mirror of
https://github.com/neondatabase/neon.git
synced 2026-06-04 05:50:38 +00:00
Improve logging on changes in a compute's status
I'm trying to debug a situation with the LR benchmark publisher not being in the correct state. This should aid in debugging, while just being generally useful. PR: https://github.com/neondatabase/neon/pull/9265 Signed-off-by: Tristan Partin <tristan@neon.tech>
This commit is contained in:
@@ -402,8 +402,7 @@ fn start_postgres(
|
||||
) -> Result<(Option<PostgresHandle>, StartPostgresResult)> {
|
||||
// We got all we need, update the state.
|
||||
let mut state = compute.state.lock().unwrap();
|
||||
state.status = ComputeStatus::Init;
|
||||
compute.state_changed.notify_all();
|
||||
state.set_status(ComputeStatus::Init, &compute.state_changed);
|
||||
|
||||
info!(
|
||||
"running compute with features: {:?}",
|
||||
|
||||
@@ -109,6 +109,18 @@ impl ComputeState {
|
||||
metrics: ComputeMetrics::default(),
|
||||
}
|
||||
}
|
||||
|
||||
pub fn set_status(&mut self, status: ComputeStatus, state_changed: &Condvar) {
|
||||
let prev = self.status;
|
||||
info!("Changing compute status from {} to {}", prev, status);
|
||||
self.status = status;
|
||||
state_changed.notify_all();
|
||||
}
|
||||
|
||||
pub fn set_failed_status(&mut self, err: anyhow::Error, state_changed: &Condvar) {
|
||||
self.error = Some(format!("{err:?}"));
|
||||
self.set_status(ComputeStatus::Failed, state_changed);
|
||||
}
|
||||
}
|
||||
|
||||
impl Default for ComputeState {
|
||||
@@ -303,15 +315,12 @@ impl ComputeNode {
|
||||
|
||||
pub fn set_status(&self, status: ComputeStatus) {
|
||||
let mut state = self.state.lock().unwrap();
|
||||
state.status = status;
|
||||
self.state_changed.notify_all();
|
||||
state.set_status(status, &self.state_changed);
|
||||
}
|
||||
|
||||
pub fn set_failed_status(&self, err: anyhow::Error) {
|
||||
let mut state = self.state.lock().unwrap();
|
||||
state.error = Some(format!("{err:?}"));
|
||||
state.status = ComputeStatus::Failed;
|
||||
self.state_changed.notify_all();
|
||||
state.set_failed_status(err, &self.state_changed);
|
||||
}
|
||||
|
||||
pub fn get_status(&self) -> ComputeStatus {
|
||||
|
||||
@@ -24,8 +24,7 @@ fn configurator_main_loop(compute: &Arc<ComputeNode>) {
|
||||
// Re-check the status after waking up
|
||||
if state.status == ComputeStatus::ConfigurationPending {
|
||||
info!("got configuration request");
|
||||
state.status = ComputeStatus::Configuration;
|
||||
compute.state_changed.notify_all();
|
||||
state.set_status(ComputeStatus::Configuration, &compute.state_changed);
|
||||
drop(state);
|
||||
|
||||
let mut new_status = ComputeStatus::Failed;
|
||||
|
||||
@@ -288,8 +288,7 @@ async fn handle_configure_request(
|
||||
return Err((msg, StatusCode::PRECONDITION_FAILED));
|
||||
}
|
||||
state.pspec = Some(parsed_spec);
|
||||
state.status = ComputeStatus::ConfigurationPending;
|
||||
compute.state_changed.notify_all();
|
||||
state.set_status(ComputeStatus::ConfigurationPending, &compute.state_changed);
|
||||
drop(state);
|
||||
info!("set new spec and notified waiters");
|
||||
}
|
||||
@@ -362,15 +361,15 @@ async fn handle_terminate_request(compute: &Arc<ComputeNode>) -> Result<(), (Str
|
||||
}
|
||||
if state.status != ComputeStatus::Empty && state.status != ComputeStatus::Running {
|
||||
let msg = format!(
|
||||
"invalid compute status for termination request: {:?}",
|
||||
state.status.clone()
|
||||
"invalid compute status for termination request: {}",
|
||||
state.status
|
||||
);
|
||||
return Err((msg, StatusCode::PRECONDITION_FAILED));
|
||||
}
|
||||
state.status = ComputeStatus::TerminationPending;
|
||||
compute.state_changed.notify_all();
|
||||
state.set_status(ComputeStatus::TerminationPending, &compute.state_changed);
|
||||
drop(state);
|
||||
}
|
||||
|
||||
forward_termination_signal();
|
||||
info!("sent signal and notified waiters");
|
||||
|
||||
@@ -384,7 +383,8 @@ async fn handle_terminate_request(compute: &Arc<ComputeNode>) -> Result<(), (Str
|
||||
while state.status != ComputeStatus::Terminated {
|
||||
state = c.state_changed.wait(state).unwrap();
|
||||
info!(
|
||||
"waiting for compute to become Terminated, current status: {:?}",
|
||||
"waiting for compute to become {}, current status: {:?}",
|
||||
ComputeStatus::Terminated,
|
||||
state.status
|
||||
);
|
||||
}
|
||||
|
||||
@@ -1,5 +1,7 @@
|
||||
//! Structs representing the JSON formats used in the compute_ctl's HTTP API.
|
||||
|
||||
use std::fmt::Display;
|
||||
|
||||
use chrono::{DateTime, Utc};
|
||||
use serde::{Deserialize, Serialize, Serializer};
|
||||
|
||||
@@ -58,6 +60,21 @@ pub enum ComputeStatus {
|
||||
Terminated,
|
||||
}
|
||||
|
||||
impl Display for ComputeStatus {
|
||||
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
|
||||
match self {
|
||||
ComputeStatus::Empty => f.write_str("empty"),
|
||||
ComputeStatus::ConfigurationPending => f.write_str("configuration-pending"),
|
||||
ComputeStatus::Init => f.write_str("init"),
|
||||
ComputeStatus::Running => f.write_str("running"),
|
||||
ComputeStatus::Configuration => f.write_str("configuration"),
|
||||
ComputeStatus::Failed => f.write_str("failed"),
|
||||
ComputeStatus::TerminationPending => f.write_str("termination-pending"),
|
||||
ComputeStatus::Terminated => f.write_str("terminated"),
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
fn rfc3339_serialize<S>(x: &Option<DateTime<Utc>>, s: S) -> Result<S::Ok, S::Error>
|
||||
where
|
||||
S: Serializer,
|
||||
|
||||
Reference in New Issue
Block a user