hyperhive/hive-c0re/src/server.rs

239 lines
9.2 KiB
Rust

use std::path::Path;
use std::sync::Arc;
use anyhow::{Context, Result};
use hive_sh4re::{HostRequest, HostResponse};
use tokio::io::{AsyncBufReadExt, AsyncWriteExt, BufReader};
use tokio::net::{UnixListener, UnixStream};
use crate::actions;
use crate::coordinator::Coordinator;
use crate::lifecycle;
pub async fn serve(socket: &Path, coord: Arc<Coordinator>) -> Result<()> {
// Prefer a socket passed by systemd socket-activation (LISTEN_FDS).
// When running under a `.socket` unit, systemd has already created,
// bound, and chmod-ed the socket for us — we just accept on it.
// Fall back to the traditional bind path when not socket-activated
// (direct invocation, dev, tests).
let listener = {
let mut listenfd = listenfd::ListenFd::from_env();
if let Some(std_listener) = listenfd
.take_unix_listener(0)
.context("take socket-activated unix listener")?
{
std_listener.set_nonblocking(true)?;
UnixListener::from_std(std_listener)
.context("convert socket-activated listener to tokio")?
} else {
// Standalone: create parent dir, remove any stale socket, bind.
if let Some(parent) = socket.parent() {
std::fs::create_dir_all(parent)
.with_context(|| format!("create socket parent {}", parent.display()))?;
}
if socket.exists() {
std::fs::remove_file(socket).context("remove stale socket")?;
}
UnixListener::bind(socket)
.with_context(|| format!("bind admin socket {}", socket.display()))?
}
};
tracing::info!(socket = %socket.display(), hyperhive_flake = %coord.hyperhive_flake, "hive-c0re admin listening");
loop {
let (stream, _) = listener.accept().await.context("accept connection")?;
let coord = coord.clone();
tokio::spawn(async move {
if let Err(e) = handle(stream, coord).await {
tracing::warn!(error = ?e, "connection failed");
}
});
}
}
async fn handle(stream: UnixStream, coord: Arc<Coordinator>) -> Result<()> {
let (read, mut write) = stream.into_split();
let mut reader = BufReader::new(read);
let mut line = String::new();
loop {
line.clear();
let n = reader.read_line(&mut line).await?;
if n == 0 {
return Ok(());
}
let resp = match serde_json::from_str::<HostRequest>(line.trim()) {
Ok(req) => dispatch(&req, coord.clone()).await,
Err(e) => HostResponse::error(format!("parse error: {e}")),
};
let mut payload = serde_json::to_string(&resp)?;
payload.push('\n');
write.write_all(payload.as_bytes()).await?;
write.flush().await?;
}
}
async fn dispatch(req: &HostRequest, coord: Arc<Coordinator>) -> HostResponse {
let result: anyhow::Result<HostResponse> = async {
Ok(match req {
HostRequest::Spawn { name } => handle_spawn(&coord, name).await?,
HostRequest::RequestSpawn { name } => {
tracing::info!(%name, "request_spawn");
let id =
coord
.approvals
.submit_kind(name, hive_sh4re::ApprovalKind::Spawn, "", None)?;
tracing::info!(%id, %name, "spawn approval queued");
HostResponse::success()
}
HostRequest::Kill { name } => handle_kill(&coord, name).await?,
HostRequest::Restart { name } => {
tracing::info!(%name, "restart");
lifecycle::restart(name).await?;
HostResponse::success()
}
HostRequest::RestartAll => handle_restart_all().await?,
HostRequest::Destroy { name, purge } => {
actions::destroy(&coord, name, *purge).await?;
HostResponse::success()
}
HostRequest::Rebuild { name } => handle_rebuild(&coord, name).await?,
HostRequest::List => HostResponse::list(lifecycle::list().await?),
HostRequest::Pending => HostResponse::pending(coord.approvals.pending()?),
HostRequest::Approve { id } => {
actions::approve(coord.clone(), *id).await?;
HostResponse::success()
}
HostRequest::Deny { id } => {
actions::deny(&coord, *id, None).await?;
HostResponse::success()
}
HostRequest::SetParent { child, new_parent } => {
tracing::info!(%child, ?new_parent, "set_parent");
// `reparent_with_notify` wraps `topology::set_parent`
// with the three notification messages + the
// ContainerView rescan. Idempotent same-parent calls
// skip both the messages and the disk write per the
// topology fast-path.
