# Install
sudo apt install linux-perf    # Debian/Ubuntu (version-matched)
sudo dnf install perf          # Fedora/RHEL

# Check permissions
# By default perf requires root or paranoid level ≤ 1
cat /proc/sys/kernel/perf_event_paranoid
# 2 = only CPU stats (not kernel), 1 = user+kernel, 0 = all, -1 = no restrictions

# Temporarily lower (session only)
sudo sysctl -w kernel.perf_event_paranoid=1

# Persistent
echo 'kernel.perf_event_paranoid=1' | sudo tee /etc/sysctl.d/99-perf.conf
sudo sysctl -p /etc/sysctl.d/99-perf.conf

gcc -g -O2 -fno-omit-frame-pointer -o prog main.c
# -fno-omit-frame-pointer: essential for frame-pointer-based unwinding
# Alternative: compile with DWARF CFI and use --call-graph=dwarf

# Basic hardware counters
perf stat ./prog

# With specific events
perf stat -e cache-misses,cache-references,instructions,cycles,branch-misses ./prog

# Wall-clock comparison: N runs
perf stat -r 5 ./prog

# Attach to existing process
perf stat -p 12345 sleep 10

# Default: sample at 1000 Hz (cycles event)
perf record -g ./prog

# Specify frequency
perf record -F 999 -g ./prog

# Specific event
perf record -e cache-misses -g ./prog

# Attach to running process
perf record -F 999 -g -p 12345 sleep 30

# Off-CPU profiling (time spent waiting)
perf record -e sched:sched_switch -ag sleep 10

# DWARF call graphs (better for binaries without frame pointers)
perf record -F 999 --call-graph=dwarf ./prog

# Save to named file
perf record -o myapp.perf.data -g ./prog

perf report                          # reads perf.data
perf report -i myapp.perf.data
perf report --no-children            # self time only (not cumulative)
perf report --sort comm,dso,sym      # sort by fields
perf report --stdio                  # non-interactive text output

# Show assembly with hit percentages
perf annotate sym_name

# From report: press 'a' on a symbol
# Or directly:
perf annotate -i perf.data --symbol=hot_function --stdio

# Live top, like 'top' but for functions
sudo perf top -g

# Filter by process
sudo perf top -p 12345

# Generate perf script output
perf script > out.perf

# Use Brendan Gregg's FlameGraph tools
git clone https://github.com/brendangregg/FlameGraph
./FlameGraph/stackcollapse-perf.pl out.perf > out.folded
./FlameGraph/flamegraph.pl out.folded > flamegraph.svg

# Open flamegraph.svg in browser

# List all available events
perf list

# Common hardware events
cycles
instructions
cache-references
cache-misses
branch-instructions
branch-misses
stalled-cycles-frontend
stalled-cycles-backend

# Software events
context-switches
cpu-migrations
page-faults

# Tracepoints (requires root)
sched:sched_switch
syscalls:sys_enter_read