job_queue: retire the now-off-wire step sub-step label
The `step` label was taken off the wire in #2661, when each deploy phase became a first-class DAG node. Since then it has been written but never read: `NodeRuntime` derives only `Debug, Default, Clone` — no serde — so the field could not reach any client, and the only reads of it were the dedup checks inside its own setters. This deletes the machinery. Removed: - `NodeRuntime.step`, `set_step`, `set_step_running`, and the `rt.step = None` clear in `complete_node`. `NodeRuntime` keeps its remaining `build_log_id` field (deliberately still a struct — collapsing it to a bare `Option<i64>` would churn every call site for no gain). - `Ctx::step` and its ~15 call sites in `job_queue/exec.rs`. `Ctx` itself stays: it is the build-log sink, which `run_prebuild` and `run_swap` still use. - `Coordinator::set_queue_step` and its 11 callers in `actions.rs`. - `JobQueue::running_node_of`, reachable only from `set_queue_step`. - `swap_update`'s `on_step` parameter and its one body call. - The `set_step_only_on_running_and_signals_change` test. Dropping the calls orphaned parameters, which are removed with their call sites: `ctx` on ten executors that used it only as a step sink, and `queue_entry_id` on `run_deploy_merge_verify` / `run_deploy_apply` / `run_finalize_deploy` plus both `coord` and `queue_entry_id` on `prepare_applied_target`. `run_deploy_tail` KEEPS its `queue_entry_id` — that one has a genuine surviving use (the build-log link in the failure comment posted to the PR). One behavioural change, called out so it is not mistaken for a dropped dashboard refresh: `Ctx::step` and `set_queue_step` each emitted a `rebuild_queue_changed` snapshot when the label changed, and those emissions go away with them. This is safe — the snapshot payload has no step field, so those pushes carried nothing a client could observe. Real state transitions still emit from the scheduler's claim and completion paths, from `submit`, and from the three `actions.rs` sites. Net effect is strictly fewer redundant SSE pushes. Docs: `docs/coordinator.md` still listed `step` as a `NodeView` wire field and `docs/web-ui/dashboard.md` documented a cyan `↳ <step>` sub-line under each queue row. Neither has existed since #2661 — both corrected here, plus the `job_queue/model.rs` module doc. Not touched: `frontend/packages/dashboard/src/system-sections.css` has a dead `.rqe-step` rule with no JS referencing it. Left for the frontend owner rather than deleted here. Closes: #2664
This commit is contained in:
atlas
mara
parent
ff62bf2235
commit
1db3cc32a1
9 changed files with 51 additions and 210 deletions
|
|
@ -43,7 +43,7 @@ pub struct NodeOutput {
|
|||
pub append_subgraph: Vec<Vec<NodeSpec>>,
|
||||
}
|
||||
|
||||
/// Step-label + build-log sink for one claimed node.
|
||||
/// Build-log sink for one claimed node.
|
||||
struct Ctx<'a> {
|
||||
coord: &'a Arc<Coordinator>,
|
||||
dag_id: u64,
|
||||
|
|
@ -51,16 +51,6 @@ struct Ctx<'a> {
|
|||
}
|
||||
|
||||
impl Ctx<'_> {
|
||||
fn step(&self, step: &str) {
|
||||
if self
|
||||
.coord
|
||||
.job_queue
|
||||
.set_step(self.dag_id, self.node_id, step)
|
||||
{
|
||||
self.coord.emit_rebuild_queue_snapshot();
|
||||
}
|
||||
}
|
||||
|
||||
fn build_log(&self, log_id: i64) {
|
||||
if self
|
||||
.coord
|
||||
|
|
@ -85,20 +75,20 @@ pub(super) async fn run_node(coord: &Arc<Coordinator>, claim: &Claim) -> Result<
|
|||
NodeKind::MetaSync { relock, .. } => run_meta_sync(coord, claim, *relock).await,
|
||||
NodeKind::Prebuild { .. } => run_prebuild(claim, &ctx).await,
|
||||
NodeKind::Swap { .. } => run_swap(coord, claim, &ctx).await,
