remove "os" "hosts" "plugin" and "module" from stock alarms (netdata#…

…17113)
ilyam8 · Mar 5, 2024 · 746ebfd · 746ebfd
1 parent 291004e
commit 746ebfd
Show file tree

Hide file tree

Showing 35 changed files with 1,124 additions and 1,306 deletions.
diff --git a/src/health/health.d/apcupsd.conf b/src/health/health.d/apcupsd.conf
@@ -5,8 +5,6 @@
  class: Utilization
  type: Power Supply
 component: UPS
- os: *
- hosts: *
  lookup: average -10m unaligned of percentage
  units: %
  every: 1m
@@ -23,8 +21,6 @@ component: UPS
  class: Errors
  type: Power Supply
 component: UPS
- os: *
- hosts: *
  lookup: average -60s unaligned of charge
  units: %
  every: 60s

diff --git a/src/health/health.d/boinc.conf b/src/health/health.d/boinc.conf
@@ -1,13 +1,11 @@
-# Alarms for various BOINC issues.
+# you can disable an alarm notification by setting the 'to' line to: silent
 
 # Warn on any compute errors encountered.
  template: boinc_compute_errors
  on: boinc.states
  class: Errors
  type: Computing
 component: BOINC
- os: *
- hosts: *
  lookup: average -10m unaligned of comperror
  units: tasks
  every: 1m
@@ -23,8 +21,6 @@ component: BOINC
  class: Errors
  type: Computing
 component: BOINC
- os: *
- hosts: *
  lookup: average -10m unaligned of upload_failed
  units: tasks
  every: 1m
@@ -40,8 +36,6 @@ component: BOINC
  class: Utilization
  type: Computing
 component: BOINC
- os: *
- hosts: *
  lookup: average -10m unaligned of total
  units: tasks
  every: 1m
@@ -57,8 +51,6 @@ component: BOINC
  class: Utilization
  type: Computing
 component: BOINC
- os: *
- hosts: *
  lookup: average -10m unaligned of active
  calc: ($boinc_total_tasks >= 1) ? ($this) : (inf)
  units: tasks

diff --git a/src/health/health.d/btrfs.conf b/src/health/health.d/btrfs.conf
@@ -1,11 +1,10 @@
+# you can disable an alarm notification by setting the 'to' line to: silent
 
  template: btrfs_allocated
  on: btrfs.disk
  class: Utilization
  type: System
 component: File system
- os: *
- hosts: *
  calc: 100 - ($unallocated * 100 / ($unallocated + $data_used + $data_free + $meta_used + $meta_free + $sys_used + $sys_free))
  units: %
  every: 10s
@@ -20,8 +19,6 @@ component: File system
  class: Utilization
  type: System
 component: File system
- os: *
- hosts: *
  calc: $used * 100 / ($used + $free)
  units: %
  every: 10s
@@ -37,8 +34,6 @@ component: File system
  class: Utilization
  type: System
 component: File system
- os: *
- hosts: *
  calc: ($used + $reserved) * 100 / ($used + $free + $reserved)
  units: %
  every: 10s
@@ -54,8 +49,6 @@ component: File system
  class: Utilization
  type: System
 component: File system
- os: *
- hosts: *
  calc: $used * 100 / ($used + $free)
  units: %
  every: 10s
@@ -71,8 +64,6 @@ component: File system
  class: Errors
  type: System
 component: File system
- os: *
- hosts: *
  units: errors
  lookup: max -10m every 1m of read_errs
  warn: $this > 0
@@ -86,8 +77,6 @@ component: File system
  class: Errors
  type: System
 component: File system
- os: *
- hosts: *
  units: errors
  lookup: max -10m every 1m of write_errs
  crit: $this > 0
@@ -101,8 +90,6 @@ component: File system
  class: Errors
  type: System
 component: File system
- os: *
- hosts: *
  units: errors
  lookup: max -10m every 1m of flush_errs
  crit: $this > 0
@@ -116,8 +103,6 @@ component: File system
  class: Errors
  type: System
 component: File system
- os: *
- hosts: *
  units: errors
  lookup: max -10m every 1m of corruption_errs
  warn: $this > 0
@@ -131,8 +116,6 @@ component: File system
  class: Errors
  type: System
 component: File system
- os: *
- hosts: *
  units: errors
  lookup: max -10m every 1m of generation_errs
  warn: $this > 0

diff --git a/src/health/health.d/cgroups.conf b/src/health/health.d/cgroups.conf
@@ -1,72 +1,67 @@
-
 # you can disable an alarm notification by setting the 'to' line to: silent
 
