feat(heal): add authenticated control RPC contract (#4993)

* fix(rpc): bind internode auth to exact targets

* fix(heal): initialize the runtime atomically

* fix(heal): aggregate status across cluster nodes

* fix(heal): return canonical tokens for duplicate starts

* feat(heal): add authenticated control RPC contract

* fix(heal): return canonical tokens for duplicate starts (#4992)

---------

Co-authored-by: Zhengchao An <anzhengchao@gmail.com>
This commit is contained in:
cxymds
2026-07-20 12:07:38 +08:00
committed by GitHub
parent 69f543568b
commit a774bc07da
12 changed files with 705 additions and 32 deletions
@@ -586,6 +586,8 @@ pub struct DeleteVersionRequest {
pub force_del_marker: bool,
#[prost(string, tag = "6")]
pub opts: ::prost::alloc::string::String,
/// msgpack payloads mirroring the JSON fields above (grpc-optimization P2). Senders dual-write
/// both; receivers prefer the \*\_bin form and fall back to the JSON string when it is empty.
#[prost(bytes = "bytes", tag = "7")]
pub file_info_bin: ::prost::bytes::Bytes,
#[prost(bytes = "bytes", tag = "8")]
@@ -610,6 +612,8 @@ pub struct DeleteVersionsRequest {
pub versions: ::prost::alloc::vec::Vec<::prost::alloc::string::String>,
#[prost(string, tag = "4")]
pub opts: ::prost::alloc::string::String,
/// msgpack payloads mirroring the JSON fields above (grpc-optimization P2). Senders dual-write
/// both; receivers prefer the \*\_bin form and fall back to the JSON string when it is empty.
#[prost(bytes = "bytes", repeated, tag = "5")]
pub versions_bin: ::prost::alloc::vec::Vec<::prost::bytes::Bytes>,
#[prost(bytes = "bytes", tag = "6")]
@@ -650,6 +654,9 @@ pub struct DeleteVolumeRequest {
pub disk: ::prost::alloc::string::String,
#[prost(string, tag = "2")]
pub volume: ::prost::alloc::string::String,
/// When false (default), a non-empty volume is refused (VolumeNotEmpty); when
/// true, the volume is deleted recursively. Old peers omit this field, which
/// decodes to false — the safe, non-recursive behavior (backlog#799 B1).
#[prost(bool, tag = "3")]
pub force: bool,
}
@@ -1091,6 +1098,24 @@ pub struct BackgroundHealStatusResponse {
pub error_info: ::core::option::Option<::prost::alloc::string::String>,
}
#[derive(Clone, PartialEq, Eq, Hash, ::prost::Message)]
pub struct HealControlRequest {
#[prost(uint32, tag = "1")]
pub version: u32,
#[prost(string, tag = "2")]
pub topology_fingerprint: ::prost::alloc::string::String,
#[prost(bytes = "bytes", tag = "3")]
pub command: ::prost::bytes::Bytes,
}
#[derive(Clone, PartialEq, Eq, Hash, ::prost::Message)]
pub struct HealControlResponse {
#[prost(bool, tag = "1")]
pub success: bool,
#[prost(bytes = "bytes", tag = "2")]
pub result: ::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 GetMetacacheListingRequest {
#[prost(bytes = "bytes", tag = "1")]
pub opts: ::prost::bytes::Bytes,
@@ -5329,3 +5354,237 @@ pub mod node_service_server {
const NAME: &'static str = SERVICE_NAME;
}
}
/// Generated client implementations.
pub mod heal_control_service_client {
#![allow(unused_variables, dead_code, missing_docs, clippy::wildcard_imports, clippy::let_unit_value)]
use tonic::codegen::http::Uri;
use tonic::codegen::*;
#[derive(Debug, Clone)]
pub struct HealControlServiceClient<T> {
inner: tonic::client::Grpc<T>,
}
impl HealControlServiceClient<tonic::transport::Channel> {
/// Attempt to create a new client by connecting to a given endpoint.
pub async fn connect<D>(dst: D) -> Result<Self, tonic::transport::Error>
where
D: TryInto<tonic::transport::Endpoint>,
D::Error: Into<StdError>,
{
let conn = tonic::transport::Endpoint::new(dst)?.connect().await?;
Ok(Self::new(conn))
}
}
impl<T> HealControlServiceClient<T>
where
T: tonic::client::GrpcService<tonic::body::Body>,
T::Error: Into<StdError>,
T::ResponseBody: Body<Data = Bytes> + std::marker::Send + 'static,
<T::ResponseBody as Body>::Error: Into<StdError> + std::marker::Send,
{
pub fn new(inner: T) -> Self {
let inner = tonic::client::Grpc::new(inner);
Self { inner }
}
pub fn with_origin(inner: T, origin: Uri) -> Self {
let inner = tonic::client::Grpc::with_origin(inner, origin);
Self { inner }
}
pub fn with_interceptor<F>(inner: T, interceptor: F) -> HealControlServiceClient<InterceptedService<T, F>>
where
F: tonic::service::Interceptor,
T::ResponseBody: Default,
T: tonic::codegen::Service<
http::Request<tonic::body::Body>,
Response = http::Response<<T as tonic::client::GrpcService<tonic::body::Body>>::ResponseBody>,
>,
<T as tonic::codegen::Service<http::Request<tonic::body::Body>>>::Error:
