summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorIlya Mashchenko <ilya@netdata.cloud>2023-10-14 21:55:07 +0300
committerGitHub <noreply@github.com>2023-10-14 19:55:07 +0100
commit712926a6490504d9b065bf80bf173df9e2314983 (patch)
treebdac516c62a224ef3eb3f7b99b696ec498c577eb
parent594473cd003b50bf9787cb839b26320f857c0121 (diff)
health: attach drops ratio alarms to net.drops (#16199)
* health: attach drops ratio alarms to net.drops * update meta * enable net drops on all os * update freebsd meta
-rw-r--r--collectors/freebsd.plugin/metadata.yaml42
-rw-r--r--collectors/proc.plugin/metadata.yaml22
-rw-r--r--health/health.d/net.conf50
3 files changed, 36 insertions, 78 deletions
diff --git a/collectors/freebsd.plugin/metadata.yaml b/collectors/freebsd.plugin/metadata.yaml
index fca8982f7b..d68fc31376 100644
--- a/collectors/freebsd.plugin/metadata.yaml
+++ b/collectors/freebsd.plugin/metadata.yaml
@@ -2893,36 +2893,16 @@ modules:
metric: net.net
info: network interface ${label:device} current speed
os: "*"
- - name: 1m_received_traffic_overflow
- link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf
- metric: net.net
- info: average inbound utilization for the network interface ${label:device} over the last minute
- os: "linux"
- - name: 1m_sent_traffic_overflow
- link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf
- metric: net.net
- info: average outbound utilization for the network interface ${label:device} over the last minute
- os: "linux"
- name: inbound_packets_dropped_ratio
link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf
- metric: net.packets
+ metric: net.drops
info: ratio of inbound dropped packets for the network interface ${label:device} over the last 10 minutes
- os: "linux"
+ os: "*"
- name: outbound_packets_dropped_ratio
link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf
- metric: net.packets
- info: ratio of outbound dropped packets for the network interface ${label:device} over the last 10 minutes
- os: "linux"
- - name: wifi_inbound_packets_dropped_ratio
- link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf
- metric: net.packets
- info: ratio of inbound dropped packets for the network interface ${label:device} over the last 10 minutes
- os: "linux"
- - name: wifi_outbound_packets_dropped_ratio
- link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf
- metric: net.packets
+ metric: net.drops
info: ratio of outbound dropped packets for the network interface ${label:device} over the last 10 minutes
- os: "linux"
+ os: "*"
- name: 1m_received_packets_rate
link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf
metric: net.packets
@@ -2931,9 +2911,7 @@ modules:
- name: 10s_received_packets_storm
link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf
metric: net.packets
- info:
- ratio of average number of received packets for the network interface ${label:device} over the last 10 seconds, compared to the rate over
- the last minute
+ info: ratio of average number of received packets for the network interface ${label:device} over the last 10 seconds, compared to the rate over the last minute
os: "linux freebsd"
- name: interface_inbound_errors
link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf
@@ -2945,16 +2923,6 @@ modules:
metric: net.errors
info: number of outbound errors for the network interface ${label:device} in the last 10 minutes
os: "freebsd"
- - name: inbound_packets_dropped
- link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf
- metric: net.drops
- info: number of inbound dropped packets for the network interface ${label:device} in the last 10 minutes
- os: "linux"
- - name: outbound_packets_dropped
- link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf
- metric: net.drops
- info: number of outbound dropped packets for the network interface ${label:device} in the last 10 minutes
- os: "linux"
metrics:
folding:
title: Metrics
diff --git a/collectors/proc.plugin/metadata.yaml b/collectors/proc.plugin/metadata.yaml
index d0329420c5..45351b36f4 100644
--- a/collectors/proc.plugin/metadata.yaml
+++ b/collectors/proc.plugin/metadata.yaml
@@ -2643,22 +2643,22 @@ modules:
os: "linux"
- name: inbound_packets_dropped_ratio
link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf
- metric: net.packets
+ metric: net.drops
info: ratio of inbound dropped packets for the network interface ${label:device} over the last 10 minutes
os: "linux"
- name: outbound_packets_dropped_ratio
link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf
- metric: net.packets
+ metric: net.drops
info: ratio of outbound dropped packets for the network interface ${label:device} over the last 10 minutes
os: "linux"
- name: wifi_inbound_packets_dropped_ratio
link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf
- metric: net.packets
+ metric: net.drops
info: ratio of inbound dropped packets for the network interface ${label:device} over the last 10 minutes
os: "linux"
- name: wifi_outbound_packets_dropped_ratio
link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf
- metric: net.packets
