nginx + pagespeed downstream caching example

nginx-pagespeed.conf

#source: http://www.jefftk.com/2014-01-03--nginx.conf

# for debugging with valgrind
#daemon off;
#master_process off;

#user  nobody;
worker_processes  1;

worker_rlimit_core  500M;
working_directory   /tmp/nginx_cores/;

error_log  logs/error.log;
#error_log  logs/error.log  notice;
#error_log  logs/error.log  debug;

#pid        logs/nginx.pid;

events {
    worker_connections  1024;
}


http {
    log_format withcookie '$remote_addr - $remote_user [$time_local] '
       '"$request" (fvt=$cookie_fvt) $status $body_bytes_sent '
       '"$http_referer" "$http_user_agent"';

    map_hash_max_size 65536;

    include       mime.types;
    #default_type  application/octet-stream;
    default_type  text/html;

    sendfile        on;
    #tcp_nopush     on;

    #keepalive_timeout  0;
    keepalive_timeout  65;

    proxy_cache_path /usr/local/nginx/cache  levels=1:2 keys_zone=htmlcache:10m;
    # When combined with proxy_hide_header and 'add_header Cache-Control'
    # below, this mapping allows us to override html caching headers while
    # leaving them alone on other types of content.
    map $upstream_http_content_type $new_cache_control_header_val {
        default $upstream_http_cache_control;
        "~*text/html"      "no-cache, max-age=0";
    }

    map $uri $new_post_url {
        default no-redirect;
        /news/index /p/index;
        /news/all /p/index;
        include /usr/local/nginx/conf/nginx.redirects.conf;
    }          
        


    # enable gzip:
    gzip on;
    gzip_vary on;

    # Turn on gzip for all content types that should benefit from it.
    gzip_types application/ecmascript;
    gzip_types application/javascript;
    gzip_types application/json;
    gzip_types application/pdf;
    gzip_types application/postscript;
    gzip_types application/x-javascript;
    gzip_types image/svg+xml;
    gzip_types text/css;
    gzip_types text/csv;
    # "gzip_types text/html" is assumed.
    gzip_types text/javascript;
    gzip_types text/plain;
    gzip_types text/xml;

    gzip_http_version 1.0;

    server {
        listen 80;
        server_name bidadance.org;
        rewrite ^(.*) http://www.bidadance.org permanent;
    }

    server {
        listen 80;
        server_name jefftk.com;
        rewrite ^(.*) http://www.jefftk.com$1 permanent;
    }

    server {
        listen 80;
        server_name trycontra.com;
        rewrite ^(.*) http://www.trycontra.com$1 permanent;
    }

  server {
    if ($new_post_url !~ "no-redirect") {
      rewrite ^ $new_post_url permanent;
    }

    # This server represents the external caching layer server which
    # receives user requests and proxies them to the upstream server
    # running on 8090 when the response is not available in
    # the cache. It also services purge requests from the upstream server.
    listen 80;
    server_name www.jefftk.com;

    access_log logs/access.80.log withcookie;

    #pagespeed FileCachePath /var/ngx_pagespeed_cache;
    #pagespeed off;

    #normalize all accept-encoding headers to just gzip
    set $gzip_support "0";
    if ($http_accept_encoding ~* gzip) {
       set $gzip_support "1";
    }

    # Block 2: Define prefix for proxy_cache_key based on the UserAgent.
    set $ua_dependent_ps_capability_list "";
    set $bypass_cache 1;
    if ($http_user_agent ~* "Chrome/|Firefox/|MSIE |Safari|Wget") {
      # User Agents that support lazyload-images (ll), inline-images (ii) and
      # defer-javascript (dj).
      set $ua_dependent_ps_capability_list "ll,ii,dj:";
      set $bypass_cache 0;
    }
    if ($http_user_agent ~*
        "Chrome/[2][3-9]+\.|Chrome/[[3-9][0-9]+\.|Chrome/[0-9]{3,}\.") {
      # User Agents that support lazyload-images (ll), inline-images (ii),
      # defer-javascript (dj), webp (jw) and webp-lossless (ws).
      set $ua_dependent_ps_capability_list "ll,ii,dj,jw,ws:";
      set $bypass_cache 0;
    }

    # All User Agents that represent
    # 1) mobiles
    # 2) tablets
    # 3) desktop browsers that do not have defer-javascript capability at a minimum
    # are made to go to the pagespeed server directly bypassing the proxy_cache.
    if ($http_user_agent ~* "Firefox/[1-2]\.|MSIE [5-8]\.") {
      set $ua_dependent_ps_capability_list "";
      set $bypass_cache 1;
    }
    if ($http_user_agent ~* "Mozilla.*Android.*Mobile*|iPhone|BlackBerry|Opera Mobi|Opera Mini|SymbianOS|UP.Browser|J-PHONE|Profile/MIDP|portalmmm|DoCoMo|Obigo") {
      # These are Mobile User Agents. We don't cache responses for these.
      set $ua_dependent_ps_capability_list "";
      set $bypass_cache 1;
    }
    if ($http_user_agent ~* "Android|iPad|TouchPad|Silk-Accelerated|Kindle Fire") {
      # These are Tablet User Agents. We don't cache responses for these.
      set $ua_dependent_ps_capability_list "";
      set $bypass_cache 1;
    }

