Merge 'e26260d36eb8e7bf9e0b7edfed90c0dcff77fc19'
ci / check (push) Failing after 11m35s

This commit is contained in:
2026-10-26 13:59:16 +00:00
6 changed files with 801 additions and 40 deletions
+421 -34
View File
@@ -4,11 +4,44 @@ use anyhow::{Context, Result, bail};
use include_dir::{Dir, include_dir};
use serde_json::{Value, json};
use sha2::{Digest, Sha256};
use std::time::Duration;
use std::{
path::{Path, PathBuf},
sync::Arc,
};
use tokio::process::Command;
use tokio::{process::Command, time::Instant};
/// Default wall-clock budget after acquiring the build mutex (not queue time).
pub const DEFAULT_TIMEOUT_SECS: u64 = 900;
/// Default wall-clock budget for each WASI test instance.
pub const DEFAULT_TEST_TIMEOUT_SECS: u64 = 120;
/// Wall-clock budgets for a build and its individual WASI tests.
#[derive(Clone, Copy, Debug)]
pub struct BuildOptions {
pub timeout_secs: u64,
pub test_timeout_secs: u64,
}
impl Default for BuildOptions {
fn default() -> Self {
Self {
timeout_secs: DEFAULT_TIMEOUT_SECS,
test_timeout_secs: DEFAULT_TEST_TIMEOUT_SECS,
}
}
}
/// Optional RPC seconds are positive integers; null does not disable a deadline.
fn seconds(params: &Value, name: &str, default: u64) -> Result<u64, Value> {
match params.get(name) {
None => Ok(default),
Some(value) => value
.as_u64()
.filter(|seconds| *seconds >= 1)
.ok_or_else(|| {
crate::error(-32602, &format!("{name} must be an integer of at least 1"))
}),
}
}
/// The native build plugin.
pub const ID: &str = "cargo";
@@ -25,9 +58,78 @@ pub struct TestResults {
pub failed: u64,
pub output: String,
}
/// Raw, unfiltered output shared by the test and release phases of one build.
#[derive(Clone, Debug, serde::Serialize)]
pub struct BuildLogs {
pub stdout: StreamLog,
pub stderr: StreamLog,
pub total_bytes: u64,
}
#[derive(Clone, Debug, serde::Serialize)]
pub struct StreamLog {
pub path: String,
pub bytes: u64,
}
/// Persistent descriptors are inherited by cargo, so cancellation cannot lose
/// bytes already written by cargo or its descendants. No buffered writer is used.
struct LogFiles {
stdout: std::fs::File,
stderr: std::fs::File,
stdout_path: PathBuf,
stderr_path: PathBuf,
}
impl LogFiles {
fn create(world: &Path) -> Result<Self> {
let directory = world
.join("logs/cargo")
.join(chrono::Utc::now().format("%Y-%m-%d").to_string());
std::fs::create_dir_all(&directory).context("create cargo log directory")?;
let id = uuid::Uuid::now_v7();
let stdout_path = directory.join(format!("{id}.stdout.log"));
let stderr_path = directory.join(format!("{id}.stderr.log"));
let create = |path: &Path| {
std::fs::OpenOptions::new()
.create_new(true)
.append(true)
.open(path)
.with_context(|| format!("create {}", path.display()))
};
Ok(Self {
stdout: create(&stdout_path)?,
stderr: create(&stderr_path)?,
stdout_path,
stderr_path,
})
}
fn info(&self, world: &Path) -> Result<BuildLogs> {
let stream = |file: &std::fs::File, path: &Path| -> Result<StreamLog> {
Ok(StreamLog {
path: format!("/{}", path.strip_prefix(world)?.display()),
bytes: file.metadata()?.len(),
})
};
let stdout = stream(&self.stdout, &self.stdout_path)?;
let stderr = stream(&self.stderr, &self.stderr_path)?;
Ok(BuildLogs {
total_bytes: stdout.bytes + stderr.bytes,
stdout,
stderr,
})
}
fn read(&self, path: &Path, offset: u64) -> Result<Vec<u8>> {
use std::io::{Read, Seek, SeekFrom};
let mut file =
std::fs::File::open(path).with_context(|| format!("read {}", path.display()))?;
file.seek(SeekFrom::Start(offset))?;
let mut bytes = Vec::new();
file.read_to_end(&mut bytes)?;
Ok(bytes)
}
}
/// A successful build, usable without a running host.
