From c3e3753dd056446a8cfcdf728bc1255cbf3926f5 Mon Sep 17 00:00:00 2001 From: damocles Date: Fri, 28 Aug 2026 17:51:32 +0200 Subject: [PATCH] hive-priv: stream the toplevel build live, and build it for create too --- hive-priv/src/main.rs | 217 +++++++++++++++++++++++++++++------------- 1 file changed, 150 insertions(+), 67 deletions(-) diff --git a/hive-priv/src/main.rs b/hive-priv/src/main.rs index 96430c29..0c5b9315 100644 --- a/hive-priv/src/main.rs +++ b/hive-priv/src/main.rs @@ -623,19 +623,22 @@ async fn exec( } /// Shared body for `CreateContainer` / `UpdateContainer`: validate the -/// name, build the `nixos-container …` argv, and run it (streaming -/// line events to `writer` when `stream` is set). +/// name, build the toplevel ourselves, and run +/// `nixos-container … --system-path ` (streaming line +/// events to `writer` when `stream` is set). /// -/// `update` builds the toplevel itself first and passes `--system-path` -/// instead of `--flake` — see [`nix_build_toplevel`] for why. `create` -/// keeps the plain `--flake` form: `nixos-container` takes an exclusive -/// `flock` for the whole `create` action, and once `update` no longer -/// calls `buildFlake()` (below), concurrent `create`s are the only -/// remaining writers of the shared `.tmp` out-link — so they're mutually -/// excluded. ⚠️ That holds only while nothing else calls `buildFlake()` -/// unlocked: pre-this-PR, `create`'s own lock bought it nothing against a -/// concurrent *unlocked* `update` clobbering the same `.tmp` — the lock -/// alone was never what made `create` safe, this fix is. +/// **Both verbs build explicitly now — not just `update`.** The first cut +/// of this fix only rewrote `update`, reasoning that `create` was already +/// safe: it wraps its whole action in an exclusive `flock` before calling +/// `nixos-container`'s own `buildFlake()`, and once `update` stopped +/// writing to `buildFlake()`'s shared `.tmp` out-link, concurrent +/// `create`s were the only remaining writers — mutually excluded by that +/// lock. True, but it leaves `create`'s safety resting on an internal +/// implementation detail of a script we don't own (its current locking +/// behavior, which could change upstream without notice) instead of on +/// something we control. Building here for both verbs removes `buildFlake()` +/// from the picture entirely — there's no shared `.tmp` left to race on, +/// so there's nothing left to reason about staying in sync with. async fn container_flake_action( verb: &str, name: &str, @@ -643,22 +646,20 @@ async fn container_flake_action( writer: &mut OwnedWriteHalf, ) -> Result<(String, String)> { validate_container_name(name)?; - if verb == "update" { - let toplevel = nix_build_toplevel(name).await?; - let args = [ - verb, - &container_system_name(name), - "--system-path", - &toplevel, - ]; - return if stream { - container_run_streaming(&args, writer).await - } else { - container_run(&args).await - }; - } - let flake_ref = agent_flake_ref(name); - let args = [verb, &container_system_name(name), "--flake", &flake_ref]; + // The build is the multi-minute phase of this operation — give it the + // same live-line treatment `container_run_streaming` gives + // `nixos-container` itself when the caller asked for it. Without + // this, moving the build out of the streamed `nixos-container` call + // (which is the whole point of this fix) would silently regress every + // UI that shows build progress: nothing until the longest phase + // finishes, then everything at once. + let toplevel = nix_build_toplevel(name, stream.then_some(&mut *writer)).await?; + let args = [ + verb, + &container_system_name(name), + "--system-path", + &toplevel, + ]; if stream { container_run_streaming(&args, writer).await } else { @@ -677,31 +678,57 @@ fn toplevel_attr(name: &str) -> String { /// Build `nixosConfigurations..config.system.build.toplevel` and /// return the resulting store path. /// -/// **Why hive-priv builds this itself instead of letting `nixos-container -/// update` do it**: `nixos-container`'s own `buildFlake()` (invoked -/// whenever `--system-path` isn't passed) builds to a *hardcoded relative -/// path* — `$systemPath` is only ever assigned from the CLI flag or from -/// its own build result, so with no flag it stays `undef` and -/// `"$systemPath.tmp"` interpolates to the bare string `.tmp` in -/// whatever the caller's cwd is. `buildFlake()` itself takes no lock at -/// all — `create` wraps its *whole action* in an exclusive `flock` before -/// calling `buildFlake()`, but `update` calls it with no lock, so that -/// `create`-side lock never protected against a concurrent `update` -/// clobbering the same `.tmp`. hive-priv never sets a per-call cwd, so two -/// concurrent `update`s (this hive runs -/// `services.hyperhive.c0re.buildSlots` > 1) share that one `.tmp`: one's -/// `readlink(".tmp")` can resolve to the *other's* build output, handing -/// an agent's container the wrong agent's closure — the "agent container +/// **Why hive-priv builds this itself instead of letting `nixos-container` +/// do it**: `nixos-container`'s own `buildFlake()` (invoked whenever +/// `--system-path` isn't passed) builds to a *hardcoded relative path* — +/// `$systemPath` is only ever assigned from the CLI flag or from its own +/// build result, so with no flag it stays `undef` and `"$systemPath.tmp"` +/// interpolates to the bare string `.tmp` in whatever the caller's cwd +/// is. `buildFlake()` itself takes no lock at all: `create` wraps its +/// *whole action* in an exclusive `flock` before calling it, but `update` +/// used to call it with no lock at all, so that `create`-side lock never +/// protected against a concurrent `update` clobbering the same `.tmp`. +/// hive-priv never sets a per-call cwd, so with +/// `services.hyperhive.c0re.buildSlots` > 1, two concurrent calls (any mix +/// of `create`/`update`) could share that one `.tmp`: one's +/// `readlink(".tmp")` resolving to the *other's* build output, handing an +/// agent's container the wrong agent's closure — the "agent container /// gets closure of other agent" mystery bug. /// /// Building the toplevel here and passing the resolved store path via -/// `--system-path` means `buildFlake()` — and its shared `.tmp` — never -/// runs at all. `--no-link` avoids a competing out-link race of our own; -/// we only need the store path, not a GC root (the store path is safe -/// from collection for as long as it takes `nixos-container update` to -/// register it against the container's own profile, same window every -/// other consumer of a `--print-out-paths` result already relies on). -async fn nix_build_toplevel(name: &str) -> Result { +/// `--system-path` for *every* call means `buildFlake()` never runs at +/// all, for either verb — no shared `.tmp` left to race on, no locking +/// invariant of a script we don't own to keep track of. `--no-link` +/// avoids a competing out-link race of our own; we only need the store +/// path, not a GC root (the store path is safe from collection for as +/// long as it takes `nixos-container` to register it against the +/// container's own profile, same window every other consumer of a +/// `--print-out-paths` result already relies on). +/// +/// **Forwards stderr live, captures stdout silently — deliberately not +/// symmetric.** This build is the multi-minute phase of a `create`/ +/// `update`, and it used to run *inside* `nixos-container`'s own +/// `--flake` invocation, which streams every line to `writer` in real +/// time. Buffering it here (`Command::output()`, as this function first +/// shipped) regressed that: nothing on the wire — dashboard or +/// `journalctl -f` alike — until the whole build finishes, then +/// everything at once. So both pipes are drained concurrently (see the +/// in-body comments for why *both*, and why *concurrently*), but only +/// stderr — where nix's own progress goes — is forwarded to `writer` and +/// journald as it arrives, matching [`container_run_streaming`]'s shape. +/// stdout is different: `--print-out-paths` writes *only* the final store +/// path there, once, at the end — forwarding it the same way would risk +/// interleaving a progress line into the value this function hands back +/// as `--system-path`, trading a closure-mixup bug for a corrupted- +/// argument one. So stdout lines are accumulated silently and only +/// consulted after the exit status is known to be success. +/// +/// `writer` is `None` for the non-streaming call shape (`stream: false`); +/// stderr still logs to journald either way, just without the +/// `PrivEvent::Line` forwarding. +async fn nix_build_toplevel(name: &str, mut writer: Option<&mut OwnedWriteHalf>) -> Result { + use tokio::io::AsyncBufReadExt as _; + let attr = toplevel_attr(name); let args = [ "--extra-experimental-features", @@ -711,24 +738,85 @@ async fn nix_build_toplevel(name: &str) -> Result { "--print-out-paths", &attr, ]; - let out = Command::new("nix") + let mut child = Command::new("nix") .args(args) - .output() - .await + .stdout(std::process::Stdio::piped()) + .stderr(std::process::Stdio::piped()) + .spawn() .with_context(|| format!("invoke nix build {attr}"))?; - let stdout = String::from_utf8_lossy(&out.stdout).into_owned(); - let stderr = String::from_utf8_lossy(&out.stderr).into_owned(); - for line in stderr.lines() { - tracing::warn!(target: "nix-build-toplevel", "{line}"); + + let stdout = child.stdout.take().expect("stdout piped"); + let stderr = child.stderr.take().expect("stderr piped"); + let mut stdout_lines = BufReader::new(stdout).lines(); + let mut stderr_lines = BufReader::new(stderr).lines(); + + let mut stdout_buf = String::new(); + let mut stderr_buf = String::new(); + + // ⚠️ Both pipes are drained concurrently even though only one is + // streamed: reading stderr alone would let stdout fill its pipe + // buffer and deadlock the child on a build with enough stdout output + // to fill it. + // + // ⚠️ Each stream's EOF is tracked separately rather than breaking on + // the first `None`: `next_line()` on a closed stream returns + // `Ok(None)` immediately and forever, so a loop that keeps polling a + // finished stream spins hot until the other one ends too. + let mut stdout_done = false; + let mut stderr_done = false; + while !(stdout_done && stderr_done) { + tokio::select! { + line = stdout_lines.next_line(), if !stdout_done => { + match line { + // Captured, never streamed — this is the store path. + Ok(Some(l)) => { + stdout_buf.push_str(&l); + stdout_buf.push('\n'); + } + Ok(None) => stdout_done = true, + Err(e) => { + tracing::warn!(error = %e, "nix build stdout read error"); + stdout_done = true; + } + } + } + line = stderr_lines.next_line(), if !stderr_done => { + match line { + // Streamed as it arrives — the progress the dashboard + // and `journalctl -f` were missing. + Ok(Some(l)) => { + tracing::warn!(target: "nix-build-toplevel", "{l}"); + if let Some(w) = writer.as_deref_mut() { + write_line_event(w, PrivStream::Stderr, &l).await; + } + if !stderr_buf.is_empty() { + stderr_buf.push('\n'); + } + stderr_buf.push_str(&l); + } + Ok(None) => stderr_done = true, + Err(e) => { + tracing::warn!(error = %e, "nix build stderr read error"); + stderr_done = true; + } + } + } + } } - if !out.status.success() { + + // ⚠️ Success is decided by the exit status, not by "we parsed a + // path" — a build can print to stdout and still fail. + let status = child + .wait() + .await + .with_context(|| format!("wait nix build {attr}"))?; + if !status.success() { bail!( - "nix build {attr} failed ({}): {}", - out.status, - stderr.trim() + "nix build {attr} failed ({status}): {}", + stderr_buf.lines().last().unwrap_or("").trim() ); } - let path = stdout.trim(); + let path = stdout_buf.trim(); if path.is_empty() { bail!("nix build {attr} produced no output path"); } @@ -2486,11 +2574,6 @@ fn validate_name_chars(name: &str) -> Result<()> { Ok(()) } -/// Derive the meta-flake ref for an agent by name. -fn agent_flake_ref(name: &str) -> String { - format!("{META_DIR}#{name}") -} - /// Validate a bind-mount path: must be absolute, non-empty, and contain /// no newlines, null bytes, or double-quotes (which would break the /// `EXTRA_NSPAWN_FLAGS="..."` conf line format).