mirror of
https://github.com/rustfs/rustfs.git
synced 2026-08-20 19:42:17 +00:00
319a03e638
* fix(lifecycle): safely expire all object versions * fix(lifecycle): preserve delete-all replication purges * fix(lifecycle): remove dead replication journal * fix(ci): avoid lifecycle transition test stack overflow * fix(lifecycle): release recovery locks before tier IO * test(lifecycle): align object-lock error assertions * test(lifecycle): avoid scanner restore stack overflow * test(scanner): avoid stack overflow in transition and restore flow test (#6300) * refactor(scanner): split remote_scanner.rs into stream child module (#6289) Split the 3080-line remote_scanner.rs (47% inline tests) into a canonical foo.rs + foo/ module tree with zero behavior change: - remote_scanner.rs (~320): protocol constants, process statics, and the request decode/validate/admit/preflight/claim API plus root re-exports - remote_scanner/stream.rs (~1340): wire/frame types, replay cache, FrameAuthenticator, serve path, local bucket scan + persist, client scan, and the bounded stream plumbing - remote_scanner/stream/tests.rs (~1470): the inline test module as a child module of stream so it can reach both parents' private items All crate paths are unchanged: lib.rs re-exports (serve_remote_scanner_request, RemoteScannerRequest, ...) resolve through root re-exports, and scanner_io's crate::remote_scanner:: {scan_remote_bucket, RemoteScannerScanSpec, RemoteScannerOutcome} paths resolve through pub(crate) re-exports. Cross-module items gain pub(super), whose scope equals the old single-module privacy domain; no item's effective visibility widens. Code is moved verbatim apart from those markers, per-module import headers, and rustfmt line re-wraps. Co-authored-by: heihutu <heihutu@gmail.com> * refactor(heal): split resume.rs into focused child modules (#6290) Split the 4242-line resume.rs (46% inline tests) into a canonical foo.rs + foo/ module tree with zero behavior change: - resume.rs (~1020): state file constants, PersistThrottle, ResumeState, ResumeManager core (constructors, load/discovery, progress mutators, ordinary persistence) plus root re-exports - resume/replacement.rs (~690): replacement-intent/proof types and the ResumeManager replacement-lifecycle methods - resume/checkpoint.rs (~350): ResumeCheckpoint + CheckpointManager - resume/utils.rs (~310): ResumeUtils statics - resume/tests.rs (~1980): the inline test module as a child module All module paths are unchanged (heal::resume::CheckpointManager and friends resolve through root re-exports), so no consumer inside or outside the crate changes. Items defined in child modules keep module-private visibility; only the ten cross-module helpers gain pub(super), which is not part of the crate API. Code is moved verbatim apart from those visibility markers, four super::storage_api path fixes, and the new per-module import headers. Co-authored-by: heihutu <heihutu@gmail.com> * refactor(scanner): split scanner_io.rs into child modules (#6294) Split the 5369-line scanner_io.rs (39% inline tests) into a canonical scanner_io.rs + scanner_io/ module tree with zero behavior change: - scanner_io.rs (~660): constants, metadata-error constructors, the bucket scan plan, cycle-status classification helpers, the ScannerIO / ScannerIOCache / ScannerIODisk traits, and ScannerCycleResult - scanner_io/dirty_usage.rs (~300): process-wide dirty-usage statics and the acknowledgment protocol - scanner_io/guards.rs (~270): concurrency gauges and RAII guards - scanner_io/cache.rs (~410): scanner cache locks and the snapshot persist/publish path - scanner_io/io_cycle.rs (~390), io_cache.rs (~1160), io_disk.rs (~230): the ECStore / SetDisks / Disk trait implementations - scanner_io/publish_gate_tests.rs (~750) and tests.rs (~1340): the two inline test modules as child modules All crate paths are unchanged: the lib.rs scanner_io re-exports and every crate::scanner_io:: consumer (scanner.rs, remote_scanner, scanner_folder, and cross-crate rustfs users) resolve through root re-exports with their original visibilities (pub stays pub, pub(crate) stays pub(crate)). Cross-module items gain pub(super), whose scope equals the old single-module privacy domain. Code is moved verbatim apart from those markers, per-module import headers, and rustfmt re-wraps. The logging-guardrail nsscanner_disk skip-set_disks