环境
- EMQX 版本：4.4.11
- 操作系统版本：Centos7.9 ，虚拟机上 zip 安装方式启动
重现此问题的步骤
- 两台虚拟机+Haproxy 部署，配置如下（参考与官方配置，截取部分），集群部署好之后，管理端登录正常
##----------------------------------------------------------------
## global 2021/04/05
##----------------------------------------------------------------
global
log stdout format raw daemon debug
# Replace 1024000 with deployment connections
maxconn 102400
nbproc 1
nbthread 2
cpu-map auto:1/1-2 0-1
tune.ssl.default-dh-param 2048
ssl-default-bind-ciphers ECDHE-ECDSA-CHACHA20-POLY1305:ECDHE-RSA-CHACHA20-POLY1305:ECDHE-RSA-AES128-GCM-SHA256:ECDHE-ECDSA-AES128-GCM-SHA256:ECDHE-RSA-AES256-GCM-SHA384:ECDHE-ECDSA-AES256-GCM-SHA384:DHE-RSA-AES128-GCM-SHA256:DHE-DSS-AES128-GCM-SHA256:kEDH+AESGCM:ECDHE-RSA-AES128-SHA256:ECDHE-ECDSA-AES128-SHA256:ECDHE-RSA-AES128-SHA:ECDHE-ECDSA-AES128-SHA:ECDHE-RSA-AES256-SHA384:ECDHE-ECDSA-AES256-SHA384:ECDHE-RSA-AES256-SHA:ECDHE-ECDSA-AES256-SHA:DHE-RSA-AES128-SHA256:DHE-RSA-AES128-SHA:DHE-DSS-AES128-SHA256:DHE-RSA-AES256-SHA256:DHE-DSS-AES256-SHA:DHE-RSA-AES256-SHA:ECDHE-RSA-DES-CBC3-SHA:ECDHE-ECDSA-DES-CBC3-SHA:EDH-RSA-DES-CBC3-SHA:AES128-GCM-SHA256:AES256-GCM-SHA384:AES128-SHA256:AES256-SHA256:AES128-SHA:AES256-SHA:AES:DES-CBC3-SHA:HIGH:SEED:!aNULL:!eNULL:!EXPORT:!DES:!RC4:!MD5:!PSK:!RSAPSK:!aDH:!aECDH:!EDH-DSS-DES-CBC3-SHA:!KRB5-DES-CBC3-SHA:!SRP
# Enable the HAProxy Runtime API
# e.g. echo "show table emqx_tcp_back" | sudo socat stdio tcp4-connect:172.100.239.4:9999
stats socket :9999 level admin expose-fd listeners
##----------------------------------------------------------------
## defaults
##----------------------------------------------------------------
defaults
log global
mode tcp
option tcplog
# Replace 1024000 with deployment connections
maxconn 102400
timeout connect 30000
timeout client 600s
timeout server 600s
##----------------------------------------------------------------
## API
##----------------------------------------------------------------
frontend emqx_mgmt
mode tcp
option tcplog
bind *:28083
default_backend emqx_mgmt_back
frontend emqx_dashboard
mode tcp
option tcplog
bind *:28083
default_backend emqx_dashboard_back
backend emqx_mgmt_back
mode http
# balance static-rr
server emqx1 192.168.181.83:18083
server emqx2 192.168.181.190:18083
backend emqx_dashboard_back
mode http
# balance static-rr
server emqx1 192.168.181.83:18083
server emqx2 192.168.181.190:18083
##----------------------------------------------------------------
## public
##----------------------------------------------------------------
frontend emqx_tcp
mode tcp
option tcplog
bind *:2883
# Reject connections that have an invalid MQTT packet
# tcp-request content reject unless { req.payload(0,0), mqtt_is_valid }
default_backend emqx_tcp_back
backend emqx_tcp_back
mode tcp
# Create a stick table for session persistence
stick-table type string len 32 size 100k expire 30m
# Use ClientID / client_identifier as persistence key
stick on req.payload(0,0),mqtt_field_value(connect,client_identifier)
server emqx1 192.168.181.83:1883 check-send-proxy send-proxy-v2
server emqx2 192.168.181.190:1883 check-send-proxy send-proxy-v2
- MQTTX 进行连接测试，第一次连不上，再次点击连接可成功，断开后又连接不上(135连接不上，246可以连接上)，能连上的都集中在节点2
- 节点情况：(无相关连接错误日志)
- 节点1:
+节点2:
3. 测试连接半个小时左右，集群出现异常，连接不上，查看后有一个节点变成未启动了，还在的那台查看集群状态变成只有一个了，stop 那边为空，管理端也登不上，返回错误501
- 节点情况：(集群异常无相关日志)
- 节点1:
+节点2:
问题
- 135 连接失败，246成功这个是否配置哪里写的不对呢？我看emq日志处无相关连接失败的错误
- 在一段时间之后，节点1会因为连接不上而导致中断？日志我看了也没有报错，集群异常只能重启两个节点，这个是否和问题1有关系？
