FlameGraph أوامر

FlameGraph هي مجموعة سكريبتات من Brendan Gregg تُنشئ مخططات لهب SVG تفاعلية من بيانات تتبع المكدس. تُصوّر مخططات اللهب البرمجيات المحللة بإظهار مسارات الكود التي تستهلك أكبر قدر من الموارد، مما يجعل اختناقات الأداء مرئية فوراً.

التثبيت

Linux/Ubuntu

# Clone the repository
git clone https://github.com/brendangregg/FlameGraph.git
cd FlameGraph

# Add to PATH (optional)
export PATH="$PATH:$(pwd)"

# Verify
./flamegraph.pl --help 2>&1 | head -3

# Dependencies — Perl is required (usually pre-installed)
perl --version

سير العمل الأساسي

# The standard 3-step process:
# 1. Capture stacks (perf, bpftrace, dtrace, etc.)
# 2. Collapse/fold stacks into single lines
# 3. Generate the SVG flame graph

# Example with perf:
perf record -F 99 -a -g -- sleep 30
perf script > out.perf
./stackcollapse-perf.pl out.perf > out.folded
./flamegraph.pl out.folded > flamegraph.svg

طيّ المكدسات

# Collapse perf script output
./stackcollapse-perf.pl out.perf > out.folded

# Collapse with PID annotations
./stackcollapse-perf.pl --pid out.perf > out.folded

# Collapse with thread IDs
./stackcollapse-perf.pl --tid out.perf > out.folded

# Collapse DTrace output
./stackcollapse.pl out.dtrace > out.folded

# Collapse bpftrace output
./stackcollapse-bpftrace.pl out.bpftrace > out.folded

# Collapse Java jstack output
./stackcollapse-jstack.pl out.jstack > out.folded

# Collapse Go pprof output
./stackcollapse-go.pl out.pprof > out.folded

# Collapse Python cProfile output
./stackcollapse-python.pl out.cprofile > out.folded

# Collapse Xcode Instruments output
./stackcollapse-instruments.pl out.instruments > out.folded

# Collapse strace output
./stackcollapse-stap.pl out.strace > out.folded

# Collapse recursive grep of /proc/PID/stack
./stackcollapse-recursive.pl out.procstack > out.folded

إنشاء مخططات اللهب

# Basic flame graph
./flamegraph.pl out.folded > flamegraph.svg

# Custom title
./flamegraph.pl --title "My App CPU Profile" out.folded > flamegraph.svg

# Custom subtitle
./flamegraph.pl --subtitle "Production 2026-05-21" out.folded > flamegraph.svg

# Set minimum display width (percentage)
./flamegraph.pl --minwidth 0.5 out.folded > flamegraph.svg

# Custom width and height
./flamegraph.pl --width 1400 --height 24 out.folded > flamegraph.svg

# Reverse stack order (icicle graph — grows downward)
./flamegraph.pl --inverted out.folded > icicle.svg

# Custom color palette
./flamegraph.pl --color hot out.folded > flamegraph.svg
./flamegraph.pl --color mem out.folded > flamegraph.svg
./flamegraph.pl --color io out.folded > flamegraph.svg
./flamegraph.pl --color java out.folded > flamegraph.svg

# Count name on y-axis
./flamegraph.pl --countname "microseconds" out.folded > flamegraph.svg

# Custom name type
./flamegraph.pl --nametype "Function:" out.folded > flamegraph.svg

مخططات لهب المعالج

# On-CPU flame graph from perf
perf record -F 99 -a -g -- sleep 30
perf script > out.perf
./stackcollapse-perf.pl out.perf > out.folded
./flamegraph.pl --title "CPU Flame Graph" out.folded > cpu.svg

# On-CPU flame graph from bpftrace
sudo bpftrace -e 'profile:hz:99 { @[kstack] = count(); }' > out.bpftrace
./stackcollapse-bpftrace.pl out.bpftrace > out.folded
./flamegraph.pl out.folded > cpu_bpf.svg

# User-space only CPU flame graph
perf record -F 99 -g --call-graph dwarf -p 1234 -- sleep 30
perf script > out.perf
./stackcollapse-perf.pl --kernel out.perf > out.folded
./flamegraph.pl --color java out.folded > user_cpu.svg

