Varnish VCL and Config for WordPress with W3 Total Cache

I have been working on a Varnish front-end for Apache, to be used with WordPress sites. I described the architecture in Load Balancing Virtualmin WordPress Hosting Server with Varnish on AWS. I now have a configuration that seems to work for all WordPress features, including logged-out commenting. This configuration also works well with W3 Total Cache.

This configuration is for Varnish on a separate server, but should also work on a single server with appropriate changes to the port and backend IP settings.

Varnish Config (/etc/sysconfig/varnish)

# Configuration file for varnish
#
# /etc/init.d/varnish expects the variable $DAEMON_OPTS to be set from this
# shell script fragment.
#
#
# Maximum number of open files (for ulimit -n)
NFILES=131072
#
# Locked shared memory (for ulimit -l)
# Default log size is 82MB + header
MEMLOCK=82000
#
# Maximum size of corefile (for ulimit -c). Default in Fedora is 0
# DAEMON_COREFILE_LIMIT="unlimited"
#
# Set this to 1 to make init script reload try to switch vcl without restart.
# To make this work, you need to set the following variables
# explicit: VARNISH_VCL_CONF, VARNISH_ADMIN_LISTEN_ADDRESS,
# VARNISH_ADMIN_LISTEN_PORT, VARNISH_SECRET_FILE
RELOAD_VCL=1
#
## Advanced configuration
#
# # Main configuration file.
VARNISH_VCL_CONF=/etc/varnish/wordpress-varnish3.vcl
#
# # Default address and port to bind to
# # Blank address means all IPv4 and IPv6 interfaces, otherwise specify
# # a host name, an IPv4 dotted quad, or an IPv6 address in brackets.
# VARNISH_LISTEN_ADDRESS=
VARNISH_LISTEN_PORT=80
#
# # Telnet admin interface listen address and port
VARNISH_ADMIN_LISTEN_ADDRESS=127.0.0.1
VARNISH_ADMIN_LISTEN_PORT=6082
#
# # Shared secret file for admin interface
VARNISH_SECRET_FILE=/etc/varnish/secret
#
# # The minimum number of worker threads to start
VARNISH_MIN_THREADS=1
#
# # The Maximum number of worker threads to start
VARNISH_MAX_THREADS=1000
#
# # Idle timeout for worker threads
VARNISH_THREAD_TIMEOUT=120
#
# # Cache file location if using file cache
#VARNISH_STORAGE_FILE=/var/lib/varnish/varnish_storage.bin
#
# # Cache size: in bytes, optionally using k / M / G / T suffix,
# # or in percentage of available disk space using the % suffix.
VARNISH_STORAGE_SIZE=3G
#
# # Backend storage specification
# malloc runs from RAM, file from file
VARNISH_STORAGE="malloc,${VARNISH_STORAGE_SIZE}"
#VARNISH_STORAGE="file,${VARNISH_STORAGE_FILE},${VARNISH_STORAGE_SIZE}"
#
# # Default TTL used when the backend does not specify one
VARNISH_TTL=120
#
# # DAEMON_OPTS is used by the init script. If you add or remove options,
# # be sure you update this section, too.
DAEMON_OPTS="-a ${VARNISH_LISTEN_ADDRESS}:${VARNISH_LISTEN_PORT} \
-f ${VARNISH_VCL_CONF} \
-T ${VARNISH_ADMIN_LISTEN_ADDRESS}:${VARNISH_ADMIN_LISTEN_PORT} \
-t ${VARNISH_TTL} \
-w ${VARNISH_MIN_THREADS},${VARNISH_MAX_THREADS},${VARNISH_THREAD_TIMEOUT} \
-u varnish -g varnish \
-S ${VARNISH_SECRET_FILE} \
-s ${VARNISH_STORAGE}"
#

Varnish VCL (/etc/varnish/wordpress-varnish3.vcl)

