Compare commits

..

1 Commits

Author SHA1 Message Date
overtrue c57f22c3a0 fix(app): wait for peer bucket metadata reload 2026-08-22 15:49:37 +08:00
15 changed files with 176 additions and 700 deletions
+18 -64
View File
@@ -585,12 +585,9 @@ impl VersionsHistogram {
}
}
/// Replication statistics for a single target.
///
/// Renamed from `ReplicationStats`; serde field names are preserved
/// byte-identically to maintain wire compatibility with existing snapshots.
#[derive(Debug, Default, Clone, Serialize, Deserialize, PartialEq, Eq)]
pub struct ReplicationTargetUsage {
/// Replication statistics for a single target
#[derive(Debug, Default, Clone, Serialize, Deserialize)]
pub struct ReplicationStats {
pub pending_size: u64,
pub replicated_size: u64,
pub failed_size: u64,
@@ -603,7 +600,7 @@ pub struct ReplicationTargetUsage {
pub replicated_count: u64,
}
impl ReplicationTargetUsage {
impl ReplicationStats {
pub fn is_empty(&self) -> bool {
let Self {
pending_size,
@@ -639,7 +636,7 @@ impl ReplicationTargetUsage {
/// Replication statistics for all targets
#[derive(Debug, Default, Clone, Serialize, Deserialize)]
pub struct ReplicationAllStats {
pub targets: HashMap<String, ReplicationTargetUsage>,
pub targets: HashMap<String, ReplicationStats>,
pub replica_size: u64,
pub replica_count: u64,
}
@@ -652,7 +649,7 @@ impl ReplicationAllStats {
targets,
} = self;
*replica_size == 0 && *replica_count == 0 && targets.values().all(ReplicationTargetUsage::is_empty)
*replica_size == 0 && *replica_count == 0 && targets.values().all(ReplicationStats::is_empty)
}
#[deprecated(note = "use is_empty instead")]
@@ -2469,7 +2466,7 @@ mod tests {
#[test]
fn replication_stats_empty_checks_every_field() {
type SetField = fn(&mut ReplicationTargetUsage);
type SetField = fn(&mut ReplicationStats);
let cases: [(&str, SetField); 10] = [
("pending_size", |stats| stats.pending_size = 1),
@@ -2484,9 +2481,9 @@ mod tests {
("replicated_count", |stats| stats.replicated_count = 1),
];
assert!(ReplicationTargetUsage::default().is_empty());
assert!(ReplicationStats::default().is_empty());
for (field, set_nonzero) in cases {
let mut stats = ReplicationTargetUsage::default();
let mut stats = ReplicationStats::default();
set_nonzero(&mut stats);
assert!(!stats.is_empty(), "{field} must make replication stats non-empty");
}
@@ -2517,17 +2514,17 @@ mod tests {
}
let empty_targets = ReplicationAllStats {
targets: HashMap::from([("arn:test:empty".to_string(), ReplicationTargetUsage::default())]),
targets: HashMap::from([("arn:test:empty".to_string(), ReplicationStats::default())]),
..Default::default()
};
assert!(empty_targets.is_empty(), "all-empty targets must keep aggregate stats empty");
let stats = ReplicationAllStats {
targets: HashMap::from([
("arn:test:empty".to_string(), ReplicationTargetUsage::default()),
("arn:test:empty".to_string(), ReplicationStats::default()),
(
"arn:test:non-empty".to_string(),
ReplicationTargetUsage {
ReplicationStats {
pending_count: 1,
..Default::default()
},
@@ -2568,7 +2565,7 @@ mod tests {
replication_stats: Some(ReplicationAllStats {
targets: HashMap::from([(
"arn:test:pending".to_string(),
ReplicationTargetUsage {
ReplicationStats {
pending_count: 1,
..Default::default()
},
@@ -2717,7 +2714,7 @@ mod tests {
targets: HashMap::from([
(
"arn:self-only".to_string(),
ReplicationTargetUsage {
ReplicationStats {
pending_size: 7,
pending_count: 1,
..Default::default()
@@ -2725,7 +2722,7 @@ mod tests {
),
(
"arn:shared".to_string(),
ReplicationTargetUsage {
ReplicationStats {
failed_size: 3,
failed_count: 1,
missed_threshold_size: 2,
@@ -2744,7 +2741,7 @@ mod tests {
targets: HashMap::from([
(
"arn:shared".to_string(),
ReplicationTargetUsage {
ReplicationStats {
failed_size: 5,
failed_count: 2,
after_threshold_size: 4,
@@ -2754,7 +2751,7 @@ mod tests {
),
(
"arn:other-only".to_string(),
ReplicationTargetUsage {
ReplicationStats {
replicated_size: 11,
replicated_count: 3,
..Default::default()
@@ -2996,9 +2993,7 @@ mod tests {
fn replication_target_deserialization_preserves_large_historical_maps() {
let mut stats = ReplicationAllStats::default();
for index in 0..=1024 {
stats
.targets
.insert(format!("target-{index}"), ReplicationTargetUsage::default());
stats.targets.insert(format!("target-{index}"), ReplicationStats::default());
}
let encoded = rmp_serde::to_vec_named(&stats).expect("large replication target fixture should encode");
let decoded = rmp_serde::from_slice::<ReplicationAllStats>(&encoded)
@@ -3007,47 +3002,6 @@ mod tests {
assert_eq!(decoded.targets.len(), stats.targets.len());
}
/// Round-trip test: encoding a [`ReplicationTargetUsage`] and decoding it back
/// must produce the exact same value. This guards against accidental serde
/// field-name drift during the `ReplicationStats` -> `ReplicationTargetUsage`
/// rename. Wire-level field names are the serialized Rust field identifiers,
/// which must remain byte-identical.
#[test]
fn replication_target_usage_rmp_round_trip() {
let original = ReplicationTargetUsage {
pending_size: 100,
replicated_size: 2_000,
failed_size: 50,
failed_count: 3,
pending_count: 7,
missed_threshold_size: 11,
after_threshold_size: 22,
missed_threshold_count: 1,
after_threshold_count: 2,
replicated_count: 99,
};
let buf = rmp_serde::to_vec_named(&original).expect("encode ReplicationTargetUsage to msgpack");
let decoded: ReplicationTargetUsage = rmp_serde::from_slice(&buf).expect("decode ReplicationTargetUsage from msgpack");
assert_eq!(original, decoded, "round-trip through rmp must preserve every field");
// Also verify that encoding as an unnamed sequence and then decoding
// with named fields produces the correct mapping (this catches reordering).
let named_buf = rmp_serde::to_vec_named(&original).expect("re-encode for field-name pinning");
// Spot-check that known field names appear in the named encoding.
