test(ecstore): use replication status types

* fix(ecstore): fail closed on unresolved decommission entries

* perf(ecstore): avoid successful listing name clone

.github/workflows/ci.yml

@@ -400,7 +400,7 @@ jobs:
     if: github.event_name != 'pull_request' || github.event.action != 'closed'
     needs: [ quick-checks ]
     runs-on: sm-standard-4
-    timeout-minutes: 45
+    timeout-minutes: 90
     env:
       FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: "true"
     steps:
@@ -440,7 +440,7 @@ jobs:
     if: github.event_name != 'pull_request' || github.event.action != 'closed'
     needs: [ quick-checks ]
     runs-on: sm-standard-4
-    timeout-minutes: 60
+    timeout-minutes: 90
     env:
       FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: "true"
     steps:
@@ -470,7 +470,7 @@ jobs:
     if: github.event_name != 'pull_request' || github.event.action != 'closed'
     needs: [ quick-checks ]
     runs-on: sm-standard-4
-    timeout-minutes: 60
+    timeout-minutes: 90
     strategy:
       # On a PR, one failing protocol leg is enough to know the PR is not ready,
       # so stop the sibling leg instead of paying another ~40 minutes for it.

crates/config/src/constants/runtime.rs

@@ -57,6 +57,13 @@ pub const DEFAULT_MAX_IO_EVENTS_PER_TICK: usize = 1024;
 pub const DEFAULT_EVENT_INTERVAL: u32 = 61;
 pub const DEFAULT_RNG_SEED: Option<u64> = None; // None means random
 
+/// Dedicated blocking thread pool for fsync/fdatasync operations.
+/// When > 1, fsync operations are isolated from the main blocking pool to
+/// prevent device-bound fsync from starving read operations (pread/stat/open).
+/// Default 0 means auto (no isolation, use main runtime).
+pub const ENV_FSYNC_BLOCKING_THREADS: &str = "RUSTFS_RUNTIME_FSYNC_BLOCKING_THREADS";
+pub const DEFAULT_FSYNC_BLOCKING_THREADS: usize = 0;
+
 // Dial9 Tokio Telemetry Default values
 pub const DEFAULT_RUNTIME_DIAL9_ENABLED: bool = false; // Disabled by default
 pub const DEFAULT_RUNTIME_DIAL9_OUTPUT_DIR: &str = "/var/log/rustfs/telemetry";

crates/ecstore/src/core/pools.rs

@@ -36,7 +36,8 @@ use crate::disk::error::DiskError;
 use crate::disk::{BUCKET_META_PREFIX, RUSTFS_META_BUCKET};
 use crate::error::{Error, Result};
 use crate::error::{
-    StorageError, is_err_bucket_exists, is_err_bucket_not_found, is_err_object_not_found, is_err_version_not_found,
+    StorageError, is_err_bucket_exists, is_err_bucket_not_found, is_err_object_not_found, is_err_operation_canceled,
+    is_err_version_not_found,
 };
 use crate::layout::endpoints::EndpointServerPools;
 use crate::object_api::{GetObjectReader, ObjectOptions};
@@ -89,6 +90,7 @@ const DECOMMISSION_STAGE_SOURCE_CLEANUP: &str = "source_cleanup";
 const DECOMMISSION_STAGE_ENTRY_FINISHED: &str = "entry_finished";
 const DECOMMISSION_PROGRESS_SAVE_INTERVAL: Duration = Duration::seconds(30);
 const DECOMMISSION_PROGRESS_SAVE_ITEM_THRESHOLD: usize = 1000;
+const DECOMMISSION_PROGRESS_SAVE_RETRY_BACKOFF: Duration = Duration::seconds(1);
 const DECOMMISSION_BUCKET_CONCURRENCY_ENV: &str = "RUSTFS_DECOMMISSION_BUCKET_CONCURRENCY";
 const DECOMMISSION_BUCKET_CONCURRENCY_DEFAULT_CAP: usize = 4;
 const DECOMMISSION_TARGET_CAPACITY_OVERHEAD_PERCENT: usize = 30;
@@ -638,22 +640,6 @@ fn track_decommission_current_object(meta: &mut PoolMeta, idx: usize, bucket: &s
     track_decommission_current_object_stage(meta, idx, bucket, object, "")
 }
 
-fn touch_decommission_progress(meta: &mut PoolMeta, idx: usize) -> Result<()> {
-    let pool_count = meta.pools.len();
-    ensure_valid_decommission_pool_index(pool_count, idx)?;
-
-    let Some(pool) = meta.pools.get_mut(idx) else {
-        return Err(invalid_decommission_pool_index_error(pool_count, idx));
-    };
-    let Some(info) = pool.decommission.as_mut() else {
-        return Err(decommission_metadata_not_initialized_error("touch decommission progress"));
-    };
-
-    pool.last_update = OffsetDateTime::now_utc();
-    info.mark_progress_saved();
-    Ok(())
-}
-
 fn resolve_decommission_update_after_result(result: Result<bool>) -> Result<bool> {
     result.map_err(|err| Error::other(format!("decommission metadata update failed: {err}")))
 }
@@ -773,7 +759,76 @@ async fn load_decommission_entry_exact_versions(
 }
 
 fn resolve_decommission_check_after_list_result(list_result: Result<()>, entry_error: Option<Error>) -> Result<()> {
-    if let Some(err) = entry_error { Err(err) } else { list_result }
+    match list_result {
+        Ok(()) => entry_error.map_or(Ok(()), Err),
+        Err(list_err) => resolve_decommission_listing_error(Some(list_err), entry_error).map_or(Ok(()), Err),
+    }
+}
+
+fn resolve_decommission_listing_error(listing_error: Option<Error>, entry_error: Option<Error>) -> Option<Error> {
+    match (listing_error, entry_error) {
+        (Some(listing_error), Some(entry_error)) if is_err_operation_canceled(&listing_error) => Some(entry_error),
+        (Some(listing_error), Some(entry_error)) if is_err_operation_canceled(&entry_error) => Some(listing_error),
+        (Some(listing_error), _) => Some(listing_error),
+        (None, entry_error) => entry_error,
+    }
+}
+
+fn decommission_unresolved_listing_error(
+    bucket: &str,
+    prefix: &str,
+    candidate: Option<&str>,
+    candidate_count: usize,
+    disk_error_count: usize,
+    pool_index: usize,
+    set_index: usize,
+) -> Error {
+    let location = candidate.unwrap_or(prefix);
+    Error::other(format!(
+        "decommission listing could not resolve metadata for {bucket}/{location} on pool {pool_index} set {set_index} ({candidate_count} candidate(s), {disk_error_count} disk error(s))"
+    ))
+}
+
+fn resolve_decommission_partial_listing_entry(
+    entries: MetaCacheEntries,
+    resolver: MetadataResolutionParams,
+    bucket: &str,
+    prefix: &str,
+    disk_error_count: usize,
+    pool_index: usize,
+    set_index: usize,
+) -> Result<MetaCacheEntry> {
+    let candidate_count = entries.as_ref().iter().flatten().count();
+    if let Some(entry) = entries.resolve(resolver) {
+        return Ok(entry);
+    }
+
+    let candidate = entries.as_ref().iter().flatten().map(|entry| entry.name.as_str()).next();
+    Err(decommission_unresolved_listing_error(
+        bucket,
+        prefix,
+        candidate,
+        candidate_count,
+        disk_error_count,
+        pool_index,
+        set_index,
+    ))
+}
+
+async fn record_decommission_entry_error(
+    entry_error: &Arc<tokio::sync::Mutex<Option<Error>>>,
+    rx: &CancellationToken,
+    err: Error,
+) {
+    if rx.is_cancelled() {
+        return;
+    }
+
+    let mut first_err = entry_error.lock().await;
+    if first_err.is_none() && !rx.is_cancelled() {
+        *first_err = Some(err);
+        rx.cancel();
+    }
 }
 
 fn resolve_decommission_pool_meta_reload_result(result: Result<()>, stage: &str) -> Result<()> {
@@ -1483,6 +1538,7 @@ impl TryFrom<PersistedPoolDecommissionInfo> for PoolDecommissionInfo {
             terminal_reload_attempt_at: value.terminal_reload_attempt_at,
             terminal_reload_failures: value.terminal_reload_failures,
             progress_save_item_baseline: value.items_decommissioned.saturating_add(value.items_decommission_failed),
+            progress_save_retry_after: None,
         })
     }
 }
@@ -1514,6 +1570,7 @@ impl TryFrom<LegacyPoolDecommissionInfo> for PoolDecommissionInfo {
             terminal_reload_attempt_at: None,
             terminal_reload_failures: Vec::new(),
             progress_save_item_baseline: value.items_decommissioned.saturating_add(value.items_decommission_failed),
+            progress_save_retry_after: None,
         })
     }
 }
@@ -1627,6 +1684,82 @@ impl PoolMeta {
         }
     }
 
+    fn decommission_progress_checkpoint(
+        &self,
+        idx: usize,
+        duration: Duration,
+        now: OffsetDateTime,
+    ) -> Result<Option<DecommissionProgressCheckpoint>> {
+        let pool_count = self.pools.len();
+        ensure_valid_decommission_pool_index(pool_count, idx)?;
+
+        let Some(pool) = self.pools.get(idx) else {
+            return Err(invalid_decommission_pool_index_error(pool_count, idx));
+        };
+        let Some(info) = pool.decommission.as_ref() else {
+            return Err(decommission_metadata_not_initialized_error("update decommission metadata timestamp"));
+        };
+
+        if info.progress_save_retry_after.is_some_and(|retry_after| now < retry_after) {
+            return Ok(None);
+        }
+
+        let time_threshold_reached = now.unix_timestamp() - pool.last_update.unix_timestamp() >= duration.whole_seconds();
+        let item_threshold_reached = info.items_since_last_progress_save() >= DECOMMISSION_PROGRESS_SAVE_ITEM_THRESHOLD;
+        if !time_threshold_reached && !item_threshold_reached {
+            return Ok(None);
+        }
+
+        Ok(Some(DecommissionProgressCheckpoint {
+            start_time: info.start_time,
+            queued: info.queued,
+            counted_items: info.counted_items(),
+            checkpoint_at: now,
+        }))
+    }
+
+    fn commit_decommission_progress_checkpoint(&mut self, idx: usize, checkpoint: DecommissionProgressCheckpoint) -> bool {
+        let Some(pool) = self.pools.get_mut(idx) else {
+            return false;
+        };
+        let Some(info) = pool.decommission.as_mut() else {
+            return false;
+        };
+
+        if info.start_time != checkpoint.start_time
+            || info.queued != checkpoint.queued
+            || !is_decommission_active(info.complete, info.failed, info.canceled)
+        {
+            return false;
+        }
+
+        info.progress_save_item_baseline = info.progress_save_item_baseline.max(checkpoint.counted_items);
+        info.progress_save_retry_after = None;
+        pool.last_update = pool.last_update.max(checkpoint.checkpoint_at);
+        true
+    }
+
+    fn defer_decommission_progress_checkpoint(
+        &mut self,
+        idx: usize,
+        checkpoint: DecommissionProgressCheckpoint,
+        retry_after: OffsetDateTime,
+    ) {
+        let Some(pool) = self.pools.get_mut(idx) else {
+            return;
+        };
+        let Some(info) = pool.decommission.as_mut() else {
+            return;
+        };
+
+        if info.start_time == checkpoint.start_time
+            && info.queued == checkpoint.queued
+            && is_decommission_active(info.complete, info.failed, info.canceled)
+        {
+            info.progress_save_retry_after = Some(retry_after);
+        }
+    }
+
     fn load_from_config_data(&mut self, data: Vec<u8>) -> Result<()> {
         if data.is_empty() {
             return Ok(());
@@ -1987,30 +2120,9 @@ impl PoolMeta {
     }
 
