rust/neon
1
0
Fork 0
mirror of https://github.com/neondatabase/neon.git synced 2026-01-05 20:42:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

Hopefully stabilize test_bad_connection.py (#6976)

Browse Source 
## Problem
It seems that even though we have a retry on basebackup, it still
sometimes fails to fetch it with the failpoint enabled, resulting in a
test error.

## Summary of changes
If we fail to get the basebackup, disable the failpoint and try again.
This commit is contained in:
Sasha Krassovsky
2024-03-07 09:12:06 -09:00
committed by GitHub
parent ce7a82db05
commit 2fc89428c3
2 changed files with 5 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
compute_tools/src/compute.rs
View File

@@ -396,9 +396,9 @@ impl ComputeNode {
// Gets the basebackup in a retry loop
#[instrument(skip_all, fields(%lsn))]
pub fn get_basebackup(&self, compute_state: &ComputeState, lsn: Lsn) -> Result<()> {
let mut retry_period_ms = 500;
let mut retry_period_ms = 500.0;
let mut attempts = 0;
let max_attempts = 5;
let max_attempts = 10;
loop {
let result = self.try_get_basebackup(compute_state, lsn);
match result {
@@ -410,8 +410,8 @@ impl ComputeNode {
"Failed to get basebackup: {} (attempt {}/{})",
e, attempts, max_attempts
);
std::thread::sleep(std::time::Duration::from_millis(retry_period_ms));
retry_period_ms *= 2;
std::thread::sleep(std::time::Duration::from_millis(retry_period_ms as u64));
retry_period_ms *= 1.5;
}
Err(_) => {
return result;

2
control_plane/src/endpoint.rs
View File

@@ -656,7 +656,7 @@ impl Endpoint {
// Wait for it to start
let mut attempt = 0;
const ATTEMPT_INTERVAL: Duration = Duration::from_millis(100);
const MAX_ATTEMPTS: u32 = 10 * 30; // Wait up to 30 s
const MAX_ATTEMPTS: u32 = 10 * 90; // Wait up to 1.5 min
loop {
attempt += 1;
match self.get_status().await {