let named_str = String::from_utf8_lossy(&named_buf);
assert!(named_str.contains("pending_size"), "field 'pending_size' must survive the rename");
assert!(named_str.contains("replicated_size"), "field 'replicated_size' must survive the rename");
assert!(
named_str.contains("missed_threshold_size"),
"field 'missed_threshold_size' must survive the rename"
);
assert!(
named_str.contains("after_threshold_count"),
"field 'after_threshold_count' must survive the rename"
);
}
#[test]
fn checked_merge_rejects_noncanonical_histograms_without_mutation() {
let mut entry = DataUsageEntry {
@@ -15,12 +15,14 @@
use crate::common::RustFSTestClusterEnvironment;
use aws_sdk_s3::Client;
use aws_sdk_s3::error::SdkError;
use aws_sdk_s3::types::{CorsConfiguration, CorsRule};
use bytes::Bytes;
use std::sync::Arc;
use tokio::sync::Barrier;
use tracing::{info, warn};
const BUCKET: &str = "conditional-put-race-bucket";
const BUCKET_METADATA_RELOAD_BUCKET: &str = "bucket-metadata-reload-barrier";
async fn cleanup_object(client: &Client, key: &str) {
if let Err(e) = client.delete_object().bucket(BUCKET).key(key).send().await {
@@ -28,6 +30,16 @@ async fn cleanup_object(client: &Client, key: &str) {
}
}
async fn assert_bucket_cors_missing(client: &Client) {
let result = client.get_bucket_cors().bucket(BUCKET_METADATA_RELOAD_BUCKET).send().await;
match result {
Err(SdkError::ServiceError(error)) => {
assert_eq!(error.err().meta().code(), Some("NoSuchCORSConfiguration"));
}
result => panic!("expected the peer to report a missing CORS configuration: {result:?}"),
}
}
async fn conditional_put(
client: &Client,
key: &str,
@@ -236,3 +248,48 @@ async fn test_conditional_put_basic_cluster() -> Result<(), Box<dyn std::error::
cleanup_object(&client, test_key).await;
Ok(())
}
#[tokio::test]
async fn test_bucket_cors_write_is_visible_on_peer_before_response() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
crate::common::init_logging();
let mut cluster = RustFSTestClusterEnvironment::new(2).await?;
cluster.start().await?;
cluster.create_test_bucket(BUCKET_METADATA_RELOAD_BUCKET).await?;
let writer = cluster.create_s3_client(0)?;
let reader = cluster.create_s3_client(1)?;
assert_bucket_cors_missing(&reader).await;
let rule = CorsRule::builder()
.allowed_methods("GET")
.allowed_origins("https://example.com")
.build()?;
let configuration = CorsConfiguration::builder().cors_rules(rule).build()?;
writer
.put_bucket_cors()
.bucket(BUCKET_METADATA_RELOAD_BUCKET)
.cors_configuration(configuration)
.send()
.await?;
let response = reader.get_bucket_cors().bucket(BUCKET_METADATA_RELOAD_BUCKET).send().await?;
let rules = response.cors_rules();
assert_eq!(
rules.len(),
1,
"peer should observe the committed CORS rule before the write response returns"
);
assert_eq!(rules[0].allowed_methods(), ["GET"]);
assert_eq!(rules[0].allowed_origins(), ["https://example.com"]);
writer
.delete_bucket_cors()
.bucket(BUCKET_METADATA_RELOAD_BUCKET)
.send()
.await?;
assert_bucket_cors_missing(&reader).await;
writer.delete_bucket().bucket(BUCKET_METADATA_RELOAD_BUCKET).send().await?;
Ok(())
}
@@ -85,6 +85,7 @@ const PEER_REST_RECOVERY_MAX_ATTEMPTS: u32 = 60;
const PEER_REST_RECOVERY_MAX_BACKOFF: Duration = Duration::from_secs(30);
const SCANNER_ACTIVITY_MAX_MESSAGE_SIZE: usize = 1024;
const REPLICATION_STATS_MAX_MESSAGE_SIZE: usize = 8 * 1024 * 1024;
const BUCKET_METADATA_RELOAD_TIMEOUT: Duration = Duration::from_secs(5);
/// Error for a peer that reported `success = false` without an `error_info` payload.
///
@@ -1328,27 +1329,38 @@ impl PeerRestClient {
}
pub async fn load_bucket_metadata(&self, bucket: &str, scanner_maintenance_change: bool) -> Result<()> {
self.finalize_result(
async {
let mut client = self.get_client().await?;
let mut request = Request::new(LoadBucketMetadataRequest {
bucket: bucket.to_string(),
scanner_maintenance_change,
});
set_tonic_mutation_body_digest(&mut request)?;
let response = client.load_bucket_metadata(request).await?.into_inner();
if !response.success {
if let Some(msg) = response.error_info {
return Err(Error::other(msg));
}
return Err(peer_failure_without_details("load_bucket_metadata", Some(bucket)));
}
Ok(())
let result = tokio::time::timeout(BUCKET_METADATA_RELOAD_TIMEOUT, async {
let result = self.load_bucket_metadata_once(bucket, scanner_maintenance_change).await;
if let Err(err) = &result
&& Self::is_network_like_error(err)
{
self.prepare_retry().await;
return self.load_bucket_metadata_once(bucket, scanner_maintenance_change).await;
}
.await,
)
result
})
.await
.unwrap_or_else(|_| Err(Error::other(format!("load_bucket_metadata({bucket}) timed out"))));
self.finalize_result(result).await
}
async fn load_bucket_metadata_once(&self, bucket: &str, scanner_maintenance_change: bool) -> Result<()> {
let mut client = self.get_client().await?;
let mut request = Request::new(LoadBucketMetadataRequest {
bucket: bucket.to_string(),
scanner_maintenance_change,
});
set_tonic_mutation_body_digest(&mut request)?;
request.set_timeout(BUCKET_METADATA_RELOAD_TIMEOUT);
let response = client.load_bucket_metadata(request).await?.into_inner();
if !response.success {
if let Some(msg) = response.error_info {
return Err(Error::other(msg));
}
return Err(peer_failure_without_details("load_bucket_metadata", Some(bucket)));
}
Ok(())
}
pub async fn delete_bucket_metadata(&self, bucket: &str) -> Result<()> {
+17 -84
View File
@@ -50,10 +50,10 @@ use rustfs_protos::evict_failed_connection;
use rustfs_protos::proto_gen::node_service::RenamePartRequest;
use rustfs_protos::proto_gen::node_service::{
BatchReadVersionRequest, BatchReadVersionResponse, CheckPartsRequest, DeletePathsRequest, DeleteRequest,
DeleteVersionRequest, DeleteVersionsRequest, DeleteVersionsResponse, DeleteVolumeRequest, DiskInfoRequest, ListDirRequest,
ListVolumesRequest, MakeVolumeRequest, MakeVolumesRequest, PreparePartTransactionRequest, ReadAllRequest,
ReadMetadataRequest, ReadMultipleRequest, ReadMultipleResponse, ReadPartsRequest, ReadVersionRequest, ReadXlRequest,
RenameDataRequest, RenameFileRequest, SettlePartTransactionRequest, SnapshotLeaseReleaseRequest, SnapshotLeaseRenewRequest,
DeleteVersionRequest, DeleteVersionsRequest, DeleteVolumeRequest, DiskInfoRequest, ListDirRequest, ListVolumesRequest,
MakeVolumeRequest, MakeVolumesRequest, PreparePartTransactionRequest, ReadAllRequest, ReadMetadataRequest,
ReadMultipleRequest, ReadMultipleResponse, ReadPartsRequest, ReadVersionRequest, ReadXlRequest, RenameDataRequest,
RenameFileRequest, SettlePartTransactionRequest, SnapshotLeaseReleaseRequest, SnapshotLeaseRenewRequest,
SnapshotLeaseRequest, SnapshotLeaseResponse, StatVolumeRequest, UpdateMetadataRequest, VerifyFileRequest, WriteAllRequest,
WriteMetadataRequest, node_service_client::NodeServiceClient,
};
@@ -112,28 +112,6 @@ const EVENT_REMOTE_DISK_RPC: &str = "remote_disk_rpc";
const SNAPSHOT_LEASE_PROTOCOL_VERSION: u32 = 1;
pub const REMOTE_SNAPSHOT_LEASE_TTL: Duration = Duration::from_secs(60);
fn decode_delete_versions_errors(response: DeleteVersionsResponse, expected_len: usize) -> Vec<Option<Error>> {
if !response.item_errors.is_empty() {
if response.item_errors.len() != expected_len {
return vec![Some(Error::other("malformed delete_versions item errors")); expected_len];
}
return response
.item_errors
.into_iter()
.map(|error| (error.code != 0).then(|| error.into()))
.collect();
}
if response.errors.len() != expected_len {
