Refactor PBO to PGO with true Profile-Guided Optimization

- Rename PBO (Profile-Based) to PGO (Performance Guided Optimization)
- Implement true PGO using Go's -pgo compiler flag
- Refactor script into maintainable functions:
  - setup_environment(): Initialize paths and variables
  - create_test_file(): Generate 100MB test file with 1M lines
  - build_baseline(): Build version without PGO optimizations
  - collect_training_data(): Generate CPU profiles for training
  - build_pgo_optimized(): Build with -pgo flag using training profile
  - run_pgo_performance_test(): Profile PGO-optimized version
  - run_performance_comparison(): Compare baseline vs PGO performance
  - generate_detailed_analysis(): Create comprehensive profile analysis
  - cleanup(): Remove temporary files
  - show_summary(): Display results and process summary
- Update Makefile target from 'pbo' to 'pgo'
- Update .gitignore patterns for PGO temporary files
- Update CLAUDE.md documentation for new PGO process
- Remove git stash dependencies for simpler automation
- Generate before/after performance comparison reports

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>

5 files changed, 176 insertions, 129 deletions

diff --git a/.gitignore b/.gitignore
index 89c6501..88674e0 100644
--- a/.gitignore
+++ b/.gitignore
@@ -18,7 +18,8 @@ id_rsa
 id_rsa.pub
 ssh_host_key
 
-# PBO (Profile-Based Optimization) temporary files
-scripts/pbo_*.prof
-scripts/pbo_report.txt
+# PGO (Performance Guided Optimization) temporary files
+scripts/pgo_*.prof
+scripts/pgo_report.txt
 scripts/test_100mb.txt
+dgrep_pgo
diff --git a/CLAUDE.md b/CLAUDE.md
index 753b3bf..e2353af 100644
--- a/CLAUDE.md
+++ b/CLAUDE.md
@@ -44,18 +44,18 @@ make lint
 
 ### Performance Optimization
 ```bash
-# Run Profile-Based Optimization (PBO) for dgrep
-make pbo
+# Run Performance Guided Optimization (PGO) for dgrep
+make pgo
 
-# This target will:
+# This implements true PGO using Go's -pgo compiler flag:
 # - Create test file (100MB with 1M lines) in scripts/ if needed
-# - Run baseline profiling (CPU and memory)
-# - Run performance benchmarks
-# - Generate optimized profiles in scripts/ directory
-# - Create detailed comparison report (scripts/pbo_report.txt)
-# - Show key optimizations implemented
+# - Build baseline version without PGO
+# - Collect CPU profile for training data
+# - Rebuild dgrep with -pgo flag using the training profile
+# - Compare baseline vs PGO-optimized performance (5 iterations each)
+# - Generate detailed before/after analysis report (scripts/pgo_report.txt)
 # 
-# All PBO files are organized in scripts/ directory to keep project root clean
+# All PGO files are organized in scripts/ directory to keep project root clean
 ```
 
 ### Installation
diff --git a/Makefile b/Makefile
index d47df58..ef6cffa 100644
--- a/Makefile
+++ b/Makefile
@@ -17,7 +17,7 @@ help:
 	@echo "  vet       - Run go vet on all packages"
 	@echo "  lint      - Run golint on all packages"
 	@echo "  install   - Install all binaries to \$$GOPATH/bin"
-	@echo "  pbo       - Run Profile-Based Optimization for dgrep"
+	@echo "  pgo       - Run Performance Guided Optimization for dgrep"
 	@echo ""
 	@echo "Individual binary targets:"
 	@echo "  dserver, dcat, dgrep, dmap, dtail, dtailhealth"
@@ -63,6 +63,6 @@ test:
 	set -e; find . -name '*_test.go' | while read file; do dirname $$file; done | \
 		sort -u | while read dir; do ${GO} test -tags '${GO_TAGS}' --race -v -failfast $$dir || exit 2; done
 
