Estamos com um problema estranho com a configuração atual do Varnish.
Servidores Web 4x (IIS 6.5 no Windows 2003 Server, cada um instalado em uma CPU Intel (R) Xeon (R) E5450 @ 3.00GHz Quad Core, 4 GB de RAM)
Servidores Varnish 3x (verniz-3.0.3 revisão 9e6a70f no Ubuntu 12.04.2 LTS - 64 bit / preciso, kernel Linux 3.2.0-29-genérico, cada um instalado em um processador Intel (R) Xeon (R) CPU E5450 @ 3,00 GHz Quad Core, 4 GB de RAM)
O desempenho do Varnish Servers é muito ruim em geral, a ponto de, se desligarmos um deles, os outros dois não conseguirem preencher todos os pedidos e começarem a pular batidas, resultando em solicitações pendentes, tempos limite, 404, etc.
O que podemos fazer para melhorar nosso desempenho em verniz? Considerando que estamos recebendo menos de 5 mil solicitações por segundo durante o nosso pico máximo, poderemos servir nossas páginas mesmo com uma única delas sem qualquer problema.
Usamos um padrão CFG vanilla, conforme mostrado por esta saída varnishadm > param.show:
acceptor_sleep_decay 0.900000 []
acceptor_sleep_incr 0.001000 [s]
acceptor_sleep_max 0.050000 [s]
auto_restart on [bool]
ban_dups on [bool]
ban_lurker_sleep 0.010000 [s]
between_bytes_timeout 60.000000 [s]
cc_command "exec gcc -std=gnu99 -g -O2 -pthread -fpic -shared - Wl,-x -o %o %s"
cli_buffer 8192 [bytes]
cli_timeout 20 [seconds]
clock_skew 10 [s]
connect_timeout 0.700000 [s]
critbit_cooloff 180.000000 [s]
default_grace 10.000000 [seconds]
default_keep 0.000000 [seconds]
default_ttl 120.000000 [seconds]
diag_bitmap 0x0 [bitmap]
esi_syntax 0 [bitmap]
expiry_sleep 1.000000 [seconds]
fetch_chunksize 128 [kilobytes]
fetch_maxchunksize 262144 [kilobytes]
first_byte_timeout 60.000000 [s]
group varnish (113)
gzip_level 6 []
gzip_memlevel 8 []
gzip_stack_buffer 32768 [Bytes]
gzip_tmp_space 0 []
gzip_window 15 []
http_gzip_support off [bool]
http_max_hdr 64 [header lines]
http_range_support on [bool]
http_req_hdr_len 8192 [bytes]
http_req_size 32768 [bytes]
http_resp_hdr_len 8192 [bytes]
http_resp_size 32768 [bytes]
idle_send_timeout 60 [seconds]
listen_address :80
listen_depth 1024 [connections]
log_hashstring on [bool]
log_local_address off [bool]
lru_interval 2 [seconds]
max_esi_depth 5 [levels]
max_restarts 4 [restarts]
nuke_limit 50 [allocations]
pcre_match_limit 10000 []
pcre_match_limit_recursion 10000 []
ping_interval 3 [seconds]
pipe_timeout 60 [seconds]
prefer_ipv6 off [bool]
queue_max 100 [%]
rush_exponent 3 [requests per request]
saintmode_threshold 10 [objects]
send_timeout 600 [seconds]
sess_timeout 5 [seconds]
sess_workspace 16384 [bytes]
session_linger 50 [ms]
session_max 100000 [sessions]
shm_reclen 255 [bytes]
shm_workspace 8192 [bytes]
shortlived 10.000000 [s]
syslog_cli_traffic on [bool]
thread_pool_add_delay 2 [milliseconds]
thread_pool_add_threshold 2 [requests]
thread_pool_fail_delay 200 [milliseconds]
thread_pool_max 2000 [threads]
thread_pool_min 5 [threads]
thread_pool_purge_delay 1000 [milliseconds]
thread_pool_stack unlimited [bytes]
thread_pool_timeout 300 [seconds]
thread_pool_workspace 65536 [bytes]
thread_pools 2 [pools]
thread_stats_rate 10 [requests]
user varnish (106)
vcc_err_unref on [bool]
vcl_dir /etc/varnish
vcl_trace off [bool]
vmod_dir /usr/lib/varnish/vmods
waiter default (epoll, poll)