Into<StdError> + std::marker::Send + std::marker::Sync,
{
HealControlServiceClient::new(InterceptedService::new(inner, interceptor))
}
/// Compress requests with the given encoding.
///
/// This requires the server to support it otherwise it might respond with an
/// error.
#[must_use]
pub fn send_compressed(mut self, encoding: CompressionEncoding) -> Self {
self.inner = self.inner.send_compressed(encoding);
self
}
/// Enable decompressing responses.
#[must_use]
pub fn accept_compressed(mut self, encoding: CompressionEncoding) -> Self {
self.inner = self.inner.accept_compressed(encoding);
self
}
/// Limits the maximum size of a decoded message.
///
/// Default: `4MB`
#[must_use]
pub fn max_decoding_message_size(mut self, limit: usize) -> Self {
self.inner = self.inner.max_decoding_message_size(limit);
self
}
/// Limits the maximum size of an encoded message.
///
/// Default: `usize::MAX`
#[must_use]
pub fn max_encoding_message_size(mut self, limit: usize) -> Self {
self.inner = self.inner.max_encoding_message_size(limit);
self
}
pub async fn heal_control(
&mut self,
request: impl tonic::IntoRequest<super::HealControlRequest>,
) -> std::result::Result<tonic::Response<super::HealControlResponse>, 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.HealControlService/HealControl");
let mut req = request.into_request();
req.extensions_mut()
.insert(GrpcMethod::new("node_service.HealControlService", "HealControl"));
self.inner.unary(req, path, codec).await
}
}
}
/// Generated server implementations.
pub mod heal_control_service_server {
#![allow(unused_variables, dead_code, missing_docs, clippy::wildcard_imports, clippy::let_unit_value)]
use tonic::codegen::*;
/// Generated trait containing gRPC methods that should be implemented for use with HealControlServiceServer.
#[async_trait]
pub trait HealControlService: std::marker::Send + std::marker::Sync + 'static {
async fn heal_control(
&self,
request: tonic::Request<super::HealControlRequest>,
) -> std::result::Result<tonic::Response<super::HealControlResponse>, tonic::Status>;
}
#[derive(Debug)]
pub struct HealControlServiceServer<T> {
inner: Arc<T>,
accept_compression_encodings: EnabledCompressionEncodings,
send_compression_encodings: EnabledCompressionEncodings,
max_decoding_message_size: Option<usize>,
max_encoding_message_size: Option<usize>,
}
impl<T> HealControlServiceServer<T> {
pub fn new(inner: T) -> Self {
Self::from_arc(Arc::new(inner))
}
pub fn from_arc(inner: Arc<T>) -> Self {
Self {
inner,
accept_compression_encodings: Default::default(),
send_compression_encodings: Default::default(),
max_decoding_message_size: None,
max_encoding_message_size: None,
}
}
pub fn with_interceptor<F>(inner: T, interceptor: F) -> InterceptedService<Self, F>
where
F: tonic::service::Interceptor,
{
InterceptedService::new(Self::new(inner), interceptor)
}
/// Enable decompressing requests with the given encoding.
#[must_use]
pub fn accept_compressed(mut self, encoding: CompressionEncoding) -> Self {
self.accept_compression_encodings.enable(encoding);
self
}
/// Compress responses with the given encoding, if the client supports it.
#[must_use]
pub fn send_compressed(mut self, encoding: CompressionEncoding) -> Self {
self.send_compression_encodings.enable(encoding);
self
}
/// Limits the maximum size of a decoded message.
///
/// Default: `4MB`
#[must_use]
pub fn max_decoding_message_size(mut self, limit: usize) -> Self {
self.max_decoding_message_size = Some(limit);
self
}
/// Limits the maximum size of an encoded message.
///
/// Default: `usize::MAX`
#[must_use]
pub fn max_encoding_message_size(mut self, limit: usize) -> Self {
self.max_encoding_message_size = Some(limit);
self
}
}
impl<T, B> tonic::codegen::Service<http::Request<B>> for HealControlServiceServer<T>
where
T: HealControlService,
B: Body + std::marker::Send + 'static,
B::Error: Into<StdError> + std::marker::Send + 'static,
{
type Response = http::Response<tonic::body::Body>;
type Error = std::convert::Infallible;
type Future = BoxFuture<Self::Response, Self::Error>;
fn poll_ready(&mut self, _cx: &mut Context<'_>) -> Poll<std::result::Result<(), Self::Error>> {
Poll::Ready(Ok(()))
}
fn call(&mut self, req: http::Request<B>) -> Self::Future {
match req.uri().path() {
"/node_service.HealControlService/HealControl" => {
#[allow(non_camel_case_types)]
struct HealControlSvc<T: HealControlService>(pub Arc<T>);
impl<T: HealControlService> tonic::server::UnaryService<super::HealControlRequest> for HealControlSvc<T> {
type Response = super::HealControlResponse;
