Report startup metrics and failure reason from compute_ctl (#1581)

+ neondatabase/cloud#1103 This adds a couple of control endpoints to simplify compute state discovery for control-plane. For example, now we may figure out that Postgres wasn't able to start or basebackup failed within seconds instead of just blindly polling the compute readiness for a minute or two. Also we now expose startup metrics (time of the each step: basebackup, sync safekeepers, config, total). Console grabs them after each successful start and report as histogram to prometheus and grafana. OpenAPI spec is added and up-tp date, but is not currently used in the console yet.
2026-05-26 01:20:38 +00:00 · 2022-05-09 19:45:28 +03:00
parent b9f84f4a83
commit 772c2fb4ff
18 changed files with 787 additions and 429 deletions
--- a/compute_tools/src/http/api.rs
+++ b/compute_tools/src/http/api.rs
@@ -0,0 +1,109 @@
+use std::convert::Infallible;
+use std::net::SocketAddr;
+use std::sync::Arc;
+use std::thread;
+
+use anyhow::Result;
+use hyper::service::{make_service_fn, service_fn};
+use hyper::{Body, Method, Request, Response, Server, StatusCode};
+use log::{error, info};
+use serde_json;
+
+use crate::compute::{ComputeNode, ComputeStatus};
+
+// Service function to handle all available routes.
+async fn routes(req: Request<Body>, compute: Arc<ComputeNode>) -> Response<Body> {
+    match (req.method(), req.uri().path()) {
+        // Timestamp of the last Postgres activity in the plain text.
+        // DEPRECATED in favour of /status
+        (&Method::GET, "/last_activity") => {
+            info!("serving /last_active GET request");
+            let state = compute.state.read().unwrap();
+
+            // Use RFC3339 format for consistency.
+            Response::new(Body::from(state.last_active.to_rfc3339()))
+        }
+
+        // Has compute setup process finished? -> true/false.
+        // DEPRECATED in favour of /status
+        (&Method::GET, "/ready") => {
+            info!("serving /ready GET request");
+            let status = compute.get_status();
+            Response::new(Body::from(format!("{}", status == ComputeStatus::Running)))
+        }
+
+        // Serialized compute state.
+        (&Method::GET, "/status") => {
+            info!("serving /status GET request");
+            let state = compute.state.read().unwrap();
+            Response::new(Body::from(serde_json::to_string(&*state).unwrap()))
+        }
+
+        // Startup metrics in JSON format. Keep /metrics reserved for a possible
+        // future use for Prometheus metrics format.
+        (&Method::GET, "/metrics.json") => {
+            info!("serving /metrics.json GET request");
+            Response::new(Body::from(serde_json::to_string(&compute.metrics).unwrap()))
+        }
+
+        // DEPRECATED, use POST instead
+        (&Method::GET, "/check_writability") => {
+            info!("serving /check_writability GET request");
+            let res = crate::checker::check_writability(&compute).await;
+            match res {
+                Ok(_) => Response::new(Body::from("true")),
+                Err(e) => Response::new(Body::from(e.to_string())),
+            }
+        }
+
+        (&Method::POST, "/check_writability") => {
+            info!("serving /check_writability POST request");
+            let res = crate::checker::check_writability(&compute).await;
+            match res {
+                Ok(_) => Response::new(Body::from("true")),
+                Err(e) => Response::new(Body::from(e.to_string())),
+            }
+        }
+
+        // Return the `404 Not Found` for any other routes.
+        _ => {
+            let mut not_found = Response::new(Body::from("404 Not Found"));
+            *not_found.status_mut() = StatusCode::NOT_FOUND;
+            not_found
+        }
+    }
+}
+
+// Main Hyper HTTP server function that runs it and blocks waiting on it forever.
+#[tokio::main]
+async fn serve(state: Arc<ComputeNode>) {
+    let addr = SocketAddr::from(([0, 0, 0, 0], 3080));
+
+    let make_service = make_service_fn(move |_conn| {
+        let state = state.clone();
+        async move {
+            Ok::<_, Infallible>(service_fn(move |req: Request<Body>| {
+                let state = state.clone();
+                async move { Ok::<_, Infallible>(routes(req, state).await) }
+            }))
+        }
+    });
+
+    info!("starting HTTP server on {}", addr);
+
+    let server = Server::bind(&addr).serve(make_service);
+
+    // Run this server forever
+    if let Err(e) = server.await {
+        error!("server error: {}", e);
+    }
+}
+
+/// Launch a separate Hyper HTTP API server thread and return its `JoinHandle`.
