|
|
|
@ -10,9 +10,11 @@
|
|
|
|
# -------------------------------------------------------------------
|
|
|
|
# -------------------------------------------------------------------
|
|
|
|
# Related Issue: 1584
|
|
|
|
# Related Issue: 1584
|
|
|
|
# Notes: Home dashboard consumes `infra_*` entities for exceptions-only alerts.
|
|
|
|
# Notes: Home dashboard consumes `infra_*` entities for exceptions-only alerts.
|
|
|
|
|
|
|
|
# Notes: WAN outages alert immediately at near-zero throughput or 90% packet loss; performance degradation requires 6 continuous hours below 300/300 Mbps, above 80 ms, above 5% loss, or unavailable telemetry.
|
|
|
|
# Notes: Nightly Duplicati verification runs at 08:00 after the 05:30 Duplicati job and docker_14 reboot window.
|
|
|
|
# Notes: Nightly Duplicati verification runs at 08:00 after the 05:30 Duplicati job and docker_14 reboot window.
|
|
|
|
# Notes: Duplicati transport/API errors are logged only; repairs are reserved for proven failed or stale backups.
|
|
|
|
# Notes: Duplicati transport/API errors are logged only; repairs are reserved for proven failed or stale backups.
|
|
|
|
# Notes: Duplicati failure Repairs enable a recovery poll that clears the Repair after a later successful run.
|
|
|
|
# Notes: Duplicati failure Repairs enable a recovery poll that clears the Repair after a later successful run.
|
|
|
|
|
|
|
|
# Notes: Duplicati verification persists its result and latest successful backup time for the Docker storage dashboard.
|
|
|
|
# Notes: Monthly HA log hygiene review requests Telegram + public-safe GitHub issue follow-up only; Joanna must wait for approval before any changes.
|
|
|
|
# Notes: Monthly HA log hygiene review requests Telegram + public-safe GitHub issue follow-up only; Joanna must wait for approval before any changes.
|
|
|
|
# Notes: Numeric WAN telemetry exposes state_class so recorder can keep long-term statistics.
|
|
|
|
# Notes: Numeric WAN telemetry exposes state_class so recorder can keep long-term statistics.
|
|
|
|
# Notes: Docker host root disk usage uses Glances-backed normalized sensors; raw Glances sensors are recorder/logbook-filtered.
|
|
|
|
# Notes: Docker host root disk usage uses Glances-backed normalized sensors; raw Glances sensors are recorder/logbook-filtered.
|
|
|
|
@ -22,6 +24,7 @@
|
|
|
|
# Notes: Promoted IoT DNS consistency compares primary/backup Pi-hole answers for reserved IoT host records.
|
|
|
|
# Notes: Promoted IoT DNS consistency compares primary/backup Pi-hole answers for reserved IoT host records.
|
|
|
|
# Notes: Garage compute health uses the same 145 F threshold as the existing temperature notification.
|
|
|
|
# Notes: Garage compute health uses the same 145 F threshold as the existing temperature notification.
|
|
|
|
# Notes: Immediate website-down states create Repairs; the installed UptimeRobot integration exposes current state, not trend rollups.
|
|
|
|
# Notes: Immediate website-down states create Repairs; the installed UptimeRobot integration exposes current state, not trend rollups.
