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
Ilya Mashchenko committed
Oct 14, 2023 at 21:55 UTC
712926a6490504d9b065bf80bf173df9e2314983
3 files changed
+36
-78
collectors/freebsd.plugin/metadata.yaml
+5
-37
@@ -2893,36 +2893,16 @@ modules:
2893
metric: net.net
2894
info: network interface ${label:device} current speed
2895
os: "*"
2896
- - name: 1m_received_traffic_overflow
2897
- link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf
2898
- metric: net.net
2899
- info: average inbound utilization for the network interface ${label:device} over the last minute
2900
- os: "linux"
2901
- - name: 1m_sent_traffic_overflow
2902
- link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf
2903
- metric: net.net
2904
- info: average outbound utilization for the network interface ${label:device} over the last minute
2905
- os: "linux"
2896
- name: inbound_packets_dropped_ratio
2897
link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf
2908
- metric: net.packets
2898
+ metric: net.drops
2899
info: ratio of inbound dropped packets for the network interface ${label:device} over the last 10 minutes
2910
- os: "linux"
2900
+ os: "*"
2901
- name: outbound_packets_dropped_ratio
2902
link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf
2913
- metric: net.packets
2914
- info: ratio of outbound dropped packets for the network interface ${label:device} over the last 10 minutes
2915
- os: "linux"
2916
- - name: wifi_inbound_packets_dropped_ratio
2917
- link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf
2918
- metric: net.packets
2919
- info: ratio of inbound dropped packets for the network interface ${label:device} over the last 10 minutes
2920
- os: "linux"
2921
- - name: wifi_outbound_packets_dropped_ratio
2922
- link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf
2923
- metric: net.packets
2903
+ metric: net.drops
2904
info: ratio of outbound dropped packets for the network interface ${label:device} over the last 10 minutes
2925
- os: "linux"
2905
+ os: "*"
2906
- name: 1m_received_packets_rate
2907
link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf
2908
metric: net.packets
@@ -2931,9 +2911,7 @@ modules:
2911
- name: 10s_received_packets_storm
2912
link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf
2913
metric: net.packets
2934
- info:
2935
- ratio of average number of received packets for the network interface ${label:device} over the last 10 seconds, compared to the rate over
2936
- the last minute
2914
+ 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
2915
os: "linux freebsd"
2916
- name: interface_inbound_errors
2917
link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf
@@ -2945,16 +2923,6 @@ modules:
2923
metric: net.errors
2924
info: number of outbound errors for the network interface ${label:device} in the last 10 minutes
2925
os: "freebsd"
2948
- - name: inbound_packets_dropped
2949
- link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf
2950
- metric: net.drops
2951
- info: number of inbound dropped packets for the network interface ${label:device} in the last 10 minutes
2952
- os: "linux"
2953
- - name: outbound_packets_dropped
2954
- link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf
2955
- metric: net.drops
2956
- info: number of outbound dropped packets for the network interface ${label:device} in the last 10 minutes
2957
- os: "linux"
2926
metrics:
2927
folding:
2928
title: Metrics
collectors/proc.plugin/metadata.yaml
+5
-17
@@ -2643,22 +2643,22 @@ modules:
2643
os: "linux"
2644
- name: inbound_packets_dropped_ratio
2645
link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf
2646
- metric: net.packets
2646
+ metric: net.drops
2647
info: ratio of inbound dropped packets for the network interface ${label:device} over the last 10 minutes
2648
os: "linux"
2649
- name: outbound_packets_dropped_ratio
2650
link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf
2651
- metric: net.packets
2651
+ metric: net.drops
2652
info: ratio of outbound dropped packets for the network interface ${label:device} over the last 10 minutes
2653
os: "linux"
2654
- name: wifi_inbound_packets_dropped_ratio
2655
link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf
2656
- metric: net.packets
2656
+ metric: net.drops
2657
info: ratio of inbound dropped packets for the network interface ${label:device} over the last 10 minutes
2658
os: "linux"
2659
- name: wifi_outbound_packets_dropped_ratio
2660
link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf
2661
- metric: net.packets
2661
+ metric: net.drops
2662
info: ratio of outbound dropped packets for the network interface ${label:device} over the last 10 minutes
2663
os: "linux"
2664
- name: 1m_received_packets_rate
@@ -2669,20 +2669,8 @@ modules:
2669
- name: 10s_received_packets_storm
2670
link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf
2671
metric: net.packets
2672
- info:
2673
