mirror of
https://github.com/cfal/shoes.git
synced 2026-11-06 08:14:11 +00:00
cfal
b0b30617a2
Add URL-scoped health and delay-based upstream selection so new connections can use healthy, transport-compatible proxies without requiring a controller listener. This introduces strict client_group.type configuration in place of strategy, bounded automatic probes with lazy activity tracking and reload fencing, controller reporting, and configuration documentation. It also preserves local failure attribution through outbound HTTP/2 adapters so local resource limits do not incorrectly penalize proxy health.
371 lines
12 KiB
Rust
371 lines
12 KiB
Rust
use std::collections::{BTreeMap, HashMap, HashSet};
|
|
use std::io;
|
|
use std::time::Duration;
|
|
|
|
use parking_lot::Mutex;
|
|
use tokio::time::Instant;
|
|
|
|
use crate::config::UrlTestConfig;
|
|
|
|
tokio::task_local! {
|
|
pub static BACKGROUND: ();
|
|
}
|
|
|
|
pub fn is_background() -> bool {
|
|
BACKGROUND.try_with(|_| ()).is_ok()
|
|
}
|
|
|
|
// Only unambiguous transport failures request a recheck. A user destination's
|
|
// failure is not evidence that the configured probe URL is unreachable.
|
|
pub fn remote_failure(error: &io::Error) -> bool {
|
|
if crate::resources::is_exhausted(error) {
|
|
return false;
|
|
}
|
|
matches!(
|
|
error.kind(),
|
|
io::ErrorKind::ConnectionRefused
|
|
| io::ErrorKind::ConnectionReset
|
|
| io::ErrorKind::ConnectionAborted
|
|
| io::ErrorKind::NotConnected
|
|
| io::ErrorKind::TimedOut
|
|
| io::ErrorKind::UnexpectedEof
|
|
| io::ErrorKind::BrokenPipe
|
|
| io::ErrorKind::NetworkUnreachable
|
|
| io::ErrorKind::HostUnreachable
|
|
)
|
|
}
|
|
|
|
#[derive(Debug, Clone, Copy)]
|
|
struct Sample {
|
|
at: Instant,
|
|
delay: Option<u16>,
|
|
}
|
|
|
|
#[derive(Debug, Default)]
|
|
struct State {
|
|
samples: HashMap<String, Sample>,
|
|
incumbent: [Option<String>; 2],
|
|
last_touch: Option<Instant>,
|
|
last_check: Option<Instant>,
|
|
last_unqueued_admission: Option<Instant>,
|
|
recheck: bool,
|
|
cursor: usize,
|
|
}
|
|
|
|
#[derive(Debug)]
|
|
pub struct AutomaticGroup {
|
|
pub config: UrlTestConfig,
|
|
pub members: Vec<String>,
|
|
state: Mutex<State>,
|
|
}
|
|
|
|
#[derive(Debug, Default)]
|
|
pub struct AutomaticGroups(pub BTreeMap<String, AutomaticGroup>);
|
|
|
|
impl AutomaticGroups {
|
|
pub fn filter(
|
|
&self,
|
|
origins: &[Option<super::catalog::MemberOrigin>],
|
|
candidates: &mut Vec<usize>,
|
|
udp: bool,
|
|
) {
|
|
let mut depths = HashMap::<&str, usize>::new();
|
|
for &index in candidates.iter() {
|
|
let Some(origin) = &origins[index] else {
|
|
continue;
|
|
};
|
|
for (depth, (group, _)) in origin.path.iter().enumerate() {
|
|
if self.0.contains_key(group) {
|
|
depths
|
|
.entry(group)
|
|
.and_modify(|value| *value = (*value).max(depth))
|
|
.or_insert(depth);
|
|
}
|
|
}
|
|
}
|
|
let mut groups: Vec<_> = depths.into_iter().collect();
|
|
groups.sort_unstable_by_key(|(_, depth)| std::cmp::Reverse(*depth));
|
|
for (group, _) in groups {
|
|
let eligible = candidates
|
|
.iter()
|
|
.filter_map(|&index| origins[index].as_ref())
|
|
.flat_map(|origin| &origin.path)
|
|
.filter(|(name, _)| name == group)
|
|
.map(|(_, member)| member.as_str())
|
|
.collect();
|
|
if let Some(selected) = self.0[group].choose(&eligible, udp) {
|
|
candidates.retain(|&index| {
|
|
origins[index].as_ref().is_none_or(|origin| {
|
|
origin
|
|
.path
|
|
.iter()
|
|
.all(|(name, member)| name != group || member == &selected)
|
|
})
|
|
});
|
|
}
|
|
}
|
|
}
|
|
|
|
pub fn insert(
|
|
&mut self,
|
|
name: String,
|
|
mut config: UrlTestConfig,
|
|
members: Vec<String>,
|
|
) -> io::Result<()> {
|
|
config.validate()?;
|
|
if members.is_empty() || members.iter().collect::<HashSet<_>>().len() != members.len() {
|
|
return Err(io::Error::new(
|
|
io::ErrorKind::InvalidInput,
|
|
"url-test requires nonempty, distinct members",
|
|
));
|
|
}
|
|
config.url = url::Url::parse(&config.url)
|
|
.map_err(io::Error::other)?
