nginx防止DDOS攻击配置（2）

我们用的高防服务器只防流量攻击不防CC，现在的攻击多数都是混合型的，而且CC攻击很多，防CC只能自己搞了，按照第一篇的配置，在实际的使用中效果并不理想。限制每秒钟的请求数和ip连接数，属于杀敌一千自损八百的做法。是可以防小规模的cc攻击，但是不够灵活，限制严了，误杀率很大；限制少了，当攻击的ip量达到一定规模的时候，传递到后端的请求还是非常多，导致php撑不住挂掉。这里在上一篇的基础上详细介绍一下我在生产中使用的配置。

1.修改最大连接数

最大连接数不够的话，nginx日志中会出现"Too many open files"错误。系统默认的1024太小了，在/etc/security/limits.conf中增加：

* soft nproc 65535
* hard nproc 65535
* soft nofile 65535
* hard nofile 65535

 

2.sysctl优化

这个比较考验内功，暂时还没太多研究，从网上搬运了一份，以后在慢慢学习：

###
### GENERAL SYSTEM SECURITY OPTIONS ###
###

# Controls the System Request debugging functionality of the kernel
kernel.sysrq = 0

# Controls whether core dumps will append the PID to the core filename.
# Useful for debugging multi-threaded applications.
kernel.core_uses_pid = 1

#Allow for more PIDs
kernel.pid_max = 65535

# The contents of /proc/<pid>/maps and smaps files are only visible to
# readers that are allowed to ptrace() the process
kernel.maps_protect = 1

#Enable ExecShield protection
kernel.exec-shield = 1
kernel.randomize_va_space = 2

# Controls the maximum size of a message, in bytes
kernel.msgmnb = 65535

# Controls the default maxmimum size of a mesage queue
kernel.msgmax = 65535

# Restrict core dumps
fs.suid_dumpable = 0

# Hide exposed kernel pointers
kernel.kptr_restrict = 1

###
### IMPROVE SYSTEM MEMORY MANAGEMENT ###
###

# Increase size of file handles and inode cache
fs.file-max = 209708

# Do less swapping
vm.swappiness = 30
vm.dirty_ratio = 30
vm.dirty_background_ratio = 5

# specifies the minimum virtual address that a process is allowed to mmap
vm.mmap_min_addr = 4096

# 50% overcommitment of available memory
vm.overcommit_ratio = 50
vm.overcommit_memory = 0

# Set maximum amount of memory allocated to shm to 256MB
kernel.shmmax = 268435456
kernel.shmall = 268435456

# Keep at least 64MB of free RAM space available
vm.min_free_kbytes = 65535

###
### GENERAL NETWORK SECURITY OPTIONS ###
###

#Prevent SYN attack, enable SYNcookies (they will kick-in when the max_syn_backlog reached)
net.ipv4.tcp_syncookies = 1
net.ipv4.tcp_syn_retries = 2
net.ipv4.tcp_synack_retries = 2
net.ipv4.tcp_max_syn_backlog = 4096

# Disables packet forwarding
net.ipv4.ip_forward = 0
net.ipv4.conf.all.forwarding = 0
net.ipv4.conf.default.forwarding = 0
net.ipv6.conf.all.forwarding = 0
net.ipv6.conf.default.forwarding = 0

# Disables IP source routing
net.ipv4.conf.all.send_redirects = 0
net.ipv4.conf.default.send_redirects = 0
net.ipv4.conf.all.accept_source_route = 0
net.ipv4.conf.default.accept_source_route = 0
net.ipv6.conf.all.accept_source_route = 0
net.ipv6.conf.default.accept_source_route = 0

# Enable IP spoofing protection, turn on source route verification
net.ipv4.conf.all.rp_filter = 1
net.ipv4.conf.default.rp_filter = 1