-# Profile-Based Optimization (PBO) target for dgrep
-pbo: clean build
-	@./scripts/pbo.sh
+# Performance Guided Optimization (PGO) target for dgrep
+pgo: clean build
+	@./scripts/pgo.sh
diff --git a/scripts/pbo.sh b/scripts/pbo.sh
deleted file mode 100755
index 909d28a..0000000
--- a/scripts/pbo.sh
+++ /dev/null
@@ -1,113 +0,0 @@
-#!/bin/bash
-
-# Profile-Based Optimization (PBO) script for dgrep
-# This script automates the complete PBO process including baseline testing,
-# optimization application, and performance comparison
-
-set -e
-
-# Get the directory where this script is located
-SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
-# Get the project root directory (parent of scripts)
-PROJECT_ROOT="$(dirname "$SCRIPT_DIR")"
-
-# Change to project root to run commands
-cd "$PROJECT_ROOT"
-
-# Define paths for all PBO files in scripts directory
-PBO_DIR="$SCRIPT_DIR"
-TEST_FILE="$PBO_DIR/test_100mb.txt"
-BASELINE_CPU_PROF="$PBO_DIR/pbo_baseline_cpu.prof"
-BASELINE_MEM_PROF="$PBO_DIR/pbo_baseline_mem.prof"
-OPTIMIZED_CPU_PROF="$PBO_DIR/pbo_optimized_cpu.prof"
-OPTIMIZED_MEM_PROF="$PBO_DIR/pbo_optimized_mem.prof"
-REPORT_FILE="$PBO_DIR/pbo_report.txt"
-
-echo "=== Starting Profile-Based Optimization (PBO) for dgrep ==="
-echo "Working directory: $PROJECT_ROOT"
-echo "PBO files location: $PBO_DIR"
-
-# 1. Create test file if needed
-echo "1. Creating test file if needed..."
-if [ ! -f "$TEST_FILE" ]; then
-    echo "Creating 100MB test file with 1M lines..."
-    for i in $(seq 1 1000000); do
-        echo "$i: This is a test line with INFO level logging and some extra content to make it realistic"
-    done > "$TEST_FILE"
-fi
-
-# 2. Run baseline performance test (assumes current state is baseline)
-echo "2. Running baseline performance test..."
-echo "   - Generating CPU profile (baseline)..."
-./dgrep --plain -regex "INFO" -files "$TEST_FILE" -cpuprofile "$BASELINE_CPU_PROF" -memprofile "$BASELINE_MEM_PROF" > /dev/null
-
-echo "   - Analyzing baseline profiles..."
-echo "   CPU Profile (baseline):" > "$REPORT_FILE"
-go tool pprof -top "$BASELINE_CPU_PROF" | head -10 >> "$REPORT_FILE"
-echo "   Memory Profile (baseline):" >> "$REPORT_FILE"  
-go tool pprof -top "$BASELINE_MEM_PROF" | head -10 >> "$REPORT_FILE"
-
-# 3. Run performance benchmark
-echo "3. Running performance benchmark (3 iterations)..."
-echo "   Baseline timings:" >> "$REPORT_FILE"
-for i in 1 2 3; do
-    echo "   Iteration $i:"
-    (time ./dgrep --plain -regex "INFO" -files "$TEST_FILE" > /dev/null) 2>&1 | grep real >> "$REPORT_FILE"
-done
-
-# 4. Note optimizations (already implemented in code)
-echo "4. PBO optimizations are already implemented in the code"
-echo "   - Timer allocation reduction (reusable timers)"
-echo "   - I/O operation optimization (bulk writes, pre-allocated buffers)"
-echo "   - Memory allocation improvements (buffer pooling)"
-
-# 5. Run optimized performance test
-echo "5. Running optimized performance test..."
-echo "   - Generating CPU profile (optimized)..."
-./dgrep --plain -regex "INFO" -files "$TEST_FILE" -cpuprofile "$OPTIMIZED_CPU_PROF" -memprofile "$OPTIMIZED_MEM_PROF" > /dev/null
-
-echo "   - Analyzing optimized profiles..."
-echo "   CPU Profile (optimized):" >> "$REPORT_FILE"
-go tool pprof -top "$OPTIMIZED_CPU_PROF" | head -10 >> "$REPORT_FILE"
-echo "   Memory Profile (optimized):" >> "$REPORT_FILE"
-go tool pprof -top "$OPTIMIZED_MEM_PROF" | head -10 >> "$REPORT_FILE"  
-
-# 6. Run optimized benchmark
-echo "6. Running optimized benchmark (3 iterations)..."
-echo "   Optimized timings:" >> "$REPORT_FILE"
-for i in 1 2 3; do
-    echo "   Iteration $i:"
-    (time ./dgrep --plain -regex "INFO" -files "$TEST_FILE" > /dev/null) 2>&1 | grep real >> "$REPORT_FILE"
