summaryrefslogtreecommitdiffstats
path: root/health/health.d
diff options
context:
space:
mode:
Diffstat (limited to 'health/health.d')
-rw-r--r--health/health.d/backend.conf42
-rw-r--r--health/health.d/cgroups.conf37
-rw-r--r--health/health.d/fronius.conf14
-rw-r--r--health/health.d/ioping.conf10
-rw-r--r--health/health.d/net.conf8
-rw-r--r--health/health.d/nut.conf47
-rw-r--r--health/health.d/stiebeleltron.conf14
-rw-r--r--health/health.d/tcp_resets.conf2
-rw-r--r--health/health.d/timex.conf2
9 files changed, 95 insertions, 81 deletions
diff --git a/health/health.d/backend.conf b/health/health.d/backend.conf
deleted file mode 100644
index 91d469395..000000000
--- a/health/health.d/backend.conf
+++ /dev/null
@@ -1,42 +0,0 @@
-# Alert that backends subsystem will be disabled soon
- alarm: backend_metrics_eol
- on: netdata.backend_metrics
- class: Errors
- type: Netdata
-component: Exporting engine
- units: boolean
- calc: $now - $last_collected_t
- every: 1m
- warn: $this > 0
- delay: down 5m multiplier 1.5 max 1h
- info: the backends subsystem is deprecated and will be removed soon. Migrate your configuration to exporting.conf.
- to: sysadmin
-
-# make sure we are sending data to backend
-
- alarm: backend_last_buffering
- on: netdata.backend_metrics
- class: Latency
- type: Netdata
-component: Exporting engine
- 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 * $update_every))
- delay: down 5m multiplier 1.5 max 1h
- info: number of seconds since the last successful buffering of backend data
- to: dba
-
- alarm: backend_metrics_sent
- on: netdata.backend_metrics
- class: Workload
- type: Netdata
-component: Exporting engine
- units: %
- calc: abs($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
diff --git a/health/health.d/cgroups.conf b/health/health.d/cgroups.conf
index 45b34806c..aa416c795 100644
--- a/health/health.d/cgroups.conf
+++ b/health/health.d/cgroups.conf
@@ -32,3 +32,40 @@ component: Memory
delay: down 15m multiplier 1.5 max 1h
info: cgroup memory utilization
to: sysadmin
+
+# -----------------------------------------------------------------------------
+# check for packet storms
+
+# 1. calculate the rate packets are received in 1m: 1m_received_packets_rate
+# 2. do the same for the last 10s
+# 3. raise an alarm if the later is 10x or 20x the first
+# we assume the minimum packet storm should at least have
+# 10000 packets/s, average of the last 10 seconds
+
+ template: cgroup_1m_received_packets_rate
+ on: cgroup.net_packets
+ class: Workload
+ type: Cgroups
+component: Network
+ hosts: *
+ lookup: average -1m unaligned of received
+ units: packets
+ every: 10s
+ info: average number of packets received by the network interface $family over the last minute
+
+ template: cgroup_10s_received_packets_storm
+ on: cgroup.net_packets
+ class: Workload
+ type: Cgroups
+component: Network
+ hosts: *
+ lookup: average -10s unaligned of received
+ calc: $this * 100 / (($1m_received_packets_rate < 1000)?(1000):($1m_received_packets_rate))
+ every: 10s
+ units: %
+ warn: $this > (($status >= $WARNING)?(200):(5000))
+ crit: $this > (($status == $CRITICAL)?(5000):(6000))
+ options: no-clear-notification
+ info: ratio of average number of received packets for the network interface $family over the last 10 seconds, \
+ compared to the rate over the last minute
+ to: sysadmin
diff --git a/health/health.d/fronius.conf b/health/health.d/fronius.conf
deleted file mode 100644
index 853bd7fbc..000000000
--- a/health/health.d/fronius.conf
+++ /dev/null
@@ -1,14 +0,0 @@
- template: fronius_last_collected_secs
- families: *
- on: fronius.power
- class: Latency
- type: Power Supply
-component: Solar
- calc: $now - $last_collected_t
- every: 10s
- units: seconds ago
- 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 data collection
- to: sitemgr
diff --git a/health/health.d/ioping.conf b/health/health.d/ioping.conf
index ee4befbea..8b498ad3c 100644
--- a/health/health.d/ioping.conf
+++ b/health/health.d/ioping.conf
@@ -4,12 +4,12 @@
class: Latency
type: System
component: Disk
- lookup: average -10s unaligned of average
- units: ms
+ lookup: average -10s unaligned of latency
+ units: microseconds
every: 10s
- green: 500
- red: 1000
- warn: $this > $green OR $max > $red
+ green: 5000