#[derive(Debug)]
pub struct BuildOutput {
pub logs: Option<BuildLogs>,
pub wasm: PathBuf,
pub warnings: String,
pub tests: TestResults,
@@ -35,9 +137,12 @@ pub struct BuildOutput {
/// A failed compiler or test phase, with its complete diagnostics.
#[derive(Debug)]
pub struct BuildFailure {
pub logs: Option<BuildLogs>,
pub reason: String,
pub tests: TestResults,
pub output: String,
pub elapsed_secs: Option<f64>,
pub step: Option<&'static str>,
}
impl std::fmt::Display for BuildFailure {
fn fmt(&self, formatter: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
@@ -48,9 +153,12 @@ impl std::error::Error for BuildFailure {}
impl From<anyhow::Error> for BuildFailure {
fn from(error: anyhow::Error) -> Self {
Self {
logs: None,
reason: "build preparation failed".into(),
output: format!("{error:#}"),
tests: TestResults::default(),
elapsed_secs: None,
step: None,
}
}
}
@@ -142,19 +250,59 @@ impl Cargo {
host.register_native(ID,Arc::new(move |_context,method,params| {
let builder=builder.clone();
Box::pin(async move {
if method=="rpc.discover" { return Ok(json!({"openrpc":"1.2.6","info":{"title":"cargo","version":"native"},"methods":[{"name":"build","paramStructure":"by-name","params":[{"name":"plugin","required":true,"schema":{"type":"string"}}],"result":{"name":"build","schema":{"type":"object","required":["wasm","tests","warnings"],"properties":{"wasm":{"type":"string"},"warnings":{"type":"string"},"tests":{"type":"object","required":["passed","failed","output"],"properties":{"passed":{"type":"integer","minimum":0},"failed":{"type":"integer","minimum":0},"output":{"type":"string"}}}}}},"errors":[{"code":-32004,"message":"Build failed"}]}]})); }
if method=="rpc.discover" { return Ok(json!({"openrpc":"1.2.6","info":{"title":"cargo","version":"native"},"methods":[{"name":"build","paramStructure":"by-name","description":"Copies source, runs bounded WASI tests, then builds a release component. Deadlines kill cargo and its descendants; cancellation releases the build mutex.","params":[{"name":"plugin","required":true,"schema":{"type":"string"}},{"name":"timeout_secs","required":false,"description":"Total wall-clock limit in seconds for tests and release build after acquiring the build mutex (queue time excluded). Default 900; minimum 1. Cannot be disabled.","schema":{"type":"integer","minimum":1,"default":DEFAULT_TIMEOUT_SECS}},{"name":"test_timeout_secs","required":false,"description":"Wall-clock limit in seconds for each WASI test instance. Default 120; minimum 1. A timed-out test is named and fails; remaining tests continue.","schema":{"type":"integer","minimum":1,"default":DEFAULT_TEST_TIMEOUT_SECS}}],"result":{"name":"build","schema":{"type":"object","required":["wasm","tests","warnings","logs"],"properties":{"logs":{"type":"object","required":["stdout","stderr","total_bytes"],"properties":{"stdout":{"type":"object","required":["path","bytes"],"properties":{"path":{"type":"string"},"bytes":{"type":"integer","minimum":0}}},"stderr":{"type":"object","required":["path","bytes"],"properties":{"path":{"type":"string"},"bytes":{"type":"integer","minimum":0}}},"total_bytes":{"type":"integer","minimum":0}}},"wasm":{"type":"string"},"warnings":{"type":"string"},"tests":{"type":"object","required":["passed","failed","output"],"properties":{"passed":{"type":"integer","minimum":0},"failed":{"type":"integer","minimum":0},"output":{"type":"string"}}}}}},"errors":[{"code":-32004,"message":"Build failed"}]}]})); }
