hyperhive/hive-c0re/src/migrate.rs
müde 78f21ccc5d meta: serialize all ops behind a tokio mutex + clear stale lock at startup
journal showed three concurrent rebuilds racing on the meta
repo's .git/index.lock — auto_update::run kicks off parallel
tokio::spawn for every stale agent, each rebuild eventually
calls into meta::sync_agents / lock_update_for_rebuild which
do git add + commit, git isn't safe across concurrent processes
on the same .git/, and one of the failing-mid-write children
left index.lock behind. subsequent ops blocked until somebody
rm'd it manually.

fix: static META_LOCK (tokio::sync::Mutex<()>) acquired at the
top of every public meta function. concurrent rebuilds take
turns on meta ops; the actual nix build (nixos-container update)
releases the lock first and runs without it, so parallel agent
builds still parallelize on nix-daemon's own concurrency model.

migrate::run additionally clears /var/lib/hyperhive/meta/.git/
index.lock on startup if it exists — we just booted, nothing
of ours is holding it. covers the 'previous crash left a stale
lock' case the user just hit so the daemon recovers without
manual intervention.
2026-05-16 02:44:39 +02:00

213 lines
7.5 KiB
Rust

//! Startup auto-migration from the pre-meta layout. Runs before
//! `auto_update::run` and consists of four phases, each idempotent:
//!
//! 1. Per-agent applied repo: rewrite `flake.nix` to the module-only
//! boilerplate if it isn't already, commit, relocate `deployed/0`
//! to HEAD so `setup_applied`'s existence check passes.
//! 2. Per-agent proposed repo: ensure the `applied` git remote
//! points at `/applied/<n>/.git` (re-runs `setup_proposed`'s
//! `ensure_applied_remote` indirectly via a host-side git call).
//! 3. Meta repo: `meta::sync_agents` over the current agent list —
//! init the repo on first call, rerender + relock if anything
//! drifted.
//! 4. Container repoint: for every existing container, run
//! `nixos-container update <c> --flake meta#<name>` so it
//! activates against the meta flake. Guarded by a marker file
//! so the (expensive) phase 4 only runs once across hive-c0re
//! restarts.
//!
//! Env kill-switch: `HIVE_SKIP_META_MIGRATION=1` skips the whole
//! migration. Use when smoke-testing one agent at a time by hand.
use std::path::{Path, PathBuf};
use std::sync::Arc;
use anyhow::{Context, Result};
use tokio::process::Command;
use crate::coordinator::Coordinator;
use crate::lifecycle::{self, AGENT_PREFIX, MANAGER_NAME};
use crate::meta;
const KILL_SWITCH: &str = "HIVE_SKIP_META_MIGRATION";
/// Marker for phase 4. Once present, container repoint is skipped on
/// future restarts.
fn repoint_marker() -> PathBuf {
PathBuf::from("/var/lib/hyperhive/.meta-migration-done")
}
/// Substring that identifies the *current* agent flake boilerplate.
/// Bumped whenever the template changes so the startup migration
/// re-renders existing agents onto the new shape. Today the marker
/// is the `flakeInputs` module-arg forwarding line — older templates
/// (raw `import ./agent.nix`) get rewritten on next hive-c0re start.
const MODULE_FLAKE_MARKER: &str = "_module.args.flakeInputs";
pub async fn run(coord: &Arc<Coordinator>) -> Result<()> {
if std::env::var(KILL_SWITCH).is_ok() {
tracing::info!("migration: {KILL_SWITCH} set — skipping");
return Ok(());
}
// Stale meta index lock: a previous hive-c0re crash mid-`git add`
// can leave `.git/index.lock` behind, which blocks every
// subsequent meta op until somebody `rm`s it manually. We just
// booted so nothing of ours is holding it; safe to clear.
let meta_lock = std::path::PathBuf::from("/var/lib/hyperhive/meta/.git/index.lock");
if meta_lock.exists() {
match std::fs::remove_file(&meta_lock) {
Ok(()) => tracing::warn!("cleared stale meta/.git/index.lock"),
Err(e) => tracing::warn!(error = ?e, "clear stale meta lock failed"),
}
}
