bvandeusenandClaude Opus 5.5
4195b9171a
docs/plugins/prometheus-widgets.md covers: - where templates live and how to copy one in, duplicate, export and share; - a first template, walked through; - each block (states with its deadlines, values, times, table, info) with an example; - the format reference: keys, units, spans, limits, what the checker refuses; - the Fabled Archives template, block by block, with what it leaves out and why. Linked from the README, the plugin guide, the editor and template_format. tests/plugins/prometheus/test_widget_guide.py checks every YAML example in the guide against the checker, so the guide can't drift from the format. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
69 lines
2.6 KiB
YAML
69 lines
2.6 KiB
YAML
# Fabled Archives, from its /metrics on the LAN-only backup listener (:8081).
|
|
# Written against the series Steward stores for Archives (#5693); the format
|
|
# is docs/plugins/prometheus-widgets.md.
|
|
#
|
|
# Left out on purpose:
|
|
# - fabledarchives_section_up: a section Archives can't read stops reporting
|
|
# its series, and the rows here that read them then say "not reported".
|
|
# - the background queue (fabledarchives_jobs, *_job_attempts_*), HTTP
|
|
# requests and the audit counters: they belong on charts and alert rules,
|
|
# not on a glance.
|
|
name: Fabled Archives
|
|
description: Backup targets, replication jobs, storage, integrity and the version running.
|
|
version: 2
|
|
expects: fabledarchives_
|
|
blocks:
|
|
- states:
|
|
title: Backup targets
|
|
metric: fabledarchives_backup_target_state
|
|
name: target
|
|
healthy: [fresh]
|
|
quiet: [disabled, waiting]
|
|
warning: [late]
|
|
columns:
|
|
- {label: Last backup, metric: fabledarchives_backup_target_last_backup_timestamp_seconds}
|
|
- {label: Stored, metric: fabledarchives_backup_target_stored_bytes}
|
|
- states:
|
|
title: Replication
|
|
metric: fabledarchives_replication_job_state
|
|
name: job
|
|
# Archives ranks "running" above lateness: a run that never ends still
|
|
# reads "running". Its own deadlines say when it is overdue.
|
|
healthy: [ok, running]
|
|
warning: [late, warning, never]
|
|
warn_past: fabledarchives_replication_job_late_at_timestamp_seconds
|
|
crit_past: fabledarchives_replication_job_missing_at_timestamp_seconds
|
|
columns:
|
|
- {label: Last good copy, metric: fabledarchives_replication_job_last_success_timestamp_seconds}
|
|
- {label: Next run, metric: fabledarchives_replication_job_next_run_timestamp_seconds}
|
|
- values:
|
|
title: Storage and integrity
|
|
items:
|
|
- label: Disk free
|
|
metric: fabledarchives_data_disk_free_bytes
|
|
of: fabledarchives_data_disk_size_bytes
|
|
warn_below: 10%
|
|
crit_below: 5%
|
|
sparkline: true
|
|
- label: Files checked
|
|
metric: fabledarchives_files_checked
|
|
of: fabledarchives_files
|
|
unit: count
|
|
- label: Malware held
|
|
metric: fabledarchives_malware_held_files
|
|
unit: count
|
|
warn_above: 0
|
|
- label: Notification channels failing
|
|
metric: fabledarchives_notification_channels_failing
|
|
unit: count
|
|
warn_above: 0
|
|
- table:
|
|
title: Stored per person
|
|
metric: fabledarchives_person_stored_bytes
|
|
rows: person
|
|
columns: kind
|
|
- info:
|
|
title: Running
|
|
metric: fabledarchives_build_info
|
|
labels: [version, channel, commit]
|