|
||||
NodeKind::PostSwap { .. } => run_post_swap(coord, claim, &ctx).await,
|
||||
NodeKind::Provision { .. } => run_provision(coord, claim, &ctx).await,
|
||||
NodeKind::Create { .. } => run_create(claim, &ctx).await,
|
||||
NodeKind::PostSwap { .. } => run_post_swap(coord, claim).await,
|
||||
NodeKind::Provision { .. } => run_provision(coord, claim).await,
|
||||
NodeKind::Create { .. } => run_create(claim).await,
|
||||
NodeKind::MetaLock { sweep, fanout } => {
|
||||
run_meta_lock(coord, claim, &ctx, *sweep, fanout.clone()).await
|
||||
run_meta_lock(coord, claim, *sweep, fanout.clone()).await
|
||||
}
|
||||
NodeKind::Reconcile { .. } => run_reconcile(coord, claim).await,
|
||||
NodeKind::Start { .. } => run_start(coord, claim, &ctx).await,
|
||||
NodeKind::Stop { .. } => run_stop(coord, claim, &ctx).await,
|
||||
NodeKind::StopForUpdate { .. } => run_stop_for_update(coord, claim, &ctx).await,
|
||||
NodeKind::Signal { .. } => Ok(run_signal(coord, claim, &ctx)),
|
||||
NodeKind::Drain { .. } => run_drain(coord, claim, &ctx).await,
|
||||
NodeKind::Start { .. } => run_start(coord, claim).await,
|
||||
NodeKind::Stop { .. } => run_stop(coord, claim).await,
|
||||
NodeKind::StopForUpdate { .. } => run_stop_for_update(coord, claim).await,
|
||||
NodeKind::Signal { .. } => Ok(run_signal(coord, claim)),
|
||||
NodeKind::Drain { .. } => run_drain(coord, claim).await,
|
||||
NodeKind::WriteDropin { .. } => run_write_dropin(coord, claim).await,
|
||||
NodeKind::WritePermFile { .. } => run_write_perm_file(coord, claim, &ctx).await,
|
||||
NodeKind::WritePermFile { .. } => run_write_perm_file(coord, claim).await,
|
||||
NodeKind::DeployWindow { .. } => run_deploy_window(claim),
|
||||
NodeKind::MergeVerify { .. } => run_merge_verify(coord, claim).await,
|
||||
NodeKind::DeployApply { .. } => run_deploy_apply(coord, claim).await,
|
||||
|
|
@ -239,12 +229,9 @@ async fn run_prebuild(claim: &Claim, ctx: &Ctx<'_>) -> Result<NodeOutput> {
|
|||
// stopped agent has no uptime to preserve, so skip the (expensive)
|
||||
// eval and let the downstream `Swap` build inline.
|
||||
if crate::lifecycle::is_running(name).await {
|
||||
ctx.step("nix build");
|
||||
let flake_ref = format!("{}#{name}", crate::paths::meta_root().display());
|
||||
crate::lifecycle::prebuild_toplevel(name, &flake_ref, &|log_id| ctx.build_log(log_id))
|
||||
.await?;
|
||||
} else {
|
||||
ctx.step("skipped prebuild (container down)");
|
||||
}
|
||||
Ok(NodeOutput::default())
|
||||
}
|
||||
|
|
@ -261,11 +248,10 @@ async fn run_swap(coord: &Arc<Coordinator>, claim: &Claim, ctx: &Ctx<'_>) -> Res
|
|||
let agent_dir = crate::paths::agent_runtime_dir(name);
|
||||
let hive = coord.hive_env();
|
||||
let paths = Coordinator::agent_paths(name, agent_dir);
|
||||
let result =
|
||||
crate::lifecycle::swap_update(name, &hive, &paths, &|step| ctx.step(step), &|log_id| {
|
||||
ctx.build_log(log_id);
|
||||
})
|
||||
.await;
|
||||
let result = crate::lifecycle::swap_update(name, &hive, &paths, &|log_id| {
|
||||
ctx.build_log(log_id);
|
||||
})
|
||||
.await;
|
||||
// On success the Ok-only bookkeeping tail (rev marker, forge/matrix
|
||||
// sync, kick, rescan, snapshot) runs in the sibling `PostSwap` node,
|
||||
// which deps `AfterOk(Swap)`. On failure `PostSwap` is cancel-cascaded
|
||||
|
|
@ -284,11 +270,7 @@ async fn run_swap(coord: &Arc<Coordinator>, claim: &Claim, ctx: &Ctx<'_>) -> Res
|
|||
/// means the profile swap succeeded. Store/forge/matrix work only — no nix
|
||||
/// build (build-slot-exempt); the agent lease taken at `Swap` is still held
|
||||
/// (the whole chain up to `Reconcile` is one agent's subgraph).
