fix(replication): bin transfer summaries at 128 MiB and keep window refresh off the hot path

Second review round:

- update_xfer_rate split at 1 MiB while the minio-go transferSummary
  labels (and RustFS's own worker-pool split) mean >= 128 MiB for
  Large, so a 2 MiB replication reported under Large with Small stuck
  at zero. The producer now bins on MIN_LARGE_OBJ_SIZE; a MetricsV2
  assertion covers 2 MiB / 127 MiB / exactly 128 MiB.
- add_size no longer recomputes the rolling windows: two full
  one-hour-deque scans per failure under the bucket-stats write lock
  made failure bursts quadratic (30k events ~2.1s). The windows are
  stamped only at the collection point (get_latest_replication_stats,
  which serves both the local leg and the peer RPC); the aggregation
  regression now drives that path explicitly before the RPC round trip
  and merge.

crates/ecstore/src/api/mod.rs

@@ -184,17 +184,18 @@ pub mod bucket {
             mrf_backlog_observability_snapshot,
         };
         pub use crate::bucket::replication::{
-            BucketReplicationResyncStatus, BucketReplicationStats, BucketStats, DeleteReplicationConfigSnapshot,
-            DeletedObjectReplicationInfo, DurableMrfBacklog, DynReplicationPool, MrfOpKind, MrfReplicateEntry,
-            MustReplicateOptions, ObjectOpts, REMOTE_TARGET_CAPABILITY_CONTRACT_VERSION, REMOTE_TARGET_UNSUPPORTED_FIELDS,
-            REMOTE_TARGET_WRITABLE_FIELDS, REPLICATE_INCOMING_DELETE, REPLICATION_CAPABILITY_CONTRACT_VERSION,
-            REPLICATION_READ_ONLY_HISTORICAL_FIELDS, REPLICATION_WRITABLE_FIELDS, ReplicateDecision, ReplicateObjectInfo,
-            ReplicationBatchAdmission, ReplicationConfig, ReplicationConfigStructureError, ReplicationConfigurationExt,
-            ReplicationDeleteScheduleInput, ReplicationDeleteStateSource, ReplicationHealQueueResult, ReplicationObjectBridge,
-            ReplicationObjectIO, ReplicationOperation, ReplicationPoolTrait, ReplicationPriority, ReplicationQueueAdmission,
-            ReplicationScannerBridge, ReplicationState, ReplicationStats, ReplicationStatusType, ReplicationStorage,
-            ReplicationTargetValidationError, ReplicationType, ResyncOpts, ResyncStatusType, RuntimeReplicationTargetBacklog,
-            TargetReplicationResyncStatus, VersionPurgeStatusType, commit_force_delete_intent, complete_force_delete_intent,
+            BucketReplicationResyncStatus, BucketReplicationStat, BucketReplicationStats, BucketStats,
+            DeleteReplicationConfigSnapshot, DeletedObjectReplicationInfo, DurableMrfBacklog, DynReplicationPool, InQueueMetric,
+            MrfOpKind, MrfReplicateEntry, MustReplicateOptions, ObjectOpts, REMOTE_TARGET_CAPABILITY_CONTRACT_VERSION,
+            REMOTE_TARGET_UNSUPPORTED_FIELDS, REMOTE_TARGET_WRITABLE_FIELDS, REPLICATE_INCOMING_DELETE,
+            REPLICATION_CAPABILITY_CONTRACT_VERSION, REPLICATION_READ_ONLY_HISTORICAL_FIELDS, REPLICATION_WRITABLE_FIELDS,
+            ReplicateDecision, ReplicateObjectInfo, ReplicationBatchAdmission, ReplicationConfig,
+            ReplicationConfigStructureError, ReplicationConfigurationExt, ReplicationDeleteScheduleInput,
+            ReplicationDeleteStateSource, ReplicationHealQueueResult, ReplicationObjectBridge, ReplicationObjectIO,
+            ReplicationOperation, ReplicationPoolTrait, ReplicationPriority, ReplicationQueueAdmission, ReplicationScannerBridge,
+            ReplicationState, ReplicationStats, ReplicationStatusType, ReplicationStorage, ReplicationTargetValidationError,
+            ReplicationType, ResyncOpts, ResyncStatusType, RuntimeReplicationTargetBacklog, TargetReplicationResyncStatus,
+            VersionPurgeStatusType, XferStats, commit_force_delete_intent, complete_force_delete_intent,
             delete_replication_state_from_config, delete_replication_version_id, get_global_replication_pool,
             get_global_replication_stats, init_background_replication, invalid_replication_config_status_field,
             persist_force_delete_intent, read_durable_mrf_backlog, replication_state_to_filemeta, replication_status_to_filemeta,

crates/ecstore/src/bucket/replication/mod.rs

@@ -81,6 +81,6 @@ pub use replication_queue_boundary::{
 pub use replication_resync_boundary::{BucketReplicationResyncStatus, ResyncOpts, TargetReplicationResyncStatus};
 pub use replication_scanner_bridge::ReplicationScannerBridge;
 pub use replication_state::{ReplicationStats, RuntimeReplicationTargetBacklog};
-pub use replication_stats_boundary::{BucketReplicationStats, BucketStats};
+pub use replication_stats_boundary::{BucketReplicationStat, BucketReplicationStats, BucketStats, InQueueMetric, XferStats};
 pub use replication_storage_boundary::{ReplicationObjectIO, ReplicationStorage};
 pub(crate) use replication_target_config_bridge::ReplicationTargetConfigBridge;

crates/ecstore/src/bucket/replication/replication_state.rs

@@ -704,6 +704,12 @@ impl ReplicationStats {
         } else {
             BucketReplicationStats::new()
         };
+        // Stamp the serializable failure windows from the live samples: the
+        // samples themselves do not cross the peer-RPC wire, so this snapshot
+        // is what cluster aggregation and the metrics endpoints see.
+        for stat in replication_stats.stats.values_mut() {
+            stat.fail_stats.refresh_windows();
+        }
         let uptime = if cache.contains_key(bucket) {
             SystemTime::now()
                 .duration_since(SystemTime::UNIX_EPOCH)

crates/ecstore/src/bucket/replication/replication_stats_boundary.rs

@@ -15,7 +15,9 @@
 #[cfg(test)]
 pub(crate) use rustfs_replication::FailStats;
 pub(crate) use rustfs_replication::{
-    ActiveWorkerStat, BucketReplicationStat, InQueueMetric, ProxyMetric, ProxyStatsCache, QueueCache, ReplicationMetricScope,
-    SRMetricsSummary, XferStats,
+    ActiveWorkerStat, ProxyMetric, ProxyStatsCache, QueueCache, ReplicationMetricScope, SRMetricsSummary,
 };
-pub use rustfs_replication::{BucketReplicationStats, BucketStats};
+// Public so the admin wire DTOs (rustfs/src/admin/replication_metrics_wire.rs)
+// can project the internal stats onto the minio-go response shapes through
+// the storage_api facade chain.
+pub use rustfs_replication::{BucketReplicationStat, BucketReplicationStats, BucketStats, InQueueMetric, XferStats};

crates/replication/src/stats.rs

@@ -520,6 +520,14 @@ struct FailureSample {
 pub struct FailStats {
     pub count: i64,
     pub size: i64,
+    /// Rolling-window snapshots refreshed at collection time
+    /// ([`Self::refresh_windows`]). The raw samples (`recent`) are process
+    /// local (serde-skipped), so these fields are what survives the peer-RPC
+    /// wire and [`Self::merge`]-based cluster aggregation.
+    #[serde(default)]
+    pub last_minute: FailedMetric,
+    #[serde(default)]
+    pub last_hour: FailedMetric,
     #[serde(skip)]
     recent: VecDeque<FailureSample>,
 }
@@ -537,6 +545,17 @@ impl FailStats {
         self.prune(observed_at);
     }
 
+    /// Recompute the serializable rolling-window snapshots from the local
+    /// samples. Called at the collection point (per-node stats snapshot),
+    /// never on the failure hot path — the two deque scans are O(window) and
+    /// `add_size` runs under the bucket-stats write lock. Only meaningful on
+    /// the live per-node struct: a deserialized or merged struct has no
+    /// samples, and refreshing it would wipe the aggregated windows.
+    pub fn refresh_windows(&mut self) {
+        self.last_minute = self.recent_since(Duration::from_secs(60));
+        self.last_hour = self.recent_since(Duration::from_secs(3600));
+    }
+
     fn prune(&mut self, observed_at: Instant) {
         while self
             .recent
@@ -565,6 +584,16 @@ impl FailStats {
         Self {
             count: self.count.saturating_add(other.count),
             size: self.size.saturating_add(other.size),
+            // The window snapshots sum across nodes; the raw samples do not
+            // travel and stay empty on aggregated structs.
+            last_minute: FailedMetric {
+                count: self.last_minute.count.saturating_add(other.last_minute.count),
+                size: self.last_minute.size.saturating_add(other.last_minute.size),
+            },
+            last_hour: FailedMetric {
+                count: self.last_hour.count.saturating_add(other.last_hour.count),
+                size: self.last_hour.size.saturating_add(other.last_hour.size),
+            },
             recent: VecDeque::new(),
         }
     }
@@ -636,7 +665,9 @@ impl BucketReplicationStat {
     }
 
     pub fn update_xfer_rate(&mut self, size: i64, duration: Duration) {
-        if size > 1024 * 1024 {
+        // Same boundary as the worker-pool split and minio-go's
+        // Large/Small transfer-summary labels: >= 128 MiB is "large".
+        if size >= crate::runtime::MIN_LARGE_OBJ_SIZE {
             self.xfer_rate_lrg.add_size(size, duration);
         } else {
             self.xfer_rate_sml.add_size(size, duration);

rustfs/src/admin/handlers/replication.rs

@@ -535,8 +535,13 @@ impl Operation for GetReplicationMetricsHandler {
 
         let bucket_stats = cluster_replication_stats(bucket, app_context_from_req(&req)).await;
 
