我们有一个 Varnish 服务器在 Magento 站点前面运行。我们发现 Magento 在提供页面时非常慢,因此我们希望 Varnish 从缓存中提供所有类别和产品页面。
我们对 VCL 文件进行了更改,以确保 TTL 和宽限期设置为 365 天,以确保页面尽可能长时间地保留在内存中。我们每天运行一个缓存预热器,它会查看站点地图并向每个 URL 发出请求以预热缓存。我们看到的问题是,一些在缓存预热器运行时是热的页面(根据 HIT/MISS 标头)在稍后检查时不再获得缓存命中。
我知道可以使对象从缓存中失效的几种方法:
有没有办法使用相关页面的 URL 来确定上述哪种情况导致对象失效?这将帮助我们追踪导致对象失效的原因并防止这种情况发生。
VCL(如果相关):
# VCL version 5.0 is not supported so it should be 4.0 even though actually used Varnish version is 5
vcl 4.0;
import std;
# The minimal Varnish version is 5.0
# For SSL offloading, pass the following header in your proxy server or load balancer: 'X-Forwarded-Proto: https'
backend default {
.host = "127.0.0.1";
.port = "8181";
.first_byte_timeout = 600s;
.probe = {
.url = "/pub/health_check.php";
.timeout = 2s;
.interval = 5s;
.window = 10;
.threshold = 5;
}
}
#acl purge {
# "127.0.0.1";
#}
sub vcl_recv {
if (req.method == "PURGE") {
#if (client.ip !~ purge) {
return (synth(405, "Method not allowed"));
#}
# To use the X-Pool header for purging varnish during automated deployments, make sure the X-Pool header
# has been added to the response in your backend server config. This is used, for example, by the
# capistrano-magento2 gem for purging old content from varnish during it's deploy routine.
#if (!req.http.X-Magento-Tags-Pattern && !req.http.X-Pool) {
# return (synth(400, "X-Magento-Tags-Pattern or X-Pool header required"));
#}
#if (req.http.X-Magento-Tags-Pattern) {
# ban("obj.http.X-Magento-Tags ~ " + req.http.X-Magento-Tags-Pattern);
#}
#if (req.http.X-Pool) {
# ban("obj.http.X-Pool ~ " + req.http.X-Pool);
#}
#return (synth(200, "Purged"));
}
if (req.method != "GET" &&
req.method != "HEAD" &&
req.method != "PUT" &&
req.method != "POST" &&
req.method != "TRACE" &&
req.method != "OPTIONS" &&
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);
}
# Bypass shopping cart, checkout and search requests
if (req.url ~ "/checkout" || req.url ~ "/catalogsearch") {
return (pass);
}
# Bypass health check requests
if (req.url ~ "/pub/health_check.php") {
return (pass);
}
# Set initial grace period usage status
set req.http.grace = "none";
# normalize url in case of leading HTTP scheme and domain
set req.url = regsub(req.url, "^http[s]?://", "");
# collect all cookies
std.collect(req.http.Cookie);
# Compression filter. See https://www.varnish-cache.org/trac/wiki/FAQ/Compression
if (req.http.Accept-Encoding) {
if (req.url ~ "\.(jpg|jpeg|png|gif|gz|tgz|bz2|tbz|mp3|ogg|swf|flv)$") {
# No point in compressing these
unset req.http.Accept-Encoding;
} elsif (req.http.Accept-Encoding ~ "gzip") {
set req.http.Accept-Encoding = "gzip";
} elsif (req.http.Accept-Encoding ~ "deflate" && req.http.user-agent !~ "MSIE") {
set req.http.Accept-Encoding = "deflate";
} else {
# unknown algorithm
unset req.http.Accept-Encoding;
}
}
