1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
|
{ pkgs, lib, ... }:
{
name = "netbird";
meta.maintainers = with pkgs.lib.maintainers; [
nazarewk
];
nodes = {
node = {
services.netbird = {
enable = true;
clients.custom.port = 51819;
ui.enable = true;
};
};
};
/*
Historically waiting for the NetBird client daemon initialization helped catch number of bugs with the service,
so we keep try to keep it here in as much details as it makes sense.
Initially `netbird status` returns a "Disconnected" messages:
OS: linux/amd64
Daemon version: 0.54.0
CLI version: 0.54.0
Profile: default
Management: Disconnected, reason: rpc error: code = FailedPrecondition desc = failed connecting to Management Service : context deadline exceeded
Signal: Disconnected
Relays: 0/0 Available
Nameservers: 0/0 Available
FQDN:
NetBird IP: N/A
Interface type: N/A
Quantum resistance: false
Lazy connection: false
Networks: -
Forwarding rules: 0
Peers count: 0/0 Connected
After a while passes it should start returning "NeedsLogin" help message.
As of ~0.53.0+ in ~30 second intervals the `netbird status` instead of "NeedsLogin" it briefly (for under 2 seconds) crashes with:
Error: status failed: failed connecting to Management Service : context deadline exceeded
This might be related to the following log line:
2025-08-11T15:03:25Z ERRO shared/management/client/grpc.go:65: failed creating connection to Management Service: context deadline exceeded
*/
# TODO: confirm the whole solution is working end-to-end when netbird server is implemented
testScript = ''
import textwrap
import time
start_all()
def run_with_debug(node, cmd, check=True, display=True, **kwargs):
cmd = f"{cmd} 2>&1"
start = time.time()
ret, output = node.execute(cmd, **kwargs)
duration = time.time() - start
txt = f">>> {cmd=} {ret=} {duration=:.2f}:\n{textwrap.indent(output, '... ')}"
if check:
assert ret == 0, txt
if display:
print(txt)
return ret, output
def wait_until_rcode(node, cmd, rcode=0, retries=30, **kwargs):
def check_success(_last_try):
nonlocal output
ret, output = run_with_debug(node, cmd, **kwargs)
return ret == rcode
kwargs.setdefault('check', False)
output = None
with node.nested(f"waiting for {cmd=} to exit with {rcode=}"):
retry(check_success, retries)
return output
instances = ["netbird", "netbird-custom"]
for name in instances:
node.wait_for_unit(f"{name}.service")
node.wait_for_file(f"/var/run/{name}/sock")
for name in instances:
wait_until_rcode(node, f"{name} status |& grep -C20 Disconnected", 0, retries=5)
''
# The status used to turn into `NeedsLogin`, but recently started crashing instead.
# leaving the snippets in here, in case some update goes back to the old behavior and can be tested again
+ lib.optionalString false ''
for name in instances:
#wait_until_rcode(node, f"{name} status |& grep -C20 NeedsLogin", 0, retries=20)
output = wait_until_rcode(node, f"{name} status", 1, retries=61)
msg = "Error: status failed: failed connecting to Management Service : context deadline exceeded"
assert output.strip() == msg, f"expected {msg=}, got {output=} instead"
wait_until_rcode(node, f"{name} status |& grep -C20 Disconnected", 0, retries=10)
'';
}
|