rule now points at scanner_io/io_disk.rs where the function moved; the pattern and thresholds are unchanged. Co-authored-by: heihutu <heihutu@gmail.com> * refactor(scanner): split data_usage_define persistence and tests (#6292) Split the 3655-line data_usage_define.rs (59% inline tests) into a canonical foo.rs + foo/ module tree with zero behavior change: - data_usage_define.rs (~950): cache constants and revision helpers, the data-usage tree types, DataUsageCacheInfo with its hand-written Serialize, the in-memory tree operations, dui, and marshal/unmarshal - data_usage_define/persistence.rs (~580): the load/backup/restore ladder (load, try_load_inner, revision_for_path) and the CAS save path with its retry policy and save metrics - data_usage_define/tests.rs (~2155): the inline test module as a child module All module paths are unchanged (the lib.rs data_usage_define::* glob re-export and every crate::data_usage_define:: consumer resolve as before). The hand-written map-encoded Serialize for DataUsageCacheInfo is moved byte-for-byte per the AGENTS.md cross-cutting invariant; on-disk names and the cache key format const stay in the root. Four persistence helpers used by tests gain pub(super), whose scope equals the old single-module privacy domain. Code is moved verbatim apart from those markers, per-module import headers, and rustfmt re-wraps. Co-authored-by: heihutu <heihutu@gmail.com> * chore(deps): bump datafusion to 55.0.0 (#6288) * refactor(heal): split task.rs per heal kind (#6293) * feat(ecstore): batch small file fdatasync commits (#6297) * feat(ecstore): batch small file fdatasync commits Add a default-off experimental file fdatasync group commit path for small rename_data shard directories. The coordinator batches same-disk waiters into one blocking task while preserving per-directory source fsync after shard contents are durable. Co-Authored-By: heihutu <heihutu@gmail.com> * test(e2e): wait for compression S3 readiness Reuse the shared S3 API readiness probe for compression test servers so multipart requests do not race the startup readiness gate after the TCP port opens. Co-Authored-By: heihutu <heihutu@gmail.com> --------- Co-authored-by: heihutu <heihutu@gmail.com> * fix(tier): recover multi-committed mutation intents (#6296) * fix(tier): recover multi-committed mutation intents * fix(tier): recover committed mutations on standalone nodes * test(scanner): avoid stack overflow in transition test --------- Co-authored-by: heihutu <heihutu@gmail.com> Co-authored-by: cxymds <cxymds@gmail.com> --------- Co-authored-by: houseme <housemecn@gmail.com> Co-authored-by: heihutu <heihutu@gmail.com>
168 lines
6.2 KiB
Rust
168 lines
6.2 KiB
Rust
// Copyright 2024 RustFS Team
|
|
//
|
|
// Licensed under the Apache License, Version 2.0 (the "License");
|
|
// you may not use this file except in compliance with the License.
|
|
// You may obtain a copy of the License at
|
|
//
|
|
// http://www.apache.org/licenses/LICENSE-2.0
|
|
//
|
|
// Unless required by applicable law or agreed to in writing, software
|
|
// distributed under the License is distributed on an "AS IS" BASIS,
|
|
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
// See the License for the specific language governing permissions and
|
|
// limitations under the License.
|
|
|
|
use s3s::dto::ReplicationConfiguration;
|
|
|
|
use super::replication_config_boundary::ReplicationConfigurationExt as _;
|
|
use super::replication_filemeta_boundary::{
|
|
REPLICATE_INCOMING_DELETE, ReplicateDecision, ReplicationState, version_purge_statuses_map,
|
|
};
|
|
use super::replication_object_config::{ReplicationConfig, check_replicate_delete};
|
|
use super::replication_queue_boundary::DeletedObjectReplicationInfo;
|
|
use super::replication_storage_boundary::{
|
|
DeletedObject, ObjectInfo, ObjectOptions, ObjectToDelete, deleted_object_for_replication,
|
|
};
|
|
#[cfg(test)]
|
|
use std::sync::Mutex;
|
|
|
|
#[allow(
|
|
dead_code,
|
|
reason = "declared boundary surface for the ECStore replication split plan; no caller in this port (backlog#1823)"
|
|
)]
|
|
pub(crate) type ReplicationLifecycleConfig = ReplicationConfig;
|
|
|
|
pub(crate) struct ReplicationLifecycleBridge;
|
|
|
|
#[cfg(test)]
|
|
static SCHEDULED_DELETE_OBJECTS: Mutex<Vec<DeletedObject>> = Mutex::new(Vec::new());
|
|
|
|
impl ReplicationLifecycleBridge {
|
|
#[allow(
