summaryrefslogtreecommitdiffstats
path: root/health
diff options
context:
space:
mode:
authorIlya Mashchenko <ilya@netdata.cloud>2022-10-31 21:24:19 +0200
committerGitHub <noreply@github.com>2022-10-31 21:24:19 +0200
commit3a2dc5149b1cf2e41794b741e4cb24ee107f069e (patch)
treec631efa1608c952d97dd38584b5ef610835b23f4 /health
parent282e0dfaa97289cc6542742e9e389bd76b7e4164 (diff)
add ping dashboard info and alarms (#13916)
Co-authored-by: Shyam Sreevalsan <shyam@netdata.cloud>
Diffstat (limited to 'health')
-rw-r--r--health/Makefile.am1
-rw-r--r--health/health.d/ping.conf49
2 files changed, 50 insertions, 0 deletions
diff --git a/health/Makefile.am b/health/Makefile.am
index 1bf3c87893..c5dcb844bc 100644
--- a/health/Makefile.am
+++ b/health/Makefile.am
@@ -67,6 +67,7 @@ dist_healthconfig_DATA = \
health.d/netfilter.conf \
health.d/nut.conf \
health.d/pihole.conf \
+ health.d/ping.conf \
health.d/postgres.conf \
health.d/portcheck.conf \
health.d/processes.conf \
diff --git a/health/health.d/ping.conf b/health/health.d/ping.conf
new file mode 100644
index 0000000000..16827851f0
--- /dev/null
+++ b/health/health.d/ping.conf
@@ -0,0 +1,49 @@
+
+ template: ping_host_reachable
+ families: *
+ on: ping.host_packet_loss
+ class: Errors
+ type: Other
+component: Network
+ lookup: average -30s unaligned of loss
+ calc: $this != nan AND $this < 100
+ units: up/down
+ every: 10s
+ crit: $this == 0
+ delay: down 30m multiplier 1.5 max 2h
+ info: reachability status of the network host
+ to: sysadmin
+
+ template: ping_packet_loss
+ families: *
+ on: ping.host_packet_loss
+ class: Errors
+ type: Other
+component: Network
+ lookup: average -10m unaligned of loss
+ green: 5
+ red: 10
+ units: %
+ every: 10s
+ warn: $this > $green
+ crit: $this > $red
+ delay: down 30m multiplier 1.5 max 2h
+ info: packet loss percentage to the network host over the last 10 minutes
+ to: sysadmin
+
+ template: ping_host_latency
+ families: *
+ on: ping.host_rtt
+ class: Latency
+ type: Other
+component: Network
+ lookup: average -10s unaligned of avg
+ units: ms
+ every: 10s
+ green: 500
+ red: 1000
+ warn: $this > $green OR $max > $red
+ crit: $this > $red
+ delay: down 30m multiplier 1.5 max 2h
+ info: average latency to the network host over the last 10 seconds
+ to: sysadmin