return vec![Some(Error::other("malformed delete_versions errors")); expected_len];
}
response
.errors
.into_iter()
.map(|error| (!error.is_empty()).then(|| Error::other(error)))
.collect()
}
fn snapshot_lease_token_from_response(response: SnapshotLeaseResponse) -> Result<SnapshotLeaseToken> {
if !response.success {
return Err(response.error.unwrap_or_default().into());
@@ -2428,6 +2406,8 @@ impl DiskAPI for RemoteDisk {
return errors;
}
// TODO(backlog): replace string errors with typed `StorageError` variants
let result = self
.execute_with_timeout(
|| async {
@@ -2459,7 +2439,17 @@ impl DiskAPI for RemoteDisk {
}
return errors;
}
decode_delete_versions_errors(response, versions.len())
response
.errors
.iter()
.map(|error| {
if error.is_empty() {
None
} else {
Some(Error::other(error.to_string()))
}
})
.collect()
}
#[tracing::instrument(level = "trace", skip_all)]
@@ -3770,63 +3760,6 @@ mod tests {
static INIT: Once = Once::new();
#[test]
fn delete_versions_response_preserves_typed_item_errors() {
let errors = decode_delete_versions_errors(
DeleteVersionsResponse {
success: true,
errors: vec!["file not found".to_string(), String::new()],
error: None,
item_errors: vec![
rustfs_protos::proto_gen::node_service::Error {
code: DiskError::FileNotFound.to_u32(),
error_info: "file not found".to_string(),
},
rustfs_protos::proto_gen::node_service::Error::default(),
],
},
2,
);
assert!(matches!(errors.as_slice(), [Some(DiskError::FileNotFound), None]));
}
#[test]
fn delete_versions_response_accepts_legacy_string_errors() {
let errors = decode_delete_versions_errors(
DeleteVersionsResponse {
success: true,
errors: vec!["legacy error".to_string(), String::new()],
error: None,
item_errors: Vec::new(),
},
2,
);
assert_eq!(errors.len(), 2);
assert_eq!(errors[0].as_ref().map(ToString::to_string).as_deref(), Some("io error legacy error"));
assert!(errors[1].is_none());
}
#[test]
fn delete_versions_response_rejects_misaligned_item_errors() {
let errors = decode_delete_versions_errors(
DeleteVersionsResponse {
success: true,
errors: vec!["file not found".to_string()],
error: None,
item_errors: vec![rustfs_protos::proto_gen::node_service::Error {
code: DiskError::FileNotFound.to_u32(),
error_info: "file not found".to_string(),
}],
},
2,
);
assert_eq!(errors.len(), 2);
assert!(errors.iter().all(Option::is_some));
}
#[test]
fn disk_mutation_digest_marks_rolling_compatibility() {
let mut request = Request::new(());
-54
View File
@@ -1640,60 +1640,6 @@ mod tests {
assert_eq!(payload["items"].as_array().expect("items should be an array").len(), 0);
}
#[tokio::test]
async fn test_process_query_request_reports_displaced_terminal_detail() {
let heal_manager = Arc::new(HealManager::new(
Arc::new(MockStorage),
Some(HealConfig {
queue_size: 1,
..HealConfig::default()
}),
));
let mut displaced = HealRequest::new(
HealType::Bucket {
bucket: "displaced-channel".to_string(),
},
HealOptions::default(),
HealPriority::Low,
);
displaced.id = "displaced-channel-task".to_string();
let displaced_id = displaced.id.clone();
heal_manager
.submit_heal_request(displaced)
.await
.expect("initial channel task should queue");
heal_manager
.submit_heal_request(HealRequest::new(
HealType::Bucket {
bucket: "successor-channel".to_string(),
},
HealOptions::default(),
HealPriority::High,
))
.await
.expect("successor channel task should displace the initial task");
let processor = HealChannelProcessor::new(heal_manager);
let (tx, rx) = oneshot::channel();
processor
.process_query_request("displaced-channel".to_string(), displaced_id, None, tx)
.await
.expect("displaced query should process");
let response = rx
.await
.expect("query response should be returned")
.expect("displaced query should remain successful");
let payload: serde_json::Value = serde_json::from_slice(response.data.as_deref().expect("status payload should exist"))
.expect("status payload should be json");
assert_eq!(payload["summary"], "stopped");
assert!(
response
.error
.as_deref()
.is_some_and(|detail| detail.contains("reason=displaced"))
);
}
#[tokio::test]
async fn test_process_query_request_reports_running_for_queued_task() {
let heal_manager = create_test_heal_manager();
+10 -105
View File
@@ -40,7 +40,6 @@ use tracing::{debug, error, info, warn};
use super::{DiskError, Endpoint, HealDiskExt as _, local_disk_map_read};
const KEEP_HEAL_TASK_STATUS_DURATION: Duration = Duration::from_secs(10 * 60);
const DISPLACED_HEAL_REASON: &str = "reason=displaced; retry_hint=submit_again";
const LOG_COMPONENT_HEAL: &str = "heal";
const LOG_SUBSYSTEM_DISK_SCANNER: &str = "disk_scanner";
const LOG_SUBSYSTEM_MANAGER: &str = "manager";
@@ -121,30 +120,26 @@ struct MrfRepairNoticeTarget {
version_id: Option<[u8; 16]>,
}
#[derive(Debug, Clone)]
#[derive(Debug, Clone, PartialEq, Eq)]
struct HealAdmissionDecision {
result: HealAdmissionResult,
displaced_request: Option<HealRequest>,
displaced_task_id: Option<String>,
}
impl HealAdmissionDecision {
const fn new(result: HealAdmissionResult) -> Self {
Self {
result,
displaced_request: None,
displaced_task_id: None,
}
}
fn accepted_with_displacement(displaced_request: HealRequest) -> Self {
fn accepted_with_displacement(displaced_task_id: String) -> Self {
Self {
result: HealAdmissionResult::Accepted,
displaced_request: Some(displaced_request),
displaced_task_id: Some(displaced_task_id),
}
}
fn displaced_task_id(&self) -> Option<&str> {
self.displaced_request.as_ref().map(|request| request.id.as_str())
}
}
fn lock_mrf_repair_notice_targets(
@@ -156,55 +151,6 @@ fn lock_mrf_repair_notice_targets(
}
}
fn lock_displaced_terminals(
registry: &StdMutex<HashMap<String, Arc<CompletedHealStatus>>>,
) -> StdMutexGuard<'_, HashMap<String, Arc<CompletedHealStatus>>> {
match registry.lock() {
Ok(guard) => guard,
Err(poisoned) => poisoned.into_inner(),
}
}
fn record_displaced_terminal(
registry: &StdMutex<HashMap<String, Arc<CompletedHealStatus>>>,
request: &HealRequest,
) -> Arc<CompletedHealStatus> {
let terminal = Arc::new(CompletedHealStatus {
heal_type: request.heal_type.clone(),
status: HealTaskStatus::Failed {
error: format!("heal task displaced by a higher-priority request ({DISPLACED_HEAL_REASON})"),
},
result_items_truncated: false,
completed_at: SystemTime::now(),
seqed_items: Vec::new(),
next_seq: 0,
min_seq: 0,
});
let mut terminals = lock_displaced_terminals(registry);
prune_completed_heal_statuses(&mut terminals);
terminals.insert(request.id.clone(), Arc::clone(&terminal));
terminal
}
async fn remove_displaced_task_aliases(
aliases: &Arc<Mutex<HashMap<String, HealTaskAlias>>>,
terminals: &StdMutex<HashMap<String, Arc<CompletedHealStatus>>>,
task_id: &str,
terminal: &Arc<CompletedHealStatus>,
) {
let mut aliases = aliases.lock().await;
let alias_ids = aliases
.iter()
.filter_map(|(alias_id, alias)| (alias.task_id == task_id).then_some(alias_id.clone()))
.collect::<Vec<_>>();
let mut displaced_terminals = lock_displaced_terminals(terminals);
prune_completed_heal_statuses(&mut displaced_terminals);
for alias_id in alias_ids {
displaced_terminals.insert(alias_id, Arc::clone(terminal));
}
aliases.retain(|alias_id, alias| alias_id != task_id && alias.task_id != task_id);
}
async fn remove_task_aliases_for_task(registry: &Arc<Mutex<HashMap<String, HealTaskAlias>>>, task_id: &str) {
registry
.lock()
@@ -672,14 +618,6 @@ pub struct HealManager {
/// are shared so the lookup helper can hand a completed entry to a
/// caller without cloning the retained result window.