# Remove Google gclid parameters to minimize the cache objects
set req.url = regsuball(req.url,"\?gclid=[^&]+$",""); # strips when QS = "?gclid=AAA"
set req.url = regsuball(req.url,"\?gclid=[^&]+&","?"); # strips when QS = "?gclid=AAA&foo=bar"
set req.url = regsuball(req.url,"&gclid=[^&]+",""); # strips when QS = "?foo=bar&gclid=AAA" or QS = "?foo=bar&gclid=AAA&bar=baz"
# Static files caching
if (req.url ~ "^/(pub/)?(media|static)/") {
# Static files should not be cached by default
#return (pass);
# But if you use a few locales and don't use CDN you can enable caching static files by commenting previous line (#return (pass);) and uncommenting next 3 lines
unset req.http.Https;
unset req.http.X-Forwarded-Proto;
unset req.http.Cookie;
}
#bypass for elasticsuite trackers
if(req.url ~ "elasticsuite/tracker"){
return (pass);
}
#bypass api requests
if(req.url ~ "/rest/"){
return (pass);
}
#bypass sale nav
if(req.url ~ "saleNavMarkup.php"){
return (pass);
}
return (hash);
}
sub vcl_hash {
# if (req.http.cookie ~ "X-Magento-Vary=") {
# hash_data(regsub(req.http.cookie, "^.*?X-Magento-Vary=([^;]+);*.*$", "\1"));
# }
# For multi site configurations to not cache each other's content
if (req.http.host) {
hash_data(req.http.host);
} else {
hash_data(server.ip);
}
# To make sure http users don't see ssl warning
if (req.http.X-Forwarded-Proto) {
hash_data(req.http.X-Forwarded-Proto);
}
}
sub vcl_backend_response {
set beresp.ttl = 365d;
set beresp.grace = 365d;
if (beresp.http.content-type ~ "text") {
set beresp.do_esi = true;
}
if (bereq.url ~ "\.js$" || beresp.http.content-type ~ "text") {
set beresp.do_gzip = true;
}
if (beresp.http.X-Magento-Debug) {
set beresp.http.X-Magento-Cache-Control = beresp.http.Cache-Control;
}
# cache only successfully responses and 404s
if (beresp.status != 200 && beresp.status != 404) {
set beresp.ttl = 0s;
set beresp.uncacheable = true;
return (deliver);
} elsif (beresp.http.Cache-Control ~ "private") {
set beresp.uncacheable = true;
set beresp.ttl = 120s;
return (deliver);
}
# validate if we need to cache it and prevent from setting cookie
if (beresp.ttl > 0s && (bereq.method == "GET" || bereq.method == "HEAD")) {
unset beresp.http.set-cookie;
}
# If page is not cacheable then bypass varnish for 2 minutes as Hit-For-Pass
if (beresp.ttl <= 0s ||
beresp.http.Surrogate-control ~ "no-store" ||
(!beresp.http.Surrogate-Control &&
beresp.http.Cache-Control ~ "no-cache|no-store") ||
beresp.http.Vary == "*") {
# Mark as Hit-For-Pass for the next 2 minutes
set beresp.ttl = 120s;
set beresp.uncacheable = true;
}
return (deliver);
}
sub vcl_deliver {
#if (resp.http.X-Magento-Debug) {
if (resp.http.x-varnish ~ " ") {
set resp.http.X-Magento-Cache-Debug = "HIT";
set resp.http.Grace = req.http.grace;
} else {
set resp.http.X-Magento-Cache-Debug = "MISS";
