Назад | Перейти на главную страницу

Как заставить Varnish 4.0 работать с nginx и Pagespeed

Я пытаюсь настроить Varnish 4 + Nginx с помощью mod_pagespeed.

Я использую следующую конфигурацию для Varnish 4 согласно этому документу:

https://developers.google.com/speed/pagespeed/module/downstream-caching

Конфигурация, которую я использую, не дает ошибок, но я почти не получаю попаданий в кеш от Varnish

MAIN.cache_hit  80
MAIN.cache_miss 347 

Полная конфигурация .vcl:

# Marker to tell the VCL compiler that this VCL has been adapted to the
# new 4.0 format.
vcl 4.0;

import std;

# Block 1: Define upstream server's host and port. Set this to point to your
# content server.
backend default {
    .host = "127.0.0.1";
    .port = "8080";
}

# Block 2: Define a key based on the User-Agent which can be used for hashing.
# Also set the PS-CapabilityList header for PageSpeed server to respect.
sub generate_user_agent_based_key {
    # Define placeholder PS-CapabilityList header values for large and small
    # screens with no UA dependent optimizations. Note that these placeholder
    # values should not contain any of ll, ii, dj, jw or ws, since these
    # codes will end up representing optimizations to be supported for the
    # request.
    set req.http.default_ps_capability_list_for_large_screens = "LargeScreen.SkipUADependentOptimizations:";
    set req.http.default_ps_capability_list_for_small_screens = "TinyScreen.SkipUADependentOptimizations:";

    # As a fallback, the PS-CapabilityList header that is sent to the upstream
    # PageSpeed server should be for a large screen device with no browser
    # specific optimizations.
    set req.http.PS-CapabilityList = req.http.default_ps_capability_list_for_large_screens;

    # Cache-fragment 1: Desktop User-Agents that support lazyload_images (ll),
    # inline_images (ii) and defer_javascript (dj).
    # Note: Wget is added for testing purposes only.
    if (req.http.User-Agent ~ "(?i)Chrome/|Firefox/|MSIE |Safari|Wget") {
      set req.http.PS-CapabilityList = "ll,ii,dj:";
    }
    # Cache-fragment 2: Desktop User-Agents that support lazyload_images (ll),
    # inline_images (ii), defer_javascript (dj), webp (jw) and lossless_webp
    # (ws).
    if (req.http.User-Agent ~
        "(?i)Chrome/[2][3-9]+\.|Chrome/[[3-9][0-9]+\.|Chrome/[0-9]{3,}\.") {
      set req.http.PS-CapabilityList = "ll,ii,dj,jw,ws:";
    }
    # Cache-fragment 3: This fragment contains (a) Desktop User-Agents that
    # match fragments 1 or 2 but should not because they represent older
    # versions of certain browsers or bots and (b) Tablet User-Agents that
    # on all browsers and use image compression qualities applicable to large
    # screens. Note that even tablets that are capable of supporting inline or
    # webp images, e.g. Android 4.1.2, will not get these advanced
    # optimizations.
    if (req.http.User-Agent ~ "(?i)Firefox/[1-2]\.|MSIE [5-8]\.|bot|Yahoo!|Ruby|RPT-HTTPClient|(Google \(\+https\:\/\/developers\.google\.com\/\+\/web\/snippet\/\))|Android|iPad|TouchPad|Silk-Accelerated|Kindle Fire") {
      set req.http.PS-CapabilityList = req.http.default_ps_capability_list_for_large_screens;
    }
    # Cache-fragment 4: Mobiles and small screen tablets will use image
    # compression qualities applicable to small screens, but all other
    # optimizations will be those that work on all browsers.
    if (req.http.User-Agent ~ "(?i)Mozilla.*Android.*Mobile*|iPhone|BlackBerry|Opera Mobi|Opera Mini|SymbianOS|UP.Browser|J-PHONE|Profile/MIDP|portalmmm|DoCoMo|Obigo|Galaxy Nexus|GT-I9300|GT-N7100|HTC One|Nexus [4|7|S]|Xoom|XT907") {
      set req.http.PS-CapabilityList = req.http.default_ps_capability_list_for_small_screens;
    }
    # Remove placeholder header values.
    unset req.http.default_ps_capability_list_for_large_screens;
    unset req.http.default_ps_capability_list_for_large_screens;
}

sub vcl_hash {
  # Block 3: Use the PS-CapabilityList value for computing the hash.
  hash_data(req.http.PS-CapabilityList);
}

# Block 3a: Define ACL for purge requests
acl purge {
  # Purge requests are only allowed from localhost.
  "localhost";
  "127.0.0.1";
}


# Block 4: In vcl_recv, on receiving a request, call the method responsible for
# generating the User-Agent based key for hashing into the cache.
sub vcl_recv {
  # We want to support beaconing filters, i.e., one or more of inline_images,
  # lazyload_images, inline_preview_images or prioritize_critical_css are
  # enabled. We define a placeholder constant called ps_should_beacon_key_value
  # so that some percentages of hits and misses can be sent to the backend
  # with this value used for the PS-ShouldBeacon header to force beaconing.
  # This value should match the value of the DownstreamCacheRebeaconingKey
  # pagespeed directive used by your backend server.
  # WARNING: Do not use "random_rebeaconing_key" for your configuration, but
  # instead change it to something specific to your site, to keep it secure.
  set req.http.ps_should_beacon_key_value = "random_rebeaconing_key";

  # Incoming PS-ShouldBeacon headers should not be allowed since this will allow
  # external entities to force the server to instrument pages.
  unset req.http.PS-ShouldBeacon;

  call generate_user_agent_based_key;
  # Block 3d: Verify the ACL for an incoming purge request and handle it.
  if (req.method == "PURGE") {
    if (!client.ip ~ purge) {
      return (synth(405,"Not allowed."));
    }
    return (purge);
  }
  # Blocks which decide whether cache should be bypassed or not go here.

