Varnish configuration example

varnish.tokyo.vcl

# VCL configuration file for Varnish

# Define which IP addresses or hosts have access to files that are
# blocked from the public internet
acl internal {
  "localhost";
}

# Define origin servers
backend web { .host = "1.2.3.4"; .port = "80"; }
backend web_ssl { .host = "1.2.3.4"; .port = "443"; }

# Uncomment to support Munin graphs
# backend monitoring { .host = "127.0.0.1"; .port = "8081"; }

# Uncomment to include Security.VCL module
# @see: https://github.com/comotion/security.vcl
# include "/etc/varnish/security/main.vcl";

# Respond to incoming requests
sub vcl_recv {
  
  # Uncomment to support Munin graphs. Access is granted if visitor is coming
  # from a whitelisted IP address and secret token is provided.
  #   e.g. http://www.example.com/munin?your-secret-token
  # if (req.url ~ "^/munin" && client.ip ~ internal
  #     && (req.url ~ "\?your-secret-token"
  #     || req.http.referer ~ "(www\.)?example\.com")) {
  #   set req.backend = monitoring;
  #   return (pipe);
  # }
  
  # Uncomment to have New Relic track queue times
  # C{
  # #include </etc/varnish/newrelic.h>
  # }C
  
  # Handle HTTPS connection
  if (server.port == 443) {
    set req.backend = web_ssl;
  } else {
    set req.backend = web;
  }
  
  if (req.restarts == 0) {
    if (req.http.x-forwarded-for) {
      set req.http.X-Forwarded-For =
          req.http.X-Forwarded-For + ", "  + client.ip;
    } else {
      set req.http.X-Forwarded-For = client.ip;
    }
  }
  
  # Normalize requests sent via curls -X mode and LWP
  if (req.url ~ "^http://") {
    set req.url = regsub(req.url, "http://[^/]*", "");
  }
  
  # Normalize hostname to avoid double caching
  set req.http.host = regsub(req.http.host,
      "^example\.com$", "www.example.com");
  
  # Uncomment to support shared hosting when testing through staging server
  # set req.http.host = regsub(req.http.host, "^cache\.example\.com$",
  #     "www.example.com");
  
  # Use anonymous, cached pages if all backends are down
  if (!req.backend.healthy) {
    unset req.http.Cookie;
  }
  
  # Allow the backend to serve up stale content if it is responding slowly
  set req.grace = 6h;
  
  # Do not cache these paths
  if (req.url ~ "^/status\.php$" ||
      req.url ~ "^/administrator") {
    return (pass);
  }
  
  # Do not cache authenticated sessions
  if (req.http.Cookie && req.http.Cookie ~ "authtoken=") {
    return (pipe);
  }
  
  # Do not allow outside access to configuration.php
  if (req.url ~ "^/configuration\.php$" && !client.ip ~ internal) {
    # Have Varnish throw the error directly
    # error 404 "Page not found.";

    # Use a custom error page
    set req.url = "/";
  }
  
  # Allow purge only from internal users
  if (req.request == "PURGE") {
    if (!client.ip ~ internal) {
      error 405 "Not allowed.";
    }
    return (lookup);
  }
  
  # Handle compression correctly. Different browsers send different
  # "Accept-Encoding" headers, even though they mostly all support the same
  # compression mechanisms. By consolidating these compression headers into
  # a consistent format, we can reduce the size of the cache and get more hits.
  # @see: http:// varnish.projects.linpro.no/wiki/FAQ/Compression
  if (req.http.Accept-Encoding) {
    if (req.http.Accept-Encoding ~ "gzip") {
      # If the browser supports it, we'll use gzip.
      set req.http.Accept-Encoding = "gzip";
    } else if (req.http.Accept-Encoding ~ "deflate") {
      # Next, try deflate if it is supported.
      set req.http.Accept-Encoding = "deflate";
    } else {
      # Unknown algorithm. Remove it and send unencoded.
      unset req.http.Accept-Encoding;
    }
  }
  
  # Always cache the following file types for all users
  if (req.url ~
      "(?i)\.(png|gif|jpeg|jpg|ico|swf|pdf|txt|css|js|html|htm|gz|xml)(\?[a-z0-9]+)?$") {
    unset req.http.Cookie;
  }
  
  if (req.request != "GET" &&
      req.request != "HEAD" &&
      req.request != "PUT" &&
      req.request != "POST" &&
      req.request != "TRACE" &&
      req.request != "OPTIONS" &&
      req.request != "DELETE") {
    /* Non-RFC2616 or CONNECT which is weird. */
    return (pipe);
  }
  
  if (req.request != "GET" && req.request != "HEAD") {
    return (pass);
  }

  # We cache requests with cookies too (e.g. Google Analytics)
  # Original: if (req.http.Authenticate || req.http.Authorization
  #     || req.http.Cookie) {
  if (req.http.Authenticate || req.http.Authorization) {
    return (pass);
  }
  
  return (lookup);
}
 
# sub vcl_pipe {
#     # Note that only the first request to the backend will have
#     # X-Forwarded-For set.  If you use X-Forwarded-For and want to
#     # have it set for all requests, make sure to have:
#     # set bereq.http.connection = "close";
#     # here.  It is not set by default as it might break some broken web
#     # applications, like IIS with NTLM authentication.
#     return (pipe);
# }

