home-network-k3s-impl/infra/ansible/roles/node_health/templates/summary.txt.j2

{# ===========================================================================
   node_health human summary. Rendered ONCE (tasks/report.yml) and used for both
   the on-screen report and the .txt artifact, so the two can never drift.

   Detail strings are normalised with regex_replace('\s+',' ') because the check
   details are authored as YAML folded scalars in assess.yml and can carry stray
   newlines/indentation from that folding.
   =========================================================================== #}
{% macro fmt(text, width=74, pad=10) -%}
{{ text | regex_replace('\s+', ' ') | trim | wordwrap(width) | indent(pad, first=True) }}
{%- endmacro %}
{% macro gib(n) -%}
{{ (n | int / 1073741824) | round(1) }} GiB
{%- endmacro %}
{# smartctl OMITS `thresh` entirely for any attribute whose threshold the drive does not
   report (surfaced 2026-09-03 by k3s-prod-3's WDC WDS500G2B0A, which reports one for 1 of
   its 25 attributes) — an ABSENT key, not thresh=0, so a bare `a.thresh` raised
   "object of type 'dict' has no attribute 'thresh'" and killed the whole report. Render it
   as `n/a` (the same token this template already uses for unreported readings) rather than
   defaulting to 0, which would falsely read as a real ATA "cannot trip" threshold. The
   collector already guards this — tasks/collect_smart.yml uses selectattr('thresh',
   'defined') and `a.thresh | default(0)` — so only the template was exposed. #}
{% macro thr(a) -%}
{{ a.thresh | default('n/a') }}
{%- endmacro %}
================================================================================
 NODE HEALTH — {{ inventory_hostname }} ({{ ansible_host | default('n/a') }})
 collected {{ node_health_facts.collected_at }} as uid {{ node_health_facts.collector_uid }}
================================================================================

 VERDICT   {{ node_health_counts.FAIL }} FAIL · {{ node_health_counts.WARN }} WARN · {{ node_health_counts.PASS }} PASS · {{ node_health_counts.SKIP }} SKIP · {{ node_health_counts.INFO }} INFO
 {{ 'privileged checks RAN' if node_health_root_available | bool else 'privileged checks SKIPPED — root not available' }}

--------------------------------------------------------------------------------
 CHECKS
--------------------------------------------------------------------------------
{% for c in node_health_checks %}
 [{{ '%-4s' | format(c.status) }}] {{ c.id }} — {{ c.title }}
{{ fmt(c.detail) }}
{% endfor %}

--------------------------------------------------------------------------------
 MACHINE — {{ node_health_facts.dmi.sys_vendor | default('?') }} {{ node_health_facts.dmi.product_name | default('?') }}
--------------------------------------------------------------------------------
 OS           {{ node_health_facts.os.pretty_name | default('?') }}
 Kernel       {{ node_health_facts.os.kernel | default('?') }}
 Uptime       {{ (node_health_facts.os.uptime_seconds | float / 86400) | round(2) }} days
 BIOS         {{ node_health_facts.dmi.bios_vendor | default('?') }} {{ node_health_facts.dmi.bios_version | default('?') }} ({{ node_health_facts.dmi.bios_date | default('?') }}){% if node_health_facts.dmi.ec_firmware_release %}, EC {{ node_health_facts.dmi.ec_firmware_release }}{% endif %}