|
|
|
|
|
|
|
|
# Notes: Dashboard aggregate issue count is live-only; its underlying degraded sensors retain actionable history.
|
|
|
|
######################################################################
|
|
|
|
######################################################################
|
|
|
|
|
|
|
|
|
|
|
|
input_text:
|
|
|
|
input_text:
|
|
|
|
@ -40,11 +43,20 @@ input_text:
|
|
|
|
infra_pihole_iot_dns_health_band:
|
|
|
|
infra_pihole_iot_dns_health_band:
|
|
|
|
name: "Pi-hole IoT DNS health band"
|
|
|
|
name: "Pi-hole IoT DNS health band"
|
|
|
|
max: 20
|
|
|
|
max: 20
|
|
|
|
|
|
|
|
infra_duplicati_backup_verification_status:
|
|
|
|
|
|
|
|
name: "Duplicati backup verification status"
|
|
|
|
|
|
|
|
max: 20
|
|
|
|
|
|
|
|
|
|
|
|
input_boolean:
|
|
|
|
input_boolean:
|
|
|
|
infra_duplicati_backup_repair_active:
|
|
|
|
infra_duplicati_backup_repair_active:
|
|
|
|
name: "Duplicati backup repair active"
|
|
|
|
name: "Duplicati backup repair active"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
input_datetime:
|
|
|
|
|
|
|
|
infra_duplicati_backup_last_success:
|
|
|
|
|
|
|
|
name: "Duplicati backup last success"
|
|
|
|
|
|
|
|
has_date: true
|
|
|
|
|
|
|
|
has_time: true
|
|
|
|
|
|
|
|
|
|
|
|
command_line:
|
|
|
|
command_line:
|
|
|
|
- sensor:
|
|
|
|
- sensor:
|
|
|
|
name: Infra WAN Packet Loss
|
|
|
|
name: Infra WAN Packet Loss
|
|
|
|
@ -193,7 +205,6 @@ template:
|
|
|
|
- name: "Infra Dashboard Active Issue Count"
|
|
|
|
- name: "Infra Dashboard Active Issue Count"
|
|
|
|
unique_id: infra_dashboard_active_issue_count
|
|
|
|
unique_id: infra_dashboard_active_issue_count
|
|
|
|
icon: mdi:alert-circle-check-outline
|
|
|
|
icon: mdi:alert-circle-check-outline
|
|
|
|
state_class: measurement
|
|
|
|
|
|
|
|
state: >-
|
|
|
|
state: >-
|
|
|
|
{% set categories = [
|
|
|
|
{% set categories = [
|
|
|
|
'binary_sensor.infra_wan_quality_degraded',
|
|
|
|
'binary_sensor.infra_wan_quality_degraded',
|
|
|
|
@ -215,17 +226,55 @@ template:
|
|
|
|
{{ expand(categories) | selectattr('state', 'eq', 'on') | map(attribute='entity_id') | list }}
|
|
|
|
{{ expand(categories) | selectattr('state', 'eq', 'on') | map(attribute='entity_id') | list }}
|
|
|
|
|
|
|
|
|
|
|
|
- binary_sensor:
|
|
|
|
- binary_sensor:
|
|
|
|
- name: "Infra WAN Quality Degraded"
|
|
|
|
- name: "Infra WAN Outage"
|
|
|
|
unique_id: infra_wan_quality_degraded
|
|
|
|
unique_id: infra_wan_outage
|
|
|
|
device_class: problem
|
|
|
|
device_class: problem
|
|
|
|
|
|
|
|
state: >-
|
|
|
|
|
|
|
|
{% set loss_raw = states('sensor.infra_wan_packet_loss') %}
|
|
|
|
|
|
|
|
{% set download_raw = states('sensor.speedtest_download') %}
|
|
|
|
|
|
|
|
{% set upload_raw = states('sensor.speedtest_upload') %}
|
|
|
|
|
|
|
|
{% set invalid_values = ['unknown', 'unavailable', 'none', ''] %}
|
|
|
|
|
|
|
|
{% set loss = loss_raw | float(0) %}
|
|
|
|
|
|
|
|
{% set download = download_raw | float(0) %}
|
|
|
|
|
|
|
|
{% set upload = upload_raw | float(0) %}
|
|
|
|
|
|
|
|
{{ (loss_raw not in invalid_values and loss >= 90) or
|
|
|
|
|
|
|
|
(download_raw not in invalid_values and download <= 1) or
|
|
|
|
|
|
|
|
(upload_raw not in invalid_values and upload <= 1) }}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
- name: "Infra WAN Sustained Degradation"
|
|
|
|
|
|
|
|
unique_id: infra_wan_sustained_degradation
|
|
|
|
|
|
|
|
device_class: problem
|
|
|
|
|
|
|
|
delay_on: "06:00:00"
|
|
|
|
|
|
|
|
delay_off: "00:30:00"
|
|
|
|
state: >-
|
|
|
|
state: >-
|
|
|
|
{% set loss_raw = states('sensor.infra_wan_packet_loss') %}
|
|
|
|
{% set loss_raw = states('sensor.infra_wan_packet_loss') %}
|
|
|
|
{% set lat_raw = states('sensor.infra_wan_latency_ms') %}
|
|
|
|
{% set lat_raw = states('sensor.infra_wan_latency_ms') %}
|
|
|
|
{% set invalid = loss_raw in ['unknown', 'unavailable', 'none', ''] or
|
|
|
|
{% set download_raw = states('sensor.speedtest_download') %}
