From 0a74629c481baf01f96921b0a55d75fa969c3537 Mon Sep 17 00:00:00 2001
From: houseme <housemecn@gmail.com>
Date: Fri, 5 Jun 2026 01:00:58 +0800
Subject: [PATCH] chore: add delete-objects lock batch diagnostics (#3218)

* chore(ecstore): add missing-shard first-scene diagnostics

Log rename_data quorum context behind RUSTFS_ISSUE3031_DIAG_ENABLE so partial-disk success can be correlated with later missing shard reads.

Also log put_object commit success and tmp cleanup boundaries to capture when successful quorum writes are followed by tmp_dir cleanup.

* chore(ecstore): add delete-objects lock batch diagnostics

Log DeleteObjects batch-lock request size, distributed lock quorum summary, and failed object keys behind RUSTFS_ISSUE3031_DIAG_ENABLE.

Include a Chinese operator checklist under docs/ that explains which logs to capture and how to interpret DeleteObjects lock_batch timeout incidents.

* chore: remove lock batch checklist from repo

Keep docs/issue-658-deleteobjects-lock-batch-checklist-zh.md only in the local checkout and drop it from the PR history.
---
 crates/ecstore/src/set_disk.rs | 46 ++++++++++++++++++++++++++++++++++
 1 file changed, 46 insertions(+)

diff --git a/crates/ecstore/src/set_disk.rs b/crates/ecstore/src/set_disk.rs
index e198554bb..382035e37 100644
--- a/crates/ecstore/src/set_disk.rs
+++ b/crates/ecstore/src/set_disk.rs
@@ -1375,6 +1375,33 @@ impl SetDisks {
             }
         }
 
+        if issue3031_diag_enabled() {
+            let succeeded_count = resolution_by_object
+                .iter()
+                .filter(|resolution| matches!(resolution, ObjectLockResolution::Succeeded))
+                .count();
+            let failed_count = resolution_by_object
+                .iter()
+                .filter(|resolution| matches!(resolution, ObjectLockResolution::Failed))
+                .count();
+            let pending_count = resolution_by_object
+                .iter()
+                .filter(|resolution| matches!(resolution, ObjectLockResolution::Pending))
+                .count();
+            warn!(
+                target: "rustfs_ecstore::set_disk",
+                request_count = requests.len(),
+                locker_count = self.lockers.len(),
+                write_quorum,
+                succeeded_count,
+                failed_count,
+                pending_count,
+                pending_clients,
+                errors_by_object = ?errors_by_object,
+                "issue3031_delete_objects_dist_batch_lock_summary"
+            );
+        }
+
         if !pending.is_empty() {
             let cleanup_requests = requests.clone();
             let lockers = self.lockers.clone();
@@ -1809,6 +1836,7 @@ impl ObjectOperations for SetDisks {
                 batch = batch.add_write_lock(ObjectKey::new(bucket, dobj.object_name.clone()));
             }
         }
+        let unique_lock_count = batch.requests.len();
 
         let mut failed_map = HashMap::new();
         let mut _local_batch_guards: Vec<FastLockGuard> = Vec::with_capacity(batch.requests.len());
@@ -1832,6 +1860,24 @@ impl ObjectOperations for SetDisks {
             }
         }
 
+        if issue3031_diag_enabled() {
+            let failed_lock_count = failed_map.len();
+            let locked_object_count = locked_objects.len();
+            let dist_lock_id_count = dist_batch_lock_ids.iter().map(Vec::len).sum::<usize>();
+            warn!(
+                target: "rustfs_ecstore::set_disk",
+                bucket = %bucket,
+                requested_object_count = objects.len(),
+                unique_lock_count,
+                locked_object_count,
+                failed_lock_count,
+                dist_erasure,
+                dist_lock_id_count,
+                failed_objects = ?failed_map.keys().collect::<Vec<_>>(),
+                "issue3031_delete_objects_lock_batch_context"
+            );
+        }
+
         // Mark failures for objects that could not be locked
         for (i, dobj) in objects.iter().enumerate() {
             if let Some(err) = failed_map.get(&(bucket.to_string(), dobj.object_name.clone())) {