completed_heals: Arc<Mutex<HashMap<String, Arc<CompletedHealStatus>>>>,
/// Terminals for requests removed by priority displacement. An Accepted
/// task ID remains queryable for the same process lifetime and the normal
/// ten-minute status TTL; clients should treat `reason=displaced` as a
/// terminal result and submit a fresh request. This sidecar is synchronous
/// so admission can publish the terminal while the queue transition is
/// still under its lock, without awaiting another tokio lock. Queue state
/// is process-local, so this guarantee does not extend across restart.
displaced_terminals: Arc<StdMutex<HashMap<String, Arc<CompletedHealStatus>>>>,
/// Client tokens merged into an existing task id.
task_aliases: Arc<Mutex<HashMap<String, HealTaskAlias>>>,
/// Heal tasks waiting for a retry backoff to expire.
@@ -721,7 +659,6 @@ struct HealQueueContext<'a> {
heal_queue: &'a Arc<Mutex<PriorityHealQueue>>,
active_heals: &'a Arc<Mutex<HashMap<String, Arc<HealTask>>>>,
completed_heals: &'a Arc<Mutex<HashMap<String, Arc<CompletedHealStatus>>>>,
displaced_terminals: &'a Arc<StdMutex<HashMap<String, Arc<CompletedHealStatus>>>>,
task_aliases: &'a Arc<Mutex<HashMap<String, HealTaskAlias>>>,
retrying_heals: &'a Arc<Mutex<HashMap<String, RetryingHeal>>>,
mrf_repair_notice_targets: &'a Arc<StdMutex<HashMap<String, Vec<MrfRepairNoticeTarget>>>>,
@@ -937,7 +874,7 @@ impl HealManager {
result = "accepted_by_displacement",
"Heal queue request accepted by displacement"
});
return HealAdmissionDecision::accepted_with_displacement(displaced);
return HealAdmissionDecision::accepted_with_displacement(displaced.id);
}
demote_to_debug_when!(per_object_request, warn, target: "rustfs::heal::manager", {
@@ -1168,7 +1105,6 @@ impl HealManager {
active_heals: Arc::new(Mutex::new(HashMap::new())),
heal_queue: Arc::new(Mutex::new(PriorityHealQueue::new())),
completed_heals: Arc::new(Mutex::new(HashMap::new())),
displaced_terminals: Arc::new(StdMutex::new(HashMap::new())),
task_aliases: Arc::new(Mutex::new(HashMap::new())),
retrying_heals: Arc::new(Mutex::new(HashMap::new())),
mrf_repair_notice_targets: Arc::new(StdMutex::new(HashMap::new())),
@@ -1273,10 +1209,6 @@ impl HealManager {
active_heals.clear();
publish_active_heal_count(&active_heals);
self.completed_heals.lock().await.clear();
// Do not let the synchronous guard live across the following async lock.
{
lock_displaced_terminals(&self.displaced_terminals).clear();
}
self.task_aliases.lock().await.clear();
self.retrying_heals.lock().await.clear();
lock_mrf_repair_notice_targets(&self.mrf_repair_notice_targets).clear();
@@ -1527,11 +1459,7 @@ impl HealManager {
task_id = queued_id.to_owned();
}
let should_notify = matches!(admission, HealAdmissionResult::Accepted) && config.event_driven_scheduler_enable;
let displaced_task_id = admission_decision.displaced_task_id().map(ToOwned::to_owned);
let displaced_terminal = admission_decision
.displaced_request
.as_ref()
.map(|request| record_displaced_terminal(&self.displaced_terminals, request));
let displaced_task_id = admission_decision.displaced_task_id;
if matches!(admission, HealAdmissionResult::Accepted | HealAdmissionResult::Merged)
&& let Some(target) = mrf_notice_target
{
@@ -1545,12 +1473,8 @@ impl HealManager {
drop(queue);
drop(active_heals);
if let (Some(displaced_task_id), Some(displaced_terminal)) = (displaced_task_id, displaced_terminal) {
// The queue has already removed the displaced request, so the
// synchronous terminal sidecar was published before aliases and
// MRF ownership are cleaned up.
