mirror of
https://github.com/neondatabase/neon.git
synced 2026-05-21 23:20:40 +00:00
storcon: Introduce deletion tombstones to support flaky node scenario (#12096)
## Problem Removed nodes can re-add themselves on restart if not properly tombstoned. We need a mechanism (e.g. soft-delete flag) to prevent this, especially in cases where the node is unreachable. More details there: #12036 ## Summary of changes - Introduced `NodeLifecycle` enum to represent node lifecycle states. - Added a string representation of `NodeLifecycle` to the `nodes` table. - Implemented node removal using a tombstone mechanism. - Introduced `/debug/v1/tombstone*` handlers to manage the tombstone state.
This commit is contained in:
committed by
Alex Chi Z
parent
72b09473c1
commit
765b76f4cd
@@ -61,10 +61,16 @@ enum Command {
|
||||
#[arg(long)]
|
||||
scheduling: Option<NodeSchedulingPolicy>,
|
||||
},
|
||||
// Set a node status as deleted.
|
||||
NodeDelete {
|
||||
#[arg(long)]
|
||||
node_id: NodeId,
|
||||
},
|
||||
/// Delete a tombstone of node from the storage controller.
|
||||
NodeDeleteTombstone {
|
||||
#[arg(long)]
|
||||
node_id: NodeId,
|
||||
},
|
||||
/// Modify a tenant's policies in the storage controller
|
||||
TenantPolicy {
|
||||
#[arg(long)]
|
||||
@@ -82,6 +88,8 @@ enum Command {
|
||||
},
|
||||
/// List nodes known to the storage controller
|
||||
Nodes {},
|
||||
/// List soft deleted nodes known to the storage controller
|
||||
NodeTombstones {},
|
||||
/// List tenants known to the storage controller
|
||||
Tenants {
|
||||
/// If this field is set, it will list the tenants on a specific node
|
||||
@@ -900,6 +908,39 @@ async fn main() -> anyhow::Result<()> {
|
||||
.dispatch::<(), ()>(Method::DELETE, format!("control/v1/node/{node_id}"), None)
|
||||
.await?;
|
||||
}
|
||||
Command::NodeDeleteTombstone { node_id } => {
|
||||
storcon_client
|
||||
.dispatch::<(), ()>(
|
||||
Method::DELETE,
|
||||
format!("debug/v1/tombstone/{node_id}"),
|
||||
None,
|
||||
)
|
||||
.await?;
|
||||
}
|
||||
Command::NodeTombstones {} => {
|
||||
let mut resp = storcon_client
|
||||
.dispatch::<(), Vec<NodeDescribeResponse>>(
|
||||
Method::GET,
|
||||
"debug/v1/tombstone".to_string(),
|
||||
None,
|
||||
)
|
||||
.await?;
|
||||
|
||||
resp.sort_by(|a, b| a.listen_http_addr.cmp(&b.listen_http_addr));
|
||||
|
||||
let mut table = comfy_table::Table::new();
|
||||
table.set_header(["Id", "Hostname", "AZ", "Scheduling", "Availability"]);
|
||||
for node in resp {
|
||||
table.add_row([
|
||||
format!("{}", node.id),
|
||||
node.listen_http_addr,
|
||||
node.availability_zone_id,
|
||||
format!("{:?}", node.scheduling),
|
||||
format!("{:?}", node.availability),
|
||||
]);
|
||||
}
|
||||
println!("{table}");
|
||||
}
|
||||
Command::TenantSetTimeBasedEviction {
|
||||
tenant_id,
|
||||
period,
|
||||
|
||||
Reference in New Issue
Block a user