+pub fn launch_http_server(state: &Arc<ComputeNode>) -> Result<thread::JoinHandle<()>> {
+    let state = Arc::clone(state);
+
+    Ok(thread::Builder::new()
+        .name("http-endpoint".into())
+        .spawn(move || serve(state))?)
+}
--- a/compute_tools/src/http/mod.rs
+++ b/compute_tools/src/http/mod.rs
@@ -0,0 +1 @@
+pub mod api;
--- a/compute_tools/src/http/openapi_spec.yaml
+++ b/compute_tools/src/http/openapi_spec.yaml
@@ -0,0 +1,158 @@
+openapi: "3.0.2"
+info:
+  title: Compute node control API
+  version: "1.0"
+
+servers:
+  - url: "http://localhost:3080"
+
+paths:
+  /status:
+    get:
+      tags:
+      - "info"
+      summary: Get compute node internal status
+      description: ""
+      operationId: getComputeStatus
+      responses:
+        "200":
+          description: ComputeState
+          content:
+            application/json:
+              schema:
+                $ref: "#/components/schemas/ComputeState"
+
+  /metrics.json:
+    get:
+      tags:
+      - "info"
+      summary: Get compute node startup metrics in JSON format
+      description: ""
+      operationId: getComputeMetricsJSON
+      responses:
+        "200":
+          description: ComputeMetrics
+          content:
+            application/json:
+              schema:
+                $ref: "#/components/schemas/ComputeMetrics"
+
+  /ready:
+    get:
+      deprecated: true
+      tags:
+      - "info"
+      summary: Check whether compute startup process finished successfully
+      description: ""
+      operationId: computeIsReady
+      responses:
+        "200":
+          description: Compute is ready ('true') or not ('false')
+          content:
+            text/plain:
+              schema:
+                type: string
+                example: "true"
+
+  /last_activity:
+    get:
+      deprecated: true
+      tags:
+      - "info"
+      summary: Get timestamp of the last compute activity
+      description: ""
+      operationId: getLastComputeActivityTS
+      responses:
+        "200":
+          description: Timestamp of the last compute activity
+          content:
+            text/plain:
+              schema:
+                type: string
+                example: "2022-10-12T07:20:50.52Z"
+
+  /check_writability:
+    get:
+      deprecated: true
+      tags:
+      - "check"
+      summary: Check that we can write new data on this compute
+      description: ""
+      operationId: checkComputeWritabilityDeprecated
+      responses:
+        "200":
+          description: Check result
+          content:
+            text/plain:
+              schema:
+                type: string
+                description: Error text or 'true' if check passed
+                example: "true"
+
+    post:
+      tags:
+      - "check"
+      summary: Check that we can write new data on this compute
+      description: ""
+      operationId: checkComputeWritability
+      responses:
+        "200":
+          description: Check result
+          content:
+            text/plain:
+              schema:
+                type: string
+                description: Error text or 'true' if check passed
+                example: "true"
+
+components:
+  securitySchemes:
+    JWT:
+      type: http
+      scheme: bearer
+      bearerFormat: JWT
+
+  schemas:
+    ComputeMetrics:
+      type: object
+      description: Compute startup metrics
+      required:
+        - sync_safekeepers_ms
+        - basebackup_ms
+        - config_ms
+        - total_startup_ms
+      properties:
+        sync_safekeepers_ms:
+          type: integer
+        basebackup_ms:
+          type: integer
+        config_ms:
+          type: integer
+        total_startup_ms:
+          type: integer
+
+    ComputeState:
+      type: object
+      required:
+        - status
+        - last_active
+      properties:
+        status:
+          $ref: '#/components/schemas/ComputeStatus'
+        last_active:
+          type: string
+          description: The last detected compute activity timestamp in UTC and RFC3339 format
+          example: "2022-10-12T07:20:50.52Z"
+        error:
+          type: string
+          description: Text of the error during compute startup, if any
+
+    ComputeStatus:
+      type: string
+      enum:
+        - init
+        - failed
+        - running
+
+security:
+  - JWT: []