  # Block 5a: Bypass the cache for .pagespeed. resource. PageSpeed has its own
  # cache for these, and these could bloat up the caching layer.
  if (req.url ~ "\.pagespeed\.([a-z]\.)?[a-z]{2}\.[^.]{10}\.[^.]+") {
    # Skip the cache for .pagespeed. resource.  PageSpeed has its own
    # cache for these, and these could bloat up the caching layer.
    return (pass);
  }

  # Block 5b: Only cache responses to clients that support gzip.  Most clients
  # do, and the cache holds much more if it stores gzipped responses.
  if (req.http.Accept-Encoding !~ "gzip") {
    return (pass);
  }
}

# Block 6: Mark HTML uncacheable by caches beyond our control.
sub vcl_backend_response {
   if (beresp.http.Content-Type ~ "text/html") {
     # Hide the upstream cache control header.
     unset beresp.http.Cache-Control;
     # Add no-cache Cache-Control header for html.
     set beresp.http.Cache-Control = "no-cache, max-age=0";
   }
   return (deliver);
}

sub vcl_hit { 
  if (std.random(0, 100) < 5) {
    set req.http.PS-ShouldBeacon = req.http.ps_should_beacon_key_value;
    return (pass);
  }
}

sub vcl_miss {
  # Send 25% of the MISSes to the backend for instrumentation.
  if (std.random(0, 100) < 25) {
    set req.http.PS-ShouldBeacon = req.http.ps_should_beacon_key_value;
    return (pass);
  }
}

# Block 7: Add a header for identifying cache hits/misses.
sub vcl_deliver {
  if (obj.hits > 0) {
    set resp.http.X-Cache = "HIT";
  } else {
    set resp.http.X-Cache = "MISS";
  }
}

И полная конфигурация pagepeed:

pagespeed on;

# Needs to exist and be writable by nginx.  Use tmpfs for best performance.
pagespeed FileCachePath /tmp/pagespeed;

location ~ "\.pagespeed\.([a-z]\.)?[a-z]{2}\.[^.]{10}\.[^.]+" {
  add_header "" "";
}
location ~ "^/pagespeed_static/" { }
location ~ "^/ngx_pagespeed_beacon$" { }

#pagespeed ModifyCachingHeaders on;

pagespeed RewriteLevel CoreFilters;

pagespeed EnableFilters rewrite_domains;
#Testing CDN

#Authorize Domains

pagespeed Domain origindomain.com;
pagespeed Domain cdn.domain.com;

#Rewrite to CDN

pagespeed MapRewriteDomain cdn.domain.com origindomain.com;

#Disallow wp-admin / login

pagespeed Disallow "*/wp-admin/*";
pagespeed Disallow "*/checkout/*";

Демонстрация того, как заголовки отрываются при вызове домашней страницы:

Accept-Ranges   bytes
Access-Control-Allow-Head...    X-Requested-With
Access-Control-Allow-Meth...    GET, HEAD, OPTIONS
Access-Control-Allow-Orig...    *
Age 0
Cache-Control   no-cache, max-age=0
Connection  keep-alive
Content-Encoding    gzip
Content-Length  8473
Content-Type    text/html; charset=UTF-8
Date    Wed, 15 Oct 2014 08:38:49 GMT
Link    <http://origindomain.com/>; rel=shortlink
Server  nginx/1.7.6
Set-Cookie  _icl_current_language=en; expires=Thu, 16-Oct-2014 08:38:49 GMT; Max-Age=86400; path=/
Vary    Accept-Encoding
Via 1.1 varnish-v4
X-Cache MISS
X-Page-Speed    1.9.32.1-4238
X-Pingback  http://origindomain.com/xmlrpc.php
X-Powered-By    PHP/7.0.0-dev
X-Varnish   393416

Кажется, что он никогда не попадает в кеш и выталкивает оптимизированную версию сайта. На самом деле в начале тестов он иногда попадал, но не уверен, что это была оптимизированная версия или просто обычная версия.

Так что он пропускает, passthrough и nginx обслуживает сайт, оптимизированный для скорости страницы, но Varnish не имеет никакого эффекта.

Похоже, что в конфигурации Pagespeed для nginx отсутствуют директивы DownstreamCache * из https://developers.google.com/speed/pagespeed/module/downstream-caching

Также для лака vcl, пожалуйста, обратите внимание на https://github.com/pagespeed/ngx_pagespeed/issues/787, поскольку официальные документы еще нужно обновить до этого. Без изменений вы можете столкнуться с кешированием в Varnish того, что не следует кэшировать.