Files
felhom.eu/hub/internal/monitor/pbsdr_box.go
T
admin 7f11cfb36c hub v0.65.0 — PBS DR storage visibility (ep0 usage op) + Offsite tab split + dual dashboard gauges (R-5)
Makes PBS DR storage visible like the restic pool box (v0.64.0), differentiated. Scoping
correction: restic = subaccounts on the shared Hetzner Storage Box (Hetzner API); PBS DR =
the felhom-offsite PBS datastore on the ep0 endpoint VM (NO Hetzner API). Option A
(Viktor-ruled): a read-only `usage` op on the felhom-tenantsync ep0 forced command (twin of
fingerprint), polled by a new hub checker on the 15-min throttle. READ-ONLY throughout.

Phase-0 (gate PASSED): on ep0 (PBS 4.2.3), df -B1 --output=size,used,avail <datastore path>
yields bytes (39990112256/7627939840/... ~19%), read-only, existing sudo context, no admin token.

- scripts/felhom-tenantsync.sh -> v1.2.0: read-only `usage` short-circuit (df on the datastore
  path), no customer_id, no admin token, NO mutation. + a bash harness proving zero mutation.
- tenantsync.Client.Usage() + BoxUsage; unknown-op -> typed ErrUsageUnsupported (graceful).
- monitor.PBSDRBoxChecker: OffsiteBoxChecker clone over a usageReader seam; 15-min throttle,
  cached PBSBoxSnapshot, escalation-only pbsdr_box_fill on the "pbsdr-box" scope (operator only,
  no SaveEvent), recovery re-arm. Fill only. THREE states: ok / unavailable (ep0 <=v1.1.0,
  neutral no-alert) / degraded (exec failed, keep last).
- config: Alerting.PBSDRBoxFill{Warn,Crit}Percent (80/90); built with the tenantsync client,
  60s sweep, SetPBSDRBox. Hub deploy INDEPENDENT of the ep0 update (graceful degradation).
- web: /offsite splits into Restic + PBS DR hash tabs (endpoint cards under PBS DR); PBS panel;
  the single dashboard tile becomes two gauges (RESTIC pct.ratio, PBS DR pct / n/a).
- runbook offsite-endpoint.md 10: v1.2.0 update steps (no sudoers/authorized_keys change).

Tests: 10 Go + the harness; 3 red-proofs (usage mutation, escalation-only, unavailable-drives-band)
confirmed red then restored. go build/vet/test + bash -n + hub confirm gate all pass.
2026-07-17 21:13:30 +02:00

