happyDomain/checker-alias
2
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

checker: report chain transport errors as Unknown, not Warn

Browse source 
A transport-level query failure (connection refused, timeout, network
unreachable) means the alias state could not be observed, not that the
alias is misconfigured. Mapping it to Warn made the check flap whenever a
flaky auth server alternated between refusing connections (Warn) and
answering SERVFAIL (Crit). Report TermQueryErr as Unknown so only
definitive DNS evidence drives Warn/Crit.
This commit is contained in:
nemunaire 2026-06-18 09:30:01 +09:00
commit 680a7735f0
2 changed files with 8 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

10
checker/rules_chain.go
View file

@ -90,11 +90,15 @@ func (chainQueryErrorRule) Evaluate(ctx context.Context, obs sdk.ObservationGett
if data.ChainTerminated.Reason != TermQueryErr {
return okState(data.Owner, "all chain queries succeeded")
}
// A transport failure (connection refused, timeout, network unreachable)
// means we could not observe the alias, not that the alias is broken. Report
// it as Unknown so an intermittent reachability glitch does not flap the
// check into Warn/Crit; only definitive DNS evidence drives those statuses.
return []sdk.CheckState{withHint(sdk.CheckState{
Status: sdk.StatusWarn,
Status: sdk.StatusUnknown,
Subject: data.ChainTerminated.Subject,
Message: fmt.Sprintf("CNAME query for %s failed: %s", data.ChainTerminated.Subject, data.ChainTerminated.Detail),
}, "Check authoritative-server reachability and firewall rules; the alias is unusable while queries fail.")}
Message: fmt.Sprintf("CNAME query for %s could not be completed: %s", data.ChainTerminated.Subject, data.ChainTerminated.Detail),
}, "Check authoritative-server reachability and firewall rules; the alias state could not be determined while queries fail.")}
}
type chainRcodeRule struct{}

2
checker/rules_test.go
View file

@ -125,7 +125,7 @@ func TestChainQueryErrorRule(t *testing.T) {
t.Run("query err", func(t *testing.T) {
d := apexKnownData()
d.ChainTerminated = ChainTermination{Reason: TermQueryErr, Subject: "broken.example.com.", Detail: "timeout"}
assertSingle(t, run(chainQueryErrorRule{}, d, nil), sdk.StatusWarn)
assertSingle(t, run(chainQueryErrorRule{}, d, nil), sdk.StatusUnknown)
})
}