|
|
dead_code,
|
|
reason = "declared boundary surface for the ECStore replication split plan; no caller in this port (backlog#1823)"
|
|
)]
|
|
pub(crate) fn new_config(config: ReplicationConfiguration) -> ReplicationLifecycleConfig {
|
|
ReplicationConfig::new(Some(config), None)
|
|
}
|
|
|
|
#[allow(
|
|
dead_code,
|
|
reason = "declared boundary surface for the ECStore replication split plan; no caller in this port (backlog#1823)"
|
|
)]
|
|
pub(crate) fn has_pending_version_purge(
|
|
config: &ReplicationLifecycleConfig,
|
|
object_name: &str,
|
|
version_purge_pending: bool,
|
|
) -> bool {
|
|
version_purge_pending
|
|
&& config
|
|
.config
|
|
.as_ref()
|
|
.is_some_and(|config| config.has_active_rules(object_name, true))
|
|
}
|
|
|
|
#[allow(
|
|
dead_code,
|
|
reason = "declared boundary surface for the ECStore replication split plan; no caller in this port (backlog#1823)"
|
|
)]
|
|
pub(crate) async fn check_delete_replication(
|
|
bucket: &str,
|
|
object: &ObjectToDelete,
|
|
source: &ObjectInfo,
|
|
opts: &ObjectOptions,
|
|
) -> ReplicateDecision {
|
|
check_replicate_delete(bucket, object, source, opts, None).await
|
|
}
|
|
|
|
#[allow(
|
|
dead_code,
|
|
reason = "declared boundary surface for the ECStore replication split plan; no caller in this port (backlog#1823)"
|
|
)]
|
|
pub(crate) fn version_delete_replication_state(decision: &ReplicateDecision) -> ReplicationState {
|
|
let pending_status = decision.pending_status();
|
|
ReplicationState {
|
|
replicate_decision_str: decision.to_string(),
|
|
version_purge_status_internal: pending_status.clone(),
|
|
purge_targets: version_purge_statuses_map(pending_status.as_deref().unwrap_or_default()),
|
|
..Default::default()
|
|
}
|
|
}
|
|
|
|
pub(crate) async fn schedule_delete(bucket: String, delete_object: DeletedObject) {
|
|
#[cfg(test)]
|
|
{
|
|
SCHEDULED_DELETE_OBJECTS
|
|
.lock()
|
|
.expect("scheduled delete test hook lock should not poison")
|
|
.push(delete_object.clone());
|
|
}
|
|
super::replication_pool::schedule_replication_delete(DeletedObjectReplicationInfo {
|
|
delete_object: deleted_object_for_replication(delete_object),
|
|
bucket,
|
|
event_type: REPLICATE_INCOMING_DELETE.to_string(),
|
|
..Default::default()
|
|
})
|
|
.await;
|
|
}
|
|
|
|
#[cfg(test)]
|
|
pub(crate) fn take_scheduled_deletes_for_test() -> Vec<DeletedObject> {
|
|
std::mem::take(
|
|
&mut *SCHEDULED_DELETE_OBJECTS
|
|
.lock()
|
|
.expect("scheduled delete test hook lock should not poison"),
|
|
)
|
|
}
|
|
}
|
|
|
|
#[cfg(test)]
|
|
mod tests {
|
|
use s3s::dto::{Destination, ReplicationRule, ReplicationRuleStatus};
|
|
|
|
use super::super::replication_filemeta_boundary::{ReplicateTargetDecision, VersionPurgeStatusType};
|
|
use super::*;
|
|
|
|
fn replication_rule() -> ReplicationRule {
|
|
ReplicationRule {
|
|
delete_marker_replication: None,
|
|
delete_replication: None,
|
|
destination: Destination {
|
|
bucket: "arn:aws:s3:::target-bucket".to_string(),
|
|
..Default::default()
|
|
},
|
|
existing_object_replication: None,
|
|
filter: None,
|
|
id: Some("rule".to_string()),
|
|
prefix: Some(String::new()),
|
|
priority: Some(1),
|
|
source_selection_criteria: None,
|
|
status: ReplicationRuleStatus::from_static(ReplicationRuleStatus::ENABLED),
|
|
}
|
|
}
|
|
|
|
#[test]
|
|
fn has_pending_version_purge_preserves_replication_active_rule_behavior() {
|
|
let config = ReplicationLifecycleBridge::new_config(ReplicationConfiguration {
|
|
role: String::new(),
|
|
rules: vec![replication_rule()],
|
|
});
|
|
|
|
assert!(ReplicationLifecycleBridge::has_pending_version_purge(&config, "logs/object", true));
|
|
assert!(!ReplicationLifecycleBridge::has_pending_version_purge(&config, "logs/object", false));
|
|
}
|
|
|
|
#[test]
|
|
fn version_delete_replication_state_tracks_pending_purge_targets() {
|
|
let target = ReplicateTargetDecision::new("arn:aws:s3:::target".to_string(), true, false);
|
|
let mut decision = ReplicateDecision::new();
|
|
decision.set(target);
|
|
|
|
let state = ReplicationLifecycleBridge::version_delete_replication_state(&decision);
|
|
|
|
assert_eq!(state.version_purge_status_internal.as_deref(), Some("arn:aws:s3:::target=PENDING;"));
|
|
assert!(state.purge_targets.contains_key("arn:aws:s3:::target"));
|
|
assert_eq!(state.purge_targets["arn:aws:s3:::target"], VersionPurgeStatusType::Pending);
|
|
}
|
|
}
|