diff options
| author |  Ruslan Drozhdzh <30860269+rdrozhdzh@users.noreply.github.com>
| 2020-09-14 12:42:55 +0300 |
|---|---|---|
| committer |  GitHub <noreply@github.com>
| 2020-09-14 11:42:55 +0200 |
| commit | 30a4a87eaa3c4974cbfb7cc746b2d3f21842523a (patch) | |
| tree | 8151d02dbbbd427df7e9ce13736f57fb0140e4d1 | |
| parent | 2fe5d684f9d9bf5691ef0bceb06d7838d66d3cd7 (diff) | |
| download | coredns-30a4a87eaa3c4974cbfb7cc746b2d3f21842523a.tar.gz coredns-30a4a87eaa3c4974cbfb7cc746b2d3f21842523a.tar.zst coredns-30a4a87eaa3c4974cbfb7cc746b2d3f21842523a.zip | |
plugin/forward: add hit/miss metrics for connection cache (#4114)
Signed-off-by: Ruslan Drozhdzh <rdrozhdzh@infoblox.com>
| -rw-r--r-- | plugin/forward/README.md | 6 | ||||
| -rw-r--r-- | plugin/forward/connect.go | 2 | ||||
| -rw-r--r-- | plugin/forward/metrics.go | 12 |
3 files changed, 18 insertions, 2 deletions
diff --git a/plugin/forward/README.md b/plugin/forward/README.md index 46422b263..e7eb577d0 100644 --- a/plugin/forward/README.md +++ b/plugin/forward/README.md @@ -112,10 +112,12 @@ If monitoring is enabled (via the *prometheus* plugin) then the following metric * `coredns_forward_healthcheck_failures_total{to}` - number of failed health checks per upstream. * `coredns_forward_healthcheck_broken_total{}` - counter of when all upstreams are unhealthy, and we are randomly (this always uses the `random` policy) spraying to an upstream. -* `max_concurrent_rejects_total{}` - counter of the number of queries rejected because the +* `coredns_forward_max_concurrent_rejects_total{}` - counter of the number of queries rejected because the number of concurrent queries were at maximum. +* `coredns_forward_conn_cache_hits_total{to, proto}` - counter of connection cache hits per upstream and protocol. +* `coredns_forward_conn_cache_misses_total{to, proto}` - counter of connection cache misses per upstream and protocol. Where `to` is one of the upstream servers (**TO** from the config), `rcode` is the returned RCODE -from the upstream. +from the upstream, `proto` is the transport protocol like `udp`, `tcp`, `tcp-tls`. ## Examples diff --git a/plugin/forward/connect.go b/plugin/forward/connect.go index 9ac1afe16..c181c98cb 100644 --- a/plugin/forward/connect.go +++ b/plugin/forward/connect.go @@ -54,8 +54,10 @@ func (t *Transport) Dial(proto string) (*persistConn, bool, error) { pc := <-t.ret if pc != nil { + ConnCacheHitsCount.WithLabelValues(t.addr, proto).Add(1) return pc, true, nil } + ConnCacheMissesCount.WithLabelValues(t.addr, proto).Add(1) reqTime := time.Now() timeout := t.dialTimeout() diff --git a/plugin/forward/metrics.go b/plugin/forward/metrics.go index 0b63ce1e7..98f2805c1 100644 --- a/plugin/forward/metrics.go +++ b/plugin/forward/metrics.go @@ -52,4 +52,16 @@ var ( Name: "max_concurrent_rejects_total", Help: "Counter of the number of queries rejected because the concurrent queries were at maximum.", }) + ConnCacheHitsCount = promauto.NewCounterVec(prometheus.CounterOpts{ + Namespace: plugin.Namespace, + Subsystem: "forward", + Name: "conn_cache_hits_total", + Help: "Counter of connection cache hits per upstream and protocol.", + }, []string{"to", "proto"}) + ConnCacheMissesCount = promauto.NewCounterVec(prometheus.CounterOpts{ + Namespace: plugin.Namespace, + Subsystem: "forward", + Name: "conn_cache_misses_total", + Help: "Counter of connection cache misses per upstream and protocol.", + }, []string{"to", "proto"}) ) |