+ metric: net.drops
info: ratio of outbound dropped packets for the network interface ${label:device} over the last 10 minutes
os: "linux"
- name: 1m_received_packets_rate
@@ -2669,20 +2669,8 @@ modules:
- name: 10s_received_packets_storm
link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf
metric: net.packets
- info:
- ratio of average number of received packets for the network interface ${label:device} over the last 10 seconds, compared to the rate over
- the last minute
+ info: ratio of average number of received packets for the network interface ${label:device} over the last 10 seconds, compared to the rate over the last minute
os: "linux freebsd"
- - name: inbound_packets_dropped
- link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf
- metric: net.drops
- info: number of inbound dropped packets for the network interface ${label:device} in the last 10 minutes
- os: "linux"
- - name: outbound_packets_dropped
- link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf
- metric: net.drops
- info: number of outbound dropped packets for the network interface ${label:device} in the last 10 minutes
- os: "linux"
- name: 10min_fifo_errors
link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf
metric: net.fifo
diff --git a/health/health.d/net.conf b/health/health.d/net.conf
index e41e2ab12d..ea49541874 100644
--- a/health/health.d/net.conf
+++ b/health/health.d/net.conf
@@ -60,40 +60,42 @@ component: Network
# it is possible to have expected packet drops on an interface for some network configurations
# look at the Monitoring Network Interfaces section in the proc.plugin documentation for more information
- template: inbound_packets_dropped
- on: net.drops
- class: Errors
+ template: net_interface_inbound_packets
+ on: net.packets
+ class: Workload
type: System
component: Network
- os: linux
+ os: *
hosts: *
- lookup: sum -10m unaligned absolute of inbound
+ lookup: sum -10m unaligned absolute of received
units: packets
every: 1m
- info: Number of inbound dropped packets for the network interface ${label:device} in the last 10 minutes
+ summary: Network interface ${label:device} received packets
+ info: Received packets for the network interface ${label:device} in the last 10 minutes
- template: outbound_packets_dropped
- on: net.drops
- class: Errors
+ template: net_interface_outbound_packets
+ on: net.packets
+ class: Workload
type: System
component: Network
- os: linux
+ os: *
hosts: *
- lookup: sum -10m unaligned absolute of outbound
+ lookup: sum -10m unaligned absolute of sent
units: packets
every: 1m
- info: Number of outbound dropped packets for the network interface ${label:device} in the last 10 minutes
+ summary: Network interface ${label:device} sent packets
+ info: Sent packets for the network interface ${label:device} in the last 10 minutes
template: inbound_packets_dropped_ratio
- on: net.packets
+ on: net.drops
class: Errors
type: System
component: Network
- os: linux
+ os: *
hosts: *
chart labels: device=!wl* *
- lookup: sum -10m unaligned absolute of received
- calc: (($inbound_packets_dropped != nan AND $this > 10000) ? ($inbound_packets_dropped * 100 / $this) : (0))
+ lookup: sum -10m unaligned absolute of inbound
+ calc: (($net_interface_inbound_packets > 10000) ? ($this * 100 / $net_interface_inbound_packets) : (0))
units: %
every: 1m
warn: $this >= 2
@@ -103,15 +105,15 @@ chart labels: device=!wl* *
to: silent
template: outbound_packets_dropped_ratio
- on: net.packets
+ on: net.drops
class: Errors
type: System
component: Network
- os: linux
+ os: *
hosts: *
chart labels: device=!wl* *
- lookup: sum -10m unaligned absolute of sent
- calc: (($outbound_packets_dropped != nan AND $this > 1000) ? ($outbound_packets_dropped * 100 / $this) : (0))
+ lookup: sum -10m unaligned absolute of outbound
+ calc: (($net_interface_outbound_packets > 1000) ? ($this * 100 / $net_interface_outbound_packets) : (0))
units: %
every: 1m
warn: $this >= 2
@@ -121,7 +123,7 @@ chart labels: device=!wl* *
to: silent
template: wifi_inbound_packets_dropped_ratio
- on: net.packets
+ on: net.drops
class: Errors
type: System
component: Network
@@ -129,7 +131,7 @@ component: Network
hosts: *
chart labels: device=wl*
lookup: sum -10m unaligned absolute of received
- calc: (($inbound_packets_dropped != nan AND $this > 10000) ? ($inbound_packets_dropped * 100 / $this) : (0))
+ calc: (($net_interface_inbound_packets > 10000) ? ($this * 100 / $net_interface_inbound_packets) : (0))
units: %
every: 1m
warn: $this >= 10
@@ -139,7 +141,7 @@ chart labels: device=wl*
to: silent
template: wifi_outbound_packets_dropped_ratio
- on: net.packets
+ on: net.drops
class: Errors
type: System
component: Network
@@ -147,7 +149,7 @@ component: Network
hosts: *
chart labels: device=wl*
lookup: sum -10m unaligned absolute of sent
- calc: (($outbound_packets_dropped != nan AND $this > 1000) ? ($outbound_packets_dropped * 100 / $this) : (0))
+ calc: (($net_interface_outbound_packets > 1000) ? ($this * 100 / $net_interface_outbound_packets) : (0))
units: %
every: 1m
warn: $this >= 10