編寫Shell過程中注意事項(xiàng)：
開頭加解釋器：#!/bin/bash
語法縮進(jìn)焚挠，使用四個(gè)空格；多加注釋說明湾笛。
命名建議規(guī)則：變量名大寫饮怯、局部變量小寫，函數(shù)名小寫嚎研，名字體現(xiàn)出實(shí)際作用蓖墅。
默認(rèn)變量是全局的，在函數(shù)中變量local指定為局部變量，避免污染其他作用域论矾。
有兩個(gè)命令能幫助我調(diào)試腳本：set -e 遇到執(zhí)行非0時(shí)退出腳本教翩，set-x 打印執(zhí)行過程。
寫腳本一定先測試再到生產(chǎn)上贪壳。

1饱亿、獲取隨機(jī)字符串或數(shù)字

獲取隨機(jī)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

獲取隨機(jī)8位數(shù)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效驗(yàn)和統(tǒng)計(jì)字節(jié)

2、定義一個(gè)顏色輸出字符串函數(shù)

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關(guān)鍵字定義一個(gè)函數(shù)寥袭，可加或不加。

3关霸、批量創(chuàng)建用戶

#!/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
}

# 如果用戶文件存在并且大小大于0就備份
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传黄、檢查軟件包是否安裝

#!/bin/bash
if rpm -q sysstat &>/dev/null; then
    echo "sysstat is already installed."
else
    echo "sysstat is not installed!"
fi

5、檢查服務(wù)狀態(tài)

#!/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队寇、檢查主機(jī)存活狀態(tài)

方法1：將錯(cuò)誤IP放到數(shù)組里面判斷是否ping失敗三次
#!/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：將錯(cuò)誤次數(shù)放到FAIL_COUNT變量里面判斷是否ping失敗三次
#!/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循環(huán)將ping通就跳出循環(huán)繼續(xù)膘掰，如果不跳出就會(huì)走到打印ping失敗
#!/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、監(jiān)控CPU佳遣、內(nèi)存和硬盤利用率

#!/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识埋、批量主機(jī)磁盤利用率監(jiān)控

前提監(jiān)控端和被監(jiān)控端SSH免交互登錄或者密鑰登錄。
寫一個(gè)配置文件保存被監(jiān)控主機(jī)SSH連接信息零渐，文件內(nèi)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%=*} ##從右到左窒舟，非貪婪匹配，匹配到的刪除
        USE_RATE=${USE_RATE#*=} ##從左到右诵盼，非貪婪匹配惠豺，匹配到的刪除
        if [ $USE_RATE -ge 10 ];then
        echo "Warning: $IP $PART_NAME Partition usage $USE_RATE%!"
        fi
    done
done

9、檢查網(wǎng)站可用性

#!/bin/bash

#--------------------
#1）檢查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超時(shí)時(shí)間风宁，--tries嘗試1次洁墙，--spider爬蟲模式
        echo "Warning: $1 Access failure!"
    fi
}

#check_url www.baidu.com
#check_url_2 www.aaaa.com

#2）判斷三次URL可用性
#思路與上面檢查主機(jī)存活狀態(tài)一樣。

#---------------------------------

URL_LIST="www.baidu.com www.agasgf.com"

#------
#方法1：利用循環(huán)技巧戒财，如果成功就跳出當(dāng)前循環(huán)热监，否則執(zhí)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：錯(cuò)誤次數(shù)保存到變量

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：錯(cuò)誤次數(shù)保存到數(shù)組
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、檢查MySQL主從同步狀態(tài)

#!/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去除冒號(hào)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