|
||||
async fn run_post_swap(
|
||||
coord: &Arc<Coordinator>,
|
||||
claim: &Claim,
|
||||
ctx: &Ctx<'_>,
|
||||
) -> Result<NodeOutput> {
|
||||
async fn run_post_swap(coord: &Arc<Coordinator>, claim: &Claim) -> Result<NodeOutput> {
|
||||
let name = &claim.agent;
|
||||
if let Some(rev) = crate::auto_update::current_flake_rev(&coord.hyperhive_flake)
|
||||
&& let Err(e) = std::fs::write(crate::paths::applied_rev_marker(name), rev)
|
||||
|
|
@ -298,7 +280,6 @@ async fn run_post_swap(
|
|||
// The `Rebuilt` manager event fires exactly once per DAG from the
|
||||
// terminal hook — emitting ok here and letting a failed tail `Reconcile`
|
||||
// add a contradictory !ok would double-report the same rebuild.
|
||||
ctx.step("forge sync");
|
||||
// Full forge + matrix sync on every successful rebuild so the rebuild
|
||||
// path is equivalent to the startup sweep: tokens, config-repo mirror,
|
||||
// meta access all recover without a hive-c0re restart.
|
||||
|
|
@ -317,16 +298,11 @@ async fn run_post_swap(
|
|||
/// subvolume, and the meta `sync_agents` registration. Runs under the
|
||||
/// deploy window (`NodeKind::needs_meta_window`) so its commit can't
|
||||
/// land inside another node's staged deploy window.
|
||||
async fn run_provision(
|
||||
coord: &Arc<Coordinator>,
|
||||
claim: &Claim,
|
||||
ctx: &Ctx<'_>,
|
||||
) -> Result<NodeOutput> {
|
||||
async fn run_provision(coord: &Arc<Coordinator>, claim: &Claim) -> Result<NodeOutput> {
|
||||
let name = &claim.agent;
|
||||
let agent_dir = crate::paths::agent_runtime_dir(name);
|
||||
let hive = coord.hive_env();
|
||||
let paths = Coordinator::agent_paths(name, agent_dir);
|
||||
ctx.step("provisioning");
|
||||
crate::lifecycle::provision_container(name, &hive, &paths).await?;
|
||||
Ok(NodeOutput::default())
|
||||
}
|
||||
|
|
@ -337,8 +313,7 @@ async fn run_provision(
|
|||
/// dir creation and MCP listener registration are deferred to the tail
|
||||
/// `Reconcile` (`converge_start_preamble` + `register_agent`) so this
|
||||
/// node stays purely "create", not "create + start".
|
||||
async fn run_create(claim: &Claim, ctx: &Ctx<'_>) -> Result<NodeOutput> {
|
||||
ctx.step("nixos-container create");
|
||||
async fn run_create(claim: &Claim) -> Result<NodeOutput> {
|
||||
crate::lifecycle::create_only(&claim.agent).await?;
|
||||
Ok(NodeOutput::default())
|
||||
}
|
||||
|
|
@ -350,12 +325,10 @@ async fn run_create(claim: &Claim, ctx: &Ctx<'_>) -> Result<NodeOutput> {
|
|||
async fn run_meta_lock(
|
||||
coord: &Arc<Coordinator>,
|
||||
claim: &Claim,
|
||||
ctx: &Ctx<'_>,
|
||||
sweep: bool,
|
||||
fanout: Option<Vec<String>>,
|
||||
) -> Result<NodeOutput> {
|
||||
if sweep {
|
||||
ctx.step("nix flake update hyperhive");
|
||||
if let Err(e) = crate::meta::lock_update_hyperhive().await {
|
||||
tracing::warn!(error = ?e, "startup sweep: meta lock_update_hyperhive failed");
|
||||
}
|
||||
|
|
@ -371,7 +344,6 @@ async fn run_meta_lock(
|
|||
return Ok(NodeOutput { append_subgraph });
|
||||
}
|
||||
let _progress = coord.meta_update_guard();
|
||||
ctx.step("nix flake update");
|
||||
crate::meta::lock_update(&claim.inputs).await?;
|
||||
// Lock file changed — meta-inputs panel re-renders.
|
||||
crate::dashboard::emit_meta_inputs_snapshot(coord);
|
||||
|
|
@ -424,7 +396,7 @@ async fn run_reconcile(coord: &Arc<Coordinator>, claim: &Claim) -> Result<NodeOu
|
|||
|
||||
/// Mechanical container start — the sub-step a `Reconcile` planner fans
|
||||
/// out when it observes `wanted = Up` and the container down.
