vinzenz/hyperhive
vinzenz/hyperhive
Watch
0
0
Fork
You've already forked hyperhive
 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

feat(#2392): group boot sweep + reconciles under one boot dag

Browse source
This commit is contained in:
damocles 2026-07-13 11:34:42 +02:00 • committed by mara
commit 16f69ca890
6 changed files with 111 additions and 23 deletions
Download patch file Download diff file Expand all files Collapse all files

77
hive-c0re/src/workers/auto_update.rs
View file

@ -273,10 +273,52 @@ pub async fn run(coord: Arc<Coordinator>) -> Result<()> {
"boot reconcile"
);
// Sweep parent whenever ANY marker is stale — even when every
// stale agent is wanted-offline: the hyperhive lock bump must land
// now so their later start-upgrade rebuilds build against it.
// No stale agents ⇒ no sweep ⇒ no meta commit on a no-change boot.
submit_boot_tree(&coord, any_stale, fanout, drifted, n_deferred, n_skipped);
Ok(())
}
/// Submit this boot's DAGs under one `Boot` root: a `Noop` anchor with the
/// startup sweep + per-agent reconciles hung off it via `parent_id`, so the
/// dashboard renders the boot as a single tree instead of N+1 rows. No-op when
/// there's nothing to do. The `parent_id` link is a display grouping, not a
/// dependency edge — the children run concurrently, so the reconciles never
/// wait behind the lock bump.
fn submit_boot_tree(
coord: &Arc<Coordinator>,
any_stale: bool,
fanout: Vec<String>,
drifted: Vec<String>,
n_deferred: usize,
n_skipped: usize,
) {
// Only emit a boot root when there's actually boot work — a fully-quiet
// boot (nothing stale, nothing drifted) submits nothing, exactly as before.
let boot_root_id = if any_stale || !drifted.is_empty() {
let reason = format!(
"boot: {} rebuild(s), {} reconcile(s), {} deferred (offline), {} up-to-date",
fanout.len(),
drifted.len(),
n_deferred,
n_skipped,
);
match coord
.job_queue
.submit(crate::job_queue::templates::boot_root(reason))
{
Ok(id) => Some(id),
Err(e) => {
tracing::warn!(error = ?e, "boot reconcile: boot-root submit failed");
None
}
}
} else {
None
};
// Sweep whenever ANY marker is stale — even when every stale agent is
// wanted-offline: the hyperhive lock bump must land now so their later
// start-upgrade rebuilds build against it. No stale agents ⇒ no sweep ⇒ no
// meta commit on a no-change boot.
if any_stale {
let reason = format!(
"startup sweep: {} rebuild(s), {} deferred (offline), {} up-to-date",
@ -284,27 +326,24 @@ pub async fn run(coord: Arc<Coordinator>) -> Result<()> {
n_deferred,
n_skipped,
);
if let Err(e) = coord
.job_queue
.submit(crate::job_queue::templates::startup_sweep(reason, fanout))
{
let mut spec = crate::job_queue::templates::startup_sweep(reason, fanout);
spec.parent_id = boot_root_id;
if let Err(e) = coord.job_queue.submit(spec) {
tracing::warn!(error = ?e, "boot reconcile: sweep submit failed");
}
}
for name in drifted {
if let Err(e) = coord
.job_queue
.submit(crate::job_queue::templates::reconcile_only(
crate::job_queue::Template::Reconcile,
&name,
crate::job_queue::Source::AutoUpdate,
"boot reconcile".to_owned(),
None,
))
{
let mut spec = crate::job_queue::templates::reconcile_only(
crate::job_queue::Template::Reconcile,
&name,
crate::job_queue::Source::AutoUpdate,
"boot reconcile".to_owned(),
None,
);
spec.parent_id = boot_root_id;
if let Err(e) = coord.job_queue.submit(spec) {
tracing::warn!(%name, error = ?e, "boot reconcile: submit failed");
}
}
coord.emit_rebuild_queue_snapshot();
Ok(())
}