type Future = BoxFuture<tonic::Response<Self::Response>, tonic::Status>;
fn call(&mut self, request: tonic::Request<super::HealControlRequest>) -> Self::Future {
let inner = Arc::clone(&self.0);
let fut = async move { <T as HealControlService>::heal_control(&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 = HealControlSvc(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)
}
_ => Box::pin(async move {
let mut response = http::Response::new(tonic::body::Body::default());
let headers = response.headers_mut();
headers.insert(tonic::Status::GRPC_STATUS, (tonic::Code::Unimplemented as i32).into());
headers.insert(http::header::CONTENT_TYPE, tonic::metadata::GRPC_CONTENT_TYPE);
Ok(response)
}),
}
}
}
impl<T> Clone for HealControlServiceServer<T> {
fn clone(&self) -> Self {
let inner = self.inner.clone();
Self {
inner,
accept_compression_encodings: self.accept_compression_encodings,
send_compression_encodings: self.send_compression_encodings,
max_decoding_message_size: self.max_decoding_message_size,
max_encoding_message_size: self.max_encoding_message_size,
}
}
}
/// Generated gRPC service name
pub const SERVICE_NAME: &str = "node_service.HealControlService";
impl<T> tonic::server::NamedService for HealControlServiceServer<T> {
const NAME: &'static str = SERVICE_NAME;
}
}
+58
View File
@@ -140,6 +140,64 @@ pub fn internode_rpc_max_message_size() -> usize {
rustfs_utils::get_env_usize(rustfs_config::ENV_INTERNODE_RPC_MAX_MESSAGE_SIZE, DEFAULT_GRPC_SERVER_MESSAGE_LEN)
}
pub const HEAL_CONTROL_RPC_MAX_MESSAGE_SIZE: usize = 65 * 1024;
/// Builds the stable byte representation authenticated for a heal-control request.
///
/// This deliberately does not reuse protobuf encoding: mixed-version peers may
/// retain unknown protobuf fields, which must not change the signed contract.
pub fn canonical_heal_control_request_body(
version: u32,
topology_fingerprint: &str,
command: &[u8],
) -> Result<Vec<u8>, std::num::TryFromIntError> {
const DOMAIN: &[u8] = b"rustfs-heal-control-v1\0";
let fingerprint = topology_fingerprint.as_bytes();
let mut body = Vec::with_capacity(DOMAIN.len() + 4 + 8 + fingerprint.len() + 8 + command.len());
body.extend_from_slice(DOMAIN);
body.extend_from_slice(&version.to_be_bytes());
body.extend_from_slice(&u64::try_from(fingerprint.len())?.to_be_bytes());
body.extend_from_slice(fingerprint);
body.extend_from_slice(&u64::try_from(command.len())?.to_be_bytes());
body.extend_from_slice(command);
Ok(body)
}
#[cfg(test)]
mod heal_control_tests {
use super::canonical_heal_control_request_body;
#[test]
fn canonical_heal_control_body_binds_every_field_and_boundary() {
let baseline = canonical_heal_control_request_body(1, "ab", b"c").expect("small request should encode");
let mut golden = b"rustfs-heal-control-v1\0".to_vec();
golden.extend_from_slice(&1_u32.to_be_bytes());
golden.extend_from_slice(&2_u64.to_be_bytes());
golden.extend_from_slice(b"ab");
golden.extend_from_slice(&1_u64.to_be_bytes());
golden.extend_from_slice(b"c");
assert_eq!(baseline, golden);
assert_ne!(
baseline,
canonical_heal_control_request_body(2, "ab", b"c").expect("small request should encode")
);
assert_ne!(
baseline,
canonical_heal_control_request_body(1, "ac", b"c").expect("small request should encode")
);
assert_ne!(
baseline,
canonical_heal_control_request_body(1, "ab", b"d").expect("small request should encode")
);
assert_ne!(
canonical_heal_control_request_body(1, "ab", b"c").expect("small request should encode"),
canonical_heal_control_request_body(1, "a", b"bc").expect("small request should encode")
);
}
}
/// Whether internode metadata RPCs should send only the msgpack `_bin` payloads and leave the JSON
/// compatibility strings empty (grpc-optimization P2-1). Shared by the client (`remote_disk`) and
/// server (`node_service`) send paths. Defaults to `false` (dual-write); see
+16
View File
@@ -773,6 +773,18 @@ message BackgroundHealStatusResponse {
optional string error_info = 3;
}
message HealControlRequest {
uint32 version = 1;
string topology_fingerprint = 2;
bytes command = 3;
}
message HealControlResponse {
bool success = 1;
bytes result = 2;
optional string error_info = 3;
}
message GetMetacacheListingRequest {
bytes opts = 1;
}
@@ -966,3 +978,7 @@ service NodeService {
rpc LoadTransitionTierConfig(LoadTransitionTierConfigRequest) returns (LoadTransitionTierConfigResponse) {};
rpc GetLiveEvents(GetLiveEventsRequest) returns (GetLiveEventsResponse) {};
}
service HealControlService {
rpc HealControl(HealControlRequest) returns (HealControlResponse) {};
}