-done
-
-# 7. Generate comparison report
-echo "7. Generating comparison report..."
-echo "=== PROFILE-BASED OPTIMIZATION REPORT ===" >> "$REPORT_FILE"
-echo "Baseline memory usage:" >> "$REPORT_FILE"
-go tool pprof -top "$BASELINE_MEM_PROF" | grep "Showing nodes" >> "$REPORT_FILE" || echo "N/A" >> "$REPORT_FILE"
-echo "Optimized memory usage:" >> "$REPORT_FILE"  
-go tool pprof -top "$OPTIMIZED_MEM_PROF" | grep "Showing nodes" >> "$REPORT_FILE" || echo "N/A" >> "$REPORT_FILE"
-echo "Baseline CPU samples:" >> "$REPORT_FILE"
-go tool pprof -top "$BASELINE_CPU_PROF" | grep "Total samples" >> "$REPORT_FILE" || echo "N/A" >> "$REPORT_FILE"
-echo "Optimized CPU samples:" >> "$REPORT_FILE"
-go tool pprof -top "$OPTIMIZED_CPU_PROF" | grep "Total samples" >> "$REPORT_FILE" || echo "N/A" >> "$REPORT_FILE"
-
-# 8. Summary
-echo "=== PBO Complete! ==="
-echo "Results saved to: $REPORT_FILE"
-echo "Profile files generated:"
-echo "  - $BASELINE_CPU_PROF"
-echo "  - $BASELINE_MEM_PROF"  
-echo "  - $OPTIMIZED_CPU_PROF"
-echo "  - $OPTIMIZED_MEM_PROF"
-echo ""
-echo "Test file location: $TEST_FILE"
-echo ""
-echo "Key improvements implemented:"
-echo "  ✓ Timer allocation reduction (eliminated time.After() calls)"
-echo "  ✓ I/O operation optimization (bulk writes vs byte-by-byte)"
-echo "  ✓ Memory allocation improvements (buffer pooling, pre-allocation)"
-echo ""
-
-# Show summary from report
-tail -20 "$REPORT_FILE"
\ No newline at end of file
diff --git a/scripts/pgo.sh b/scripts/pgo.sh
new file mode 100755
index 0000000..a590313
--- /dev/null
+++ b/scripts/pgo.sh
@@ -0,0 +1,159 @@
+#!/bin/bash
+
+# Performance Guided Optimization (PGO) script for dgrep
+# This script implements true PGO using Go's -pgo compiler flag:
+# 1. Build baseline version
+# 2. Generate CPU profile for training
+# 3. Rebuild with PGO using the profile
+# 4. Compare before/after performance
+
+set -e
+
+# Global variables
+setup_environment() {
+    # Get the directory where this script is located
+    SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+    # Get the project root directory (parent of scripts)
+    PROJECT_ROOT="$(dirname "$SCRIPT_DIR")"
+    
+    # Change to project root to run commands
+    cd "$PROJECT_ROOT"
+    
+    # Define paths for all PGO files in scripts directory
+    PGO_DIR="$SCRIPT_DIR"
+    TEST_FILE="$PGO_DIR/test_100mb.txt"
+    BASELINE_CPU_PROF="$PGO_DIR/pgo_baseline_cpu.prof"
+    BASELINE_MEM_PROF="$PGO_DIR/pgo_baseline_mem.prof"
+    TRAINING_PROF="$PGO_DIR/pgo_training.prof"
+    OPTIMIZED_CPU_PROF="$PGO_DIR/pgo_optimized_cpu.prof"
+    OPTIMIZED_MEM_PROF="$PGO_DIR/pgo_optimized_mem.prof"
+    REPORT_FILE="$PGO_DIR/pgo_report.txt"
+    
+    echo "=== Starting Profile Guided Optimization (PGO) for dgrep ==="
+    echo "Working directory: $PROJECT_ROOT"
+    echo "PGO files location: $PGO_DIR"
+}
+
+create_test_file() {
+    echo "1. Creating test file if needed..."
+    if [ ! -f "$TEST_FILE" ]; then
+        echo "Creating 100MB test file with 1M lines..."
+        for i in $(seq 1 1000000); do
+            echo "$i: This is a test line with INFO level logging and some extra content to make it realistic"
+        done > "$TEST_FILE"
+    fi
+}
+
+build_baseline() {
+    echo "2. Building baseline version (without PGO)..."
+    # Clean any existing binaries
+    rm -f dgrep dgrep_pgo dcat dmap dtail dserver dtailhealth
+    go build -tags '' -o dgrep ./cmd/dgrep/main.go
+}
+
+collect_training_data() {
+    echo "3. Running baseline performance test and collecting training profile..."
+    echo "   - Generating baseline CPU and memory profiles..."
+    ./dgrep --plain -regex "INFO" -files "$TEST_FILE" -cpuprofile "$BASELINE_CPU_PROF" -memprofile "$BASELINE_MEM_PROF" > /dev/null
