nginx+php-fpm性能优化原则
无    26    0    0
libi
1.worker_processes 越大越好(一定数量后性能增加不明显)
2.worker_cpu_affinity 所有cpu平分worker_processes 要比每个worker_processes 都跨cpu分配性能要好;不考虑php的执行,测试结果worker_processes数量是cpu核数的2倍性能最优
3.unix domain socket(共享内存的方式)要比tcp网络端口配置性能要好
不考虑backlog,请求速度有量级的飞跃, 但错误率超过50%
加上backlog, 性能有10%左右提升
4.调整nginx、php-fpm和内核的backlog(积压),connect() to unix:/tmp/php-fpm.socket failed (11: Resource temporarily unavailable) while connecting to upstream错误的返回会减少
nginx:
配置文件的server块
listen 80 default backlog=1024;
php-fpm:
配置文件的
listen.backlog = 2048
kernel参数:
/etc/sysctl.conf,不能低于上面的配置
net.ipv4.tcp_max_syn_backlog = 4096
net.core.netdev_max_backlog = 4096
5.增加单台服务器上的php-fpm的master实例,会增加fpm的处理能力,也能减少报错返回的几率
多实例启动方法,使用多个配置文件:
/usr/local/php/sbin/php-fpm -y /usr/local/php/etc/php-fpm.conf &
/usr/local/php/sbin/php-fpm -y /usr/local/php/etc/php-fpm1.conf &
nginx的fastcgi配置
nginx的fastcgi配置
    upstream phpbackend {
#      server   127.0.0.1:9000 weight=100 max_fails=10 fail_timeout=30;
#      server   127.0.0.1:9001 weight=100 max_fails=10 fail_timeout=30;
#      server   127.0.0.1:9002 weight=100 max_fails=10 fail_timeout=30;
#      server   127.0.0.1:9003 weight=100 max_fails=10 fail_timeout=30;
      server   unix:/var/www/php-fpm.sock weight=100 max_fails=10 fail_timeout=30;
      server   unix:/var/www/php-fpm1.sock weight=100 max_fails=10 fail_timeout=30;
      server   unix:/var/www/php-fpm2.sock weight=100 max_fails=10 fail_timeout=30;
      server   unix:/var/www/php-fpm3.sock weight=100 max_fails=10 fail_timeout=30;
#      server   unix:/var/www/php-fpm4.sock weight=100 max_fails=10 fail_timeout=30;
#      server   unix:/var/www/php-fpm5.sock weight=100 max_fails=10 fail_timeout=30;
#      server   unix:/var/www/php-fpm6.sock weight=100 max_fails=10 fail_timeout=30;
#      server   unix:/var/www/php-fpm7.sock weight=100 max_fails=10 fail_timeout=30;
    }

        location ~ \.php* {
            fastcgi_pass   phpbackend;
#           fastcgi_pass   unix:/var/www/php-fpm.sock;
            fastcgi_index index.php;
       ..........
       }
6.测试环境和结果
内存2G
swap2G
cpu 2核 Intel(R) Xeon(R) CPU E5405  @ 2.00GHz
采用ab远程访问测试,测试程序为php的字符串处理程序
1)在开4个php-fpm实例,nginx 8个worker_processes 每个cpu4个worker_processes ,backlog为1024,php的backlog为2048,内核backlog为4096,采用unix domain socket连接的情况下,其他保持参数不变
性能和错误率较为平衡,可接受,超过4个fpm实例,性能开始下降,错误率并没有明显下降
结论是fpm实例数,worker_processes数和cpu保持倍数关系,性能较高
影响性能和报错的参数为
php-fpm实例, nginx worker_processes数量,fpm的max_request,php的backlog,unix domain socket
10W请求,500并发无报错,1000并发报错率为0.9%
500并发:
Time taken for tests:   25 seconds avg.
Complete requests:      100000
Failed requests:        0
Write errors:           0
Requests per second:    4000 [#/sec] (mean) avg.
Time per request:       122.313 [ms] (mean)
Time per request:       0.245 [ms] (mean, across all concurrent requests)
Transfer rate:          800 [Kbytes/sec] received avg.
1000并发:
Time taken for tests:   25 seconds avg.
Complete requests:      100000
Failed requests:        524
(Connect: 0, Length: 524, Exceptions: 0)
Write errors:           0
Non-2xx responses:      524
Requests per second:    3903.25 [#/sec] (mean)
Time per request:       256.197 [ms] (mean)
Time per request:       0.256 [ms] (mean, across all concurrent requests)
Transfer rate:          772.37 [Kbytes/sec] received
2)在其他参数不变,unix domain socket换为tcp网络端口连接,结果如下
500并发:
Concurrency Level:      500
Time taken for tests:   26.934431 seconds
Complete requests:      100000
Failed requests:        0
Write errors:           0
Requests per second:    3712.72 [#/sec] (mean)
Time per request:       134.672 [ms] (mean)
Time per request:       0.269 [ms] (mean, across all concurrent requests)
Transfer rate:          732.37 [Kbytes/sec] received
1000并发:
Concurrency Level:      1000
Time taken for tests:   28.385349 seconds
Complete requests:      100000
Failed requests:        0
Write errors:           0
Requests per second:    3522.94 [#/sec] (mean)
Time per request:       283.853 [ms] (mean)
Time per request:       0.284 [ms] (mean, across all concurrent requests)
Transfer rate:          694.94 [Kbytes/sec] received
与1)比较,有大约10%的性能下降
7. 5.16调整fpm的max_request参数为1000,并发1000报错返回降到200个以下,
Transfer rate在800左右

文档导航