# sub vcl_pass {
#     return (pass);
# }

# Determine the cache key when storing/retrieving a cached page
sub vcl_hash {
  hash_data(req.url);
  if (req.http.host) {
    hash_data(req.http.host);
  } else {
    hash_data(server.ip);
  }
  
  # Don't include cookie in hash
  # if (req.http.Cookie) {
  #   hash_data(req.http.Cookie);
  # }
  
  return (hash);
}

sub vcl_hit {
  if (req.request == "PURGE") {
    purge;
    error 200 "Purged.";
  }
  if (obj.ttl <= 0s) {
    return (pass);
  }
  
  return (deliver);
}

sub vcl_miss {
  if (req.request == "PURGE") {
    error 404 "Not in cache.";
  }
  
  return (fetch);
}

# Called when the requested object has been retrieved from the backend, or the
# request to the backend has failed; "beresp" stands for back-end response
sub vcl_fetch {
  
  # Don't allow static files to set cookies
  if (req.url ~
      "(?i)\.(png|gif|jpeg|jpg|ico|swf|pdf|txt|css|js|html|htm|gz|xml)(\?[a-z0-9]+)?$") {
    unset beresp.http.Set-cookie;
  }
  
  # Allow items to be stale if needed
  set beresp.grace = 6h;
  
  if (beresp.ttl <= 0s) {
    set beresp.http.X-Cacheable = "NO:Not Cacheable";
    return (hit_for_pass);
  } else if (req.http.Cookie ~"(UserID|_session)") {
    # Don't cache content for logged in users
    set beresp.http.X-Cacheable = "NO:Got Session";
    return (hit_for_pass);
  } else if (beresp.http.Cache-Control ~ "private") {
    # Respect the Cache-Control=private header from the backend
    set beresp.http.X-Cacheable = "NO:Cache-Control=private";
    return (hit_for_pass);
  } else if (beresp.ttl < 1s) {
    # Extend the lifetime of the object artificially
    set beresp.ttl   = 300s;
    set beresp.grace = 300s;
    set beresp.http.X-Cacheable = "YES:Forced";
  } else {
    # Varnish determined the object was cacheable
    set beresp.http.X-Cacheable = "YES";
    
    # Uncomment to have Varnish cache objects longer than the clients do.
    # Cache must be purged manually when the site changes, so don't use with
    # frequently changing content - comments, visitor counters etc.
    # @see: https://www.varnish-cache.org/trac/wiki/VCLExampleLongerCaching
    # unset beresp.http.expires;
    # set beresp.ttl = 1w;
    # set beresp.http.magicmarker = "1";
  }
  
  return (deliver);
}

sub vcl_deliver {
  
  # Uncomment to add hostname to headers
  # set resp.http.X-Served-By = server.hostname;

  # Identify which Varnish handled the request
  if (obj.hits > 0) {
    set resp.http.X-Cache = "HIT from Tokyo"; 
    set resp.http.X-Cache-Hits = obj.hits;
  } else {
    set resp.http.X-Cache = "MISS from Tokyo";  
  }
  
  # Remove version number sometimes set by CMS
  if (resp.http.X-Content-Encoded-By) {
    unset resp.http.X-Content-Encoded-By;
  }
  
  if (resp.http.magicmarker) {
    # Remove the magic marker, see vcl_fetch
    unset resp.http.magicmarker;
    
    # By definition we have a fresh object
    set resp.http.Age = "0";
  }

  return (deliver);
}

sub vcl_error {
  
  # Redirect to some other URL in case of root page failure
  # if (req.url ~ "^/?$") {
  #   set obj.status = 302;
  #   set obj.http.Location = "http://backup.example.com/";
  # }

  # Otherwise redirect to root, which will likely be in the cache
  set obj.http.Content-Type = "text/html; charset=utf-8";
  synthetic {"
<html>
<head>
  <title>Page Unavailable</title>
  <style>
    body { background: #efefef; text-align: center; color: white;
        font-family: Trebuchet MS, sans-serif; }
    #page { width: 500px; margin: 100px auto 0; padding: 30px; background: #888888;
        border-radius: 14px; -moz-border-radius: 14px; -webkit-border-radius: 14px; border: 0 }
    a, a:link, a:visited { color: #cccccc; }
    .error { color: #222222; }
  </style>
</head>
<body onload="setTimeout(function() { window.location = '/' }, 3000)">
  <div id="page">
    <h1 class="title">Page Unavailable</h1>
    <p>The page you requested is temporarily unavailable.</p>
    <p>We're redirecting you to the <a href="/">homepage</a> in 3 seconds.</p>
    <div class="error">(Error "} + obj.status + " " + obj.response + {")</div>
  </div>
</body>
</html>
"};
  return (deliver);
}

From presentation Improving Site Response Time, Part 3 - Varnish Configuration Step by Step