From 836b47cb7e99a977c5a23b059ca1d0b5065d310e Mon Sep 17 00:00:00 2001 From: Daniel Baumann Date: Wed, 24 Jul 2024 11:54:23 +0200 Subject: Merging upstream version 1.46.3. Signed-off-by: Daniel Baumann --- src/health/health.d/systemdunits.conf | 177 ++++++++++++++++++++++++++++++++++ 1 file changed, 177 insertions(+) create mode 100644 src/health/health.d/systemdunits.conf (limited to 'src/health/health.d/systemdunits.conf') diff --git a/src/health/health.d/systemdunits.conf b/src/health/health.d/systemdunits.conf new file mode 100644 index 00000000..bb5c627e --- /dev/null +++ b/src/health/health.d/systemdunits.conf @@ -0,0 +1,177 @@ +# you can disable an alarm notification by setting the 'to' line to: silent + +## Service units + template: systemd_service_unit_failed_state + on: systemd.service_unit_state + class: Errors + type: Linux + component: Systemd units +chart labels: unit_name=!* + calc: $failed + units: state + every: 10s + warn: $this != nan AND $this == 1 + delay: down 5m multiplier 1.5 max 1h + summary: systemd unit ${label:unit_name} state + info: systemd service unit in the failed state + to: sysadmin + +## Socket units + template: systemd_socket_unit_failed_state + on: systemd.socket_unit_state + class: Errors + type: Linux + component: Systemd units +chart labels: unit_name=!* + calc: $failed + units: state + every: 10s + warn: $this != nan AND $this == 1 + delay: down 5m multiplier 1.5 max 1h + summary: systemd unit ${label:unit_name} state + info: systemd socket unit in the failed state + to: sysadmin + +## Target units + template: systemd_target_unit_failed_state + on: systemd.target_unit_state + class: Errors + type: Linux + component: Systemd units +chart labels: unit_name=!* + calc: $failed + units: state + every: 10s + warn: $this != nan AND $this == 1 + delay: down 5m multiplier 1.5 max 1h + summary: systemd unit ${label:unit_name} state + info: systemd target unit in the failed state + to: sysadmin + +## Path units + template: systemd_path_unit_failed_state + on: systemd.path_unit_state + class: Errors + type: Linux + component: Systemd units +chart labels: unit_name=!* + calc: $failed + units: state + every: 10s + warn: $this != nan AND $this == 1 + delay: down 5m multiplier 1.5 max 1h + summary: systemd unit ${label:unit_name} state + info: systemd path unit in the failed state + to: sysadmin + +## Device units + template: systemd_device_unit_failed_state + on: systemd.device_unit_state + class: Errors + type: Linux + component: Systemd units +chart labels: unit_name=!* + calc: $failed + units: state + every: 10s + warn: $this != nan AND $this == 1 + delay: down 5m multiplier 1.5 max 1h + summary: systemd unit ${label:unit_name} state + info: systemd device unit in the failed state + to: sysadmin + +## Mount units + template: systemd_mount_unit_failed_state + on: systemd.mount_unit_state + class: Errors + type: Linux + component: Systemd units +chart labels: unit_name=!* + calc: $failed + units: state + every: 10s + warn: $this != nan AND $this == 1 + delay: down 5m multiplier 1.5 max 1h + summary: systemd unit ${label:unit_name} state + info: systemd mount units in the failed state + to: sysadmin + +## Automount units + template: systemd_automount_unit_failed_state + on: systemd.automount_unit_state + class: Errors + type: Linux + component: Systemd units +chart labels: unit_name=!* + calc: $failed + units: state + every: 10s + warn: $this != nan AND $this == 1 + delay: down 5m multiplier 1.5 max 1h + summary: systemd unit ${label:unit_name} state + info: systemd automount unit in the failed state + to: sysadmin + +## Swap units + template: systemd_swap_unit_failed_state + on: systemd.swap_unit_state + class: Errors + type: Linux + component: Systemd units +chart labels: unit_name=!* + calc: $failed + units: state + every: 10s + warn: $this != nan AND $this == 1 + delay: down 5m multiplier 1.5 max 1h + summary: systemd unit ${label:unit_name} state + info: systemd swap units in the failed state + to: sysadmin + +## Scope units + template: systemd_scope_unit_failed_state + on: systemd.scope_unit_state + class: Errors + type: Linux + component: Systemd units +chart labels: unit_name=!* + calc: $failed + units: state + every: 10s + warn: $this != nan AND $this == 1 + delay: down 5m multiplier 1.5 max 1h + summary: systemd unit ${label:unit_name} state + info: systemd scope units in the failed state + to: sysadmin + +## Slice units + template: systemd_slice_unit_failed_state + on: systemd.slice_unit_state + class: Errors + type: Linux + component: Systemd units +chart labels: unit_name=!* + calc: $failed + units: state + every: 10s + warn: $this != nan AND $this == 1 + delay: down 5m multiplier 1.5 max 1h + summary: systemd unit ${label:unit_name} state + info: systemd slice units in the failed state + to: sysadmin + +## Timer units + template: systemd_timer_unit_failed_state + on: systemd.timer_unit_state + class: Errors + type: Linux + component: Systemd units +chart labels: unit_name=!* + calc: $failed + units: state + every: 10s + warn: $this != nan AND $this == 1 + delay: down 5m multiplier 1.5 max 1h + summary: systemd unit ${label:unit_name} state + info: systemd timer unit in the failed state + to: sysadmin -- cgit v1.2.3