|
||||
async fn run_start(coord: &Arc<Coordinator>, claim: &Claim, ctx: &Ctx<'_>) -> Result<NodeOutput> {
|
||||
async fn run_start(coord: &Arc<Coordinator>, claim: &Claim) -> Result<NodeOutput> {
|
||||
let name = &claim.agent;
|
||||
// Node-local transient only when the DAG holds none (the
|
||||
// boot-reconcile template); a rebuild/spawn/etc. DAG's lease-window
|
||||
|
|
@ -441,7 +413,6 @@ async fn run_start(coord: &Arc<Coordinator>, claim: &Claim, ctx: &Ctx<'_>) -> Re
|
|||
let hive = coord.hive_env();
|
||||
let paths = Coordinator::agent_paths(name, agent_dir);
|
||||
let token = crate::lifecycle::converge_start_preamble(name, &hive, &paths).await?;
|
||||
ctx.step("nixos-container start");
|
||||
crate::lifecycle::start_with_fallback(token).await?;
|
||||
// Bind the MCP listener immediately after starting the container.
|
||||
// The preamble created the runtime dir; the container is now coming
|
||||
|
|
@ -456,13 +427,12 @@ async fn run_start(coord: &Arc<Coordinator>, claim: &Claim, ctx: &Ctx<'_>) -> Re
|
|||
|
||||
/// Mechanical container stop — the sub-step a `Reconcile` planner fans
|
||||
/// out when it observes `wanted = Offline` and the container up.
|
||||
async fn run_stop(coord: &Arc<Coordinator>, claim: &Claim, ctx: &Ctx<'_>) -> Result<NodeOutput> {
|
||||
async fn run_stop(coord: &Arc<Coordinator>, claim: &Claim) -> Result<NodeOutput> {
|
||||
let name = &claim.agent;
|
||||
let _guard = claim
|
||||
.transient
|
||||
.is_none()
|
||||
.then(|| coord.transient_guard(name, crate::coordinator::TransientKind::Stopping));
|
||||
ctx.step("nixos-container stop");
|
||||
crate::lifecycle::kill(name).await?;
|
||||
coord.unregister_agent(name);
|
||||
coord.notify_manager(&hive_sh4re::HelperEvent::Killed {
|
||||
|
|
@ -474,11 +444,7 @@ async fn run_stop(coord: &Arc<Coordinator>, claim: &Claim, ctx: &Ctx<'_>) -> Res
|
|||
|
||||
/// Mechanical stop for the profile swap. Never *changes* `wanted`;
|
||||
/// noop when already stopped.
|
||||
async fn run_stop_for_update(
|
||||
coord: &Arc<Coordinator>,
|
||||
claim: &Claim,
|
||||
ctx: &Ctx<'_>,
|
||||
) -> Result<NodeOutput> {
|
||||
async fn run_stop_for_update(coord: &Arc<Coordinator>, claim: &Claim) -> Result<NodeOutput> {
|
||||
let name = &claim.agent;
|
||||
if crate::lifecycle::is_running(name).await {
|
||||
// Seed a missing agent_power row from the PRE-stop observation
|
||||
|
|
@ -488,7 +454,6 @@ async fn run_stop_for_update(
|
|||
if let Err(e) = coord.power.get_or_seed(name, true) {
|
||||
tracing::warn!(%name, error = ?e, "agent_power: pre-stop seed failed");
|
||||
}
|
||||
ctx.step("nixos-container stop");
|
||||
crate::lifecycle::kill(name).await?;
|
||||
coord.rescan_containers_and_emit().await;
|
||||
}
|
||||
|
|
@ -504,12 +469,10 @@ async fn run_stop_for_update(
|
|||
/// `GRACEFUL_STOP_TIMEOUT`. Safe because the harness tests the marker at
|
||||
/// the top of its loop — a paused agent has no turn in flight, so there
|
||||
/// is nothing to checkpoint.
|
||||
fn run_signal(coord: &Arc<Coordinator>, claim: &Claim, ctx: &Ctx<'_>) -> NodeOutput {
|
||||
fn run_signal(coord: &Arc<Coordinator>, claim: &Claim) -> NodeOutput {
|
||||
if hive_types::Ident::parse(&claim.agent).is_ok_and(|a| Coordinator::is_paused(&a)) {
|
||||
ctx.step("graceful stop: agent paused, nothing to drain");
|
||||
return NodeOutput::default();
|
||||
}
|
||||
ctx.step("graceful stop: signalling agent");
|
||||
coord.mark_graceful_stop(&claim.agent);
|
||||
coord.kick_agent(&claim.agent, "graceful stop requested");
|
||||
NodeOutput::default()
|
||||
|
|
@ -518,9 +481,8 @@ fn run_signal(coord: &Arc<Coordinator>, claim: &Claim, ctx: &Ctx<'_>) -> NodeOut
|
|||
/// Await the harness clearing the fence (`GracefulStopComplete`) or
|
||||
/// the timeout — either way the downstream `Reconcile` proceeds with
|
||||
/// the actual stop.