remove_displaced_task_aliases(&self.task_aliases, &self.displaced_terminals, &displaced_task_id, &displaced_terminal)
.await;
if let Some(displaced_task_id) = displaced_task_id {
self.remove_aliases_for_task(&displaced_task_id).await;
}
if should_notify {
@@ -1625,15 +1549,6 @@ impl HealManager {
}
}
if terminal_completed.is_none() {
let mut displaced_terminals = lock_displaced_terminals(&self.displaced_terminals);
prune_completed_heal_statuses(&mut displaced_terminals);
terminal_completed = displaced_terminals
.get(canonical_task_id)
.filter(|terminal| matches_path(&terminal.heal_type))
.cloned();
}
match terminal_completed {
Some(completed) => TaskStateLookup::Completed(completed),
None => TaskStateLookup::NotFound,
@@ -1754,19 +1669,9 @@ impl HealManager {
let mut completed_heals = self.completed_heals.lock().await;
prune_completed_heal_statuses(&mut completed_heals);
if completed_heals
completed_heals
.values()
.any(|completed| heal_type_matches_path(&completed.heal_type, heal_path))
{
return true;
}
drop(completed_heals);
let mut displaced_terminals = lock_displaced_terminals(&self.displaced_terminals);
prune_completed_heal_statuses(&mut displaced_terminals);
displaced_terminals
.values()
.any(|terminal| heal_type_matches_path(&terminal.heal_type, heal_path))
}
/// Get task progress
+2 -15
View File
@@ -21,7 +21,6 @@ impl HealManager {
let heal_queue = self.heal_queue.clone();
let active_heals = self.active_heals.clone();
let task_aliases = self.task_aliases.clone();
let displaced_terminals = self.displaced_terminals.clone();
let mrf_repair_notice_targets = self.mrf_repair_notice_targets.clone();
let storage = self.storage.clone();
let replacement_recovery_anchors = self.replacement_recovery_anchors.clone();
@@ -482,10 +481,6 @@ impl HealManager {
let admission = admission_decision.result;
let should_notify =
matches!(admission, HealAdmissionResult::Accepted) && config.event_driven_scheduler_enable;
let displaced_terminal = admission_decision
.displaced_request
.as_ref()
.map(|request| record_displaced_terminal(&displaced_terminals, request));
if matches!(admission, HealAdmissionResult::Accepted)
&& let Some(anchor) = recovery_anchor
{
@@ -496,16 +491,8 @@ impl HealManager {
}
drop(queue);
drop(config);
if let (Some(displaced_task_id), Some(displaced_terminal)) =
(admission_decision.displaced_task_id().map(ToOwned::to_owned), displaced_terminal)
{
remove_displaced_task_aliases(
&task_aliases,
&displaced_terminals,
&displaced_task_id,
&displaced_terminal,
)
.await;
if let Some(displaced_task_id) = admission_decision.displaced_task_id {
remove_task_aliases_for_task(&task_aliases, &displaced_task_id).await;
lock_mrf_repair_notice_targets(&mrf_repair_notice_targets).remove(&displaced_task_id);
}
if matches!(admission, HealAdmissionResult::Accepted) {
+3 -25
View File
@@ -21,7 +21,6 @@ impl HealManager {
let heal_queue = self.heal_queue.clone();
let active_heals = self.active_heals.clone();
let completed_heals = self.completed_heals.clone();
let displaced_terminals = self.displaced_terminals.clone();
let task_aliases = self.task_aliases.clone();
let retrying_heals = self.retrying_heals.clone();
let mrf_repair_notice_targets = self.mrf_repair_notice_targets.clone();
@@ -54,7 +53,6 @@ impl HealManager {
heal_queue: &heal_queue,
active_heals: &active_heals,
completed_heals: &completed_heals,
displaced_terminals: &displaced_terminals,
task_aliases: &task_aliases,
retrying_heals: &retrying_heals,
mrf_repair_notice_targets: &mrf_repair_notice_targets,
@@ -73,7 +71,6 @@ impl HealManager {
heal_queue: &heal_queue,
active_heals: &active_heals,
completed_heals: &completed_heals,
displaced_terminals: &displaced_terminals,
task_aliases: &task_aliases,
retrying_heals: &retrying_heals,
mrf_repair_notice_targets: &mrf_repair_notice_targets,
@@ -101,7 +98,6 @@ impl HealManager {
heal_queue,
active_heals,
completed_heals,
displaced_terminals,
task_aliases,
retrying_heals,
mrf_repair_notice_targets,
@@ -187,7 +183,6 @@ impl HealManager {
let active_heals_clone = active_heals.clone();
let heal_queue_clone = heal_queue.clone();
let completed_heals_clone = completed_heals.clone();
let displaced_terminals_clone = displaced_terminals.clone();
let task_aliases_clone = task_aliases.clone();
let retrying_heals_clone = retrying_heals.clone();
let mrf_repair_notice_targets_clone = mrf_repair_notice_targets.clone();
@@ -368,7 +363,6 @@ impl HealManager {
let retry_heal_queue = heal_queue_clone.clone();
let retrying_heals_for_spawn = retrying_heals_clone.clone();
let retry_task_aliases = task_aliases_clone.clone();
let retry_displaced_terminals = displaced_terminals_clone.clone();
let retry_mrf_repair_notice_targets = mrf_repair_notice_targets_clone.clone();
let retry_completed_heals = completed_heals_clone.clone();
let retry_notify = notify_clone.clone();
@@ -436,14 +430,6 @@ impl HealManager {
let admission = admission_decision.result;
let should_notify = matches!(admission, HealAdmissionResult::Accepted)
&& retry_config.event_driven_scheduler_enable;
// Publish the terminal synchronously while the
// queue transition is protected. The subsequent
// queue -> retrying handoff retains the lock order
// used by operations_snapshot.
let displaced_terminal = admission_decision
.displaced_request
.as_ref()
.map(|request| record_displaced_terminal(&retry_displaced_terminals, request));
match admission {
HealAdmissionResult::Accepted => {
// Transfer ownership while holding queue -> retrying,
@@ -451,18 +437,10 @@ impl HealManager {
#[cfg(test)]
pause_retry_ownership_transition(&retry_request_id, true).await;
retrying_heals_for_spawn.lock().await.remove(&retry_request_id);
let displaced_task_id = admission_decision.displaced_task_id().map(ToOwned::to_owned);
let displaced_task_id = admission_decision.displaced_task_id;
drop(queue);
if let (Some(displaced_task_id), Some(displaced_terminal)) =
(displaced_task_id, displaced_terminal)
{
remove_displaced_task_aliases(
&retry_task_aliases,
&retry_displaced_terminals,
&displaced_task_id,
&displaced_terminal,
)
.await;
if let Some(displaced_task_id) = displaced_task_id {
remove_task_aliases_for_task(&retry_task_aliases, &displaced_task_id).await;
remove_mrf_repair_notice_targets(
&retry_mrf_repair_notice_targets,
&displaced_task_id,
+1 -262
View File
@@ -84,7 +84,6 @@ async fn process_manager_queue_once(manager: &HealManager) {
heal_queue: &manager.heal_queue,
active_heals: &manager.active_heals,
completed_heals: &manager.completed_heals,
displaced_terminals: &manager.displaced_terminals,
task_aliases: &manager.task_aliases,
retrying_heals: &manager.retrying_heals,
mrf_repair_notice_targets: &manager.mrf_repair_notice_targets,
@@ -2779,10 +2778,7 @@ async fn test_high_priority_request_displaces_lower_priority_when_queue_full() {
HealAdmissionResult::Accepted
);
assert_eq!(manager.get_queue_length().await, 1);
assert!(matches!(
manager.get_task_status(&low_id).await,
Ok(HealTaskStatus::Failed { error }) if error.contains("reason=displaced")
));
assert!(matches!(manager.get_task_status(&low_id).await, Err(Error::TaskNotFound { .. })));
assert_eq!(
manager
.get_task_status(&high_id)
@@ -2792,263 +2788,6 @@ async fn test_high_priority_request_displaces_lower_priority_when_queue_full() {
);
}
#[tokio::test]
async fn displaced_task_remains_queryable() {
let manager = HealManager::new(
Arc::new(MockStorage),
Some(HealConfig {
queue_size: 1,
..HealConfig::default()
}),
);
let mut displaced = HealRequest::new(
HealType::Bucket {
bucket: "displaced-bucket".to_string(),
},
HealOptions::default(),
HealPriority::Low,
);
displaced.id = "displaced-task".to_string();
let displaced_id = displaced.id.clone();
manager
.submit_heal_request(displaced)
.await
.expect("displaced request should queue");
let successor = HealRequest::new(
HealType::Bucket {
bucket: "successor-bucket".to_string(),
},
HealOptions::default(),
HealPriority::High,
);
manager
.submit_heal_request(successor)
.await
.expect("successor should displace low work");
let report = manager
.get_task_report(&displaced_id)
.await
.expect("displaced report should remain queryable");
assert!(matches!(report.status, HealTaskStatus::Failed { ref error } if error.contains("reason=displaced")));
}
#[tokio::test]
async fn displaced_archive_failure_keeps_queryable_terminal() {
let manager = HealManager::new(Arc::new(MockStorage), None);
let mut request = HealRequest::new(
HealType::Bucket {
bucket: "archive-failure".to_string(),
},
HealOptions::default(),
HealPriority::Low,
);
request.id = "archive-failure-task".to_string();
let request_id = request.id.clone();
// The synchronous sidecar is the authoritative fallback when the normal
// completed-task archive has no entry (the failure window that must not
// turn an Accepted ID into NotFound).
