vinzenz/hyperhive
vinzenz/hyperhive
Watch
0
0
Fork
You've already forked hyperhive
 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1

swarm-queue-based lifecycle notices, replacing push_todo(MANAGER_AGENT)

Browse source
This commit is contained in:
damocles 2026-08-16 15:58:45 +02:00 • committed by mara
commit e44ea9d8d4
12 changed files with 388 additions and 142 deletions
Download patch file Download diff file Expand all files Collapse all files

67
hive-c0re/src/swarm_status.rs
View file

@ -47,10 +47,6 @@ use crate::stats::sweep_health::{self, SweepHealth};
/// other silently re-tunes the swarm's definition of "quiet".
pub const PUBLISH_INTERVAL: Duration = Duration::from_mins(1);
/// Env var prefix for this daemon's swarm-queue credentials — see
/// [`swarm_queue_client::QueueConfig::from_env`]. All four or none.
const ENV_PREFIX: &str = "HIVE_C0RE";
/// Consecutive failed publishes before the dashboard banners.
///
/// At [`PUBLISH_INTERVAL`] this is ~3 minutes of genuine failure, so a
@ -59,43 +55,15 @@ const FAILURES_BEFORE_BANNER: u32 = 3;
/// Start the publish loop, if this deployment wired up a swarm queue.
///
/// Absent queue config is the ordinary case — most hives are not in a
/// swarm — so it is an `info` and not a warning. A *half*-set environment
/// is a different thing entirely and [`swarm_queue_client::QueueConfig::from_env`]
/// makes it a hard error; it is bannered here rather than swallowed,
/// because the failure it otherwise produces is a hive that looks fine
/// and silently never reports.
/// The connect itself is shared with every other swarm-queue consumer in
/// this process — see [`crate::swarm_queue`] for why one connection and
/// not one per consumer, and for where "no queue configured" vs. "queue
/// configured but unreachable" gets bannered. This function only decides
/// whether *status* has anything to offer once a client exists.
pub fn spawn(
coord: std::sync::Arc<crate::coordinator::Coordinator>,
mut shutdown: tokio::sync::watch::Receiver<bool>,
) {
let cfg = match swarm_queue_client::QueueConfig::from_env(ENV_PREFIX) {
Ok(Some(cfg)) => cfg,
Ok(None) => {
tracing::info!("no swarm queue configured; this hive offers no status upward");
return;
}
Err(e) => {
// A one-shot startup step with no later retry to clear it —
// exactly what `set_boot_warning` is for. The fix is a
// redeploy, which restarts this process anyway.
//
// `chain`, not `{:#}`: this is the queue client's own error
// type, whose Display ignores the alternate flag, so `{:#}`
// would show only "swarm queue is half-configured" and drop
// which variables are missing.
crate::warnings::set_boot_warning(
"swarm_status_config",
"warn",
format!(
"swarm status publishing is off: {}",
swarm_queue_client::chain(&e)
),
);
return;
}
};
let Some(hive) = crate::container_view::hive_swarm_names().0 else {
crate::warnings::set_boot_warning(
"swarm_status_config",
@ -107,26 +75,11 @@ pub fn spawn(
};
tokio::spawn(async move {
// `retry_on_initial_connect` inside, so this returns a client
// that may not be connected yet rather than failing on a queue
// that comes up second. The publish below is what discovers that,
// and it is already the thing that reports it.
let client = match swarm_queue_client::connect(cfg).await {
Ok(client) => client,
Err(e) => {
// `chain` for the same reason as above: without it this
// banner reads "connecting to the swarm queue at <url>"
// and drops the nats error that says why.
crate::warnings::set_boot_warning(
"swarm_status_config",
"warn",
format!(
"swarm status publishing is off: {}",
swarm_queue_client::chain(&e)
),
);
return;
}
let Some(client) = crate::swarm_queue::client().await else {
// Absent or failed — either way already handled (an `info`
// log or a `swarm_queue_config` banner) by the shared
// connector; nothing left to report here.
return;
};
// The hive's ONE queue connection, now serving both directions: