gsadmin/rustfs
1
0
Fork 0
mirror of https://github.com/rustfs/rustfs.git synced 2026-09-07 12:35:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat(tier): report cluster tier stats and count tier requests (#7110)

Browse Source 
`GET /v3/tier-stats` answered from whichever process received the
request, returning that node's rolling 24-hour transition counters as
if they were cluster totals, and the `TierRequestsSuccess` and
`TierRequestsFailure` metric names had no producer at all.

The body now separates the two quantities a tier carries. Stored
inventory comes from the persisted scanner usage snapshot, which is
already cluster-wide; rolling activity is summed over every member
through a new read-only `TierDailyStats` peer RPC. Rings are merged
rather than added, so an idle node's expired hours age out, and each
node counts only its own committed transitions, so a retry is counted
once. Coverage travels with the numbers: `activity.status` names the
reporting members and the ones that could not be asked, timed out, or
answered with a ring this build refuses to merge, and per-tier
inventory is absent rather than zero when the snapshot has no
accounting. The version 1 body stays reachable at `?format=legacy`.

Tier request counters are recorded at the two seams every remote
request passes through, so a new provider is counted by construction,
with a closed operation/outcome label set that can never grow a tier
name, endpoint or object key.

Closes rustfs/backlog#2207

Co-authored-by: cxymds <cxymds@gmail.com>
This commit is contained in:
Zhengchao An
2026-09-04 09:40:03 +08:00
committed by GitHub
parent 7dfc2ee5f0
commit 9863f4848d
27 changed files with 1844 additions and 46 deletions
Download Patch File Download Diff File Expand all files Collapse all files
crates/protos/src/generated/proto_gen/node_service.rs
+66
View File
@@ -1482,6 +1482,25 @@ pub struct LoadTransitionTierConfigResponse {
#[prost(enumeration = "ControlPlaneErrorCode", optional, tag = "3")]
pub error_code: ::core::option::Option<i32>,
}
#[derive(Clone, Copy, PartialEq, Eq, Hash, ::prost::Message)]
pub struct TierDailyStatsRequest {}
/// One node's own rolling-day transition counters, per remote tier.
///
/// `tier_daily_stats` is a msgpack map of tier name to the responder's 24-bin
/// ring plus the clock that ring was last aged to. A node counts only the
/// transitions it completed itself, so a caller sums the rings of every node to
/// obtain a cluster total. A peer that does not implement this RPC answers
/// UNIMPLEMENTED, which the caller reports as a non-reporting node rather than
/// as zero activity.
#[derive(Clone, PartialEq, Eq, Hash, ::prost::Message)]
pub struct TierDailyStatsResponse {
#[prost(bool, tag = "1")]
pub success: bool,
#[prost(bytes = "bytes", tag = "2")]
pub tier_daily_stats: ::prost::bytes::Bytes,
#[prost(string, optional, tag = "3")]
pub error_info: ::core::option::Option<::prost::alloc::string::String>,
}
#[derive(Clone, PartialEq, Eq, Hash, ::prost::Message)]
pub struct TierMutationPrepareRequest {
#[prost(uint32, tag = "1")]
@@ -3075,6 +3094,21 @@ pub mod node_service_client {
.insert(GrpcMethod::new("node_service.NodeService", "LoadTransitionTierConfig"));
self.inner.unary(req, path, codec).await
}
pub async fn tier_daily_stats(
&mut self,
request: impl tonic::IntoRequest<super::TierDailyStatsRequest>,
) -> std::result::Result<tonic::Response<super::TierDailyStatsResponse>, tonic::Status> {
self.inner
.ready()
.await
.map_err(|e| tonic::Status::unknown(format!("Service was not ready: {}", e.into())))?;
let codec = tonic_prost::ProstCodec::default();
let path = http::uri::PathAndQuery::from_static("/node_service.NodeService/TierDailyStats");
