mirror of
https://github.com/neondatabase/neon.git
synced 2026-08-18 03:58:19 +00:00
storage controller: check warmth of secondary before doing proactive migration (#7583)
## Problem The logic in Service::optimize_all would sometimes choose to migrate a tenant to a secondary location that was only recently created, resulting in Reconciler::live_migrate hitting its 5 minute timeout warming up the location, and proceeding to attach a tenant to a location that doesn't have a warm enough local set of layer files for good performance. Closes: #7532 ## Summary of changes - Add a pageserver API for checking download progress of a secondary location - During `optimize_all`, connect to pageservers of candidate optimization secondary locations, and check they are warm. - During shard split, do heatmap uploads and start secondary downloads, so that the new shards' secondary locations start downloading ASAP, rather than waiting minutes for background downloads to kick in. I have intentionally not implemented this by continuously reading the status of locations, to avoid dealing with the scale challenge of efficiently polling & updating 10k-100k locations status. If we implement that in the future, then this code can be simplified to act based on latest state of a location rather than fetching it inline during optimize_all.
This commit is contained in:
@@ -2160,6 +2160,27 @@ async fn secondary_download_handler(
|
||||
json_response(status, progress)
|
||||
}
|
||||
|
||||
async fn secondary_status_handler(
|
||||
request: Request<Body>,
|
||||
_cancel: CancellationToken,
|
||||
) -> Result<Response<Body>, ApiError> {
|
||||
let state = get_state(&request);
|
||||
let tenant_shard_id: TenantShardId = parse_request_param(&request, "tenant_shard_id")?;
|
||||
|
||||
let Some(secondary_tenant) = state
|
||||
.tenant_manager
|
||||
.get_secondary_tenant_shard(tenant_shard_id)
|
||||
else {
|
||||
return Err(ApiError::NotFound(
|
||||
anyhow::anyhow!("Shard {} not found", tenant_shard_id).into(),
|
||||
));
|
||||
};
|
||||
|
||||
let progress = secondary_tenant.progress.lock().unwrap().clone();
|
||||
|
||||
json_response(StatusCode::OK, progress)
|
||||
}
|
||||
|
||||
async fn handler_404(_: Request<Body>) -> Result<Response<Body>, ApiError> {
|
||||
json_response(
|
||||
StatusCode::NOT_FOUND,
|
||||
@@ -2521,6 +2542,9 @@ pub fn make_router(
|
||||
.put("/v1/deletion_queue/flush", |r| {
|
||||
api_handler(r, deletion_queue_flush)
|
||||
})
|
||||
.get("/v1/tenant/:tenant_shard_id/secondary/status", |r| {
|
||||
api_handler(r, secondary_status_handler)
|
||||
})
|
||||
.post("/v1/tenant/:tenant_shard_id/secondary/download", |r| {
|
||||
api_handler(r, secondary_download_handler)
|
||||
})
|
||||
|
||||
Reference in New Issue
Block a user