Files
neon/storage_controller/src/safekeeper_client.rs
Arpad Müller 536bdb3209 storcon: track safekeepers in memory, send heartbeats to them (#10583)
In #9011, we want to schedule timelines to safekeepers. In order to do
such scheduling, we need information about how utilized a safekeeper is
and if it's available or not.

Therefore, send constant heartbeats to the safekeepers and try to figure
out if they are online or not.

Includes some code from #10440.
2025-02-13 11:06:30 +00:00

106 lines
3.0 KiB
Rust

use crate::metrics::PageserverRequestLabelGroup;
use safekeeper_api::models::{SafekeeperUtilization, TimelineCreateRequest, TimelineStatus};
use safekeeper_client::mgmt_api::{Client, Result};
use utils::{
id::{NodeId, TenantId, TimelineId},
logging::SecretString,
};
/// Thin wrapper around [`safekeeper_client::mgmt_api::Client`]. It allows the storage
/// controller to collect metrics in a non-intrusive manner.
///
/// Analogous to [`crate::pageserver_client::PageserverClient`].
#[derive(Debug, Clone)]
pub(crate) struct SafekeeperClient {
inner: Client,
node_id_label: String,
}
macro_rules! measured_request {
($name:literal, $method:expr, $node_id: expr, $invoke:expr) => {{
let labels = PageserverRequestLabelGroup {
pageserver_id: $node_id,
path: $name,
method: $method,
};
let latency = &crate::metrics::METRICS_REGISTRY
.metrics_group
.storage_controller_safekeeper_request_latency;
let _timer_guard = latency.start_timer(labels.clone());
let res = $invoke;
if res.is_err() {
let error_counters = &crate::metrics::METRICS_REGISTRY
.metrics_group
.storage_controller_pageserver_request_error;
error_counters.inc(labels)
}
res
}};
}
impl SafekeeperClient {
#[allow(dead_code)]
pub(crate) fn new(
node_id: NodeId,
mgmt_api_endpoint: String,
jwt: Option<SecretString>,
) -> Self {
Self {
inner: Client::from_client(reqwest::Client::new(), mgmt_api_endpoint, jwt),
node_id_label: node_id.0.to_string(),
}
}
pub(crate) fn from_client(
node_id: NodeId,
raw_client: reqwest::Client,
mgmt_api_endpoint: String,
jwt: Option<SecretString>,
) -> Self {
Self {
inner: Client::from_client(raw_client, mgmt_api_endpoint, jwt),
node_id_label: node_id.0.to_string(),
}
}
#[allow(dead_code)]
pub(crate) async fn create_timeline(
&self,
req: &TimelineCreateRequest,
) -> Result<TimelineStatus> {
measured_request!(
"create_timeline",
crate::metrics::Method::Post,
&self.node_id_label,
self.inner.create_timeline(req).await
)
}
#[allow(dead_code)]
pub(crate) async fn delete_timeline(
&self,
tenant_id: TenantId,
timeline_id: TimelineId,
) -> Result<TimelineStatus> {
measured_request!(
"delete_timeline",
crate::metrics::Method::Delete,
&self.node_id_label,
self.inner.delete_timeline(tenant_id, timeline_id).await
)
}
pub(crate) async fn get_utilization(&self) -> Result<SafekeeperUtilization> {
measured_request!(
"utilization",
crate::metrics::Method::Get,
&self.node_id_label,
self.inner.utilization().await
)
}
}