record_displaced_terminal(&manager.displaced_terminals, &request);
assert!(manager.completed_heals.lock().await.is_empty());
assert!(matches!(
manager.get_task_status(&request_id).await,
Ok(HealTaskStatus::Failed { error }) if error.contains("reason=displaced")
));
}
#[tokio::test]
async fn scheduler_retry_displacement_keeps_evicted_task_queryable() {
let manager = Arc::new(HealManager::new(
Arc::new(MockStorage),
Some(HealConfig {
queue_size: 1,
event_driven_scheduler_enable: false,
..HealConfig::default()
}),
));
let mut retry_request = HealRequest::object("retry-transition".to_string(), "object".to_string(), None);
retry_request.priority = HealPriority::High;
let retry_id = retry_request.id.clone();
manager
.submit_heal_request(retry_request)
.await
.expect("retry request should queue");
// Process exactly one queue cycle so the retry task is spawned without a
// background scheduler consuming the filler request before the retry wakes.
process_manager_queue_once(&manager).await;
tokio::time::timeout(Duration::from_secs(1), async {
loop {
if manager.retrying_heals.lock().await.contains_key(&retry_id) {
break;
}
tokio::task::yield_now().await;
}
})
.await
.expect("retry request should enter backoff");
let filler = HealRequest::new(
HealType::Bucket {
bucket: "retry-displaced-filler".to_string(),
},
HealOptions::default(),
HealPriority::Low,
);
let filler_id = filler.id.clone();
manager
.submit_heal_request(filler)
.await
.expect("filler request should occupy the queue");
tokio::time::timeout(Duration::from_secs(5), async {
loop {
if matches!(
manager.get_task_status(&filler_id).await,
Ok(HealTaskStatus::Failed { ref error }) if error.contains("reason=displaced")
) {
break;
}
tokio::time::sleep(Duration::from_millis(10)).await;
}
})
.await
.expect("retry admission should displace the filler request");
assert_eq!(manager.get_queue_length().await, 1);
assert_eq!(
manager.get_task_status(&retry_id).await.expect("retry should be queued"),
HealTaskStatus::Pending
);
}
#[tokio::test]
async fn concurrent_displacers_produce_one_terminal_generation() {
let manager = Arc::new(HealManager::new(
Arc::new(MockStorage),
Some(HealConfig {
queue_size: 1,
..HealConfig::default()
}),
));
let mut displaced = HealRequest::new(
HealType::Bucket {
bucket: "concurrent-displaced".to_string(),
},
HealOptions::default(),
HealPriority::Low,
);
displaced.id = "concurrent-displaced-task".to_string();
let displaced_id = displaced.id.clone();
manager
.submit_heal_request(displaced)
.await
.expect("initial request should queue");
let first = HealRequest::new(
HealType::Bucket {
bucket: "concurrent-successor-a".to_string(),
},
HealOptions::default(),
HealPriority::High,
);
let second = HealRequest::new(
HealType::Bucket {
bucket: "concurrent-successor-b".to_string(),
},
HealOptions::default(),
HealPriority::High,
);
let (first_result, second_result) = tokio::join!(manager.submit_heal_request(first), manager.submit_heal_request(second));
let accepted = [&first_result, &second_result]
.into_iter()
.filter(|result| matches!(result, Ok(HealAdmissionResult::Accepted)))
.count();
assert_eq!(accepted, 1, "exactly one concurrent displacer should win the full queue");
assert!(
first_result.is_ok() && second_result.is_ok(),
"the losing request should receive a typed Full result"
);
let terminals = lock_displaced_terminals(&manager.displaced_terminals);
assert_eq!(terminals.len(), 1);
assert!(terminals.contains_key(&displaced_id));
}
#[tokio::test]
async fn successor_chain_is_bounded_and_authorized() {
let manager = HealManager::new(
Arc::new(MockStorage),
Some(HealConfig {
queue_size: 1,
..HealConfig::default()
}),
);
let mut original = HealRequest::new(
HealType::Bucket {
bucket: "authorized-original".to_string(),
},
HealOptions::default(),
HealPriority::Low,
);
original.id = "authorized-original-task".to_string();
let original_id = original.id.clone();
manager.submit_heal_request(original).await.expect("original should queue");
let mut duplicate = HealRequest::new(
HealType::Bucket {
bucket: "authorized-original".to_string(),
},
HealOptions::default(),
HealPriority::Low,
);
duplicate.id = "authorized-duplicate-task".to_string();
let duplicate_id = duplicate.id.clone();
manager
.submit_heal_request(duplicate)
.await
.expect("same-target duplicate should merge");
let successor = HealRequest::new(
HealType::Bucket {
bucket: "authorized-successor".to_string(),
},
HealOptions::default(),
HealPriority::High,
);
let successor_id = successor.id.clone();
manager.submit_heal_request(successor).await.expect("successor should queue");
assert!(manager.task_aliases.lock().await.is_empty());
assert!(matches!(manager.get_task_status(&original_id).await, Ok(HealTaskStatus::Failed { .. })));
assert!(matches!(manager.get_task_status(&duplicate_id).await, Ok(HealTaskStatus::Failed { .. })));
assert_eq!(
manager
.get_task_status(&successor_id)
.await
.expect("successor should remain queued"),
HealTaskStatus::Pending
);
}
#[tokio::test]
async fn displaced_terminal_expires_after_bounded_ttl() {
let manager = HealManager::new(Arc::new(MockStorage), None);
let mut request = HealRequest::new(
HealType::Bucket {
bucket: "expires".to_string(),
},
HealOptions::default(),
HealPriority::Low,
);
request.id = "expires-task".to_string();
let request_id = request.id.clone();
record_displaced_terminal(&manager.displaced_terminals, &request);
{
let mut terminals = lock_displaced_terminals(&manager.displaced_terminals);
let entry =
Arc::get_mut(terminals.get_mut(&request_id).expect("terminal should be retained")).expect("test owns terminal entry");
entry.completed_at = SystemTime::now() - KEEP_HEAL_TASK_STATUS_DURATION - Duration::from_secs(1);
}
assert!(matches!(manager.get_task_status(&request_id).await, Err(Error::TaskNotFound { .. })));
}
#[tokio::test]
async fn test_displacing_registered_mrf_task_drops_notice_ownership() {
let storage: Arc<dyn HealStorageAPI> = Arc::new(MockStorage);
@@ -722,10 +722,6 @@ pub struct DeleteVersionsResponse {
pub errors: ::prost::alloc::vec::Vec<::prost::alloc::string::String>,
#[prost(message, optional, tag = "3")]
pub error: ::core::option::Option<Error>,
/// Senders dual-write the legacy strings and typed entries. Receivers prefer typed entries
/// when present and fall back to strings for peers that predate this field. Code zero means success.