- template: cgroup_10min_cpu_usage
- on: cgroup.cpu_limit
- class: Utilization
- type: Cgroups
-component: CPU
- os: linux
- hosts: *
- lookup: average -10m unaligned
- units: %
- every: 1m
- warn: $this > (($status == $CRITICAL) ? (85) : (95))
- delay: down 15m multiplier 1.5 max 1h
- summary: Cgroup ${label:cgroup_name} CPU utilization
- info: Cgroup ${label:cgroup_name} average CPU utilization over the last 10 minutes
- to: silent
+ template: cgroup_10min_cpu_usage
+ on: cgroup.cpu_limit
+ class: Utilization
+ type: Cgroups
+ component: CPU
+host labels: _os=linux
+ lookup: average -10m unaligned
+ units: %
+ every: 1m
+ warn: $this > (($status == $CRITICAL) ? (85) : (95))
+ delay: down 15m multiplier 1.5 max 1h
+ summary: Cgroup ${label:cgroup_name} CPU utilization
+ info: Cgroup ${label:cgroup_name} average CPU utilization over the last 10 minutes
+ to: silent
 
- template: cgroup_ram_in_use
- on: cgroup.mem_usage
- class: Utilization
- type: Cgroups
-component: Memory
- os: linux
- hosts: *
- calc: ($ram) * 100 / $memory_limit
- units: %
- every: 10s
- warn: $this > (($status >= $WARNING) ? (80) : (90))
- crit: $this > (($status == $CRITICAL) ? (90) : (98))
- delay: down 15m multiplier 1.5 max 1h
- summary: Cgroup ${label:cgroup_name} memory utilization
- info: Cgroup ${label:cgroup_name} memory utilization
- to: silent
+ template: cgroup_ram_in_use
+ on: cgroup.mem_usage
+ class: Utilization
+ type: Cgroups
+ component: Memory
+host labels: _os=linux
+ calc: ($ram) * 100 / $memory_limit
+ units: %
+ every: 10s
+ warn: $this > (($status >= $WARNING) ? (80) : (90))
+ crit: $this > (($status == $CRITICAL) ? (90) : (98))
+ delay: down 15m multiplier 1.5 max 1h
+ summary: Cgroup ${label:cgroup_name} memory utilization
+ info: Cgroup ${label:cgroup_name} memory utilization
+ to: silent
 
 # ---------------------------------K8s containers--------------------------------------------
 
- template: k8s_cgroup_10min_cpu_usage
- on: k8s.cgroup.cpu_limit
- class: Utilization
- type: Cgroups
-component: CPU
- os: linux
- hosts: *
- lookup: average -10m unaligned
- units: %
- every: 1m
- warn: $this > (($status >= $WARNING) ? (75) : (85))
- delay: down 15m multiplier 1.5 max 1h
- summary: Container ${label:k8s_container_name} pod ${label:k8s_pod_name} CPU utilization
- info: Container ${label:k8s_container_name} of pod ${label:k8s_pod_name} of namespace ${label:k8s_namespace}, \
- average CPU utilization over the last 10 minutes
- to: silent
+ template: k8s_cgroup_10min_cpu_usage
+ on: k8s.cgroup.cpu_limit
+ class: Utilization
+ type: Cgroups
+ component: CPU
+host labels: _os=linux
+ lookup: average -10m unaligned
+ units: %
+ every: 1m
+ warn: $this > (($status >= $WARNING) ? (75) : (85))
+ delay: down 15m multiplier 1.5 max 1h
+ summary: Container ${label:k8s_container_name} pod ${label:k8s_pod_name} CPU utilization
+ info: Container ${label:k8s_container_name} of pod ${label:k8s_pod_name} of namespace ${label:k8s_namespace}, \
+ average CPU utilization over the last 10 minutes
+ to: silent
 
- template: k8s_cgroup_ram_in_use
- on: k8s.cgroup.mem_usage
- class: Utilization
- type: Cgroups
-component: Memory
- os: linux
- hosts: *
- calc: ($ram) * 100 / $memory_limit
- units: %
- every: 10s
- warn: $this > (($status >= $WARNING) ? (80) : (90))
- crit: $this > (($status == $CRITICAL) ? (90) : (98))
- delay: down 15m multiplier 1.5 max 1h
- summary: Container ${label:k8s_container_name} pod ${label:k8s_pod_name} memory utilization
- info: container ${label:k8s_container_name} of pod ${label:k8s_pod_name} of namespace ${label:k8s_namespace}, \
- memory utilization
- to: silent
+ template: k8s_cgroup_ram_in_use
+ on: k8s.cgroup.mem_usage
+ class: Utilization
+ type: Cgroups
+ component: Memory
+host labels: _os=linux
+ calc: ($ram) * 100 / $memory_limit
+ units: %
+ every: 10s
+ warn: $this > (($status >= $WARNING) ? (80) : (90))
+ crit: $this > (($status == $CRITICAL) ? (90) : (98))
+ delay: down 15m multiplier 1.5 max 1h
+ summary: Container ${label:k8s_container_name} pod ${label:k8s_pod_name} memory utilization
+ info: container ${label:k8s_container_name} of pod ${label:k8s_pod_name} of namespace ${label:k8s_namespace}, \
+ memory utilization
+ to: silent