbolKind(K);
}
// Get the stats sorted by size, descending.
std::vector<StatCollection::KindAndStat>
StatCollection::getStatsSortedBySize() const {
std::vector<KindAndStat> SortedStats(Individual.begin(), Individual.end());
std::stable_sort(SortedStats.begin(), SortedStats.end(),
[](const KindAndStat &LHS, const KindAndStat &RHS) {
return LHS.second.Size > RHS.second.Size;
});
return SortedStats;
}
template <typename Kind>
static void printModuleDetailStats(LinePrinter &P, StringRef Label,
const StatCollection &Stats) {
P.NewLine();
P.formatLine(" {0}", Label);
AutoIndent Indent(P);
P.formatLine("{0,40}: {1,7} entries ({2,8} bytes)", "Total",
P.formatLine("{0,40}: {1,7} entries ({2,12:N} bytes)", "Total",
Stats.Totals.Count, Stats.Totals.Size);
P.formatLine("{0}", fmt_repeat('-', 74));
for (const auto &K : Stats.Individual) {
for (const auto &K : Stats.getStatsSortedBySize()) {
std::string KindName = formatModuleDetailKind(Kind(K.first));
P.formatLine("{0,40}: {1,7} entries ({2,8} bytes)", KindName,
P.formatLine("{0,40}: {1,7} entries ({2,12:N} bytes)", KindName,
K.second.Count, K.second.Size);
}
}
@ -676,6 +694,35 @@ Error DumpOutputStyle::dumpSymbolStats() {
return Error::success();
}
Error DumpOutputStyle::dumpTypeStats() {
printHeader(P, "Type Record Stats");
// Iterate the types, categorize by kind, accumulate size stats.
StatCollection TypeStats;
LazyRandomTypeCollection &Types = File.types();
for (Optional<TypeIndex> TI = Types.getFirst(); TI; TI = Types.getNext(*TI)) {
CVType Type = Types.getType(*TI);
TypeStats.update(uint32_t(Type.kind()), Type.length());
}
P.NewLine();
P.formatLine(" Types");
AutoIndent Indent(P);
P.formatLine("{0,14}: {1,7} entries ({2,12:N} bytes, {3,7} avg)", "Total",
TypeStats.Totals.Count, TypeStats.Totals.Size,
(double)TypeStats.Totals.Size / TypeStats.Totals.Count);
P.formatLine("{0}", fmt_repeat('-', 74));
for (const auto &K : TypeStats.getStatsSortedBySize()) {
P.formatLine("{0,14}: {1,7} entries ({2,12:N} bytes, {3,7} avg)",
formatTypeLeafKind(TypeLeafKind(K.first)), K.second.Count,
K.second.Size, (double)K.second.Size / K.second.Count);
}
return Error::success();
}
static bool isValidNamespaceIdentifier(StringRef S) {
if (S.empty())
return false;
@ -820,7 +867,7 @@ Error DumpOutputStyle::dumpUdtStats() {
fmt_align(SizeHeader, AlignStyle::Right, SD));
P.formatLine("{0}", fmt_repeat('-', TableWidth));
for (const auto &Stat : UdtTargetStats.Individual) {
for (const auto &Stat : UdtTargetStats.getStatsSortedBySize()) {
StringRef Label = getUdtStatLabel(Stat.first);
P.formatLine("{0} | {1:N} {2:N}",
fmt_align(Label, AlignStyle::Right, FieldWidth),
@ -833,12 +880,25 @@ Error DumpOutputStyle::dumpUdtStats() {
fmt_align(UdtStats.Totals.Count, AlignStyle::Right, CD),
fmt_align(UdtStats.Totals.Size, AlignStyle::Right, SD));
P.formatLine("{0}", fmt_repeat('-', TableWidth));
for (const auto &Stat : NamespacedStats) {
std::string Label = formatv("namespace '{0}'", Stat.getKey());
struct StrAndStat {
StringRef Key;
StatCollection::Stat Stat;
};
// Print namespace stats in descending order of size.
std::vector<StrAndStat> NamespacedStatsSorted;
for (const auto &Stat : NamespacedStats)
NamespacedStatsSorted.push_back({Stat.getKey(), Stat.second});
std::stable_sort(NamespacedStatsSorted.begin(), NamespacedStatsSorted.end(),
[](const StrAndStat &L, const StrAndStat &R) {
return L.Stat.Size > R.Stat.Size;
});
for (const auto &Stat : NamespacedStatsSorted) {
std::string Label = formatv("namespace '{0}'", Stat.Key);
P.formatLine("{0} | {1:N} {2:N}",
fmt_align(Label, AlignStyle::Right, FieldWidth),
fmt_align(Stat.second.Count, AlignStyle::Right, CD),
fmt_align(Stat.second.Size, AlignStyle::Right, SD));
fmt_align(Stat.Stat.Count, AlignStyle::Right, CD),
fmt_align(Stat.Stat.Size, AlignStyle::Right, SD));
}
return Error::success();
}

View File

@ -49,6 +49,8 @@ struct StatCollection {
}
};
using KindAndStat = std::pair<uint32_t, Stat>;
void update(uint32_t Kind, uint32_t RecordSize) {
Totals.update(RecordSize);
auto Iter = Individual.try_emplace(Kind, 1, RecordSize);
@ -57,6 +59,8 @@ struct StatCollection {
}
Stat Totals;
DenseMap<uint32_t, Stat> Individual;
std::vector<KindAndStat> getStatsSortedBySize() const;
};
class DumpOutputStyle : public OutputStyle {
@ -78,6 +82,7 @@ private:
Error dumpStreamSummary();
Error dumpSymbolStats();
Error dumpUdtStats();
Error dumpTypeStats();
Error dumpNamedStreams();
Error dumpStringTable();
Error dumpStringTableFromPdb();

View File

@ -462,7 +462,10 @@ cl::opt<bool> DumpSymbolStats(
"sym-stats",
cl::desc("Dump a detailed breakdown of symbol usage/size for each module"),
cl::cat(MsfOptions), cl::sub(DumpSubcommand));
cl::opt<bool> DumpTypeStats(
"type-stats",
cl::desc("Dump a detailed breakdown of type usage/size"),
cl::cat(MsfOptions), cl::sub(DumpSubcommand));
cl::opt<bool> DumpUdtStats(
"udt-stats",
cl::desc("Dump a detailed breakdown of S_UDT record usage / stats"),

View File

@ -140,6 +140,7 @@ extern llvm::cl::opt<bool> DumpSummary;
extern llvm::cl::opt<bool> DumpFpm;
extern llvm::cl::opt<bool> DumpStreams;
extern llvm::cl::opt<bool> DumpSymbolStats;
extern llvm::cl::opt<bool> DumpTypeStats;
extern llvm::cl::opt<bool> DumpUdtStats;
extern llvm::cl::opt<bool> DumpStreamBlocks;