if method!="build" { return Err(crate::error(-32601,"cargo method not found")); }
let plugin=params["plugin"].as_str().ok_or_else(||crate::error(-32602,"plugin must be a string"))?;
match builder.build(&builder.world.plugin_dir(plugin).join("source")).await {
Ok(output)=>Ok(json!({"wasm":format!("/{}",output.wasm.strip_prefix(&builder.world.root).unwrap().display()),"tests":output.tests,"warnings":output.warnings})),
Err(failure)=>Err(json!({"code":-32004,"message":failure.reason,"data":{"tests":failure.tests,"output":failure.output}})),
let options = BuildOptions {
timeout_secs: seconds(&params, "timeout_secs", DEFAULT_TIMEOUT_SECS)?,
test_timeout_secs: seconds(&params, "test_timeout_secs", DEFAULT_TEST_TIMEOUT_SECS)?,
};
match builder.build_with_options(&builder.world.plugin_dir(plugin).join("source"), options).await {
Ok(output)=>Ok(json!({"wasm":format!("/{}",output.wasm.strip_prefix(&builder.world.root).unwrap().display()),"tests":output.tests,"warnings":output.warnings,"logs":output.logs})),
Err(failure)=>Err(json!({"code":-32004,"message":failure.reason,"data":{"reason":failure.reason,"tests":failure.tests,"output":failure.output,"elapsed_secs":failure.elapsed_secs,"step":failure.step,"logs":failure.logs}})),
}
})
}));
}
/// Copies source once, runs WASI tests, then publishes a release component under state/cargo/builds.
pub async fn build(&self, source: &Path) -> std::result::Result<BuildOutput, BuildFailure> {
self.build_with_options(source, BuildOptions::default())
.await
}
/// Like build, with explicit positive wall-clock budgets. Waiting for the mutex is unbounded.
pub async fn build_with_options(
&self,
source: &Path,
options: BuildOptions,
) -> std::result::Result<BuildOutput, BuildFailure> {
let logs = LogFiles::create(&self.world.root)?;
let result = self.build_logged(source, options, &logs).await;
let info = logs.info(&self.world.root)?;
match result {
Ok(mut output) => {
output.logs = Some(info);
Ok(output)
}
Err(mut failure) => {
failure.logs = Some(info);
Err(failure)
}
}
}
async fn build_logged(
&self,
source: &Path,
options: BuildOptions,
logs: &LogFiles,
) -> std::result::Result<BuildOutput, BuildFailure> {
if options.timeout_secs == 0 || options.test_timeout_secs == 0 {
return Err(anyhow::anyhow!("timeouts must be at least 1 second").into());
}
let build_guard = self.builds.clone().lock_owned().await;
let started = Instant::now();
let deadline = started
.checked_add(Duration::from_secs(options.timeout_secs))
.ok_or_else(|| anyhow::anyhow!("timeout_secs is too large"))?;
let work = self.world.state_dir(ID).join("work");
let target = self.target.clone();
let temporary = self.world.state_dir(ID).join("tmp");
@@ -208,16 +356,35 @@ impl Cargo {
.await
.map_err(anyhow::Error::from)??;
let mut test = Command::new("cargo");
test.args(["test", "--release", "--target", TARGET, "--target-dir"])
.arg(&target)
.current_dir(&work)
.env("TMPDIR", &temporary)
.arg("--config")
.arg(format!(
"target.wasm32-wasip2.runner={}",
json!([self.runner, "test-runner"])
));
let output = run_command(test).await?;
test.args([
"test",
"--no-fail-fast",
"--release",
"--target",
TARGET,
"--target-dir",
])
.arg(&target)
.current_dir(&work)
.env("TMPDIR", &temporary)
.env(
"SAUSAGE_TEST_TIMEOUT_SECS",
options.test_timeout_secs.to_string(),
)
.arg("--config")
.arg(format!(
"target.wasm32-wasip2.runner={}",