#[prost(message, repeated, tag = "4")]
pub item_errors: ::prost::alloc::vec::Vec<Error>,
}
#[derive(Clone, PartialEq, Eq, Hash, ::prost::Message)]
pub struct ReadMultipleRequest {
-3
View File
@@ -493,9 +493,6 @@ message DeleteVersionsResponse {
bool success = 1;
repeated string errors = 2;
optional Error error = 3;
// Senders dual-write the legacy strings and typed entries. Receivers prefer typed entries
// when present and fall back to strings for peers that predate this field. Code zero means success.
repeated Error item_errors = 4;
}
message ReadMultipleRequest {
@@ -16,7 +16,7 @@ use super::persistence::DataUsageCacheLoadAttempt;
use super::*;
use crate::storage_api::scanner_io::{HTTPRangeSpec, ObjectIO};
use crate::{ScannerGetObjectReader, ScannerPutObjReader};
use rustfs_data_usage::{ReplicationAllStats, ReplicationTargetUsage};
use rustfs_data_usage::{ReplicationAllStats, ReplicationStats};
use serde_json::Value;
use std::io::Cursor;
use std::pin::Pin;
@@ -1636,7 +1636,7 @@ fn size_recursive_prunes_empty_and_preserves_threshold_replication_stats() {
replication_stats: Some(ReplicationAllStats {
targets: HashMap::from([(
"arn:test:threshold".to_string(),
ReplicationTargetUsage {
ReplicationStats {
after_threshold_count: 1,
..Default::default()
},
@@ -13,7 +13,7 @@
// limitations under the License.
use super::*;
use rustfs_data_usage::{ReplicationAllStats, ReplicationTargetUsage};
use rustfs_data_usage::{ReplicationAllStats, ReplicationStats};
const TEST_PLAN_DIGEST: DataUsageScanPlanDigest = DataUsageScanPlanDigest([7; 32]);
@@ -271,7 +271,7 @@ fn completed_data_usage_info_flattens_nested_bucket_entries() {
replication_stats: Some(ReplicationAllStats {
targets: HashMap::from([(
"arn:target".to_string(),
ReplicationTargetUsage {
ReplicationStats {
replicated_size: 2048,
replicated_count: 2,
..Default::default()
+22 -18
View File
@@ -513,13 +513,15 @@ fn sr_bucket_meta_item(bucket: String, item_type: &str) -> SRBucketMeta {
}
}
fn notify_bucket_metadata_reload(
async fn notify_bucket_metadata_reload(
bucket: String,
operation: &'static str,
request_context: Option<request_context::RequestContext>,
scanner_maintenance_change: bool,
) {
record_local_scanner_maintenance_reload(&bucket, scanner_maintenance_change);
// Keep reload detached across request cancellation, but wait before a healthy peer can serve the previous config.
let (completed_tx, completed_rx) = tokio::sync::oneshot::channel();
spawn_background_with_context(request_context, async move {
if let Some(notification_sys) = current_notification_system() {
let result = if scanner_maintenance_change {
@@ -531,7 +533,9 @@ fn notify_bucket_metadata_reload(
warn!(bucket = %bucket, error = %err, "failed to notify peers after {operation}");
}
}
let _ = completed_tx.send(());
});
let _ = completed_rx.await;
}
fn record_local_scanner_maintenance_reload(bucket: &str, scanner_maintenance_change: bool) {
@@ -1476,7 +1480,7 @@ impl DefaultBucketUsecase {
.await
.map_err(ApiError::from)?;
notify_bucket_metadata_reload(bucket.clone(), "delete bucket encryption", request_context, false);
notify_bucket_metadata_reload(bucket.clone(), "delete bucket encryption", request_context, false).await;
let item = sr_bucket_meta_item(bucket.clone(), "sse-config");
if let Err(err) = site_replication_bucket_meta_hook(item).await {
@@ -1508,7 +1512,7 @@ impl DefaultBucketUsecase {
.await
.map_err(ApiError::from)?;
notify_bucket_metadata_reload(bucket.clone(), "delete bucket cors", request_context, false);
notify_bucket_metadata_reload(bucket.clone(), "delete bucket cors", request_context, false).await;
let item = sr_bucket_meta_item(bucket.clone(), "cors-config");
if let Err(err) = site_replication_bucket_meta_hook(item).await {
@@ -1540,7 +1544,7 @@ impl DefaultBucketUsecase {
.await
.map_err(ApiError::from)?;
notify_bucket_metadata_reload(bucket.clone(), "delete bucket lifecycle", request_context, true);
notify_bucket_metadata_reload(bucket.clone(), "delete bucket lifecycle", request_context, true).await;
let item = sr_bucket_meta_item(bucket.clone(), "lc-config");
if let Err(err) = site_replication_bucket_meta_hook(item).await {
@@ -1572,7 +1576,7 @@ impl DefaultBucketUsecase {
.await
.map_err(ApiError::from)?;
notify_bucket_metadata_reload(bucket.clone(), "delete bucket policy", request_context, false);
notify_bucket_metadata_reload(bucket.clone(), "delete bucket policy", request_context, false).await;
let item = sr_bucket_meta_item(bucket.clone(), "policy");
if let Err(err) = site_replication_bucket_meta_hook(item).await {
@@ -1630,7 +1634,7 @@ impl DefaultBucketUsecase {
}
drop(targets_guard);
notify_bucket_metadata_reload(bucket.clone(), "delete bucket replication", request_context, true);
notify_bucket_metadata_reload(bucket.clone(), "delete bucket replication", request_context, true).await;
let item = sr_bucket_meta_item(bucket.clone(), "replication-config");
if let Err(err) = site_replication_bucket_meta_hook(item).await {
@@ -1655,7 +1659,7 @@ impl DefaultBucketUsecase {
.await
.map_err(ApiError::from)?;
notify_bucket_metadata_reload(bucket.clone(), "delete bucket tagging", request_context, false);
notify_bucket_metadata_reload(bucket.clone(), "delete bucket tagging", request_context, false).await;
let item = sr_bucket_meta_item(bucket.clone(), "tags");
if let Err(err) = site_replication_bucket_meta_hook(item).await {
@@ -1688,7 +1692,7 @@ impl DefaultBucketUsecase {
.await
.map_err(ApiError::from)?;
notify_bucket_metadata_reload(bucket.clone(), "delete public access block", request_context, false);
notify_bucket_metadata_reload(bucket.clone(), "delete public access block", request_context, false).await;
Ok(S3Response::with_status(DeletePublicAccessBlockOutput::default(), StatusCode::NO_CONTENT))
}
@@ -2143,7 +2147,7 @@ impl DefaultBucketUsecase {
.await
.map_err(ApiError::from)?;
notify_bucket_metadata_reload(bucket.clone(), "put bucket encryption", request_context, false);
notify_bucket_metadata_reload(bucket.clone(), "put bucket encryption", request_context, false).await;
let mut item = sr_bucket_meta_item(bucket.clone(), "sse-config");
item.sse_config = Some(
@@ -2222,7 +2226,7 @@ impl DefaultBucketUsecase {
.await
.map_err(ApiError::from)?;
notify_bucket_metadata_reload(bucket.clone(), "put bucket lifecycle", request_context, true);
notify_bucket_metadata_reload(bucket.clone(), "put bucket lifecycle", request_context, true).await;
let mut item = sr_bucket_meta_item(bucket.clone(), "lc-config");
item.expiry_lc_config =
@@ -2307,7 +2311,7 @@ impl DefaultBucketUsecase {
.await
.map_err(ApiError::from)?;
