add ping dashboard info and alarms (#13916)
Co-authored-by: Shyam Sreevalsan <shyam@netdata.cloud>
Ilya Mashchenko committed
Oct 31, 2022 at 21:24 UTC
3a2dc5149b1cf2e41794b741e4cb24ee107f069e
3 files changed
+68
health/Makefile.am
+1
@@ -67,6 +67,7 @@ dist_healthconfig_DATA = \
67
health.d/netfilter.conf \
68
health.d/nut.conf \
69
health.d/pihole.conf \
70
+ health.d/ping.conf \
71
health.d/postgres.conf \
72
health.d/portcheck.conf \
73
health.d/processes.conf \
health/health.d/ping.conf
new
+49
@@ -0,0 +1,49 @@
1
+
2
+ template: ping_host_reachable
3
+ families: *
4
+ on: ping.host_packet_loss
5
+ class: Errors
6
+ type: Other
7
+component: Network
8
+ lookup: average -30s unaligned of loss
9
+ calc: $this != nan AND $this < 100
10
+ units: up/down
11
+ every: 10s
12
+ crit: $this == 0
13
+ delay: down 30m multiplier 1.5 max 2h
14
+ info: reachability status of the network host
15
+ to: sysadmin
16
+
17
+ template: ping_packet_loss
18
+ families: *
19
+ on: ping.host_packet_loss
20
+ class: Errors
21
+ type: Other
22
+component: Network
23
+ lookup: average -10m unaligned of loss
24
+ green: 5
25
+ red: 10
26
+ units: %
27
+ every: 10s
28
+ warn: $this > $green
29
+ crit: $this > $red
30
+ delay: down 30m multiplier 1.5 max 2h
31
+ info: packet loss percentage to the network host over the last 10 minutes
32
+ to: sysadmin
33
+
34
+ template: ping_host_latency
35
+ families: *
36
+ on: ping.host_rtt
37
+ class: Latency
38
+ type: Other
39
+component: Network
40
+ lookup: average -10s unaligned of avg
41
+ units: ms
42
+ every: 10s
43
+ green: 500
44
+ red: 1000
45
+ warn: $this > $green OR $max > $red
46
+ crit: $this > $red
47
+ delay: down 30m multiplier 1.5 max 2h
48
+ info: average latency to the network host over the last 10 seconds
49
+ to: sysadmin
web/gui/dashboard_info.js
+18
@@ -303,6 +303,12 @@ netdataDashboard.menu = {
303
info: 'Network latency statistics, via <b>fping</b>. <b>fping</b> is a program to send ICMP echo probes to network hosts, similar to <code>ping</code>, but much better performing when pinging multiple hosts. fping versions after 3.15 can be directly used as netdata plugins.'
304
},
305
306
+ 'ping': {
307
+ title: 'Ping',
308
+ icon: '<i class="fas fa-exchange-alt"></i>',
309
+ info: 'Measures round-trip time and packet loss by sending ping messages to network hosts.'
310
+ },
311
+
312
'gearman': {
313
title: 'Gearman',
314
icon: '<i class="fas fa-tasks"></i>',
@@ -7564,6 +7570,18 @@ netdataDashboard.context = {
7570
'<a href="https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle/#container-state-terminated" target="_blank">More info.</a>'
7571
},
7572
7573
+ // Ping
7574
+
7575
+ 'ping.host_rtt': {
7576
+ info: 'Round-trip time (RTT) is the time it takes for a data packet to reach its destination and return back to its original source.'
7577
+ },
7578
+ 'ping.host_packet_loss': {
7579
+ info: 'Packet loss occurs when one or more transmitted data packets do not reach their destination. Usually caused by data transfer errors, network congestion or firewall blocking. ICMP echo packets are often treated as lower priority by routers and target hosts, so ping test packet loss may not always translate to application packet loss.'
7580
+ },
7581
+ 'ping.host_packets': {
7582
+ info: 'Number of ICMP messages sent and received. These counters should be equal if there is no packet loss.'
7583
+ },
7584
+
7585
// ------------------------------------------------------------------------
7586
7587
};