|
|
|
|
lat_raw in ['unknown', 'unavailable', 'none', ''] %}
|
|
|
|
{% set upload_raw = states('sensor.speedtest_upload') %}
|
|
|
|
|
|
|
|
{% set invalid_values = ['unknown', 'unavailable', 'none', ''] %}
|
|
|
|
|
|
|
|
{% set invalid = loss_raw in invalid_values or
|
|
|
|
|
|
|
|
lat_raw in invalid_values or
|
|
|
|
|
|
|
|
download_raw in invalid_values or
|
|
|
|
|
|
|
|
upload_raw in invalid_values %}
|
|
|
|
{% set loss = loss_raw | float(0) %}
|
|
|
|
{% set loss = loss_raw | float(0) %}
|
|
|
|
{% set lat = lat_raw | float(0) %}
|
|
|
|
{% set lat = lat_raw | float(0) %}
|
|
|
|
{{ invalid or loss > 5 or lat > 80 }}
|
|
|
|
{% set download = download_raw | float(0) %}
|
|
|
|
|
|
|
|
{% set upload = upload_raw | float(0) %}
|
|
|
|
|
|
|
|
{{ invalid or loss > 5 or lat > 80 or download < 300 or upload < 300 }}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
- name: "Infra WAN Quality Degraded"
|
|
|
|
|
|
|
|
unique_id: infra_wan_quality_degraded
|
|
|
|
|
|
|
|
device_class: problem
|
|
|
|
|
|
|
|
state: >-
|
|
|
|
|
|
|
|
{{ is_state('binary_sensor.infra_wan_outage', 'on') or
|
|
|
|
|
|
|
|
is_state('binary_sensor.infra_wan_sustained_degradation', 'on') }}
|
|
|
|
|
|
|
|
attributes:
|
|
|
|
|
|
|
|
evaluation_window: "6 hours"
|
|
|
|
|
|
|
|
throughput_threshold_mbps: 300
|
|
|
|
|
|
|
|
latency_threshold_ms: 80
|
|
|
|
|
|
|
|
packet_loss_threshold_percent: 5
|
|
|
|
|
|
|
|
outage_throughput_mbps: 1
|
|
|
|
|
|
|
|
outage_packet_loss_percent: 90
|
|
|
|
|
|
|
|
|
|
|
|
- name: "Infra DNS Pihole Degraded"
|
|
|
|
- name: "Infra DNS Pihole Degraded"
|
|
|
|
unique_id: infra_dns_pihole_degraded
|
|
|
|
unique_id: infra_dns_pihole_degraded
|
|
|
|
@ -992,8 +1041,24 @@ automation:
|
|
|
|
- service: input_boolean.turn_off
|
|
|
|
- service: input_boolean.turn_off
|
|
|
|
target:
|
|
|
|
target:
|
|
|
|
entity_id: input_boolean.infra_duplicati_backup_repair_active
|
|
|
|
entity_id: input_boolean.infra_duplicati_backup_repair_active
|
|
|
|
|
|
|
|
- service: input_text.set_value
|
|
|
|
|
|
|
|
target:
|
|
|
|
|
|
|
|
entity_id: input_text.infra_duplicati_backup_verification_status
|
|
|
|
|
|
|
|
data:
|
|
|
|
|
|
|
|
value: "verified"
|
|
|
|
|
|
|
|
- service: input_datetime.set_datetime
|
|
|
|
|
|
|
|
target:
|
|
|
|
|
|
|
|
entity_id: input_datetime.infra_duplicati_backup_last_success
|
|
|
|
|
|
|
|
data:
|
|
|
|
|
|
|
|
timestamp: >-
|
|
|
|
|
|
|
|
{{ as_timestamp(verify_last_success.get('endedAt'), as_timestamp(now())) }}
|
|
|
|
- conditions: "{{ verify_transport_issue }}"
|
|
|
|
- conditions: "{{ verify_transport_issue }}"
|
|
|
|
sequence:
|
|
|
|
sequence:
|
|
|
|
|
|
|
|
- service: input_text.set_value
|
|
|
|
|
|
|
|
target:
|
|
|
|
|
|
|
|
entity_id: input_text.infra_duplicati_backup_verification_status
|
|
|
|
|
|
|
|
data:
|
|
|
|
|
|
|
|
value: "unverified"
|
|
|
|
- service: script.send_to_logbook
|
|
|
|
- service: script.send_to_logbook
|
|
|
|
data:
|
|
|
|
data:
|
|
|
|
topic: "BACKUP"
|
|
|
|
topic: "BACKUP"
|
|
|
|
@ -1002,6 +1067,11 @@ automation:
|
|
|
|
status {{ verify_status }} with issue {{ verify_issue }}. No repair card was opened because
|
|
|
|
status {{ verify_status }} with issue {{ verify_issue }}. No repair card was opened because
|
|
|
|
this is verifier transport state, not a confirmed backup failure.
|
|
|
|
this is verifier transport state, not a confirmed backup failure.
|
|
|
|
default:
|
|
|
|
default:
|
|
|
|
|
|
|
|
- service: input_text.set_value
|
|
|
|
|
|
|
|
target:
|
|
|
|
|
|
|
|
entity_id: input_text.infra_duplicati_backup_verification_status
|
|
|
|
|
|
|
|
data:
|
|
|
|
|
|
|
|
value: "failed"
|
|
|
|
- service: input_boolean.turn_on
|
|
|
|
- service: input_boolean.turn_on
|
|
|
|
target:
|
|
|
|
target:
|
|
|
|
entity_id: input_boolean.infra_duplicati_backup_repair_active
|
|
|
|
entity_id: input_boolean.infra_duplicati_backup_repair_active
|
|
|
|
|
Carlo Costanzo
5 days ago