shell2（随机数、主机存活、批量建用户）
- 语法缩进，使用四个空格；多加注释说明。
- 命名建议规则：变量名大写、局部变量小写，函数名小写，名字体现出实际作用。
- 默认变量是全局的，在函数中变量local指定为局部变量，避免污染其他作用域。
- 有两个命令能帮助调试脚本：set -e 遇到执行非0时退出脚本，set-x 打印执行过程。
- 写脚本一定先测试再到生产上。
- bash -xv *.sh 显示执行的过程
- bash -n ***.sh 判断语法错误
1、获取随机字符串或数字
获取随机8位字符串：
方法1：
1 # echo $RANDOM |md5sum |cut -c 1-8
2 471b94f2
方法2：
1 # openssl rand -base64 4
2 vg3BEg==
方法3：
# cat /proc/sys/kernel/random/uuid |cut -c 1-8
ed9e032c
方法4：
# uuidgen 1
e42b3f04-7a45-4fe7-a95e-8396b8585c8c
# uuidgen 2 |cut -c 1-8
a9384a68
# uuidgen 1 | sed -r 's/(........)(.*)/\1/'
a9ca086c
方法5：
# openssl rand -hex 3 （注：-hex 3表示生成3个16进制数，一个十六进制用2位表示，如9表示为09）
8e152a
# openssl rand -hex 2
7cd2
# openssl rand -hex 3 |sed -r 's/(..)\B/\1:/g' （\B表示使非单词边界失效，\b使单词边界失效）
49:ff:1c
获取随机8位数字：
方法1：
# echo $RANDOM |cksum |cut -c 1-8
23648321
方法2：
# openssl rand -base64 4 |cksum |cut -c 1-8 （cksum：打印CRC效验和统计字节）
38571131
方法3：
# date +%N |cut -c 1-8 69024815 $ date +%s%N | cut -c 1-8 16103596
2、定义一个颜色输出字符串函数
方法1：
function echo_color() {
if [ "$1" == "green" ]; then
echo -e "\033[32;40m$2\033[0m"
elif [" $1" == "red" ]; then
echo -e "\033[31;40m$2\033[0m"
fi
}
echo_color() $1 $2
方法2：
function echo_color() {
case $1 in
green)
echo -e "[32;40m$2[0m"
;;
red)
echo -e "[31;40m$2[0m"
;;
*)
echo "Example: echo_color red string"
esac
}
使用方法：echo_color green "test"
function关键字定义一个函数，可加或不加。
3、批量创建用户
假如所要创建的用户名字已经确定，放在/root/uname.txt
#!/bin/bash
DATE=$(date +%F_%T)
USER_FILE=user.txt
USERS=`cat /root/uname.txt`
echo_color(){
if [ $1 == "blue" ]; then
echo -e "\033[7;46;30m$2\033[0m"
elif [ $1 == "yellow" ]; then
echo -e "\033[33m$2\033[0m"
elif [ $1 == "purple" ]; then
echo -e "\033[45;30m$2\033[0m"
fi
}
# 如果用户文件存在并且大小大于0就备份
if [ -s $USER_FILE ]; then
mv $USER_FILE ${USER_FILE}-${DATE}.bak
echo_color blue "$USER_FILE exist, rename ${USER_FILE}-${DATE}.bak"
fi
echo "User -> Password" >> $USER_FILE
echo "-------------------" >> $USER_FILE
for USER in $USERS; do
if ! id $USER &>/dev/null; then
PASS=$(echo $RANDOM |md5sum |cut -c 1-8)
useradd $USER
echo $PASS | passwd --stdin $USER &>/dev/null
echo "$USER -> $PASS" >> $USER_FILE
echo_color purple "$USER User create successful."
else
echo_color yellow "$USER User already exists!" # (echo_color(函数) $1 $2)
fi
done
###命令行操作
for user in `cat name.txt`;do useradd $user && echo moqi#233 | passwd --stdin $user ; done
4、检查软件包是否安装
#!/bin/bash
read -p "请输入要检测的软件名：" app;
if rpm -q $app &> /dev/null;then
echo "$app is already installed."
