gsadmin/rustfs
1
0
Fork 0
mirror of https://github.com/rustfs/rustfs.git synced 2026-08-08 22:33:22 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(cluster): clarify peer health and listing timeouts (#5086)

Browse Source 
* fix(cluster): surface observed peer health

Refs rustfs/backlog#1387

Co-Authored-By: heihutu <heihutu@gmail.com>

* fix(admin): distinguish unreported peer health

Refs rustfs/backlog#1388

Co-Authored-By: heihutu <heihutu@gmail.com>

* fix(ecstore): decouple metacache peek timeout

Refs rustfs/backlog#1389

Co-Authored-By: heihutu <heihutu@gmail.com>

* docs(ops): diagnose metacache listing timeouts

Refs rustfs/backlog#1390

Co-Authored-By: heihutu <heihutu@gmail.com>

* refactor(cluster): clarify observed peer health

Co-Authored-By: heihutu <heihutu@gmail.com>

* fix(ecstore): route capability state through contract

Co-Authored-By: heihutu <heihutu@gmail.com>

---------

Co-authored-by: heihutu <heihutu@gmail.com>
This commit is contained in:
houseme
2026-07-21 19:11:24 +08:00
committed by GitHub
parent bb7bba3237
commit 7805cf5ae6
10 changed files with 349 additions and 45 deletions
Download Patch File Download Diff File Expand all files Collapse all files
rustfs/src/admin/handlers/cluster_snapshot.rs
+59
View File
@@ -564,8 +564,17 @@ fn summarize_peer_health(snapshot: &ClusterReadOnlySnapshot) -> CapabilityStatus
.iter()
.filter(|peer| peer.status.state == CapabilityState::Unknown)
.count();
let disabled = snapshot
.peer_health
.peers
.iter()
.filter(|peer| peer.status.state == CapabilityState::Disabled)
.count();
if unknown > 0 {
CapabilityStatus::unknown().with_reason(format!("cluster peer health has {unknown} unresolved peers"))
} else if disabled > 0 {
let noun = if disabled == 1 { "peer" } else { "peers" };
CapabilityStatus::disabled().with_reason(format!("cluster peer health is not reported by {disabled} {noun}"))
} else {
CapabilityStatus::supported().with_reason("cluster peer health resolved for all peers")
}
@@ -827,6 +836,56 @@ mod tests {
assert_eq!(summary.actionable_pressure.state, CapabilityState::Disabled);
}
#[test]
fn cluster_snapshot_summary_treats_not_reported_peer_health_as_disabled() {
let snapshot = ClusterReadOnlySnapshot {
topology: TopologySnapshot::default(),
membership: ClusterMembershipSnapshot {
nodes: vec![ClusterNodeMembership {
node_id: "node-a".to_string(),
grid_host: "node-a:9000".to_string(),
is_local: true,
pools: vec![0],
}],
drives: Vec::new(),
},
pool_state: ClusterPoolStateSnapshot::default(),
local_storage: ClusterLocalNodeStorageSnapshot::default(),
peer_health: ClusterPeerHealthSnapshot {
peers: vec![ClusterPeerHealth {
node_id: "node-a".to_string(),
is_local: true,
status: CapabilityStatus::disabled().with_reason("peer health not reported by endpoints"),
}],
},
rpc_boundary: sample_rpc_boundary_snapshot(),
observability: ObservabilitySnapshot::default(),
workload_admission: WorkloadAdmissionRegistrySnapshot::new(vec![WorkloadAdmissionSnapshot::new(
WorkloadClass::ForegroundRead,
AdmissionState::Open,
)]),
runtime_status: ClusterRuntimeStatusSnapshot {
readiness: DependencyReadiness {
storage_ready: true,
iam_ready: true,
lock_quorum_ready: true,
peer_health_ready: true,
},
state: ClusterRuntimeReadinessState::Ready,
degraded_reasons: Vec::new(),
},
};
let summary = ClusterSnapshotSummary::from(&snapshot);
assert_eq!(summary.peer_health.state, CapabilityState::Disabled);
assert_eq!(
summary.peer_health.reason.as_deref(),
Some("cluster peer health is not reported by 1 peer")
);
assert_eq!(summary.actionable_pressure.state, CapabilityState::Disabled);
}
fn sample_rpc_boundary_snapshot() -> ClusterRpcBoundarySnapshot {
ClusterRpcBoundarySnapshot {
control_channels: vec![ClusterRpcChannelSnapshot {