coord
.reparent_with_notify(child, new_parent.as_deref())
.await
.map_err(anyhow::Error::msg)?;
HostResponse::success()
}
})
}
.await;
match result {
Ok(r) => r,
Err(e) => HostResponse::error(format!("{e:#}")),
}
}
/// Create + start the container for `name`, rolling back socket
/// registration and notifying the manager on failure.
async fn handle_spawn(coord: &Arc<Coordinator>, name: &str) -> Result<HostResponse> {
tracing::info!(%name, "spawn");
let agent_dir = coord.ensure_runtime(name)?;
let hive = coord.hive_env();
let paths = Coordinator::agent_paths(name, agent_dir);
match lifecycle::spawn(name, &hive, &paths).await {
Ok(()) => {
coord.notify_manager(&hive_sh4re::HelperEvent::Spawned {
agent: name.to_owned(),
ok: true,
note: None,
sha: None,
});
}
Err(e) => {
// Roll back socket registration if container creation failed.
coord.unregister_agent(name);
coord.notify_manager(&hive_sh4re::HelperEvent::Spawned {
agent: name.to_owned(),
ok: false,
note: Some(format!("{e:#}")),
sha: None,
});
return Err(e);
}
}
Ok(HostResponse::success())
}
/// Kill `name`'s container, unregister its socket, notify the manager.
async fn handle_kill(coord: &Arc<Coordinator>, name: &str) -> Result<HostResponse> {
tracing::info!(%name, "kill");
lifecycle::kill(name).await?;
coord.unregister_agent(name);
coord.notify_manager(&hive_sh4re::HelperEvent::Killed {
agent: name.to_owned(),
});
Ok(HostResponse::success())
}
/// Restart every container, aggregating per-agent failures into one
/// response rather than aborting on the first error.
async fn handle_restart_all() -> Result<HostResponse> {
tracing::info!("restart-all");
let agents = lifecycle::list().await?;
let mut ok_agents: Vec<String> = Vec::new();
let mut errors: Vec<String> = Vec::new();
for agent in &agents {
if let Err(e) = lifecycle::restart(agent).await {
tracing::warn!(%agent, error = ?e, "restart-all: failed to restart agent");
errors.push(format!("{agent}: {e:#}"));
} else {
ok_agents.push(agent.clone());
}
}
if errors.is_empty() {
Ok(HostResponse::list(ok_agents))
} else {
Ok(HostResponse {
ok: false,
error: Some(errors.join("; ")),
agents: Some(ok_agents),
approvals: None,
})
}
}
/// Rebuild `name`'s container, notifying the manager of the outcome
/// (success or failure) and kicking the agent's next turn on success.
async fn handle_rebuild(coord: &Arc<Coordinator>, name: &str) -> Result<HostResponse> {
tracing::info!(%name, "rebuild");
let agent_dir = coord.ensure_runtime(name)?;
let hive = coord.hive_env();
let paths = Coordinator::agent_paths(name, agent_dir);
let result = lifecycle::rebuild(name, &hive, &paths, &|_| (), &|_| ()).await;
// Mirror auto_update::rebuild_agent — the manager wants to know
// about every rebuild attempt regardless of which surface triggered
// it, especially failures (build error → manager can adjust the
// agent's agent.nix). Without this the admin-socket CLI was a
// notify-gap.
match &result {
Ok(()) => {
coord.notify_manager(&hive_sh4re::HelperEvent::Rebuilt {
agent: name.to_owned(),
ok: true,
note: None,
sha: None,
tag: None,
});
// Wake the agent's next turn with the "you were rebuilt"
// hint. Same pattern as auto_update::rebuild_agent and the
// dashboard rebuild path — this is the CLI's equivalent.
coord.kick_agent(name, "container rebuilt");
}
Err(e) => coord.notify_manager(&hive_sh4re::HelperEvent::Rebuilt {
agent: name.to_owned(),
ok: false,
note: Some(format!("{e:#}")),
sha: None,
tag: None,
}),
}
result?;
Ok(HostResponse::success())
}