[lld][BP] Print total size of startup symbols (#145106)

A good proxy to estimate the number of page faults during startup is the
total size of startup functions. Assuming profiles are up-to-date, we
can measure this total size pretty easily. Note that if profile data is
old, this number could be wrong.

Author: ellishg

lld/include/lld/Common/BPSectionOrdererBase.inc

@@ -292,45 +292,54 @@ auto BPOrderer<D>::computeOrder(
     bp.run(nodesForDataCompression);
   }
 
-  unsigned numStartupSections = 0;
-  unsigned numCodeCompressionSections = 0;
-  unsigned numDuplicateCodeSections = 0;
-  unsigned numDataCompressionSections = 0;
-  unsigned numDuplicateDataSections = 0;
+  unsigned numStartupSections = 0, startupSize = 0;
+  unsigned numCodeCompressionSections = 0, codeCompressionSize = 0;
+  unsigned numDuplicateCodeSections = 0, duplicateCodeSize = 0;
+  unsigned numDataCompressionSections = 0, dataCompressionSize = 0;
+  unsigned numDuplicateDataSections = 0, duplicateDataSize = 0;
   SetVector<const Section *> orderedSections;
   // Order startup functions,
   for (auto &node : nodesForStartup) {
     const auto *isec = sections[node.Id];
-    if (orderedSections.insert(isec))
+    if (orderedSections.insert(isec)) {
+      startupSize += D::getSize(*isec);
       ++numStartupSections;
+    }
   }
   // then functions for compression,
   for (auto &node : nodesForFunctionCompression) {
     const auto *isec = sections[node.Id];
-    if (orderedSections.insert(isec))
+    if (orderedSections.insert(isec)) {
+      codeCompressionSize += D::getSize(*isec);
       ++numCodeCompressionSections;
-
+    }
     auto It = duplicateSectionIdxs.find(node.Id);
     if (It == duplicateSectionIdxs.end())
       continue;
     for (auto dupSecIdx : It->getSecond()) {
       const auto *dupIsec = sections[dupSecIdx];
-      if (orderedSections.insert(dupIsec))
+      if (orderedSections.insert(dupIsec)) {
+        duplicateCodeSize += D::getSize(*isec);
         ++numDuplicateCodeSections;
+      }
     }
   }
   // then data for compression.
   for (auto &node : nodesForDataCompression) {
     const auto *isec = sections[node.Id];
-    if (orderedSections.insert(isec))
+    if (orderedSections.insert(isec)) {
+      dataCompressionSize += D::getSize(*isec);
       ++numDataCompressionSections;
+    }
     auto It = duplicateSectionIdxs.find(node.Id);
     if (It == duplicateSectionIdxs.end())
       continue;
     for (auto dupSecIdx : It->getSecond()) {
       const auto *dupIsec = sections[dupSecIdx];
-      if (orderedSections.insert(dupIsec))
+      if (orderedSections.insert(dupIsec)) {
+        duplicateDataSize += D::getSize(*isec);
         ++numDuplicateDataSections;
+      }
     }
   }
 
@@ -339,14 +348,21 @@ auto BPOrderer<D>::computeOrder(
         numStartupSections + numCodeCompressionSections +
         numDuplicateCodeSections + numDataCompressionSections +
         numDuplicateDataSections;
-    dbgs()
-        << "Ordered " << numTotalOrderedSections
-        << " sections using balanced partitioning:\n  Functions for startup: "
-        << numStartupSections
-        << "\n  Functions for compression: " << numCodeCompressionSections
-        << "\n  Duplicate functions: " << numDuplicateCodeSections
-        << "\n  Data for compression: " << numDataCompressionSections
-        << "\n  Duplicate data: " << numDuplicateDataSections << "\n";
+    unsigned totalOrderedSize = startupSize + codeCompressionSize +
+                                duplicateCodeSize + dataCompressionSize +
+                                duplicateDataSize;
+    dbgs() << "Ordered " << numTotalOrderedSections << " sections ("
+           << totalOrderedSize << " bytes) using balanced partitioning:\n";
+    dbgs() << "  Functions for startup: " << numStartupSections << " ("
+           << startupSize << " bytes)\n";
+    dbgs() << "  Functions for compression: " << numCodeCompressionSections
+           << " (" << codeCompressionSize << " bytes)\n";
+    dbgs() << "  Duplicate functions: " << numDuplicateCodeSections << " ("
+           << duplicateCodeSize << " bytes)\n";
+    dbgs() << "  Data for compression: " << numDataCompressionSections << " ("
+           << dataCompressionSize << " bytes)\n";
+    dbgs() << "  Duplicate data: " << numDuplicateDataSections << " ("
+           << duplicateDataSize << " bytes)\n";
 
     if (!profilePath.empty()) {
       // Evaluate this function order for startup

lld/test/ELF/bp-section-orderer.s

@@ -21,7 +21,7 @@
 # RUN: llvm-profdata merge a.proftext -o a.profdata
 # RUN: ld.lld a.o --irpgo-profile=a.profdata --bp-startup-sort=function --verbose-bp-section-orderer --icf=all --gc-sections 2>&1 | FileCheck %s --check-prefix=STARTUP-FUNC-ORDER
 
-# STARTUP-FUNC-ORDER: Ordered 3 sections using balanced partitioning
+# STARTUP-FUNC-ORDER: Ordered 3 sections ([[#]] bytes) using balanced partitioning
 # STARTUP-FUNC-ORDER: Total area under the page fault curve: 3.
 