}
#} else {
# unset resp.http.Age;
#}
# Not letting browser to cache non-static files.
if (resp.http.Cache-Control !~ "private" && req.url !~ "^/(pub/)?(media|static)/") {
set resp.http.Pragma = "no-cache";
set resp.http.Expires = "-1";
set resp.http.Cache-Control = "no-store, no-cache, must-revalidate, max-age=0";
}
unset resp.http.X-Magento-Debug;
unset resp.http.X-Magento-Tags;
unset resp.http.X-Powered-By;
unset resp.http.Server;
unset resp.http.X-Varnish;
unset resp.http.Via;
unset resp.http.Link;
}
sub vcl_hit {
if (obj.ttl >= 0s) {
# Hit within TTL period
return (deliver);
}
if (std.healthy(req.backend_hint)) {
if (obj.ttl + 300s > 0s) {
# Hit after TTL expiration, but within grace period
set req.http.grace = "normal (healthy server)";
return (deliver);
} else {
# Hit after TTL and grace expiration
return (miss);
}
} else {
# server is not healthy, retrieve from cache
set req.http.grace = "unlimited (unhealthy server)";
return (deliver);
}
}
日志是你最好的朋友:
varnishlog
可以非常详细地回答这个问题。挑战(一如既往)是在查看 varnishlog
输出时重现问题。
我会制定一些策略,让这件事变得更容易。
每个交易都有一个 vxid,这是通过
X-Varnish
响应标头公开的唯一交易 ID。
日志项也通过该事务 ID 来标识。如果您知道未命中的
X-Varnish
标头的值,您有机会在日志中查找该值。
想象一下,您正在尝试跟踪一个事务,其中
X-Varnish: 5
标头是响应的一部分。这将导致以下 varnishlog
命令:
sudo varnishlog -d -g request -q "vxid == 5"
如您所见,
-q
选项用于根据日志中的vxid
标签进行过滤。 -d
选项将转储 Varnish 共享内存日志的内容,而不是寻找新的输入。
但是,由于 Varnish 共享内存日志存储在内存中以避免性能下降,因此您必须幸运的是,您正在查找的事务尚未被覆盖。
有两种方法可以解决这个潜在的限制:
增加 VSL 缓冲区可以在
varnishadm
中完成。默认情况下,vsl_space
运行时参数设置为 80 MB。如果我们暂时将其增加到 500 MB,可以在 Varnish 服务器上运行以下命令:
sudo varnishadm param.set vsl_space 500M
sudo varnishadm stop
sudo varnishadm start
需要重新启动子进程才能更改
vsl_space
的值。重新启动 varnishd
将撤消此设置。
stop
和start
命令将导致清空缓存。请记住这一点。
运行以下命令来验证更改:
sudo varnishadm param.show vsl_space
vsl_space
Value is: 500M [bytes]
Default is: 80M
Minimum is: 1M
Maximum is: 4G
The amount of space to allocate for the VSL fifo buffer in the
VSM memory segment. If you make this too small,
varnish{ncsa|log} etc will not be able to keep up. Making it
too large just costs memory resources.
NB: This parameter will not take any effect until the child
process has been restarted.
另一种选择是将日志存储在磁盘上。虽然这有能力捕获更多相关交易,但也存在风险:
如果您确实想将日志写入磁盘,我建议将它们存储为二进制格式,以便您稍后可以使用
varnishlog
重播它们。
这是您需要的命令:
sudo varnishlog -g session -a -w /var/log/vsl.log
如果您已经知道要过滤的 URL,则在
varnishlog
命令中包含 URL 过滤器会有所帮助。这是主页的示例:
sudo varnishlog -g session -q "ReqUrl eq '/'" -a -w /var/log/vsl.log
URL过滤器将大大减轻服务器的压力,并使整个事情变得更加轻量。
然后可以使用以下命令重播
varnishlog
中的日志:
sudo varnishlog -g request -r /var/log/vsl.log
有一整套 VSL 标签可以暴露您面临的问题。完整列表可以在 https://varnish-cache.org/docs/trunk/reference/vsl.html.
找到对于您的情况,我建议密切关注以下几点:
ExpBan
ExpKill
Hit
HitMiss
HitPass
TTL
VCL_call
VCL_return
当您追踪到最终失败的交易的完整日志时,请毫不犹豫地将此交易的完整
varnishlog
输出附加到您的问题中。
当你有信息时我会帮你调试。