mirror of
https://github.com/neondatabase/neon.git
synced 2026-05-30 19:40:39 +00:00
storcon: do not update observed state on node activation (#11155)
## Problem When a node becomes active, we query its locations and update the observed state in-place. This can race with the observed state updates done when processing reconcile results. ## Summary of changes The argument for this reconciliation step is that is reduces the need for background reconciliations. I don't think is actually true anymore. There's two cases. 1. Restart of node after drain. Usually the node does not go through the offline state here, so observed locations were not marked as none. In any case, there should be a handful of shards max on the node since we've just drained it. 2. Node comes back online after failure or network partition. When the node is marked offline, we reschedule everything away from it. When it later becomes active, the previous observed location is extraneous and requires a reconciliation anyway. Closes https://github.com/neondatabase/neon/issues/11148
This commit is contained in:
@@ -36,7 +36,9 @@ use pageserver_api::config::{
|
||||
use pageserver_api::controller_api::{
|
||||
NodeAvailabilityWrapper, PlacementPolicy, TenantCreateRequest,
|
||||
};
|
||||
use pageserver_api::models::{ShardParameters, TimelineCreateRequest, TimelineInfo};
|
||||
use pageserver_api::models::{
|
||||
ShardParameters, TenantConfigRequest, TimelineCreateRequest, TimelineInfo,
|
||||
};
|
||||
use pageserver_api::shard::{ShardCount, ShardStripeSize, TenantShardId};
|
||||
use postgres_backend::AuthType;
|
||||
use postgres_connection::parse_host_port;
|
||||
@@ -1129,12 +1131,16 @@ async fn handle_tenant(subcmd: &TenantCmd, env: &mut local_env::LocalEnv) -> any
|
||||
let tenant_id = get_tenant_id(args.tenant_id, env)?;
|
||||
let tenant_conf: HashMap<_, _> =
|
||||
args.config.iter().flat_map(|c| c.split_once(':')).collect();
|
||||
let config = PageServerNode::parse_config(tenant_conf)?;
|
||||
|
||||
pageserver
|
||||
.tenant_config(tenant_id, tenant_conf)
|
||||
let req = TenantConfigRequest { tenant_id, config };
|
||||
|
||||
let storage_controller = StorageController::from_env(env);
|
||||
storage_controller
|
||||
.set_tenant_config(&req)
|
||||
.await
|
||||
.with_context(|| format!("Tenant config failed for tenant with id {tenant_id}"))?;
|
||||
println!("tenant {tenant_id} successfully configured on the pageserver");
|
||||
println!("tenant {tenant_id} successfully configured via storcon");
|
||||
}
|
||||
}
|
||||
Ok(())
|
||||
|
||||
@@ -14,7 +14,7 @@ use pageserver_api::controller_api::{
|
||||
NodeConfigureRequest, NodeDescribeResponse, NodeRegisterRequest, TenantCreateRequest,
|
||||
TenantCreateResponse, TenantLocateResponse,
|
||||
};
|
||||
use pageserver_api::models::{TimelineCreateRequest, TimelineInfo};
|
||||
use pageserver_api::models::{TenantConfigRequest, TimelineCreateRequest, TimelineInfo};
|
||||
use pageserver_api::shard::TenantShardId;
|
||||
use pageserver_client::mgmt_api::ResponseErrorMessageExt;
|
||||
use postgres_backend::AuthType;
|
||||
@@ -878,4 +878,9 @@ impl StorageController {
|
||||
)
|
||||
.await
|
||||
}
|
||||
|
||||
pub async fn set_tenant_config(&self, req: &TenantConfigRequest) -> anyhow::Result<()> {
|
||||
self.dispatch(Method::PUT, "v1/tenant/config".to_string(), Some(req))
|
||||
.await
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user