Nginx+PHP-fpm environment performance parameter optimization method

1. The bigger the worker_processes, the better (the performance will not increase significantly after a certain number) 2.worker_cpu_affinity divides all cpu equally into worker_processes Than each worker_processes The performance of cross-cpu allocation is better; regardless of the execution of PHP, the test result is that the number of worker_processes is 2 times the number of cpu cores, and the optimal performance is 3.Unix domain socket (shared memory method) has better performance than tcp network port configuration Regardless of the backlog, the request speed has jumped by an order of magnitude, but but the error rate exceeds 50% With the addition of backlog, performance is improved by about 10% 4. Adjust the backlog of nginx, php-fpm and the kernel, connect() to unix:/tmp/php-fpm.socket failed (11: Resource temporarily unavailable) while connecting to upstream error returns will be reduced nginx: The server block of the configuration file listen 80 default backlog=1024; php-fpm: configuration file listen.backlog = 2048 kernel parameters: /etc/sysctl.conf, cannot be lower than the above configuration net.ipv4.tcp_max_syn_backlog = 4096 net.core.netdev_max_backlog = 4096 5. Adding a master instance of php-fpm on a single server will increase fpm’s processing capabilities and reduce the chance of error returns. Multi-instance startup method, using multiple configuration files: /usr/local/php/sbin/php-fpm…