     pub fn update_after(&mut self, idx: usize, duration: Duration) -> Result<bool> {
-        let pool_count = self.pools.len();
-        ensure_valid_decommission_pool_index(pool_count, idx)?;
-
-        let (last_update, item_threshold_reached) = match self.pools.get(idx) {
-            Some(pool) if let Some(info) = pool.decommission.as_ref() => (
-                pool.last_update,
-                info.items_since_last_progress_save() >= DECOMMISSION_PROGRESS_SAVE_ITEM_THRESHOLD,
-            ),
-            Some(_) => {
-                return Err(decommission_metadata_not_initialized_error("update decommission metadata timestamp"));
-            }
-            None => return Err(invalid_decommission_pool_index_error(pool_count, idx)),
-        };
-        let now = OffsetDateTime::now_utc();
-
-        if now.unix_timestamp() - last_update.unix_timestamp() >= duration.whole_seconds() || item_threshold_reached {
-            let Some(pool) = self.pools.get_mut(idx) else {
-                return Err(invalid_decommission_pool_index_error(pool_count, idx));
-            };
-            pool.last_update = now;
-            return Ok(true);
-        }
-
-        Ok(false)
+        Ok(self
+            .decommission_progress_checkpoint(idx, duration, OffsetDateTime::now_utc())?
+            .is_some())
     }
 
     pub fn validate(&self, pools: Vec<Arc<Sets>>) -> Result<bool> {
@@ -2151,6 +2263,16 @@ pub struct PoolDecommissionInfo {
     pub terminal_reload_failures: Vec<String>,
     #[serde(skip)]
     pub progress_save_item_baseline: usize,
+    #[serde(skip)]
+    pub progress_save_retry_after: Option<OffsetDateTime>,
+}
+
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+struct DecommissionProgressCheckpoint {
+    start_time: Option<OffsetDateTime>,
+    queued: bool,
+    counted_items: usize,
+    checkpoint_at: OffsetDateTime,
 }
 
 impl PoolDecommissionInfo {
@@ -2185,6 +2307,7 @@ impl PoolDecommissionInfo {
 
     fn mark_progress_saved(&mut self) {
         self.progress_save_item_baseline = self.counted_items();
+        self.progress_save_retry_after = None;
     }
 
     pub fn bucket_push(&mut self, bucket: &DecomBucketInfo) {
@@ -2489,6 +2612,40 @@ impl ECStore {
         snapshot.save(self.pools.clone()).await
     }
 
+    async fn save_decommission_progress_checkpoint(&self, idx: usize) -> Result<bool> {
+        // Lock order: save gate, then the short pool metadata read/write sections. Peer
+        // reloads are intentionally performed by the caller after both locks are released.
+        let _save_guard = self.pool_meta_save_gate.lock().await;
+        let (snapshot, checkpoint) = {
+            let pool_meta = self.pool_meta.read().await;
+            let Some(checkpoint) = pool_meta.decommission_progress_checkpoint(
+                idx,
+                DECOMMISSION_PROGRESS_SAVE_INTERVAL,
+                OffsetDateTime::now_utc(),
+            )?
+            else {
+                return Ok(false);
+            };
+
+            let mut snapshot = pool_meta.clone();
+            let Some(pool) = snapshot.pools.get_mut(idx) else {
+                return Err(invalid_decommission_pool_index_error(snapshot.pools.len(), idx));
+            };
+            pool.last_update = checkpoint.checkpoint_at;
+            (snapshot, checkpoint)
+        };
+
+        if let Err(err) = snapshot.save(self.pools.clone()).await {
+            let retry_after = OffsetDateTime::now_utc() + DECOMMISSION_PROGRESS_SAVE_RETRY_BACKOFF;
+            let mut pool_meta = self.pool_meta.write().await;
+            pool_meta.defer_decommission_progress_checkpoint(idx, checkpoint, retry_after);
+            return Err(err);
+        }
+
+        let mut pool_meta = self.pool_meta.write().await;
+        Ok(pool_meta.commit_decommission_progress_checkpoint(idx, checkpoint))
+    }
+
     async fn save_current_pool_meta_for_decommission_start(
         &self,
         indices: &[usize],
@@ -2871,7 +3028,7 @@ impl ECStore {
         Ok(())
     }
 
-    async fn save_decommission_entry_progress_stage(
+    async fn track_decommission_entry_progress_stage(
         &self,
         idx: usize,
         bucket: &str,
@@ -2882,22 +3039,6 @@ impl ECStore {
             let mut pool_meta = self.pool_meta.write().await;
             track_decommission_current_object_stage(&mut pool_meta, idx, bucket, object, stage)
                 .map_err(|err| with_decommission_entry_context(stage, bucket, object, err))?;
-            touch_decommission_progress(&mut pool_meta, idx)
-                .map_err(|err| with_decommission_entry_context(stage, bucket, object, err))?;
-        }
-
-        if let Some(err) = resolve_decommission_progress_save_result(self.save_current_pool_meta().await) {
-            warn!(
-                event = EVENT_DECOMMISSION_ENTRY,
-                component = LOG_COMPONENT_ECSTORE,
-                subsystem = LOG_SUBSYSTEM_POOLS,
-                pool_index = idx,
-                bucket = %bucket,
-                object = %object,
-                stage,
-                error = ?err,
-                "Decommission progress stage save failed"
-            );
         }
 
         Ok(())
@@ -3165,7 +3306,7 @@ impl ECStore {
                 let bucket_name = bucket.clone();
                 let object_name = rd.object_info.name.clone();
 
-                self.save_decommission_entry_progress_stage(
+                self.track_decommission_entry_progress_stage(
                     idx,
                     bucket_name.as_str(),
                     object_name.as_str(),
@@ -3259,7 +3400,7 @@ impl ECStore {
             }
             decommission_cancel_signal_result(rx.is_cancelled())?;
 
-            self.save_decommission_entry_progress_stage(
+            self.track_decommission_entry_progress_stage(
                 idx,
                 bucket.as_str(),
                 entry.name.as_str(),
@@ -3267,7 +3408,7 @@ impl ECStore {
             )
             .await?;
 
-            self.save_decommission_entry_progress_stage(
+            self.track_decommission_entry_progress_stage(
                 idx,
                 bucket.as_str(),
                 entry.name.as_str(),
@@ -3334,34 +3475,42 @@ impl ECStore {
             }
         };
 
-        self.save_decommission_entry_progress_stage(idx, bucket.as_str(), entry.name.as_str(), DECOMMISSION_STAGE_ENTRY_FINISHED)
-            .await?;
+        self.track_decommission_entry_progress_stage(
+            idx,
+            bucket.as_str(),
+            entry.name.as_str(),
+            DECOMMISSION_STAGE_ENTRY_FINISHED,
+        )
+        .await?;
 
         if should_save_progress {
-            let save_result = self.save_current_pool_meta().await;
-            if let Some(err) = resolve_decommission_progress_save_result(save_result) {
-                warn!(
-                    event = EVENT_DECOMMISSION_ENTRY,
-                    component = LOG_COMPONENT_ECSTORE,
-                    subsystem = LOG_SUBSYSTEM_POOLS,
-                    pool_index = idx,
-                    bucket = %bucket,
-                    object = %entry.name,
-                    state = "progress_save_failed",
-                    error = %err,
-                    "Decommission progress save failed; continuing and will retry at the next checkpoint"
-                );
-            } else {
-                let mut pool_meta = self.pool_meta.write().await;
-                pool_meta.mark_decommission_progress_saved();
-                if let Some(notification_sys) = runtime_sources::notification_sys()
-                    && let Err(err) = resolve_decommission_entry_reload_result(
-                        notification_sys.reload_pool_meta().await,
-                        bucket.as_str(),
-                        entry.name.as_str(),
-                    )
-                {
-                    warn!("{err}");
+            match self.save_decommission_progress_checkpoint(idx).await {
+                Ok(true) => {
+                    if let Some(notification_sys) = runtime_sources::notification_sys()
+                        && let Err(err) = resolve_decommission_entry_reload_result(
+                            notification_sys.reload_pool_meta().await,
+                            bucket.as_str(),
+                            entry.name.as_str(),
+                        )
+                    {
+                        warn!("{err}");
+                    }
+                }
+                Ok(false) => {}
+                Err(err) => {
+                    if let Some(err) = resolve_decommission_progress_save_result(Err(err)) {
+                        warn!(
+                            event = EVENT_DECOMMISSION_ENTRY,
+                            component = LOG_COMPONENT_ECSTORE,
+                            subsystem = LOG_SUBSYSTEM_POOLS,
+                            pool_index = idx,
+                            bucket = %bucket,
+                            object = %entry.name,
+                            state = "progress_save_failed",
+                            error = %err,
+                            "Decommission progress save failed; continuing and will retry at the next checkpoint"
+                        );
+                    }
                 }
             }
         }
@@ -3538,6 +3687,7 @@ impl ECStore {
             let rx_clone = rx.clone();
             let bi = bi.clone();
             let set_id = set_idx;
+            let listing_entry_error = entry_error.clone();
             let worker = tokio::spawn(async move {
                 let _listing_permit = listing_permit;
                 run_decommission_listing_with_retry(
@@ -3551,7 +3701,11 @@ impl ECStore {
                         let set = set.clone();
                         let rx = rx_clone.clone();
                         let bucket = bi.clone();
-                        async move { set.list_objects_to_decommission(rx, bucket, callback).await }
+                        let entry_error = listing_entry_error.clone();
+                        async move {
+                            set.list_objects_to_decommission(rx, bucket, callback, entry_error.clone(), idx, set_id)
+                                .await
+                        }
                     },
                 )
                 .await
@@ -3581,11 +3735,7 @@ impl ECStore {
 
         wait_decommission_worker_drain(&workers, worker_limit).await?;
 
-        if let Some(err) = listing_worker_error {
-            return Err(err);
-        }
-
-        if let Some(err) = entry_error.lock().await.clone() {
+        if let Some(err) = resolve_decommission_listing_error(listing_worker_error, entry_error.lock().await.clone()) {
             return Err(err);
         }
 
@@ -4191,7 +4341,7 @@ impl ECStore {
         let buckets = self.get_buckets_to_decommission().await?;
         let pool = self.pools[idx].clone();
 
-        for set in &pool.disk_set {
+        for (set_index, set) in pool.disk_set.iter().enumerate() {
             for bucket_info in &buckets {
                 let mut lifecycle_config = None;
                 let mut object_lock_config = None;
@@ -4286,7 +4436,7 @@ impl ECStore {
                 });
 
                 let list_result = set
-                    .list_objects_to_decommission(callback_rx, bucket_info.clone(), callback)
+                    .list_objects_to_decommission(callback_rx, bucket_info.clone(), callback, entry_error.clone(), idx, set_index)
                     .await;
                 let entry_error = entry_error.lock().await.clone();
                 resolve_decommission_check_after_list_result(list_result, entry_error)?;
@@ -5021,12 +5171,15 @@ mod tests {
 pub type ListCallback = Arc<dyn Fn(MetaCacheEntry) -> BoxFuture<'static, ()> + Send + Sync + 'static>;
 
 impl SetDisks {
-    #[tracing::instrument(skip(self, rx, cb_func))]
+    #[tracing::instrument(skip(self, rx, cb_func, entry_error))]
     async fn list_objects_to_decommission(
         self: &Arc<Self>,
         rx: CancellationToken,
         bucket_info: DecomBucketInfo,
         cb_func: ListCallback,
+        entry_error: Arc<tokio::sync::Mutex<Option<Error>>>,
+        pool_index: usize,
+        set_index: usize,
     ) -> Result<()> {
         let (disks, _) = self.get_online_disks_with_healing(false).await;
         ensure_decommission_listing_disks_available(!disks.is_empty(), &bucket_info.name)?;
@@ -5041,6 +5194,12 @@ impl SetDisks {
         };
 
         let cb1 = cb_func.clone();
+        let unresolved_error = entry_error.clone();
+        let unresolved_rx = rx.clone();
+        let unresolved_bucket = bucket_info.name.clone();
+        let unresolved_prefix = bucket_info.prefix.clone();
+        let unresolved_pool_index = pool_index;
+        let unresolved_set_index = set_index;
 
