vinzenz/hyperhive
vinzenz/hyperhive
Watch
0
0
Fork
You've already forked hyperhive
 0
Code Activity

retry every failed meta build each round, a timeout included, and drop the attempt count

Browse source
This commit is contained in:
atlas 2026-10-26 18:39:09 +01:00
commit 59456c3c58
1 changed files with 251 additions and 435 deletions
Download patch file Download diff file Expand all files Collapse all files

161
swarm-controller/src/meta_build.rs
View file

@ -8,17 +8,17 @@
//! key itself: the builder holds no grant on the bucket. A `Built` reply and
//! nothing else writes, so a red build leaves the previous record.
//!
//! The node ends one of three ways. `Done` is a green build. Every `Failed` skips
//! the deploy behind it, and the Jobs page shows why. What decides whether the
//! timer builds again (`jobq::queue_meta_update`) is the error text:
//! - No verdict (no builder, a timeout, a forge error, no `internal/meta` head,
//! a missing read grant, a failed closure write): [`RETRY_PREFIX`]. The next
//! build has the same `attempt`.
//! - `nix` exited with an error on the first attempt: [`FIRST_FAILURE_PREFIX`]
//! and `nix`'s tail. The next build is `attempt + 1`, which catches a fetch
//! hiccup inside `nix` without reading its output.
//! - `nix` exited with an error again: `nix`'s tail alone. That is a red build:
//! the deploy stays held until a config merge, and nothing retries it.
//! The node ends one of two ways. `Done` is a green build. Every `Failed` skips
//! the deploy behind it, and the Jobs page shows why:
//! - `nix` failed, its timeout included: `Failed` with `nix`'s tail, or `nix
//! timed out`. The deploy stays held and counts as a failed build.
//! - The build got no verdict (no builder, a forge error, no `internal/meta`
//! head, a missing read grant, a failed closure write): `Failed` starting with
//! [`NO_VERDICT_PREFIX`], which the held-deploys gauge reads to label the
//! reason.
//!
//! Both are built again on every round of the meta timer
//! (`jobq::queue_meta_update`) until a build succeeds.
use std::fmt::Display;
use std::future::Future;
@ -32,32 +32,16 @@ use crate::agent_renewal::unix_now;
use crate::forge::{self, objects::SHARED_ORG};
use crate::meta_flake::{META_REPO, MetaForge};
/// What a `Failed` outcome that is not a verdict on the config starts with.
pub(crate) const RETRY_PREFIX: &str = "not built, will be retried: ";
/// What a `Failed` outcome starts with when the build got no verdict.
pub(crate) const NO_VERDICT_PREFIX: &str = "no verdict: ";
/// What the `Failed` outcome of a first `nix` error starts with.
pub(crate) const FIRST_FAILURE_PREFIX: &str = "build failed, will be built once more: ";
/// How many times `nix` may exit with an error before the build is red.
const NIX_ATTEMPTS: u32 = 2;
/// Whether a `Failed` node's `error` asks for another build.
pub(crate) fn is_retried(error: &str) -> bool {
error.starts_with(RETRY_PREFIX) || error.starts_with(FIRST_FAILURE_PREFIX)
/// Whether a `Failed` node's `error` says the build got no verdict.
pub(crate) fn is_no_verdict(error: &str) -> bool {
error.starts_with(NO_VERDICT_PREFIX)
}
/// The `attempt` of the build that follows a `Failed` build of `attempt`
/// with `error`: one more after an error `nix` gave, the same after none.
pub(crate) fn next_attempt(attempt: u32, error: &str) -> u32 {
if error.starts_with(FIRST_FAILURE_PREFIX) {
attempt + 1
} else {
attempt
}
}
fn not_built(why: impl Display) -> Outcome {
Outcome::Failed(format!("{RETRY_PREFIX}{why}"))
fn no_verdict(why: impl Display) -> Outcome {
Outcome::Failed(format!("{NO_VERDICT_PREFIX}{why}"))
}
/// Where `internal/meta` is read and shared with the builder: the forge in
@ -136,47 +120,41 @@ impl MetaBuilds for async_nats::Client {
}
/// Build `agent` from `internal/meta`'s head and record the closure.