json!([self.runner, "test-runner"])
));
let output = run_command(
test,
started,
deadline,
"tests",
TestResults::default(),
logs,
)
.await?;
let stdout = String::from_utf8_lossy(&output.stdout);
let stderr = String::from_utf8_lossy(&output.stderr);
let tests = TestResults {
@@ -231,25 +398,36 @@ impl Cargo {
};
if !output.status.success() {
return Err(BuildFailure {
logs: None,
reason: "WASI tests failed".into(),
output: tests.output.clone(),
tests,
elapsed_secs: None,
step: None,
});
}
let mut build = Command::new("cargo");
build
.args([
"build",
"--release",
"--target",
TARGET,
"--message-format=json-render-diagnostics",
"--target-dir",
])
.arg(&target)
.current_dir(&work);
let output = run_command(
build,
started,
deadline,
"release build",
tests.clone(),
logs,
)
.await?;
let result = async {
let mut build = Command::new("cargo");
build
.args([
"build",
"--release",
"--target",
TARGET,
"--message-format=json-render-diagnostics",
"--target-dir",
])
.arg(&target)
.current_dir(&work);
let output = run_command(build).await?;
let stdout = String::from_utf8_lossy(&output.stdout);
let stderr = String::from_utf8_lossy(&output.stderr);
let diagnostics = stderr.to_string();
@@ -282,6 +460,7 @@ impl Cargo {
})
.await??;
Ok(BuildOutput {
logs: None,
wasm: destination,
warnings: strip_progress(&diagnostics),
tests: tests.clone(),
@@ -289,9 +468,12 @@ impl Cargo {
}
.await;
result.map_err(|error: anyhow::Error| BuildFailure {
logs: None,
reason: "release build failed".into(),
output: format!("{error:#}"),
tests,
elapsed_secs: None,
step: None,
})
}
}
@@ -306,16 +488,81 @@ impl Drop for ProcessGroup {
}
}
/// Starts one process group and retains its guard across all output collection.
async fn run_command(mut command: Command) -> Result<std::process::Output> {
async fn run_command(
mut command: Command,
started: Instant,
deadline: Instant,
step: &'static str,
mut tests: TestResults,
logs: &LogFiles,
) -> std::result::Result<std::process::Output, BuildFailure> {
command
.process_group(0)
.kill_on_drop(true)
.stdin(std::process::Stdio::null())
.stdout(std::process::Stdio::piped())
.stderr(std::process::Stdio::piped());
let child = command.spawn().context("start cargo")?;
let _group = ProcessGroup(child.id().unwrap());
Ok(child.wait_with_output().await?)
// Child writes go straight to persistent files: no pipe buffers or reader
// tasks can be dropped on cancellation. Parsing happens only afterwards.
.stdout(logs.stdout.try_clone().context("clone stdout log")?)
.stderr(logs.stderr.try_clone().context("clone stderr log")?);
let out_start = logs.stdout.metadata().context("stat stdout log")?.len();
let err_start = logs.stderr.metadata().context("stat stderr log")?.len();
let mut child = command.spawn().context("start cargo")?;
let group = ProcessGroup(child.id().unwrap());
let (status, timed_out) = {
let collect = child.wait();
tokio::pin!(collect);
tokio::select! {
biased;
_ = tokio::time::sleep_until(deadline) => {
// Kill the entire tree before waiting for EOF/reaping cargo. The guard also
// covers cancellation while collecting, and runs before the mutex drops.
let _ = nix::sys::signal::killpg(nix::unistd::Pid::from_raw(group.0 as i32), nix::sys::signal::Signal::SIGKILL);
(collect.await, true)
}
status = &mut collect => (status, false),
}
};
let status = status.map_err(anyhow::Error::from)?;
// Also stop any descendants that kept the streams open after cargo exited.
