vinzenz/hyperhive
vinzenz/hyperhive
Watch
0
0
Fork
You've already forked hyperhive
 0
Code Activity

hive-c0re: replace the agents_crashing banner with a crash-watcher log line + grafana alert

Browse source
This commit is contained in:
damocles 2026-10-12 22:21:04 +02:00 • committed by mara
commit 02831fb5e9
13 changed files with 214 additions and 224 deletions
Download patch file Download diff file Expand all files Collapse all files

18
hive-c0re/src/dashboard/state_snapshot.rs
View file

@ -120,13 +120,6 @@ struct TransientView {
secs: u64,
}
/// Window over which container crashes count toward the `agents_crashing`
/// banner warning. Wide enough that a crash-looping container (restarted
/// by `Restart=on-failure` every few seconds) keeps the warning lit
/// between flaps, short enough that a single recovered crash clears within
/// minutes.
const CRASH_WARNING_WINDOW: std::time::Duration = std::time::Duration::from_mins(10);
/// Cold-load snapshot of the whole dashboard.
///
/// Includes the roster, tombstones, job queue, meta inputs, and more. Live
@ -195,15 +188,12 @@ pub(super) async fn api_state(
let tombstones = build_tombstone_views(&state.coord, &containers);
let port_conflicts = build_port_conflicts(&containers);
// Banner warnings: host probes (disk) + agent-state (pending logins,
// crashing agents). Built before the response struct because the
// agent-state producer borrows `containers`, which moves in below.
// Banner warnings: host probes (disk) + agent-state (pending logins).
// Built before the response struct because the agent-state producer
// borrows `containers`, which moves in below.
let server_warnings = {
let mut w = crate::host_stats::server_warnings();
w.extend(crate::host_stats::agent_state_warnings(
&containers,
&state.coord.recent_crash_counts(CRASH_WARNING_WINDOW),
));
w.extend(crate::host_stats::agent_state_warnings(&containers));
w
};