-        let data = serde_json::to_vec(&bucket_stats.replication_stats)
-            .map_err(|_| S3Error::with_message(S3ErrorCode::InternalError, "serialize failed"))?;
+        // Same minio-go `replication.Metrics` wire shape as
+        // `?replication-metrics` — the internal snake_case stats are the peer
+        // RPC wire format and must not leak here.
+        let data = serde_json::to_vec(&crate::admin::replication_metrics_wire::MetricsWire::from(
+            &bucket_stats.replication_stats,
+        ))
+        .map_err(|_| S3Error::with_message(S3ErrorCode::InternalError, "serialize failed"))?;
         let mut headers = HeaderMap::new();
         headers.insert(CONTENT_TYPE, HeaderValue::from_static("application/json"));
         Ok(S3Response::with_headers((StatusCode::OK, Body::from(data)), headers))

rustfs/src/admin/handlers/site_replication.rs

@@ -3004,9 +3004,6 @@ fn reconcile_site_replication_wiring() -> std::pin::Pin<Box<dyn std::future::Fut
                 "admin site replication state"
             );
         }
-        // Failed peer deliveries recorded in the retry queue; runs behind the
-        // same lifecycle guard and pending_* gates as the reconcilers above.
-        drain_site_replication_retry_queue().await;
     })
 }
 
@@ -3956,7 +3953,7 @@ async fn persist_site_replication_repair_task(
         match failure.as_deref() {
             Some(error) => upsert_site_replication_retry_event(&mut state.retry_queue, &peer, &path, error, None),
             None => {
-                dequeue_site_replication_retry_events_including_escalated(&mut state.retry_queue, &peer, &path);
+                dequeue_site_replication_retry_events(&mut state.retry_queue, &peer, &path);
             }
         }
         Ok(())
@@ -6044,20 +6041,6 @@ fn dequeue_site_replication_retry_events(queue: &mut Vec<SiteReplicationRetryEve
     settle_site_replication_retry_events(queue, peer, path, None)
 }
 
-/// Repair-path settlement: also clears snapshot-escalated entries. Running a
-/// repair is the operator's explicit accountability transfer for the
-/// possibly-unreplayed deletion the marker records; ordinary delivery
-/// successes must not clear it (see [`settle_site_replication_retry_events`]).
-fn dequeue_site_replication_retry_events_including_escalated(
-    queue: &mut Vec<SiteReplicationRetryEvent>,
-    peer: &PeerInfo,
-    path: &str,
-) -> usize {
-    let before = queue.len();
-    queue.retain(|event| !retry_event_matches(event, peer, path));
-    before.saturating_sub(queue.len())
-}
-
 /// Remove the retry events for (peer, path) that `generation` is entitled to
 /// settle. A successful delivery only proves the peer reached the state the
 /// delivery carried: while it was in flight another edit can commit, fail its
@@ -6077,13 +6060,6 @@ fn settle_site_replication_retry_events(
         if !retry_event_matches(event, peer, path) {
             return true;
         }
-        // A snapshot-escalated entry records a possibly-unreplayed deletion.
-        // Collapsed paths are shared by every entity, so a later successful
-        // delivery of a DIFFERENT item proves nothing about the deleted one —
-        // only a repair settles it (dequeue_..._including_escalated).
-        if event.last_error == SITE_REPLICATION_RETRY_SNAPSHOT_REPLAYED_MARKER {
-            return true;
-        }
         match (generation, event.edit_generation) {
             (Some(settled), Some(failed)) => failed > settled,
             _ => false,
@@ -6161,12 +6137,7 @@ async fn enqueue_site_replication_retry_event_for_generation(
     let path_owned = path.to_string();
     let error_text = error.to_string();
     let result = update_site_replication_state(move |state| {
-        // A peer that left the state can never drain its entries again
-        // (remove_sites already pruned them); recording a late failure for it
-        // would only pollute retry_stats until the queue cap evicts it.
-        if state.peers.contains_key(&peer_owned.deployment_id) {
-            upsert_site_replication_retry_event(&mut state.retry_queue, &peer_owned, &path_owned, &error_text, generation);
-        }
+        upsert_site_replication_retry_event(&mut state.retry_queue, &peer_owned, &path_owned, &error_text, generation);
         Ok(())
     })
     .await;
@@ -6200,420 +6171,6 @@ fn retry_event_replayed_by_bootstrap(event: &SiteReplicationRetryEvent) -> bool
     )
 }
 
-/// Exponential backoff base for the background retry drain, aligned with the
-/// reconcile cadence (`site_replication_reconcile::RECONCILE_INTERVAL`).
-const SITE_REPLICATION_RETRY_DRAIN_BASE_BACKOFF_SECS: i64 = 600;
-/// Backoff ceiling: a permanently failed peer is still probed daily.
-const SITE_REPLICATION_RETRY_DRAIN_MAX_BACKOFF_SECS: i64 = 86_400;
-
-/// What the background drain may do for one retry event. Everything not
-/// representable here is operator territory (manual repair).
-#[derive(Debug, Clone, PartialEq, Eq)]
-enum RetryDrainAction {
-    /// Constant-path IAM item deliveries collapse into one queue entry per
-    /// peer and their bodies are not persisted; the only faithful replay is
-    /// the current IAM snapshot from the bootstrap plan.
-    IamSnapshot,
-    /// Same collapse for bucket-meta deliveries: replay the bucket metadata
-    /// snapshot from the bootstrap plan.
-    BucketMetadataSnapshot,
-    /// A self-contained bucket op the bootstrap plan can re-derive for its
-    /// bucket (`make-with-versioning` / `configure-replication`).
-    BucketOpReplay { operation: String, bucket: String },
-    /// Re-send the current peer records under a fresh edit generation.
-    PeerEdit,
-}
-
-fn classify_site_replication_retry_event(event: &SiteReplicationRetryEvent) -> Option<RetryDrainAction> {
-    if event.path.starts_with("internal:") {
-        // Marker records store payloads in `last_error` (legacy
-        // pending-endpoint-refresh backup); they are not delivery failures.
-        return None;
-    }
-    if event.last_error == SITE_REPLICATION_RETRY_SNAPSHOT_REPLAYED_MARKER {
-        // Already snapshot-replayed once for this failure episode; a possible
-        // deletion cannot be replayed from a snapshot, so re-sending daily
-        // proves nothing. A new hook failure overwrites the marker.
-        return None;
-    }
-    let base_path = event.path.split_once('?').map(|(base, _)| base).unwrap_or(&event.path);
-    match base_path {
-        "/rustfs/admin/v3/site-replication/peer/iam-item" => Some(RetryDrainAction::IamSnapshot),
-        "/rustfs/admin/v3/site-replication/peer/bucket-meta" => Some(RetryDrainAction::BucketMetadataSnapshot),
-        SITE_REPLICATION_PEER_EDIT_PATH => Some(RetryDrainAction::PeerEdit),
-        SITE_REPLICATION_PEER_BUCKET_OPS_PATH => {
-            let operation = retry_bucket_operation(&event.path)?;
-            if !matches!(
-                operation.as_str(),
-                SITE_REPLICATION_BUCKET_OP_MAKE_WITH_VERSIONING | SITE_REPLICATION_BUCKET_OP_CONFIGURE_REPLICATION
-            ) {
-                // Destructive ops (delete-bucket / force-delete-bucket) are
-                // operator territory: replaying them against a peer whose
-                // bucket was since recreated is irreversible.
-                return None;
-            }
-            let bucket = retry_bucket_name(&event.path)?;
-            Some(RetryDrainAction::BucketOpReplay { operation, bucket })
-        }
-        _ => None,
-    }
-}
-
-fn retry_bucket_name(path: &str) -> Option<String> {
-    let (_, query) = path.split_once('?')?;
-    form_urlencoded::parse(query.as_bytes())
-        .find_map(|(key, value)| (key == "bucket" && !value.is_empty()).then(|| value.into_owned()))
-}
-
-/// A collapsed (constant-path) retry event after a successful snapshot
-/// resend is escalated with this marker instead of being cleared: the
-/// snapshot replays every entity that still exists, but a failed *deletion*
-/// leaves no task in the plan, so remote absence is unproven and the entry
-/// must stay operator-visible until a later full delivery or a manual repair
-/// settles it. The drain skips marked entries so the once-per-episode
-/// snapshot is not re-sent daily; a new hook failure overwrites the marker
-/// and re-arms the drain.
-const SITE_REPLICATION_RETRY_SNAPSHOT_REPLAYED_MARKER: &str = "snapshot replayed; a failed deletion cannot be replayed from a snapshot — run site replication repair or re-deliver to settle";
-
-/// Escalate a collapsed retry event after its snapshot resend succeeded,
-/// unless a newer failure was recorded after `snapshot_updated_at` (that
-/// failure belongs to a newer local commit the snapshot did not contain and
-/// must keep the entry drain-eligible).
-fn escalate_site_replication_retry_events_up_to(
-    queue: &mut [SiteReplicationRetryEvent],
-    peer: &PeerInfo,
-    path: &str,
-    snapshot_updated_at: Option<OffsetDateTime>,
-) -> usize {
-    let mut escalated = 0usize;
-    for event in queue.iter_mut() {
-        if !retry_event_matches(event, peer, path) {
-            continue;
-        }
-        let newer_failure_recorded = match (event.updated_at, snapshot_updated_at) {
-            (Some(current), Some(seen)) => current > seen,
-            (Some(_), None) => true,
-            (None, _) => false,
-        };
-        if newer_failure_recorded {
-            continue;
-        }
-        event.failed = true;
-        event.retry_count = event.retry_count.max(SITE_REPLICATION_RETRY_FAILED_AFTER);
-        event.last_error = SITE_REPLICATION_RETRY_SNAPSHOT_REPLAYED_MARKER.to_string();
-        escalated += 1;
-    }
-    escalated
-}
-
-async fn escalate_site_replication_retry_event_up_to(peer: &PeerInfo, path: &str, snapshot_updated_at: Option<OffsetDateTime>) {
-    let peer_owned = peer.clone();
-    let path_owned = path.to_string();
-    let result = update_site_replication_state(move |state| {
-        escalate_site_replication_retry_events_up_to(&mut state.retry_queue, &peer_owned, &path_owned, snapshot_updated_at);
-        Ok(())
-    })
-    .await;
-
-    if let Err(err) = result {
-        warn!(
-            component = LOG_COMPONENT_ADMIN,
-            subsystem = LOG_SUBSYSTEM_SITE_REPLICATION,
-            event = EVENT_ADMIN_SITE_REPLICATION_STATE,
-            peer = %peer.endpoint,
-            deployment_id = %peer.deployment_id,
-            path,
-            error = ?err,
-            "failed to escalate site replication retry event"
-        );
-    }
-}
-
-/// Whether the drain may attempt this event now.
-fn site_replication_retry_backoff_elapsed(event: &SiteReplicationRetryEvent, now: OffsetDateTime) -> bool {
-    let Some(updated_at) = event.updated_at else {
-        return true;
-    };
-    // 600 * 2^8 already exceeds the daily ceiling; capping the shift keeps
-    // the arithmetic overflow-free for any persisted retry_count.
-    let exponent = event.retry_count.saturating_sub(1).min(8);
-    let delay = (SITE_REPLICATION_RETRY_DRAIN_BASE_BACKOFF_SECS << exponent).min(SITE_REPLICATION_RETRY_DRAIN_MAX_BACKOFF_SECS);
-    now.unix_timestamp().saturating_sub(updated_at.unix_timestamp()) >= delay
-}
-
-/// The subset of the retry queue the background drain is allowed to touch.
-fn actionable_site_replication_retry_events(state: &SiteReplicationState, now: OffsetDateTime) -> Vec<SiteReplicationRetryEvent> {
-    state
-        .retry_queue
-        .iter()
-        .filter(|event| classify_site_replication_retry_event(event).is_some())
-        .filter(|event| state.peers.contains_key(&event.peer_deployment_id))
-        .filter(|event| site_replication_retry_backoff_elapsed(event, now))
-        .cloned()
-        .collect()
-}
-
-/// Background consumer for the retry queue, run from the reconcile tick.
-///
-/// Scope: this settles "delivered once and failed" entries whose replay is
-/// faithful (bucket ops, peer edits). Collapsed iam-item / bucket-meta
-/// entries are snapshot-resent and then *escalated*, not cleared — a failed
-/// deletion leaves no task in the snapshot, so remote absence stays unproven
-/// until a later delivery or a manual repair. A hook that never fired (crash
-/// between the local commit and the send) leaves no entry at all, so the
-/// drain is not a full cross-site diff-heal; manual repair remains the
-/// authoritative catch-all.
-async fn drain_site_replication_retry_queue() {
-    if let Err(err) = drain_site_replication_retry_queue_inner().await {
-        warn!(
-            event = EVENT_ADMIN_SITE_REPLICATION_STATE,
-            component = LOG_COMPONENT_ADMIN,
-            subsystem = LOG_SUBSYSTEM_SITE_REPLICATION,
-            result = "retry_drain_failed",
-            error = ?err,
-            "admin site replication state"
-        );
-    }
-}
-
-async fn drain_site_replication_retry_queue_inner() -> S3Result<()> {
-    let Some(runtime) = runtime_site_replication_targets().await? else {
-        return Ok(());
-    };
-    let actionable = actionable_site_replication_retry_events(&runtime.state, OffsetDateTime::now_utc());
-    if actionable.is_empty() {
-        return Ok(());
-    }
-    let Some(store) = current_object_store_handle() else {
-        return Ok(());
-    };
-    if runtime.state.pending_endpoint_refresh.is_some()
-        || runtime.state.pending_remove.is_some()
-        || runtime.state.pending_rotation.is_some()
-    {
-        // The tick-level gate ran before the reconcilers; a multi-step flow
-        // (endpoint refresh commits its pending marker without the lifecycle
-        // guard) may have started since. Re-check on the fresh state.
-        return Ok(());
-    }
-    // Serialize against operator repair execution. This does NOT close the
-    // dry-run -> execute window (dry-run takes no lock): a drain settling a
-    // replayable bucket-op entry in that window changes the preflight token
-    // and execute fails safe with "preflight is stale" — the operator
-    // re-runs the dry-run. Lock order matches repair: lifecycle guard (held
-    // by the reconcile tick) -> repair execution lock -> state object lock
-    // inside the send bookkeeping. An operator repair holding the lock makes
-    // this tick skip after the lock-acquire timeout.
-    with_config_object_write_lock(store, SITE_REPLICATION_REPAIR_EXECUTION_LOCK_PATH.to_string(), move || async move {
-        drain_site_replication_retry_queue_locked(runtime, actionable).await
-    })
-    .await
-    .map_err(ApiError::from)?
-}
-
-async fn drain_site_replication_retry_queue_locked(
-    runtime: SiteReplicationRuntime,
-    events: Vec<SiteReplicationRetryEvent>,
-) -> S3Result<()> {
-    let needs_plan = events
-        .iter()
-        .any(|event| !matches!(classify_site_replication_retry_event(event), Some(RetryDrainAction::PeerEdit)));
-    // The plan is a full local snapshot (buckets + IAM); build it once per
-    // tick and only when a snapshot resend is actually due.
-    let plan = if needs_plan {
-        let info = build_sr_info(&runtime.state, &runtime.local_peer).await?;
-        Some(site_replication_bootstrap_plan(&info)?)
-    } else {
-        None
-    };
-
-    let mut events_by_peer: BTreeMap<String, Vec<SiteReplicationRetryEvent>> = BTreeMap::new();
-    for event in events {
-        events_by_peer
-            .entry(event.peer_deployment_id.clone())
-            .or_default()
-            .push(event);
-    }
-
-    let mut settled = 0usize;
-    let mut failures = 0usize;
-    for (deployment_id, peer_events) in events_by_peer {
-        let Some(peer) = runtime.state.peers.get(&deployment_id) else {
-            continue;
-        };
-        if deployment_id == runtime.local_peer.deployment_id
-            || same_identity_endpoint(&peer.endpoint, &runtime.local_peer.endpoint)
-        {
-            continue;
-        }
-        let transport = match PeerTransport::for_runtime_peer(peer).await {
-            Ok(transport) => transport,
-            Err(err) => {
-                // Record the attempt so backoff advances for an unreachable
-                // peer instead of re-dialing it every tick.
-                for event in &peer_events {
-                    enqueue_site_replication_retry_event(peer, &event.path, &err).await;
-                }
-                failures += peer_events.len();
-                continue;
-            }
-        };
-        for event in peer_events {
-            let Some(action) = classify_site_replication_retry_event(&event) else {
-                continue;
-            };
-            match drain_one_site_replication_retry_event(&runtime, peer, &transport, &event, action, plan.as_ref()).await {
-                Ok(true) => settled += 1,
-                Ok(false) => {}
-                Err(_) => failures += 1,
-            }
-        }
-    }
-
-    if settled > 0 || failures > 0 {
-        info!(
-            event = EVENT_ADMIN_SITE_REPLICATION_STATE,
-            component = LOG_COMPONENT_ADMIN,
-            subsystem = LOG_SUBSYSTEM_SITE_REPLICATION,
-            result = "retry_drain_settled",
-            settled,
-            failures,
-            "admin site replication state"
-        );
-    }
-    Ok(())
-}
-
-/// Replay one retry event against its peer. Returns `Ok(true)` when the
-/// event was settled (delivered, or provably stale), `Ok(false)` when it was
-/// skipped, and `Err` after a failed delivery (already re-queued with an
-/// incremented retry count).
-async fn drain_one_site_replication_retry_event(
-    runtime: &SiteReplicationRuntime,
-    peer: &PeerInfo,
-    transport: &PeerTransport,
-    event: &SiteReplicationRetryEvent,
-    action: RetryDrainAction,
-    plan: Option<&SiteReplicationBootstrapPlan>,
-) -> S3Result<bool> {
-    let access_key = &runtime.state.service_account_access_key;
-    let secret_key = &runtime.service_account_secret_key;
-    match action {
-        RetryDrainAction::IamSnapshot | RetryDrainAction::BucketMetadataSnapshot => {
-            let Some(plan) = plan else {
-                return Ok(false);
-            };
-            let tasks: Vec<SiteReplicationRepairTask<'_>> = match action {
-                RetryDrainAction::IamSnapshot => plan.iam_items.iter().map(SiteReplicationRepairTask::Iam).collect(),
-                _ => plan
-                    .bucket_items
-                    .iter()
-                    .map(SiteReplicationRepairTask::BucketMetadata)
-                    .collect(),
-            };
-            for task in &tasks {
-                if let Err(err) = task.send(transport, access_key, secret_key).await {
-                    enqueue_site_replication_retry_event(peer, &event.path, &err).await;
-                    return Err(err);
-                }
-            }
-            // The snapshot replays every entity that still exists, but a
-            // failed *deletion* leaves no task in the plan — remote absence
-            // is unproven, so escalate (operator-visible, drain-idle) instead
-            // of clearing. Conditional on the snapshot timestamp: a hook
-            // failure recorded while this snapshot was in flight belongs to a
-            // newer commit and keeps the entry drain-eligible.
-            escalate_site_replication_retry_event_up_to(peer, &event.path, event.updated_at).await;
-            Ok(true)
-        }
-        RetryDrainAction::BucketOpReplay { operation, bucket } => {
-            let Some(plan) = plan else {
-                return Ok(false);
-            };
-            // Replay from the CURRENT plan, never the recorded path: the
-            // recorded query can carry an expired one-shot bootstrap token or
-            // a stale createdAt.
-            let make_op = operation == SITE_REPLICATION_BUCKET_OP_MAKE_WITH_VERSIONING;
-            let paths = if make_op {
-                &plan.bucket_make_ops
-            } else {
-                &plan.bucket_configure_ops
-            };
-            let tasks: Vec<SiteReplicationRepairTask<'_>> = paths
-                .iter()
-                .filter(|path| retry_bucket_name(path).as_deref() == Some(bucket.as_str()))
-                .map(|path| {
-                    if make_op {
-                        SiteReplicationRepairTask::BucketMake(path)
-                    } else {
-                        SiteReplicationRepairTask::Replication(path)
-                    }
-                })
-                .collect();
-            if tasks.is_empty() {
-                // The bucket left the plan (deleted, or replication no longer
-                // configured): the recorded intent is stale, settle it.
-                dequeue_site_replication_retry_event(peer, &event.path).await;
-                return Ok(true);
-            }
-            for task in &tasks {
-                if let Err(err) = task.send(transport, access_key, secret_key).await {
-                    enqueue_site_replication_retry_event(peer, &event.path, &err).await;
-                    return Err(err);
-                }
-            }
-            dequeue_site_replication_retry_event(peer, &event.path).await;
-            Ok(true)
-        }
-        RetryDrainAction::PeerEdit => {
-            // The recorded generation is stale by definition — the receiver
-            // fences it. Allocate a fresh generation and re-send the current
-            // peer records (a superset of the failed body; the receiver
-            // upserts), all inside one state transaction so the fence and the
-            // bodies agree.
-            let target_id = peer.deployment_id.clone();
-            let (generation, bodies) = update_site_replication_state(move |state| {
-                if !state.peers.contains_key(&target_id) {
-                    return Ok((None, Vec::new()));
-                }
-                Ok((Some(next_peer_edit_generation(state)), state.peers.values().cloned().collect::<Vec<_>>()))
-            })
-            .await?;
-            let Some(generation) = generation else {
-                // Peer left between the snapshot and now; the queue entry was
-                // already pruned by remove_sites.
-                return Ok(false);
-            };
-            let local_deployment_id = Some(runtime.local_peer.deployment_id.as_str()).filter(|id| !id.is_empty());
-            let edit_path = peer_edit_path_with_fence(local_deployment_id, generation);
-            let delivery_fence = local_deployment_id.is_some().then_some(generation);
-            for body in &bodies {
-                if let Err(err) = send_peer_admin_request_with_client(
-                    &transport.client,
-                    &transport.connection,
-                    &edit_path,
-                    access_key,
-                    secret_key,
-                    body,
-                )
-                .await
-                {
-                    enqueue_site_replication_retry_event_for_generation(
-                        peer,
-                        SITE_REPLICATION_PEER_EDIT_PATH,
-                        &err,
-                        delivery_fence,
-                    )
-                    .await;
-                    return Err(err);
-                }
-            }
-            dequeue_site_replication_retry_event_for_generation(peer, SITE_REPLICATION_PEER_EDIT_PATH, delivery_fence).await;
-            Ok(true)
-        }
-    }
-}
-
 /// Remove a retry event for (peer, path) from the queue on successful delivery.
 /// This is a no-op (load + no-op persist skipped) when no matching entry exists,
 /// avoiding unnecessary I/O on the common path.
@@ -11870,213 +11427,6 @@ mod tests {
         assert!(target_state.peers["remote"].skip_tls_verify);
     }
 
-    fn drain_event(peer: &str, path: &str, retry_count: u32, updated_at: Option<OffsetDateTime>) -> SiteReplicationRetryEvent {
-        SiteReplicationRetryEvent {
-            id: format!("evt-{peer}"),
-            peer_deployment_id: peer.to_string(),
-            peer_endpoint: format!("https://{peer}.example.com"),
-            path: path.to_string(),
-            retry_count,
-            failed: retry_count >= SITE_REPLICATION_RETRY_FAILED_AFTER,
-            last_error: "remote-operation-failed".to_string(),
-            updated_at,
-            edit_generation: None,
-        }
-    }
-
-    /// P1-3 red-light: the drain must only ever act on deliveries it can
-    /// replay faithfully. IAM / bucket-meta entries collapse per (peer, path)
-    /// with no body persisted — only a snapshot resend is truthful; bucket
-    /// makes/replication configs are re-derivable; destructive bucket ops and
-    /// `internal:` marker records (the pending-endpoint-refresh backup store)
-    /// are never background-replayed.
-    #[test]
-    fn test_classify_site_replication_retry_event_actions() {
-        let now = OffsetDateTime::from_unix_timestamp(1_700_000_000).expect("timestamp");
-        let classify = |path: &str| classify_site_replication_retry_event(&drain_event("remote", path, 1, Some(now)));
-
-        assert_eq!(
-            classify("/rustfs/admin/v3/site-replication/peer/iam-item"),
-            Some(RetryDrainAction::IamSnapshot)
-        );
-        assert_eq!(
-            classify("/rustfs/admin/v3/site-replication/peer/bucket-meta"),
-            Some(RetryDrainAction::BucketMetadataSnapshot)
-        );
-        assert_eq!(classify(SITE_REPLICATION_PEER_EDIT_PATH), Some(RetryDrainAction::PeerEdit));
-        assert_eq!(
-            classify(
-                "/rustfs/admin/v3/site-replication/peer/bucket-ops?bucket=photos&operation=make-with-versioning&createdAt=1"
-            ),
-            Some(RetryDrainAction::BucketOpReplay {
-                operation: SITE_REPLICATION_BUCKET_OP_MAKE_WITH_VERSIONING.to_string(),
-                bucket: "photos".to_string(),
-            })
-        );
-        assert_eq!(
-            classify("/rustfs/admin/v3/site-replication/peer/bucket-ops?bucket=photos&operation=configure-replication"),
-            Some(RetryDrainAction::BucketOpReplay {
-                operation: SITE_REPLICATION_BUCKET_OP_CONFIGURE_REPLICATION.to_string(),
-                bucket: "photos".to_string(),
-            })
-        );
-        // Destructive ops are operator territory: replaying a bucket delete
-        // against a peer whose bucket was since recreated is irreversible.
-        assert_eq!(
-            classify("/rustfs/admin/v3/site-replication/peer/bucket-ops?bucket=photos&operation=delete-bucket"),
-            None
-        );
-        assert_eq!(
-            classify("/rustfs/admin/v3/site-replication/peer/bucket-ops?bucket=photos&operation=force-delete-bucket"),
-            None
-        );
-        // `internal:` records store payloads in `last_error`, not failures.
-        assert_eq!(classify(SITE_REPLICATION_ENDPOINT_REFRESH_RETRY_PATH), None);
-        assert_eq!(classify("internal:some-future-marker"), None);
-        assert_eq!(classify("/rustfs/admin/v3/site-replication/peer/unknown"), None);
-    }
-
-    /// Exponential backoff gates every attempt: without it a dead peer's
-    /// entries hit `failed` (retry_count >= 3) within 30 minutes of reconcile
-    /// ticks and the retry stats lose their signal.
-    #[test]
-    fn test_site_replication_retry_backoff_schedule() {
-        let now = OffsetDateTime::from_unix_timestamp(1_700_000_000).expect("timestamp");
-        let at = |secs_ago: i64| Some(now - time::Duration::seconds(secs_ago));
-        let elapsed = |retry_count: u32, secs_ago: i64| {
-            site_replication_retry_backoff_elapsed(&drain_event("remote", "/p", retry_count, at(secs_ago)), now)
-        };
-
-        // No record of when it failed: attempt now.
-        assert!(site_replication_retry_backoff_elapsed(&drain_event("remote", "/p", 1, None), now));
-        // First failure: one reconcile interval.
-        assert!(!elapsed(1, 599));
-        assert!(elapsed(1, 601));
-        // Third failure: 600 * 2^2 = 2400s.
-        assert!(!elapsed(3, 1200));
-        assert!(elapsed(3, 2401));
-        // Ceiling: a long-dead peer is still probed daily, never less often.
-        assert!(!elapsed(30, 86_000));
-        assert!(elapsed(30, 86_401));
-    }
-
-    /// The actionable subset respects classification, peer membership and
-    /// backoff; everything else stays untouched in the queue.
-    #[test]
-    fn test_actionable_site_replication_retry_events_filters() {
-        let now = OffsetDateTime::from_unix_timestamp(1_700_000_000).expect("timestamp");
-        let old = Some(now - time::Duration::seconds(700));
-        let mut state = SiteReplicationState::default();
-        state
-            .peers
-            .insert("remote".to_string(), peer("remote", "https://remote.example.com"));
-
-        state.retry_queue = vec![
-            // Eligible: known peer, replayable, past backoff.
-            drain_event("remote", "/rustfs/admin/v3/site-replication/peer/iam-item", 1, old),
-            // Not yet due.
-            drain_event("remote", "/rustfs/admin/v3/site-replication/peer/bucket-meta", 2, Some(now)),
-            // Unknown peer (removed since the failure was recorded).
-            drain_event("gone", "/rustfs/admin/v3/site-replication/peer/iam-item", 1, old),
-            // Marker record, not a delivery failure.
-            drain_event("remote", SITE_REPLICATION_ENDPOINT_REFRESH_RETRY_PATH, 0, old),
-            // Destructive op: operator-only.
-            drain_event(
-                "remote",
-                "/rustfs/admin/v3/site-replication/peer/bucket-ops?bucket=photos&operation=delete-bucket",
-                1,
-                old,
-            ),
-        ];
-
-        let actionable = actionable_site_replication_retry_events(&state, now);
-        assert_eq!(actionable.len(), 1, "only the due, replayable, known-peer event is actionable");
-        assert_eq!(actionable[0].path, "/rustfs/admin/v3/site-replication/peer/iam-item");
-    }
-
-    /// The drain settles a peer-edit success under a freshly allocated
-    /// generation; legacy queue entries carry `edit_generation: None` and
-    /// must be cleared by that generation-scoped settlement (`(Some, None)`
-    /// falls through to removal), or the drain would spin on them forever.
-    #[test]
-    fn test_settle_clears_legacy_none_generation_event_for_generation_scoped_success() {
-        let target = peer("remote", "https://remote.example.com");
-        let mut queue = vec![drain_event("remote", SITE_REPLICATION_PEER_EDIT_PATH, 1, None)];
-        assert!(queue[0].edit_generation.is_none());
-
-        let settled = settle_site_replication_retry_events(&mut queue, &target, SITE_REPLICATION_PEER_EDIT_PATH, Some(42));
-
-        assert_eq!(settled, 1, "a legacy None-generation event must settle under a newer generation");
-        assert!(queue.is_empty());
-    }
-
-    /// A successful snapshot resend cannot prove a failed *deletion* was
-    /// replayed, so the collapsed entry is escalated (operator-visible,
-    /// drain-idle) instead of cleared — unless a newer failure was stamped
-    /// during the delivery window, which keeps the entry drain-eligible.
-    #[test]
-    fn test_escalate_up_to_marks_snapshot_replayed_and_keeps_newer_failures() {
-        let target = peer("remote", "https://remote.example.com");
-        let path = "/rustfs/admin/v3/site-replication/peer/iam-item";
-        let snapshot_at = OffsetDateTime::from_unix_timestamp(1_700_000_000).expect("timestamp");
-
-        // Failure re-stamped after the snapshot: untouched, still eligible.
-        let mut queue = vec![drain_event("remote", path, 2, Some(snapshot_at + time::Duration::seconds(5)))];
-        assert_eq!(
-            escalate_site_replication_retry_events_up_to(&mut queue, &target, path, Some(snapshot_at)),
-            0
-        );
-        assert!(!queue[0].failed);
-        assert!(
-            classify_site_replication_retry_event(&queue[0]).is_some(),
-            "a newer failure must stay drain-eligible"
-        );
-
-        // Unchanged since the snapshot: escalated, kept, drain-idle.
-        let mut queue = vec![drain_event("remote", path, 2, Some(snapshot_at))];
-        assert_eq!(
-            escalate_site_replication_retry_events_up_to(&mut queue, &target, path, Some(snapshot_at)),
-            1
-        );
-        assert_eq!(queue.len(), 1, "the entry must survive until remote absence is proven");
-        assert!(queue[0].failed);
-        assert_eq!(queue[0].last_error, SITE_REPLICATION_RETRY_SNAPSHOT_REPLAYED_MARKER);
-        assert!(
-            classify_site_replication_retry_event(&queue[0]).is_none(),
-            "a snapshot-replayed entry must not be re-sent daily"
-        );
-        // Ordinary success dequeues must not clear the marker: collapsed
-        // paths are shared by every entity, so a successful Bob update
-        // proves nothing about a failed Alice deletion (second review
-        // round).
-        assert_eq!(dequeue_site_replication_retry_events(&mut queue, &target, path), 0);
-        assert_eq!(queue.len(), 1, "an escalated entry must survive an ordinary delivery success");
-        // Only a repair — the operator's accountability transfer — settles it.
-        assert_eq!(dequeue_site_replication_retry_events_including_escalated(&mut queue, &target, path), 1);
-        assert!(queue.is_empty());
-
-        // A later hook failure overwrites the marker and re-arms the drain.
-        let mut queue = vec![drain_event("remote", path, 2, Some(snapshot_at))];
-        escalate_site_replication_retry_events_up_to(&mut queue, &target, path, Some(snapshot_at));
-        upsert_site_replication_retry_event(&mut queue, &target, path, "peer offline", None);
-        assert!(classify_site_replication_retry_event(&queue[0]).is_some());
-
-        // Legacy entry without a timestamp: escalated.
-        let mut queue = vec![drain_event("remote", path, 2, None)];
-        assert_eq!(
-            escalate_site_replication_retry_events_up_to(&mut queue, &target, path, Some(snapshot_at)),
-            1
-        );
-
-        // Other (peer, path) entries are untouched.
-        let mut queue = vec![drain_event("other", path, 2, Some(snapshot_at))];
-        assert_eq!(
-            escalate_site_replication_retry_events_up_to(&mut queue, &target, path, Some(snapshot_at)),
-            0
-        );
-        assert!(!queue[0].failed);
-    }
-
     #[test]
     fn test_pending_endpoint_refresh_retry_summary_redacts_pem() {
         let pem = "-----BEGIN CERTIFICATE-----\nsecret-marker\n-----END CERTIFICATE-----";
@@ -16922,31 +16272,17 @@ mod tests {
     async fn test_retry_event_persist_must_not_wipe_concurrent_locked_rmw() {
         publish_ready_iam_context().await;
 
-        const ROUNDS: usize = 8;
         let seed = SiteReplicationState {
             pending_rotation: Some(PendingRotation {
                 id: "rot-1".to_string(),
                 access_key: "svc-account".to_string(),
                 ..Default::default()
             }),
-            // Retry events are only recorded for current peers; seed them so
-            // the concurrency assertion below exercises the persist path.
-            peers: (0..ROUNDS)
-                .map(|round| {
-                    let deployment_id = format!("peer-{round}-deployment");
-                    (
-                        deployment_id.clone(),
-                        PeerInfo {
-                            endpoint: format!("https://peer-{round}.example:9000"),
-                            deployment_id,
-                            ..Default::default()
-                        },
-                    )
-                })
-                .collect(),
             ..Default::default()
         };
         save_site_replication_state(&seed).await.expect("seed state");
+
+        const ROUNDS: usize = 8;
         for round in 0..ROUNDS {
             let peer = PeerInfo {
                 endpoint: format!("https://peer-{round}.example:9000"),

rustfs/src/admin/mod.rs

@@ -17,6 +17,7 @@ mod auth;
 pub mod console;
 pub mod handlers;
 mod plugin_contract;
+pub(crate) mod replication_metrics_wire;
 // Contract inventory is validated by tests before later runtime integration.
 #[allow(dead_code)]
 pub(crate) mod route_policy;

