Compare commits

..

2 Commits

Author SHA1 Message Date
overtrue da3fd83aa7 style: cargo fmt 2026-08-22 10:11:51 +08:00
overtrue a2e7036cb1 refactor(data-usage): ReplicationStats -> ReplicationTargetUsage
Rename the data-usage crate's ReplicationStats to ReplicationTargetUsage.
Serde field names are byte-identical (only the Rust type name changed;
field identifiers that rmp encodes are untouched). An rmp round-trip test
guards against future drift.

Scanner test imports updated to match.
2026-08-22 10:11:51 +08:00
7 changed files with 379 additions and 1270 deletions
+64 -18
View File
@@ -585,9 +585,12 @@ impl VersionsHistogram {
}
}
/// Replication statistics for a single target
#[derive(Debug, Default, Clone, Serialize, Deserialize)]
pub struct ReplicationStats {
/// 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 {
pub pending_size: u64,
pub replicated_size: u64,
pub failed_size: u64,
@@ -600,7 +603,7 @@ pub struct ReplicationStats {
pub replicated_count: u64,
}
impl ReplicationStats {
impl ReplicationTargetUsage {
pub fn is_empty(&self) -> bool {
let Self {
pending_size,
@@ -636,7 +639,7 @@ impl ReplicationStats {
/// Replication statistics for all targets
#[derive(Debug, Default, Clone, Serialize, Deserialize)]
pub struct ReplicationAllStats {
pub targets: HashMap<String, ReplicationStats>,
pub targets: HashMap<String, ReplicationTargetUsage>,
pub replica_size: u64,
pub replica_count: u64,
}
@@ -649,7 +652,7 @@ impl ReplicationAllStats {
targets,
} = self;
*replica_size == 0 && *replica_count == 0 && targets.values().all(ReplicationStats::is_empty)
*replica_size == 0 && *replica_count == 0 && targets.values().all(ReplicationTargetUsage::is_empty)
}
#[deprecated(note = "use is_empty instead")]
@@ -2466,7 +2469,7 @@ mod tests {
#[test]
fn replication_stats_empty_checks_every_field() {
type SetField = fn(&mut ReplicationStats);
type SetField = fn(&mut ReplicationTargetUsage);
let cases: [(&str, SetField); 10] = [
("pending_size", |stats| stats.pending_size = 1),
@@ -2481,9 +2484,9 @@ mod tests {
("replicated_count", |stats| stats.replicated_count = 1),
];
assert!(ReplicationStats::default().is_empty());
assert!(ReplicationTargetUsage::default().is_empty());
for (field, set_nonzero) in cases {
let mut stats = ReplicationStats::default();
let mut stats = ReplicationTargetUsage::default();
set_nonzero(&mut stats);
assert!(!stats.is_empty(), "{field} must make replication stats non-empty");
}
@@ -2514,17 +2517,17 @@ mod tests {
}
let empty_targets = ReplicationAllStats {
targets: HashMap::from([("arn:test:empty".to_string(), ReplicationStats::default())]),
targets: HashMap::from([("arn:test:empty".to_string(), ReplicationTargetUsage::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(), ReplicationStats::default()),
("arn:test:empty".to_string(), ReplicationTargetUsage::default()),
(
"arn:test:non-empty".to_string(),
ReplicationStats {
ReplicationTargetUsage {
pending_count: 1,
..Default::default()
},
@@ -2565,7 +2568,7 @@ mod tests {
replication_stats: Some(ReplicationAllStats {
targets: HashMap::from([(
"arn:test:pending".to_string(),
ReplicationStats {
ReplicationTargetUsage {
pending_count: 1,
..Default::default()
},
@@ -2714,7 +2717,7 @@ mod tests {
targets: HashMap::from([
(
"arn:self-only".to_string(),
ReplicationStats {
ReplicationTargetUsage {
pending_size: 7,
pending_count: 1,
..Default::default()
@@ -2722,7 +2725,7 @@ mod tests {
),
(
"arn:shared".to_string(),
ReplicationStats {
ReplicationTargetUsage {
failed_size: 3,
failed_count: 1,
missed_threshold_size: 2,
@@ -2741,7 +2744,7 @@ mod tests {
targets: HashMap::from([
(
"arn:shared".to_string(),
ReplicationStats {
ReplicationTargetUsage {
failed_size: 5,
failed_count: 2,
after_threshold_size: 4,
@@ -2751,7 +2754,7 @@ mod tests {
),
(
"arn:other-only".to_string(),
ReplicationStats {
ReplicationTargetUsage {
replicated_size: 11,
replicated_count: 3,
..Default::default()
@@ -2993,7 +2996,9 @@ 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}"), ReplicationStats::default());
stats
.targets
.insert(format!("target-{index}"), ReplicationTargetUsage::default());
}
let encoded = rmp_serde::to_vec_named(&stats).expect("large replication target fixture should encode");
let decoded = rmp_serde::from_slice::<ReplicationAllStats>(&encoded)
@@ -3002,6 +3007,47 @@ 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 {
File diff suppressed because it is too large Load Diff
-9
View File
@@ -160,10 +160,6 @@ pub struct InstanceContext {