let mut req = request.into_request();
req.extensions_mut()
.insert(GrpcMethod::new("node_service.NodeService", "TierDailyStats"));
self.inner.unary(req, path, codec).await
}
pub async fn get_live_events(
&mut self,
request: impl tonic::IntoRequest<super::GetLiveEventsRequest>,
@@ -3475,6 +3509,10 @@ pub mod node_service_server {
&self,
request: tonic::Request<super::LoadTransitionTierConfigRequest>,
) -> std::result::Result<tonic::Response<super::LoadTransitionTierConfigResponse>, tonic::Status>;
async fn tier_daily_stats(
&self,
request: tonic::Request<super::TierDailyStatsRequest>,
) -> std::result::Result<tonic::Response<super::TierDailyStatsResponse>, tonic::Status>;
async fn get_live_events(
&self,
request: tonic::Request<super::GetLiveEventsRequest>,
@@ -6080,6 +6118,34 @@ pub mod node_service_server {
};
Box::pin(fut)
}
"/node_service.NodeService/TierDailyStats" => {
#[allow(non_camel_case_types)]
struct TierDailyStatsSvc<T: NodeService>(pub Arc<T>);
impl<T: NodeService> tonic::server::UnaryService<super::TierDailyStatsRequest> for TierDailyStatsSvc<T> {
type Response = super::TierDailyStatsResponse;
type Future = BoxFuture<tonic::Response<Self::Response>, tonic::Status>;
fn call(&mut self, request: tonic::Request<super::TierDailyStatsRequest>) -> Self::Future {
let inner = Arc::clone(&self.0);
let fut = async move { <T as NodeService>::tier_daily_stats(&inner, request).await };
Box::pin(fut)
}
}
let accept_compression_encodings = self.accept_compression_encodings;
let send_compression_encodings = self.send_compression_encodings;
let max_decoding_message_size = self.max_decoding_message_size;
let max_encoding_message_size = self.max_encoding_message_size;
let inner = self.inner.clone();
let fut = async move {
let method = TierDailyStatsSvc(inner);
let codec = tonic_prost::ProstCodec::default();
let mut grpc = tonic::server::Grpc::new(codec)
.apply_compression_config(accept_compression_encodings, send_compression_encodings)
.apply_max_message_size_config(max_decoding_message_size, max_encoding_message_size);
let res = grpc.unary(method, req).await;
Ok(res)
};
Box::pin(fut)
}
"/node_service.NodeService/GetLiveEvents" => {
#[allow(non_camel_case_types)]
struct GetLiveEventsSvc<T: NodeService>(pub Arc<T>);
crates/protos/src/node.proto
+17
View File
@@ -1043,6 +1043,22 @@ message LoadTransitionTierConfigResponse {
optional ControlPlaneErrorCode error_code = 3;
}
message TierDailyStatsRequest {}
// One node's own rolling-day transition counters, per remote tier.
//
// `tier_daily_stats` is a msgpack map of tier name to the responder's 24-bin
// ring plus the clock that ring was last aged to. A node counts only the
// transitions it completed itself, so a caller sums the rings of every node to
// obtain a cluster total. A peer that does not implement this RPC answers
// UNIMPLEMENTED, which the caller reports as a non-reporting node rather than
// as zero activity.
message TierDailyStatsResponse {
bool success = 1;
bytes tier_daily_stats = 2;
optional string error_info = 3;
}
message TierMutationPrepareRequest {
uint32 version = 1;
string mutation_id = 2;
@@ -1203,6 +1219,7 @@ service NodeService {
rpc CancelDecommission(CancelDecommissionRequest) returns (CancelDecommissionResponse) {}; // auth-policy: body-bound
rpc ClearDecommission(ClearDecommissionRequest) returns (ClearDecommissionResponse) {}; // auth-policy: body-bound
rpc LoadTransitionTierConfig(LoadTransitionTierConfigRequest) returns (LoadTransitionTierConfigResponse) {}; // auth-policy: body-bound
rpc TierDailyStats(TierDailyStatsRequest) returns (TierDailyStatsResponse) {}; // auth-policy: read-only
rpc GetLiveEvents(GetLiveEventsRequest) returns (GetLiveEventsResponse) {}; // auth-policy: read-only
}