Este é o nosso arquivo default.vcl: LINK
sub vcl_recv {
# BASIC recv COMMANDS:
#
# lookup -> search the item in the cache
# pass -> always serve a fresh item (no-caching)
# pipe -> like pass but ensures a direct-connection with the backend (no-cache AND no-proxy)
# Allow the backend to serve up stale content if it is responding slow.
# This defines when Varnish should use a stale object if it has one in the cache.
set req.grace = 30s;
if (client.ip == "127.0.0.1") {
# request from NGINX - do not alter X-Forwarded-For
set req.http.HTTPS = "on";
}
else {
# Add an X-Forwarded-For to keep track of original request
unset req.http.HTTPS;
unset req.http.X-Forwarded-For;
set req.http.X-Forwarded-For = client.ip;
}
set req.backend = www_director;
# Strip all cookies to force an anonymous request when the back-end servers are down.
if (!req.backend.healthy) {
unset req.http.Cookie;
}
## HHTP Accept-Encoding
if (req.http.Accept-Encoding) {
if (req.http.Accept-Encoding ~ "gzip") {
set req.http.Accept-Encoding = "gzip";
}
else if (req.http.Accept-Encoding ~ "deflate") {
set req.http.Accept-Encoding = "deflate";
}
else {
unset req.http.Accept-Encoding;
}
}
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 */
return (pipe);
}
if (req.request != "GET" && req.request != "HEAD") {
/* only deal with GET and HEAD by default */
return (pass);
}
if (req.http.Authorization) {
return (pass);
}
if (req.http.HTTPS ~ "on") {
return (pass);
}
######################################################
# COOKIE HANDLING
######################################################
# METHOD 1: do not remove cookies, but pass the page if they contain TB_NC
if (!(req.url ~ "(?i)\.(png|gif|ipeg|jpg|ico|swf|css|js)(\?[a-z0-9]+)?$")) {
if (req.http.Cookie && req.http.Cookie ~ "TB_NC") {
return (pass);
}
}
return (lookup);
}
# Code determining what to do when serving items from the IIS Server
sub vcl_fetch {
unset beresp.http.Server;
set beresp.http.Server = "Server-1";
# Allow items to be stale if needed. This is the maximum time Varnish should keep an object.
set beresp.grace = 1h;
if (req.url ~ "(?i)\.(png|gif|ipeg|jpg|ico|swf|css|js)(\?[a-z0-9]+)?$") {
unset beresp.http.set-cookie;
}
# Default Varnish VCL logic
if (!beresp.cacheable ||
beresp.ttl <= 0s ||
beresp.http.Set-Cookie ||
beresp.http.Vary == "*") {
set beresp.ttl = 120 s;
return(hit_for_pass);
}
# Not Cacheable if it has specific TB_NC no-caching cookie
if (req.http.Cookie && req.http.Cookie ~ "TB_NC") {
set beresp.http.X-Cacheable = "NO:Got Cookie";
set beresp.ttl = 120 s;
return(hit_for_pass);
}
# Not Cacheable if it has Cache-Control private
else if (beresp.http.Cache-Control ~ "private") {
set beresp.http.X-Cacheable = "NO:Cache-Control=private";
set beresp.ttl = 120 s;
return(hit_for_pass);
}
# Not Cacheable if it has Cache-Control no-cache or Pragma no-cache
else if (beresp.http.Cache-Control ~ "no-cache" || beresp.http.Pragma ~ "no-cache") {
set beresp.http.X-Cacheable = "NO:Cache-Control=no-cache (or pragma no-cache)";
set beresp.ttl = 120 s;
return(hit_for_pass);
}
# If we reach to this point, the object is cacheable.
# Cacheable but with not enough ttl: we need to extend the lifetime of the object artificially
# NOTE: Varnish default TTL is set in /etc/sysconfig/varnish
# and can be checked using the following command:
# varnishadm param.show default_ttl
else if (beresp.ttl < 1s) {
set beresp.ttl = 5s;
set beresp.grace = 5s;
set beresp.http.X-Cacheable = "YES:FORCED";
}
# Cacheable and with valid TTL.
else {
set beresp.http.X-Cacheable = "YES";
}
# DEBUG INFO (Cookies)
# set beresp.http.X-Cookie-Debug = "Request cookie: " + req.http.Cookie;
return(deliver);
}
sub vcl_error {
set obj.http.Content-Type = "text/html; charset=utf-8";
if (obj.status == 404) {
synthetic {"
<!-- Markup for the 404 page goes here -->
"};
}
else if (obj.status == 500) {
synthetic {"
<!-- Markup for the 500 page goes here -->
"};
}
else if (obj.status == 503) {
if (req.restarts < 4) { return(restart); }
else {
synthetic {"
<!-- Markup for the 503 page goes here -->
"};
}
}
else {
synthetic {"
<!-- Markup for a generic error page goes here -->
"};
}
}
sub vcl_deliver {
if (obj.hits > 0) {
set resp.http.X-Cache = "HIT";
} else {
set resp.http.X-Cache = "MISS";
}
}
Agradecemos antecipadamente
Você não postou a única coisa útil para resolver problemas de desempenho; "varnishstat -1". Então, aqui estão alguns conselhos gerais.
min_threads para que o verniz possa ter alguns tópicos por aí. /var/lib/varnish on tmpfs (o Linux grava a memória compartilhada em disco.
meh). Eu tinha quase o mesmo problema, e descobri que aumentar os limites de memlock e nofile na minha caixa Ubuntu dramaticamente aumentou o desempenho. Por exemplo, acrescente o seguinte ao seu /etc/security/limits.conf:
root soft nofile 100000
root hard nofile 200000
root soft memlock 100000
root hard memlock 200000
Em /etc/pam.d/common-session, anexe:
session required pam_limits.so
Por fim, no seu / etc / default / verniz, verifique se você tem:
NFILES=-n
MEMLOCK=-l
Em seguida, reinicie e assista os fogos de artifício!
Eu obtive minha solução aqui: link