+ red: 10000
+ warn: $this > $green
crit: $this > $red
delay: down 30m multiplier 1.5 max 2h
info: average I/O latency over the last 10 seconds
diff --git a/health/health.d/net.conf b/health/health.d/net.conf
index 028ca7b81..9d5b3b8d3 100644
--- a/health/health.d/net.conf
+++ b/health/health.d/net.conf
@@ -68,7 +68,7 @@ component: Network
component: Network
os: linux
hosts: *
- families: !net* *
+ families: *
lookup: sum -10m unaligned absolute of inbound
units: packets
every: 1m
@@ -81,7 +81,7 @@ component: Network
component: Network
os: linux
hosts: *
- families: !net* *
+ families: *
lookup: sum -10m unaligned absolute of outbound
units: packets
every: 1m
@@ -94,7 +94,7 @@ component: Network
component: Network
os: linux
hosts: *
- families: !net* !wl* *
+ families: !wl* *
lookup: sum -10m unaligned absolute of received
calc: (($inbound_packets_dropped != nan AND $this > 10000) ? ($inbound_packets_dropped * 100 / $this) : (0))
units: %
@@ -111,7 +111,7 @@ component: Network
component: Network
os: linux
hosts: *
- families: !net* !wl* *
+ families: !wl* *
lookup: sum -10m unaligned absolute of sent
calc: (($outbound_packets_dropped != nan AND $this > 1000) ? ($outbound_packets_dropped * 100 / $this) : (0))
units: %
diff --git a/health/health.d/nut.conf b/health/health.d/nut.conf
new file mode 100644
index 000000000..6231dd97b
--- /dev/null
+++ b/health/health.d/nut.conf
@@ -0,0 +1,47 @@
+# you can disable an alarm notification by setting the 'to' line to: silent
+
+ template: nut_10min_ups_load
+ on: nut.load
+ class: Utilization
+ type: Power Supply
+component: UPS
+ os: *
+ hosts: *
+ lookup: average -10m unaligned of load
+ units: %
+ every: 1m
+ warn: $this > (($status >= $WARNING) ? (70) : (80))
+ crit: $this > (($status == $CRITICAL) ? (85) : (95))
+ delay: down 10m multiplier 1.5 max 1h
+ info: average UPS load over the last 10 minutes
+ to: sitemgr
+
+ template: nut_ups_charge
+ on: nut.charge
+ class: Errors
+ type: Power Supply
+component: UPS
+ os: *
+ hosts: *
+ lookup: average -60s unaligned of battery_charge
+ units: %
+ every: 60s
+ warn: $this < 100
+ crit: $this < (($status == $CRITICAL) ? (60) : (50))
+ delay: down 10m multiplier 1.5 max 1h
+ info: average UPS charge over the last minute
+ to: sitemgr
+
+ template: nut_last_collected_secs
+ on: nut.load
+ class: Latency
+ type: Power Supply
+component: UPS device
+ calc: $now - $last_collected_t
+ every: 10s
+ units: seconds ago
+ 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 data collection
+ to: sitemgr
diff --git a/health/health.d/stiebeleltron.conf b/health/health.d/stiebeleltron.conf
deleted file mode 100644
index 493c8b73a..000000000
--- a/health/health.d/stiebeleltron.conf
+++ /dev/null
@@ -1,14 +0,0 @@
- template: stiebeleltron_last_collected_secs
- families: *
- on: stiebeleltron.heating.hc1
- class: Latency
- type: Other
-component: Sensors
- calc: $now - $last_collected_t
- every: 10s
- units: seconds ago
- 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 data collection
- to: sitemgr
diff --git a/health/health.d/tcp_resets.conf b/health/health.d/tcp_resets.conf
index 190271e47..35cb6366c 100644
--- a/health/health.d/tcp_resets.conf
+++ b/health/health.d/tcp_resets.conf
@@ -26,7 +26,7 @@ component: Network
lookup: average -10s unaligned absolute of OutRsts
units: tcp resets/s
every: 10s
- warn: $this > ((($1m_ipv4_tcp_resets_sent < 5)?(5):($1m_ipv4_tcp_resets_sent)) * (($status >= $WARNING) ? (1) : (20)))
+ warn: $this > ((($1m_ipv4_tcp_resets_sent < 5)?(5):($1m_ipv4_tcp_resets_sent)) * (($status >= $WARNING) ? (1) : (10)))
delay: up 20s down 60m multiplier 1.2 max 2h
options: no-clear-notification
info: average number of sent TCP RESETS over the last 10 seconds. \
diff --git a/health/health.d/timex.conf b/health/health.d/timex.conf
index ea90c4000..23c18ba10 100644
--- a/health/health.d/timex.conf
+++ b/health/health.d/timex.conf
@@ -13,5 +13,5 @@ component: Clock
every: 10s
warn: $system.uptime.uptime > 17 * 60 AND $this == 0
delay: down 5m
- info: the system time is not synchronized to a reliable server
+ info: when set to 0, the system kernel believes the system clock is not properly synchronized to a reliable server
to: silent
generated by cgit v1.2.3 (git 2.39.1) at 2024-05-19 20:59:42 +0000