Files
housecarl/internal/server/h_health.go
T
abrown38andClaude Opus 5.5 de075edd5d Shadow mode: Housecarl beside the firewall in force, changing nothing
shadow.enabled in housecarl.yaml loads Housecarl's ruleset so that it
blocks, rejects and translates nothing: drops and rejects count and
accept (an accept only ends Housecarl's chain), policies accept and log
what they would drop, NAT only counts, MSS clamping and the flowtable
are left out, and raw rules that do more than accept, drop or reject are
left out with a warning. Comments mark what would happen ([would drop]).
Filter chains run after the other firewall's (+10) or before (-10); NAT
chains always first. Every change is checked by nftables in both forms.
No probation; takeovers and closing connections are refused. The boot
fallback filters nothing. internal/tablewatch puts the table back after
a flush ruleset. Mode in status, healthz, whoami, the web UI, the log
and the tracer; hc ruleset --enforcing. docs/shadow.md.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-20 18:11:01 +01:00

78 lines
2.3 KiB
Go

package server
import (
"net/http"
"sync"
"time"
"housecarl/internal/version"
)
// fallbackInForce is what status and /healthz say while the boot fallback
// (render.Fallback) is in force.
const fallbackInForce = "the boot fallback is in force, not Housecarl's ruleset: the saved ruleset failed to load at boot (journalctl -u housecarl-ruleset), and housecarld couldn't apply it since; it lets nothing new in from external zones (with none, nothing but loopback)"
// health is GET /healthz, for monitoring (Checkmk, a load balancer). It
// needs no authentication, so it says only what a monitor needs, and reads
// the ruleset at most every few seconds however often it is asked.
type health struct {
OK bool `json:"ok"`
Version string `json:"version"`
Firewall string `json:"firewall"` // applied, unconfigured, fallback, missing
// Mode is enforcing, or shadow: the ruleset blocks nothing.
Mode string `json:"mode"`
// Probation: changes waiting to be confirmed, rolled back otherwise.
Probation int `json:"probation"`
// Warnings are the codes of the machine's problems (nftables_service).
Warnings []string `json:"warnings"`
}
const healthTTL = 5 * time.Second
type healthCache struct {
mu sync.Mutex
at time.Time
out health
}
func (s *Server) healthz(w http.ResponseWriter, r *http.Request) {
c := &s.health
c.mu.Lock()
if time.Since(c.at) >= healthTTL {
c.out, c.at = s.checkHealth(r), time.Now()
}
out := c.out
c.mu.Unlock()
code := http.StatusOK
if !out.OK {
code = http.StatusServiceUnavailable
}
writeJSON(w, code, out)
}
func (s *Server) checkHealth(r *http.Request) health {
out := health{Version: version.String(), Warnings: []string{}, Mode: s.mode()}
t, err := s.fw.Table(r.Context())
switch {
case err != nil && s.eng.State().Empty():
out.Firewall, out.OK = "unconfigured", true
case err != nil:
out.Firewall = "missing"
case t.Fallback:
out.Firewall = "fallback"
default:
out.Firewall, out.OK = "applied", true
}
pr := s.probationStatus()
out.Probation = len(pr.Pending) + pr.Takeovers
// The other tables matter in shadow mode (shadow_unprotected).
var ruleset []byte
if s.cfg.Shadow {
ruleset, _ = s.fw.ListRuleset(r.Context())
}
for _, p := range s.hostProblems(r.Context(), ruleset) {
out.Warnings = append(out.Warnings, p.Code)
}
return out
}