drop(group);
let out = logs.read(&logs.stdout_path, out_start)?;
let err = logs.read(&logs.stderr_path, err_start)?;
if timed_out {
let output = format!(
"{}\n{}",
String::from_utf8_lossy(&out),
String::from_utf8_lossy(&err)
);
let output = output
.trim_end()
.lines()
.rev()
.take(50)
.collect::<Vec<_>>()
.into_iter()
.rev()
.collect::<Vec<_>>()
.join("\n");
if step == "tests" {
tests.passed = test_count(&String::from_utf8_lossy(&out), "passed");
tests.failed = test_count(&String::from_utf8_lossy(&out), "failed");
tests.output = output.clone();
}
return Err(BuildFailure {
logs: None,
reason: "timeout".into(),
tests,
output,
elapsed_secs: Some(started.elapsed().as_secs_f64()),
step: Some(step),
});
}
Ok(std::process::Output {
status,
stdout: out,
stderr: err,
})
}
/// Copies only source, excluding build outputs and git internals at every level.
fn copy_source(source: &Path, destination: &Path, root: bool) -> Result<()> {
@@ -457,3 +704,143 @@ fn strip_progress(output: &str) -> String {
.collect::<Vec<_>>()
.join("\n")
}
#[cfg(test)]
mod timeout_tests {
use super::*;
/// Streams retain exact bytes, including non-UTF8, progress and JSON; phases append.
#[tokio::test]
async fn raw_streams_append_before_parsing() {
let directory = tempfile::tempdir().unwrap();
let logs = LogFiles::create(directory.path()).unwrap();
for _ in 0..2 {
let mut command = Command::new("sh");
command.args(["-c", "printf '\\377raw\\r'; printf ' Compiling progress\\n{\"reason\":\"compiler-artifact\"}\\n' >&2; exit 3"]);
let now = Instant::now();
let output = tokio::time::timeout(
Duration::from_secs(5),
run_command(
command,
now,
now + Duration::from_secs(3),
"tests",
TestResults::default(),
&logs,
),
)
.await
.unwrap()
.unwrap();
assert!(!output.status.success());
assert_eq!(output.stdout, b"\xffraw\r");
assert!(String::from_utf8_lossy(&output.stderr).contains("Compiling progress"));
}
assert_eq!(
std::fs::read(&logs.stdout_path).unwrap(),
b"\xffraw\r\xffraw\r"
);
let info = logs.info(directory.path()).unwrap();
assert_eq!(info.stdout.bytes, 10);
assert_eq!(info.total_bytes, info.stdout.bytes + info.stderr.bytes);
assert!(info.stdout.path.starts_with("/logs/cargo/"));
assert!(!directory.path().join("state/cargo").exists());
}
/// Cancellation leaves kernel-written data intact, even without a newline.
#[tokio::test]
async fn cancelled_command_keeps_logs() {
use notify::Watcher;
let directory = tempfile::tempdir().unwrap();
let logs = LogFiles::create(directory.path()).unwrap();
let (tx, mut rx) = tokio::sync::mpsc::unbounded_channel();
let mut watcher =
notify::recommended_watcher(move |event: notify::Result<notify::Event>| {
if let Ok(event) = event {
if event
.paths
.iter()
.any(|path| path.file_name().is_some_and(|name| name == "ready"))
{
let _ = tx.send(());
}
}
})
.unwrap();
watcher
.watch(directory.path(), notify::RecursiveMode::NonRecursive)
.unwrap();
let mut command = Command::new("sh");
command.args(["-c", "printf 'partial\\377'; printf 'stderr\\r' >&2; touch \"$1/ready\"; exec sleep 1000", "sh"]).arg(directory.path());
let now = Instant::now();
let task = tokio::spawn(async move {
run_command(
command,
now,
now + Duration::from_secs(60),
"tests",
TestResults::default(),
&logs,
)
.await
});
tokio::time::timeout(Duration::from_secs(5), rx.recv())
.await
.unwrap()
.unwrap();
task.abort();
assert!(task.await.unwrap_err().is_cancelled());
let paths: Vec<_> = std::fs::read_dir(directory.path().join("logs/cargo"))
.unwrap()
.flat_map(|day| std::fs::read_dir(day.unwrap().path()).unwrap())
.map(|file| file.unwrap().path())
.collect();
assert_eq!(paths.len(), 2);
for path in paths {
let expected: &[u8] = if path.to_string_lossy().ends_with(".stdout.log") {
b"partial\xff"
} else {
b"stderr\r"
};
assert_eq!(std::fs::read(path).unwrap(), expected);
}
}
/// Deadline errors retain the shared start time, phase, test totals, and output tail.