         list_path_raw(
             rx,
@@ -5053,20 +5212,51 @@ impl SetDisks {
                 skip_walkdir_total_timeout: true,
                 walkdir_stall_timeout: Some(DECOMMISSION_BACKGROUND_WALKDIR_STALL_TIMEOUT),
                 agreed: Some(Box::new(move |entry: MetaCacheEntry| Box::pin(cb1(entry)))),
-                partial: Some(Box::new(move |entries: MetaCacheEntries, _: &[Option<DiskError>]| {
+                partial: Some(Box::new(move |entries: MetaCacheEntries, errs: &[Option<DiskError>]| {
                     let resolver = resolver.clone();
                     let cb_func = cb_func.clone();
-                    match entries.resolve(resolver) {
-                        Some(entry) => {
+                    let bucket = unresolved_bucket.clone();
+                    let prefix = unresolved_prefix.clone();
+                    let unresolved_error = unresolved_error.clone();
+                    let unresolved_rx = unresolved_rx.clone();
+                    let pool_index = unresolved_pool_index;
+                    let set_index = unresolved_set_index;
+                    let disk_error_count = errs.iter().flatten().count();
+                    if unresolved_rx.is_cancelled() {
+                        return Box::pin(async {});
+                    }
+
+                    match resolve_decommission_partial_listing_entry(
+                        entries,
+                        resolver,
+                        &bucket,
+                        &prefix,
+                        disk_error_count,
+                        pool_index,
+                        set_index,
+                    ) {
+                        Ok(entry) => {
                             warn!("decommission_pool: list_objects_to_decommission get {}", &entry.name);
                             Box::pin(async move {
                                 cb_func(entry).await;
                             })
                         }
-                        None => {
-                            warn!("decommission_pool: list_objects_to_decommission get none");
-                            Box::pin(async {})
-                        }
+                        Err(err) => Box::pin(async move {
+                            if unresolved_rx.is_cancelled() {
+                                return;
+                            }
+                            warn!(
+                                event = EVENT_DECOMMISSION_BUCKET,
+                                component = LOG_COMPONENT_ECSTORE,
+                                subsystem = LOG_SUBSYSTEM_POOLS,
+                                bucket = %bucket,
+                                prefix = %prefix,
+                                state = "unresolved_entry",
+                                error = %err,
+                                "Decommission listing failed closed on unresolved metadata"
+                            );
+                            record_decommission_entry_error(&unresolved_error, &unresolved_rx, err).await;
+                        }),
                     }
                 })),
                 ..Default::default()
@@ -5074,6 +5264,10 @@ impl SetDisks {
         )
         .await?;
 
+        if let Some(err) = entry_error.lock().await.clone() {
+            return Err(err);
+        }
+
         Ok(())
     }
 }
@@ -5264,11 +5458,11 @@ pub(crate) fn fallback_free_capacity_dedup(disks: &[rustfs_madmin::Disk]) -> usi
 #[cfg(test)]
 mod pools_tests {
     use super::{
-        DECOMMISSION_PROGRESS_SAVE_INTERVAL, DECOMMISSION_PROGRESS_SAVE_ITEM_THRESHOLD, DecomBucketInfo,
-        DecommissionStartPoolState, DecommissionTerminalState, ListCallback, PoolDecommissionInfo, PoolMeta, PoolSpaceInfo,
-        PoolStatus, apply_decommission_status_space_info, bind_decommission_cancelers, bind_missing_decommission_cancelers,
-        cancel_decommission_canceler, classify_decommission_terminal_state, count_decommission_item,
-        decommission_cancel_signal_result, decommission_item_size, decommission_meta_bucket_options,
+        DECOMMISSION_PROGRESS_SAVE_INTERVAL, DECOMMISSION_PROGRESS_SAVE_ITEM_THRESHOLD, DECOMMISSION_PROGRESS_SAVE_RETRY_BACKOFF,
+        DecomBucketInfo, DecommissionStartPoolState, DecommissionTerminalState, ListCallback, PoolDecommissionInfo, PoolMeta,
+        PoolSpaceInfo, PoolStatus, apply_decommission_status_space_info, bind_decommission_cancelers,
+        bind_missing_decommission_cancelers, cancel_decommission_canceler, classify_decommission_terminal_state,
+        count_decommission_item, decommission_cancel_signal_result, decommission_item_size, decommission_meta_bucket_options,
         decommission_start_pool_state, dedup_indices, default_decommission_bucket_concurrency,
         ensure_decommission_cancel_allowed, ensure_decommission_clear_allowed, ensure_decommission_listing_disks_available,
         ensure_decommission_not_rebalancing, ensure_decommission_start_allowed, ensure_decommission_start_keeps_active_pool,
@@ -5279,11 +5473,12 @@ mod pools_tests {
         has_active_decommission_canceler, is_decommission_active, is_decommission_cancel_requested,
         load_decommission_entry_versions, local_decommission_queue_prefix, mark_decommission_bucket_done,
         merge_pool_status_refresh, missing_decommission_worker_prefix, observe_decommission_terminal_reload_result,
-        pool_meta_has_active_decommission, require_decommission_store, resolve_decommission_bucket_done_save_result,
-        resolve_decommission_bucket_state, resolve_decommission_check_after_list_result,
-        resolve_decommission_entry_cleanup_delete_result, resolve_decommission_entry_exact_versions,
-        resolve_decommission_entry_reload_result, resolve_decommission_listing_worker_result,
-        resolve_decommission_optional_bucket_config_result, resolve_decommission_pool_meta_reload_result,
+        pool_meta_has_active_decommission, record_decommission_entry_error, require_decommission_store,
+        resolve_decommission_bucket_done_save_result, resolve_decommission_bucket_state,
+        resolve_decommission_check_after_list_result, resolve_decommission_entry_cleanup_delete_result,
+        resolve_decommission_entry_exact_versions, resolve_decommission_entry_reload_result, resolve_decommission_listing_error,
+        resolve_decommission_listing_worker_result, resolve_decommission_optional_bucket_config_result,
+        resolve_decommission_partial_listing_entry, resolve_decommission_pool_meta_reload_result,
         resolve_decommission_preflight_heal_result, resolve_decommission_progress_save_result,
         resolve_decommission_spawn_failure_result, resolve_decommission_terminal_mark_after_error_result,
         resolve_decommission_terminal_mark_result, resolve_decommission_update_after_result,
@@ -5293,16 +5488,17 @@ mod pools_tests {
         should_preserve_decommission_canceled_state, should_reject_decommission_cancel_as_terminal,
         should_retry_decommission_cancel_reload, should_retry_decommission_listing, should_skip_canceled_decommission_routine,
         split_decommission_buckets, take_and_cancel_decommission_canceler, take_decommission_canceler,
-        touch_decommission_progress, track_decommission_current_object, track_decommission_current_object_stage,
-        validate_start_decommission_request, wait_decommission_listing_retry, wait_decommission_worker_drain,
-        with_decommission_entry_context,
+        track_decommission_current_object, track_decommission_current_object_stage, validate_start_decommission_request,
+        wait_decommission_listing_retry, wait_decommission_worker_drain, with_decommission_entry_context,
     };
     use crate::data_movement;
     use crate::disk::endpoint::Endpoint;
     use crate::error::{Error, StorageError};
     use crate::layout::endpoints::{EndpointServerPools, Endpoints, PoolEndpoints};
     use crate::services::rebalance::{RebalStatus, RebalanceInfo, RebalanceMeta, RebalanceStats};
-    use rustfs_filemeta::{FileInfo, FileInfoVersions, MetaCacheEntry, ObjectPartInfo};
+    use rustfs_filemeta::{
+        FileInfo, FileInfoVersions, MetaCacheEntries, MetaCacheEntry, MetadataResolutionParams, ObjectPartInfo,
+    };
     use rustfs_rio::Index;
     use std::sync::{
         Arc,
@@ -6321,6 +6517,65 @@ mod pools_tests {
         assert!(matches!(err, Error::SlowDown));
     }
 
+    #[test]
+    fn test_resolve_decommission_partial_listing_entry_rejects_unresolved_metadata() {
+        let err = resolve_decommission_partial_listing_entry(
+            MetaCacheEntries(vec![None]),
+            MetadataResolutionParams {
+                dir_quorum: 2,
+                obj_quorum: 2,
+                bucket: "bucket-a".to_string(),
+                ..Default::default()
+            },
+            "bucket-a",
+            "prefix/",
+            1,
+            2,
+            3,
+        )
+        .expect_err("unresolved partial listing must fail closed");
+
+        let message = err.to_string();
+        assert!(message.contains("decommission listing could not resolve metadata"));
+        assert!(message.contains("bucket-a/prefix/"));
+        assert!(message.contains("pool 2 set 3"));
+        assert!(message.contains("1 disk error(s)"));
+    }
+
+    #[tokio::test]
+    async fn test_record_decommission_entry_error_cancels_listing_and_preserves_first_error() {
+        let entry_error = Arc::new(tokio::sync::Mutex::new(None));
+        let rx = CancellationToken::new();
+
+        record_decommission_entry_error(&entry_error, &rx, Error::SlowDown).await;
+        record_decommission_entry_error(&entry_error, &rx, Error::OperationCanceled).await;
+
+        assert!(rx.is_cancelled());
+        assert!(matches!(*entry_error.lock().await, Some(Error::SlowDown)));
+    }
+
+    #[tokio::test]
+    async fn test_record_decommission_entry_error_ignores_already_canceled_listing() {
+        let entry_error = Arc::new(tokio::sync::Mutex::new(None));
+        let rx = CancellationToken::new();
+        rx.cancel();
+
+        record_decommission_entry_error(&entry_error, &rx, Error::SlowDown).await;
+
+        assert!(entry_error.lock().await.is_none());
+    }
+
+    #[test]
+    fn test_resolve_decommission_listing_error_preserves_real_listing_failure() {
+        let err = resolve_decommission_listing_error(Some(Error::SlowDown), Some(Error::OperationCanceled))
+            .expect("listing failure should be returned");
+        assert!(matches!(err, Error::SlowDown));
+
+        let err = resolve_decommission_listing_error(Some(Error::OperationCanceled), Some(Error::SlowDown))
+            .expect("entry failure should be returned");
+        assert!(matches!(err, Error::SlowDown));
+    }
+
     #[test]
     fn test_resolve_decommission_check_after_list_result_returns_list_result_without_entry_error() {
         let err = resolve_decommission_check_after_list_result(Err(Error::OperationCanceled), None)
@@ -6538,7 +6793,7 @@ mod pools_tests {
     }
 
     #[test]
-    fn test_touch_decommission_progress_updates_last_update_and_save_baseline() {
+    fn test_track_decommission_stage_does_not_advance_checkpoint_state() {
         let mut meta = PoolMeta {
             pools: vec![PoolStatus {
                 id: 0,
@@ -6553,11 +6808,13 @@ mod pools_tests {
             ..Default::default()
         };
 
-        touch_decommission_progress(&mut meta, 0).expect("valid decommission progress should be touched");
+        track_decommission_current_object_stage(&mut meta, 0, "bucket", "object", "migrate_object")
+            .expect("valid decommission progress should be tracked");
 
-        assert!(meta.pools[0].last_update > OffsetDateTime::UNIX_EPOCH);
+        assert_eq!(meta.pools[0].last_update, OffsetDateTime::UNIX_EPOCH);
         let info = meta.pools[0].decommission.as_ref().expect("decommission info should exist");
-        assert_eq!(info.items_since_last_progress_save(), 0);
+        assert_eq!(info.items_since_last_progress_save(), 5);
+        assert_eq!(info.stage, "migrate_object");
     }
 
     #[test]
@@ -6632,6 +6889,134 @@ mod pools_tests {
         assert_eq!(info.items_since_last_progress_save(), 1);
     }
 