/// `attempt` is how many times `nix` has already exited with an error for this
/// deploy.
pub(crate) async fn run(
head: Option<&impl MetaRepo>,
queue: Option<&impl MetaBuilds>,
agent: String,
attempt: u32,
) -> Outcome {
let Some(head) = head else {
return not_built(
return no_verdict(
"no forge access here (SWARM_CONTROLLER_FORGE_URL unset, or its token not in the \
swarm secret store), so internal/meta's head cannot be read",
);
};
let Some(queue) = queue else {
return not_built("no swarm queue is configured on this host, so no build can be sent");
return no_verdict("no swarm queue is configured on this host, so no build can be sent");
};
// The repo is private, and the grant is otherwise made only by a meta update.
if let Err(e) = head.grant_builder_read().await {
return not_built(format!(
return no_verdict(format!(
"the builder's read on internal/meta could not be granted: {e:#}"
));
}
let meta_rev = match head.head().await {
Ok(Some(rev)) => rev,
Ok(None) => return not_built("the swarm has not published internal/meta yet"),
Err(e) => return not_built(format!("{e:#}")),
Ok(None) => return no_verdict("the swarm has not published internal/meta yet"),
Err(e) => return no_verdict(format!("{e:#}")),
};
let request = match serde_json::to_vec(&BuildFromMeta {
agent: agent.clone(),
meta_rev: meta_rev.clone(),
}) {
Ok(request) => request,
Err(e) => return not_built(format!("encoding the build request: {e}")),
Err(e) => return no_verdict(format!("encoding the build request: {e}")),
};
match queue.build(request).await {
Err(why) => not_built(why),
Ok(FromMetaReply::Unavailable { reason }) => not_built(reason),
Ok(FromMetaReply::Failed { error_tail }) if attempt + 1 < NIX_ATTEMPTS => {
Outcome::Failed(format!("{FIRST_FAILURE_PREFIX}{error_tail}"))
}
Err(why) => no_verdict(why),
Ok(FromMetaReply::Unavailable { reason }) => no_verdict(reason),
Ok(FromMetaReply::Failed { error_tail }) => Outcome::Failed(error_tail),
Ok(FromMetaReply::Built { out_path, system }) => {
let closure = AgentClosure {
@ -187,7 +165,7 @@ pub(crate) async fn run(
};
match queue.record(&agent, &closure).await {
Ok(()) => Outcome::Done,
Err(e) => not_built(format!("built {out_path}, but recording it failed: {e:#}")),
Err(e) => no_verdict(format!("built {out_path}, but recording it failed: {e:#}")),
}
}
}
@ -278,11 +256,7 @@ mod tests {
}
async fn run_with(head: &FakeHead, queue: &FakeQueue) -> Outcome {
run_at(head, queue, 0).await
}
async fn run_at(head: &FakeHead, queue: &FakeQueue, attempt: u32) -> Outcome {
run(Some(head), Some(queue), "atlas".to_owned(), attempt).await
run(Some(head), Some(queue), "atlas".to_owned()).await
}
#[tokio::test]
@ -308,56 +282,30 @@ mod tests {
assert!(closure.built_unix > 0);
}
fn nix_error() -> FakeQueue {
FakeQueue::answering(Ok(FromMetaReply::Failed {
error_tail: "error: builder for foo failed".to_owned(),
}))
}
/// `nix` exiting with an error the first time is asked for once more: the
/// failure carries the tail and the retry marker, and the next build is the
/// second attempt. Nothing is recorded.
/// Any `nix` failure, a timeout included, fails the node at once with what
/// the builder said: not a no-verdict failure, and nothing is recorded. The
/// green test above is the control that a record is written when the build
/// is green.
#[tokio::test]
async fn the_first_nix_error_is_built_once_more() {
let queue = nix_error();
let Outcome::Failed(error) = run_with(&FakeHead::reading(Ok(Some(REV))), &queue).await
else {
panic!("not failed")
};
assert!(is_retried(&error), "{error}");
assert!(error.ends_with("error: builder for foo failed"), "{error}");
assert_eq!(next_attempt(0, &error), 1);
assert!(queue.recorded.lock().unwrap().is_empty());
}
/// The second `nix` error is a red build: the tail alone, nothing retries
/// it, nothing is recorded. The green test above is the control that a
/// record is written when the build is green.
