Watch
0
0
Fork
You've already forked hyperhive
0

a failed container start shows the unit's own journal lines in the op output

This commit is contained in:
atlas 2026-11-01 16:33:26 +01:00 • committed by mara
commit 9a773349a8
3 changed files with 203 additions and 5 deletions

View file

@ -799,16 +799,23 @@ fn make_log_callback(
/// Put a failed non-streaming op's error into its build-log row, which has no
/// other output: `start` runs through `call`, not the streaming protocol. The
/// error carries `nixos-container`'s stderr.
/// error carries `nixos-container`'s stderr; `journal` is the container
/// unit's own log from hive-priv. An `Err` there (an older hive-priv does not
/// know the op) leaves the stderr alone.
fn record_failure(
logs: Option<&crate::build_logs::BuildLogs>,
log_id: Option<i64>,
err: &anyhow::Error,
journal: Result<String>,
) {
if let (Some(h), Some(id)) = (logs, log_id) {
for line in format!("{err:#}").lines() {
h.append_stderr(id, line);
}
match journal {
Ok(text) => text.lines().for_each(|l| h.append_stderr(id, l)),
Err(e) => tracing::debug!(error = ?e, "start journal unavailable"),
}
}
}
@ -879,9 +886,13 @@ async fn priv_run_inner(
None => Err(missing_toplevel(kind, name)),
},
"start" => {
let attempt = std::time::SystemTime::now()
.duration_since(std::time::UNIX_EPOCH)
.map_or(0, |d| d.as_secs());
let started = crate::priv_client::start_container(name).await;
if let Err(e) = &started {
record_failure(logs.as_deref(), log_id, e);
let journal = crate::priv_client::start_failure_log(name, attempt).await;
record_failure(logs.as_deref(), log_id, e, journal);
}
started
}

View file

@ -529,9 +529,33 @@ fn a_failed_start_puts_its_error_in_the_op_output() {
.start("updo", "start", "nixos-container start h-updo", None)
.expect("start");
let err = anyhow::anyhow!("nixos-container start h-updo failed (exit status: 1): Job failed");
record_failure(Some(&logs), Some(id), &err);
let journal = Ok("Creating mount point failed: Read-only file system".to_owned());
record_failure(Some(&logs), Some(id), &err, journal);
let full = logs.get_full(id).expect("get").expect("row");
assert!(full.stderr.contains("Job failed"), "{}", full.stderr);
record_failure(Some(&logs), None, &err);
record_failure(None, Some(id), &err);
assert!(
full.stderr.contains("Read-only file system"),
"{}",
full.stderr
);
record_failure(Some(&logs), None, &err, Ok(String::new()));
record_failure(None, Some(id), &err, Ok(String::new()));
}
/// An older hive-priv rejects the op; the start's own error is still recorded.
#[test]
fn an_unknown_journal_op_keeps_the_start_error() {
let dir = tempfile::tempdir().expect("tempdir");
let logs = crate::build_logs::BuildLogs::open(dir.path()).expect("open");
let id = logs
.start("updo", "start", "nixos-container start h-updo", None)
.expect("start");
let err = anyhow::anyhow!("Job failed");
let unknown = Err(anyhow::anyhow!(
"parse request: unknown variant `start_failure_log`"
));
record_failure(Some(&logs), Some(id), &err, unknown);
let full = logs.get_full(id).expect("get").expect("row");
assert!(full.stderr.contains("Job failed"), "{}", full.stderr);
assert!(!full.stderr.contains("unknown variant"), "{}", full.stderr);
}

View file

@ -216,6 +216,19 @@ pub async fn start_container(name: &str) -> Result<()> {
.await?)
}
/// The container unit's journal lines since `since_unix`. An older hive-priv
/// answers an error (it does not know the op).
pub async fn start_failure_log(name: &str, since_unix: u64) -> Result<String> {
let (stdout, _) = check(
call(&PrivRequest::StartFailureLog {
name: name.to_owned(),
since_unix,
})
.await?,
)?;
Ok(stdout)
}
pub async fn stop_container(name: &str) -> Result<()> {
ok(call(&PrivRequest::StopContainer {
name: name.to_owned(),