# Disable ICMP Redirect Acceptance
net.ipv4.conf.all.accept_redirects = 0
net.ipv4.conf.default.accept_redirects = 0
net.ipv4.conf.all.secure_redirects = 0
net.ipv4.conf.default.secure_redirects = 0
net.ipv6.conf.all.accept_redirects = 0
net.ipv6.conf.default.accept_redirects = 0

# Enable Log Spoofed Packets, Source Routed Packets, Redirect Packets
net.ipv4.conf.all.log_martians = 1
net.ipv4.conf.default.log_martians = 1

# Decrease the time default value for tcp_fin_timeout connection
net.ipv4.tcp_fin_timeout = 7

# Decrease the time default value for connections to keep alive
net.ipv4.tcp_keepalive_time = 300
net.ipv4.tcp_keepalive_probes = 5
net.ipv4.tcp_keepalive_intvl = 15

# Don't relay bootp
net.ipv4.conf.all.bootp_relay = 0

# Don't proxy arp for anyone
net.ipv4.conf.all.proxy_arp = 0

# Turn on the tcp_timestamps, accurate timestamp make TCP congestion control algorithms work better
net.ipv4.tcp_timestamps = 1

# Don't ignore directed pings
net.ipv4.icmp_echo_ignore_all = 0

# Enable ignoring broadcasts request
net.ipv4.icmp_echo_ignore_broadcasts = 1

# Enable bad error message Protection
net.ipv4.icmp_ignore_bogus_error_responses = 1

# Allowed local port range
net.ipv4.ip_local_port_range = 16384 65535

# Enable a fix for RFC1337 - time-wait assassination hazards in TCP
net.ipv4.tcp_rfc1337 = 1

# Do not auto-configure IPv6
net.ipv6.conf.all.autoconf=0
net.ipv6.conf.all.accept_ra=0
net.ipv6.conf.default.autoconf=0
net.ipv6.conf.default.accept_ra=0
net.ipv6.conf.eth0.autoconf=0
net.ipv6.conf.eth0.accept_ra=0

###
### TUNING NETWORK PERFORMANCE ###
###

# For high-bandwidth low-latency networks, use 'htcp' congestion control
# Do a 'modprobe tcp_htcp' first
net.ipv4.tcp_congestion_control = htcp

# For servers with tcp-heavy workloads, enable 'fq' queue management scheduler (kernel > 3.12)
net.core.default_qdisc = fq

# Turn on the tcp_window_scaling
net.ipv4.tcp_window_scaling = 1

# Increase the read-buffer space allocatable
net.ipv4.tcp_rmem = 8192 87380 16777216
net.ipv4.udp_rmem_min = 16384
net.core.rmem_default = 262144
net.core.rmem_max = 16777216

# Increase the write-buffer-space allocatable
net.ipv4.tcp_wmem = 8192 65536 16777216
net.ipv4.udp_wmem_min = 16384
net.core.wmem_default = 262144
net.core.wmem_max = 16777216

# Increase number of incoming connections
net.core.somaxconn = 32768

# Increase number of incoming connections backlog
net.core.netdev_max_backlog = 16384
net.core.dev_weight = 64

# Increase the maximum amount of option memory buffers
net.core.optmem_max = 65535

# Increase the tcp-time-wait buckets pool size to prevent simple DOS attacks
net.ipv4.tcp_max_tw_buckets = 1440000

# try to reuse time-wait connections, but don't recycle them (recycle can break clients behind NAT)
net.ipv4.tcp_tw_recycle = 0
net.ipv4.tcp_tw_reuse = 1

# Limit number of orphans, each orphan can eat up to 16M (max wmem) of unswappable memory
net.ipv4.tcp_max_orphans = 16384
net.ipv4.tcp_orphan_retries = 0

# Increase the maximum memory used to reassemble IP fragments
net.ipv4.ipfrag_high_thresh = 512000
net.ipv4.ipfrag_low_thresh = 446464

