mirror of
https://github.com/netbirdio/netbird.git
synced 2026-10-04 20:49:06 +02:00
[client] Make netbird up wait for the daemon to become ready
The CLI up path only tolerated a not-yet-ready daemon via a 10s blocking dial, so "netbird service start" immediately followed by "netbird up" (e.g. a container entrypoint) failed with a generic "daemon not running" error. The container entrypoint worked around this with a shell poll loop (status --check live) before running up. Move the readiness wait into the CLI, mirroring how the GUI already dials: - DialClientGRPCServer now uses grpc.NewClient with a tuned reconnect backoff and waits for the connection to reach READY (retrying on TRANSIENT_FAILURE) up to a 30s deadline, instead of grpc.DialContext + WithBlock with a hard 10s timeout. - up now polls Status via waitForDaemonStatus, retrying while the RPC is Unavailable (socket up but service not yet registered). Add an explicit daemon-ready signal so clients can wait deterministically instead of heuristically: - New optional StatusResponse.daemonReady field (field 5, wire-compatible with older GUIs/daemons which leave it unset). Regenerated with the pinned protoc v33.1 toolchain so no version churn leaks into the diff. - The server sets ready once Start succeeds and the DaemonService is registered (SetReady, called from the service controller). - waitForDaemonStatus waits for daemonReady=true (or an already-Connected status), with a bounded grace window so older daemons that never set the field are not blocked. Simplify the container entrypoint accordingly: drop the readiness poll loop (up now waits) and the now-dead NB_ENTRYPOINT_SERVICE_TIMEOUT env, keeping only the daemon+up process glue and SIGTERM forwarding for clean shutdown.
This commit is contained in:
@@ -995,8 +995,13 @@ type StatusResponse struct {
|
||||
// Unset when the peer is not SSO-registered or login expiration is disabled.
|
||||
// The UI derives "warning active" from this value and its own clock.
|
||||
SessionExpiresAt *timestamppb.Timestamp `protobuf:"bytes,4,opt,name=sessionExpiresAt,proto3" json:"sessionExpiresAt,omitempty"`
|
||||
unknownFields protoimpl.UnknownFields
|
||||
sizeCache protoimpl.SizeCache
|
||||
// daemonReady reports whether the daemon has finished starting up and is
|
||||
// serving RPCs backed by a running engine. Older daemons never set this
|
||||
// (it defaults to false); clients must treat an unset value as "unknown"
|
||||
// and fall back to their previous readiness heuristics for compatibility.
|
||||
DaemonReady bool `protobuf:"varint,5,opt,name=daemonReady,proto3" json:"daemonReady,omitempty"`
|
||||
unknownFields protoimpl.UnknownFields
|
||||
sizeCache protoimpl.SizeCache
|
||||
}
|
||||
|
||||
func (x *StatusResponse) Reset() {
|
||||
@@ -1057,6 +1062,13 @@ func (x *StatusResponse) GetSessionExpiresAt() *timestamppb.Timestamp {
|
||||
return nil
|
||||
}
|
||||
|
||||
func (x *StatusResponse) GetDaemonReady() bool {
|
||||
if x != nil {
|
||||
return x.DaemonReady
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
type DownRequest struct {
|
||||
state protoimpl.MessageState `protogen:"open.v1"`
|
||||
unknownFields protoimpl.UnknownFields
|
||||
@@ -7083,14 +7095,15 @@ const file_daemon_proto_rawDesc = "" +
|
||||
"\x11getFullPeerStatus\x18\x01 \x01(\bR\x11getFullPeerStatus\x12(\n" +
|
||||
"\x0fshouldRunProbes\x18\x02 \x01(\bR\x0fshouldRunProbes\x12'\n" +
|
||||
"\fwaitForReady\x18\x03 \x01(\bH\x00R\fwaitForReady\x88\x01\x01B\x0f\n" +
|
||||
"\r_waitForReady\"\xca\x01\n" +
|
||||
"\r_waitForReady\"\xec\x01\n" +
|
||||
"\x0eStatusResponse\x12\x16\n" +
|
||||
"\x06status\x18\x01 \x01(\tR\x06status\x122\n" +
|
||||
"\n" +
|
||||
"fullStatus\x18\x02 \x01(\v2\x12.daemon.FullStatusR\n" +
|
||||
"fullStatus\x12$\n" +
|
||||
"\rdaemonVersion\x18\x03 \x01(\tR\rdaemonVersion\x12F\n" +
|
||||
"\x10sessionExpiresAt\x18\x04 \x01(\v2\x1a.google.protobuf.TimestampR\x10sessionExpiresAt\"\r\n" +
|
||||
"\x10sessionExpiresAt\x18\x04 \x01(\v2\x1a.google.protobuf.TimestampR\x10sessionExpiresAt\x12 \n" +
|
||||
"\vdaemonReady\x18\x05 \x01(\bR\vdaemonReady\"\r\n" +
|
||||
"\vDownRequest\"\x0e\n" +
|
||||
"\fDownResponse\"P\n" +
|
||||
"\x10GetConfigRequest\x12 \n" +
|
||||
|
||||
@@ -291,6 +291,11 @@ message StatusResponse{
|
||||
// Unset when the peer is not SSO-registered or login expiration is disabled.
|
||||
// The UI derives "warning active" from this value and its own clock.
|
||||
google.protobuf.Timestamp sessionExpiresAt = 4;
|
||||
// daemonReady reports whether the daemon has finished starting up and is
|
||||
// serving RPCs backed by a running engine. Older daemons never set this
|
||||
// (it defaults to false); clients must treat an unset value as "unknown"
|
||||
// and fall back to their previous readiness heuristics for compatibility.
|
||||
bool daemonReady = 5;
|
||||
}
|
||||
|
||||
message DownRequest {}
|
||||
|
||||
Reference in New Issue
Block a user