backend origin {
.host = "10.11.12.13";
.port = "80";
.connect_timeout = 60s;
.first_byte_timeout = 60s;
.between_bytes_timeout = 60s;
}
#
sub vcl_recv {
# only using one backend
set req.backend = origin;
#
# set standard proxied ip header for getting original remote address
set req.http.X-Forwarded-For = client.ip;
#
# logged in users must always pass
if( req.url ~ "^/wp-(login|admin)" || req.http.Cookie ~ "wordpress_logged_in_" ){
return (pass);
}
# accept purges from w3tc and varnish http purge
if (req.request == "PURGE") {
return (lookup);
}
#
# don't cache search results
if( req.url ~ "\?s=" ){
return (pass);
}
#
# always pass through posted requests and those with basic auth
if ( req.request == "POST" || req.http.Authorization ) {
return (pass);
}
#
# else ok to fetch a cached page
unset req.http.Cookie;
return (lookup);
}
#
# accept purges from w3tc and varnish http purge
sub vcl_hit {
if (req.request == "PURGE") { purge; }
return (deliver);
}
#
# accept purges from w3tc and varnish http purge
sub vcl_miss {
if (req.request == "PURGE") { purge; }
return (fetch);
}
#
sub vcl_fetch {
#
# remove some headers we never want to see
unset beresp.http.Server;
unset beresp.http.X-Powered-By;
#
# only allow cookies to be set if we're in admin area - i.e. commenters stay logged out
if( beresp.http.Set-Cookie && req.url !~ "^/wp-(login|admin)" ){
unset beresp.http.Set-Cookie;
}
#
# don't cache response to posted requests or those with basic auth
if ( req.request == "POST" || req.http.Authorization ) {
return (hit_for_pass);
}
#
# only cache status ok
if ( beresp.status != 200 ) {
return (hit_for_pass);
}
#
# don't cache search results
if( req.url ~ "\?s=" ){
return (hit_for_pass);
}
#
# else ok to cache the response
set beresp.ttl = 24h;
return (deliver);
}
#
sub vcl_deliver {
# add debugging headers, so we can see what's cached
if (obj.hits > 0) {
set resp.http.X-Cache = "HIT";
}
else {
set resp.http.X-Cache = "MISS";
}
# remove some headers added by varnish
unset resp.http.Via;
unset resp.http.X-Varnish;
}
#
sub vcl_hash {
hash_data( req.url );
# altering hash so subdomains are ignored.
# don't do this if you actually run different sites on different subdomains
if ( req.http.host ) {
hash_data( regsub( req.http.host, "^([^\.]+\.)+([a-z]+)$", " class="lang:default decode:true"backend origin {
.host = "10.11.12.13";
.port = "80";
.connect_timeout = 60s;
.first_byte_timeout = 60s;
.between_bytes_timeout = 60s;
}
#
sub vcl_recv {
# only using one backend
set req.backend = origin;
#
# set standard proxied ip header for getting original remote address
set req.http.X-Forwarded-For = client.ip;
#
# logged in users must always pass
if( req.url ~ "^/wp-(login|admin)" || req.http.Cookie ~ "wordpress_logged_in_" ){
return (pass);
}
# accept purges from w3tc and varnish http purge
if (req.request == "PURGE") {
return (lookup);
}
#
# don't cache search results
if( req.url ~ "\?s=" ){
return (pass);
}
#
# always pass through posted requests and those with basic auth
if ( req.request == "POST" || req.http.Authorization ) {
return (pass);
}
#
# else ok to fetch a cached page
unset req.http.Cookie;
return (lookup);
}
#
# accept purges from w3tc and varnish http purge
sub vcl_hit {
if (req.request == "PURGE") { purge; }
return (deliver);
}
#
# accept purges from w3tc and varnish http purge
sub vcl_miss {
if (req.request == "PURGE") { purge; }
return (fetch);
}
#
sub vcl_fetch {
#
# remove some headers we never want to see
unset beresp.http.Server;
unset beresp.http.X-Powered-By;
#
# only allow cookies to be set if we're in admin area - i.e. commenters stay logged out
if( beresp.http.Set-Cookie && req.url !~ "^/wp-(login|admin)" ){
unset beresp.http.Set-Cookie;
}
#
# don't cache response to posted requests or those with basic auth
if ( req.request == "POST" || req.http.Authorization ) {
return (hit_for_pass);
}
#
# only cache status ok
if ( beresp.status != 200 ) {
return (hit_for_pass);
}
#
# don't cache search results
if( req.url ~ "\?s=" ){
return (hit_for_pass);
}
#
# else ok to cache the response
set beresp.ttl = 24h;
return (deliver);
}
#
sub vcl_deliver {
# add debugging headers, so we can see what's cached
if (obj.hits > 0) {
set resp.http.X-Cache = "HIT";
}
else {
set resp.http.X-Cache = "MISS";
}
# remove some headers added by varnish
unset resp.http.Via;
unset resp.http.X-Varnish;
}
#
sub vcl_hash {
hash_data( req.url );
# altering hash so subdomains are ignored.
# don't do this if you actually run different sites on different subdomains
if ( req.http.host ) {
hash_data( regsub( req.http.host, "^([^\.]+\.)+([a-z]+)$", "\1\2" ) );
} else {
hash_data( server.ip );
}
# ensure separate cache for mobile clients (WPTouch workaround)
if( req.http.User-Agent ~ "(iPod|iPhone|incognito|webmate|dream|CUPCAKE|WebOS|blackberry9\d\d\d)" ){
hash_data("touch");
}
return (hash);
}" ) );
} else {
hash_data( server.ip );
}
# ensure separate cache for mobile clients (WPTouch workaround)
if( req.http.User-Agent ~ "(iPod|iPhone|incognito|webmate|dream|CUPCAKE|WebOS|blackberry9\d\d\d)" ){
hash_data("touch");
}
return (hash);
}