我的应用程序在 Amazon EC2 t2.small 实例上提供服务。
当使用ab命令测试性能时。
ab -n 3000 -c 100 mydomain.com
HTTP
Finished 3000 requests
Server Software: nginx/1.8.1
Server Hostname: www.mydomain.com
Server Port: 80
Document Path: /
Document Length: 184 bytes
Concurrency Level: 100
Time taken for tests: 3.201 seconds
Complete requests: 3000
Failed requests: 0
Non-2xx responses: 3000
Total transferred: 1401000 bytes
HTML transferred: 552000 bytes
Requests per second: 937.09 [#/sec] (mean)
Time per request: 106.714 [ms] (mean)
Time per request: 1.067 [ms] (mean, across all concurrent requests)
Transfer rate: 427.36 [Kbytes/sec] received
Connection Times (ms)
min mean[+/-sd] median max
Connect: 15 43 50.0 33 783
Processing: 19 53 79.2 37 1437
Waiting: 17 47 75.1 34 1437
Total: 41 96 93.3 71 1463
Percentage of the requests served within a certain time (ms)
50% 71
66% 79
75% 85
80% 91
90% 160
95% 175
98% 478
99% 573
100% 1463 (longest request)
HTTPS
Finished 3000 requests
Server Software: nginx/1.8.1
Server Hostname: www.mydomain.com
Server Port: 443
SSL/TLS Protocol: TLSv1.2,ECDHE-RSA-AES256-GCM-SHA384,1024,256
Document Path: /
Document Length: 212 bytes
Concurrency Level: 100
Time taken for tests: 23.034 seconds
Complete requests: 3000
Failed requests: 124
(Connect: 0, Receive: 0, Length: 124, Exceptions: 0)
Non-2xx responses: 2876
Total transferred: 21357330 bytes
HTML transferred: 20773030 bytes
Requests per second: 130.24 [#/sec] (mean)
Time per request: 767.790 [ms] (mean)
Time per request: 7.678 [ms] (mean, across all concurrent requests)
Transfer rate: 905.49 [Kbytes/sec] received
Connection Times (ms)
min mean[+/-sd] median max
Connect: 105 521 170.7 584 892
Processing: 20 228 264.1 153 2629
Waiting: 17 149 131.1 111 772
Total: 201 749 214.4 714 3124
Percentage of the requests served within a certain time (ms)
50% 714
66% 740
75% 745
80% 755
90% 798
95% 903
98% 1484
99% 2002
100% 3124 (longest request)
我的 nginx.conf 的相关部分：
user ec2-user ec2-user;
worker_processes 4;
error_log /home/ec2-user/.log/error.log error;
pid /var/run/nginx.pid;
#timer_resolution 500ms;
worker_rlimit_nofile 8192;
events {
worker_connections 4096;
}
http {
include /etc/nginx/mime.types;
default_type application/octet-stream;
autoindex off;
index index.php index.html index.htm;
sendfile on;
tcp_nopush on;
tcp_nodelay off;
keepalive_timeout 60;
keepalive_requests 10;
client_max_body_size 20M;
client_body_timeout 60;
client_body_buffer_size 10M;
client_header_timeout 60;
client_header_buffer_size 1k;
#server_names_hash_max_size 512;
server_names_hash_bucket_size 128;
gzip on;
gzip_disable "msie6";
gzip_vary on;
gzip_proxied any;
gzip_comp_level 6;
gzip_buffers 16 8k;
gzip_http_version 1.1;
gzip_min_length 1000;
gzip_types text/plain text/css application/json application/x-javascript text/xml application/xml application/rss+xml text/javascript image/svg+xml application/vnd.ms-fontobject application/x-font-ttf font/opentype;
}
和 mydomain.conf
ssl on;
ssl_session_timeout 5m;
ssl_protocols TLSv1 TLSv1.1 TLSv1.2;
ssl_ciphers ECDHE-RSA-AES256-GCM-SHA384:ECDHE-RSA-AES128-GCM-SHA256:DHE-RSA-AES256-GCM-SHA384:DHE-RSA-AES128-GCM-SHA256:ECDHE-RSA-AES256-SHA384:ECDHE-RSA-AES128-SHA256:ECDHE-RSA-AES256-SHA:ECDHE-RSA-AES128-SHA:DHE-RSA-AES256-SHA256:DHE-RSA-AES128-SHA256:DHE-RSA-AES256-SHA:DHE-RSA-AES128-SHA:ECDHE-RSA-DES-CBC3-SHA:EDH-RSA-DES-CBC3-SHA:AES256-GCM-SHA384:AES128-GCM-SHA256:AES256-SHA256:AES128-SHA256:AES256-SHA:AES128-SHA:DES-CBC3-SHA:HIGH:!aNULL:!eNULL:!EXPORT:!DES:!MD5:!PSK:!RC4;
ssl_prefer_server_ciphers on;
ssl_dhparam /home/ec2-user/.nginx/dhparam.pem;
ssl_stapling on;
ssl_stapling_verify on;
resolver 8.8.4.4 8.8.8.8 valid=300s;
resolver_timeout 10s;
add_header Strict-Transport-Security max-age=63072000;
add_header X-Content-Type-Options nosniff;
答案1
我最好的猜测是测试站点和服务器之间的延迟是一个重要因素。 SSL 需要多次往返才能建立 SSL 连接，而 Apache Bench 相当简单，我认为它不会重复使用连接。我怀疑如果你从同一可用区的现货实例进行测试，SSL 统计数据会上升，仅仅是因为延迟。
其背后是一般开销。SSL 需要更多资源来设置，而且您在一个小实例上运行 100 个连接。
您可以查看我在 t2.micro 上使用 Wordpress 和 Nginx 进行的一些基准测试这里。最有趣的测量是提供静态 html 文件，这是从服务器本身测试的，使用 http 和 https。由于在同一台机器上，因此没有延迟。以毫秒为单位的时间是总事务时间，我想，我之前做过测试。
HTTP: 440tps, 10ms
HTPS: 166tps, 145ms
我很想知道其他人能想出什么，因为我认为我也没有完全解决这个问题。
Nginx fast_cgi 缓存对 Wordpress 性能产生了巨大影响。它从 10tps 增加到 1000tps，因为它不必调用 PHP，并且 Nginx 页面缓存保存在 RAM 中。您只需小心设置，以便登录用户不会获得缓存页面，并且他们的页面不会进入缓存。