mirror of
https://github.com/neondatabase/neon.git
synced 2026-01-15 17:32:56 +00:00
dd4fd89dc6
Our scale-to-zero logic was optimized for short auto-suspend intervals, e.g. minutes or hours. In this case, if compute was restarted by k8s due to some reason (OOM, k8s node went down, pod relocation, etc.), `last_active` got bumped, we start counting auto-suspend timeout again. It's not a big deal, i.e. we suspend completely idle compute not after 5 minutes, but after 10 minutes or so. Yet, some clients may want days or even weeks. And chance that compute could be restarted during this interval is pretty high, but in this case we could be not able to suspend some computes for weeks. After this commit, we won't initialize `last_active` on start, so `/status` could return an unset attribute. This means that there was no user activity since start. Control-plane should deal with it by taking `max()` out of all available activity timestamps: `started_at`, `last_active`, etc. compute_ctl part of neondatabase/cloud#4853
97 lines
2.7 KiB
Rust
97 lines
2.7 KiB
Rust
//! Structs representing the JSON formats used in the compute_ctl's HTTP API.
|
|
|
|
use chrono::{DateTime, Utc};
|
|
use serde::{Deserialize, Serialize, Serializer};
|
|
|
|
use crate::spec::ComputeSpec;
|
|
|
|
#[derive(Serialize, Debug)]
|
|
pub struct GenericAPIError {
|
|
pub error: String,
|
|
}
|
|
|
|
/// Response of the /status API
|
|
#[derive(Serialize, Debug)]
|
|
#[serde(rename_all = "snake_case")]
|
|
pub struct ComputeStatusResponse {
|
|
pub start_time: DateTime<Utc>,
|
|
pub tenant: Option<String>,
|
|
pub timeline: Option<String>,
|
|
pub status: ComputeStatus,
|
|
#[serde(serialize_with = "rfc3339_serialize")]
|
|
pub last_active: Option<DateTime<Utc>>,
|
|
pub error: Option<String>,
|
|
}
|
|
|
|
#[derive(Serialize)]
|
|
#[serde(rename_all = "snake_case")]
|
|
pub struct ComputeState {
|
|
pub status: ComputeStatus,
|
|
/// Timestamp of the last Postgres activity
|
|
#[serde(serialize_with = "rfc3339_serialize")]
|
|
pub last_active: Option<DateTime<Utc>>,
|
|
pub error: Option<String>,
|
|
}
|
|
|
|
#[derive(Serialize, Clone, Copy, Debug, PartialEq, Eq)]
|
|
#[serde(rename_all = "snake_case")]
|
|
pub enum ComputeStatus {
|
|
// Spec wasn't provided at start, waiting for it to be
|
|
// provided by control-plane.
|
|
Empty,
|
|
// Compute configuration was requested.
|
|
ConfigurationPending,
|
|
// Compute node has spec and initial startup and
|
|
// configuration is in progress.
|
|
Init,
|
|
// Compute is configured and running.
|
|
Running,
|
|
// New spec is being applied.
|
|
Configuration,
|
|
// Either startup or configuration failed,
|
|
// compute will exit soon or is waiting for
|
|
// control-plane to terminate it.
|
|
Failed,
|
|
}
|
|
|
|
fn rfc3339_serialize<S>(x: &Option<DateTime<Utc>>, s: S) -> Result<S::Ok, S::Error>
|
|
where
|
|
S: Serializer,
|
|
{
|
|
if let Some(x) = x {
|
|
x.to_rfc3339().serialize(s)
|
|
} else {
|
|
s.serialize_none()
|
|
}
|
|
}
|
|
|
|
/// Response of the /metrics.json API
|
|
#[derive(Clone, Debug, Default, Serialize)]
|
|
pub struct ComputeMetrics {
|
|
pub wait_for_spec_ms: u64,
|
|
pub sync_safekeepers_ms: u64,
|
|
pub basebackup_ms: u64,
|
|
pub config_ms: u64,
|
|
pub total_startup_ms: u64,
|
|
}
|
|
|
|
/// Response of the `/computes/{compute_id}/spec` control-plane API.
|
|
/// This is not actually a compute API response, so consider moving
|
|
/// to a different place.
|
|
#[derive(Deserialize, Debug)]
|
|
pub struct ControlPlaneSpecResponse {
|
|
pub spec: Option<ComputeSpec>,
|
|
pub status: ControlPlaneComputeStatus,
|
|
}
|
|
|
|
#[derive(Deserialize, Clone, Copy, Debug, PartialEq, Eq)]
|
|
#[serde(rename_all = "snake_case")]
|
|
pub enum ControlPlaneComputeStatus {
|
|
// Compute is known to control-plane, but it's not
|
|
// yet attached to any timeline / endpoint.
|
|
Empty,
|
|
// Compute is attached to some timeline / endpoint and
|
|
// should be able to start with provided spec.
|
|
Attached,
|
|
}
|