Linux monitoring

Table of Contents

1. Linux monitoring

1.1. Network I/O

1.2. Disk I/O

1.2.1. NCurses Disk Usage

See where your space is going

1.3. Process Monitoring

1.3.1. 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

1.3.3. 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.

1.3.4. amanusk/s-tui: Terminal-based CPU stress and monitoring utility

1.3.5. 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

1.4. Flamegraph

Time spent in each function call
https://www.brendangregg.com/flamegraphs.html

  • The following pages (or posts) introduce different types of flame graphs:
    1. CPU
    2. Memory
    3. Off-CPU
    4. Hot/Cold
    5. Differential

https://github.com/ariava/flamegraph
https://pypi.org/project/flameprof/

1.5. Limit memory usage for a single Linux process - Unix & Linux Stack Exchange

1.6. 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
    • LTTng (Linux Kernel CPU scheduling, Processes, Threads, Block IO/Disk, Syscalls, File events, etc)
    • perf Linux CPU Sampling(cpu-clock)
    • Perfetto Android & Chromium (CPU Scheduling, CPU Sampling, CPU Frequency, FTrace, Android Logs, Generic Events / Default Tracks, GPU Counters)
  • For Logging

Author: Julian Lopez Carballal

Created: 2024-09-16 Mon 05:28