|
|
.to_string();
|
|
self.0.insert(
|
|
name,
|
|
AutomaticGroup {
|
|
config,
|
|
members,
|
|
state: Mutex::default(),
|
|
},
|
|
);
|
|
Ok(())
|
|
}
|
|
|
|
pub fn record(&self, member: &str, url: &str, delay: Option<u16>) {
|
|
for group in self.0.values() {
|
|
if group.config.url == url && group.members.iter().any(|name| name == member) {
|
|
group.state.lock().samples.insert(
|
|
member.into(),
|
|
Sample {
|
|
at: Instant::now(),
|
|
delay,
|
|
},
|
|
);
|
|
}
|
|
}
|
|
}
|
|
|
|
pub fn touch(&self, name: &str, failed: bool) {
|
|
if !is_background()
|
|
&& let Some(group) = self.0.get(name)
|
|
{
|
|
let mut state = group.state.lock();
|
|
state.last_touch = Some(Instant::now());
|
|
state.recheck |= failed;
|
|
}
|
|
}
|
|
}
|
|
|
|
impl AutomaticGroup {
|
|
fn fresh(&self, sample: &Sample, now: Instant) -> bool {
|
|
now.duration_since(sample.at)
|
|
<= Duration::from_secs(self.config.interval * 2)
|
|
+ Duration::from_millis(self.config.timeout)
|
|
}
|
|
|
|
pub fn choose(&self, eligible: &HashSet<&str>, udp: bool) -> Option<String> {
|
|
let mut state = self.state.lock();
|
|
let now = Instant::now();
|
|
let delay = |name: &str| {
|
|
state
|
|
.samples
|
|
.get(name)
|
|
.filter(|sample| self.fresh(sample, now))
|
|
.and_then(|sample| sample.delay)
|
|
};
|
|
let best = self
|
|
.members
|
|
.iter()
|
|
.filter(|name| eligible.contains(name.as_str()))
|
|
.filter_map(|name| delay(name).map(|delay| (name, delay)))
|
|
.min_by_key(|(_, delay)| *delay);
|
|
let incumbent = state.incumbent[usize::from(udp)]
|
|
.as_ref()
|
|
.filter(|name| eligible.contains(name.as_str()));
|
|
let selected = match (best, incumbent) {
|
|
(Some((best, best_delay)), Some(current)) => {
|
|
if delay(current).is_some_and(|delay| {
|
|
u32::from(delay) <= u32::from(best_delay) + u32::from(self.config.tolerance)
|
|
}) {
|
|
Some(current.clone())
|
|
} else {
|
|
Some(best.clone())
|
|
}
|
|
}
|
|
(Some((best, _)), None) => Some(best.clone()),
|
|
(None, Some(current)) => Some(current.clone()),
|
|
(None, None) => self
|
|
.members
|
|
.iter()
|
|
.find(|name| eligible.contains(name.as_str()))
|
|
.cloned(),
|
|
};
|
|
state.incumbent[usize::from(udp)] = selected.clone();
|
|
selected
|
|
}
|
|
|
|
pub fn health(&self, member: &str) -> &'static str {
|
|
let state = self.state.lock();
|
|
match state.samples.get(member) {
|
|
None => "unprobed",
|
|
Some(sample) if !self.fresh(sample, Instant::now()) => "stale",
|
|
Some(Sample { delay: Some(_), .. }) => "healthy",
|
|
Some(_) => "dead",
|
|
}
|
|
}
|
|
|
|
pub fn due_members(&self, now: Instant) -> Option<Vec<usize>> {
|
|
let mut state = self.state.lock();
|
|
let interval = Duration::from_secs(self.config.interval);
|
|
if let Some(last_check) = state.last_check {
|
|
let elapsed = now.duration_since(last_check);
|
|
let recheck_due = state.recheck && elapsed >= Duration::from_secs(1);
|
|
if !recheck_due {
|
|
if elapsed < interval {
|
|
return None;
|
|
}
|
|
let idle = state
|
|
.last_touch
|
|
.is_none_or(|touch| now.duration_since(touch) >= interval);
|
|
if self.config.lazy && idle {
|
|
return None;
|
|
}
|
|
}
|
|
}
|
|
state.last_check = Some(now);
|
|
state.recheck = false;
|
|
let members = (state.cursor..self.members.len())
|
|
.chain(0..state.cursor)
|
|
.collect();
|
|
Some(members)
|
|
}
|
|
|
|
pub fn admitted(&self, index: usize, queued: bool) {
|
|
let mut state = self.state.lock();
|
|
state.cursor = (index + 1) % self.members.len();
|
|
if !queued {
|
|
state.last_unqueued_admission = Some(Instant::now());
|
|
}
|
|
}
|
|
|
|
pub fn last_unqueued_admission(&self) -> Option<Instant> {
|
|
self.state.lock().last_unqueued_admission
|
|
}
|
|
|
|
pub fn cancel_check(&self) {
|
|
self.state.lock().last_check = None;
|
|
}
|
|
}
|
|
|
|
#[cfg(test)]
|
|
mod tests {
|
|
