From 9a00591de62dd5da14ae8f4e1da090135ccf8cfb Mon Sep 17 00:00:00 2001
From: lihangyu <15605149486@163.com>
Date: Sun, 4 Feb 2024 21:58:06 +0800
Subject: [PATCH] [Improve](Tablet Schema) Use deterministic way to serialize
 protobuf (#101)

---
 be/src/olap/rowset/rowset_meta.cpp |  3 ++-
 be/src/olap/tablet_schema.cpp      | 17 +++++++++++++++--
 be/src/olap/tablet_schema.h        | 11 +++++++----
 3 files changed, 24 insertions(+), 7 deletions(-)

diff --git a/be/src/olap/rowset/rowset_meta.cpp b/be/src/olap/rowset/rowset_meta.cpp
index 78bc4b7fe622a1..125089a28626e9 100644
--- a/be/src/olap/rowset/rowset_meta.cpp
+++ b/be/src/olap/rowset/rowset_meta.cpp
@@ -133,7 +133,8 @@ void RowsetMeta::set_tablet_schema(const TabletSchemaPB& tablet_schema) {
     if (_handle) {
         TabletSchemaCache::instance()->release(_handle);
     }
-    auto pair = TabletSchemaCache::instance()->insert(tablet_schema.SerializeAsString());
+    auto pair = TabletSchemaCache::instance()->insert(
+            TabletSchema::deterministic_string_serialize(tablet_schema));
     _handle = pair.first;
     _schema = pair.second;
 }
diff --git a/be/src/olap/tablet_schema.cpp b/be/src/olap/tablet_schema.cpp
index bd54af19603ebe..e02833277ee48b 100644
--- a/be/src/olap/tablet_schema.cpp
+++ b/be/src/olap/tablet_schema.cpp
@@ -20,6 +20,9 @@
 #include <gen_cpp/Descriptors_types.h>
 #include <gen_cpp/olap_file.pb.h>
 #include <glog/logging.h>
+#include <google/protobuf/io/coded_stream.h>
+#include <google/protobuf/io/zero_copy_stream.h>
+#include <google/protobuf/io/zero_copy_stream_impl_lite.h>
 
 #include <algorithm>
 #include <cctype>
@@ -27,6 +30,7 @@
 #include <cmath> // IWYU pragma: keep
 #include <memory>
 #include <ostream>
+#include <vector>
 
 #include "common/compiler_util.h" // IWYU pragma: keep
 #include "common/consts.h"
@@ -770,7 +774,7 @@ void TabletIndex::to_schema_pb(TabletIndexPB* index) const {
         index->add_col_unique_id(col_unique_id);
     }
     index->set_index_type(_index_type);
-    for (auto& kv : _properties) {
+    for (const auto& kv : _properties) {
         (*index->mutable_properties())[kv.first] = kv.second;
     }
     index->set_index_suffix_name(_escaped_index_suffix_path);
@@ -929,7 +933,7 @@ void TabletSchema::copy_from(const TabletSchema& tablet_schema) {
 std::string TabletSchema::to_key() const {
     TabletSchemaPB pb;
     to_schema_pb(&pb);
-    return pb.SerializeAsString();
+    return TabletSchema::deterministic_string_serialize(pb);
 }
 
 void TabletSchema::build_current_tablet_schema(int64_t index_id, int32_t version,
@@ -1382,4 +1386,13 @@ bool operator!=(const TabletSchema& a, const TabletSchema& b) {
     return !(a == b);
 }
 
+std::string TabletSchema::deterministic_string_serialize(const TabletSchemaPB& schema_pb) {
+    std::string output;
+    google::protobuf::io::StringOutputStream string_output_stream(&output);
+    google::protobuf::io::CodedOutputStream output_stream(&string_output_stream);
+    output_stream.SetSerializationDeterministic(true);
+    schema_pb.SerializeToCodedStream(&output_stream);
+    return output;
+}
+
 } // namespace doris
diff --git a/be/src/olap/tablet_schema.h b/be/src/olap/tablet_schema.h
index a515095814ffe4..3ca4392584327d 100644
--- a/be/src/olap/tablet_schema.h
+++ b/be/src/olap/tablet_schema.h
@@ -240,6 +240,9 @@ class TabletSchema {
     // void create_from_pb(const TabletSchemaPB& schema, TabletSchema* tablet_schema).
     TabletSchema() = default;
     void init_from_pb(const TabletSchemaPB& schema, bool ignore_extracted_columns = false);
+    // Notice: Use deterministic way to serialize protobuf,
+    // since serialize Map in protobuf may could lead to un-deterministic by default
+    static std::string deterministic_string_serialize(const TabletSchemaPB& schema_pb);
     void to_schema_pb(TabletSchemaPB* tablet_meta_pb) const;
     void append_column(TabletColumn column, ColumnType col_type = ColumnType::NORMAL);
     void append_index(TabletIndex index);
@@ -363,17 +366,17 @@ class TabletSchema {
     // Dump [(name, type, is_nullable), ...]
     string dump_structure() const {
         string str = "[";
-        for (auto p : _field_name_to_index) {
+        for (auto p : _cols) {
             if (str.size() > 1) {
                 str += ", ";
             }
             str += "(";
-            str += p.first;
+            str += p.name();
             str += ", ";
-            str += TabletColumn::get_string_by_field_type(_cols[p.second].type());
+            str += TabletColumn::get_string_by_field_type(p.type());
             str += ", ";
             str += "is_nullable:";
-            str += (_cols[p.second].is_nullable() ? "true" : "false");
+            str += (p.is_nullable() ? "true" : "false");
             str += ")";
         }
         str += "]";