+    
+    echo "   - Collecting training profile for PGO..."
+    ./dgrep --plain -regex "INFO" -files "$TEST_FILE" -cpuprofile "$TRAINING_PROF" > /dev/null
+}
+
+build_pgo_optimized() {
+    echo "4. Building PGO-optimized version using training profile..."
+    go build -tags '' -pgo="$TRAINING_PROF" -o dgrep_pgo ./cmd/dgrep/main.go
+}
+
+run_pgo_performance_test() {
+    echo "5. Running PGO-optimized performance test..."
+    echo "   - Generating optimized CPU and memory profiles..."
+    ./dgrep_pgo --plain -regex "INFO" -files "$TEST_FILE" -cpuprofile "$OPTIMIZED_CPU_PROF" -memprofile "$OPTIMIZED_MEM_PROF" > /dev/null
+}
+
+run_performance_comparison() {
+    echo "6. Running performance comparison..."
+    echo "=== PROFILE GUIDED OPTIMIZATION REPORT ===" > "$REPORT_FILE"
+    echo "Generated: $(date)" >> "$REPORT_FILE"
+    echo "" >> "$REPORT_FILE"
+    
+    echo "BASELINE (without PGO):" >> "$REPORT_FILE"
+    echo "Baseline performance (5 iterations):" >> "$REPORT_FILE"
+    for i in 1 2 3 4 5; do
+        echo "   Iteration $i:"
+        { time ./dgrep --plain -regex "INFO" -files "$TEST_FILE" > /dev/null; } 2>&1 | grep real >> "$REPORT_FILE"
+    done
+    
+    echo "" >> "$REPORT_FILE"
+    echo "PGO-OPTIMIZED:" >> "$REPORT_FILE"
+    echo "PGO-optimized performance (5 iterations):" >> "$REPORT_FILE"
+    for i in 1 2 3 4 5; do
+        echo "   Iteration $i:"
+        { time ./dgrep_pgo --plain -regex "INFO" -files "$TEST_FILE" > /dev/null; } 2>&1 | grep real >> "$REPORT_FILE"
+    done
+}
+
+generate_detailed_analysis() {
+    echo "7. Adding detailed profile analysis..."
+    echo "" >> "$REPORT_FILE"
+    echo "DETAILED ANALYSIS:" >> "$REPORT_FILE"
+    echo "" >> "$REPORT_FILE"
+    echo "Baseline CPU Profile:" >> "$REPORT_FILE"
+    go tool pprof -top "$BASELINE_CPU_PROF" | head -10 >> "$REPORT_FILE"
+    echo "" >> "$REPORT_FILE"
+    echo "PGO-Optimized CPU Profile:" >> "$REPORT_FILE"
+    go tool pprof -top "$OPTIMIZED_CPU_PROF" | head -10 >> "$REPORT_FILE"
+    echo "" >> "$REPORT_FILE"
+    echo "Baseline Memory Profile:" >> "$REPORT_FILE"
+    go tool pprof -top "$BASELINE_MEM_PROF" | head -10 >> "$REPORT_FILE"
+    echo "" >> "$REPORT_FILE"
+    echo "PGO-Optimized Memory Profile:" >> "$REPORT_FILE"
+    go tool pprof -top "$OPTIMIZED_MEM_PROF" | head -10 >> "$REPORT_FILE"
+}
+
+cleanup() {
+    echo "8. Cleaning up..."
+    rm -f dgrep_pgo
+}
+
+show_summary() {
+    echo "=== PGO Complete! ==="
+    echo "Results saved to: $REPORT_FILE"
+    echo "Profile files generated:"
+    echo "  - Baseline: $BASELINE_CPU_PROF, $BASELINE_MEM_PROF"
+    echo "  - Training: $TRAINING_PROF"
+    echo "  - Optimized: $OPTIMIZED_CPU_PROF, $OPTIMIZED_MEM_PROF"
+    echo ""
+    echo "Test file location: $TEST_FILE"
+    echo ""
+    echo "PGO Process:"
+    echo "  ✓ Built baseline version without PGO"
+    echo "  ✓ Collected CPU profile for training"
+    echo "  ✓ Rebuilt with Go's -pgo flag using training profile"
+    echo "  ✓ Compared baseline vs PGO-optimized performance"
+    echo ""
+    
+    # Show performance comparison from report
+    echo "=== Performance Comparison ==="
+    echo "Check $REPORT_FILE for detailed before/after comparison"
+    grep -A 20 "BASELINE (without PGO)" "$REPORT_FILE" | head -10
+    echo "..."
+    grep -A 20 "PGO-OPTIMIZED" "$REPORT_FILE" | head -10
+}
+
+# Main execution flow
+main() {
+    setup_environment
+    create_test_file
+    build_baseline
+    collect_training_data
+    build_pgo_optimized
+    run_pgo_performance_test
+    run_performance_comparison
+    generate_detailed_analysis
+    cleanup
+    show_summary
+}
+
+# Run the main function
+main "$@"
\ No newline at end of file