编写Shell过程中注意事项：
开头加解释器：#!/bin/bash
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。
有两个命令能帮助我调试脚本：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。
获取随机8位字符串：
方法1：
# echo $RANdoM |md5sum |cut -c 1-8
471b94f2
方法2：
# openssl rand -base64 4
vg3BEg==
方法3：
# cat /proc/sys/kernel/random/uuid |cut -c 1-8
ed9e032c
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
38571131
方法3：
# date %N |cut -c 1-8
69024815
cksum：打印CRC效验和统计字节
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
}
方法2：
function echo_color() {
case $1 in
green)
echo -e "[32;40m$2[0m"
;;
red)
echo -e "[31;40m$2[0m"
;;
*)
echo "Example: echo_color red string"
esac
}
使用方法：echo_color green "test"
function关键字定义一个函数，可加或不加。
3、批量创建用户#!/bin/bash
DATE=$(date %F_%T)
USER_FILE=user.txt
echo_color(){
if [ $1 == 'green' ]; then
echo -e "[32;40m$2[0m"
elif [ $1 == 'red' ]; then
echo -e "[31;40m$2[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 green "$USER_FILE exist, rename ${USER_FILE}-${DATE}.bak"
fi
echo -e "User Password" >> $USER_FILE
echo "-------------------">> $USER_FILE
for USER in user{1..10}; do
if ! id $USER &>/dev/null; then
PASS=$(echo $RANDOM |md5sum |cut -c 1-8)
useradd $USER
echo $PASS |passwd --stdin $USER &> /dev/dell
echo -e "$USER $PASS" >> $USER_FILE
echo "$USER User create successful."
else
echo_color red "$USER User already exists!"
fi
done
4、检查软件包是否安装#!/bin/bash
if rpm -q sysstat &>/dev/null; then
echo "sysstat is already installed."
else
echo "sysstat is not installed!"
fi
5、检查服务状态#!/bin/bash
PORT_C=$(ss -ant |grep -c 6443)
PS_C=$(ps -ef |grep kube-apiserver |grep -vc grep)
if [ $PORT_C -eq 0 -o $PS_C -eq 0 ]; then
echo "kube-apiserver service dowmped"
else
echo "kube-apiserver service running!"
fi
6、检查主机存活状态方法1：将错误IP放到数组里面判断是否ping失败三次
#!/bin/bash
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
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
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
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 Ping is successful."
continue
fi
}
for IP in $IP_LIST; do
ping_success_status
ping_success_status
ping_success_status
echo "$IP Ping is failure!"
done
7、监控CPU、内存和硬盘利用率#!/bin/bash
DATE=$(date %F" "%H:%M)
IP=$(ifconfig eth0 |awk '/netmask/ {print $2}')
if ! which vmstat &> /dev/null; then
echo "vmstat command no found, Please install procps package."
exit 1
fi
## CPU
US=$(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 $15}')
USE=$(($US $SY))
if [ $USE -ge 50 ];then
echo "
Date: $DATE
Host: $IP
Problem: CPU utilization $USE"
fi
## Mem
TOTAL=$(free -m |awk '/Mem/ {print $2}')
USE=$(free -m |awk '/Mem/ {print $3}')
FREE=$(free -m |awk '/Mem/ {print $4 $6}')
if [ $FREE -lt 1024 ]; then
echo "
Date: $DATE
Host: $IP
Problem: Total=$TOTAL,Use=$USE,Free=$FREE"
fi
#disk
PART_USE=$(df -h |awk -F'[% ] ' 'BEGIN{OFS="="} /^\/dev/ {print $1,$2,$5,$6}')
for i in $PART_USE; do
PART=$(echo $i |cut -d"=" -f1)
TOTAL=$(echo $i |cut -d "=" -f2)
USE=$(echo $i |cut -d"=" -f3)
MOUNT=$(echo $i |cut -d"=" -f4)
if [ $USE -gt 80 ]; then
echo "
Date: $DATE
Host: $IP
Total: $TOTAL
Problem: $PART=$USE($MOUNT)"
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 $NF,int($5)}' $TMP_FILE)
for USE_RATE in $USE_RATE_LIST; do
PART_NAME=${USE_RATE%=*} ##从右到左，非贪婪匹配，匹配到的删除
USE_RATE=${USE_RATE#*=} ##从左到右，非贪婪匹配，匹配到的删除
if [ $USE_RATE -ge 10 ];then
echo "Warning: $IP $PART_NAME Partition usage $USE_RATE%!"
fi
done
done
9、检查网站可用性#!/bin/bash
#--------------------
#1）检查URL可用性
#方法1：
check_url() {
HTTP_CODE=$(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_2() {
if ! wget -T 10 --tries=1 --spider $1 &>/dev/null; then
#-T超时时间，--tries尝试1次，--spider爬虫模式
echo "Warning: $1 Access failure!"
fi
}
#check_url www.baidu.com
#check_url_2 www.aaaa.com
#2）判断三次URL可用性
#思路与上面检查主机存活状态一样。
#---------------------------------
URL_LIST="www.baidu.com www.agasgf.com"
#------
#方法1：利用循环技巧，如果成功就跳出当前循环，否则执行到最后一行
check_url_3() {
HTTP_CODE=$(curl -o /dev/null --connect-timeout 3 -s -w "%{http_code}" $1)
if [ $HTTP_CODE -eq 200 ]; then
continue
fi
}
for URL in $URL_LIST; do
check_url_3 $URL
check_url_3 $URL
check_url_3 $URL
echo "Warning: $URL Access failure!"
done
#------
#方法2：错误次数保存到变量
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
for URL in $URL_LIST;do
NUM=1
unset FAIL_COUNT
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]=$URL
let NUM
else
break
fi
done
if [ ${#FAIL_COUNT[@]} -eq 3 ];then
echo "Warning: $URL Access failure!"
fi
done
10、检查MySQL主从同步状态#!/bin/bash
USER=bak
PASSWD=123456
IO_SQL_STATUS=$(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
,
