I'm trying to manage a Xkey soft-purge on objects stored from different hosts, using Xkey as a sort of tag to purge all objects that match the Xkey tag disregarding the hashing. First of all, is it possible? Or is hashing in the loop in any case?
In vcl_recv I manually set a Xkey key with set req.http.xkey = req.url;
Then during PURGE call I use set req.http.x-purges = xkey.purge(req.url); to find objects, here non objects are found.
Full VCL:
vcl 4.0;
import std;
import directors;
import purge;
import xkey;
backend server1 {
.host = "ecommerce-node1-prod";
.port = "80";
.probe = {
.url = "/admin";
.timeout = 1s;
.interval = 5s;
.window = 5;
.threshold = 3;
}
}
backend server2 {
.host = "ecommerce-node2-prod";
.port = "80";
.probe = {
.url = "/admin";
.timeout = 1s;
.interval = 5s;
.window = 5;
.threshold = 3;
}
}
sub vcl_init {
new bar = directors.round_robin();
bar.add_backend(server1);
bar.add_backend(server2);
}
# ACL for purgers IP. (This needs to contain app server ips)
acl purgers {
"127.0.0.1";
"localhost";
"::1";
"ecommerce-node1-prod";
"ecommerce-node2-prod";
}
sub vcl_recv {
# Mitigate httpoxy application vulnerability, see: https://httpoxy.org/
unset req.http.Proxy;
set req.http.xkey = req.url;
# Strip query strings only needed by browser javascript. Customize to used tags.
if (req.url ~ "(\?|&)(pk_campaign|piwik_campaign|pk_kwd|piwik_kwd|pk_keyword|pixelId|kwid|kw|adid|chl|dv|nk|pa|camid|adgid|cx|ie|cof|siteurl|utm_[a-z]+|_ga|gclid)=") {
# see rfc3986#section-2.3 "Unreserved Characters" for regex
set req.url = regsuball(req.url, "(pk_campaign|piwik_campaign|pk_kwd|piwik_kwd|pk_keyword|pixelId|kwid|kw|adid|chl|dv|nk|pa|camid|adgid|cx|ie|cof|siteurl|utm_[a-z]+|_ga|gclid)=[A-Za-z0-9\-\_\.\~]+&?", "");
}
set req.url = regsub(req.url, "(\?|\?&|&)$", "");
# Normalize query arguments
set req.url = std.querysort(req.url);
# Normalize Accept-Encoding header
# straight from the manual: https://www.varnish-cache.org/docs/3.0/tutorial/vary.html
if (req.http.Accept-Encoding) {
if (req.url ~ "\.(jpg|png|gif|gz|tgz|bz2|tbz|mp3|ogg)$") {
# No point in compressing these
unset req.http.Accept-Encoding;
} elsif (req.http.Accept-Encoding ~ "gzip") {
set req.http.Accept-Encoding = "gzip";
} elsif (req.http.Accept-Encoding ~ "deflate") {
set req.http.Accept-Encoding = "deflate";
} else {
# unkown algorithm
unset req.http.Accept-Encoding;
}
}
# Handle PURGE
if (req.method == "PURGE") {
if (!client.ip ~ purgers) {
return (synth(405, "Method not allowed"));
}
#set req.http.n-gone = xkey.softpurge(req.http.xkey);
set req.http.x-purges = xkey.purge(req.url);
return (synth(200, "Invalidated "+ req.http.x-purges +" objects"));
}
if (req.method != "GET" &&
req.method != "HEAD" &&
req.method != "PUT" &&
req.method != "POST" &&
req.method != "TRACE" &&
req.method != "OPTIONS" &&
req.method != "PATCH" &&
req.method != "DELETE") {
/* Non-RFC2616 or CONNECT which is weird. */
return (pipe);
}
# We only deal with GET and HEAD by default
if (req.method != "GET" && req.method != "HEAD") {