# don't cache ssthresh from previous connection
net.ipv4.tcp_no_metrics_save = 1
net.ipv4.tcp_moderate_rcvbuf = 1

# Increase size of RPC datagram queue length
net.unix.max_dgram_qlen = 50

# Don't allow the arp table to become bigger than this
net.ipv4.neigh.default.gc_thresh3 = 2048

# Tell the gc when to become aggressive with arp table cleaning.
# Adjust this based on size of the LAN. 1024 is suitable for most /24 networks
net.ipv4.neigh.default.gc_thresh2 = 1024

# Adjust where the gc will leave arp table alone - set to 32.
net.ipv4.neigh.default.gc_thresh1 = 32

# Adjust to arp table gc to clean-up more often
net.ipv4.neigh.default.gc_interval = 30

# Increase TCP queue length
net.ipv4.neigh.default.proxy_qlen = 96
net.ipv4.neigh.default.unres_qlen = 6

# Enable Explicit Congestion Notification (RFC 3168), disable it if it doesn't work for you
net.ipv4.tcp_ecn = 1
net.ipv4.tcp_reordering = 3

# How many times to retry killing an alive TCP connection
net.ipv4.tcp_retries2 = 15
net.ipv4.tcp_retries1 = 3

# Avoid falling back to slow start after a connection goes idle
# keeps our cwnd large with the keep alive connections (kernel > 3.6)
net.ipv4.tcp_slow_start_after_idle = 0

# Allow the TCP fastopen flag to be used, beware some firewalls do not like TFO! (kernel > 3.7)
net.ipv4.tcp_fastopen = 3

# This will enusre that immediatly subsequent connections use the new values
net.ipv4.route.flush = 1
net.ipv6.route.flush = 1

    # 具体值根据服务器硬件计算，配置不当可能导致过早关闭TCP连接
    # net.netfilter.nf_conntrack_max = 1048576
    # net.netfilter.nf_conntrack_tcp_timeout_established = 1200

 

3.nginx和lua防御cc攻击

参考了opencdn团队的做法，通过nginx和lua来防御cc，原理见下面的参考文章，效果很棒
nginx需要编译lua模块，见：http://www.52os.net/articles/nginx-install-lua-and-lua-based-waf.html
在nginx.conf的http段中加入：

limit_req_zone $cookie_token zone=session_limit:20m rate=1r/s;
limit_req_zone $binary_remote_addr $uri zone=auth_limit:20m rate=1r/m;

 

在server段中加入：

location  / {
    limit_req zone=session_limit burst=5;
    rewrite_by_lua '
        local random = ngx.var.cookie_random
        if (random == nil) then
            return ngx.redirect("/auth?url=" .. ngx.var.request_uri)
        end
        local token = ngx.md5("opencdn" .. ngx.var.remote_addr .. random)
        if (ngx.var.cookie_token ~= token) then
            return ngx.redirect("/auth?url=".. ngx.var.request_uri)
        end
    ';
            proxy_redirect         off;
            proxy_set_header Host $host;
            proxy_set_header X-Real-IP $remote_addr;
            proxy_set_header  X-Forwarded-For $proxy_add_x_forwarded_for;
                            proxy_pass http://backend;
    }

location /auth {
        limit_req zone=auth_limit burst=1; 
        if ($arg_url = "") {
            return 403;
        }     
        access_by_lua '
            local random = math.random(9999)
            local token = ngx.md5("opencdn" .. ngx.var.remote_addr .. random)
            if (ngx.var.cookie_token ~= token) then
                ngx.header["Set-Cookie"] = {"token=" .. token, "random=" .. random}
                return ngx.redirect(ngx.var.arg_url)
            end
        ';
    }

 

这个方法会造成搜索引擎蜘蛛一直处在302中，不利于seo，可以通过智能dns来为蜘蛛指定单独的线路。和被打到宕机比起来，seo几乎可以无视

4.iptables限制tcp连接和频率

通过上述的配置，cc攻击流量就处在302中了，但是保险起见对ip进行连接频率和并发限制，限制单ip连接和频率，在/etc/sysconfig/iptables中加入：