else
echo "$app is not installed!"
fi
5、检查服务状态
#!/bin/bash
PORT_C=$(ss -anu |grep -c 123)
PS_C=$(ps -ef |grep ntpd |grep -vc grep)
if [ $PORT_C -eq 0 -o $PS_C -eq 0 ]; then
echo "内容" | mail -s "主题" dst@example.com
fi
6、检查主机存活状态检查
方法1：将错误IP放到数组里面判断是否ping失败三次
#!/bin/bash
IP_LIST="192.168.18.1 192.168.1.1 192.168.18.2"
for IP in $IP_LIST; do
NUM=1
while [ $NUM -le 3 ]; do
if ping -c 1 $IP > /dev/null; then
echo "$IP Ping is successful."
break
else
# echo "$IP Ping is failure $NUM"
FAIL_COUNT[$NUM]=$IP
let NUM++
fi
done
if [ ${#FAIL_COUNT[*]} -eq 3 ];then
echo "${FAIL_COUNT[1]} Ping is failure!"
unset FAIL_COUNT[*]
fi
done
方法2：将错误次数放到FAIL_COUNT变量里面判断是否ping失败三次
#!/bin/bash
IP_LIST="192.168.18.1 192.168.1.1 192.168.18.2"
for IP in $IP_LIST; do
FAIL_COUNT=0
for ((i=1;i< =3;i++)); do
if ping -c 1 $IP >/dev/null; then
echo "$IP Ping is successful."
break
else
# echo "$IP Ping is failure $i"
let FAIL_COUNT++
fi
done
if [ $FAIL_COUNT -eq 3 ]; then
echo "$IP Ping is failure!"
fi
done
方法3：利用for循环将ping通就跳出循环继续，如果不跳出就会走到打印ping失败
#!/bin/bash
ping_success_status() {
if ping -c 1 $IP >> /dev/null; then
echo "$IP is on" >> /root/success-host.txt
continue
fi
}
success=/root/success-host.txt
failure=/root/failure-host.txt
rm -rf $success
rm -rf $failure
if [[ ! -f $success ]];then
touch /root/success-host.txt && chmod 777 /root/success-host.txt
echo "$success 文件创建成功"
else
echo "$success 文件已经存在"
fi
if [[ ! -f $failure ]];then
touch /root/failure-host.txt && chmod 777 /root/failure-host.txt
echo "$failure 文件创建成功"
else
echo "$failure 文件已经存在"
fi
for IP in `echo 10.1.1.{1..254}`; do
ping_success_status
echo "$IP is off!" >> /root/failure-host.txt
done
echo "在线主机数如下:" && cat /root/success-host.txt | wc -l
#cat /root/success-host.txt
echo "离线主机数如下:" && cat /root/failure-host.txt | wc -l
#cat /root/failure-host.txt
探测254个ip执行时间，耗时
time bash ping.sh /root/success-host.txt 文件创建成功 /root/failure-host.txt 文件创建成功 在线主机数如下: 99 离线主机数如下: 155 real 7m56.204s user 0m0.121s sys 0m0.267s
优化：
#!/bin/bash
ping_success_status() {
if ping -c 1 $IP >> /dev/null; then
echo "$IP is on" >> /root/success-host.txt
continue
fi
}
success=/root/success-host.txt
failure=/root/failure-host.txt
rm -rf $success
rm -rf $failure
if [[ ! -f $success ]];then
touch /root/success-host.txt && chmod 777 /root/success-host.txt
echo "$success 文件创建成功"
else
echo "$success 文件已经存在"
fi
if [[ ! -f $failure ]];then
touch /root/failure-host.txt && chmod 777 /root/failure-host.txt
echo "$failure 文件创建成功"
else
echo "$failure 文件已经存在"
fi
for IP in `echo 10.1.1.{1..254}`
do
{ ping_success_status
echo "$IP is off!" >> /root/failure-host.txt
} &
done
wait
echo "在线主机数如下:" && cat /root/success-host.txt | wc -l
