The three nodes memcached.service is active(running):

[root@ha-node3 my.cnf.d]# systemctl status   memcached.service
● memcached.service - memcached daemon
   Loaded: loaded (/usr/lib/systemd/system/memcached.service; enabled; vendor preset: disabled)
   Active: active (running) since Wed 2017-08-02 01:01:29 CST; 6min ago
 Main PID: 13329 (memcached)
   CGroup: /system.slice/memcached.service
           └─13329 /usr/bin/memcached -p 11211 -u memcached -m 1024 -c 8192 -l 127.0.0.1,::1,10.10.0.101 -t 4 -I 10m

Aug 02 01:01:29 ha-node3 systemd[1]: Started memcached daemon.
Aug 02 01:01:29 ha-node3 systemd[1]: Starting memcached daemon...

but in the haproxy web, the three nodes all is down.

EDIT-1

I found the Memcache_Servers configuration in the /etc/haproxy/haproxy.cfg the port is 22122(I write wrong), so I changed to 11211, and restart the haproxy, but still not work.

listen Memcache_Servers
  bind 45.117.40.168:11211
  balance roundrobin
  mode   tcp
  option  tcpka
  server ha-node1 ha-node1:11211 check inter 10s fastinter 2s downinter 2s rise 30 fall 3
  server ha-node2 ha-node2:11211 check inter 10s fastinter 2s downinter 2s rise 30 fall 3
  server ha-node3 ha-node3:11211 check inter 10s fastinter 2s downinter 2s rise 30 fall 3