#单个IP在60秒内只允许新建20个连接
-A INPUT -i eth0 -p tcp -m tcp --dport 80 -m state --state NEW -m recent --update --seconds 60 --hitcount 20 --name DEFAULT --rsource -j DROP
-A INPUT -i eth0 -p tcp -m tcp --dport 80 -m state --state NEW -m recent --set --name DEFAULT --rsource

#控制单个IP的最大并发连接数为20
-I INPUT -p tcp --dport 80 -m connlimit  --connlimit-above 20 -j REJECT  

#每个IP最多20个初始连接
-A INPUT -p tcp --syn -m connlimit --connlimit-above 20 -j DROP

 

这样配置后，单个ip能建立的连接不是只有20个，具体能建立多少连接还要看tcp的超时设置，但单个ip不会建立大量的tcp连接消耗系统资源

5.使用fail2ban屏蔽攻击ip

通过上面设置nginx后，cc攻击请求变为302，直接由性能强劲的nginx处理。但是攻击ip还是在不停的访问服务器，消耗着服务器的资源，一旦达到一定数量级，也会严重影响到系统的性能，所以通过分析nginx的访问日志彻底屏蔽这些ip

安装fail2ban并升级iptables至最新：

yum install -y epel-release 
yum install -y fail2ban iptables python-inotify

 

先看下我nginx的访问日志格式 ：

log_format  main  '$remote_addr $status $request $body_bytes_sent [$time_local] 

 

攻击日志的效果：

159.138.198.106 302 GET /auth?url=/ HTTP/1.1 235 [17/Oct/2015:21:06:22 +0800]  Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_2) AppleWebKit/600.4.10 (KHTML, like Gecko) Version/8.0.4 Safari/600.4.10 -  - - - - -

 

cc攻击的ip会经过nginx和lua处理后，访问状态变为302，根据nginx的访问日志格式，过滤这些ip和302状态，加入黑名单即可。
新建fail2ban的规则文件/etc/fail2ban/filter.d/nginx-302-cc.conf，内容为：

[Definition]
failregex = <HOST> 302.(GET|POST)*.*HTTP/1.*$
ignoreregex =

 

新建fail2ban的配置文件/etc/fail2ban/jail.d/nginx-anti-302.conf,内容为：

[nginx-anti-302]
enabled = true
port = http
filter = nginx-302-cc
logpath = /opt/nginx/logs/52os.net/access_web.log
findtime = 60     #检测60秒内的日志
bantime = 900     #屏蔽ip的时间为15分钟
maxretry = 90      #达到90次就屏蔽
    backend = pyinotify #使用pyinotify检测日志变化，被攻击时检测海量日志时性能最好
    banaction = iptables-ipset-proto6-allports  #使用ipset屏蔽IP，使用iptables屏蔽大量IP需要时非常慢，并且资源占用非常大

 

访客访问一次网站会产生2次302，这样配置后60秒内允许45次正常的访问，基本上不会屏蔽正常访客

如果使用iptables屏蔽，需注意fail2ban-0.9.3在执行iptables命令时，会加上了-w参数防止规则冲突，iptables-1.4.20以后才有这个参数，而CentOS 6 的iptables是1.4.7,导致iptables规则添加失败，解决方法是删除iptables-common.conf中的<lockingopt>：

sed -i 's/iptables = iptables <lockingopt>/iptables = iptables/' /etc/fail2ban/action.d/iptables-common.conf

 

service fail2ban start    

 

通过以上设置实现了：

1. 增大了系统的吞吐量
2. cc流量直接由高性能的nginx返回302，不会proxy_pass到后端的服务器或应用
3. 限制单个ip建立的tcp连接数量和频率
4. 恶意攻击ip实时黑名单

实际使用效果非常不错。面对专业的ddos玩家，在好的系统终有薄弱的环节，攻击达到一定规模，基本上是不可防的，但是可以尽量利用有限的资源和攻击者周旋，提高攻击的门槛。当然，要是烧的起钱，这篇文章可以无视