rustfs/src/admin/replication_metrics_wire.rs

@@ -0,0 +1,597 @@
+// 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.
+
+//! Serialize-only wire projections of the internal replication statistics
+//! onto the minio-go `replication.Metrics` / `replication.MetricsV2` json
+//! shapes consumed by `mc replicate status` (`?replication-metrics[=2]` and
+//! the admin `replicationmetrics` endpoint).
+//!
+//! Red line: the internal `BucketStats` family in
+//! `crates/replication/src/stats.rs` is ALSO the intra-cluster peer-RPC wire
+//! format — `node_service.rs` encodes it with `rmp_serde::to_vec_named`, so
+//! its Rust field names travel between nodes as msgpack map keys. Renaming
+//! those serde names would break mixed-version clusters mid rolling upgrade.
+//! All madmin/minio-go interop therefore happens in these DTOs; never add
+//! `#[serde(rename)]` to the internal structs instead.
+//!
+//! Field names below are the exact json tags of minio-go
+//! `pkg/replication/replication.go` (v7.0.91). Keys minio-go does not know
+//! are RustFS extensions; Go decoders ignore unknown keys. `max`/`peak` are
+//! both emitted for the queue peak because the MinIO server writes `max`
+//! while minio-go reads `peak` (an upstream drift); emitting both keeps every
+//! decoder working.
+
+use serde::Serialize;
+use std::collections::HashMap;
+use std::time::Duration;
+
+use crate::admin::storage_api::replication::{
+    BucketReplicationStat as InternalReplicationStat, BucketReplicationStats as InternalReplicationStats, BucketStats,
+    InQueueMetric as InternalInQueueMetric, XferStats as InternalXferStats,
+};
+
+/// minio-go `replication.RStat`.
+#[derive(Debug, Default, Clone, Copy, Serialize)]
+pub(crate) struct RStatWire {
+    #[serde(rename = "count")]
+    pub count: f64,
+    #[serde(rename = "bytes")]
+    pub bytes: i64,
+}
+
+/// minio-go `replication.TimedErrStats`.
+#[derive(Debug, Default, Clone, Copy, Serialize)]
+pub(crate) struct TimedErrStatsWire {
+    #[serde(rename = "lastMinute")]
+    pub last_minute: RStatWire,
+    #[serde(rename = "lastHour")]
+    pub last_hour: RStatWire,
+    #[serde(rename = "totals")]
+    pub totals: RStatWire,
+}
+
+impl TimedErrStatsWire {
+    fn add(self, other: TimedErrStatsWire) -> TimedErrStatsWire {
+        fn add(a: RStatWire, b: RStatWire) -> RStatWire {
+            RStatWire {
+                count: a.count + b.count,
+                bytes: a.bytes.saturating_add(b.bytes),
+            }
+        }
+        TimedErrStatsWire {
+            last_minute: add(self.last_minute, other.last_minute),
+            last_hour: add(self.last_hour, other.last_hour),
+            totals: add(self.totals, other.totals),
+        }
+    }
+}
+
+/// minio-go `replication.QStat`.
+#[derive(Debug, Default, Clone, Copy, Serialize)]
+pub(crate) struct QStatWire {
+    #[serde(rename = "count")]
+    pub count: f64,
+    #[serde(rename = "bytes")]
+    pub bytes: f64,
+}
+
+/// minio-go `replication.InQueueMetric`, with the queue peak emitted under
+/// both `peak` (minio-go tag) and `max` (MinIO server tag).
+#[derive(Debug, Default, Clone, Copy, Serialize)]
+pub(crate) struct InQueueMetricWire {
+    #[serde(rename = "curr")]
+    pub curr: QStatWire,
+    #[serde(rename = "avg")]
+    pub avg: QStatWire,
+    #[serde(rename = "max")]
+    pub max: QStatWire,
+    #[serde(rename = "peak")]
+    pub peak: QStatWire,
+}
+
+impl From<&InternalInQueueMetric> for InQueueMetricWire {
+    fn from(metric: &InternalInQueueMetric) -> Self {
+        fn qstat(bytes: i64, count: i64) -> QStatWire {
+            QStatWire {
+                count: count as f64,
+                bytes: bytes as f64,
+            }
+        }
+        let peak = qstat(metric.max.bytes, metric.max.count);
+        InQueueMetricWire {
+            curr: qstat(metric.curr.bytes, metric.curr.count),
+            avg: qstat(metric.avg.bytes, metric.avg.count),
+            max: peak,
+            peak,
+        }
+    }
+}
+
+/// minio-go `replication.XferStats`.
+#[derive(Debug, Default, Clone, Copy, Serialize)]
+pub(crate) struct XferStatsWire {
+    #[serde(rename = "avgRate")]
+    pub avg_rate: f64,
+    #[serde(rename = "peakRate")]
+    pub peak_rate: f64,
+    #[serde(rename = "currRate")]
+    pub curr_rate: f64,
+}
+
+impl XferStatsWire {
+    fn merge(self, other: XferStatsWire) -> XferStatsWire {
+        XferStatsWire {
+            avg_rate: self.avg_rate + other.avg_rate,
+            peak_rate: self.peak_rate.max(other.peak_rate),
+            curr_rate: self.curr_rate + other.curr_rate,
+        }
+    }
+}
+
+impl From<&InternalXferStats> for XferStatsWire {
+    fn from(stats: &InternalXferStats) -> Self {
+        XferStatsWire {
+            avg_rate: stats.avg,
+            peak_rate: stats.peak,
+            curr_rate: stats.curr,
+        }
+    }
+}
+
+/// minio-go `replication.WorkerStat`. RustFS does not track per-bucket worker
+/// occupancy yet, so this always reports zeros.
+#[derive(Debug, Default, Clone, Copy, Serialize)]
+pub(crate) struct WorkerStatWire {
+    #[serde(rename = "curr")]
+    pub curr: i32,
+    #[serde(rename = "avg")]
+    pub avg: f32,
+    #[serde(rename = "max")]
+    pub max: i32,
+}
+
+/// minio-go `replication.ReplMRFStats`. RustFS does not track the 5-minute /
+/// dropped MRF windows, so this always reports zeros; the durable backlog is
+/// enumerable via `/v3/replication/mrf` instead.
+#[derive(Debug, Default, Clone, Copy, Serialize)]
+pub(crate) struct ReplMrfStatsWire {
+    #[serde(rename = "failedCount_last5min")]
+    pub last_failed_count: u64,
+    #[serde(rename = "droppedCount_since_uptime")]
+    pub total_dropped_count: u64,
+    #[serde(rename = "droppedBytes_since_uptime")]
+    pub total_dropped_bytes: u64,
+}
+
+/// minio-go `replication.CounterSummary`.
+#[derive(Debug, Default, Clone, Copy, Serialize)]
+pub(crate) struct CounterSummaryWire {
+    #[serde(rename = "last1hr")]
+    pub last1hr: u64,
+    #[serde(rename = "last1m")]
+    pub last1m: u64,
+    #[serde(rename = "total")]
+    pub total: u64,
+}
+
+/// minio-go `replication.TargetMetrics` (one remote target / ARN).
+#[derive(Debug, Default, Serialize)]
+pub(crate) struct TargetMetricsWire {
+    #[serde(rename = "replicationCount")]
+    pub replicated_count: i64,
+    #[serde(rename = "completedReplicationSize")]
+    pub replicated_size: i64,
+    /// Bandwidth limit for this target. The tag says "bits" but both MinIO
+    /// and minio-go treat the value as bytes/sec; keep bytes/sec.
+    #[serde(rename = "limitInBits")]
+    pub bandwidth_limit_bytes_per_sec: i64,
+    #[serde(rename = "currentBandwidth")]
+    pub current_bandwidth_bytes_per_sec: f64,
+    #[serde(rename = "failed")]
+    pub failed: TimedErrStatsWire,
+    #[serde(rename = "failedReplicationSize")]
+    pub failed_size: i64,
+    #[serde(rename = "failedReplicationCount")]
+    pub failed_count: i64,
+}
+
+fn target_timed_err_stats(stat: &InternalReplicationStat) -> TimedErrStatsWire {
+    // Cluster aggregation merges FailStats without the process-local samples,
+    // so the serializable window snapshots (refreshed at each node's
+    // collection point, summed by merge) are authoritative here; the live
+    // samples only ever agree with or lag them, so take the larger.
+    let sampled_minute = stat.fail_stats.recent_since(Duration::from_secs(60));
+    let sampled_hour = stat.fail_stats.recent_since(Duration::from_secs(3600));
+    let window = |sampled_count: i64, sampled_size: i64, snapshot_count: i64, snapshot_size: i64| RStatWire {
+        count: sampled_count.max(snapshot_count) as f64,
+        bytes: sampled_size.max(snapshot_size),
+    };
+    TimedErrStatsWire {
+        last_minute: window(
+            sampled_minute.count,
+            sampled_minute.size,
+            stat.fail_stats.last_minute.count,
+            stat.fail_stats.last_minute.size,
+        ),
+        last_hour: window(
+            sampled_hour.count,
+            sampled_hour.size,
+            stat.fail_stats.last_hour.count,
+            stat.fail_stats.last_hour.size,
+        ),
+        totals: RStatWire {
+            count: stat.failed.count as f64,
+            bytes: stat.failed.size,
+        },
+    }
+}
+
+impl From<&InternalReplicationStat> for TargetMetricsWire {
+    fn from(stat: &InternalReplicationStat) -> Self {
+        TargetMetricsWire {
+            replicated_count: stat.replicated_count,
+            replicated_size: stat.replicated_size,
+            bandwidth_limit_bytes_per_sec: stat.bandwidth_limit_bytes_per_sec,
+            current_bandwidth_bytes_per_sec: stat.current_bandwidth_bytes_per_sec,
+            failed: target_timed_err_stats(stat),
+            failed_size: stat.failed.size,
+            failed_count: stat.failed.count,
+        }
+    }
+}
+
+/// minio-go `replication.Metrics` — the `currStats` member of `MetricsV2` and
+/// the whole v1 response body. The trailing snake_case fields are RustFS
+/// source-health extension keys (ignored by Go decoders) carried over from
+/// the previous response shape.
+#[derive(Debug, Default, Serialize)]
+pub(crate) struct MetricsWire {
+    #[serde(rename = "Stats")]
+    pub stats: HashMap<String, TargetMetricsWire>,
+    #[serde(rename = "completedReplicationSize")]
+    pub replicated_size: i64,
+    #[serde(rename = "replicaSize")]
+    pub replica_size: i64,
+    #[serde(rename = "replicaCount")]
+    pub replica_count: i64,
+    #[serde(rename = "replicationCount")]
+    pub replicated_count: i64,
+    #[serde(rename = "failed")]
+    pub failed: TimedErrStatsWire,
+    #[serde(rename = "queued")]
+    pub queued: InQueueMetricWire,
+    // RustFS extension keys (source health of the aggregation).
+    pub provider_available: bool,
+    pub cluster_complete: bool,
+    pub observed_node_count: u32,
+    pub expected_node_count: u32,
+}
+
+impl From<&InternalReplicationStats> for MetricsWire {
+    fn from(stats: &InternalReplicationStats) -> Self {
+        let mut failed = TimedErrStatsWire::default();
+        let mut targets = HashMap::with_capacity(stats.stats.len());
+        for (arn, stat) in &stats.stats {
+            let target = TargetMetricsWire::from(stat);
+            failed = failed.add(target.failed);
+            targets.insert(arn.clone(), target);
+        }
+        MetricsWire {
+            stats: targets,
+            replicated_size: stats.replicated_size,
+            replica_size: stats.replica_size,
+            replica_count: stats.replica_count,
+            replicated_count: stats.replicated_count,
+            failed,
+            queued: InQueueMetricWire::from(&stats.q_stat),
+            provider_available: stats.provider_available,
+            cluster_complete: stats.cluster_complete,
+            observed_node_count: stats.observed_node_count,
+            expected_node_count: stats.expected_node_count,
+        }
+    }
+}
+
+/// minio-go `replication.ReplQNodeStats`.
+#[derive(Debug, Default, Serialize)]
+pub(crate) struct ReplQNodeStatsWire {
+    #[serde(rename = "nodeName")]
+    pub node_name: String,
+    #[serde(rename = "uptime")]
+    pub uptime: i64,
+    #[serde(rename = "activeWorkers")]
+    pub workers: WorkerStatWire,
+    #[serde(rename = "transferSummary")]
+    pub xfer_stats: XferSummaryWire,
+    #[serde(rename = "tgtTransferStats")]
+    pub tgt_xfer_stats: TargetXferSummaryWire,
+    #[serde(rename = "queueStats")]
+    pub q_stats: InQueueMetricWire,
+    #[serde(rename = "mrfStats")]
+    pub mrf_stats: ReplMrfStatsWire,
+    #[serde(rename = "retries")]
+    pub retries: CounterSummaryWire,
+    #[serde(rename = "errors")]
+    pub errors: CounterSummaryWire,
+}
+
+/// minio-go `replication.ReplQueueStats`.
+#[derive(Debug, Default, Serialize)]
+pub(crate) struct ReplQueueStatsWire {
+    #[serde(rename = "nodes")]
+    pub nodes: Vec<ReplQNodeStatsWire>,
+}
+
+/// minio-go `replication.MetricsV2` — the `?replication-metrics=2` body.
