[PATCH 1 of 1 RFC] Better recheck of dead upstream servers
Maxim Dounin
mdounin at mdounin.ru
Tue Sep 27 12:24:03 UTC 2011
# HG changeset patch
# User Maxim Dounin <mdounin at mdounin.ru>
# Date 1317126090 -14400
# Node ID a0fc6910248f8f92ff8b7cc1465ba3fd8cd8c52d
# Parent a0228f0e9fe2ad166324a80bc915ad8ec1050dcc
Better recheck of dead upstream servers.
Previously nginx used to mark backend again as live as soon as fail_timeout
passes (10s by default) since last failure. On the other hand, detecting
dead backend takes up to 60s (proxy_connect_timeout) in typical situation
"backend is down and doesn't respond to any packets". This resulted in
suboptimal behaviour in the above situation (up to 23% of requests were
directed to dead backend with default settings).
More detailed description of the problem may be found here (in Russian):
http://mailman.nginx.org/pipermail/nginx-ru/2011-August/042172.html
Fix is to only allow one request after fail_timeout passes, and
mark backend as "live" only if this request succeeds.
Note that with new code backend will not be marked "live" unless "check"
request is completed, and this may take a while in some specific workloads
(e.g. streaming). This is believed to be acceptable.
diff --git a/src/http/modules/ngx_http_upstream_ip_hash_module.c b/src/http/modules/ngx_http_upstream_ip_hash_module.c
--- a/src/http/modules/ngx_http_upstream_ip_hash_module.c
+++ b/src/http/modules/ngx_http_upstream_ip_hash_module.c
@@ -185,8 +185,8 @@ ngx_http_upstream_get_ip_hash_peer(ngx_p
break;
}
- if (now - peer->accessed > peer->fail_timeout) {
- peer->fails = 0;
+ if (now - peer->checked > peer->fail_timeout) {
+ peer->checked = now;
break;
}
}
diff --git a/src/http/ngx_http_upstream_round_robin.c b/src/http/ngx_http_upstream_round_robin.c
--- a/src/http/ngx_http_upstream_round_robin.c
+++ b/src/http/ngx_http_upstream_round_robin.c
@@ -443,8 +443,8 @@ ngx_http_upstream_get_round_robin_peer(n
break;
}
- if (now - peer->accessed > peer->fail_timeout) {
- peer->fails = 0;
+ if (now - peer->checked > peer->fail_timeout) {
+ peer->checked = now;
break;
}
@@ -491,8 +491,8 @@ ngx_http_upstream_get_round_robin_peer(n
break;
}
- if (now - peer->accessed > peer->fail_timeout) {
- peer->fails = 0;
+ if (now - peer->checked > peer->fail_timeout) {
+ peer->checked = now;
break;
}
@@ -663,15 +663,16 @@ ngx_http_upstream_free_round_robin_peer(
return;
}
+ peer = &rrp->peers->peer[rrp->current];
+
if (state & NGX_PEER_FAILED) {
now = ngx_time();
- peer = &rrp->peers->peer[rrp->current];
-
/* ngx_lock_mutex(rrp->peers->mutex); */
peer->fails++;
peer->accessed = now;
+ peer->checked = now;
if (peer->max_fails) {
peer->current_weight -= peer->weight / peer->max_fails;
@@ -686,6 +687,14 @@ ngx_http_upstream_free_round_robin_peer(
}
/* ngx_unlock_mutex(rrp->peers->mutex); */
+
+ } else {
+
+ /* mark peer live if check passed */
+
+ if (peer->accessed < peer->checked) {
+ peer->fails = 0;
+ }
}
rrp->current++;
diff --git a/src/http/ngx_http_upstream_round_robin.h b/src/http/ngx_http_upstream_round_robin.h
--- a/src/http/ngx_http_upstream_round_robin.h
+++ b/src/http/ngx_http_upstream_round_robin.h
@@ -23,6 +23,7 @@ typedef struct {
ngx_uint_t fails;
time_t accessed;
+ time_t checked;
ngx_uint_t max_fails;
time_t fail_timeout;
More information about the nginx-devel
mailing list