 Board        {{ node_health_facts.dmi.board_vendor | default('?') }} {{ node_health_facts.dmi.board_name | default('?') }}
 CPU          {{ node_health_facts.cpu.model | default('?') }}
              {{ node_health_facts.cpu.cpus | default('?') }} logical / {{ node_health_facts.cpu.sockets | default('?') }} socket(s) x {{ node_health_facts.cpu.cores_per_socket | default('?') }} core(s) x {{ node_health_facts.cpu.threads_per_core | default('?') }} thread(s)
              virtualisation: {{ node_health_facts.cpu.virtualization | default('none reported') }}, /dev/kvm={{ node_health_facts.cpu.kvm_device }}
{% if node_health_facts.cpu.scaling %}
              scaling: {{ node_health_facts.cpu.scaling.driver }}/{{ node_health_facts.cpu.scaling.governor }}, {{ (node_health_facts.cpu.scaling.min_khz | int / 1000) | round | int }}–{{ (node_health_facts.cpu.scaling.max_khz | int / 1000) | round | int }} MHz (now {{ (node_health_facts.cpu.scaling.cur_khz | int / 1000) | round | int }} MHz)
{% endif %}
 Memory       {{ (node_health_facts.memory.mem_total_kb | int / 1048576) | round(1) }} GiB total, {{ (node_health_facts.memory.mem_available_kb | int / 1048576) | round(1) }} GiB available, swap {{ (node_health_facts.memory.swap_total_kb | int / 1048576) | round(2) }} GiB
 ECC/EDAC     {{ 'controllers: ' ~ (node_health_facts.memory.edac.controllers | map(attribute='name') | join(', ')) ~ ' CE=' ~ node_health_facts.memory.edac.ce_total | string ~ ' UE=' ~ node_health_facts.memory.edac.ue_total | string if node_health_facts.memory.edac.controllers_present else 'not exposed (no EDAC controller bound — ECC status UNKNOWN on this platform)' }}
{% set mz = node_health_facts.memory.zones %}
{% set md = node_health_facts.memory.devices %}
 Present RAM  {{ ((mz.present_kb | int / 1048576) | round(1) | string ~ ' GiB present / ' ~ (mz.managed_kb | int / 1048576) | round(1) | string ~ ' GiB managed — ' ~ mz.unmanaged_pct | string ~ '% never handed to the allocator') if mz.available and mz.unmanaged_pct is not none else ('NOT READ — ' ~ (mz.reason | default('no reason recorded', true))) }}
 DIMMs        {{ ((md.installed_kb | int / 1048576) | round(1) | string ~ ' GiB installed in ' ~ md.populated_slots | string ~ ' of ' ~ md.slots | string ~ ' slot(s)') if md.available else ('NOT READ — ' ~ (md.reason | default('no reason recorded', true)) | regex_replace('\s+', ' ') | trim | wordwrap(64) | indent(14)) }}
{% for dimm in md.devices | default([]) if dimm.size_kb %}
              {{ '%-8s' | format(dimm.locator | default('?', true)) }} {{ '%-8s' | format(dimm.size_raw) }} {{ dimm.type | default('?', true) }} {{ dimm.speed | default('', true) }} {{ dimm.manufacturer | default('', true) }} {{ dimm.part_number | default('', true) }}
{% endfor %}
{% set klog = node_health_facts.klog %}
 EFI memattr  {{ (klog.memattr_lines | join(' | ')) if klog.memattr_lines else (('kernel log NOT READ — ' ~ (klog.reason | default('no reason recorded', true))) if not klog.available else ('no memattr line in the kernel log' ~ ('' if klog.boot_covered else ' — BUT the ring buffer no longer reaches early boot, so that is an UNKNOWN, not a pass'))) | regex_replace('\s+', ' ') | trim | wordwrap(64) | indent(14) }}
 Load         {{ node_health_facts.cpu.loadavg | default([]) | join(' ') }}

--------------------------------------------------------------------------------
 STORAGE
--------------------------------------------------------------------------------
{% for d in node_health_facts.storage.disks %}
 {{ d.path }}  {{ gib(d.size_bytes) }}  {{ 'rotational' if d.rotational else 'non-rotating' }}  {{ d.transport | default('?', true) }}{% if d.fstype %}  whole-device {{ d.fstype }}{% endif %}{% if d.mountpoints %} mounted at {{ d.mountpoints | join(',') }}{% endif %}

   model      {{ d.model | default('(none reported)', true) }}{% if d.firmware_rev %}  fw {{ d.firmware_rev }}{% endif %}{% if d.serial %}  s/n {{ d.serial }}{% endif %}