+#[derive(Debug, Default, Serialize)]
+pub(crate) struct MetricsV2Wire {
+    #[serde(rename = "uptime")]
+    pub uptime: i64,
+    #[serde(rename = "currStats")]
+    pub current_stats: MetricsWire,
+    #[serde(rename = "queueStats")]
+    pub queue_stats: ReplQueueStatsWire,
+    #[serde(rename = "downtimeInfo")]
+    pub downtime_info: HashMap<String, serde_json::Value>,
+}
+
+/// `transferSummary` map keyed by minio-go `MetricName` (Large/Small/Total).
+type XferSummaryWire = HashMap<&'static str, XferStatsWire>;
+/// `tgtTransferStats` map keyed by target ARN.
+type TargetXferSummaryWire = HashMap<String, XferSummaryWire>;
+
+fn transfer_summaries(stats: &InternalReplicationStats) -> (XferSummaryWire, TargetXferSummaryWire) {
+    let mut summary: XferSummaryWire = HashMap::new();
+    let mut per_target: TargetXferSummaryWire = HashMap::new();
+    for (arn, stat) in &stats.stats {
+        let large = XferStatsWire::from(&stat.xfer_rate_lrg);
+        let small = XferStatsWire::from(&stat.xfer_rate_sml);
+        let total = large.merge(small);
+        per_target.insert(arn.clone(), HashMap::from([("Large", large), ("Small", small), ("Total", total)]));
+        for (key, value) in [("Large", large), ("Small", small), ("Total", total)] {
+            let entry = summary.entry(key).or_default();
+            *entry = entry.merge(value);
+        }
+    }
+    (summary, per_target)
+}
+
+impl MetricsV2Wire {
+    /// Project the aggregated internal stats onto the `MetricsV2` shape.
+    ///
+    /// The aggregation path leaves `queue_stats.nodes` empty today, so a
+    /// single node entry is synthesized from the bucket queue snapshot —
+    /// `mc replicate status` derives its queue/worker panels from
+    /// `queueStats.nodes` and treats an empty list as "no data".
+    pub(crate) fn from_stats(bucket_stats: &BucketStats, node_name: &str) -> Self {
+        let (xfer_stats, tgt_xfer_stats) = transfer_summaries(&bucket_stats.replication_stats);
+        let mut nodes: Vec<ReplQNodeStatsWire> = bucket_stats
+            .queue_stats
+            .nodes
+            .iter()
+            .map(|node| ReplQNodeStatsWire {
+                node_name: node_name.to_string(),
+                uptime: bucket_stats.uptime,
+                q_stats: InQueueMetricWire::from(&node.q_stats),
+                ..Default::default()
+            })
+            .collect();
+        if nodes.is_empty() {
+            nodes.push(ReplQNodeStatsWire {
+                node_name: node_name.to_string(),
+                uptime: bucket_stats.uptime,
+                q_stats: InQueueMetricWire::from(&bucket_stats.replication_stats.q_stat),
+                xfer_stats: xfer_stats.clone(),
+                tgt_xfer_stats: tgt_xfer_stats.clone(),
+                ..Default::default()
+            });
+        } else {
+            // Attach the transfer summaries to the first node; the internal
+            // snapshot does not attribute transfer rates per node.
+            if let Some(first) = nodes.first_mut() {
+                first.xfer_stats = xfer_stats.clone();
+                first.tgt_xfer_stats = tgt_xfer_stats.clone();
+            }
+        }
+
+        MetricsV2Wire {
+            uptime: bucket_stats.uptime,
+            current_stats: MetricsWire::from(&bucket_stats.replication_stats),
+            queue_stats: ReplQueueStatsWire { nodes },
+            downtime_info: HashMap::new(),
+        }
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    fn sample_bucket_stats() -> BucketStats {
+        let mut stats = BucketStats {
+            uptime: 42,
+            ..Default::default()
+        };
+        stats.replication_stats.replica_count = 2;
+        stats.replication_stats.replica_size = 128;
+        stats.replication_stats.replicated_count = 9;
+        stats.replication_stats.replicated_size = 4096;
+        let target = stats
+            .replication_stats
+            .stats
+            .entry("arn:minio:replication::t:b".to_string())
+            .or_default();
+        target.replicated_count = 9;
+        target.replicated_size = 4096;
+        target.failed.count = 3;
+        target.failed.size = 900;
+        target.bandwidth_limit_bytes_per_sec = 1024;
+        target.current_bandwidth_bytes_per_sec = 512.5;
+        stats
+            .replication_stats
+            .q_stat
+            .curr
+            .now_count
+            .store(4, std::sync::atomic::Ordering::Relaxed);
+        stats
+            .replication_stats
+            .q_stat
+            .curr
+            .now_bytes
+            .store(1200, std::sync::atomic::Ordering::Relaxed);
+        stats.replication_stats.q_stat = stats.replication_stats.q_stat.snapshot();
+        stats
+    }
+
+    #[test]
+    fn metrics_wire_matches_minio_go_tags() {
+        let stats = sample_bucket_stats();
+        let json = serde_json::to_value(MetricsWire::from(&stats.replication_stats)).expect("v1 wire should serialize");
+
+        assert_eq!(json["replicaCount"], 2);
+        assert_eq!(json["replicaSize"], 128);
+        assert_eq!(json["replicationCount"], 9);
+        assert_eq!(json["completedReplicationSize"], 4096);
+        assert_eq!(json["queued"]["curr"]["count"], 4.0);
+        assert_eq!(json["queued"]["curr"]["bytes"], 1200.0);
+        let target = &json["Stats"]["arn:minio:replication::t:b"];
+        assert_eq!(target["replicationCount"], 9);
+        assert_eq!(target["completedReplicationSize"], 4096);
+        assert_eq!(target["limitInBits"], 1024);
+        assert_eq!(target["currentBandwidth"], 512.5);
+        // failed is the madmin TimedErrStats envelope, not the internal
+        // {count,size} pair.
+        assert_eq!(target["failed"]["totals"]["count"], 3.0);
+        assert_eq!(target["failed"]["totals"]["bytes"], 900);
+        assert!(target["failed"].get("count").is_none());
+        // Aggregate failed mirrors the per-target totals.
+        assert_eq!(json["failed"]["totals"]["count"], 3.0);
+    }
+
+    #[test]
+    fn metrics_v2_wire_synthesizes_queue_node() {
+        let stats = sample_bucket_stats();
+        let json = serde_json::to_value(MetricsV2Wire::from_stats(&stats, "node-1:9000")).expect("v2 wire should serialize");
+
+        assert_eq!(json["uptime"], 42);
+        assert_eq!(json["currStats"]["replicaCount"], 2);
+        let node = &json["queueStats"]["nodes"][0];
+        assert_eq!(node["nodeName"], "node-1:9000");
+        assert_eq!(node["uptime"], 42);
+        assert_eq!(node["queueStats"]["curr"]["count"], 4.0);
+        // The queue peak is emitted under both the minio-go tag (`peak`) and
+        // the MinIO server tag (`max`).
+        assert_eq!(node["queueStats"]["peak"], node["queueStats"]["max"]);
+        assert!(node["activeWorkers"].get("curr").is_some());
+        assert!(node["transferSummary"].get("Total").is_some());
+        assert_eq!(json["downtimeInfo"], serde_json::json!({}));
+    }
+
+    /// minio-go's transferSummary labels mean >= 128 MiB for Large; the
+    /// producer must bin on the same boundary (MIN_LARGE_OBJ_SIZE, shared
+    /// with the worker-pool split), or a 2 MiB replication shows under Large
+    /// while Small stays zero.
+    #[test]
+    fn transfer_summary_bins_on_the_128_mib_boundary() {
+        const MIB: i64 = 1024 * 1024;
+        let mut stats = BucketStats::default();
+        let stat = stats
+            .replication_stats
+            .stats
+            .entry("arn:minio:replication::t:b".to_string())
+            .or_default();
+        stat.update_xfer_rate(2 * MIB, std::time::Duration::from_secs(1));
+        stat.update_xfer_rate(127 * MIB, std::time::Duration::from_secs(1));
+        stat.update_xfer_rate(128 * MIB, std::time::Duration::from_secs(1));
+
+        let json = serde_json::to_value(MetricsV2Wire::from_stats(&stats, "node-1")).expect("v2 wire should serialize");
+        let summary = &json["queueStats"]["nodes"][0]["tgtTransferStats"]["arn:minio:replication::t:b"];
+        let small_peak = summary["Small"]["peakRate"].as_f64().expect("Small peakRate");
+        let large_peak = summary["Large"]["peakRate"].as_f64().expect("Large peakRate");
+        assert!(
+            (small_peak - (127 * MIB) as f64).abs() < 1.0,
+            "2 MiB and 127 MiB transfers must bin as Small (peak {small_peak})"
+        );
+        assert!(
+            (large_peak - (128 * MIB) as f64).abs() < 1.0,
+            "exactly 128 MiB must bin as Large (peak {large_peak})"
+        );
+    }
+
+    /// Review regression: both metrics endpoints aggregate first, and the
+    /// FailStats merge drops the process-local samples — the rolling windows
+    /// must survive a peer-RPC round trip plus aggregation and still reach
+    /// the wire body.
+    #[test]
+    fn failure_windows_survive_aggregation_before_serialization() {
+        // Node A: live failure; the windows are stamped at the collection
+        // point (get_latest_replication_stats calls refresh_windows before
+        // the stats cross the wire), never on the failure hot path.
+        let mut node_a = crate::admin::storage_api::replication::BucketReplicationStat::default();
+        node_a.fail_stats.add_size(512, None::<&std::io::Error>);
+        node_a.fail_stats.refresh_windows();
+        node_a.failed = node_a.fail_stats.to_metric();
+
+        // Node A's stats cross the peer RPC wire: the samples are dropped,
+        // the window snapshots travel.
+        let encoded = rmp_serde::to_vec_named(&node_a).expect("stat should encode");
+        let remote: crate::admin::storage_api::replication::BucketReplicationStat =
+            rmp_serde::from_slice(&encoded).expect("stat should decode");
+
+        // Aggregation merges the remote stat with an empty local one.
+        let merged_fail = remote.fail_stats.merge(&Default::default());
+        let mut aggregated = crate::admin::storage_api::replication::BucketReplicationStat::default();
+        aggregated.failed = merged_fail.to_metric();
+        aggregated.fail_stats = merged_fail;
+
+        let mut stats = BucketStats::default();
+        stats
+            .replication_stats
+            .stats
+            .insert("arn:minio:replication::t:b".to_string(), aggregated);
+
+        let json = serde_json::to_value(MetricsWire::from(&stats.replication_stats)).expect("wire should serialize");
+        let failed = &json["Stats"]["arn:minio:replication::t:b"]["failed"];
+        assert_eq!(failed["totals"]["count"], 1.0);
+        assert_eq!(
+            failed["lastMinute"]["count"], 1.0,
+            "the rolling minute window must survive RPC + aggregation"
+        );
+        assert_eq!(failed["lastMinute"]["bytes"], 512);
+        assert_eq!(failed["lastHour"]["count"], 1.0);
+    }
+
+    /// Pin the intra-cluster peer-RPC wire format of the internal stats: it
+    /// is msgpack with the Rust field names as map keys
+    /// (`rmp_serde::to_vec_named` in node_service.rs). If someone "fixes"
+    /// the interop bug by renaming the internal serde fields instead of using
+    /// these DTOs, this test fails and points them here.
+    #[test]
+    fn internal_bucket_stats_rpc_wire_stays_snake_case() {
+        let stats = sample_bucket_stats();
+        let encoded = rmp_serde::to_vec_named(&stats).expect("internal stats should encode");
+        let value: serde_json::Value = rmp_serde::from_slice(&encoded).expect("named msgpack should decode generically");
+
+        assert!(
+            value.get("replication_stats").is_some(),
+            "peer RPC key replication_stats must not be renamed"
+        );
+        assert!(value["replication_stats"].get("q_stat").is_some());
+        assert!(value.get("queue_stats").is_some());
+        assert!(value.get("proxy_stats").is_some());
+
+        let decoded: BucketStats = rmp_serde::from_slice(&encoded).expect("round-trip through the peer RPC wire");
+        assert_eq!(decoded.replication_stats.replica_count, 2);
+    }
+}