#[tokio::test]
async fn the_second_nix_error_is_red_and_records_nothing() {
let queue = nix_error();
let outcome = run_at(&FakeHead::reading(Ok(Some(REV))), &queue, 1).await;
assert_eq!(
outcome,
Outcome::Failed("error: builder for foo failed".to_owned())
);
assert!(!is_retried("error: builder for foo failed"));
assert!(queue.recorded.lock().unwrap().is_empty());
}
/// A build with no verdict keeps its attempt, so a builder that is away for
/// hours does not use up the retry that a nix error is allowed.
#[test]
fn only_a_nix_error_uses_up_an_attempt() {
assert_eq!(next_attempt(0, &format!("{RETRY_PREFIX}no builder")), 0);
assert_eq!(next_attempt(1, &format!("{RETRY_PREFIX}no builder")), 1);
assert_eq!(next_attempt(0, &format!("{FIRST_FAILURE_PREFIX}tail")), 1);
async fn a_nix_failure_fails_the_node_with_its_tail_and_records_nothing() {
for tail in [
"error: builder for foo failed",
"timed out: nix took 60 minutes",
] {
let queue = FakeQueue::answering(Ok(FromMetaReply::Failed {
error_tail: tail.to_owned(),
}));
let outcome = run_with(&FakeHead::reading(Ok(Some(REV))), &queue).await;
assert_eq!(outcome, Outcome::Failed(tail.to_owned()));
assert!(!is_no_verdict(tail));
assert!(queue.recorded.lock().unwrap().is_empty(), "{tail}");
}
}
/// A read grant the forge will not make is the controller's precondition,
/// not the config's: nothing is sent and the failure is retried.
/// not the config's: nothing is sent and the failure has no verdict.
#[tokio::test]
async fn a_read_grant_that_cannot_be_made_is_retried_before_anything_is_sent() {
async fn a_read_grant_that_cannot_be_made_is_a_no_verdict_failure_before_anything_is_sent() {
let queue = FakeQueue::built();
let head = FakeHead {
grant_fails: true,
@ -366,13 +314,13 @@ mod tests {
let Outcome::Failed(error) = run_with(&head, &queue).await else {
panic!("not failed")
};
assert!(is_retried(&error), "{error}");
assert!(is_no_verdict(&error), "{error}");
assert!(error.contains("read on internal/meta"), "{error}");
assert!(queue.sent.lock().unwrap().is_empty());
}
#[tokio::test]
async fn a_builder_that_gave_no_verdict_is_a_retried_failure_and_records_nothing() {
async fn a_builder_that_gave_no_verdict_is_a_no_verdict_failure_and_records_nothing() {
for (name, reply) in [
(
"no responders",
@ -390,13 +338,13 @@ mod tests {
let Outcome::Failed(error) = outcome else {
panic!("{name}: not failed")
};
assert!(is_retried(&error), "{name}: {error}");
assert!(is_no_verdict(&error), "{name}: {error}");
assert!(queue.recorded.lock().unwrap().is_empty(), "{name}");
}
}
#[tokio::test]
async fn a_closure_that_cannot_be_recorded_is_a_retried_failure() {
async fn a_closure_that_cannot_be_recorded_is_a_no_verdict_failure() {
let queue = FakeQueue {
record_fails: true,
..FakeQueue::built()
@ -405,12 +353,12 @@ mod tests {
else {
panic!("not failed")
};
assert!(is_retried(&error), "{error}");
assert!(is_no_verdict(&error), "{error}");
assert!(error.contains("/nix/store/x-toplevel"), "{error}");
}
#[tokio::test]
async fn without_a_head_or_a_queue_nothing_is_sent_and_the_failure_is_retried() {
async fn without_a_head_or_a_queue_nothing_is_sent_and_the_failure_has_no_verdict() {
for (name, head, with_queue) in [
("no repo yet", Some(FakeHead::reading(Ok(None))), true),
(
@ -426,13 +374,12 @@ mod tests {
head.as_ref(),
with_queue.then_some(&queue),
"atlas".to_owned(),
0,
)
.await;
let Outcome::Failed(error) = outcome else {
panic!("{name}: not failed")
};
assert!(is_retried(&error), "{name}: {error}");
assert!(is_no_verdict(&error), "{name}: {error}");
assert!(queue.sent.lock().unwrap().is_empty(), "{name}");
}
}