- ratio of average number of received packets for the network interface ${label:device} over the last 10 seconds, compared to the rate over
2674
- the last minute
2672
+ 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
2673
os: "linux freebsd"
2676
- - name: inbound_packets_dropped
2677
- link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf
2678
- metric: net.drops
2679
- info: number of inbound dropped packets for the network interface ${label:device} in the last 10 minutes
2680
- os: "linux"
2681
- - name: outbound_packets_dropped
2682
- link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf
2683
- metric: net.drops
2684
- info: number of outbound dropped packets for the network interface ${label:device} in the last 10 minutes
2685
- os: "linux"
2674
- name: 10min_fifo_errors
2675
link: https://github.com/netdata/netdata/blob/master/health/health.d/net.conf
2676
metric: net.fifo
health/health.d/net.conf
+26
-24
@@ -60,40 +60,42 @@ component: Network
60
# it is possible to have expected packet drops on an interface for some network configurations
61
# look at the Monitoring Network Interfaces section in the proc.plugin documentation for more information
62
63
- template: inbound_packets_dropped
64
- on: net.drops
65
- class: Errors
63
+ template: net_interface_inbound_packets
64
+ on: net.packets
65
+ class: Workload
66
type: System
67
component: Network
68
- os: linux
68
+ os: *
69
hosts: *
70
- lookup: sum -10m unaligned absolute of inbound
70
+ lookup: sum -10m unaligned absolute of received
71
units: packets
72
every: 1m
73
- info: Number of inbound dropped packets for the network interface ${label:device} in the last 10 minutes
73
+ summary: Network interface ${label:device} received packets
74
+ info: Received packets for the network interface ${label:device} in the last 10 minutes
75
75
- template: outbound_packets_dropped
76
- on: net.drops
77
- class: Errors
76
+ template: net_interface_outbound_packets
77
+ on: net.packets
78
+ class: Workload
79
type: System
80
component: Network
80
- os: linux
81
+ os: *
82
hosts: *
82
- lookup: sum -10m unaligned absolute of outbound
83
+ lookup: sum -10m unaligned absolute of sent
84
units: packets
85
every: 1m
85
- info: Number of outbound dropped packets for the network interface ${label:device} in the last 10 minutes
86
+ summary: Network interface ${label:device} sent packets
87
+ info: Sent packets for the network interface ${label:device} in the last 10 minutes
88
89
template: inbound_packets_dropped_ratio
88
- on: net.packets
90
+ on: net.drops
91
class: Errors
92
type: System
93
component: Network
92
- os: linux
94
+ os: *
95
hosts: *
96
chart labels: device=!wl* *
95
- lookup: sum -10m unaligned absolute of received
96
- calc: (($inbound_packets_dropped != nan AND $this > 10000) ? ($inbound_packets_dropped * 100 / $this) : (0))
97
+ lookup: sum -10m unaligned absolute of inbound
98
+ calc: (($net_interface_inbound_packets > 10000) ? ($this * 100 / $net_interface_inbound_packets) : (0))
99
units: %
100
every: 1m
101
warn: $this >= 2
@@ -103,15 +105,15 @@ chart labels: device=!wl* *
105
to: silent
106
107
template: outbound_packets_dropped_ratio
106
- on: net.packets
108
+ on: net.drops
109
class: Errors
110
type: System
111
component: Network
110
- os: linux
112
+ os: *
113
hosts: *
114
chart labels: device=!wl* *
113
- lookup: sum -10m unaligned absolute of sent
114
- calc: (($outbound_packets_dropped != nan AND $this > 1000) ? ($outbound_packets_dropped * 100 / $this) : (0))
115
+ lookup: sum -10m unaligned absolute of outbound
116
+ calc: (($net_interface_outbound_packets > 1000) ? ($this * 100 / $net_interface_outbound_packets) : (0))
117
units: %
118
every: 1m
119
warn: $this >= 2
@@ -121,7 +123,7 @@ chart labels: device=!wl* *
123
to: silent
124
125
template: wifi_inbound_packets_dropped_ratio
124
- on: net.packets
126
+ on: net.drops
127
class: Errors
128
type: System
129
component: Network
@@ -129,7 +131,7 @@ component: Network
131
hosts: *
132
chart labels: device=wl*
133
lookup: sum -10m unaligned absolute of received
132
- calc: (($inbound_packets_dropped != nan AND $this > 10000) ? ($inbound_packets_dropped * 100 / $this) : (0))
134
+ calc: (($net_interface_inbound_packets > 10000) ? ($this * 100 / $net_interface_inbound_packets) : (0))
135
units: %
136
every: 1m
137
warn: $this >= 10
@@ -139,7 +141,7 @@ chart labels: device=wl*
141
to: silent
142
143
template: wifi_outbound_packets_dropped_ratio
142
- on: net.packets
144
+ on: net.drops
145
class: Errors
146
type: System
147
component: Network
@@ -147,7 +149,7 @@ component: Network
149
hosts: *
150
chart labels: device=wl*
151
lookup: sum -10m unaligned absolute of sent
150
- calc: (($outbound_packets_dropped != nan AND $this > 1000) ? ($outbound_packets_dropped * 100 / $this) : (0))
152
+ calc: (($net_interface_outbound_packets > 1000) ? ($this * 100 / $net_interface_outbound_packets) : (0))
153
units: %
154
every: 1m
155
warn: $this >= 10