+    #[test]
+    fn test_pool_meta_update_after_does_not_advance_last_update_before_save() {
+        let last_update = OffsetDateTime::UNIX_EPOCH;
+        let mut meta = PoolMeta {
+            pools: vec![PoolStatus {
+                id: 0,
+                cmd_line: "pool-0".to_string(),
+                last_update,
+                decommission: Some(PoolDecommissionInfo {
+                    start_time: Some(last_update),
+                    items_decommissioned: DECOMMISSION_PROGRESS_SAVE_ITEM_THRESHOLD,
+                    ..Default::default()
+                }),
+            }],
+            ..Default::default()
+        };
+
+        assert!(
+            meta.update_after(0, DECOMMISSION_PROGRESS_SAVE_INTERVAL)
+                .expect("item threshold should request a checkpoint")
+        );
+        assert_eq!(meta.pools[0].last_update, last_update);
+    }
+
+    #[test]
+    fn test_decommission_progress_checkpoint_commits_exact_snapshot_watermark() {
+        let start_time = OffsetDateTime::UNIX_EPOCH;
+        let checkpoint_at = start_time + Duration::seconds(30);
+        let mut meta = PoolMeta {
+            pools: vec![PoolStatus {
+                id: 0,
+                cmd_line: "pool-0".to_string(),
+                last_update: start_time,
+                decommission: Some(PoolDecommissionInfo {
+                    start_time: Some(start_time),
+                    items_decommissioned: DECOMMISSION_PROGRESS_SAVE_ITEM_THRESHOLD,
+                    ..Default::default()
+                }),
+            }],
+            ..Default::default()
+        };
+
+        let checkpoint = meta
+            .decommission_progress_checkpoint(0, DECOMMISSION_PROGRESS_SAVE_INTERVAL, checkpoint_at)
+            .expect("valid decommission state should produce a checkpoint")
+            .expect("item threshold should produce a checkpoint");
+        meta.count_item(0, 1, false);
+
+        assert!(meta.commit_decommission_progress_checkpoint(0, checkpoint));
+        let info = meta.pools[0].decommission.as_ref().expect("decommission info should exist");
+        assert_eq!(info.progress_save_item_baseline, checkpoint.counted_items);
+        assert_eq!(info.items_since_last_progress_save(), 1);
+        assert_eq!(meta.pools[0].last_update, checkpoint_at);
+    }
+
+    #[test]
+    fn test_decommission_progress_checkpoint_backoff_does_not_advance_baseline() {
+        let start_time = OffsetDateTime::UNIX_EPOCH;
+        let checkpoint_at = start_time + Duration::seconds(30);
+        let retry_after = checkpoint_at + DECOMMISSION_PROGRESS_SAVE_RETRY_BACKOFF;
+        let mut meta = PoolMeta {
+            pools: vec![PoolStatus {
+                id: 0,
+                cmd_line: "pool-0".to_string(),
+                last_update: start_time,
+                decommission: Some(PoolDecommissionInfo {
+                    start_time: Some(start_time),
+                    items_decommissioned: DECOMMISSION_PROGRESS_SAVE_ITEM_THRESHOLD,
+                    ..Default::default()
+                }),
+            }],
+            ..Default::default()
+        };
+
+        let checkpoint = meta
+            .decommission_progress_checkpoint(0, DECOMMISSION_PROGRESS_SAVE_INTERVAL, checkpoint_at)
+            .expect("valid decommission state should produce a checkpoint")
+            .expect("item threshold should produce a checkpoint");
+        meta.defer_decommission_progress_checkpoint(0, checkpoint, retry_after);
+
+        assert!(
+            meta.decommission_progress_checkpoint(0, DECOMMISSION_PROGRESS_SAVE_INTERVAL, checkpoint_at)
+                .expect("retry backoff check should succeed")
+                .is_none()
+        );
+        assert_eq!(meta.pools[0].last_update, start_time);
+        assert_eq!(
+            meta.pools[0]
+                .decommission
+                .as_ref()
+                .expect("decommission info should exist")
+                .progress_save_item_baseline,
+            0
+        );
+    }
+
+    #[test]
+    fn test_decommission_progress_checkpoint_count_scales_with_threshold() {
+        let start_time = OffsetDateTime::UNIX_EPOCH;
+        let checkpoint_at = start_time;
+        let mut meta = PoolMeta {
+            pools: vec![PoolStatus {
+                id: 0,
+                cmd_line: "pool-0".to_string(),
+                last_update: start_time,
+                decommission: Some(PoolDecommissionInfo {
+                    start_time: Some(start_time),
+                    ..Default::default()
+                }),
+            }],
+            ..Default::default()
+        };
+        let mut checkpoint_count = 0;
+
+        for _ in 0..(DECOMMISSION_PROGRESS_SAVE_ITEM_THRESHOLD * 10) {
+            meta.count_item(0, 1, false);
+            if let Some(checkpoint) = meta
+                .decommission_progress_checkpoint(0, DECOMMISSION_PROGRESS_SAVE_INTERVAL, checkpoint_at)
+                .expect("valid decommission state should produce a checkpoint")
+            {
+                checkpoint_count += 1;
+                assert!(meta.commit_decommission_progress_checkpoint(0, checkpoint));
+            }
+        }
+
+        assert_eq!(checkpoint_count, 10);
+    }
+
     #[test]
     fn test_ensure_decommission_not_rebalancing_rejects_running_rebalance() {
         let err = ensure_decommission_not_rebalancing(true).expect_err("rebalance running should be rejected");

crates/ecstore/src/disk/os.rs

@@ -315,7 +315,7 @@ pub async fn fsync_dir(dir: impl AsRef<Path>) -> io::Result<()> {
     #[cfg(unix)]
     {
         let dir = dir.as_ref().to_path_buf();
-        tokio::task::spawn_blocking(move || fsync_dir_std(dir)).await?
+        fsync_spawn_blocking(move || fsync_dir_std(dir)).await?
     }
 
     #[cfg(not(unix))]
@@ -683,7 +683,7 @@ async fn fsync_open_dst_dir_group(group: &DstDirFsyncGroup) -> io::Result<()> {
     #[cfg(test)]
     let dir = group.dir.clone();
     let dir_file = group.dir_file.clone();
-    tokio::task::spawn_blocking(move || {
+    fsync_spawn_blocking(move || {
         #[cfg(test)]
         {
             if let Some(kind) = fsync_dir_recorder::take_grouped_failure(&dir) {
@@ -1080,6 +1080,44 @@ const TEST_GLOBAL_FILE_SYNCS: usize = 64;
 
 static FILE_SYNC_PERMITS: LazyLock<Semaphore> = LazyLock::new(|| Semaphore::new(global_file_sync_limit()));
 static DISK_FILE_SYNC_LIMITERS: LazyLock<Mutex<HashMap<PathBuf, Weak<Semaphore>>>> = LazyLock::new(|| Mutex::new(HashMap::new()));
+
+/// Dedicated tokio runtime for fsync/fdatasync blocking operations. When
+/// configured with >1 threads, isolates device-bound fsync from the main
+/// blocking pool so reads (pread/stat/open) are not starved. `None` means
+/// fall back to the main runtime (zero behavior change).
+static FSYNC_RUNTIME: LazyLock<Option<tokio::runtime::Runtime>> = LazyLock::new(|| {
+    let threads =
+        rustfs_utils::get_env_usize(rustfs_config::ENV_FSYNC_BLOCKING_THREADS, rustfs_config::DEFAULT_FSYNC_BLOCKING_THREADS);
+    if threads <= 1 {
+        return None;
+    }
+    let mut builder = tokio::runtime::Builder::new_multi_thread();
+    builder
+        .worker_threads(num_cpus::get().min(8))
+        .max_blocking_threads(threads)
+        .thread_name("rustfs-fsync")
+        .thread_stack_size(512 * 1024)
+        .enable_all();
+    match builder.build() {
+        Ok(rt) => {
+            tracing::info!(threads, "fsync dedicated blocking pool enabled");
+            Some(rt)
+        }
+        Err(err) => {
+            tracing::warn!(%err, "failed to build fsync runtime, falling back to main pool");
+            None
+        }
+    }
+});
+
+/// Spawn a blocking task on the fsync-dedicated runtime if configured,
+/// otherwise fall back to the main tokio blocking pool.
+fn fsync_spawn_blocking<T: Send + 'static>(f: impl FnOnce() -> T + Send + 'static) -> tokio::task::JoinHandle<T> {
+    match FSYNC_RUNTIME.as_ref() {
+        Some(rt) => rt.spawn_blocking(f),
+        None => tokio::task::spawn_blocking(f),
+    }
+}
 static DISK_VOLUME_MUTATION_LOCKS: LazyLock<Mutex<HashMap<PathBuf, Weak<RwLock<()>>>>> =
     LazyLock::new(|| Mutex::new(HashMap::new()));
 type NamespaceMutationLock = AsyncMutex<()>;
@@ -1217,7 +1255,7 @@ where
     F: FnOnce() -> io::Result<T> + Send + 'static,
 {
     let (disk_permit, global_permit) = acquire_file_sync_permits(disk_permits).await?;
-    let result = tokio::task::spawn_blocking(move || {
+    let result = fsync_spawn_blocking(move || {
         let _disk_permit = disk_permit;
         work()
     })
@@ -2146,7 +2184,7 @@ async fn run_blocking_namespace_file_sync_operation_with_global<T: Send + 'stati
         wait_started,
     );
     let disk_permit = admission.disk_permit.clone();
-    let result = tokio::task::spawn_blocking(move || {
+    let result = fsync_spawn_blocking(move || {
         let _lease = lease;
         let _disk_permit = disk_permit;
         operation()

crates/ecstore/src/store/rebalance.rs

@@ -859,6 +859,7 @@ fn lifecycle_delete_all_test_failure(phase: crate::object_api::LifecycleDeleteAl
 #[cfg(test)]
 mod tests {
     use super::*;
+    use crate::bucket::replication::{ReplicationStatusType, VersionPurgeStatusType};
     use crate::config::storageclass::{CLASS_RRS, CLASS_STANDARD, lookup_config_for_pools_without_env};
     use crate::disk::error::DiskError;
     use crate::layout::endpoint::Endpoint;
@@ -1423,6 +1424,14 @@ mod tests {
         }
     }
 
+    fn object_info_with_identity(unix_ts: i64, delete_marker: bool, version_id: Uuid, etag: Option<String>) -> ObjectInfo {
+        ObjectInfo {
+            version_id: Some(version_id),
+            etag,
+            ..object_info_with_mod_time(unix_ts, delete_marker)
+        }
+    }
+
     #[test]
     fn resolve_latest_object_info_candidates_returns_latest_delete_marker() {
         let candidates = vec![
@@ -1446,7 +1455,7 @@ mod tests {
     }
 
     #[test]
-    fn resolve_latest_object_info_candidates_prefers_higher_pool_idx_on_equal_mod_time() {
+    fn resolve_latest_object_info_candidates_prefers_higher_pool_idx_on_equal_mod_time_for_equivalent_candidates() {
         let candidates = vec![
             LatestObjectInfoCandidate {
                 info: Some(object_info_with_mod_time(10, false)),
@@ -1466,6 +1475,333 @@ mod tests {
         assert_eq!(idx, 1);
     }
 
