From f1b85d86f88fa3c0fe1e8cdd880dca5c1a69aaf3 Mon Sep 17 00:00:00 2001
From: Yukang-Lian <lianyukang@selectdb.com>
Date: Mon, 27 Jan 2025 22:34:58 +0800
Subject: [PATCH 1/3] 1

---
 cloud/src/recycler/recycler.cpp | 29 ++++++++++++++++-------------
 1 file changed, 16 insertions(+), 13 deletions(-)

diff --git a/cloud/src/recycler/recycler.cpp b/cloud/src/recycler/recycler.cpp
index 763c3e8065105a..ca7dd8a1a277bc 100644
--- a/cloud/src/recycler/recycler.cpp
+++ b/cloud/src/recycler/recycler.cpp
@@ -1521,25 +1521,28 @@ int InstanceRecycler::delete_rowset_data(const std::vector<doris::RowsetMetaClou
             InvertedIndexInfo index_info;
             int get_ret =
                     inverted_index_id_cache_->get(rs.index_id(), rs.schema_version(), index_info);
-            if (get_ret != 0) {
-                if (get_ret == 1) { // Schema kv not found
-                    // Check tablet existence
-                    std::string tablet_idx_key, tablet_idx_val;
-                    meta_tablet_idx_key({instance_id_, tablet_id}, &tablet_idx_key);
-                    if (txn_get(txn_kv_.get(), tablet_idx_key, tablet_idx_val) == 1) {
-                        // Tablet has been recycled, rowset data has already been deleted
-                        std::lock_guard lock(recycled_tablets_mtx_);
-                        recycled_tablets_.insert(tablet_id);
-                        continue;
-                    }
+            if (get_ret == 0) {
+                index_format = index_info.first;
+                index_ids = std::move(index_info.second);
+            } else if (get_ret == 1) {
+                // Schema kv not found means tablet has been recycled
+                // Maybe some tablet recycle failed by some bugs
+                // We need to delete again to double check
+                LOG_INFO(
+                        "delete rowset data schema kv not found, need to delete again to double "
+                        "check")
+                        .tag("instance_id", instance_id_)
+                        .tag("tablet_id", tablet_id)
+                        .tag("rowset", rs.ShortDebugString());
+                for (int64_t i = 0; i < num_segments; ++i) {
+                    file_paths.push_back(segment_path(tablet_id, rowset_id, i));
                 }
+            } else {
                 LOG(WARNING) << "failed to get schema kv for rowset, instance_id=" << instance_id_
                              << " tablet_id=" << tablet_id << " rowset_id=" << rowset_id;
                 ret = -1;
                 continue;
             }
-            index_format = index_info.first;
-            index_ids = std::move(index_info.second);
         }
         if (rs.rowset_state() == RowsetStatePB::BEGIN_PARTIAL_UPDATE) {
             // if rowset state is RowsetStatePB::BEGIN_PARTIAL_UPDATE, the number of segments data

From 51605aa7b7a51c33bee6dacf298c1ba65ac7e95f Mon Sep 17 00:00:00 2001
From: Yukang-Lian <lianyukang@selectdb.com>
Date: Mon, 27 Jan 2025 23:02:27 +0800
Subject: [PATCH 2/3] 2

---
 cloud/src/recycler/recycler.cpp | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/cloud/src/recycler/recycler.cpp b/cloud/src/recycler/recycler.cpp
index ca7dd8a1a277bc..85f6de82dfe397 100644
--- a/cloud/src/recycler/recycler.cpp
+++ b/cloud/src/recycler/recycler.cpp
@@ -1523,7 +1523,7 @@ int InstanceRecycler::delete_rowset_data(const std::vector<doris::RowsetMetaClou
                     inverted_index_id_cache_->get(rs.index_id(), rs.schema_version(), index_info);
             if (get_ret == 0) {
                 index_format = index_info.first;
-                index_ids = std::move(index_info.second);
+                index_ids = index_info.second;
             } else if (get_ret == 1) {
                 // Schema kv not found means tablet has been recycled
                 // Maybe some tablet recycle failed by some bugs
@@ -1534,9 +1534,11 @@ int InstanceRecycler::delete_rowset_data(const std::vector<doris::RowsetMetaClou
                         .tag("instance_id", instance_id_)
                         .tag("tablet_id", tablet_id)
                         .tag("rowset", rs.ShortDebugString());
-                for (int64_t i = 0; i < num_segments; ++i) {
-                    file_paths.push_back(segment_path(tablet_id, rowset_id, i));
-                }
+                // Ensure this operation only deletes tablets and does not perform any operations on indexes,
+                // because we are uncertain about the inverted index information.
+                // If there are inverted indexes, some data might not be deleted,
+                // but this is acceptable as we have made our best effort to delete the data.
+                index_ids.clear();
             } else {
                 LOG(WARNING) << "failed to get schema kv for rowset, instance_id=" << instance_id_
                              << " tablet_id=" << tablet_id << " rowset_id=" << rowset_id;

From 5568bc464cd98fa92b229eec9fe27af9fc4b6ba9 Mon Sep 17 00:00:00 2001
From: Yukang-Lian <lianyukang@selectdb.com>
Date: Mon, 27 Jan 2025 23:15:53 +0800
Subject: [PATCH 3/3] 3

---
 cloud/src/recycler/recycler.cpp | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/cloud/src/recycler/recycler.cpp b/cloud/src/recycler/recycler.cpp
index 85f6de82dfe397..c7c9d8e0a02fe4 100644
--- a/cloud/src/recycler/recycler.cpp
+++ b/cloud/src/recycler/recycler.cpp
@@ -1525,19 +1525,22 @@ int InstanceRecycler::delete_rowset_data(const std::vector<doris::RowsetMetaClou
                 index_format = index_info.first;
                 index_ids = index_info.second;
             } else if (get_ret == 1) {
-                // Schema kv not found means tablet has been recycled
+                // 1. Schema kv not found means tablet has been recycled
                 // Maybe some tablet recycle failed by some bugs
                 // We need to delete again to double check
+                // 2. Ensure this operation only deletes tablets and does not perform any operations on indexes,
+                // because we are uncertain about the inverted index information.
+                // If there are inverted indexes, some data might not be deleted,
+                // but this is acceptable as we have made our best effort to delete the data.
                 LOG_INFO(
                         "delete rowset data schema kv not found, need to delete again to double "
                         "check")
                         .tag("instance_id", instance_id_)
                         .tag("tablet_id", tablet_id)
                         .tag("rowset", rs.ShortDebugString());
-                // Ensure this operation only deletes tablets and does not perform any operations on indexes,
-                // because we are uncertain about the inverted index information.
-                // If there are inverted indexes, some data might not be deleted,
-                // but this is acceptable as we have made our best effort to delete the data.
+                // Currently index_ids is guaranteed to be empty,
+                // but we clear it again here as a safeguard against future code changes
+                // that might cause index_ids to no longer be empty
                 index_ids.clear();
             } else {
                 LOG(WARNING) << "failed to get schema kv for rowset, instance_id=" << instance_id_