Retry tracker registration when initial connect fails.
Start background re-registration when the tracker is unreachable at startup so nodes do not stay permanently unregistered. Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
@@ -331,6 +331,9 @@ def _attach_relay_bridge(node: StubNodeServer | TorchNodeServer, bridge: RelayHt
|
||||
node.stop = _stop_with_bridge # type: ignore[method-assign]
|
||||
|
||||
|
||||
_PENDING_NODE_ID = "pending"
|
||||
|
||||
|
||||
def _start_heartbeat(
|
||||
tracker_url: str,
|
||||
node_id: str,
|
||||
@@ -421,7 +424,7 @@ def _start_heartbeat(
|
||||
def _loop() -> None:
|
||||
nonlocal node_id
|
||||
hb_url = f"{tracker_url}/v1/nodes/{node_id}/heartbeat"
|
||||
outage_streak = 0 # consecutive intervals where tracker was unreachable
|
||||
outage_streak = 1 if node_id == _PENDING_NODE_ID else 0
|
||||
|
||||
while True:
|
||||
time.sleep(interval)
|
||||
@@ -476,9 +479,6 @@ def _start_heartbeat(
|
||||
return t
|
||||
|
||||
|
||||
_PENDING_NODE_ID = "pending"
|
||||
|
||||
|
||||
def _register_with_tracker(
|
||||
tracker_url: str,
|
||||
reg_payload: dict,
|
||||
@@ -782,16 +782,9 @@ def run_startup(
|
||||
**registration_capabilities,
|
||||
**relay_fields,
|
||||
}
|
||||
tracker_node_id: str | None = None
|
||||
try:
|
||||
reg_resp = _post_json(f"{tracker_url}/v1/nodes/register", reg_payload)
|
||||
tracker_node_id = str(reg_resp.get("node_id") or "?")
|
||||
setattr(node, "tracker_node_id", tracker_node_id)
|
||||
print(f" Registered with tracker — node ID: {tracker_node_id}", flush=True)
|
||||
_start_heartbeat(tracker_url, tracker_node_id, reg_payload, node_ref=node, start_time=_node_start_time)
|
||||
except Exception as exc:
|
||||
setattr(node, "tracker_node_id", None)
|
||||
print(f" Warning: tracker registration failed: {exc}", flush=True)
|
||||
tracker_node_id = _register_with_tracker(
|
||||
tracker_url, reg_payload, node, _node_start_time,
|
||||
)
|
||||
|
||||
print(
|
||||
f"\n{'=' * 32}\n"
|
||||
@@ -917,16 +910,9 @@ def run_startup(
|
||||
**registration_capabilities,
|
||||
**relay_fields,
|
||||
}
|
||||
tracker_node_id = None
|
||||
try:
|
||||
reg_resp = _post_json(f"{tracker_url}/v1/nodes/register", auto_reg_payload)
|
||||
tracker_node_id = str(reg_resp.get("node_id") or "?")
|
||||
setattr(node, "tracker_node_id", tracker_node_id)
|
||||
print(f" Registered with tracker — node ID: {tracker_node_id}", flush=True)
|
||||
_start_heartbeat(tracker_url, tracker_node_id, auto_reg_payload, node_ref=node, start_time=_node_start_time)
|
||||
except Exception as exc:
|
||||
setattr(node, "tracker_node_id", None)
|
||||
print(f" Warning: tracker registration failed: {exc}", flush=True)
|
||||
tracker_node_id = _register_with_tracker(
|
||||
tracker_url, auto_reg_payload, node, _node_start_time,
|
||||
)
|
||||
shard_count = assigned_shard_end - assigned_shard_start + 1
|
||||
print(
|
||||
f"\n{'=' * 32}\n"
|
||||
|
||||
Reference in New Issue
Block a user