#cat /root/success-host.txt
echo "离线主机数如下:" && cat /root/failure-host.txt | wc -l
#cat /root/failure-host.txt
简单写法
#!/bin/bash
for i in {1..20}
do
{
ping -c 2 192.168.1.$i >/dev/null
if [ $? = 0 ];then
echo "192.168.1.$i 存活"
else
echo "192.168.1.$i 不存活"
fi
} &
done
wait
&是把进程放到后台，不用等待
wait是等所有进程都执行完才退出
如果没有wait可能会导致程序无法退出，原因是父进程先退出，子进程还没执行完。这种情况就是所谓的僵尸进程。
注意：多线程展示的结果和实现过程的脚本一致，只不过多线程的脚本是不用等待的，所以它展示的结果不是按ip的顺序展示的
优化后执行效率大大提高，由7分56秒缩短到10秒
time bash ping.sh /root/success-host.txt 文件创建成功 /root/failure-host.txt 文件创建成功 在线主机数如下: 99 离线主机数如下: 155 real 0m10.055s user 0m0.171s sys 0m0.294s
7、监控CPU、内存和硬盘利用率
1）CPU
借助vmstat工具来分析CPU统计信息。
#!/bin/bash
DATE=$(date +%F" "%H:%M)
IP=$(ifconfig eth0 |awk -F [ :]+ /inet addr/{print $4} ) # 只支持CentOS6
MAIL="example@mail.com"
if ! which vmstat &>/dev/null; then
echo "vmstat command no found, Please install procps package."
exit 1
fi
US=$(vmstat |awk NR==3{print $13} )
SY=$(vmstat |awk NR==3{print $14} )
IDLE=$(vmstat |awk NR==3{print $15} )
WAIT=$(vmstat |awk NR==3{print $16} )
USE=$(($US+$SY))
if [ $USE -ge 50 ]; then
echo "
Date: $DATE
Host: $IP
Problem: CPU utilization $USE
" | mail -s "CPU Monitor" $MAIL
fi
2）内存
#!/bin/bash
DATE=$(date +%F" "%H:%M)
IP=$(ifconfig eth0 |awk -F [ :]+ /inet addr/{print $4} )
MAIL="example@mail.com"
TOTAL=$(free -m |awk /Mem/{print $2} )
USE=$(free -m |awk /Mem/{print $3-$6-$7} )
FREE=$(($TOTAL-$USE))
# 内存小于1G发送报警邮件
if [ $FREE -lt 1024 ]; then
echo "
Date: $DATE
Host: $IP
Problem: Total=$TOTAL,Use=$USE,Free=$FREE
" | mail -s "Memory Monitor" $MAIL
fi
3）硬盘
#!/bin/bash
DATE=$(date +%F" "%H:%M)
IP=$(ifconfig eth0 |awk -F [ :]+ /inet addr/{print $4} )
MAIL="example@mail.com"
TOTAL=$(fdisk -l |awk -F [: ]+ BEGIN{OFS="="}/^Disk /dev/{printf "%s=%sG,",$2,$3} )
PART_USE=$(df -h |awk BEGIN{OFS="="}/^/dev/{print $1,int($5),$6} )
for i in $PART_USE; do
PART=$(echo $i |cut -d"=" -f1)
USE=$(echo $i |cut -d"=" -f2)
MOUNT=$(echo $i |cut -d"=" -f3)
if [ $USE -gt 80 ]; then
echo "
Date: $DATE
Host: $IP
Total: $TOTAL
Problem: $PART=$USE($MOUNT)
" | mail -s "Disk Monitor" $MAIL
fi
done
8、批量主机磁盘利用率监控
前提监控端和被监控端SSH免交互登录或者密钥登录。
写一个配置文件保存被监控主机SSH连接信息，文件内容格式：IP User Port
#!/bin/bash
HOST_INFO=host.info
for IP in $(awk /^[^#]/{print $1} $HOST_INFO); do
USER=$(awk -v ip=$IP ip==$1{print $2} $HOST_INFO)
PORT=$(awk -v ip=$IP ip==$1{print $3} $HOST_INFO)
TMP_FILE=/tmp/disk.tmp
ssh -p $PORT $USER@$IP df -h > $TMP_FILE
USE_RATE_LIST=$(awk BEGIN{OFS="="}/^/dev/{print $1,int($5)} $TMP_FILE)
for USE_RATE in $USE_RATE_LIST; do
PART_NAME=${USE_RATE%=*}
USE_RATE=${USE_RATE#*=}
if [ $USE_RATE -ge 80 ]; then
echo "Warning: $PART_NAME Partition usage $USE_RATE%!"
