Audiobuzz
df7dad81b7
The manager lets an admin schedule a reboot (desired.reboot_at) but never showed whether it had happened. Add host uptime to the health snapshot and derive a reboot status from it. - proto: HealthSnapshot.uptime_seconds (15); regenerated pb.go (manager + agent copy). - agent: probe /proc/uptime -> uptime_seconds (with parser + test). - manager: Health.UptimeSeconds cached in inventory; snapshotToHealth maps it; influx writes + whitelists uptime_seconds as a queryable field. - UI: fmt.js dur() + rebootStatus() — boot_time = last_seen - uptime (manager clock frame, no host/manager sync needed), compared to reboot_at. Monitor host detail shows an "uptime" row and a "reboot" row: pending in X / overdue by X / rebooted. Observability-only — works before the reboot ACTUATOR lands (deferred). Once a host boots after the scheduled time (BMC/manual now, agent later), the badge flips to "rebooted" automatically.
99 lines
3.6 KiB
Protocol Buffer
99 lines
3.6 KiB
Protocol Buffer
syntax = "proto3";
|
|
|
|
// The steady-state contract between the on-host fleet agent and the
|
|
// fleet-manager. ONE long-lived, host-dialed, mTLS bidi stream (health/metrics
|
|
// up, desired-state down) — the design's resolved transport fork (bespoke gRPC,
|
|
// not OTLP+Wazuh). See docs/fleet-management-design.md + tpm-enrolment-design.md.
|
|
//
|
|
// Identity is the mTLS peer cert (the host's reused TPM identity cert, fleet CA);
|
|
// the manager derives the cert serial (= inventory key) from it, so AgentUp
|
|
// messages carry NO self-asserted identity — a host can only ever be itself.
|
|
package fleet.agent.v1;
|
|
|
|
option go_package = "fleet-manager/proto;fleetpb";
|
|
|
|
service FleetAgent {
|
|
// Session: the single bidirectional stream. The host opens it (dials out, no
|
|
// inbound host port); the manager pushes desired-state/commands back over the
|
|
// same connection. Closing/keepalive-timeout = the host's offline signal.
|
|
rpc Session(stream AgentUp) returns (stream ManagerDown);
|
|
}
|
|
|
|
// ---- host -> manager ------------------------------------------------------
|
|
|
|
message AgentUp {
|
|
oneof msg {
|
|
Hello hello = 1; // first frame after connect
|
|
HealthSnapshot snapshot = 2; // periodic telemetry (also written to InfluxDB)
|
|
CommandResult result = 3; // outcome of a ManagerDown.Command
|
|
}
|
|
}
|
|
|
|
// Hello — what the host is running, sent once on connect so the manager can
|
|
// reconcile version drift immediately.
|
|
message Hello {
|
|
string image_version = 1;
|
|
string rootfs_digest = 2;
|
|
string kernel = 3;
|
|
string kiosk_url = 4;
|
|
string starship_name = 5; // advisory; manager already knows it from inventory
|
|
}
|
|
|
|
// HealthSnapshot — one telemetry sample. Cached as the latest value in inventory
|
|
// AND written as a time-series point to InfluxDB (tagged with the authenticated
|
|
// cert serial / hostnqn).
|
|
message HealthSnapshot {
|
|
int64 at_unix = 1; // sample time, unix seconds (0 = manager stamps now)
|
|
double load_avg = 2;
|
|
double cpu_pct = 3;
|
|
double temp_c = 4;
|
|
double mem_used_pct = 5;
|
|
double tmpfs_used_pct = 6; // overlay RAM pressure
|
|
string nvme_root = 7; // ok|degraded|down
|
|
string auth = 8; // 802.1x/macsec: up|down
|
|
string selinux = 9; // enforcing|permissive
|
|
string chrony = 10; // synced|unsynced
|
|
bool kiosk_active = 11;
|
|
string session_uptime = 12; // KIOSK session uptime (advisory string)
|
|
int32 chromium_crashes = 13;
|
|
string display = 14;
|
|
int64 uptime_seconds = 15; // HOST uptime (seconds since boot) — boot_time =
|
|
// manager receive-time - this; drives reboot-pending
|
|
}
|
|
|
|
message CommandResult {
|
|
string command_id = 1;
|
|
bool ok = 2;
|
|
string detail = 3;
|
|
}
|
|
|
|
// ---- manager -> host ------------------------------------------------------
|
|
|
|
message ManagerDown {
|
|
oneof msg {
|
|
DesiredState desired = 1; // full desired-state: sent on connect + on change
|
|
Command command = 2; // imperative action
|
|
}
|
|
}
|
|
|
|
// DesiredState — server-authoritative target the agent reconciles toward.
|
|
message DesiredState {
|
|
string target_version = 1;
|
|
string kiosk_url = 2;
|
|
int64 reboot_at_unix = 3; // 0 = no scheduled reboot
|
|
bool drain = 4;
|
|
}
|
|
|
|
// Command — an imperative action pushed live (admin clicked a button in the SPA).
|
|
message Command {
|
|
string command_id = 1;
|
|
Kind kind = 2;
|
|
|
|
enum Kind {
|
|
KIND_UNSPECIFIED = 0;
|
|
REBOOT = 1; // reboot now (into desired target_version)
|
|
DRAIN = 2; // stop taking work / prepare for maintenance
|
|
RESYNC = 3; // re-fetch + re-apply desired-state now
|
|
}
|
|
}
|