    # Skip the cache for .pagespeed. resource.  PageSpeed has its own
    # cache for these.
    if ($uri ~ "\.pagespeed\.([a-z]\.)?[a-z]{2}\.[^.]{10}\.[^.]+") {
      set $bypass_cache 1;
    }

    if ($uri ~ "^/jscss/") {
      set $bypass_cache 1;
    }

    if ($uri ~ "^/test/") {
      set $bypass_cache 1;
    }
    
    # Block 3: Location block for purge requests.
    location ~ /purge(/.*) {
      allow 127.0.0.1;
      allow 209.20.65.89;  # our ip: www.jefftk.com
      deny all;
      proxy_cache_purge htmlcache $gzip_support$ua_dependent_ps_capability_list$1$is_args$args;
    }

    # Block 4: Proxy everything except purge requests (above) in to PageSpeed.
    location / {
      proxy_pass http://www.jefftk.com:8090;

      proxy_set_header Host $http_host;
      proxy_cache htmlcache;
      add_header X-Cache $upstream_cache_status;
      proxy_cache_key $gzip_support$ua_dependent_ps_capability_list$uri$is_args$args;
      proxy_cache_bypass $bypass_cache;

      # Change control headers from the upstream, after using them to
      # decide how long we should cache here.
      proxy_hide_header Cache-Control;
      add_header Cache-Control $new_cache_control_header_val;

      # Everything is either html, in which case it's uncacheable by
      # external caches, or longcached, in which case etag and
      # last-modified are not needed.
      proxy_hide_header ETag;
      proxy_hide_header Last-Modified;
    }
  }

    server {
        listen       8090;
        server_name  www.jefftk.com;
        root   /var/www;
        index index.html;

        add_header Cache-Control "max-age=600";

        pagespeed on;
        pagespeed MessageBufferSize 200000;

        #pagespeed LoadFromFile http://www.jefftk.com/ /var/www;
        #pagespeed LoadFromFileRule Disallow /var/www/wsgi;

        location /test {
          pagespeed off;
        }

        location /jscss {
          pagespeed off;
        }

        # Javascript outlining is off by default, but if I enable if for
        # testing via a quaery param I want it to outline all the js.
        pagespeed JsOutlineMinBytes 0;

        #pagespeed InPlaceResourceOptimization on;

        #pagespeed FileCacheCleanIntervalMs 10000000000;
        #pagespeed FileCacheCleanIntervalMs 1000;

        #pagespeed MetadataCacheStalenessThresholdMs 60000;

        pagespeed FileCachePath /var/ngx_pagespeed_cache;
        pagespeed RewriteLevel CoreFilters;
        #pagespeed MapProxyDomain http://www.jefftk.com:8050/ http://www.jefftk.com/;
        pagespeed AnalyticsID "UA-27645543-1";
        pagespeed EnableFilters add_instrumentation,remove_quotes;
        pagespeed EnableFilters insert_ga,trim_urls;
        pagespeed EnableFilters convert_jpeg_to_webp;

        pagespeed RunExperiment off;
        pagespeed ExperimentSpec "id=1;percent=50;default";
        pagespeed ExperimentSpec "id=2;percent=50";

        pagespeed Statistics on;
        pagespeed StatisticsLogging on;
        pagespeed LogDir /var/log/pagespeed;

        pagespeed ModifyCachingHeaders off;

        pagespeed DownstreamCachePurgeMethod "GET";
        pagespeed DownstreamCachePurgeLocationPrefix "http://www.jefftk.com/purge";

        location ~ \.html$ {
           rewrite ^(/.+)\.html$ $scheme://$host$1 permanent;
        }

        location ~ ^/?\+$ {
           rewrite ^ https://plus.google.com/103013777355236494008/about permanent;
        }

        location / {
            try_files $uri.html $uri $uri/ =404;
        }
        location /wsgi {
            proxy_pass http://127.0.0.1:8080/wsgi/;
            pagespeed off;
        }

        location ~ "\.pagespeed\.([a-z]\.)?[a-z]{2}\.[^.]{10}\.[^.]+" { }
        location ~ "^/ngx_pagespeed_static/" { }
        location ~ "^/ngx_pagespeed_beacon$" { }
        #location /ngx_pagespeed_statistics {
        #  allow 127.0.0.1;
        #  deny all;
        #}
        #location /ngx_pagespeed_message {
        #  allow 127.0.0.1;
        #  deny all;
        #}

        # redirect server error pages to the static page /50x.html
        #
        error_page   500 502 503 504  /50x.html;
        location = /50x.html {
            root   html;
        }
    }

    server {
        listen 80;
        server_name www.trycontra.com;
        root   /var/www-tc;
        index index.html;

        charset utf8;

        location /draft {
          rewrite ^ / permanent;
        }
    }
}