{% if d.scsi_counters %}
   kernel I/O completed={{ d.scsi_counters.iodone_cnt }} errors={{ d.scsi_counters.ioerr_cnt }} timeouts={{ d.scsi_counters.iotmo_cnt }}
{% endif %}
{% set sm = (node_health_smart | selectattr('path', 'equalto', d.path) | list | first) | default(none) %}
{% if sm and sm.available %}
   SMART      overall-health={{ 'PASSED' if sm.passed else 'FAILED' }}  power_on_hours={{ sm.power_on_hours | default('?') }}  power_cycles={{ sm.power_cycles | default('?') }}
              lifetime_remaining={{ (sm.lifetime_remaining_pct | string ~ '%') if sm.lifetime_remaining_pct is not none else 'not reported' }}  temp={{ (sm.temperature_c | string ~ 'C') if sm.temperature_c is not none else 'not reported by this drive' }}
              pending(197)={{ sm.pending_sectors | default('?') }}  offline_uncorrectable(198)={{ sm.offline_uncorrectable | default('?') }}  reported_uncorrect(187)={{ sm.reported_uncorrect | default('?') }}  crc(199)={{ sm.crc_errors | default('?') }}
{% if sm.failing_now or sm.failed_past %}
              THRESHOLD TRIPS{% for a in sm.failing_now %} [{{ a.id }} {{ a.name }} FAILING_NOW value={{ a.value }}<=thresh={{ thr(a) }}{{ ' Pre-fail' if a.flags.prefailure | default(false) else ' Old_age' }}]{% endfor %}{% for a in sm.failed_past %} [{{ a.id }} {{ a.name }} In_the_past worst={{ a.worst }}<=thresh={{ thr(a) }}]{% endfor %}

{% elif sm.thresholds_present %}
              no attribute at/below its manufacturer threshold{% if sm.prefail_closest %}; closest Pre-fail margin: {{ sm.prefail_closest.id }} {{ sm.prefail_closest.name }} value={{ sm.prefail_closest.value }} vs thresh={{ thr(sm.prefail_closest) }}{% endif %}

{% endif %}
              vendor context (NOT used for the verdict — raw units are vendor-defined):
              reallocation events(196)={{ sm.realloc_events if sm.realloc_events is not none else 'n/a' }}  grown bad blocks={{ sm.grown_bad_blocks if sm.grown_bad_blocks is not none else 'n/a' }}  erase fails={{ sm.erase_fail_count if sm.erase_fail_count is not none else 'n/a' }}  program fails={{ sm.program_fail_count if sm.program_fail_count is not none else 'n/a' }}  unexpected power loss={{ sm.unexpected_power_loss if sm.unexpected_power_loss is not none else 'n/a' }}
{% if sm.realloc_attr %}
              attr 5 {{ sm.realloc_attr.name }} raw={{ sm.realloc_attr.raw.string | default(sm.realloc_attr.raw.value) }} (vendor-encoded) vs normalised value={{ sm.realloc_attr.value }} thresh={{ thr(sm.realloc_attr) }} (the signal that is judged)
{% endif %}
{% for a in sm.attributes | default([]) %}
              [{{ '%3d' | format(a.id) }}] {{ '%-26s' | format(a.name) }} value={{ a.value }} worst={{ a.worst }} thresh={{ thr(a) }} raw={{ a.raw.string | default(a.raw.value) }}{% if a.when_failed | default('') %}  <<< when_failed={{ a.when_failed }}{% endif %}

{% endfor %}
{% else %}
   SMART      NOT READ — {{ (node_health_root_skip_reason if not node_health_root_available else ('smartmontools not installed on this node (ships with roles/node_baseline; this role never installs packages)' if not node_health_facts.tools.smartctl else 'device exposes no SMART data')) | regex_replace('\s+', ' ') | trim }}
{% endif %}
{% for p in d.partitions %}
   {{ '%-12s' | format(p.kname) }} {{ '%9s' | format(gib(p.size_bytes)) }}  {{ '%-6s' | format(p.fstype | default('-', true)) }}  {{ (p.mountpoints[:2] | join(', ') ~ (' (+%d more)' | format(p.mountpoints | length - 2) if (p.mountpoints | length) > 2 else '')) if p.mountpoints else '(unmounted)' }}
{% endfor %}

{% endfor %}
{% if node_health_facts.storage.attached_volumes | default([]) %}
 ATTACHED VOLUMES (iSCSI/FC — Longhorn replicas etc., not hardware in this box)
{% for a in node_health_facts.storage.attached_volumes %}
   {{ '%-10s' | format(a.path) }} {{ '%9s' | format(gib(a.size_bytes)) }}  {{ a.transport }}  {{ a.model | default('-', true) }}
{% endfor %}

{% endif %}
 MOUNTED FILESYSTEMS
{% for m in node_health_facts.storage.mounts | sort(attribute='mountpoint') %}
   {{ '%-14s' | format(m.mountpoint) }} {{ '%-6s' | format(m.fstype) }} {{ '%9s' | format(gib(m.size_bytes)) }} total, {{ '%9s' | format(gib(m.avail_bytes)) }} free ({{ m.used_pct }}% used, inodes {{ (m.inodes_used_pct | string ~ '%') if m.inodes_used_pct is not none else 'n/a' }})
{% endfor %}