return (pass);
}
#pass media to backend (already cached by CloudFront)
if (req.url ~ "^\/(media|bundles|css|fonts|js|theme|thumbnail)(\/.*)?$") {
return (pass);
}
# Don't cache Authenticate & Authorization
if (req.http.Authenticate || req.http.Authorization) {
return (pass);
}
# Always pass these paths directly to php without caching
# Note: virtual URLs might bypass this rule (e.g. /en/checkout)
if (req.url ~ "^/(checkout|account|admin|api)(/.*)?$") {
return (pass);
}
return (hash);
}
sub vcl_hash {
# Consider Shopware http cache cookies
if (req.http.cookie ~ "sw-cache-hash=") {
hash_data("+context=" + regsub(req.http.cookie, "^.*?sw-cache-hash=([^;]*);*.*$", "\1"));
} elseif (req.http.cookie ~ "sw-currency=") {
hash_data("+currency=" + regsub(req.http.cookie, "^.*?sw-currency=([^;]*);*.*$", "\1"));
}
#return(lookup);
}
sub vcl_hit {
# Consider client states for response headers
if (req.http.cookie ~ "sw-states=") {
set req.http.states = regsub(req.http.cookie, "^.*?sw-states=([^;]*);*.*$", "\1");
if (req.http.states ~ "logged-in" && obj.http.sw-invalidation-states ~ "logged-in" ) {
return (pass);
}
if (req.http.states ~ "cart-filled" && obj.http.sw-invalidation-states ~ "cart-filled" ) {
return (pass);
}
}
}
sub vcl_backend_response {
# Fix Vary Header in some cases
if (beresp.http.Vary ~ "User-Agent") {
set beresp.http.Vary = regsub(beresp.http.Vary, ",? *User-Agent *", "");
set beresp.http.Vary = regsub(beresp.http.Vary, "^, *", "");
if (beresp.http.Vary == "") {
unset beresp.http.Vary;
}
}
# Respect the Cache-Control=private header from the backend
if (
beresp.http.Pragma ~ "no-cache" ||
beresp.http.Cache-Control ~ "no-cache" ||
beresp.http.Cache-Control ~ "private"
) {
set beresp.ttl = 0s;
set beresp.http.X-Cacheable = "NO:Cache-Control=private";
set beresp.uncacheable = true;
return (deliver);
}
# strip the cookie before the image is inserted into cache.
if (bereq.url ~ "\.(png|gif|jpg|swf|css|js|webp)$") {
unset beresp.http.set-cookie;
}
# Allow items to be stale if needed.
set beresp.grace = 60s;
# Save the bereq.url so purges work efficiently
set beresp.http.x-url = bereq.url;
set beresp.http.X-Cacheable = "YES";
# Remove the exact PHP Version from the response for more security
unset beresp.http.x-powered-by;
return (deliver);
}
sub vcl_deliver {
## we don't want the client to cache
set resp.http.Cache-Control = "max-age=0, private";
# remove link header, if session is already started to save client resources
if (req.http.cookie ~ "session-") {
unset resp.http.Link;
}
# Set a cache header to allow us to inspect the response headers during testing
if (obj.hits > 0) {
unset resp.http.set-cookie;
set resp.http.X-Cache = "HIT";
} else {
set resp.http.X-Cache = "MISS";
}
# Remove the exact PHP Version from the response for more security (e.g. 404 pages)
unset resp.http.x-powered-by;
# invalidation headers are only for internal use
unset resp.http.sw-invalidation-states;
set resp.http.X-Cache-Hits = obj.hits;
}
Request where xkey is added
* << Request >> 32796
- Begin req 32795 rxreq
- Timestamp Start: 1664372821.615382 0.000000 0.000000
- Timestamp Req: 1664372821.615382 0.000000 0.000000
- VCL_use boot
- ReqStart 172.16.0.80 20244 a0
- ReqMethod GET
- ReqURL /it-it/prodotti/catene/catene-di-luci/
- ReqProtocol HTTP/1.1
- ReqHeader X-Forwarded-For: 84.247.245.84, 130.176.89.143
- ReqHeader X-Forwarded-Proto: https
- ReqHeader X-Forwarded-Port: 443
- ReqHeader Host: test-prod.luminalpark.com
- ReqHeader X-Amzn-Trace-Id: Root=1-63345055-76f876fd27d8613e28b7c9db
- ReqHeader User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/105.0.0.0 Safari/537.36 Edg/105.0.1343.53
- ReqHeader X-Amz-Cf-Id: JA7XrQuv5k-jhdhb3uKmlf88YjlJVvcDcw6udobH5vL-YkSMDT2flw==
- ReqHeader Via: 2.0 6c61cea6f371b1744d3b5315a0029062.cloudfront.net (CloudFront)
- ReqHeader Cookie: _dc_gtm_UA-830149-18=1; _ga=GA1.1.1015042543.1664369859; _ga_499EG6CXZD=GS1.1.1664371930.2.1.1664372814.0.0.0; _gcl_au=1.1.1616057317.1664369858; _gid=GA1.2.1284203691.1664369859; lp-platform=it-it; lp-state=IT; newUser=1; poll_manager=1; session
- ReqHeader Accept-Language: it,it-IT;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6,fr;q=0.5
- ReqHeader Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9
- ReqHeader Accept-Encoding: gzip, deflate, br
- ReqHeader cache-control: max-age=0
- ReqHeader sec-ch-ua: "Microsoft Edge";v="105", "Not)A;Brand";v="8", "Chromium";v="105"
- ReqHeader sec-ch-ua-mobile: ?0
- ReqHeader sec-ch-ua-platform: "Windows"
- ReqHeader dnt: 1
- ReqHeader upgrade-insecure-requests: 1
- ReqHeader sec-fetch-site: none
- ReqHeader sec-fetch-mode: navigate
- ReqHeader sec-fetch-user: ?1
- ReqHeader sec-fetch-dest: document
- ReqHeader CloudFront-Viewer-HTTP-Version: 2.0
- ReqHeader CloudFront-Forwarded-Proto: https
- ReqHeader CloudFront-Viewer-Address: 84.247.245.84:59146
- ReqHeader CloudFront-Viewer-TLS: TLSv1.3:TLS_AES_128_GCM_SHA256:connectionReused
- ReqHeader X-Cloudfront-Origin: VC5ZNQ588QNE3S
- ReqUnset X-Forwarded-For: 84.247.245.84, 130.176.89.143
- ReqHeader X-Forwarded-For: 84.247.245.84, 130.176.89.143, 172.16.0.80
- ReqUnset Via: 2.0 6c61cea6f371b1744d3b5315a0029062.cloudfront.net (CloudFront)
- ReqHeader Via: 2.0 6c61cea6f371b1744d3b5315a0029062.cloudfront.net (CloudFront), 1.1 ip-172-16-3-107 (Varnish/trunk)
- VCL_call RECV
- ReqHeader xkey: /it-it/prodotti/catene/catene-di-luci/
- ReqURL /it-it/prodotti/catene/catene-di-luci/
- ReqURL /it-it/prodotti/catene/catene-di-luci/
- ReqUnset Accept-Encoding: gzip, deflate, br
- ReqHeader Accept-Encoding: gzip
- VCL_return hash
- VCL_call HASH
- VCL_return lookup
- Hit 32771 7190.679091 60.000000 0.000000
- VCL_call HIT
- VCL_return deliver
- RespProtocol HTTP/1.1
- RespStatus 200
- RespReason OK
- RespHeader Server: nginx/1.18.0 (Ubuntu)
- RespHeader Content-Type: text/html; charset=UTF-8
- RespHeader Cache-Control: must-revalidate, public, s-maxage=7200
- RespHeader Date: Wed, 28 Sep 2022 13:46:52 GMT