+    #[test]
+    fn resolve_latest_object_info_candidates_keeps_index_fallback_for_fully_equivalent_identities() {
+        let candidates = vec![
+            LatestObjectInfoCandidate {
+                info: Some(object_info_with_identity(10, false, Uuid::from_u128(1), Some("etag-a".to_string()))),
+                idx: 2,
+                err: None,
+            },
+            LatestObjectInfoCandidate {
+                info: Some(object_info_with_identity(10, false, Uuid::from_u128(1), Some("etag-a".to_string()))),
+                idx: 7,
+                err: None,
+            },
+        ];
+
+        let (info, idx) = resolve_latest_object_info_candidates(candidates, "bucket", "object", &ObjectOptions::default())
+            .expect("equivalent replicas must resolve deterministically");
+
+        assert_eq!(idx, 7);
+        assert_eq!(info.version_id, Some(Uuid::from_u128(1)));
+    }
+
+    #[test]
+    fn resolve_latest_object_info_candidates_rejects_equal_time_version_id_conflict() {
+        let candidates = vec![
+            LatestObjectInfoCandidate {
+                info: Some(object_info_with_identity(10, false, Uuid::from_u128(1), Some("etag-a".to_string()))),
+                idx: 0,
+                err: None,
+            },
+            LatestObjectInfoCandidate {
+                info: Some(object_info_with_identity(10, false, Uuid::from_u128(2), Some("etag-a".to_string()))),
+                idx: 1,
+                err: None,
+            },
+        ];
+
+        let err = resolve_latest_object_info_candidates(candidates, "bucket", "object", &ObjectOptions::default())
+            .expect_err("divergent version ids must not silently resolve to the higher pool index");
+
+        assert_eq!(err, Error::ErasureReadQuorum);
+    }
+
+    #[test]
+    fn resolve_latest_object_info_candidates_rejects_equal_time_etag_conflict() {
+        let candidates = vec![
+            LatestObjectInfoCandidate {
+                info: Some(object_info_with_identity(10, false, Uuid::from_u128(1), Some("etag-old".to_string()))),
+                idx: 0,
+                err: None,
+            },
+            LatestObjectInfoCandidate {
+                info: Some(object_info_with_identity(10, false, Uuid::from_u128(1), Some("etag-new".to_string()))),
+                idx: 1,
+                err: None,
+            },
+        ];
+
+        let err = resolve_latest_object_info_candidates(candidates, "bucket", "object", &ObjectOptions::default())
+            .expect_err("divergent etags must not silently resolve to the higher pool index");
+
+        assert_eq!(err, Error::ErasureReadQuorum);
+    }
+
+    #[test]
+    fn resolve_latest_object_info_candidates_rejects_equal_time_delete_marker_conflict() {
+        let candidates = vec![
+            LatestObjectInfoCandidate {
+                info: Some(object_info_with_identity(10, false, Uuid::from_u128(1), None)),
+                idx: 0,
+                err: None,
+            },
+            LatestObjectInfoCandidate {
+                info: Some(object_info_with_identity(10, true, Uuid::from_u128(1), Some("etag-a".to_string()))),
+                idx: 1,
+                err: None,
+            },
+        ];
+
+        let err = resolve_latest_object_info_candidates(candidates, "bucket", "object", &ObjectOptions::default())
+            .expect_err("a delete marker tied with a live version must not be masked by the pool index");
+
+        assert_eq!(err, Error::ErasureReadQuorum);
+    }
+
+    fn assert_equal_time_identity_conflict(left: ObjectInfo, right: ObjectInfo) {
+        let err = resolve_latest_object_info_candidates(
+            vec![
+                LatestObjectInfoCandidate {
+                    info: Some(left),
+                    idx: 0,
+                    err: None,
+                },
+                LatestObjectInfoCandidate {
+                    info: Some(right),
+                    idx: 1,
+                    err: None,
+                },
+            ],
+            "bucket",
+            "object",
+            &ObjectOptions::default(),
+        )
+        .expect_err("equal-time identity divergence must fail closed");
+
+        assert_eq!(err, Error::ErasureReadQuorum);
+    }
+
+    #[test]
+    fn resolve_latest_object_info_candidates_rejects_equal_time_payload_identity_conflicts() {
+        let base = object_info_with_identity(10, false, Uuid::from_u128(1), Some("etag-a".to_string()));
+
+        let mut data_dir = base.clone();
+        data_dir.data_dir = Some(Uuid::from_u128(2));
+        assert_equal_time_identity_conflict(base.clone(), data_dir);
+
+        let mut size = base.clone();
+        size.size = 1;
+        assert_equal_time_identity_conflict(base.clone(), size);
+
+        let mut actual_size = base.clone();
+        actual_size.actual_size = 1;
+        assert_equal_time_identity_conflict(base.clone(), actual_size);
+
+        let mut checksum = base.clone();
+        checksum.checksum = Some(bytes::Bytes::from_static(b"checksum"));
+        assert_equal_time_identity_conflict(base.clone(), checksum);
+
+        let mut parts = base.clone();
+        parts.parts = std::sync::Arc::new(vec![rustfs_filemeta::ObjectPartInfo {
+            etag: "part-etag".to_string(),
+            number: 1,
+            size: 1,
+            ..Default::default()
+        }]);
+        assert_equal_time_identity_conflict(base.clone(), parts);
+
+        let mut transition = base;
+        transition.transitioned_object.tier = "tier-a".to_string();
+        assert_equal_time_identity_conflict(
+            object_info_with_identity(10, false, Uuid::from_u128(1), Some("etag-a".to_string())),
+            transition,
+        );
+    }
+
+    #[test]
+    fn resolve_latest_object_info_candidates_accepts_internal_metadata_aliases() {
+        let base = object_info_with_identity(10, false, Uuid::from_u128(1), Some("etag-a".to_string()));
+        let mut rustfs_alias = base.clone();
+        rustfs_alias.user_defined = std::sync::Arc::new(std::collections::HashMap::from([(
+            "x-rustfs-internal-compression".to_string(),
+            "zstd".to_string(),
+        )]));
+        let mut minio_alias = base.clone();
+        minio_alias.user_defined = std::sync::Arc::new(std::collections::HashMap::from([(
+            "X-MINIO-INTERNAL-COMPRESSION".to_string(),
+            "zstd".to_string(),
+        )]));
+
+        let (_, idx) = resolve_latest_object_info_candidates(
+            vec![
+                LatestObjectInfoCandidate {
+                    info: Some(rustfs_alias),
+                    idx: 0,
+                    err: None,
+                },
+                LatestObjectInfoCandidate {
+                    info: Some(minio_alias),
+                    idx: 1,
+                    err: None,
+                },
+            ],
+            "bucket",
+            "object",
+            &ObjectOptions::default(),
+        )
+        .expect("same-value internal aliases should resolve");
+        assert_eq!(idx, 1);
+
+        let mut dual_alias = base.clone();
+        dual_alias.user_defined = std::sync::Arc::new(std::collections::HashMap::from([
+            ("x-rustfs-internal-compression".to_string(), "zstd".to_string()),
+            ("x-minio-internal-compression".to_string(), "zstd".to_string()),
+        ]));
+        let mut single_alias = base;
+        single_alias.user_defined = std::sync::Arc::new(std::collections::HashMap::from([(
+            "x-rustfs-internal-compression".to_string(),
+            "zstd".to_string(),
+        )]));
+
+        let (_, idx) = resolve_latest_object_info_candidates(
+            vec![
+                LatestObjectInfoCandidate {
+                    info: Some(dual_alias),
+                    idx: 0,
+                    err: None,
+                },
+                LatestObjectInfoCandidate {
+                    info: Some(single_alias),
+                    idx: 1,
+                    err: None,
+                },
+            ],
+            "bucket",
+            "object",
+            &ObjectOptions::default(),
+        )
+        .expect("dual-key and single-key internal metadata should resolve");
+        assert_eq!(idx, 1);
+    }
+
+    #[test]
+    fn resolve_latest_object_info_candidates_rejects_different_internal_metadata_alias_values() {
+        let base = object_info_with_identity(10, false, Uuid::from_u128(1), Some("etag-a".to_string()));
+        let mut rustfs_alias = base.clone();
+        rustfs_alias.user_defined = std::sync::Arc::new(std::collections::HashMap::from([(
+            "x-rustfs-internal-compression".to_string(),
+            "zstd".to_string(),
+        )]));
+        let mut minio_alias = base;
+        minio_alias.user_defined = std::sync::Arc::new(std::collections::HashMap::from([(
+            "x-minio-internal-compression".to_string(),
+            "snappy".to_string(),
+        )]));
+
+        assert_equal_time_identity_conflict(rustfs_alias, minio_alias);
+    }
+
+    #[test]
+    fn resolve_latest_object_info_candidates_rejects_conflicting_internal_metadata_aliases_in_one_candidate() {
+        let base = object_info_with_identity(10, false, Uuid::from_u128(1), Some("etag-a".to_string()));
+        let mut first = base.clone();
+        first.user_defined = std::sync::Arc::new(std::collections::HashMap::from([
+            ("x-rustfs-internal-compression".to_string(), "zstd".to_string()),
+            ("x-minio-internal-compression".to_string(), "snappy".to_string()),
+        ]));
+        let mut second = base;
+        second.user_defined = first.user_defined.clone();
+
+        assert_equal_time_identity_conflict(first, second);
+    }
+
+    #[test]
+    fn resolve_latest_object_info_candidates_rejects_replication_identity_conflict() {
+        let base = object_info_with_identity(10, false, Uuid::from_u128(1), Some("etag-a".to_string()));
+
+        let mut replication = base.clone();
+        replication.replication_status_internal = Some("PENDING".to_string());
+        replication.replication_status = ReplicationStatusType::Pending;
+        assert_equal_time_identity_conflict(base.clone(), replication);
+
+        let mut purge = base.clone();
+        purge.version_purge_status_internal = Some("PENDING".to_string());
+        purge.version_purge_status = VersionPurgeStatusType::Pending;
+        assert_equal_time_identity_conflict(base.clone(), purge);
+
+        let mut decision = base;
+        decision.replication_decision = "replicate".to_string();
+        assert_equal_time_identity_conflict(
+            object_info_with_identity(10, false, Uuid::from_u128(1), Some("etag-a".to_string())),
+            decision,
+        );
+    }
+
+    #[test]
+    fn resolve_latest_object_info_candidates_rejects_none_vs_unix_epoch_mod_time() {
+        let mut without_mod_time = object_info_with_identity(0, false, Uuid::from_u128(1), Some("etag-a".to_string()));
+        without_mod_time.mod_time = None;
+        let with_unix_epoch = object_info_with_identity(0, false, Uuid::from_u128(1), Some("etag-a".to_string()));
+
+        assert_equal_time_identity_conflict(without_mod_time, with_unix_epoch);
+    }
+
+    #[test]
+    fn resolve_latest_object_info_candidates_ignores_older_identity_conflicts() {
+        let latest = object_info_with_identity(20, false, Uuid::from_u128(1), Some("etag-latest".to_string()));
+        let mut older = object_info_with_identity(10, true, Uuid::from_u128(2), Some("etag-old".to_string()));
+        older.data_dir = Some(Uuid::from_u128(2));
+
+        let (info, idx) = resolve_latest_object_info_candidates(
+            vec![
+                LatestObjectInfoCandidate {
+                    info: Some(latest),
+                    idx: 0,
+                    err: None,
+                },
+                LatestObjectInfoCandidate {
+                    info: Some(older),
+                    idx: 9,
+                    err: None,
+                },
+            ],
+            "bucket",
+            "object",
+            &ObjectOptions::default(),
+        )
+        .expect("older identity divergence must not affect the latest candidate");
+
+        assert_eq!(idx, 0);
+        assert_eq!(
+            info.mod_time,
+            Some(OffsetDateTime::from_unix_timestamp(20).expect("operation should succeed"))
+        );
+    }
+
+    #[test]
+    fn resolve_latest_object_info_candidates_ignores_not_found_pools_when_resolving() {
+        let candidates = vec![
+            LatestObjectInfoCandidate {
+                info: Some(object_info_with_identity(10, false, Uuid::from_u128(1), Some("etag-a".to_string()))),
+                idx: 0,
+                err: None,
+            },
+            LatestObjectInfoCandidate {
+                info: None,
+                idx: 1,
+                err: Some(Error::ObjectNotFound("bucket".to_string(), "object".to_string())),
+            },
+        ];
+
+        let (info, idx) = resolve_latest_object_info_candidates(candidates, "bucket", "object", &ObjectOptions::default())
+            .expect("not-found pools must not block resolution of found candidates");
+
+        assert_eq!(idx, 0);
+        assert_eq!(info.version_id, Some(Uuid::from_u128(1)));
+    }
+
     #[test]
     fn resolve_latest_object_info_candidates_returns_non_not_found_error() {
         let err = resolve_latest_object_info_candidates(

crates/ecstore/src/store/rebalance/support.rs

@@ -12,10 +12,11 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
-use std::cmp::Ordering;
+use std::collections::HashMap;
 
 use crate::error::{Error, Result, StorageError, is_err_object_not_found, is_err_version_not_found};
 use crate::object_api::{ObjectInfo, ObjectOptions};
+use rustfs_utils::http::metadata_compat::strip_internal_prefix;
 use rustfs_utils::path::decode_dir_object;
 use time::OffsetDateTime;
 
@@ -137,37 +138,140 @@ pub(super) fn rebalance_disk_set_lookup_error(pool_idx: usize, set_idx: usize, p
     ))
 }
 