--------------------------------------------------------------------------------
 THERMAL
--------------------------------------------------------------------------------
{% for z in node_health_facts.thermal.zones %}
 zone {{ '%-18s' | format(z.type | default(z.zone)) }} {{ (z.temp_c | string ~ 'C') if z.temp_c is not none else 'unreadable (sensor returned no data)' }}{% if z.critical_c %} (critical {{ z.critical_c }}C){% endif %}

{% endfor %}
{% for chip in node_health_facts.thermal.hwmon %}
{% for t in chip.temps %}
 {{ '%-16s' | format(chip.name | default('hwmon')) }} {{ '%-22s' | format(t.label) }} {{ (t.temp_c | string ~ 'C') if t.temp_c is not none else 'unreadable (sensor returned no data)' }}{% if t.crit_c %} (crit {{ t.crit_c }}C){% endif %}

{% endfor %}
{% for f in chip.fans %}
 {{ '%-16s' | format(chip.name | default('hwmon')) }} {{ '%-22s' | format(f.label) }} {{ f.rpm }} rpm
{% endfor %}
{% endfor %}

--------------------------------------------------------------------------------
 PRESSURE STALL (/proc/pressure — % of wall time stalled)
--------------------------------------------------------------------------------
{% for res in ['cpu', 'memory', 'io'] %}
{% set p = node_health_facts.pressure[res] %}
{% if p %}
 {{ '%-7s' | format(res) }} some avg10={{ p.some.avg10 }} avg60={{ p.some.avg60 }} avg300={{ p.some.avg300 }}{% if p.full is defined %} | full avg60={{ p.full.avg60 }}{% endif %}

{% else %}
 {{ '%-7s' | format(res) }} unavailable
{% endif %}
{% endfor %}

--------------------------------------------------------------------------------
 NETWORK
--------------------------------------------------------------------------------
{% for n in node_health_facts.network.interfaces %}
 {{ '%-10s' | format(n.name) }} {{ '%-6s' | format(n.operstate) }} {{ '%-8s' | format((n.speed_mbps | string ~ 'Mb/s') if n.speed_mbps else 'no-link') }} {{ '%-9s' | format(n.duplex | default('-')) }} mtu {{ n.mtu }}  driver {{ n.driver | default('-') }}
            rx {{ n.statistics.rx_packets | default('?') }} pkts / errors {{ n.statistics.rx_errors | default('?') }} / dropped {{ n.statistics.rx_dropped | default('?') }}
            tx {{ n.statistics.tx_packets | default('?') }} pkts / errors {{ n.statistics.tx_errors | default('?') }} / dropped {{ n.statistics.tx_dropped | default('?') }}
{% endfor %}
{% if node_health_facts.network.nameservers is none %}
 nameservers NOT READ — {{ node_health_facts.network.resolver_unavailable_reason | default('the collector recorded no reason', true) | regex_replace('\s+', ' ') | trim | wordwrap(66) | indent(13) }}
{% else %}
 nameservers {{ node_health_facts.network.nameservers | join(', ') | default('none configured', true) }}
{% if node_health_facts.network.resolver_stub | default([], true) | length > 0 %}
             (/etc/resolv.conf holds only the systemd-resolved stub {{ node_health_facts.network.resolver_stub | join(', ') }}; the servers above are the real upstreams behind it)
{% endif %}
{% endif %}

--------------------------------------------------------------------------------
 NOT READ (and why) — these are UNKNOWNS, not passes
--------------------------------------------------------------------------------
{% for c in node_health_checks if c.status == 'SKIP' %}
 - {{ c.id }}: {{ c.detail | regex_replace('\s+', ' ') | trim | wordwrap(70) | indent(3) }}
{% else %}
 (nothing skipped)
{% endfor %}
{% if node_health_facts.unreadable %}

 Unreadable paths reported by the collector:
{% for u in node_health_facts.unreadable %}
 - {{ u.path }} — {{ u.reason }}
{% endfor %}
{% endif %}

 tools present: {% for t, p in node_health_facts.tools.items() %}{{ t }}={{ p | default('MISSING', true) }}{{ ', ' if not loop.last }}{% endfor %}

================================================================================