php - Nginx+php5-fpm+varnish+APC 上的 Wordpress 高 CPU 和内存使用率

Question

经过数天的调试和设置调整，我已经精疲力尽，无法找到解决方案。请指导。

我在DigitalOcean上具有以下服务器:

64GB Memory
8 Core processor
200GB SSD drive

而且我正在其上运行单个Wordpress网站。网站流量很高。 (2000至3000个并发实时用户)并且我敢肯定，由于我的设置不正确，我失去了流量并且无法为用户提供页面。我希望实时用户为5000+，但始终保持在2000左右。

我经常收到OOM错误，并且由于 mysql或 php5-fpm被杀死而导致站点关闭。如果我调整 php-fpm和 nginx，则会收到 502和 503错误。或者我收到 upstream timed out (110: Connection timed out)'或 FastCGI sent in stderr: PHP message: PHP Fatal error: Maximum execution time of 30 seconds exceeded错误。

现在，我对设置进行了调整，以使我没有任何错误，但是访问量已下降到大约1500个并发用户，并且拒绝增加流量。因此，我确定我的设置中有问题。
/etc/php5/fpm/pool.d/www.conf设置:

pm = dynamic
pm.max_children = 150
pm.start_servers = 40
pm.min_spare_servers = 30
pm.max_spare_servers = 50
pm.max_requests = 1000

FastCGI设置: /etc/nginx/conf.d/default.conf

location ~ \.php$ {
             try_files $uri =404;
             # proxy buffers - no 502 errors!
             proxy_buffer_size               128k;
             proxy_buffers                   4 256k;
             proxy_busy_buffers_size         256k;

            fastcgi_buffers 256 16k;
            fastcgi_buffer_size 128k;
            fastcgi_max_temp_file_size 0;
            fastcgi_intercept_errors on;
            fastcgi_keep_conn off;
            include fastcgi_params;
            fastcgi_param SCRIPT_FILENAME    $document_root$fastcgi_script_name;
            fastcgi_pass unix:/dev/shm/php-fpm-www.sock;


        }

APC设置: /etc/php5/fpm/php.ini

[apc]
apc.write_lock = 1
apc.slam_defense = 0
apc.shm_size = "1024M"

我注意到 php5-fpm进程占用大量内存。
例如。当我计算每个进程的平均内存时，我得到: ps --no-headers -o "rss,cmd" -C php5-fpm | awk '{ sum+=$1 } END { printf ("%d%s\n", sum/NR/1024,"M") }'为我提供了1100并发流量的 238M。

请指导我我的配置不正确的地方。因为我100％确信我的交通阻塞。

附加信息

Nginx配置: /etc/nginx/nginx.conf

worker_processes  24;
worker_rlimit_nofile 20000;


events {
    worker_connections  40000;
    use epoll;
    multi_accept on;
}

但是我注意到服务器上的ulimit是:
ulimit -n仅显示 1024。这和我的问题有关吗？

Daniel回应后添加了VCL

# This is a basic VCL configuration file for varnish.  See the vcl(7)
# man page for details on VCL syntax and semantics.
#
# Default backend definition.  Set this to point to your content
# server.
#
backend default {
    .host = "127.0.0.1";
    .port = "8080";
        .connect_timeout = 600s;
        .first_byte_timeout = 600s;
        .between_bytes_timeout = 600s;
        .max_connections = 800;
}


acl purge {
        "localhost";
}

sub vcl_recv {
        set req.grace = 6h;

  # Set X-Forwarded-For header for logging in nginx
  remove req.http.X-Forwarded-For;
  set    req.http.X-Forwarded-For = client.ip;


  # Remove has_js and CloudFlare/Google Analytics __* cookies.
  set req.http.Cookie = regsuball(req.http.Cookie, "(^|;\s*)(_[_a-z]+|has_js)=[^;]*", "");
  # Remove a ";" prefix, if present.
  set req.http.Cookie = regsub(req.http.Cookie, "^;\s*", "");



# Either the admin pages or the login
if (req.url ~ "/wp-(login|admin|cron)") {
        # Don't cache, pass to backend
        return (pass);
}

# Remove the wp-settings-1 cookie
set req.http.Cookie = regsuball(req.http.Cookie, "wp-settings-1=[^;]+(; )?", "");

# Remove the wp-settings-time-1 cookie
set req.http.Cookie = regsuball(req.http.Cookie, "wp-settings-time-1=[^;]+(; )?", "");

# Remove the wp test cookie
set req.http.Cookie = regsuball(req.http.Cookie, "wordpress_test_cookie=[^;]+(; )?", "");

# Static content unique to the theme can be cached (so no user uploaded images)
# The reason I don't take the wp-content/uploads is because of cache size on bigger blogs
# that would fill up with all those files getting pushed into cache
if (req.url ~ "wp-content/themes/" && req.url ~ "\.(css|js|png|gif|jp(e)?g)") {
    unset req.http.cookie;
}

# Even if no cookies are present, I don't want my "uploads" to be cached due to their potential size
if (req.url ~ "/wp-content/uploads/") {
    return (pass);
}

# Check the cookies for wordpress-specific items
if (req.http.Cookie ~ "wordpress_" || req.http.Cookie ~ "comment_") {
        # A wordpress specific cookie has been set
    return (pass);
}



        # allow PURGE from localhost
        if (req.request == "PURGE") {
                if (!client.ip ~ purge) {
                        error 405 "Not allowed.";
                }
                return (lookup);
        }


        # Force lookup if the request is a no-cache request from the client
        if (req.http.Cache-Control ~ "no-cache") {
                return (pass);
        }
# Try a cache-lookup
return (lookup);

}

sub vcl_fetch {
        #set obj.grace = 5m;
    set beresp.grace = 6h;

}

sub vcl_hit {
        if (req.request == "PURGE") {
                purge;
                error 200 "Purged.";
        }
}

sub vcl_miss {
        if (req.request == "PURGE") {
                purge;
                error 200 "Purged.";
        }
}

Answer 1

有了这种流量和这种配置，您就失去了很多机会(和收入):)。您真的应该动手使用Nginx微缓存和Varnish!