Files
neon/control_plane/src/broker.rs
Peter Bendel 82266a252c Allow longer timeout for starting pageserver, safe keeper and storage controller in test cases to make test cases less flaky (#8079)
## Problem

see https://github.com/neondatabase/neon/issues/8070

## Summary of changes

the neon_local subcommands to 
- start neon
- start pageserver
- start safekeeper
- start storage controller

get a new option -t=xx or --start-timeout=xx which allows to specify a
longer timeout in seconds we wait for the process start.
This is useful in test cases where the pageserver has to read a lot of
layer data, like in pagebench test cases.

In addition we exploit the new timeout option in the python test
infrastructure (python fixtures) and modify the flaky testcase to
increase the timeout from 10 seconds to 1 minute.

Example from the test execution

```bash
RUST_BACKTRACE=1 NEON_ENV_BUILDER_USE_OVERLAYFS_FOR_SNAPSHOTS=1 DEFAULT_PG_VERSION=15 BUILD_TYPE=release     ./scripts/pytest test_runner/performance/pageserver/pagebench/test_pageserver_max_throughput_getpage_at_latest_lsn.py
...
2024-06-19 09:29:34.590 INFO [neon_fixtures.py:1513] Running command "/instance_store/neon/target/release/neon_local storage_controller start --start-timeout=60s"
2024-06-19 09:29:36.365 INFO [broker.py:34] starting storage_broker to listen incoming connections at "127.0.0.1:15001"
2024-06-19 09:29:36.365 INFO [neon_fixtures.py:1513] Running command "/instance_store/neon/target/release/neon_local pageserver start --id=1 --start-timeout=60s"
2024-06-19 09:29:36.366 INFO [neon_fixtures.py:1513] Running command "/instance_store/neon/target/release/neon_local safekeeper start 1 --start-timeout=60s"
```
2024-06-21 10:36:12 +00:00

64 lines
1.9 KiB
Rust

//! Code to manage the storage broker
//!
//! In the local test environment, the data for each safekeeper is stored in
//!
//! ```text
//! .neon/safekeepers/<safekeeper id>
//! ```
use std::time::Duration;
use anyhow::Context;
use camino::Utf8PathBuf;
use crate::{background_process, local_env};
pub async fn start_broker_process(
env: &local_env::LocalEnv,
retry_timeout: &Duration,
) -> anyhow::Result<()> {
let broker = &env.broker;
let listen_addr = &broker.listen_addr;
print!("Starting neon broker at {}", listen_addr);
let args = [format!("--listen-addr={listen_addr}")];
let client = reqwest::Client::new();
background_process::start_process(
"storage_broker",
&env.base_data_dir,
&env.storage_broker_bin(),
args,
[],
background_process::InitialPidFile::Create(storage_broker_pid_file_path(env)),
retry_timeout,
|| async {
let url = broker.client_url();
let status_url = url.join("status").with_context(|| {
format!("Failed to append /status path to broker endpoint {url}")
})?;
let request = client
.get(status_url)
.build()
.with_context(|| format!("Failed to construct request to broker endpoint {url}"))?;
match client.execute(request).await {
Ok(resp) => Ok(resp.status().is_success()),
Err(_) => Ok(false),
}
},
)
.await
.context("Failed to spawn storage_broker subprocess")?;
Ok(())
}
pub fn stop_broker_process(env: &local_env::LocalEnv) -> anyhow::Result<()> {
background_process::stop_process(true, "storage_broker", &storage_broker_pid_file_path(env))
}
fn storage_broker_pid_file_path(env: &local_env::LocalEnv) -> Utf8PathBuf {
Utf8PathBuf::from_path_buf(env.base_data_dir.join("storage_broker.pid"))
.expect("non-Unicode path")
}