#[tokio::test]
async fn timeout_diagnostics() {
let mut command = Command::new("sh");
command.args([
"-c",
"i=0; while [ $i -lt 100 ]; do echo diagnostic-$i; i=$((i+1)); done; exec sleep 1000",
]);
let directory = tempfile::tempdir().unwrap();
let logs = LogFiles::create(directory.path()).unwrap();
let now = Instant::now();
let failure = run_command(
command,
now - Duration::from_secs(10),
now + Duration::from_secs(1),
"release build",
TestResults {
passed: 7,
failed: 0,
output: "successful tests".into(),
},
&logs,
)
.await
.unwrap_err();
assert_eq!(failure.reason, "timeout");
assert_eq!(failure.step, Some("release build"));
assert!(failure.elapsed_secs.unwrap() >= 11.0);
assert_eq!(failure.tests.passed, 7);
assert_eq!(failure.tests.output, "successful tests");
assert_eq!(failure.output.lines().count(), 50);
assert!(failure.output.contains("diagnostic-99"));
assert!(!failure.output.contains("diagnostic-0\n"));
let raw = std::fs::read_to_string(&logs.stdout_path).unwrap();
assert_eq!(raw.lines().count(), 100);
assert!(raw.starts_with("diagnostic-0\n"));
}
}
+19 -2
View File
@@ -64,12 +64,21 @@ async fn instance(
("SAUSAGE_PLUGIN".into(), "test".into()),
("SAUSAGE_PARENT".into(), "core".into()),
]);
let timeout_secs = std::env::var("SAUSAGE_TEST_TIMEOUT_SECS")
.ok()
.and_then(|value| value.parse::<u64>().ok())
.filter(|value| *value >= 1)
.unwrap_or(sausage::cargo::DEFAULT_TEST_TIMEOUT_SECS);
let deadline = tokio::time::Instant::now()
.checked_add(std::time::Duration::from_secs(timeout_secs))
.ok_or_else(|| anyhow::anyhow!("test_timeout_secs is too large"))?;
let (ended, mut ended_rx) = tokio::sync::watch::channel(true);
let mut guest = runtime
.start_with_args(
&component,
InstanceConfig {
filesystem,
store_ended: tokio::sync::watch::channel(true).0,
store_ended: ended,
network: true,
env,
},
@@ -88,6 +97,7 @@ async fn instance(
let mut stdout_open = true;
let mut stderr_open = true;
let mut handlers = tokio::task::JoinSet::new();
let result = tokio::time::timeout_at(deadline, async {
while stdout_open || stderr_open || !pending.is_empty() {
tokio::select! {
line=async { if let Some(line) = pending.pop_front() { Some(line) } else { guest.stdout.recv().await } }, if stdout_open || !pending.is_empty()=>match line {
@@ -129,11 +139,18 @@ async fn instance(
},
}
}
Ok::<_, anyhow::Error>(guest.wait().await)
}).await;
handlers.abort_all();
let exit = guest.wait().await;
// Dropping the instance aborts even a CPU-bound WASI loop. Wait for the
// store and outstanding filesystem work before removing its test world.
drop(guest);
let _ = ended_rx.wait_for(|ended| *ended).await;
let _ = stderr_task.await;
tracker.idle().await;
host.stop().await;
let exit =
result.map_err(|_| anyhow::anyhow!("timed out after {timeout_secs} s\n{output}"))??;
Ok(Run { exit, output })
}
/// Extracts libtest names from its stable list format.