排查 Linux 问题

1. 排查 Linux 问题

1.1. 网络

端口占用

Linux:

sudo lsof -i -P -n | grep LISTEN
sudo netstat -tulpn | grep LISTEN
sudo ss -tulpn | grep LISTEN
sudo lsof -i:22 ## see a specific port such as 22 ##
sudo nmap -sTU -O IP-address-Here

FreeBSD/macOS (OS X) netstat syntax:

netstat -anp tcp | grep LISTEN
netstat -anp udp | grep LISTEN

udo sockstat -4 -6 -l

OpenBSD netstat syntax:

netstat -na -f inet | grep LISTEN
netstat -nat | grep LISTEN

Windows:

netstat -bano | more
netstat -bano | grep LISTENING
netstat -bano | findstr /R /C:"[LISTEING]"

• 用脚本方式

(echo >/dev/tcp/localhost/23) &>/dev/null && echo "open" || echo "close"
(echo >/dev/tcp/192.168.2.20/22) &>/dev/null && echo "open" || echo "close"

#!/bin/bash
dest_box="aws-prod-server-42"
echo "Testing the ssh connectivity ... "
if ! (echo >/dev/tcp/$dest_box/22) &>/dev/null
then
    echo "$0 cannot connect to the $dest_box. Check your vpn connectivity."
else
    echo "Running the ansible playboook ..."
    ansible-playbook -i hosts --ask-vault-pass --extra-vars '@cluster.data.yml' main.yaml
fi

sh:

nc -w {timeout} -zv {server_IP_hostname} {tcp_port} &>/dev/null && echo "Open" || echo "Close"
nc -w 5 -zv 192.168.2.20 23 &>/dev/null && echo "TCP/23 Open" || echo "TCP/23 Close"

#!/bin/bash
dest_box="aws-prod-server-42"
timeout="5" # timeouts in seconds
echo "Testing the ssh connectivity in $timeout seconds ... "
# make sure 'nc' is installed, else die ..
if ! type -a nc &>/dev/null
then
    echo "$0 - nc command not found. Please install nc and run the script again."
    exit 1
fi
if !  nc -w "$timeout" -zv "${dest_box}" 22  &>/dev/null
then
    echo "$0 cannot connect to the $dest_box. Check your vpn connectivity."
    exit 1
else
    echo "Running the ansible playboook ..."
    ansible-playbook -i hosts --ask-vault-pass --extra-vars '@cluster.data.yml' main.yaml
fi

perl:

#!/usr/bin/perl -w 
use IO::Socket::INET;
 
# Set server name and port here
$my_server="192.168.2.20";
$my_server_tcp_port="22";
 
# make a new object
my $server_test = IO::Socket::INET->new(
  PeerAddr => "$my_server",
  PeerPort => "$my_server_tcp_port",
  Proto => 'tcp',
  Timeout => 5
);
 
# test it and die or continue as per your needs
if ($server_test) {
    
    
  print "TCP port $my_server_tcp_port is open for the $my_server.\n";
  print "Now doing something ...\n";
  close $server_test;
} 
else {
    
    
  print "TCP port $my_server_tcp_port is closed or timed out for the $my_server.\n";
}

python:

#!/usr/bin/python3
# Tested on Python 3.6.xx and 3.8.xx only (updated from Python 2.x)
import socket
 
# Create a new function 
def check_server_tcp_port(my_host_ip_name, my_tcp_port, timeout=5):
    s = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
    s.settimeout(timeout)
    try:
        s.connect((my_host_ip_name, my_tcp_port))
        print(f"TCP port {
      
      my_tcp_port} is open for the {
      
      my_host_ip_name}.")
        s.close()
        return True
    except socket.timeout:
        print(f"TCP port {
      
      my_tcp_port} is closed or timed out for the {
      
      my_host_ip_name}.")
        return False
 
# Test it 
check_server_tcp_port("localhost", 22)
check_server_tcp_port("192.168.2.20", 22)

• man

man lsof
man ss
man netstat
man nmap
man 5 services
man nc

参考自这里

1.2. 内存

# 查前 3 占用最高
ps -o pid,user,%mem,command ax | sort -b -k3 -r

1.3. 硬盘

# 查看总体大小
df -h

# 查看目录下每个文件夹的大小
du -h --max-depth=1

# 查看子目录文件及文件夹大小统计值
du -sh