/// workers (scanner/heal/tier/lifecycle) without touching another instance.
/// Replaces the process-global cancel-token static.
background_cancel_token: OnceLock<CancellationToken>,
/// Serializes decommission data-movement operations with cancellation and
/// a subsequent restart. Readers are held across one object side effect;
/// the transition path takes the writer after cancelling the routine.
decommission_operation_gate: Arc<RwLock<()>>,
/// Resolves object-encryption material at the application boundary.
object_encryption_resolver: OnceLock<Arc<dyn ObjectEncryptionResolver>>,
tier_delete_journal_recovery_stores: std::sync::Mutex<HashSet<Uuid>>,
@@ -204,7 +200,6 @@ impl InstanceContext {
local_disk_set_drives: Arc::new(RwLock::new(Vec::new())),
bucket_metadata_sys: std::sync::Mutex::new(None),
background_cancel_token: OnceLock::new(),
decommission_operation_gate: Arc::new(RwLock::new(())),
object_encryption_resolver: OnceLock::new(),
tier_delete_journal_recovery_stores: std::sync::Mutex::new(HashSet::new()),
transition_transaction_recovery_stores: std::sync::Mutex::new(HashSet::new()),
@@ -223,10 +218,6 @@ impl InstanceContext {
self.lock_manager.clone()
}
pub(crate) fn decommission_operation_gate(&self) -> Arc<RwLock<()>> {
Arc::clone(&self.decommission_operation_gate)
}
/// Install the application-owned object-encryption resolver once.
pub fn set_object_encryption_resolver(
&self,
@@ -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, ReplicationStats};
use rustfs_data_usage::{ReplicationAllStats, ReplicationTargetUsage};
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(),
ReplicationStats {
ReplicationTargetUsage {
after_threshold_count: 1,
..Default::default()
},
@@ -13,7 +13,7 @@
// limitations under the License.
use super::*;
use rustfs_data_usage::{ReplicationAllStats, ReplicationStats};
use rustfs_data_usage::{ReplicationAllStats, ReplicationTargetUsage};
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(),
ReplicationStats {
ReplicationTargetUsage {
replicated_size: 2048,
replicated_count: 2,
..Default::default()
+1 -26
View File
@@ -206,13 +206,6 @@ def check_runner_selection(root: Path) -> list[str]:
return errors
def check_s3_tests_runner(root: Path) -> list[str]:
runner = (root / "scripts/s3-tests/run.sh").read_text()
if "--showlocals" in runner:
return ["scripts/s3-tests/run.sh: pytest failure diagnostics must not dump local values"]
return []
def profile_selection(root: Path, profile: str) -> str:
if not re.fullmatch(r"e2e-[a-z0-9-]+", profile):
raise ValueError(f"invalid e2e profile name: {profile}")
@@ -279,7 +272,6 @@ def validate(root: Path) -> list[str]:
errors.extend(check_e2e_modules(root))
errors.extend(check_fuzz_targets(root))
errors.extend(check_runner_selection(root))
errors.extend(check_s3_tests_runner(root))
errors.extend(check_profile_definitions(root))
return errors
@@ -349,23 +341,6 @@ class SelfTests(unittest.TestCase):
)
self.assertEqual(len(check_fuzz_targets(root)), 1)
def test_s3_runner_rejects_unbounded_failure_locals(self) -> None:
with tempfile.TemporaryDirectory() as tmp:
root = Path(tmp)
runner = root / "scripts/s3-tests/run.sh"
runner.parent.mkdir(parents=True)
runner.write_text("tox -- -vv -ra --tb=long\n")
self.assertEqual(check_s3_tests_runner(root), [])
runner.write_text("tox -- -vv -ra --showlocals --tb=long\n")
self.assertEqual(len(check_s3_tests_runner(root)), 1)
with (
mock.patch(__name__ + ".check_e2e_modules", return_value=[]),
mock.patch(__name__ + ".check_fuzz_targets", return_value=[]),
mock.patch(__name__ + ".check_runner_selection", return_value=[]),
mock.patch(__name__ + ".check_profile_definitions", return_value=[]),
):
self.assertEqual(len(validate(root)), 1)
def test_profile_listing_enforces_selection(self) -> None:
with tempfile.TemporaryDirectory() as tmp:
root = Path(tmp)
@@ -436,7 +411,7 @@ def main() -> int:
for error in errors:
print(f"ERROR: {error}", file=sys.stderr)
return 1
print("OK: e2e modules, runner selection, fuzz matrices, profiles, and bounded diagnostics are wired")
print("OK: e2e modules, runner selection, fuzz matrices, and profile guards are wired")
return 0
+1 -2
View File
@@ -1028,11 +1028,10 @@ else
fi
# Run tests from s3tests/functional
# Failure locals can contain multi-MiB request bodies; keep tracebacks without expanding local values.
set +e
S3TEST_CONF="${CONF_OUTPUT_PATH}" \
tox -- \
-vv -ra --tb=long \
-vv -ra --showlocals --tb=long \
--maxfail="${MAXFAIL}" \
--timeout="${TEST_TIMEOUT}" \
--junitxml="${ARTIFACTS_DIR}/junit.xml" \