fi
done
done
9、检查网站可用性
1）检查URL可用性
方法1：
check_url() {
HTTP_CODE=$(curl -o /dev/null --connect-timeout 3 -s -w "%{http_code}" $1)
if [ $HTTP_CODE -ne 200 ]; then
echo "Warning: $1 Access failure!"
fi
}
方法2：
check_url() {
if ! wget -T 10 --tries=1 --spider $1 >/dev/null 2>&1; then
#-T超时时间，--tries尝试1次，--spider爬虫模式
echo "Warning: $1 Access failure!"
fi
}
使用方法：check_url www.baidu.com
2）判断三次URL可用性
思路与上面检查主机存活状态一样。
方法1：利用循环技巧，如果成功就跳出当前循环，否则执行到最后一行
#!/bin/bash
check_url() {
HTTP_CODE=$(curl -o /dev/null --connect-timeout 3 -s -w "%{http_code}" $1)
if [ $HTTP_CODE -eq 200 ]; then
continue
fi
}
URL_LIST="www.baidu.com www.agasgf.com"
for URL in $URL_LIST; do
check_url $URL
check_url $URL
check_url $URL
echo "Warning: $URL Access failure!"
done
方法2：错误次数保存到变量
#!/bin/bash
URL_LIST="www.baidu.com www.agasgf.com"
for URL in $URL_LIST; do
FAIL_COUNT=0
for ((i=1;i< =3;i++)); do
HTTP_CODE=$(curl -o /dev/null --connect-timeout 3 -s -w "%{http_code}" $URL)
if [ $HTTP_CODE -ne 200 ]; then
let FAIL_COUNT++
else
break
fi
done
if [ $FAIL_COUNT -eq 3 ]; then
echo "Warning: $URL Access failure!"
fi
done
方法3：错误次数保存到数组
#!/bin/bash
URL_LIST="www.baidu.com www.agasgf.com"
for URL in $URL_LIST; do
NUM=1
while [ $NUM -le 3 ]; do
HTTP_CODE=$(curl -o /dev/null --connect-timeout 3 -s -w "%{http_code}" $URL)
if [ $HTTP_CODE -ne 200 ]; then
FAIL_COUNT[$NUM]=$IP #创建数组，以$NUM下标，$IP元素
let NUM++
else
break
fi
done
if [ ${#FAIL_COUNT[*]} -eq 3 ]; then
echo "Warning: $URL Access failure!"
unset FAIL_COUNT[*] #清空数组
fi
done
10、检查MySQL主从同步状态
#!/bin/bash
USER=bak
PASSWD=123456
IO_SQL_STATUS=$(mysql -u$USER -p$PASSWD -e show slave statusG |awk -F: /Slave_.*_Running/{gsub(": ",":");print $0} ) #gsub去除冒号后面的空格
for i in $IO_SQL_STATUS; do
THREAD_STATUS_NAME=${i%:*}
THREAD_STATUS=${i#*:}
if [ "$THREAD_STATUS" != "Yes" ]; then
echo "Error: MySQL Master-Slave $THREAD_STATUS_NAME status is $THREAD_STATUS!"
fi
done