rustfs/src/admin/router.rs

@@ -1548,7 +1548,8 @@ async fn build_replication_metrics_response(
     let bucket_stats = apply_replication_metrics_bandwidth_report(bucket_stats, collect_replication_metrics_bandwidth(bucket));
     let bucket_stats = apply_replication_metrics_runtime_fields(bucket_stats, route, replication_metrics_uptime_seconds());
 
-    let body = serialize_replication_metrics_body(&bucket_stats, route)?;
+    let node_name = crate::runtime_sources::current_local_node_name().await.unwrap_or_default();
+    let body = serialize_replication_metrics_body(&bucket_stats, route, &node_name)?;
 
     let mut resp = S3Response::with_status(Body::from(body), StatusCode::OK);
     resp.headers
@@ -1608,12 +1609,24 @@ fn apply_replication_metrics_runtime_fields(
     bucket_stats
 }
 
-fn serialize_replication_metrics_body(bucket_stats: &BucketStats, route: ReplicationExtRoute) -> S3Result<Vec<u8>> {
+/// Serialize the metrics body in the minio-go wire shapes
+/// (`replication.Metrics` for v1, `replication.MetricsV2` for v2). The
+/// internal `BucketStats` serde names are the intra-cluster peer-RPC wire
+/// format and must never appear here — see
+/// `crate::admin::replication_metrics_wire`.
+fn serialize_replication_metrics_body(
+    bucket_stats: &BucketStats,
+    route: ReplicationExtRoute,
+    node_name: &str,
+) -> S3Result<Vec<u8>> {
+    use crate::admin::replication_metrics_wire::{MetricsV2Wire, MetricsWire};
     match route {
         ReplicationExtRoute::MetricsV1 => {
-            serde_json::to_vec(&bucket_stats.replication_stats).map_err(|e| s3_error!(InternalError, "{e}"))
+            serde_json::to_vec(&MetricsWire::from(&bucket_stats.replication_stats)).map_err(|e| s3_error!(InternalError, "{e}"))
+        }
+        ReplicationExtRoute::MetricsV2 => {
+            serde_json::to_vec(&MetricsV2Wire::from_stats(bucket_stats, node_name)).map_err(|e| s3_error!(InternalError, "{e}"))
         }
-        ReplicationExtRoute::MetricsV2 => serde_json::to_vec(bucket_stats).map_err(|e| s3_error!(InternalError, "{e}")),
         ReplicationExtRoute::Check | ReplicationExtRoute::ResetStart | ReplicationExtRoute::ResetStatus => {
             Err(s3_error!(InternalError, "invalid route for metrics response"))
         }
@@ -4147,22 +4160,37 @@ mod tests {
         assert!(err.message().unwrap_or_default().contains("rule-stale"));
     }
 
+    /// The v1 body must decode into minio-go `replication.Metrics` (exact
+    /// json tags); Go's decoder matches case-insensitively but does not
+    /// ignore underscores, so the internal snake_case names read as all-zero.
     #[test]
-    fn serialize_replication_metrics_body_v1_returns_replication_stats_only() {
+    fn serialize_replication_metrics_body_v1_returns_minio_go_metrics_shape() {
         let mut stats = BucketStats {
             uptime: 99,
             ..Default::default()
         };
         stats.replication_stats.replica_count = 7;
+        stats.replication_stats.replicated_size = 2048;
+        stats
+            .replication_stats
+            .stats
+            .entry("arn:minio:replication::t:b".to_string())
+            .or_default()
+            .replicated_count = 5;
         stats.proxy_stats.put_total = 3;
 
-        let body =
-            serialize_replication_metrics_body(&stats, ReplicationExtRoute::MetricsV1).expect("metrics v1 body should serialize");
+        let body = serialize_replication_metrics_body(&stats, ReplicationExtRoute::MetricsV1, "node-1:9000")
+            .expect("metrics v1 body should serialize");
         let payload: serde_json::Value = serde_json::from_slice(&body).expect("body should be json");
 
-        assert_eq!(payload["replica_count"], 7);
+        assert_eq!(payload["replicaCount"], 7);
+        assert_eq!(payload["completedReplicationSize"], 2048);
+        assert_eq!(payload["Stats"]["arn:minio:replication::t:b"]["replicationCount"], 5);
         assert!(payload.get("uptime").is_none());
         assert!(payload.get("proxy_stats").is_none());
+        // The internal snake_case names must not leak into the wire body.
+        assert!(payload.get("replica_count").is_none());
+        assert!(payload.get("q_stat").is_none());
     }
 
     #[test]
@@ -4248,22 +4276,48 @@ mod tests {
         assert_eq!(target.current_bandwidth_bytes_per_sec, 3000.0);
     }
 
+    /// The v2 body must decode into minio-go `replication.MetricsV2`
+    /// (`uptime`/`currStats`/`queueStats`); `mc replicate status` reads
+    /// `currStats` and `queueStats.nodes` and silently shows zeros when the
+    /// keys do not match.
     #[test]
-    fn serialize_replication_metrics_body_v2_returns_full_bucket_stats() {
+    fn serialize_replication_metrics_body_v2_returns_minio_go_metrics_v2_shape() {
         let mut stats = BucketStats {
             uptime: 99,
             ..Default::default()
         };
         stats.replication_stats.replica_count = 7;
+        stats
+            .replication_stats
+            .q_stat
+            .curr
+            .now_count
+            .store(4, std::sync::atomic::Ordering::Relaxed);
+        stats
+            .replication_stats
+            .q_stat
+            .curr
+            .now_bytes
+            .store(1200, std::sync::atomic::Ordering::Relaxed);
+        stats.replication_stats.q_stat = stats.replication_stats.q_stat.snapshot();
         stats.proxy_stats.put_total = 3;
 
-        let body =
-            serialize_replication_metrics_body(&stats, ReplicationExtRoute::MetricsV2).expect("metrics v2 body should serialize");
+        let body = serialize_replication_metrics_body(&stats, ReplicationExtRoute::MetricsV2, "node-1:9000")
+            .expect("metrics v2 body should serialize");
         let payload: serde_json::Value = serde_json::from_slice(&body).expect("body should be json");
 
         assert_eq!(payload["uptime"], 99);
-        assert_eq!(payload["replication_stats"]["replica_count"], 7);
-        assert_eq!(payload["proxy_stats"]["put_total"], 3);
+        assert_eq!(payload["currStats"]["replicaCount"], 7);
+        assert_eq!(payload["currStats"]["queued"]["curr"]["count"], 4.0);
+        // The queue snapshot must surface at least one node: mc derives the
+        // worker/queue panels from queueStats.nodes and treats an empty list
+        // as "no data".
+        assert_eq!(payload["queueStats"]["nodes"][0]["queueStats"]["curr"]["count"], 4.0);
+        assert_eq!(payload["queueStats"]["nodes"][0]["uptime"], 99);
+        // The internal snake_case names must not leak into the wire body.
+        assert!(payload.get("replication_stats").is_none());
+        assert!(payload.get("queue_stats").is_none());
+        assert!(payload.get("proxy_stats").is_none());
     }
 
     #[test]

rustfs/src/admin/storage_api.rs

@@ -417,6 +417,10 @@ pub(crate) mod replication {
     };
     pub(crate) type BucketReplicationResyncStatus = super::ecstore_bucket::replication::BucketReplicationResyncStatus;
     pub(crate) type BucketStats = super::ecstore_bucket::replication::BucketStats;
+    pub(crate) type BucketReplicationStats = super::ecstore_bucket::replication::BucketReplicationStats;
+    pub(crate) type BucketReplicationStat = super::ecstore_bucket::replication::BucketReplicationStat;
+    pub(crate) type InQueueMetric = super::ecstore_bucket::replication::InQueueMetric;
+    pub(crate) type XferStats = super::ecstore_bucket::replication::XferStats;
     pub(crate) type ReplicationStatusType = super::ecstore_bucket::replication::ReplicationStatusType;
     pub(crate) type ResyncOpts = super::ecstore_bucket::replication::ResyncOpts;
     pub(crate) type ResyncStatusType = super::ecstore_bucket::replication::ResyncStatusType;