|
||||
async fn run_drain(coord: &Arc<Coordinator>, claim: &Claim, ctx: &Ctx<'_>) -> Result<NodeOutput> {
|
||||
async fn run_drain(coord: &Arc<Coordinator>, claim: &Claim) -> Result<NodeOutput> {
|
||||
let name = &claim.agent;
|
||||
ctx.step("graceful stop: draining");
|
||||
let deadline = std::time::Instant::now() + GRACEFUL_STOP_TIMEOUT;
|
||||
while coord.is_graceful_stop_pending(name) {
|
||||
if std::time::Instant::now() >= deadline {
|
||||
|
|
@ -549,18 +511,13 @@ async fn run_write_dropin(coord: &Arc<Coordinator>, claim: &Claim) -> Result<Nod
|
|||
/// Write + commit the perm file(s) (fused under `META_LOCK` so the
|
||||
/// working tree is never left dirty), then emit the P3RM1SS10NS-tab
|
||||
/// snapshots so the dashboard reflects the new assignment.
|
||||
async fn run_write_perm_file(
|
||||
coord: &Arc<Coordinator>,
|
||||
claim: &Claim,
|
||||
ctx: &Ctx<'_>,
|
||||
) -> Result<NodeOutput> {
|
||||
async fn run_write_perm_file(coord: &Arc<Coordinator>, claim: &Claim) -> Result<NodeOutput> {
|
||||
use super::model::PermPayload;
|
||||
let name = &claim.agent;
|
||||
// The perm file payload rides the node itself (the only consumer).
|
||||
let NodeKind::WritePermFile { payload, .. } = &claim.kind else {
|
||||
anyhow::bail!("run_write_perm_file on a non-WritePermFile node");
|
||||
};
|
||||
ctx.step("writing + committing perm file");
|
||||
// Runs under the deploy window (`NodeKind::needs_meta_window`): a
|
||||
// perm commit landing inside another node's staged prepare→finalize
|
||||
// window would sweep the staged deploy lock into its commit (the
|
||||
|
|
@ -622,7 +579,7 @@ fn run_deploy_window(claim: &Claim) -> Result<NodeOutput> {
|
|||
/// failure here cancel-cascades the rest of the subtree with the forge and the
|
||||
/// applied repo exactly as they were.
|
||||
async fn run_merge_verify(coord: &Arc<Coordinator>, claim: &Claim) -> Result<NodeOutput> {
|
||||
crate::actions::run_deploy_merge_verify(coord, Some(claim.dag_id), deploy_approval_id(claim)?)
|
||||
crate::actions::run_deploy_merge_verify(coord, deploy_approval_id(claim)?)
|
||||
.await
|
||||
.map(|()| NodeOutput::default())
|
||||
}
|
||||
|
|
@ -637,7 +594,7 @@ async fn run_merge_verify(coord: &Arc<Coordinator>, claim: &Claim) -> Result<Nod
|
|||
/// ancestor already holding it. On failure nothing is appended and the tail
|
||||
/// compensates, exactly as before.
|
||||
async fn run_deploy_apply(coord: &Arc<Coordinator>, claim: &Claim) -> Result<NodeOutput> {
|
||||
crate::actions::run_deploy_apply(coord, Some(claim.dag_id), deploy_approval_id(claim)?).await?;
|
||||
crate::actions::run_deploy_apply(coord, deploy_approval_id(claim)?).await?;
|
||||
Ok(NodeOutput {
|
||||
append_subgraph: vec![super::templates::deploy_rebuild_nodes(claim.kind.agent())],
|
||||
})
|
||||
|
|
@ -647,7 +604,7 @@ async fn run_deploy_apply(coord: &Arc<Coordinator>, claim: &Claim) -> Result<Nod
|
|||
/// come up clean: drop the rollback ref, plant the `deployed/<id>` tag, commit
|
||||
/// the staged lock.
|
||||
async fn run_finalize_deploy(coord: &Arc<Coordinator>, claim: &Claim) -> Result<NodeOutput> {
|
||||
crate::actions::run_finalize_deploy(coord, Some(claim.dag_id), deploy_approval_id(claim)?)
|
||||
crate::actions::run_finalize_deploy(coord, deploy_approval_id(claim)?)
|
||||
.await
|
||||
.map(|()| NodeOutput::default())
|
||||
}
|
||||
|
|
|
|||
Loading…
Reference in a new issue