Compare commits

..

1 Commits

Author SHA1 Message Date
overtrue 08ddffdf42 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 00:30:44 +08:00
4 changed files with 199 additions and 54 deletions
+57 -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 +2996,7 @@ 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}"), 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 +3005,42 @@ 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 {
+138 -32
View File
@@ -12,16 +12,18 @@
// See the License for the specific language governing permissions and
// limitations under the License.
use std::{collections::HashMap, time::Duration};
use jiff::Timestamp;
use serde::{Deserialize, Serialize};
/// Bitflag helper for service trace categories.
///
/// Each variant occupies a single bit so that a `TraceType` value can represent
/// an arbitrary combination of categories via bitwise OR.
use crate::heal_commands::HealResultItem;
#[derive(Debug, Clone, Copy, Serialize, Deserialize, Default)]
pub struct TraceType(u64);
impl TraceType {
// Define some constants
pub const OS: TraceType = TraceType(1 << 0);
pub const STORAGE: TraceType = TraceType(1 << 1);
pub const S3: TraceType = TraceType(1 << 2);
@@ -38,13 +40,15 @@ impl TraceType {
pub const FTP: TraceType = TraceType(1 << 13);
pub const ILM: TraceType = TraceType(1 << 14);
/// All trace categories combined. Must be updated when adding new variants.
// MetricsAll must be last.
pub const ALL: TraceType = TraceType((1 << 15) - 1);
pub fn new(t: u64) -> Self {
Self(t)
}
}
impl TraceType {
pub fn contains(&self, x: &TraceType) -> bool {
(self.0 & x.0) == x.0
}
@@ -72,38 +76,140 @@ impl TraceType {
}
}
#[derive(Debug, Default, Clone, Serialize, Deserialize)]
pub struct TraceInfo {
#[serde(rename = "type")]
trace_type: u64,
#[serde(rename = "nodename")]
node_name: String,
#[serde(rename = "funcname")]
func_name: String,
#[serde(rename = "time")]
time: Timestamp,
#[serde(rename = "path")]
path: String,
#[serde(rename = "dur")]
duration: Duration,
#[serde(rename = "bytes", skip_serializing_if = "Option::is_none")]
bytes: Option<i64>,
#[serde(rename = "msg", skip_serializing_if = "Option::is_none")]
message: Option<String>,
#[serde(rename = "error", skip_serializing_if = "Option::is_none")]
error: Option<String>,
#[serde(rename = "custom", skip_serializing_if = "Option::is_none")]
custom: Option<HashMap<String, String>>,
#[serde(rename = "http", skip_serializing_if = "Option::is_none")]
http: Option<TraceHTTPStats>,
#[serde(rename = "healResult", skip_serializing_if = "Option::is_none")]
heal_result: Option<HealResultItem>,
}
impl TraceInfo {
pub fn mask(&self) -> u64 {
TraceType::new(self.trace_type).mask()
}
}
#[derive(Debug, Default, Clone, Serialize, Deserialize)]
pub struct TraceInfoLegacy {
trace_info: TraceInfo,
#[serde(rename = "request")]
req_info: Option<TraceRequestInfo>,
#[serde(rename = "response")]
resp_info: Option<TraceResponseInfo>,
#[serde(rename = "stats")]
call_stats: Option<TraceCallStats>,
#[serde(rename = "storageStats")]
storage_stats: Option<StorageStats>,
#[serde(rename = "osStats")]
os_stats: Option<OSStats>,
}
#[derive(Debug, Default, Clone, Serialize, Deserialize)]
pub struct StorageStats {
path: String,
duration: Duration,
}
#[derive(Debug, Default, Clone, Serialize, Deserialize)]
pub struct OSStats {
path: String,
duration: Duration,
}
#[derive(Debug, Default, Clone, Serialize, Deserialize)]
pub struct TraceHTTPStats {
req_info: TraceRequestInfo,
resp_info: TraceResponseInfo,
call_stats: TraceCallStats,
}
#[derive(Debug, Default, Clone, Serialize, Deserialize)]
pub struct TraceCallStats {
input_bytes: i32,
output_bytes: i32,
latency: Duration,
time_to_first_byte: Duration,
}
#[derive(Debug, Default, Clone, Serialize, Deserialize)]
pub struct TraceRequestInfo {
time: Timestamp,
proto: String,
method: String,
#[serde(skip_serializing_if = "Option::is_none")]
path: Option<String>,
#[serde(skip_serializing_if = "Option::is_none")]
raw_query: Option<String>,
#[serde(skip_serializing_if = "Option::is_none")]
headers: Option<HashMap<String, String>>,
#[serde(skip_serializing_if = "Option::is_none")]
body: Option<Vec<u8>>,
client: String,
}
#[derive(Debug, Default, Clone, Serialize, Deserialize)]
pub struct TraceResponseInfo {
time: Timestamp,
#[serde(skip_serializing_if = "Option::is_none")]
headers: Option<HashMap<String, String>>,
#[serde(skip_serializing_if = "Option::is_none")]
body: Option<Vec<u8>>,
#[serde(skip_serializing_if = "Option::is_none")]
status_code: Option<i32>,
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn trace_type_contains_and_overlaps() {
let mut combined = TraceType::default();
combined.merge(&TraceType::S3);
combined.merge(&TraceType::HEALING);
fn trace_timestamps_serialize_as_rfc3339_utc() {
let timestamp = Timestamp::constant(1_700_000_000, 123_456_000);
let trace = TraceInfo {
time: timestamp,
http: Some(TraceHTTPStats {
req_info: TraceRequestInfo {
time: timestamp,
..Default::default()
},
resp_info: TraceResponseInfo {
time: timestamp,
..Default::default()
},
..Default::default()
}),
..Default::default()
};
assert!(combined.contains(&TraceType::S3));
assert!(combined.contains(&TraceType::HEALING));
assert!(!combined.contains(&TraceType::SCANNER));
assert!(combined.overlaps(&TraceType::S3));
assert!(combined.overlaps(&TraceType::HEALING));
assert!(!combined.overlaps(&TraceType::SCANNER));
}
#[test]
fn trace_type_set_if() {
let mut tt = TraceType::default();
tt.set_if(true, &TraceType::OS);
tt.set_if(false, &TraceType::S3);
assert!(tt.contains(&TraceType::OS));
assert!(!tt.contains(&TraceType::S3));
}
#[test]
fn trace_type_single_type() {
assert!(TraceType::S3.single_type());
let mut combined = TraceType::S3;
combined.merge(&TraceType::HEALING);
assert!(!combined.single_type());
let value = serde_json::to_value(trace).expect("trace should serialize");
assert_eq!(value["time"], "2023-11-14T22:13:20.123456Z");
assert_eq!(value["http"]["req_info"]["time"], "2023-11-14T22:13:20.123456Z");
assert_eq!(value["http"]["resp_info"]["time"], "2023-11-14T22:13:20.123456Z");
let trace: TraceInfo = serde_json::from_value(value).expect("trace should deserialize");
assert_eq!(trace.time, timestamp);
let http = trace.http.expect("http trace should deserialize");
assert_eq!(http.req_info.time, timestamp);
assert_eq!(http.resp_info.time, timestamp);
}
}
@@ -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()