+fn latest_candidate_mod_time(candidate: &LatestObjectInfoCandidate) -> Option<OffsetDateTime> {
+    candidate
+        .info
+        .as_ref()
+        .map(|info| info.mod_time.unwrap_or(OffsetDateTime::UNIX_EPOCH))
+}
+
+fn same_transition_identity(left: &ObjectInfo, right: &ObjectInfo) -> bool {
+    left.transition_version_state == right.transition_version_state
+        && left.transitioned_object.name == right.transitioned_object.name
+        && left.transitioned_object.version_id == right.transitioned_object.version_id
+        && left.transitioned_object.tier == right.transitioned_object.tier
+        && left.transitioned_object.free_version == right.transitioned_object.free_version
+        && left.transitioned_object.status == right.transitioned_object.status
+}
+
+#[derive(PartialEq, Eq)]
+struct LatestUserDefinedIdentity {
+    internal: HashMap<String, String>,
+    other: HashMap<String, String>,
+}
+
+fn normalize_user_defined_identity(user_defined: &HashMap<String, String>) -> Option<LatestUserDefinedIdentity> {
+    let mut identity = LatestUserDefinedIdentity {
+        internal: HashMap::with_capacity(user_defined.len()),
+        other: HashMap::with_capacity(user_defined.len()),
+    };
+
+    for (key, value) in user_defined {
+        if let Some(suffix) = strip_internal_prefix(key) {
+            if identity
+                .internal
+                .insert(suffix, value.clone())
+                .is_some_and(|previous| previous != *value)
+            {
+                return None;
+            }
+        } else {
+            identity.other.insert(key.clone(), value.clone());
+        }
+    }
+
+    Some(identity)
+}
+
+fn same_user_defined_identity(left: &ObjectInfo, right: &ObjectInfo) -> bool {
+    match (
+        normalize_user_defined_identity(&left.user_defined),
+        normalize_user_defined_identity(&right.user_defined),
+    ) {
+        (Some(left), Some(right)) => left == right,
+        _ => false,
+    }
+}
+
+/// Pool-specific erasure geometry is intentionally excluded: `get_object_info`
+/// returns each pool's own `data_blocks`/`parity_blocks`, so those values can
+/// differ for the same object version while the selected winner still carries
+/// the chosen pool's layout. `put_object_reader` is also intentionally
+/// excluded because it is a transient request handle that `ObjectInfo::clone`
+/// drops. Every other ObjectInfo field is part of the production-visible
+/// identity and must agree before the pool index can provide a deterministic
+/// tie-break.
+fn same_latest_object_info_identity(left: &ObjectInfo, right: &ObjectInfo) -> bool {
+    left.bucket == right.bucket
+        && left.name == right.name
+        && left.storage_class == right.storage_class
+        && left.mod_time == right.mod_time
+        && left.size == right.size
+        && left.actual_size == right.actual_size
+        && left.is_dir == right.is_dir
+        && same_user_defined_identity(left, right)
+        && left.user_tags == right.user_tags
+        && left.version_id == right.version_id
+        && left.data_dir == right.data_dir
+        && left.delete_marker == right.delete_marker
+        && same_transition_identity(left, right)
+        && left.restore_ongoing == right.restore_ongoing
+        && left.restore_expires == right.restore_expires
+        && left.parts == right.parts
+        && left.is_latest == right.is_latest
+        && left.content_type == right.content_type
+        && left.content_encoding == right.content_encoding
+        && left.expires == right.expires
+        && left.num_versions == right.num_versions
+        && left.successor_mod_time == right.successor_mod_time
+        && left.etag == right.etag
+        && left.inlined == right.inlined
+        && left.metadata_only == right.metadata_only
+        && left.version_only == right.version_only
+        && left.replication_status_internal == right.replication_status_internal
+        && left.replication_status == right.replication_status
+        && left.version_purge_status_internal == right.version_purge_status_internal
+        && left.version_purge_status == right.version_purge_status
+        && left.replication_decision == right.replication_decision
+        && left.checksum == right.checksum
+}
+
 pub(super) fn resolve_latest_object_info_candidates(
-    mut candidates: Vec<LatestObjectInfoCandidate>,
+    candidates: Vec<LatestObjectInfoCandidate>,
     bucket: &str,
     object: &str,
     opts: &ObjectOptions,
 ) -> Result<(ObjectInfo, usize)> {
-    candidates.sort_by(|a, b| {
-        let a_mod = if let Some(info) = &a.info {
-            info.mod_time.unwrap_or(OffsetDateTime::UNIX_EPOCH)
-        } else {
-            OffsetDateTime::UNIX_EPOCH
+    let latest_mod_time = candidates.iter().filter_map(latest_candidate_mod_time).max();
+
+    if let Some(latest_mod_time) = latest_mod_time {
+        let mut latest_candidates = candidates
+            .into_iter()
+            .filter(|candidate| latest_candidate_mod_time(candidate) == Some(latest_mod_time))
+            .collect::<Vec<_>>();
+
+        latest_candidates.sort_by(|left, right| right.idx.cmp(&left.idx));
+
+        let Some(winner) = latest_candidates.first() else {
+            return Err(Error::ErasureReadQuorum);
+        };
+        let Some(winner_info) = winner.info.as_ref() else {
+            return Err(Error::ErasureReadQuorum);
         };
 
-        let b_mod = if let Some(info) = &b.info {
-            info.mod_time.unwrap_or(OffsetDateTime::UNIX_EPOCH)
-        } else {
-            OffsetDateTime::UNIX_EPOCH
-        };
-
-        if a_mod == b_mod {
-            return if a.idx < b.idx { Ordering::Greater } else { Ordering::Less };
+        if latest_candidates.iter().skip(1).any(|candidate| {
+            candidate
+                .info
+                .as_ref()
+                .is_none_or(|info| !same_latest_object_info_identity(winner_info, info))
+        }) {
+            return Err(Error::ErasureReadQuorum);
         }
 
-        b_mod.cmp(&a_mod)
-    });
+        return Ok((winner_info.clone(), winner.idx));
+    }
 
     for candidate in candidates {
-        if let Some(info) = candidate.info {
-            return Ok((info, candidate.idx));
-        }
-
         if let Some(err) = candidate.err
             && !is_err_object_not_found(&err)
             && !is_err_version_not_found(&err)

crates/heal/src/heal/channel.rs

@@ -1640,6 +1640,60 @@ mod tests {
         assert_eq!(payload["items"].as_array().expect("items should be an array").len(), 0);
     }
 
+    #[tokio::test]
+    async fn test_process_query_request_reports_displaced_terminal_detail() {
+        let heal_manager = Arc::new(HealManager::new(
+            Arc::new(MockStorage),
+            Some(HealConfig {
+                queue_size: 1,
+                ..HealConfig::default()
+            }),
+        ));
+        let mut displaced = HealRequest::new(
+            HealType::Bucket {
+                bucket: "displaced-channel".to_string(),
+            },
+            HealOptions::default(),
+            HealPriority::Low,
+        );
+        displaced.id = "displaced-channel-task".to_string();
+        let displaced_id = displaced.id.clone();
+        heal_manager
+            .submit_heal_request(displaced)
+            .await
+            .expect("initial channel task should queue");
+        heal_manager
+            .submit_heal_request(HealRequest::new(
+                HealType::Bucket {
+                    bucket: "successor-channel".to_string(),
+                },
+                HealOptions::default(),
+                HealPriority::High,
+            ))
+            .await
+            .expect("successor channel task should displace the initial task");
+
+        let processor = HealChannelProcessor::new(heal_manager);
+        let (tx, rx) = oneshot::channel();
+        processor
+            .process_query_request("displaced-channel".to_string(), displaced_id, None, tx)
+            .await
+            .expect("displaced query should process");
+        let response = rx
+            .await
+            .expect("query response should be returned")
+            .expect("displaced query should remain successful");
+        let payload: serde_json::Value = serde_json::from_slice(response.data.as_deref().expect("status payload should exist"))
+            .expect("status payload should be json");
+        assert_eq!(payload["summary"], "stopped");
+        assert!(
+            response
+                .error
+                .as_deref()
+                .is_some_and(|detail| detail.contains("reason=displaced"))
+        );
+    }
+
     #[tokio::test]
     async fn test_process_query_request_reports_running_for_queued_task() {
         let heal_manager = create_test_heal_manager();

crates/heal/src/heal/manager.rs

@@ -40,6 +40,7 @@ use tracing::{debug, error, info, warn};
 use super::{DiskError, Endpoint, HealDiskExt as _, local_disk_map_read};
 
 const KEEP_HEAL_TASK_STATUS_DURATION: Duration = Duration::from_secs(10 * 60);
+const DISPLACED_HEAL_REASON: &str = "reason=displaced; retry_hint=submit_again";
 const LOG_COMPONENT_HEAL: &str = "heal";
 const LOG_SUBSYSTEM_DISK_SCANNER: &str = "disk_scanner";
 const LOG_SUBSYSTEM_MANAGER: &str = "manager";
@@ -120,26 +121,30 @@ struct MrfRepairNoticeTarget {
     version_id: Option<[u8; 16]>,
 }
 
-#[derive(Debug, Clone, PartialEq, Eq)]
+#[derive(Debug, Clone)]
 struct HealAdmissionDecision {
     result: HealAdmissionResult,
-    displaced_task_id: Option<String>,
+    displaced_request: Option<HealRequest>,
 }
 
 impl HealAdmissionDecision {
     const fn new(result: HealAdmissionResult) -> Self {
         Self {
             result,
-            displaced_task_id: None,
+            displaced_request: None,
         }
     }
 
-    fn accepted_with_displacement(displaced_task_id: String) -> Self {
+    fn accepted_with_displacement(displaced_request: HealRequest) -> Self {
         Self {
             result: HealAdmissionResult::Accepted,
-            displaced_task_id: Some(displaced_task_id),
+            displaced_request: Some(displaced_request),
         }
     }
+
+    fn displaced_task_id(&self) -> Option<&str> {
+        self.displaced_request.as_ref().map(|request| request.id.as_str())
+    }
 }
 
 fn lock_mrf_repair_notice_targets(
@@ -151,6 +156,55 @@ fn lock_mrf_repair_notice_targets(
     }
 }
 
+fn lock_displaced_terminals(
+    registry: &StdMutex<HashMap<String, Arc<CompletedHealStatus>>>,
+) -> StdMutexGuard<'_, HashMap<String, Arc<CompletedHealStatus>>> {
+    match registry.lock() {
+        Ok(guard) => guard,
+        Err(poisoned) => poisoned.into_inner(),
+    }
+}
+
+fn record_displaced_terminal(
+    registry: &StdMutex<HashMap<String, Arc<CompletedHealStatus>>>,
+    request: &HealRequest,
+) -> Arc<CompletedHealStatus> {
+    let terminal = Arc::new(CompletedHealStatus {
+        heal_type: request.heal_type.clone(),
+        status: HealTaskStatus::Failed {
+            error: format!("heal task displaced by a higher-priority request ({DISPLACED_HEAL_REASON})"),
+        },
+        result_items_truncated: false,
+        completed_at: SystemTime::now(),
+        seqed_items: Vec::new(),
+        next_seq: 0,
+        min_seq: 0,
+    });
+    let mut terminals = lock_displaced_terminals(registry);
+    prune_completed_heal_statuses(&mut terminals);
+    terminals.insert(request.id.clone(), Arc::clone(&terminal));
+    terminal
+}
+
+async fn remove_displaced_task_aliases(
+    aliases: &Arc<Mutex<HashMap<String, HealTaskAlias>>>,
+    terminals: &StdMutex<HashMap<String, Arc<CompletedHealStatus>>>,
+    task_id: &str,
+    terminal: &Arc<CompletedHealStatus>,
+) {
+    let mut aliases = aliases.lock().await;
+    let alias_ids = aliases
+        .iter()
+        .filter_map(|(alias_id, alias)| (alias.task_id == task_id).then_some(alias_id.clone()))
+        .collect::<Vec<_>>();
+    let mut displaced_terminals = lock_displaced_terminals(terminals);
+    prune_completed_heal_statuses(&mut displaced_terminals);
+    for alias_id in alias_ids {
+        displaced_terminals.insert(alias_id, Arc::clone(terminal));
+    }
+    aliases.retain(|alias_id, alias| alias_id != task_id && alias.task_id != task_id);
+}
+
 async fn remove_task_aliases_for_task(registry: &Arc<Mutex<HashMap<String, HealTaskAlias>>>, task_id: &str) {
     registry
         .lock()
@@ -618,6 +672,14 @@ pub struct HealManager {
     /// are shared so the lookup helper can hand a completed entry to a
     /// caller without cloning the retained result window.
     completed_heals: Arc<Mutex<HashMap<String, Arc<CompletedHealStatus>>>>,
+    /// Terminals for requests removed by priority displacement. An Accepted
+    /// task ID remains queryable for the same process lifetime and the normal
+    /// ten-minute status TTL; clients should treat `reason=displaced` as a
+    /// terminal result and submit a fresh request. This sidecar is synchronous
+    /// so admission can publish the terminal while the queue transition is
+    /// still under its lock, without awaiting another tokio lock. Queue state
+    /// is process-local, so this guarantee does not extend across restart.
+    displaced_terminals: Arc<StdMutex<HashMap<String, Arc<CompletedHealStatus>>>>,
     /// Client tokens merged into an existing task id.
     task_aliases: Arc<Mutex<HashMap<String, HealTaskAlias>>>,
     /// Heal tasks waiting for a retry backoff to expire.
@@ -659,6 +721,7 @@ struct HealQueueContext<'a> {
     heal_queue: &'a Arc<Mutex<PriorityHealQueue>>,
     active_heals: &'a Arc<Mutex<HashMap<String, Arc<HealTask>>>>,
     completed_heals: &'a Arc<Mutex<HashMap<String, Arc<CompletedHealStatus>>>>,
+    displaced_terminals: &'a Arc<StdMutex<HashMap<String, Arc<CompletedHealStatus>>>>,
     task_aliases: &'a Arc<Mutex<HashMap<String, HealTaskAlias>>>,
     retrying_heals: &'a Arc<Mutex<HashMap<String, RetryingHeal>>>,
     mrf_repair_notice_targets: &'a Arc<StdMutex<HashMap<String, Vec<MrfRepairNoticeTarget>>>>,
@@ -874,7 +937,7 @@ impl HealManager {
                         result = "accepted_by_displacement",
                         "Heal queue request accepted by displacement"
                     });
-                    return HealAdmissionDecision::accepted_with_displacement(displaced.id);
+                    return HealAdmissionDecision::accepted_with_displacement(displaced);
                 }
 