notify_bucket_metadata_reload(bucket.clone(), "put bucket notification", request_context, false);
notify_bucket_metadata_reload(bucket.clone(), "put bucket notification", request_context, false).await;
let region = resolve_notification_region(self.global_region(), request_region);
let notify = current_notify_interface_for_context(self.context.as_deref());
@@ -2412,7 +2416,7 @@ impl DefaultBucketUsecase {
.await
.map_err(ApiError::from)?;
notify_bucket_metadata_reload(bucket.clone(), "put bucket policy", request_context, false);
notify_bucket_metadata_reload(bucket.clone(), "put bucket policy", request_context, false).await;
let mut item = sr_bucket_meta_item(bucket.clone(), "policy");
item.policy = Some(serde_json::from_str(&policy).map_err(|e| s3_error!(InvalidArgument, "parse policy failed {:?}", e))?);
@@ -2447,7 +2451,7 @@ impl DefaultBucketUsecase {
.await
.map_err(ApiError::from)?;
notify_bucket_metadata_reload(bucket.clone(), "put bucket cors", request_context, false);
notify_bucket_metadata_reload(bucket.clone(), "put bucket cors", request_context, false).await;
let mut item = sr_bucket_meta_item(bucket.clone(), "cors-config");
item.cors =
@@ -2491,7 +2495,7 @@ impl DefaultBucketUsecase {
.map_err(ApiError::from)?;
drop(targets_guard);
notify_bucket_metadata_reload(bucket.clone(), "put bucket replication", request_context, true);
notify_bucket_metadata_reload(bucket.clone(), "put bucket replication", request_context, true).await;
let mut item = sr_bucket_meta_item(bucket.clone(), "replication-config");
item.replication_config = Some(
@@ -2531,7 +2535,7 @@ impl DefaultBucketUsecase {
.await
.map_err(ApiError::from)?;
notify_bucket_metadata_reload(bucket.clone(), "put public access block", request_context, false);
notify_bucket_metadata_reload(bucket.clone(), "put public access block", request_context, false).await;
Ok(S3Response::new(PutPublicAccessBlockOutput::default()))
}
@@ -2560,7 +2564,7 @@ impl DefaultBucketUsecase {
.await
.map_err(ApiError::from)?;
notify_bucket_metadata_reload(bucket.clone(), "put bucket tagging", request_context, false);
notify_bucket_metadata_reload(bucket.clone(), "put bucket tagging", request_context, false).await;
let mut item = sr_bucket_meta_item(bucket.clone(), "tags");
item.tags = Some(serialize_config(&tagging).and_then(|bytes| String::from_utf8(bytes).map_err(to_internal_error))?);
@@ -2593,7 +2597,7 @@ impl DefaultBucketUsecase {
.await
.map_err(ApiError::from)?;
notify_bucket_metadata_reload(bucket.clone(), "put bucket versioning", request_context, false);
notify_bucket_metadata_reload(bucket.clone(), "put bucket versioning", request_context, false).await;
let mut item = sr_bucket_meta_item(bucket.clone(), "version-config");
item.versioning = Some(
@@ -3044,7 +3048,7 @@ mod tests {
"{method} should identify the bucket metadata operation in reload logs"
);
let expected_reload = format!(
"notify_bucket_metadata_reload(bucket.clone(), \"{operation}\", request_context, {scanner_maintenance_change});"
"notify_bucket_metadata_reload(bucket.clone(), \"{operation}\", request_context, {scanner_maintenance_change}).await;"
);
assert!(
body.contains(&expected_reload),
+11 -43
View File
@@ -146,29 +146,6 @@ fn encode_file_info_msgpack(value: &FileInfo) -> std::result::Result<Vec<u8>, Di
encode_msgpack_with_capacity(value, "FileInfo", FILE_INFO_MSGPACK_ENCODE_CAPACITY_HINT)
}
fn encode_delete_versions_errors(disk_errors: Vec<Option<DiskError>>) -> (Vec<String>, Vec<Error>) {
let mut errors = Vec::with_capacity(disk_errors.len());
let mut item_errors = Vec::with_capacity(disk_errors.len());
for error in disk_errors {
match error {
Some(error) => {
let code = match &error {
DiskError::Io(source) if source.kind() == std::io::ErrorKind::NotFound => DiskError::FileNotFound.to_u32(),
_ => error.to_u32(),
};
let error_info = error.to_string();
errors.push(error_info.clone());
item_errors.push(Error { code, error_info });
}
None => {
errors.push(String::new());
item_errors.push(Error::default());
}
}
}
(errors, item_errors)
}
fn encode_msgpack_named<T: serde::Serialize>(value: &T, value_name: &str) -> std::result::Result<Vec<u8>, DiskError> {
let mut serializer = rmp_serde::Serializer::new(Vec::with_capacity(MSGPACK_ENCODE_CAPACITY_HINT)).with_struct_map();
value
@@ -575,7 +552,6 @@ impl NodeService {
success: false,
errors: Vec::new(),
error: Some(DiskError::other(format!("decode FileInfoVersions failed: {err}")).into()),
item_errors: Vec::new(),
}));
}
};
@@ -587,26 +563,30 @@ impl NodeService {
success: false,
errors: Vec::new(),
error: Some(DiskError::other(format!("decode DeleteOptions failed: {err}")).into()),
item_errors: Vec::new(),
}));
}
};
let (errors, item_errors) =
encode_delete_versions_errors(disk.delete_versions(&request.volume, versions, opts).await);
let errors = disk
.delete_versions(&request.volume, versions, opts)
.await
.into_iter()
.map(|error| match error {
Some(e) => e.to_string(),
None => "".to_string(),
})
.collect();
Ok(Response::new(DeleteVersionsResponse {
success: true,
errors,
error: None,
item_errors,
}))
} else {
Ok(Response::new(DeleteVersionsResponse {
success: false,
errors: Vec::new(),
error: Some(DiskError::other("cannot find disk".to_string()).into()),
item_errors: Vec::new(),
}))
}
}
@@ -1632,8 +1612,8 @@ impl NodeService {
mod tests {
use super::{
compat_response_json, decode_msgpack_or_json, decode_rename_data_request_file_info,
encode_batch_read_version_response_payloads, encode_delete_versions_errors, encode_file_info_msgpack, encode_msgpack,
encode_msgpack_named, encode_read_multiple_response_payloads, encode_rename_data_response_payloads,
encode_batch_read_version_response_payloads, encode_file_info_msgpack, encode_msgpack, encode_msgpack_named,
encode_read_multiple_response_payloads, encode_rename_data_response_payloads,
};
use crate::storage::rpc::node_service::make_server;
use crate::storage::storage_api::ReadMultipleResp;
@@ -1652,18 +1632,6 @@ mod tests {
count: u32,
}
#[test]
fn delete_versions_response_dual_writes_typed_item_errors() {
let raw_not_found = super::DiskError::Io(std::io::Error::from(std::io::ErrorKind::NotFound));
let (errors, item_errors) = encode_delete_versions_errors(vec![Some(raw_not_found), None]);
assert!(errors[0].starts_with("io error "));
assert!(errors[1].is_empty());
assert_eq!(item_errors[0].code, super::DiskError::FileNotFound.to_u32());
assert_eq!(item_errors[0].error_info, errors[0]);
assert_eq!(item_errors[1].code, 0);
}
#[tokio::test]
#[serial]
async fn handle_read_version_records_attribution_for_missing_disk() {