30个Linux Shell脚本经典案例

转载

xucaibao1979 2019-07-30 09:06:13

文章标签 shell 文章分类 运维

在学习Linux运维时，普遍反馈是：Linux Shell是一个很难的知识板块。虽然大家都认真学，基本的语法也都掌握了，但有需求时，很难直接上手编程，要么写了很久，要么写不好！也有很多做运维很多年的朋友也是如此，Shell脚本一直写的不6！在网上看例子能照猫画虎写出来，完全独立写就困难了。对于初学者而言，因为没有实战经验，写不出来Shell脚本很正常，如果工作了几年的运维老年还是写不出来，那就是没主动找需求，缺乏练习，缺乏经验。针对以上问题，总结了30个生产环境中经典的Shell脚本，通过这些需求案例，希望能帮助大家提升Shell编写思路，掌握编写技巧。

先了解下编写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。

1、获取随机字符串或数字

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 $USER &>/dev/null echo -e "$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=$(ss -anu |grep -c 123) PS_C=$(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

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 Ping is successful." continue fi } IP_LIST="192.168.18.1 192.168.1.1 192.168.18.2" 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

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

11、iptables自动屏蔽访问网站频繁的IP

场景：恶意访问,安全防范

1）屏蔽每分钟访问超过200的IP

方法1：根据访问日志（Nginx为例）

#!/bin/bash DATE=$(date +%d/%b/%Y:%H:%M) ABNORMAL_IP=$(tail -n5000 access.log |grep $DATE |awk '{a[$1]++}END{for(i in a)if(a[i]>100)print i}') #先tail防止文件过大，读取慢，数字可调整每分钟最大的访问量。awk不能直接过滤日志，因为包含特殊字符。 for IP in $ABNORMAL_IP; do if [ $(iptables -vnL |grep -c "$IP") -eq 0 ]; then iptables -I INPUT -s $IP -j DROP fi done 方法2：通过TCP建立的连接

#!/bin/bash ABNORMAL_IP=$(netstat -an |awk '$4~/:80$/ && $6~/ESTABLISHED/{gsub(/:[0-9]+/,"",$5);{a[$5]++}}END{for(i in a)if(a[i]>100)print i}') #gsub是将第五列（客户端IP）的冒号和端口去掉 for IP in $ABNORMAL_IP; do if [ $(iptables -vnL |grep -c "$IP") -eq 0 ]; then iptables -I INPUT -s $IP -j DROP fi done

2）屏蔽每分钟SSH尝试登录超过10次的IP

方法1：通过lastb获取登录状态:

#!/bin/bash DATE=$(date +"%a %b %e %H:%M") #星期月天时分 %e单数字时显示7，而%d显示07 ABNORMAL_IP=$(lastb |grep "$DATE" |awk '{a[$3]++}END{for(i in a)if(a[i]>10)print i}') for IP in $ABNORMAL_IP; do if [ $(iptables -vnL |grep -c "$IP") -eq 0 ]; then iptables -I INPUT -s $IP -j DROP fi done 方法2：通过日志获取登录状态 #!/bin/bash DATE=$(date +"%b %d %H") ABNORMAL_IP="$(tail -n10000 /var/log/auth.log |grep "$DATE" |awk '/Failed/{a[$(NF-3)]++}END{for(i in a)if(a[i]>5)print i}')" for IP in $ABNORMAL_IP; do if [ $(iptables -vnL |grep -c "$IP") -eq 0 ]; then iptables -A INPUT -s $IP -j DROP echo "$(date +"%F %T") - iptables -A INPUT -s $IP -j DROP" >>~/ssh-login-limit.log fi done

12、判断用户输入的是否为IP地址

方法1:

#!/bin/bash function check_ip(){ IP=$1 VALID_CHECK=$(echo $IP|awk -F. '$1<=255&&$2<=255&&$3<=255&&$4<=255{print "yes"}') if echo $IP|grep -E "^[0-9]{1,3}.[0-9]{1,3}.[0-9]{1,3}.[0-9]{1,3}$">/dev/null; then if [ $VALID_CHECK == "yes" ]; then echo "$IP available." else echo "$IP not available!" fi else echo "Format error!" fi } check_ip 192.168.1.1 check_ip 256.1.1.1 方法2： #!/bin/bash function check_ip(){ IP=$1 if [[ $IP =~ ^[0-9]{1,3}.[0-9]{1,3}.[0-9]{1,3}.[0-9]{1,3}$ ]]; then FIELD1=$(echo $IP|cut -d. -f1) FIELD2=$(echo $IP|cut -d. -f2) FIELD3=$(echo $IP|cut -d. -f3) FIELD4=$(echo $IP|cut -d. -f4) if [ $FIELD1 -le 255 -a $FIELD2 -le 255 -a $FIELD3 -le 255 -a $FIELD4 -le 255 ]; then echo "$IP available." else echo "$IP not available!" fi else echo "Format error!" fi } check_ip 192.168.1.1 check_ip 256.1.1.1 增加版：加个死循环，如果IP可用就退出，不可用提示继续输入，并使用awk判断。 #!/bin/bash function check_ip(){ local IP=$1 VALID_CHECK=$(echo $IP|awk -F. '$1<=255&&$2<=255&&$3<=255&&$4<=255{print "yes"}') if echo $IP|grep -E "^[0-9]{1,3}.[0-9]{1,3}.[0-9]{1,3}.[0-9]{1,3}$" >/dev/null; then if [ $VALID_CHECK == "yes" ]; then return 0 else echo "$IP not available!" return 1 fi else echo "Format error! Please input again." return 1 fi } while true; do read -p "Please enter IP: " IP check_ip $IP [ $? -eq 0 ] && break || continue done

13、判断用户输入的是否为数字

方法1： #!/bin/bash if [[ $1 =~ ^[0-9]+$ ]]; then echo "Is Number." else echo "No Number." fi 方法2： #!/bin/bash if [ $1 -gt 0 ] 2>/dev/null; then echo "Is Number." else echo "No Number." fi 方法3： #!/bin/bash echo $1 |awk '{print $0~/^[0-9]+$/?"Is Number.":"No Number."}' #三目运算符 12.14 找出包含关键字的文件 DIR=$1 KEY=$2 for FILE in $(find $DIR -type f); do if grep $KEY $FILE &>/dev/null; then echo "--> $FILE" fi done

14、给定目录找出包含关键字的文件

#!/bin/bash DIR=$1 KEY=$2 for FILE in $(find $DIR -type f); do if grep $KEY $FILE &>/dev/null; then echo "--> $FILE" fi done

15、监控目录，将新创建的文件名追加到日志中

场景：记录目录下文件操作。

需先安装inotify-tools软件包。

#!/bin/bash MON_DIR=/opt inotifywait -mq --format %f -e create $MON_DIR |
while read files; do echo $files >> test.log done

16、给用户提供多个网卡选择 场景：服务器多个网卡时，获取指定网卡，例如网卡流量

#!/bin/bash function local_nic() { local NUM ARRAY_LENGTH NUM=0 for NIC_NAME in $(ls /sys/class/net|grep -vE "lo|docker0"); do NIC_IP=$(ifconfig $NIC_NAME |awk -F'[: ]+' '/inet addr/{print $4}') if [ -n "$NIC_IP" ]; then NIC_IP_ARRAY[$NUM]="$NIC_NAME:$NIC_IP" #将网卡名和对应IP放到数组 let NUM++ fi done ARRAY_LENGTH=${#NIC_IP_ARRAY[]} if [ $ARRAY_LENGTH -eq 1 ]; then #如果数组里面只有一条记录说明就一个网卡 NIC=${NIC_IP_ARRAY[0]%:} return 0 elif [ $ARRAY_LENGTH -eq 0 ]; then #如果没有记录说明没有网卡 echo "No available network card!" exit 1 else #如果有多条记录则提醒输入选择 for NIC in ${NIC_IP_ARRAY[]}; do echo $NIC done while true; do read -p "Please enter local use to network card name: " INPUT_NIC_NAME COUNT=0 for NIC in ${NIC_IP_ARRAY[]}; do NIC_NAME=${NIC%:} if [ $NIC_NAME == "$INPUT_NIC_NAME" ]; then NIC=${NIC_IP_ARRAY[$COUNT]%:} return 0 else COUNT+=1 fi done echo "Not match! Please input again." done fi } local_nic