                 demote_to_debug_when!(per_object_request, warn, target: "rustfs::heal::manager", {
@@ -1105,6 +1168,7 @@ impl HealManager {
             active_heals: Arc::new(Mutex::new(HashMap::new())),
             heal_queue: Arc::new(Mutex::new(PriorityHealQueue::new())),
             completed_heals: Arc::new(Mutex::new(HashMap::new())),
+            displaced_terminals: Arc::new(StdMutex::new(HashMap::new())),
             task_aliases: Arc::new(Mutex::new(HashMap::new())),
             retrying_heals: Arc::new(Mutex::new(HashMap::new())),
             mrf_repair_notice_targets: Arc::new(StdMutex::new(HashMap::new())),
@@ -1209,6 +1273,10 @@ impl HealManager {
         active_heals.clear();
         publish_active_heal_count(&active_heals);
         self.completed_heals.lock().await.clear();
+        // Do not let the synchronous guard live across the following async lock.
+        {
+            lock_displaced_terminals(&self.displaced_terminals).clear();
+        }
         self.task_aliases.lock().await.clear();
         self.retrying_heals.lock().await.clear();
         lock_mrf_repair_notice_targets(&self.mrf_repair_notice_targets).clear();
@@ -1459,7 +1527,11 @@ impl HealManager {
             task_id = queued_id.to_owned();
         }
         let should_notify = matches!(admission, HealAdmissionResult::Accepted) && config.event_driven_scheduler_enable;
-        let displaced_task_id = admission_decision.displaced_task_id;
+        let displaced_task_id = admission_decision.displaced_task_id().map(ToOwned::to_owned);
+        let displaced_terminal = admission_decision
+            .displaced_request
+            .as_ref()
+            .map(|request| record_displaced_terminal(&self.displaced_terminals, request));
         if matches!(admission, HealAdmissionResult::Accepted | HealAdmissionResult::Merged)
             && let Some(target) = mrf_notice_target
         {
@@ -1473,8 +1545,12 @@ impl HealManager {
         drop(queue);
         drop(active_heals);
 
-        if let Some(displaced_task_id) = displaced_task_id {
-            self.remove_aliases_for_task(&displaced_task_id).await;
+        if let (Some(displaced_task_id), Some(displaced_terminal)) = (displaced_task_id, displaced_terminal) {
+            // The queue has already removed the displaced request, so the
+            // synchronous terminal sidecar was published before aliases and
+            // MRF ownership are cleaned up.
+            remove_displaced_task_aliases(&self.task_aliases, &self.displaced_terminals, &displaced_task_id, &displaced_terminal)
+                .await;
         }
 
         if should_notify {
@@ -1549,6 +1625,15 @@ impl HealManager {
             }
         }
 
+        if terminal_completed.is_none() {
+            let mut displaced_terminals = lock_displaced_terminals(&self.displaced_terminals);
+            prune_completed_heal_statuses(&mut displaced_terminals);
+            terminal_completed = displaced_terminals
+                .get(canonical_task_id)
+                .filter(|terminal| matches_path(&terminal.heal_type))
+                .cloned();
+        }
+
         match terminal_completed {
             Some(completed) => TaskStateLookup::Completed(completed),
             None => TaskStateLookup::NotFound,
@@ -1669,9 +1754,19 @@ impl HealManager {
 
         let mut completed_heals = self.completed_heals.lock().await;
         prune_completed_heal_statuses(&mut completed_heals);
-        completed_heals
+        if completed_heals
             .values()
             .any(|completed| heal_type_matches_path(&completed.heal_type, heal_path))
+        {
+            return true;
+        }
+        drop(completed_heals);
+
+        let mut displaced_terminals = lock_displaced_terminals(&self.displaced_terminals);
+        prune_completed_heal_statuses(&mut displaced_terminals);
+        displaced_terminals
+            .values()
+            .any(|terminal| heal_type_matches_path(&terminal.heal_type, heal_path))
     }
 
     /// Get task progress

crates/heal/src/heal/manager/auto_scan.rs

@@ -21,6 +21,7 @@ impl HealManager {
         let heal_queue = self.heal_queue.clone();
         let active_heals = self.active_heals.clone();
         let task_aliases = self.task_aliases.clone();
+        let displaced_terminals = self.displaced_terminals.clone();
         let mrf_repair_notice_targets = self.mrf_repair_notice_targets.clone();
         let storage = self.storage.clone();
         let replacement_recovery_anchors = self.replacement_recovery_anchors.clone();
@@ -481,6 +482,10 @@ impl HealManager {
                             let admission = admission_decision.result;
                             let should_notify =
                                 matches!(admission, HealAdmissionResult::Accepted) && config.event_driven_scheduler_enable;
+                            let displaced_terminal = admission_decision
+                                .displaced_request
+                                .as_ref()
+                                .map(|request| record_displaced_terminal(&displaced_terminals, request));
                             if matches!(admission, HealAdmissionResult::Accepted)
                                 && let Some(anchor) = recovery_anchor
                             {
@@ -491,8 +496,16 @@ impl HealManager {
                             }
                             drop(queue);
                             drop(config);
-                            if let Some(displaced_task_id) = admission_decision.displaced_task_id {
-                                remove_task_aliases_for_task(&task_aliases, &displaced_task_id).await;
+                            if let (Some(displaced_task_id), Some(displaced_terminal)) =
+                                (admission_decision.displaced_task_id().map(ToOwned::to_owned), displaced_terminal)
+                            {
+                                remove_displaced_task_aliases(
+                                    &task_aliases,
+                                    &displaced_terminals,
+                                    &displaced_task_id,
+                                    &displaced_terminal,
+                                )
+                                .await;
                                 lock_mrf_repair_notice_targets(&mrf_repair_notice_targets).remove(&displaced_task_id);
                             }
                             if matches!(admission, HealAdmissionResult::Accepted) {

crates/heal/src/heal/manager/scheduler.rs

@@ -21,6 +21,7 @@ impl HealManager {
         let heal_queue = self.heal_queue.clone();
         let active_heals = self.active_heals.clone();
         let completed_heals = self.completed_heals.clone();
+        let displaced_terminals = self.displaced_terminals.clone();
         let task_aliases = self.task_aliases.clone();
         let retrying_heals = self.retrying_heals.clone();
         let mrf_repair_notice_targets = self.mrf_repair_notice_targets.clone();
@@ -53,6 +54,7 @@ impl HealManager {
                             heal_queue: &heal_queue,
                             active_heals: &active_heals,
                             completed_heals: &completed_heals,
+                            displaced_terminals: &displaced_terminals,
                             task_aliases: &task_aliases,
                             retrying_heals: &retrying_heals,
                             mrf_repair_notice_targets: &mrf_repair_notice_targets,
@@ -71,6 +73,7 @@ impl HealManager {
                             heal_queue: &heal_queue,
                             active_heals: &active_heals,
                             completed_heals: &completed_heals,
+                            displaced_terminals: &displaced_terminals,
                             task_aliases: &task_aliases,
                             retrying_heals: &retrying_heals,
                             mrf_repair_notice_targets: &mrf_repair_notice_targets,
@@ -98,6 +101,7 @@ impl HealManager {
             heal_queue,
             active_heals,
             completed_heals,
+            displaced_terminals,
             task_aliases,
             retrying_heals,
             mrf_repair_notice_targets,
@@ -183,6 +187,7 @@ impl HealManager {
                 let active_heals_clone = active_heals.clone();
                 let heal_queue_clone = heal_queue.clone();
                 let completed_heals_clone = completed_heals.clone();
+                let displaced_terminals_clone = displaced_terminals.clone();
                 let task_aliases_clone = task_aliases.clone();
                 let retrying_heals_clone = retrying_heals.clone();
                 let mrf_repair_notice_targets_clone = mrf_repair_notice_targets.clone();
@@ -363,6 +368,7 @@ impl HealManager {
                         let retry_heal_queue = heal_queue_clone.clone();
                         let retrying_heals_for_spawn = retrying_heals_clone.clone();
                         let retry_task_aliases = task_aliases_clone.clone();
+                        let retry_displaced_terminals = displaced_terminals_clone.clone();
                         let retry_mrf_repair_notice_targets = mrf_repair_notice_targets_clone.clone();
                         let retry_completed_heals = completed_heals_clone.clone();
                         let retry_notify = notify_clone.clone();
@@ -430,6 +436,14 @@ impl HealManager {
                                 let admission = admission_decision.result;
                                 let should_notify = matches!(admission, HealAdmissionResult::Accepted)
                                     && retry_config.event_driven_scheduler_enable;
+                                // Publish the terminal synchronously while the
+                                // queue transition is protected. The subsequent
+                                // queue -> retrying handoff retains the lock order
+                                // used by operations_snapshot.
+                                let displaced_terminal = admission_decision
+                                    .displaced_request
+                                    .as_ref()
+                                    .map(|request| record_displaced_terminal(&retry_displaced_terminals, request));
                                 match admission {
                                     HealAdmissionResult::Accepted => {
                                         // Transfer ownership while holding queue -> retrying,
@@ -437,10 +451,18 @@ impl HealManager {
                                         #[cfg(test)]
                                         pause_retry_ownership_transition(&retry_request_id, true).await;
                                         retrying_heals_for_spawn.lock().await.remove(&retry_request_id);
-                                        let displaced_task_id = admission_decision.displaced_task_id;
+                                        let displaced_task_id = admission_decision.displaced_task_id().map(ToOwned::to_owned);
                                         drop(queue);
-                                        if let Some(displaced_task_id) = displaced_task_id {
-                                            remove_task_aliases_for_task(&retry_task_aliases, &displaced_task_id).await;
+                                        if let (Some(displaced_task_id), Some(displaced_terminal)) =
+                                            (displaced_task_id, displaced_terminal)
+                                        {
+                                            remove_displaced_task_aliases(
+                                                &retry_task_aliases,
+                                                &retry_displaced_terminals,
+                                                &displaced_task_id,
+                                                &displaced_terminal,
+                                            )
+                                            .await;
                                             remove_mrf_repair_notice_targets(
                                                 &retry_mrf_repair_notice_targets,
                                                 &displaced_task_id,

crates/heal/src/heal/manager/tests.rs

@@ -84,6 +84,7 @@ async fn process_manager_queue_once(manager: &HealManager) {
         heal_queue: &manager.heal_queue,
         active_heals: &manager.active_heals,
         completed_heals: &manager.completed_heals,
+        displaced_terminals: &manager.displaced_terminals,
         task_aliases: &manager.task_aliases,
         retrying_heals: &manager.retrying_heals,
         mrf_repair_notice_targets: &manager.mrf_repair_notice_targets,
@@ -2778,7 +2779,10 @@ async fn test_high_priority_request_displaces_lower_priority_when_queue_full() {
         HealAdmissionResult::Accepted
     );
     assert_eq!(manager.get_queue_length().await, 1);
-    assert!(matches!(manager.get_task_status(&low_id).await, Err(Error::TaskNotFound { .. })));
+    assert!(matches!(
+        manager.get_task_status(&low_id).await,
+        Ok(HealTaskStatus::Failed { error }) if error.contains("reason=displaced")
+    ));
     assert_eq!(
         manager
             .get_task_status(&high_id)
@@ -2788,6 +2792,263 @@ async fn test_high_priority_request_displaces_lower_priority_when_queue_full() {
     );
 }
 