 # RUN: ld.lld -o out.s a.o --irpgo-profile=a.profdata --bp-startup-sort=function
@@ -49,10 +49,10 @@
 # RUN: llvm-nm -jn out.cbs | tr '\n' , | FileCheck %s --check-prefix=CBOTH-STARTUP
 # CBOTH-STARTUP: s5,s3,s4,s2,s1,A,B,C,F,E,D,merged1,merged2,_start,d4,d1,d3,d2,{{$}}
 
-# BP-COMPRESSION-FUNC: Ordered 9 sections using balanced partitioning
-# BP-COMPRESSION-ICF-FUNC: Ordered 8 sections using balanced partitioning
-# BP-COMPRESSION-DATA: Ordered 9 sections using balanced partitioning
-# BP-COMPRESSION-BOTH: Ordered 18 sections using balanced partitioning
+# BP-COMPRESSION-FUNC: Ordered 9 sections ([[#]] bytes) using balanced partitioning
+# BP-COMPRESSION-ICF-FUNC: Ordered 8 sections ([[#]] bytes) using balanced partitioning
+# BP-COMPRESSION-DATA: Ordered 9 sections ([[#]] bytes) using balanced partitioning
+# BP-COMPRESSION-BOTH: Ordered 18 sections ([[#]] bytes) using balanced partitioning
 
 #--- a.proftext
 :ir

lld/test/MachO/bp-section-orderer.s

@@ -9,8 +9,8 @@
 
 # RUN: %lld -arch arm64 -lSystem -e _main -o %t/a.out %t/a.o --irpgo-profile %t/a.profdata --bp-startup-sort=function --verbose-bp-section-orderer 2>&1 | FileCheck %s --check-prefix=STARTUP
 # RUN: %lld -arch arm64 -lSystem -e _main -o %t/a.out %t/a.o --irpgo-profile=%t/a.profdata --bp-startup-sort=function --verbose-bp-section-orderer --icf=all --bp-compression-sort=none 2>&1 | FileCheck %s --check-prefix=STARTUP-ICF
-# STARTUP: Ordered 5 sections using balanced partitioning
-# STARTUP-ICF: Ordered 4 sections using balanced partitioning
+# STARTUP: Ordered 5 sections ([[#]] bytes) using balanced partitioning
+# STARTUP-ICF: Ordered 4 sections ([[#]] bytes) using balanced partitioning
 
 # Check that orderfiles take precedence over BP
 # RUN: %no-fatal-warnings-lld -arch arm64 -lSystem -e _main -o - %t/a.o -order_file %t/a.orderfile --irpgo-profile-sort=%t/a.profdata  | llvm-nm --numeric-sort --format=just-symbols - | FileCheck %s --check-prefix=ORDERFILE
@@ -50,10 +50,10 @@
 # RUN: %lld -arch arm64 -lSystem -e _main -o %t/a.out %t/a.o --verbose-bp-section-orderer --bp-compression-sort=both 2>&1 | FileCheck %s --check-prefix=COMPRESSION-BOTH
 # RUN: %lld -arch arm64 -lSystem -e _main -o %t/a.out %t/a.o --verbose-bp-section-orderer --bp-compression-sort=both --irpgo-profile=%t/a.profdata --bp-startup-sort=function 2>&1 | FileCheck %s --check-prefix=COMPRESSION-BOTH
 
-# COMPRESSION-FUNC: Ordered 9 sections using balanced partitioning
-# COMPRESSION-ICF-FUNC: Ordered 7 sections using balanced partitioning
-# COMPRESSION-DATA: Ordered 7 sections using balanced partitioning
-# COMPRESSION-BOTH: Ordered 16 sections using balanced partitioning
+# COMPRESSION-FUNC: Ordered 9 sections ([[#]] bytes) using balanced partitioning
+# COMPRESSION-ICF-FUNC: Ordered 7 sections ([[#]] bytes) using balanced partitioning
+# COMPRESSION-DATA: Ordered 7 sections ([[#]] bytes) using balanced partitioning
+# COMPRESSION-BOTH: Ordered 16 sections ([[#]] bytes) using balanced partitioning
 
 #--- a.s
 .text