- RespHeader Strict-Transport-Security: max-age=31536000; includeSubDomains
- RespHeader X-Frame-Options: deny
- RespHeader X-Content-Type-Options: nosniff
- RespHeader Referrer-Policy: strict-origin-when-cross-origin
- RespHeader sw-invalidation-states:
- RespHeader Set-Cookie: sw-states=deleted; expires=Tue, 28-Sep-2021 13:46:51 GMT; Max-Age=0; path=/; secure; httponly; samesite=lax
- RespHeader Set-Cookie: sw-cache-hash=deleted; expires=Tue, 28-Sep-2021 13:46:51 GMT; Max-Age=0; path=/; httponly
- RespHeader Content-Encoding: gzip
- RespHeader Vary: Accept-Encoding
- RespHeader x-url: /it-it/prodotti/catene/catene-di-luci/
- RespHeader X-Cacheable: YES
- RespHeader X-Varnish: 32796 32771
- RespHeader Age: 9
- RespHeader Via: 1.1 ip-172-16-3-107 (Varnish/trunk)
- RespHeader Accept-Ranges: bytes
- VCL_call DELIVER
- RespUnset Cache-Control: must-revalidate, public, s-maxage=7200
- RespHeader Cache-Control: max-age=0, private
- RespUnset Set-Cookie: sw-states=deleted; expires=Tue, 28-Sep-2021 13:46:51 GMT; Max-Age=0; path=/; secure; httponly; samesite=lax
- RespUnset Set-Cookie: sw-cache-hash=deleted; expires=Tue, 28-Sep-2021 13:46:51 GMT; Max-Age=0; path=/; httponly
- RespHeader X-Cache: HIT
- RespUnset sw-invalidation-states:
- RespHeader X-Cache-Hits: 1
- VCL_return deliver
- Timestamp Process: 1664372821.615457 0.000074 0.000074
- Filters
- RespHeader Content-Length: 110820
- RespHeader Connection: keep-alive
- Timestamp Resp: 1664372821.615548 0.000166 0.000091
- ReqAcct 1598 0 1598 619 110820 111439
- End
Purge request log, showing no objects found:
* << Request >> 1277962
- Begin req 1277960 rxreq
- Timestamp Start: 1664372901.809064 0.000000 0.000000
- Timestamp Req: 1664372901.809064 0.000000 0.000000
- VCL_use boot
- ReqStart 172.16.2.136 51214 a0
- ReqMethod PURGE
- ReqURL /it-it/prodotti/catene/catene-di-luci/
- ReqProtocol HTTP/1.1
- ReqHeader Host: 172.16.3.107
- ReqHeader User-Agent: GuzzleHttp/7
- ReqHeader X-Forwarded-For: 172.16.2.136
- ReqHeader Via: 1.1 ip-172-16-3-107 (Varnish/trunk)
- VCL_call RECV
- ReqHeader xkey: /it-it/prodotti/catene/catene-di-luci/
- ReqURL /it-it/prodotti/catene/catene-di-luci/
- ReqURL /it-it/prodotti/catene/catene-di-luci/
- ReqHeader x-purges: 0
- VCL_return synth
- VCL_call HASH
- VCL_Log hashing for BAN request
- VCL_return lookup
- RespProtocol HTTP/1.1
- RespStatus 200
- RespReason Invalidated 0 objects
- RespHeader Date: Wed, 28 Sep 2022 13:48:21 GMT
- RespHeader Server: Varnish
- RespHeader X-Varnish: 1277962
- VCL_call SYNTH
- RespHeader Content-Type: text/html; charset=utf-8
- RespHeader Retry-After: 5
- VCL_return deliver
- Timestamp Process: 1664372901.809126 0.000061 0.000061
- RespHeader Content-Length: 287
- Storage malloc Transient
- Filters
- RespHeader Connection: keep-alive
- Timestamp Resp: 1664372901.809155 0.000090 0.000029
- ReqAcct 101 0 101 213 287 500
- End
It's perfectly possible, but you need to add the header to beresp object (in vcl_backend_response) to have the objects properly tagged