TIME_WAIT 1979
FIN_WAIT1 3
FIN_WAIT2 24
ESTABLISHED 741
SYN_RECV 6
LAST_ACK 4

单跑 nginx，nginx 配置
worker_rlimit_nofile 200000;
worker_connections 102400;
multi_accept on;
use epoll;
keepalive_timeout 10;
client_header_timeout 10;
client_body_timeout 5;
reset_timedout_connection on;
send_timeout 10;
open_file_cache max=100000 inactive=20s;
open_file_cache_valid 30s;
open_file_cache_min_uses 2;
open_file_cache_errors on;
gzip on;


当前 sysctl.conf
net.ipv4.tcp_syncookies = 1
net.ipv4.tcp_tw_reuse = 1
net.ipv4.tcp_tw_recycle = 1
net.ipv4.tcp_fin_timeout = 6
net.ipv4.tcp_keepalive_probes = 3
net.ipv4.tcp_orphan_retries = 1
net.ipv4.tcp_max_tw_buckets = 6000
net.ipv4.ip_local_port_range = 1024 65000
net.core.somaxconn =262144
net.core.netdev_max_backlog = 262144
net.ipv4.tcp_max_orphans = 262144
net.ipv4.tcp_timestamps = 0
net.ipv4.tcp_synack_retries = 1
net.ipv4.tcp_syn_retries = 1
net.ipv4.tcp_fin_timeout = 1

找了好多资料都不见效，有没什么猛药？
才 2000 个不到而已， 完全不用理会, 这个对系统性能影响甚微， 不用太想着去优化这一块儿。
下面是我们的一个 web 服务.
ss -nat | awk '{a[$1]++}END{for (i in a) printf("%-10s %s\n",a[i],i)}' | sort -rnk 1
29405 TIME-WAIT
2168 ESTAB
31 FIN-WAIT-2
15 SYN-SENT
12 LISTEN
10 SYN-RECV
3 FIN-WAIT-1
1 State
1 CLOSING

原来如此啊，那就不管了。谢谢~

time_wait 是正常状态，适当限制下数量就好了
不要去搜索什么 tw 解决方法，你看你就配了个 tw_recycle 害自己