MINOR: leastconn: take the queue length into account when queuing servers
When servers are queued into the leastconn tree, it's important to also
consider their queue length. There could be some servers with lots of
queued requests that we don't want to hammer with extra connections. In
order not to add extra stress to the LB algorithm, we don't update the
value when adding to the queue, only when updating the connection count
(i.e. picking from the queue or releasing a connection). This will be
sufficient to significantly improve the fairness in such situations.
diff --git a/doc/configuration.txt b/doc/configuration.txt
index ea6c589..6116f25 100644
--- a/doc/configuration.txt
+++ b/doc/configuration.txt
@@ -3205,7 +3205,9 @@
expected, such as LDAP, SQL, TSE, etc... but is not very well
suited for protocols using short sessions such as HTTP. This
algorithm is dynamic, which means that server weights may be
- adjusted on the fly for slow starts for instance.
+ adjusted on the fly for slow starts for instance. It will
+ also consider the number of queued connections in addition to
+ the established ones in order to minimize queuing.
first The first server with available connection slots receives the
connection. The servers are chosen from the lowest numeric
diff --git a/src/lb_fwlc.c b/src/lb_fwlc.c
index 78a38a4..c7e0dd8 100644
--- a/src/lb_fwlc.c
+++ b/src/lb_fwlc.c
@@ -51,7 +51,9 @@
*/
static inline void fwlc_queue_srv(struct server *s)
{
- s->lb_node.key = s->served ? (s->served + 1) * SRV_EWGHT_MAX / s->next_eweight : 0;
+ unsigned int inflight = s->served + s->nbpend;
+
+ s->lb_node.key = inflight ? (inflight + 1) * SRV_EWGHT_MAX / s->next_eweight : 0;
eb32_insert(s->lb_tree, &s->lb_node);
}