185 lines
7.0 KiB
Go

package monitor
import (
"context"
"encoding/json"
"errors"
"fmt"
"log"
"sync"
"time"
"gitea.dooplex.hu/admin/felhom-hub/internal/tenantsync"
)
// usageReader is the ep0 datastore-usage seam (satisfied by *tenantsync.Client). Narrow so tests inject
// a fake and the checker never depends on the full tenantsync surface.
type usageReader interface {
Usage(ctx context.Context) (tenantsync.BoxUsage, error)
}
// PBSDRBoxChecker (v0.65.0) watches the PBS DR datastore (felhom-offsite on ep0) fill — the sibling of
// OffsiteBoxChecker over a DIFFERENT source: the ep0 read-only `usage` op (df on the datastore path), NOT
// the Hetzner API. FILL ONLY (PBS DR uses namespaces, not soft quotas — no oversubscription concept). Same
// shape: 15-min throttle, cached snapshot, escalation-only emit + silent recovery re-arm, degraded-on-
// failure honesty. THREE snapshot states:
// - "ok" → bands drive alerts.
// - "unavailable" → the endpoint script predates the usage op (≤ v1.1.0) → ErrUsageUnsupported. An
// EXPECTED pre-update condition: neutral, NO alert, logged once. The gauge shows n/a.
// - "degraded" → exec failed/timed out → keep the last snapshot, NO band transition (missing ≠ 0%).
//
// Events carry the customer-less scope "pbsdr-box" → operator channel ONLY (processCustomer no-ops on it);
// NO SaveEvent (no customer row to key it to). Deliberately NOT bolted onto OffsiteBoxChecker.
type PBSDRBoxChecker struct {
reader usageReader
fillWarn float64
fillCrit float64
onEvent EventNotifyFunc
logger *log.Logger
now func() time.Time // injectable clock (tests)
mu sync.Mutex
snap PBSBoxSnapshot
haveSnap bool
lastFetch time.Time
fillBand string // "" until first ok eval → born/persistent; only an "ok" fetch updates it
unavailLogged bool // log the "unavailable" state ONCE, not per sweep
}
// pbsdrBoxScope is the customer-less cooldown/display key for PBS-DR box events.
const pbsdrBoxScope = "pbsdr-box"
// PBS-DR snapshot states.
const (
PBSStateOK = "ok"
PBSStateUnavailable = "unavailable"
PBSStateDegraded = "degraded"
)
const (
defaultPBSDRBoxFillWarnPercent = 80.0
defaultPBSDRBoxFillCritPercent = 90.0
)
// PBSBoxSnapshot is the cached PBS-DR datastore aggregate the web layer renders. Sizes in BYTES.
type PBSBoxSnapshot struct {
CapacityBytes int64
UsedBytes int64
FillPercent float64
FillBand string // "" | ok | warning | critical
State string // ok | unavailable | degraded
FetchedAt time.Time
}
// NewPBSDRBoxChecker builds the checker (defaults 80/90 on invalid thresholds). Nothing seeded → the
// first ok Check that finds a breach emits (born/persistent; the dispatcher's 1 h cooldown dedups a restart).
func NewPBSDRBoxChecker(reader usageReader, fillWarn, fillCrit float64, onEvent EventNotifyFunc, logger *log.Logger) *PBSDRBoxChecker {
if fillWarn <= 0 || fillWarn >= 100 {
fillWarn = defaultPBSDRBoxFillWarnPercent
}
if fillCrit <= 0 || fillCrit > 100 || fillCrit <= fillWarn {
fillCrit = defaultPBSDRBoxFillCritPercent
}
if fillCrit <= fillWarn {
fillWarn, fillCrit = defaultPBSDRBoxFillWarnPercent, defaultPBSDRBoxFillCritPercent
}
c := &PBSDRBoxChecker{
reader: reader, fillWarn: fillWarn, fillCrit: fillCrit,
onEvent: onEvent, logger: logger, now: time.Now,
}
logger.Printf("[INFO] PBS-DR box checker initialized: fill warn=%.0f%% crit=%.0f%%, refresh %s", fillWarn, fillCrit, boxFetchInterval)
return c
}
// Check runs on the 60 s sweep; fetches (throttled) and emits on each fill escalation.
func (c *PBSDRBoxChecker) Check() {
c.mu.Lock()
defer c.mu.Unlock()
if c.haveSnap && c.now().Sub(c.lastFetch) < boxFetchInterval {
return // throttle — serve the cache
}
c.lastFetch = c.now() // updated even on failure → retried once per window, not per sweep
usage, err := c.reader.Usage(context.Background())
if err != nil {
if errors.Is(err, tenantsync.ErrUsageUnsupported) {
// EXPECTED pre-update condition — a distinct "unavailable" state, NOT degraded, NO alert.
c.snap = PBSBoxSnapshot{State: PBSStateUnavailable, FetchedAt: c.now()}
c.haveSnap = true
if !c.unavailLogged {
c.logger.Printf("[INFO] PBS-DR box: usage op unavailable — endpoint tenantsync update (v1.2.0) pending; gauge shows n/a until then")
c.unavailLogged = true
}
return // fillBand untouched — an expected data gap never re-arms/transitions
}
c.logger.Printf("[WARN] PBS-DR box: usage read failed (keeping last snapshot): %v", err)
if c.haveSnap {
c.snap.State = PBSStateDegraded // serve last-known, visibly stale; NO band transition
}
return
}
c.unavailLogged = false // recovered from unavailable
snap := PBSBoxSnapshot{CapacityBytes: usage.Total, UsedBytes: usage.Used, State: PBSStateOK, FetchedAt: c.now()}
if usage.Total > 0 {
snap.FillPercent = float64(usage.Used) * 100 / float64(usage.Total)
snap.FillBand = bandForPercent(snap.FillPercent, c.fillWarn, c.fillCrit)
} else {
snap.State = PBSStateDegraded // zero total — guard the division
}
c.snap = snap
c.haveSnap = true
if snap.State != PBSStateOK {
return
}
c.logger.Printf("[INFO] PBS-DR box refreshed: %.1f%% full (%s of %s)", snap.FillPercent, fmtSize(snap.UsedBytes), fmtSize(snap.CapacityBytes))
// FILL band (escalation-only; recovery re-arms because bandOK has rank 0).
if bandRank(snap.FillBand) > bandRank(c.fillBand) {
c.emitFill(snap, snap.FillBand)
}
c.fillBand = snap.FillBand
}
// Snapshot returns the cached aggregate + whether one exists (mutex copy-out). The web layer's only
// source — it NEVER polls ep0 in the request path.
func (c *PBSDRBoxChecker) Snapshot() (PBSBoxSnapshot, bool) {
c.mu.Lock()
defer c.mu.Unlock()
return c.snap, c.haveSnap
}
// FillState exposes the current band (tests).
func (c *PBSDRBoxChecker) FillState() string {
c.mu.Lock()
defer c.mu.Unlock()
return orUnknown(c.fillBand)
}
func (c *PBSDRBoxChecker) emitFill(snap PBSBoxSnapshot, band string) {
var severity, message string
switch band {
case bandCritical:
severity = "critical"
message = fmt.Sprintf("PBS DR datastore %.0f%% full (%s of %s) — approaching capacity; the offsite DR tier's retention is at risk; free space or grow the datastore",
snap.FillPercent, fmtSize(snap.UsedBytes), fmtSize(snap.CapacityBytes))
case bandWarning:
severity = "warning"
message = fmt.Sprintf("PBS DR datastore %.0f%% full (%s of %s) — the offsite DR datastore is filling",
snap.FillPercent, fmtSize(snap.UsedBytes), fmtSize(snap.CapacityBytes))
default:
return
}
details, _ := json.Marshal(map[string]any{
"scope": pbsdrBoxScope, "capacity_bytes": snap.CapacityBytes, "used_bytes": snap.UsedBytes,
"fill_percent": snap.FillPercent, "warn_percent": c.fillWarn, "crit_percent": c.fillCrit,
})
c.logger.Printf("[INFO] PBS-DR box fill: %.0f%% (%s)", snap.FillPercent, band)
// NO SaveEvent — customer-less scope; straight to the operator dispatcher.
if c.onEvent != nil {
c.onEvent(pbsdrBoxScope, "pbsdr_box_fill", severity, message, string(details), "hub")
}
}