Linux monitoring
Table of Contents
- 1. Linux monitoring
- 1.1. https://www.brendangregg.com
- 1.2. Network I/O
- 1.3. Disk I/O
- 1.4. Process Monitoring
- 1.4.1. aristocratos/btop: A monitor of resources
- 1.4.2. Linux Load Averages: Solving the Mystery
- 1.4.3. linux - What exactly do the colors in htop status bars mean? - Server Fault
- 1.4.4. Help! Linux ate my RAM!
- 1.4.5. amanusk/s-tui: Terminal-based CPU stress and monitoring utility
- 1.4.6. Snippet load average monitoring
- 1.4.7. The /proc/meminfo File in Linux | Baeldung on Linux
- 1.5. Flamegraph
- 1.6. Limit memory usage for a single Linux process - Unix & Linux Stack Exchange
- 1.7. Microsoft Announced Open-Source Performance Measuring Tools for Linux → Uses open source tools under the hood
- 1.8. Linux debugging tools I love
- 1.9. Every Linux networking tool I know
- 1.10. Wizard Zines
1. Linux monitoring
1.2. Network I/O
- https://www.ntop.org/products/traffic-analysis/ntop/ → sudo apt install ntopng
- https://github.com/raboof/nethogs → sudo apt install nethogs
- vnStat - ArchWiki
- gping → benchmark ping or any command, terminal graph
- https://hub.docker.com/r/networkstatic/iperf3 →
1.4. Process Monitoring
1.4.1. aristocratos/btop: A monitor of resources
Este es como el principal, está en C++ y se creó después de los otros:
Gráfico, permite utilizar el ratón
1.4.3. linux - What exactly do the colors in htop status bars mean? - Server Fault
Hitting F1 or h will show you the key. But for reference, the default colors are:
CPU:
- Blue = Low priority threads
- Green = Normal priority threads
- Red = Kernel threads
Memory:
- Green = Used memory
- Blue = Buffers
- Yellow/Orange = Cache
There are a couple of different color-schemes available, you can see them through hitting F2.
1.4.4. Help! Linux ate my RAM!
1.4.5. amanusk/s-tui: Terminal-based CPU stress and monitoring utility
1.4.6. Snippet load average monitoring
echo $(date -Iminutes),$(uptime | awk '{n = 3; for (--n; n >= 0; n--){ print $(NF-n)} print ""}' | sed s/,$//g | tr , . | tr '\n' , | sed s/,,//g) >> /home/pi/cpu.csv
1.5. Flamegraph
Time spent in each function call
https://www.brendangregg.com/flamegraphs.html
- The following pages (or posts) introduce different types of flame graphs:
- CPU
- Memory
- Off-CPU
- Hot/Cold
- Differential
- CPU
https://github.com/ariava/flamegraph
https://pypi.org/project/flameprof/
1.6. Limit memory usage for a single Linux process - Unix & Linux Stack Exchange
1.7. Microsoft Announced Open-Source Performance Measuring Tools for Linux → Uses open source tools under the hood
https://www.debugpoint.com/2021/12/microsoft-performance-tools-linux/
- For Tracing
- For Logging
- Dmesg
- Cloud-Init (by Canonical)
- WaLinuxAgent (Microsoft Azure Linux Agent)
- Dmesg