mirror of
https://github.com/neondatabase/neon.git
synced 2026-05-22 07:30:37 +00:00
Introduce built-in Prometheus exporter to the Postgres extension (#12591)
Currently, the exporter exposes the same LFC metrics that are exposed by the "autoscaling" sql_exporter in the docker image. With this, we can remove the dedicated sql_exporter instance. (Actually doing the removal is left as a TODO until this is rolled out to production and we have changed autoscaling-agent to fetch the metrics from this new endpoint.) The exporter runs as a Postgres background worker process. This is extracted from the Rust communicator rewrite project, which will use the same worker process for much more, to handle the communications with the pageservers. For now, though, it merely handles the metrics requests. In the future, we will add more metrics, and perhaps even APIs to control the running Postgres instance. The exporter listens on a Unix Domain socket within the Postgres data directory. A Unix Domain socket is a bit unconventional, but it has some advantages: - Permissions are taken care of. Only processes that can access the data directory, and therefore already have full access to the running Postgres instance, can connect to it. - No need to allocate and manage a new port number for the listener It has some downsides too: it's not immediately accessible from the outside world, and the functions to work with Unix Domain sockets are more low-level than TCP sockets (see the symlink hack in `postgres_metrics_client.rs`, for example). To expose the metrics from the local Unix Domain Socket to the autoscaling agent, introduce a new '/autoscaling_metrics' endpoint in the compute_ctl's HTTP server. Currently it merely forwards the request to the Postgres instance, but we could add rate limiting and access control there in the future. --------- Co-authored-by: Conrad Ludgate <conrad@neon.tech>
This commit is contained in:
committed by
GitHub
parent
88bc06f148
commit
8bb45fd5da
@@ -1,10 +1,18 @@
|
||||
use std::path::Path;
|
||||
use std::sync::Arc;
|
||||
|
||||
use anyhow::Context;
|
||||
use axum::body::Body;
|
||||
use axum::extract::State;
|
||||
use axum::response::Response;
|
||||
use http::StatusCode;
|
||||
use http::header::CONTENT_TYPE;
|
||||
use http_body_util::BodyExt;
|
||||
use hyper::{Request, StatusCode};
|
||||
use metrics::proto::MetricFamily;
|
||||
use metrics::{Encoder, TextEncoder};
|
||||
|
||||
use crate::communicator_socket_client::connect_communicator_socket;
|
||||
use crate::compute::ComputeNode;
|
||||
use crate::http::JsonResponse;
|
||||
use crate::metrics::collect;
|
||||
|
||||
@@ -31,3 +39,42 @@ pub(in crate::http) async fn get_metrics() -> Response {
|
||||
.body(Body::from(buffer))
|
||||
.unwrap()
|
||||
}
|
||||
|
||||
/// Fetch and forward metrics from the Postgres neon extension's metrics
|
||||
/// exporter that are used by autoscaling-agent.
|
||||
///
|
||||
/// The neon extension exposes these metrics over a Unix domain socket
|
||||
/// in the data directory. That's not accessible directly from the outside
|
||||
/// world, so we have this endpoint in compute_ctl to expose it
|
||||
pub(in crate::http) async fn get_autoscaling_metrics(
|
||||
State(compute): State<Arc<ComputeNode>>,
|
||||
) -> Result<Response, Response> {
|
||||
let pgdata = Path::new(&compute.params.pgdata);
|
||||
|
||||
// Connect to the communicator process's metrics socket
|
||||
let mut metrics_client = connect_communicator_socket(pgdata)
|
||||
.await
|
||||
.map_err(|e| JsonResponse::error(StatusCode::INTERNAL_SERVER_ERROR, format!("{e:#}")))?;
|
||||
|
||||
// Make a request for /autoscaling_metrics
|
||||
let request = Request::builder()
|
||||
.method("GET")
|
||||
.uri("/autoscaling_metrics")
|
||||
.header("Host", "localhost") // hyper requires Host, even though the server won't care
|
||||
.body(Body::from(""))
|
||||
.unwrap();
|
||||
let resp = metrics_client
|
||||
.send_request(request)
|
||||
.await
|
||||
.context("fetching metrics from Postgres metrics service")
|
||||
.map_err(|e| JsonResponse::error(StatusCode::INTERNAL_SERVER_ERROR, format!("{e:#}")))?;
|
||||
|
||||
// Build a response that just forwards the response we got.
|
||||
let mut response = Response::builder();
|
||||
response = response.status(resp.status());
|
||||
if let Some(content_type) = resp.headers().get(CONTENT_TYPE) {
|
||||
response = response.header(CONTENT_TYPE, content_type);
|
||||
}
|
||||
let body = tonic::service::AxumBody::from_stream(resp.into_body().into_data_stream());
|
||||
Ok(response.body(body).unwrap())
|
||||
}
|
||||
|
||||
@@ -81,8 +81,12 @@ impl From<&Server> for Router<Arc<ComputeNode>> {
|
||||
Server::External {
|
||||
config, compute_id, ..
|
||||
} => {
|
||||
let unauthenticated_router =
|
||||
Router::<Arc<ComputeNode>>::new().route("/metrics", get(metrics::get_metrics));
|
||||
let unauthenticated_router = Router::<Arc<ComputeNode>>::new()
|
||||
.route("/metrics", get(metrics::get_metrics))
|
||||
.route(
|
||||
"/autoscaling_metrics",
|
||||
get(metrics::get_autoscaling_metrics),
|
||||
);
|
||||
|
||||
let authenticated_router = Router::<Arc<ComputeNode>>::new()
|
||||
.route("/lfc/prewarm", get(lfc::prewarm_state).post(lfc::prewarm))
|
||||
|
||||
Reference in New Issue
Block a user