rust/neon
1
0
Fork 0
mirror of https://github.com/neondatabase/neon.git synced 2025-12-22 21:59:59 +00:00
Code Issues Packages Projects Releases Wiki Activity

[compute_tools] Add /insights endpoint to compute_ctl (#3704)

Browse Source 
This commit adds a basic HTTP API endpoint that allows scraping the
`pg_stat_statements` data and getting a list of slow queries. New
insights like cache hit rate and so on could be added later.

Extension `pg_stat_statements` is checked / created only if compute
tries to load the corresponding shared library. The latter is configured
by control-plane and currently covered with feature flag.

Co-authored by Eduard Dyckman (bird.duskpoet@gmail.com)
This commit is contained in:
Alexey Kondratov
2023-03-09 14:21:10 +01:00
committed by GitHub
parent 8459e0265e
commit e43c413a3f
5 changed files with 96 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

41
compute_tools/src/compute.rs
View File

@@ -25,6 +25,7 @@ use anyhow::{Context, Result};
use chrono::{DateTime, Utc};
use postgres::{Client, NoTls};
use serde::{Serialize, Serializer};
use tokio_postgres;
use tracing::{info, instrument, warn};
use crate::checker::create_writability_check_data;
@@ -284,6 +285,7 @@ impl ComputeNode {
handle_role_deletions(self, &mut client)?;
handle_grants(self, &mut client)?;
create_writability_check_data(&mut client)?;
handle_extensions(&self.spec, &mut client)?;
// 'Close' connection
drop(client);
@@ -400,4 +402,43 @@ impl ComputeNode {
Ok(())
}
/// Select `pg_stat_statements` data and return it as a stringified JSON
pub async fn collect_insights(&self) -> String {
let mut result_rows: Vec<String> = Vec::new();
let connect_result = tokio_postgres::connect(self.connstr.as_str(), NoTls).await;
let (client, connection) = connect_result.unwrap();
tokio::spawn(async move {
if let Err(e) = connection.await {
eprintln!("connection error: {}", e);
}
});
let result = client
.simple_query(
"SELECT
row_to_json(pg_stat_statements)
FROM
pg_stat_statements
WHERE
userid != 'cloud_admin'::regrole::oid
ORDER BY
(mean_exec_time + mean_plan_time) DESC
LIMIT 100",
)
.await;
if let Ok(raw_rows) = result {
for message in raw_rows.iter() {
if let postgres::SimpleQueryMessage::Row(row) = message {
if let Some(json) = row.get(0) {
result_rows.push(json.to_string());
}
}
}
format!("{{\"pg_stat_statements\": [{}]}}", result_rows.join(","))
} else {
"{{\"pg_stat_statements\": []}}".to_string()
}
}
}

7
compute_tools/src/http/api.rs
View File

@@ -33,6 +33,13 @@ async fn routes(req: Request<Body>, compute: &Arc<ComputeNode>) -> Response<Body
Response::new(Body::from(serde_json::to_string(&compute.metrics).unwrap()))
}
// Collect Postgres current usage insights
(&Method::GET, "/insights") => {
info!("serving /insights GET request");
let insights = compute.collect_insights().await;
Response::new(Body::from(insights))
}
(&Method::POST, "/check_writability") => {
info!("serving /check_writability POST request");
let res = crate::checker::check_writability(compute).await;

37
compute_tools/src/http/openapi_spec.yaml
View File

@@ -10,12 +10,12 @@ paths:
/status:
get:
tags:
- "info"
- Info
summary: Get compute node internal status
description: ""
operationId: getComputeStatus
responses:
"200":
200:
description: ComputeState
content:
application/json:
@@ -25,27 +25,43 @@ paths:
/metrics.json:
get:
tags:
- "info"
- Info
summary: Get compute node startup metrics in JSON format
description: ""
operationId: getComputeMetricsJSON
responses:
"200":
200:
description: ComputeMetrics
content:
application/json:
schema:
$ref: "#/components/schemas/ComputeMetrics"
/insights:
get:
tags:
- Info
summary: Get current compute insights in JSON format
description: |
Note, that this doesn't include any historical data
operationId: getComputeInsights
responses:
200:
description: Compute insights
content:
application/json:
schema:
$ref: "#/components/schemas/ComputeInsights"
/check_writability:
post:
tags:
- "check"
- Check
summary: Check that we can write new data on this compute
description: ""
operationId: checkComputeWritability
responses:
"200":
200:
description: Check result
content:
text/plain:
@@ -96,6 +112,15 @@ components:
type: string
description: Text of the error during compute startup, if any
ComputeInsights:
type: object
properties:
pg_stat_statements:
description: Contains raw output from pg_stat_statements in JSON format
type: array
items:
type: object
ComputeStatus:
type: string
enum:

2
compute_tools/src/pg_helpers.rs
View File

@@ -63,6 +63,8 @@ impl GenericOption {
/// Represent `GenericOption` as configuration option.
pub fn to_pg_setting(&self) -> String {
if let Some(val) = &self.value {
// TODO: check in the console DB that we don't have these settings
// set for any non-deleted project and drop this override.
let name = match self.name.as_str() {
"safekeepers" => "neon.safekeepers",
"wal_acceptor_reconnect" => "neon.safekeeper_reconnect_timeout",

15
compute_tools/src/spec.rs
View File

@@ -515,3 +515,18 @@ pub fn handle_grants(node: &ComputeNode, client: &mut Client) -> Result<()> {
Ok(())
}
/// Create required system extensions
#[instrument(skip_all)]
pub fn handle_extensions(spec: &ComputeSpec, client: &mut Client) -> Result<()> {
if let Some(libs) = spec.cluster.settings.find("shared_preload_libraries") {
if libs.contains("pg_stat_statements") {
// Create extension only if this compute really needs it
let query = "CREATE EXTENSION IF NOT EXISTS pg_stat_statements";
info!("creating system extensions with query: {}", query);
client.simple_query(query)?;
}
}
Ok(())
}