feat(storage): harden internode data-path controls (#4224)

* fix(rio): propagate http writer shutdown errors

* fix(ecstore): unify remote lock rpc deadlines

* fix(storage): reject corrupt read multiple payloads

* feat(rio): add internode http tuning profiles

* feat(metrics): add internode baseline signals

* feat(ecstore): observe shard locality topology

* feat(ecstore): gate shard locality scheduling

* feat(ecstore): gate batch read version rpc

* feat(ecstore): observe batch processor adaptation

* feat(ecstore): gate batch processor observation

* docs: add get benchmark regression analysis

* docs: add issue 797 execution plan status

* fix(ecstore): require explicit batch rpc support

* fix(ecstore): honor documented batch read gate

* fix(ecstore): keep batch read gate stable per call

* chore: update workspace dependencies

* feat(ecstore): log batch read gate decisions

* feat(ecstore): count batch read gate decisions

* test(issue-797): add local internode A/B runner

* test(rio): fix tuning profile spelling fixture

* fix(protocols): adapt sftp channel open callbacks

* fix(metrics): wrap batch processor observation args

* chore(docs): keep issue notes local only

* fix(storage): address internode review feedback

* fix(storage): address internode data-path review findings

- Run the BatchReadVersion auto-mode unary fallback outside the batch
  RPC deadline so each read_version keeps its own per-op timeout and
  health accounting instead of racing the whole batch against one
  drive timeout.
- Cap adaptive batch-processor concurrency growth at a hard multiple
  of the configured baseline so sustained fast batches cannot ratchet
  past the configured limit.
- Parse RUSTFS_INTERNODE_HTTP_* tuning, RUSTFS_BATCH_PROCESSOR_ADAPTIVE,
  and RUSTFS_METADATA_BATCH_READ once per process instead of re-reading
  the environment on hot paths.
- Skip shard read-cost collection in observe mode when stage metrics
  are disabled, and cache the local endpoint host list instead of
  rebuilding it on every read.
- Allow --warp-extra-args values starting with -- and drop the unused
  warp_hosts_csv helper in the issue-797 A/B runner.

* fix(storage): address internode data-path review findings

- Run the BatchReadVersion auto-mode unary fallback outside the batch
  RPC deadline so each read_version keeps its own per-op timeout and
  health accounting instead of racing the whole batch against one
  drive timeout.
- Cap adaptive batch-processor concurrency growth at a hard multiple
  of the configured baseline so sustained fast batches cannot ratchet
  past the configured limit.
- Parse RUSTFS_INTERNODE_HTTP_* tuning, RUSTFS_BATCH_PROCESSOR_ADAPTIVE,
  and RUSTFS_METADATA_BATCH_READ once per process instead of re-reading
  the environment on hot paths.
- Skip shard read-cost collection in observe mode when stage metrics
  are disabled, and cache the local endpoint host list instead of
  rebuilding it on every read.
- Allow --warp-extra-args values starting with -- and drop the unused
  warp_hosts_csv helper in the issue-797 A/B runner.

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

* fix(storage): align buffer clamp test with media cap

* fix(ecstore): release optimized read locks before streaming

---------

Co-authored-by: Zhengchao An <anzhengchao@gmail.com>
This commit is contained in:
houseme
2026-07-03 17:08:15 +08:00
committed by GitHub
parent a9ac5f578d
commit 25d80d7c60
26 changed files with 3627 additions and 483 deletions
+73
View File
@@ -577,6 +577,9 @@ pub trait DiskAPI: Debug + Send + Sync + 'static {
version_id: &str,
opts: &ReadOptions,
) -> Result<FileInfo>;
async fn batch_read_version(&self, req: BatchReadVersionReq) -> Result<Vec<BatchReadVersionResp>> {
batch_read_version_one_by_one(self, req).await
}
async fn read_xl(&self, volume: &str, path: &str, read_data: bool) -> Result<RawFileInfo>;
async fn read_metadata(&self, volume: &str, path: &str) -> Result<Bytes>;
async fn rename_data(
@@ -637,6 +640,41 @@ pub trait DiskAPI: Debug + Send + Sync + 'static {
fn start_scan(&self) -> ScanGuard;
}
pub async fn batch_read_version_one_by_one<D>(disk: &D, req: BatchReadVersionReq) -> Result<Vec<BatchReadVersionResp>>
where
D: DiskAPI + ?Sized,
{
validate_batch_read_version_item_count(req.items.len())?;
let mut responses = Vec::with_capacity(req.items.len());
for (index, item) in req.items.iter().enumerate() {
let response = match disk
.read_version(&item.org_volume, &item.volume, &item.path, &item.version_id, &req.opts)
.await
{
Ok(file_info) => BatchReadVersionResp {
index,
path: item.path.clone(),
version_id: item.version_id.clone(),
success: true,
file_info,
error: String::new(),
},
Err(err) => BatchReadVersionResp {
index,
path: item.path.clone(),
version_id: item.version_id.clone(),
success: false,
file_info: FileInfo::default(),
error: err.to_string(),
},
};
responses.push(response);
}
Ok(responses)
}
#[derive(Debug, Default, Serialize, Deserialize)]
pub struct CheckPartsResp {
pub results: Vec<usize>,
@@ -807,6 +845,41 @@ pub struct ReadMultipleResp {
pub mod_time: Option<OffsetDateTime>,
}
pub const BATCH_READ_VERSION_MAX_ITEMS: usize = 128;
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct BatchReadVersionItem {
pub org_volume: String,
pub volume: String,
pub path: String,
pub version_id: String,
}
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct BatchReadVersionReq {
pub items: Vec<BatchReadVersionItem>,
pub opts: ReadOptions,
}
#[derive(Debug, Clone, Default, Serialize, Deserialize)]
pub struct BatchReadVersionResp {
pub index: usize,
pub path: String,
pub version_id: String,
pub success: bool,
pub file_info: FileInfo,
pub error: String,
}
pub fn validate_batch_read_version_item_count(item_count: usize) -> Result<()> {
if item_count > BATCH_READ_VERSION_MAX_ITEMS {
return Err(DiskError::other(format!(
"batch read version item count {item_count} exceeds limit {BATCH_READ_VERSION_MAX_ITEMS}"
)));
}
Ok(())
}
#[derive(Debug, Deserialize, Serialize)]
pub struct VolumeInfo {
pub name: String,