Files
felhom.eu/hub/internal/monitor/host_oob.go
T
admin f8fc09e5cc feat(hub): OOB access health ingest + degraded alert (H1 Part 4)
store.GetHostOOBStates parses the agent oob heartbeat stanza. monitor/host_oob:
transition-based oob_degraded/oob_recovered warning (felhom-sshd down while the
operator peer is configured, OR config invalid) — proactive "can the operator get
in right now" signal; unconfigured OOB never alerts. Wired into the 60s sweep.
Non-hollow tests + transitions.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PSK5g6qYLknKj8u3QAFEr6
2026-07-05 22:30:03 +02:00

149 lines
4.7 KiB
Go

package monitor
import (
"encoding/json"
"log"
"sync"
"gitea.dooplex.hu/admin/felhom-hub/internal/store"
)
// HostOOBChecker raises an operator WARNING when a host's OOB access path is DEGRADED — felhom-sshd
// down (while the operator peer is configured, i.e. OOB is meant to work) OR its config is invalid.
// It answers "can the operator get into this box right now, and if not, why" proactively, from the
// hub. Transition-based (ok↔degraded, one event per transition — the HostCapabilityChecker shape), so
// a persistent problem alerts ONCE, not every 60s sweep, and a recovery is noted.
//
// A host with no oob stanza (pre-H1 / feature off) is never evaluated. A degraded state requires the
// operator peer to be configured — a box where OOB was never set up is not "broken".
type HostOOBChecker struct {
store *store.Store
logger *log.Logger
onEvent EventNotifyFunc
mu sync.Mutex
degraded map[string]bool // hostID → currently-degraded
customerOf map[string]string
}
// NewHostOOBChecker seeds per-host degraded state from the latest reports WITHOUT alerting (a problem
// present at startup alerts on the first transition-in evaluated after seed = never re-alerts a
// steady bad state; matches HostCapabilityChecker). Actually seeds silent, then Check transitions.
func NewHostOOBChecker(s *store.Store, onEvent EventNotifyFunc, logger *log.Logger) *HostOOBChecker {
c := &HostOOBChecker{
store: s,
logger: logger,
onEvent: onEvent,
degraded: make(map[string]bool),
customerOf: make(map[string]string),
}
rows, err := s.GetHostOOBStates()
if err != nil {
logger.Printf("[WARN] Host OOB checker: failed to seed: %v", err)
return c
}
seeded := 0
for _, row := range rows {
if s.IsCustomerBlocked(row.CustomerID) || !row.Present {
continue
}
c.customerOf[row.HostID] = row.CustomerID
if oobDegraded(row) {
c.degraded[row.HostID] = true // seed the bad state so we don't re-alert it on cycle 1
seeded++
}
}
logger.Printf("[INFO] Host OOB checker initialized: %d host(s) seeded degraded", seeded)
return c
}
// oobDegraded is the degraded predicate: config invalid, OR (OOB meant to work — operator peer
// configured — AND felhom-sshd is not active/reachable).
func oobDegraded(r store.HostOOBRow) bool {
if !r.Present {
return false
}
if r.ConfigInvalid {
return true
}
if r.OperatorPeerConfigured && (!r.FelhomSshdActive || !r.Reachable) {
return true
}
return false
}
// Check evaluates all hosts and emits oob_degraded / oob_recovered on transitions.
func (c *HostOOBChecker) Check() {
rows, err := c.store.GetHostOOBStates()
if err != nil {
c.logger.Printf("[WARN] Host OOB check failed: %v", err)
return
}
c.mu.Lock()
defer c.mu.Unlock()
seen := make(map[string]bool, len(rows))
for _, row := range rows {
if c.store.IsCustomerBlocked(row.CustomerID) {
delete(c.degraded, row.HostID)
continue
}
if !row.Present {
continue // no oob stanza → not evaluated
}
seen[row.HostID] = true
c.customerOf[row.HostID] = row.CustomerID
bad := oobDegraded(row)
was := c.degraded[row.HostID]
switch {
case bad && !was:
c.degraded[row.HostID] = true
c.emit(row, "oob_degraded", "warning")
case !bad && was:
delete(c.degraded, row.HostID)
c.emit(row, "oob_recovered", "info")
}
}
for id := range c.degraded {
if !seen[id] {
delete(c.degraded, id)
}
}
}
// IsDegraded reports the current tracked state for a host (test/UI helper).
func (c *HostOOBChecker) IsDegraded(hostID string) bool {
c.mu.Lock()
defer c.mu.Unlock()
return c.degraded[hostID]
}
func (c *HostOOBChecker) emit(row store.HostOOBRow, eventType, severity string) {
var msg string
if eventType == "oob_degraded" {
reason := "felhom-sshd unreachable"
if row.ConfigInvalid {
reason = "felhom-sshd config invalid (sshd -t fails)"
}
msg = "Host " + row.HostID + ": OPERATOR ACCESS DEGRADED — " + reason +
". The break-glass net (auto-heal + vaulted root@pam console) is still under the box."
} else {
msg = "Host " + row.HostID + ": operator access recovered (felhom-sshd reachable again)."
}
details, _ := json.Marshal(map[string]any{
"host_id": row.HostID,
"felhom_sshd_port": row.FelhomSshdPort,
"active": row.FelhomSshdActive,
"reachable": row.Reachable,
"config_invalid": row.ConfigInvalid,
})
c.logger.Printf("[%s] Host OOB: %s (%s)", map[string]string{"warning": "WARN", "info": "INFO"}[severity], row.HostID, eventType)
if _, err := c.store.SaveEvent(row.CustomerID, eventType, severity, msg, string(details), "hub"); err != nil {
c.logger.Printf("[WARN] save %s for %s: %v", eventType, row.HostID, err)
return
}
if c.onEvent != nil {
c.onEvent(row.CustomerID, eventType, severity, msg, string(details), "hub")
}
}