17、查看网卡实时流量

适用于CentOS6操作系统。

#!/bin/bash # Description: Only CentOS6 traffic_unit_conv() { local traffic=$1 if [ $traffic -gt 1024000 ]; then printf "%.1f%s" "$(($traffic/1024/1024))" "MB/s" elif [ $traffic -lt 1024000 ]; then printf "%.1f%s" "$(($traffic/1024))" "KB/s" fi } NIC=$1 echo -e " In ------ Out" while true; do OLD_IN=$(awk -F'[: ]+' '$0~"'$NIC'"{print $3}' /proc/net/dev) OLD_OUT=$(awk -F'[: ]+' '$0~"'$NIC'"{print $11}' /proc/net/dev) sleep 1 NEW_IN=$(awk -F'[: ]+' '$0~"'$NIC'"{print $3}' /proc/net/dev) NEW_OUT=$(awk -F'[: ]+' '$0~"'$NIC'"{print $11}' /proc/net/dev) IN=$(($NEW_IN-$OLD_IN)) OUT=$(($NEW_OUT-$OLD_OUT)) echo "$(traffic_unit_conv $IN) $(traffic_unit_conv $OUT)" sleep 1 done 使用：./traffic.sh eth0

18、MySQL数据库备份

#!/bin/bash DATE=$(date +%F_%H-%M-%S) HOST=192.168.1.120 DB=test USER=bak PASS=123456 MAIL="zhangsan@example.com lisi@example.com" BACKUP_DIR=/data/db_backup SQL_FILE=${DB}full$DATE.sql BAK_FILE=${DB}full$DATE.zip cd $BACKUP_DIR if mysqldump -h$HOST -u$USER -p$PASS --single-transaction --routines --triggers -B $DB > $SQL_FILE; then zip $BAK_FILE $SQL_FILE && rm -f $SQL_FILE if [ ! -s $BAK_FILE ]; then echo "$DATE 内容" | mail -s "主题" $MAIL fi else echo "$DATE 内容" | mail -s "主题" $MAIL fi find $BACKUP_DIR -name '*.zip' -ctime +14 -exec rm {} ; 19、Nginx服务管理脚本场景：使用源码包安装Nginx不含带服务管理脚本，也就是不能使用"service nginx start"或"/etc/init.d/nginx start"，所以写了以下的服务管理脚本。

#!/bin/bash # Description: Only support RedHat system . /etc/init.d/functions WORD_DIR=/usr/local/nginx DAEMON=$WORD_DIR/sbin/nginx CONF=$WORD_DIR/conf/nginx.conf NAME=nginx PID=$(awk -F'[; ]+' '/^[^#]/{if($0~/pid;/)print $2}' $CONF) if [ -z "$PID" ]; then PID=$WORD_DIR/logs/nginx.pid else PID=$WORD_DIR/$PID fi stop() { $DAEMON -s stop sleep 1 [ ! -f $PID ] && action " Stopping $NAME" /bin/true || action "* Stopping $NAME" /bin/false } start() { $DAEMON sleep 1 [ -f $PID ] && action "* Starting $NAME" /bin/true || action "* Starting $NAME" /bin/false } reload() { $DAEMON -s reload } test_config() { $DAEMON -t } case "$1" in start) if [ ! -f $PID ]; then start else echo "$NAME is running..." exit 0 fi ;; stop) if [ -f $PID ]; then stop else echo "$NAME not running!" exit 0 fi ;; restart) if [ ! -f $PID ]; then echo "$NAME not running!" start else stop start fi ;; reload) reload ;; testconfig) test_config ;; status) [ -f $PID ] && echo "$NAME is running..." || echo "$NAME not running!" ;; *) echo "Usage: $0 {start|stop|restart|reload|testconfig|status}" exit 3 ;; esac

20、用户根据菜单选择要连接的Linux主机 Linux主机SSH连接信息： **# cat host.txt Web 192.168.1.10 root 22 DB 192.168.1.11 root 22 内容格式：主机名 IP User Port

#!/bin/bash PS3="Please input number: " HOST_FILE=host.txt while true; do select NAME in $(awk '{print $1}' $HOST_FILE) quit; do [ ${NAME:=empty} == "quit" ] && exit 0 IP=$(awk -v NAME=${NAME} '$1==NAME{print $2}' $HOST_FILE) USER=$(awk -v NAME=${NAME} '$1==NAME{print $3}' $HOST_FILE) PORT=$(awk -v NAME=${NAME} '$1==NAME{print $4}' $HOST_FILE) if [ $IP ]; then echo "Name: $NAME, IP: $IP" ssh -o StrictHostKeyChecking=no -p $PORT -i id_rsa $USER@$IP # 密钥免交互登录 break else echo "Input error, Please enter again!" break fi done done