+#[tokio::test]
+async fn displaced_task_remains_queryable() {
+    let manager = HealManager::new(
+        Arc::new(MockStorage),
+        Some(HealConfig {
+            queue_size: 1,
+            ..HealConfig::default()
+        }),
+    );
+    let mut displaced = HealRequest::new(
+        HealType::Bucket {
+            bucket: "displaced-bucket".to_string(),
+        },
+        HealOptions::default(),
+        HealPriority::Low,
+    );
+    displaced.id = "displaced-task".to_string();
+    let displaced_id = displaced.id.clone();
+    manager
+        .submit_heal_request(displaced)
+        .await
+        .expect("displaced request should queue");
+
+    let successor = HealRequest::new(
+        HealType::Bucket {
+            bucket: "successor-bucket".to_string(),
+        },
+        HealOptions::default(),
+        HealPriority::High,
+    );
+    manager
+        .submit_heal_request(successor)
+        .await
+        .expect("successor should displace low work");
+
+    let report = manager
+        .get_task_report(&displaced_id)
+        .await
+        .expect("displaced report should remain queryable");
+    assert!(matches!(report.status, HealTaskStatus::Failed { ref error } if error.contains("reason=displaced")));
+}
+
+#[tokio::test]
+async fn displaced_archive_failure_keeps_queryable_terminal() {
+    let manager = HealManager::new(Arc::new(MockStorage), None);
+    let mut request = HealRequest::new(
+        HealType::Bucket {
+            bucket: "archive-failure".to_string(),
+        },
+        HealOptions::default(),
+        HealPriority::Low,
+    );
+    request.id = "archive-failure-task".to_string();
+    let request_id = request.id.clone();
+    // The synchronous sidecar is the authoritative fallback when the normal
+    // completed-task archive has no entry (the failure window that must not
+    // turn an Accepted ID into NotFound).
+    record_displaced_terminal(&manager.displaced_terminals, &request);
+    assert!(manager.completed_heals.lock().await.is_empty());
+    assert!(matches!(
+        manager.get_task_status(&request_id).await,
+        Ok(HealTaskStatus::Failed { error }) if error.contains("reason=displaced")
+    ));
+}
+
+#[tokio::test]
+async fn scheduler_retry_displacement_keeps_evicted_task_queryable() {
+    let manager = Arc::new(HealManager::new(
+        Arc::new(MockStorage),
+        Some(HealConfig {
+            queue_size: 1,
+            event_driven_scheduler_enable: false,
+            ..HealConfig::default()
+        }),
+    ));
+    let mut retry_request = HealRequest::object("retry-transition".to_string(), "object".to_string(), None);
+    retry_request.priority = HealPriority::High;
+    let retry_id = retry_request.id.clone();
+    manager
+        .submit_heal_request(retry_request)
+        .await
+        .expect("retry request should queue");
+
+    // Process exactly one queue cycle so the retry task is spawned without a
+    // background scheduler consuming the filler request before the retry wakes.
+    process_manager_queue_once(&manager).await;
+    tokio::time::timeout(Duration::from_secs(1), async {
+        loop {
+            if manager.retrying_heals.lock().await.contains_key(&retry_id) {
+                break;
+            }
+            tokio::task::yield_now().await;
+        }
+    })
+    .await
+    .expect("retry request should enter backoff");
+
+    let filler = HealRequest::new(
+        HealType::Bucket {
+            bucket: "retry-displaced-filler".to_string(),
+        },
+        HealOptions::default(),
+        HealPriority::Low,
+    );
+    let filler_id = filler.id.clone();
+    manager
+        .submit_heal_request(filler)
+        .await
+        .expect("filler request should occupy the queue");
+
+    tokio::time::timeout(Duration::from_secs(5), async {
+        loop {
+            if matches!(
+                manager.get_task_status(&filler_id).await,
+                Ok(HealTaskStatus::Failed { ref error }) if error.contains("reason=displaced")
+            ) {
+                break;
+            }
+            tokio::time::sleep(Duration::from_millis(10)).await;
+        }
+    })
+    .await
+    .expect("retry admission should displace the filler request");
+    assert_eq!(manager.get_queue_length().await, 1);
+    assert_eq!(
+        manager.get_task_status(&retry_id).await.expect("retry should be queued"),
+        HealTaskStatus::Pending
+    );
+}
+
+#[tokio::test]
+async fn concurrent_displacers_produce_one_terminal_generation() {
+    let manager = Arc::new(HealManager::new(
+        Arc::new(MockStorage),
+        Some(HealConfig {
+            queue_size: 1,
+            ..HealConfig::default()
+        }),
+    ));
+    let mut displaced = HealRequest::new(
+        HealType::Bucket {
+            bucket: "concurrent-displaced".to_string(),
+        },
+        HealOptions::default(),
+        HealPriority::Low,
+    );
+    displaced.id = "concurrent-displaced-task".to_string();
+    let displaced_id = displaced.id.clone();
+    manager
+        .submit_heal_request(displaced)
+        .await
+        .expect("initial request should queue");
+
+    let first = HealRequest::new(
+        HealType::Bucket {
+            bucket: "concurrent-successor-a".to_string(),
+        },
+        HealOptions::default(),
+        HealPriority::High,
+    );
+    let second = HealRequest::new(
+        HealType::Bucket {
+            bucket: "concurrent-successor-b".to_string(),
+        },
+        HealOptions::default(),
+        HealPriority::High,
+    );
+    let (first_result, second_result) = tokio::join!(manager.submit_heal_request(first), manager.submit_heal_request(second));
+    let accepted = [&first_result, &second_result]
+        .into_iter()
+        .filter(|result| matches!(result, Ok(HealAdmissionResult::Accepted)))
+        .count();
+    assert_eq!(accepted, 1, "exactly one concurrent displacer should win the full queue");
+    assert!(
+        first_result.is_ok() && second_result.is_ok(),
+        "the losing request should receive a typed Full result"
+    );
+    let terminals = lock_displaced_terminals(&manager.displaced_terminals);
+    assert_eq!(terminals.len(), 1);
+    assert!(terminals.contains_key(&displaced_id));
+}
+
+#[tokio::test]
+async fn successor_chain_is_bounded_and_authorized() {
+    let manager = HealManager::new(
+        Arc::new(MockStorage),
+        Some(HealConfig {
+            queue_size: 1,
+            ..HealConfig::default()
+        }),
+    );
+    let mut original = HealRequest::new(
+        HealType::Bucket {
+            bucket: "authorized-original".to_string(),
+        },
+        HealOptions::default(),
+        HealPriority::Low,
+    );
+    original.id = "authorized-original-task".to_string();
+    let original_id = original.id.clone();
+    manager.submit_heal_request(original).await.expect("original should queue");
+    let mut duplicate = HealRequest::new(
+        HealType::Bucket {
+            bucket: "authorized-original".to_string(),
+        },
+        HealOptions::default(),
+        HealPriority::Low,
+    );
+    duplicate.id = "authorized-duplicate-task".to_string();
+    let duplicate_id = duplicate.id.clone();
+    manager
+        .submit_heal_request(duplicate)
+        .await
+        .expect("same-target duplicate should merge");
+    let successor = HealRequest::new(
+        HealType::Bucket {
+            bucket: "authorized-successor".to_string(),
+        },
+        HealOptions::default(),
+        HealPriority::High,
+    );
+    let successor_id = successor.id.clone();
+    manager.submit_heal_request(successor).await.expect("successor should queue");
+    assert!(manager.task_aliases.lock().await.is_empty());
+    assert!(matches!(manager.get_task_status(&original_id).await, Ok(HealTaskStatus::Failed { .. })));
+    assert!(matches!(manager.get_task_status(&duplicate_id).await, Ok(HealTaskStatus::Failed { .. })));
+    assert_eq!(
+        manager
+            .get_task_status(&successor_id)
+            .await
+            .expect("successor should remain queued"),
+        HealTaskStatus::Pending
+    );
+}
+
+#[tokio::test]
+async fn displaced_terminal_expires_after_bounded_ttl() {
+    let manager = HealManager::new(Arc::new(MockStorage), None);
+    let mut request = HealRequest::new(
+        HealType::Bucket {
+            bucket: "expires".to_string(),
+        },
+        HealOptions::default(),
+        HealPriority::Low,
+    );
+    request.id = "expires-task".to_string();
+    let request_id = request.id.clone();
+    record_displaced_terminal(&manager.displaced_terminals, &request);
+    {
+        let mut terminals = lock_displaced_terminals(&manager.displaced_terminals);
+        let entry =
+            Arc::get_mut(terminals.get_mut(&request_id).expect("terminal should be retained")).expect("test owns terminal entry");
+        entry.completed_at = SystemTime::now() - KEEP_HEAL_TASK_STATUS_DURATION - Duration::from_secs(1);
+    }
+    assert!(matches!(manager.get_task_status(&request_id).await, Err(Error::TaskNotFound { .. })));
+}
+
 #[tokio::test]
 async fn test_displacing_registered_mrf_task_drops_notice_ownership() {
     let storage: Arc<dyn HealStorageAPI> = Arc::new(MockStorage);

crates/protos/src/lib.rs

@@ -2106,6 +2106,9 @@ pub enum ChannelClass {
     Bulk,
 }
 
+// Keep multiplexed unary RPCs below h2's per-connection small-frame budget.
+const INTERNODE_RPC_CONCURRENCY_LIMIT: usize = 64;
+
 /// Whether control/bulk channel isolation is enabled (env-gated, default off for safe rollout).
 fn channel_isolation_enabled() -> bool {
     rustfs_utils::get_env_bool(
@@ -2188,6 +2191,7 @@ async fn build_channel(dial_addr: &str, cache_key: &str) -> Result<Channel, Box<
     let mut connector = Endpoint::from_shared(dial_addr.to_string())?
         // Fast connection timeout for dead peer detection
         .connect_timeout(connect_timeout)
+        .concurrency_limit(INTERNODE_RPC_CONCURRENCY_LIMIT)
         // TCP-level keepalive - OS will probe connection
         .tcp_keepalive(Some(tcp_keepalive))
         // Disable Nagle so latency-sensitive control-plane RPCs (locks/health) are not batched

scripts/check_test_wiring.py

@@ -206,6 +206,13 @@ 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}")
@@ -272,6 +279,7 @@ 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
 
@@ -341,6 +349,23 @@ 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)
@@ -411,7 +436,7 @@ def main() -> int:
         for error in errors:
             print(f"ERROR: {error}", file=sys.stderr)
         return 1
-    print("OK: e2e modules, runner selection, fuzz matrices, and profile guards are wired")
+    print("OK: e2e modules, runner selection, fuzz matrices, profiles, and bounded diagnostics are wired")
     return 0
 
 

scripts/s3-tests/run.sh

@@ -1028,10 +1028,11 @@ 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="${CONF_OUTPUT_PATH}" \
     tox -- \
-    -vv -ra --showlocals --tb=long \
+    -vv -ra --tb=long \
     --maxfail="${MAXFAIL}" \
     --timeout="${TEST_TIMEOUT}" \
     --junitxml="${ARTIFACTS_DIR}/junit.xml" \