# fv-ml1 pool-health actions (operator-approved 2026-09-09, "all 3 on clean context").
#
#   1. kick a scrub of `tank` (2 CKSUM on nvme7n1 after the 09-05 boot resilver,
#      no scrub since 04-12) — polled separately; `zpool clear` only after a
#      clean pass, by hand, never in this playbook.
#   2. install nvme-cli so nvme7's SMART counters can be read.
#   3. reclaim zroot (91%): dangling images + build cache ONLY. Never `prune -a`
#      here — tagged idle images include rollback seats.
#
# Rerunnable: a second run shows the scrub step skipped (in progress / done
# within the hour is not detected — the guard is "not already scrubbing"),
# nvme-cli ok, prunes ok with 0 B reclaimed.

steps:
  - name: Start scrub of tank (skip if one is already running)
    shell: zpool scrub tank
    sudo: true
    when: "! zpool status tank | grep -q 'scrub in progress'"

  - name: Install nvme-cli
    shell: DEBIAN_FRONTEND=noninteractive apt-get install -y -q nvme-cli
    sudo: true
    creates: /usr/sbin/nvme

  - name: Prune dangling docker images (NOT -a)
    shell: docker image prune -f | tail -1
    sudo: true

  - name: Prune docker build cache
    shell: docker builder prune -f | tail -1
    sudo: true

verify:
  - name: Scrub is in progress or already completed today
    shell: "zpool status tank | grep -Eq 'scrub in progress|scrub repaired .* on .*$(date +%b\\ *%e)'"
    changed_when: "false"

  - name: nvme binary present
    shell: test -x /usr/sbin/nvme
    changed_when: "false"

  - name: zroot usage after prune
    shell: df -h / | tail -1
    changed_when: "false"