added alarm when interfaces stop collected
Costa Tsaousis (ktsaou) committed
Sep 11, 2016 at 22:07 UTC
c090301a86df52845742102c9f361c0fc2a0057b
1 file changed
+19
-2
conf.d/health.d/net.conf
+19
-2
@@ -1,6 +1,21 @@
1
+# -----------------------------------------------------------------------------
2
+# make sure we collect values for each interface
3
+
4
+template: interface_last_collected_secs
5
+ on: net.net
6
+ calc: $now - $last_collected_t
7
+ every: 10s
8
+ warn: $this > ( 5 * $update_every)
9
+ crit: $this > (60 * $update_every)
10
+ units: seconds ago
11
+ info: number of seconds since the last successful data collection
12
+ to: sysadmin
13
+
14
+
15
+# -----------------------------------------------------------------------------
16
17
# check if an interface is dropping packets
3
-# the alarm is checked every 10 seconds
18
+# the alarm is checked every 1 minute
19
# and examines the last hour of data
20
21
template: 1hour_packet_drops
@@ -13,9 +28,11 @@ template: 1hour_packet_drops
28
to: sysadmin
29
30
31
+# -----------------------------------------------------------------------------
32
+
33
# check if an interface is having FIFO
34
# buffer errors
18
-# the alarm is checked every 10 seconds
35
+# the alarm is checked every 1 minute
36
# and examines the last hour of data
37
38
template: 1hour_fifo_errors