Merge pull request #40740 from amosbird/row-policy-index-fix-1

Use index when row_policy_filter is always false

src/Processors/QueryPlan/ReadFromMergeTree.cpp

@@ -865,6 +865,7 @@ MergeTreeDataSelectAnalysisResultPtr ReadFromMergeTree::selectRangesToRead(
 
     size_t total_parts = parts.size();
 
+    /// TODO Support row_policy_filter and additional_filters
     auto part_values = MergeTreeDataSelectExecutor::filterPartsByVirtualColumns(data, parts, query_info.query, context);
     if (part_values && part_values->empty())
         return std::make_shared<MergeTreeDataSelectAnalysisResult>(MergeTreeDataSelectAnalysisResult{.result = std::move(result)});
@@ -923,6 +924,9 @@ MergeTreeDataSelectAnalysisResultPtr ReadFromMergeTree::selectRangesToRead(
     }
     LOG_DEBUG(log, "Key condition: {}", key_condition->toString());
 
+    if (key_condition->alwaysFalse())
+        return std::make_shared<MergeTreeDataSelectAnalysisResult>(MergeTreeDataSelectAnalysisResult{.result = std::move(result)});
+
     const auto & select = query_info.query->as<ASTSelectQuery &>();
 
     size_t total_marks_pk = 0;

src/Storages/MergeTree/KeyCondition.cpp

@@ -2463,7 +2463,6 @@ BoolMask KeyCondition::checkInHyperrectangle(
     return rpn_stack[0];
 }
 
-
 bool KeyCondition::mayBeTrueInRange(
     size_t used_key_size,
     const FieldRef * left_keys,
@@ -2474,6 +2473,7 @@ bool KeyCondition::mayBeTrueInRange(
 }
 
 String KeyCondition::RPNElement::toString() const { return toString("column " + std::to_string(key_column), false); }
+
 String KeyCondition::RPNElement::toString(std::string_view column_name, bool print_constants) const
 {
     auto print_wrapped_column = [this, &column_name, print_constants](WriteBuffer & buf)
@@ -2563,10 +2563,12 @@ bool KeyCondition::alwaysUnknownOrTrue() const
 {
     return unknownOrAlwaysTrue(false);
 }
+
 bool KeyCondition::anyUnknownOrAlwaysTrue() const
 {
     return unknownOrAlwaysTrue(true);
 }
+
 bool KeyCondition::unknownOrAlwaysTrue(bool unknown_any) const
 {
     std::vector<UInt8> rpn_stack;
@@ -2627,6 +2629,80 @@ bool KeyCondition::unknownOrAlwaysTrue(bool unknown_any) const
     return rpn_stack[0];
 }
 
+bool KeyCondition::alwaysFalse() const
+{
+    /// 0: always_false, 1: always_true, 2: non_const
+    std::vector<UInt8> rpn_stack;
+
+    for (const auto & element : rpn)
+    {
+        if (element.function == RPNElement::ALWAYS_TRUE)
+        {
+            rpn_stack.push_back(1);
+        }
+        else if (element.function == RPNElement::ALWAYS_FALSE)
+        {
+            rpn_stack.push_back(0);
+        }
+        else if (element.function == RPNElement::FUNCTION_NOT_IN_RANGE
+            || element.function == RPNElement::FUNCTION_IN_RANGE
+            || element.function == RPNElement::FUNCTION_IN_SET
+            || element.function == RPNElement::FUNCTION_NOT_IN_SET
+            || element.function == RPNElement::FUNCTION_IS_NULL
+            || element.function == RPNElement::FUNCTION_IS_NOT_NULL
+            || element.function == RPNElement::FUNCTION_UNKNOWN)
+        {
+            rpn_stack.push_back(2);
+        }
+        else if (element.function == RPNElement::FUNCTION_NOT)
+        {
+            assert(!rpn_stack.empty());
+
+            auto & arg = rpn_stack.back();
+            if (arg == 0)
+                arg = 1;
+            else if (arg == 1)
+                arg = 0;
+        }
+        else if (element.function == RPNElement::FUNCTION_AND)
+        {
+            assert(!rpn_stack.empty());
+
+            auto arg1 = rpn_stack.back();
+            rpn_stack.pop_back();
+            auto arg2 = rpn_stack.back();
+
+            if (arg1 == 0 || arg2 == 0)
+                rpn_stack.back() = 0;
+            else if (arg1 == 1 && arg2 == 1)
+                rpn_stack.back() = 1;
+            else
+                rpn_stack.back() = 2;
+        }
+        else if (element.function == RPNElement::FUNCTION_OR)
+        {
+            assert(!rpn_stack.empty());
+
+            auto arg1 = rpn_stack.back();
+            rpn_stack.pop_back();
+            auto arg2 = rpn_stack.back();
+
+            if (arg1 == 1 || arg2 == 1)
+                rpn_stack.back() = 1;
+            else if (arg1 == 0 && arg2 == 0)
+                rpn_stack.back() = 0;
+            else
+                rpn_stack.back() = 2;
+        }
+        else
+            throw Exception("Unexpected function type in KeyCondition::RPNElement", ErrorCodes::LOGICAL_ERROR);
+    }
+
+    if (rpn_stack.size() != 1)
+        throw Exception("Unexpected stack size in KeyCondition::alwaysFalse", ErrorCodes::LOGICAL_ERROR);
+
+    return rpn_stack[0] == 0;
+}
 
 size_t KeyCondition::getMaxKeyColumn() const
 {

src/Storages/MergeTree/KeyCondition.h

@@ -279,6 +279,8 @@ public:
     /// Does not allow any FUNCTION_UNKNOWN (will instantly return true).
     bool anyUnknownOrAlwaysTrue() const;
 
+    bool alwaysFalse() const;
+
     /// Get the maximum number of the key element used in the condition.
     size_t getMaxKeyColumn() const;
 

tests/queries/0_stateless/02416_row_policy_always_false_index.sql

@@ -0,0 +1,17 @@
+drop table if exists tbl;
+
+create table tbl (s String, i int) engine MergeTree order by i;
+
+insert into tbl values ('123', 123);
+
+drop row policy if exists filter on tbl;
+
+create row policy filter on tbl using 0 to all;
+
+set max_rows_to_read = 0;
+
+select * from tbl;
+
+drop row policy filter on tbl;
+
+drop table tbl;