我们的数据库在高峰时段开始断开连接。大约有 3% 的连接断开，mysql 返回消息 "mysqli::mysqli(): (HY000/2003): Can't connect to MySQL server on '10.88.***' (99)" 。我已经调整了几个 mysql 和内核参数，但没有帮助：-/etc/sysctl.conf：
net.ipv4.tcp_max_tw_buckets = 524288 net.core.somaxconn = 2048 net.ipv4.ip_local_port_range = 1024 65000 net.ipv4.tcp_max_syn_backlog=30000 net.ipv4.tcp_syncookies = 1 net.ipv4.tcp_synack_retries = 2
-/etc/my.cnf：
open_files_limit = 65536 max_connections=3600
connect_timeout=60
wait_timeout=2400
back_log=4096
-/etc/security/limits.conf
mysql 软无文件 65536 mysql 硬无文件 65536 mysql 软 nproc 65536 mysql 硬 nproc 65536
我们的数据库通过一台数据库机器每秒处理 >40000 个查询和 >8000 个连接，没有分片和连接池。我错过了什么？有谁知道可能导致这个瓶颈的原因是什么？谢谢。
这是my.cnf中的内容：
[mysqld]
datadir=/var/lib/mysql
socket=/var/lib/mysql/mysql.sock
skip_name_resolve = off
open_files_limit = 65536
max_allowed_packet = 1073741824
expire_logs_days = 2
binlog_format = row
innodb_file_per_table = 1
innodb_flush_method=O_DIRECT
innodb_buffer_pool_instances = 16
innodb_buffer_pool_size = 43G
innodb_thread_concurrency = 0
log-bin=mysql-bin
server-id=1
innodb_flush_log_at_trx_commit=1
slave-skip-errors = 1062,1032
max_connections=3600
connect_timeout=60
wait_timeout=2400
back_log=4096
thread_cache_size=48
symbolic-links=0
user=mysql
[mysqld_safe]
log-error=/var/log/mysqld.log
pid-file=/var/run/mysqld/mysqld.pid
!includedir /etc/my.cnf.d