use super::*;
|
|
|
|
fn groups() -> AutomaticGroups {
|
|
let mut groups = AutomaticGroups::default();
|
|
for (name, url) in [
|
|
("one", "http://one.invalid/"),
|
|
("two", "http://two.invalid/"),
|
|
] {
|
|
groups
|
|
.insert(
|
|
name.into(),
|
|
UrlTestConfig {
|
|
url: url.into(),
|
|
interval: 10,
|
|
timeout: 1000,
|
|
tolerance: 50,
|
|
lazy: true,
|
|
},
|
|
vec!["a".into(), "b".into()],
|
|
)
|
|
.unwrap();
|
|
}
|
|
groups
|
|
}
|
|
|
|
#[tokio::test(start_paused = true)]
|
|
async fn selection_health_tolerance_failure_recovery_and_staleness_are_url_scoped() {
|
|
let groups = groups();
|
|
let group = &groups.0["one"];
|
|
let both = HashSet::from(["a", "b"]);
|
|
assert_eq!(group.choose(&both, false).as_deref(), Some("a"));
|
|
assert_eq!(group.health("a"), "unprobed");
|
|
groups.record("b", "http://two.invalid/", Some(1));
|
|
assert_eq!(group.choose(&both, false).as_deref(), Some("a"));
|
|
assert_eq!(groups.0["two"].choose(&both, false).as_deref(), Some("b"));
|
|
groups.record("a", &group.config.url, Some(100));
|
|
groups.record("b", &group.config.url, Some(50));
|
|
assert_eq!(group.choose(&both, false).as_deref(), Some("a"));
|
|
groups.record("b", &group.config.url, Some(49));
|
|
assert_eq!(group.choose(&both, false).as_deref(), Some("b"));
|
|
groups.record("b", &group.config.url, None);
|
|
assert_eq!(group.choose(&both, false).as_deref(), Some("a"));
|
|
groups.record("b", &group.config.url, Some(1));
|
|
assert_eq!(group.choose(&both, false).as_deref(), Some("b"));
|
|
assert_eq!(
|
|
group.choose(&HashSet::from(["a"]), true).as_deref(),
|
|
Some("a")
|
|
);
|
|
assert_eq!(group.choose(&both, false).as_deref(), Some("b"));
|
|
groups.record("a", &group.config.url, None);
|
|
groups.record("b", &group.config.url, None);
|
|
assert_eq!(group.health("b"), "dead");
|
|
assert_eq!(group.choose(&both, false).as_deref(), Some("b"));
|
|
groups.record("b", &group.config.url, Some(1));
|
|
tokio::time::advance(Duration::from_secs(22)).await;
|
|
assert_eq!(group.health("b"), "stale");
|
|
assert_eq!(group.choose(&both, false).as_deref(), Some("b"));
|
|
assert!(group.choose(&HashSet::new(), true).is_none());
|
|
groups.record("a", &group.config.url, Some(150));
|
|
assert_eq!(group.choose(&both, false).as_deref(), Some("a"));
|
|
}
|
|
|
|
#[tokio::test(start_paused = true)]
|
|
async fn lazy_startup_probe_suppression_touch_and_rate_limited_recheck() {
|
|
let groups = groups();
|
|
let group = &groups.0["one"];
|
|
assert!(group.due_members(Instant::now()).is_some());
|
|
tokio::time::advance(Duration::from_secs(10)).await;
|
|
BACKGROUND
|
|
.scope((), async {
|
|
groups.touch("one", true);
|
|
})
|
|
.await;
|
|
assert!(group.due_members(Instant::now()).is_none());
|
|
groups.touch("one", false);
|
|
assert!(group.due_members(Instant::now()).is_some());
|
|
groups.touch("one", true);
|
|
assert!(group.due_members(Instant::now()).is_none());
|
|
tokio::time::advance(Duration::from_secs(1)).await;
|
|
assert!(group.due_members(Instant::now()).is_some());
|
|
tokio::time::advance(Duration::from_secs(10)).await;
|
|
assert!(group.due_members(Instant::now()).is_none());
|
|
}
|
|
|
|
#[test]
|
|
fn local_errors_do_not_request_remote_health_changes() {
|
|
for kind in [
|
|
io::ErrorKind::WouldBlock,
|
|
io::ErrorKind::Unsupported,
|
|
io::ErrorKind::OutOfMemory,
|
|
io::ErrorKind::ResourceBusy,
|
|
io::ErrorKind::InvalidInput,
|
|
io::ErrorKind::PermissionDenied,
|
|
io::ErrorKind::Other,
|
|
] {
|
|
assert!(!remote_failure(&io::Error::from(kind)), "{kind:?}");
|
|
}
|
|
for kind in [
|
|
io::ErrorKind::ConnectionRefused,
|
|
io::ErrorKind::ConnectionReset,
|
|
io::ErrorKind::TimedOut,
|
|
io::ErrorKind::BrokenPipe,
|
|
] {
|
|
assert!(remote_failure(&io::Error::from(kind)), "{kind:?}");
|
|
}
|
|
}
|
|
}
|