let names = enumerate_agents().await;
tracing::info!(count = names.len(), "migration: scanning");
// Phase 1 + 2: per-agent applied + proposed.
for name in &names {
if let Err(e) = migrate_applied_repo(name).await {
tracing::warn!(%name, error = ?e, "migration: applied repo rewrite failed");
}
if let Err(e) = lifecycle::setup_proposed(&Coordinator::agent_proposed_dir(name), name)
.await
{
tracing::warn!(%name, error = ?e, "migration: setup_proposed failed");
}
}
// Phase 3: meta repo.
let agents = lifecycle::agents_for_meta_listing().await.unwrap_or_default();
if let Err(e) =
meta::sync_agents(
&coord.hyperhive_flake,
coord.dashboard_port,
&coord.operator_pronouns,
&agents,
)
.await
{
tracing::warn!(error = ?e, "migration: meta sync_agents failed");
}
// Phase 4: container repoint, guarded by marker.
if repoint_marker().exists() {
tracing::debug!("migration: phase 4 marker present, skipping repoint");
return Ok(());
}
let mut all_ok = true;
for name in &names {
// Mark Rebuilding so the crash watcher skips this container
// during the brief stop+start window the nixos-container
// update activation triggers. Without this, crash_watch
// would fire ContainerCrash for every agent here and the
// manager would spuriously try to recover them.
coord.set_transient(name, crate::coordinator::TransientKind::Rebuilding);
let result = repoint_container(name).await;
coord.clear_transient(name);
if let Err(e) = result {
tracing::warn!(%name, error = ?e, "migration: container repoint failed");
all_ok = false;
}
}
if all_ok && !names.is_empty()
&& let Err(e) = std::fs::write(repoint_marker(), b"done\n")
{
tracing::warn!(error = ?e, "migration: write repoint marker failed");
}
Ok(())
}
async fn enumerate_agents() -> Vec<String> {
let containers = lifecycle::list().await.unwrap_or_default();
containers
.into_iter()
.filter_map(|c| {
if c == MANAGER_NAME {
Some(MANAGER_NAME.to_owned())
} else {
c.strip_prefix(AGENT_PREFIX).map(str::to_owned)
}
})
.collect()
}
async fn migrate_applied_repo(name: &str) -> Result<()> {
let dir = Coordinator::agent_applied_dir(name);
if !dir.join(".git").exists() {
return Ok(());
}
let flake_path = dir.join("flake.nix");
let cur = std::fs::read_to_string(&flake_path).unwrap_or_default();
if cur.contains(MODULE_FLAKE_MARKER) {
return Ok(());
}
let want = lifecycle::initial_flake_nix();
std::fs::write(&flake_path, want)
.with_context(|| format!("write {}", flake_path.display()))?;
raw_git(
&dir,
&[
"-c",
"user.name=hive-c0re",
"-c",
"user.email=hive-c0re@hyperhive",
"add",
"flake.nix",
],
)
.await?;
raw_git(
&dir,
&[
"-c",
"user.name=hive-c0re",
"-c",
"user.email=hive-c0re@hyperhive",
"commit",
"-m",
"migration: module-only flake",
],
)
.await?;
// Relocate deployed/0 to the migration commit so
// setup_applied's existence check passes.
raw_git(&dir, &["tag", "-f", "deployed/0", "HEAD"]).await?;
tracing::info!(%name, "migration: applied repo migrated to module-only flake");
Ok(())
}
async fn repoint_container(name: &str) -> Result<()> {
let container = lifecycle::container_name(name);
let flake_ref = format!("{}#{name}", meta::meta_dir().display());
let out = Command::new("nixos-container")
.args(["update", &container, "--flake", &flake_ref])
.output()
.await
.with_context(|| format!("nixos-container update {container}"))?;
if !out.status.success() {
anyhow::bail!(
"nixos-container update {container} exited {}: {}",
out.status,
String::from_utf8_lossy(&out.stderr).trim()
);
}
tracing::info!(%name, %container, "migration: container repointed at meta");
Ok(())
}
async fn raw_git(dir: &Path, args: &[&str]) -> Result<()> {
let out = lifecycle::git_command()
.current_dir(dir)
.args(args)
.output()
.await
.with_context(|| format!("git {} in {}", args.join(" "), dir.display()))?;
if !out.status.success() {
anyhow::bail!(
"git {} failed: {}",
args.join(" "),
String::from_utf8_lossy(&out.stderr).trim()
);
}
Ok(())
}