Files
neon/compute_tools/src/checker.rs
Konstantin Knizhnik f64b338ce3 Ingore DISK_FULL error when performing availability check for client (#5010)
See #5001

No space is what's expected if we're at size limit.
Of course if SK incorrectly returned "no space", the availability check
wouldn't fire.
But  users would notice such a bug quite soon anyways.
So  ignoring "no space" is the right trade-off.


## Problem

## Summary of changes

## Checklist before requesting a review

- [ ] I have performed a self-review of my code.
- [ ] If it is a core feature, I have added thorough tests.
- [ ] Do we need to implement analytics? if so did you add the relevant
metrics to the dashboard?
- [ ] If this PR requires public announcement, mark it with
/release-notes label and add several sentences in this section.

## Checklist before merging

- [ ] Do not forget to reformat commit message to not include the above
checklist

---------

Co-authored-by: Konstantin Knizhnik <knizhnik@neon.tech>
Co-authored-by: Joonas Koivunen <joonas@neon.tech>
2023-09-09 21:51:04 +03:00

80 lines
2.3 KiB
Rust

use anyhow::{anyhow, Ok, Result};
use postgres::Client;
use tokio_postgres::NoTls;
use tracing::{error, instrument, warn};
use crate::compute::ComputeNode;
/// Create a special service table for availability checks
/// only if it does not exist already.
pub fn create_availability_check_data(client: &mut Client) -> Result<()> {
let query = "
DO $$
BEGIN
IF NOT EXISTS(
SELECT 1
FROM pg_catalog.pg_tables
WHERE tablename = 'health_check'
)
THEN
CREATE TABLE health_check (
id serial primary key,
updated_at timestamptz default now()
);
INSERT INTO health_check VALUES (1, now())
ON CONFLICT (id) DO UPDATE
SET updated_at = now();
END IF;
END
$$;";
client.execute(query, &[])?;
Ok(())
}
/// Update timestamp in a row in a special service table to check
/// that we can actually write some data in this particular timeline.
#[instrument(skip_all)]
pub async fn check_writability(compute: &ComputeNode) -> Result<()> {
// Connect to the database.
let (client, connection) = tokio_postgres::connect(compute.connstr.as_str(), NoTls).await?;
if client.is_closed() {
return Err(anyhow!("connection to postgres closed"));
}
// The connection object performs the actual communication with the database,
// so spawn it off to run on its own.
tokio::spawn(async move {
if let Err(e) = connection.await {
error!("connection error: {}", e);
}
});
let query = "
INSERT INTO health_check VALUES (1, now())
ON CONFLICT (id) DO UPDATE
SET updated_at = now();";
match client.simple_query(query).await {
Result::Ok(result) => {
if result.len() != 1 {
return Err(anyhow::anyhow!(
"expected 1 query results, but got {}",
result.len()
));
}
}
Err(err) => {
if let Some(state) = err.code() {
if state == &tokio_postgres::error::SqlState::DISK_FULL {
warn!("Tenant disk is full");
return Ok(());
}
}
return Err(err.into());
}
}
Ok(())
}