مخططات لهب خارج المعالج

# Using BCC offcputime
sudo offcputime-bpfcc -f 30 > offcpu.folded
./flamegraph.pl --color=io --title="Off-CPU Time" --countname=us offcpu.folded > offcpu.svg

# Using bpftrace for off-CPU analysis
sudo bpftrace -e '
tracepoint:sched:sched_switch {
    @start[tid] = nsecs;
}
tracepoint:sched:sched_wakeup /@start[args.pid]/ {
    @[kstack, args.comm] = sum(nsecs - @start[args.pid]);
    delete(@start[args.pid]);
}' > offcpu.bt

مخططات لهب الذاكرة

# Memory allocation flame graph from perf
perf record -e kmem:kmalloc -a -g -- sleep 10
perf script > mem.perf
./stackcollapse-perf.pl mem.perf > mem.folded
./flamegraph.pl --color=mem --title="Memory Allocations" --countname="bytes" mem.folded > mem.svg

مخططات اللهب التفاضلية

# Compare two profiles using difffolded.pl
# 1. Capture baseline profile
perf record -F 99 -a -g -- sleep 30
perf script > baseline.perf
./stackcollapse-perf.pl baseline.perf > baseline.folded

# 2. Capture comparison profile (after changes)
perf record -F 99 -a -g -- sleep 30
perf script > comparison.perf
./stackcollapse-perf.pl comparison.perf > comparison.folded

# 3. Generate differential folded stacks
./difffolded.pl baseline.folded comparison.folded > diff.folded

# 4. Generate differential flame graph
# Red = growth (regression), blue = shrinkage (improvement)
./flamegraph.pl --negate diff.folded > diff_flamegraph.svg

# Normalize to same sample count
./difffolded.pl -n baseline.folded comparison.folded > diff_normalized.folded
./flamegraph.pl --negate diff_normalized.folded > diff_norm.svg

التصفية والتحويل

# Grep for specific functions in folded stacks
grep 'tcp_' out.folded | ./flamegraph.pl > tcp_only.svg

# Exclude kernel stacks
grep -v 'vmlinux' out.folded | ./flamegraph.pl > user_only.svg

# Filter to specific process
grep 'my_app' out.folded | ./flamegraph.pl > my_app.svg

# Combine multiple folded stack files
cat profile1.folded profile2.folded | ./flamegraph.pl > combined.svg

# Sort folded stacks for diffing
sort out.folded > sorted.folded

صيغة المكدس المطوي

# Format: semicolon-separated stack frames followed by a space and count
# Bottom of stack is on the left, top (leaf) on the right

main;read_data;parse_json;validate 42
main;read_data;parse_json;transform 87
main;handle_request;send_response 156
main;handle_request;log_request 23

ميزات SVG التفاعلية

تتضمن ملفات SVG المُنشأة تفاعلية مدمجة:

الميزة	الوصف
Hover	Shows function name, sample count, and percentage
Click	Zooms into a specific frame and its children
Ctrl+F / Search	Highlights matching frames with magenta
Reset Zoom	Click “Reset Zoom” or press Escape
Right-click	Opens browser context menu for saving

سير العمل حسب اللغة

Java

# Using async-profiler (recommended for Java)
./asprof -d 30 -f out.html jps_pid
# Or generate folded stacks
./asprof -d 30 -o collapsed -f out.folded jps_pid
./flamegraph.pl out.folded > java_cpu.svg

Python

# Using py-spy to generate folded stacks
py-spy record -f raw -o out.folded --pid 1234
./flamegraph.pl out.folded > python_cpu.svg

Node.js

# Using 0x (wrapper around perf for Node.js)
npx 0x my_app.js
# Or perf with --perf-basic-prof
node --perf-basic-prof my_app.js &
perf record -F 99 -p $! -g -- sleep 30
perf script > out.perf
./stackcollapse-perf.pl out.perf > out.folded
./flamegraph.pl out.folded > node_cpu.svg

نصائح

# Increase sample rate for short workloads
perf record -F 999 -g -- ./short_task

# Use DWARF unwinding for accurate user-space stacks
perf record -g --call-graph dwarf -F 99 -p 1234 -- sleep 30

# Check if frame pointers are available
readelf -S /usr/bin/myapp | grep -i frame

# Pipe everything in one line
perf script | ./stackcollapse-perf.pl | ./flamegraph.pl > flamegraph.svg