Merge tag 'upstream/1.5.0+dfsg'

Upstream version 1.5.0+dfsg

1 files changed, 45 insertions, 0 deletions

diff --git a/conf.d/health.d/backend.conf b/conf.d/health.d/backend.conf
new file mode 100644
index 00000000..9c193e7b
--- /dev/null
+++ b/conf.d/health.d/backend.conf
@@ -0,0 +1,45 @@
+
+# make sure we are sending data to backend
+
+   alarm: backend_last_buffering
+      on: netdata.backend_metrics
+    calc: $now - $last_collected_t
+   units: seconds ago
+   every: 10s
+    warn: $this > (($status >= $WARNING)  ? ($update_every) : ( 5 * $update_every))
+    crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
+   delay: down 5m multiplier 1.5 max 1h
+    info: number of seconds since the last successful buffering of backend data
+      to: dba
+
+   alarm: backend_metrics_sent
+      on: netdata.backend_metrics
+   units: %
+    calc: abs($sent) * 100 / abs($buffered)
+   every: 10s
+    warn: $this != 100
+   delay: down 5m multiplier 1.5 max 1h
+    info: percentage of metrics sent to the backend server
+      to: dba
+
+   alarm: backend_metrics_lost
+      on: netdata.backend_metrics
+   units: metrics
+    calc: abs($lost)
+   every: 10s
+    crit: $this != 0
+   delay: down 5m multiplier 1.5 max 1h
+    info: number of metrics lost due to repeating failures to contact the backend server
+      to: dba
+
+# this chart has been removed from netdata
+#   alarm: backend_slow
+#      on: netdata.backend_latency
+#   units: %
+#    calc: $latency * 100 / ($update_every * 1000)
+#   every: 10s
+#    warn: $this > 50
+#    crit: $this > 100
+#   delay: down 5m multiplier 1.5 max 1h
+#    info: the percentage of time between iterations needed by the backend time to process the data sent by netdata
+#      to: dba