mirror of
https://github.com/scylladb/scylladb.git
synced 2026-04-23 18:10:39 +00:00
1eb8d170dd
This series allows creating multiple vector indexes on the same column so users can rebuild an index without losing query availability. The intended flow is: 1. Create a new vector index on a column that already has one. 2. Keep serving ANN queries from the old index while the new one is being built. 3. Verify the new index is ready. 4. Automatically switch to the remaining index. 5. Drop the old index. To make that deterministic, `index_version` is changed from the base table schema version to a real creation timeuuid. When multiple vector indexes exist on the same column, ANN query planning now picks the index according to the routing implemented in Vector Store (newest serving index). This keeps queries on the old index until it the new one is up and ready. This patch also removes the create-time restriction that rejected a second vector index on the same column. Name collisions are still rejected as before. Test coverage is updated accordingly: - Scylla now verifies that two vector indexes can coexist on the same column. - Cassandra/SAI behavior is still covered and is still expected to reject duplicate indexes on the same column. Fixes: VECTOR-610 Closes scylladb/scylladb#29407 * github.com:scylladb/scylladb: docs: document vector index metadata and duplicate handling test/cqlpy: cover vector index duplicate creation rules vector_index: allow multiple named indexes on one column vector_index: store `index_version` as creation timeuuid
55 lines
2.3 KiB
C++
55 lines
2.3 KiB
C++
/*
|
|
* Copyright 2025-present ScyllaDB
|
|
*/
|
|
|
|
/*
|
|
* SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.1
|
|
*/
|
|
|
|
#pragma once
|
|
|
|
#include "schema/schema.hh"
|
|
|
|
#include "data_dictionary/data_dictionary.hh"
|
|
#include "cql3/statements/index_target.hh"
|
|
#include "index/secondary_index_manager.hh"
|
|
|
|
#include <vector>
|
|
|
|
namespace secondary_index {
|
|
|
|
class vector_index: public custom_index {
|
|
public:
|
|
// The minimal TTL for the CDC used by Vector Search.
|
|
// Required to ensure that the data is not deleted until the vector index is fully built.
|
|
static constexpr int VS_TTL_SECONDS = 86400; // 24 hours
|
|
|
|
vector_index() = default;
|
|
~vector_index() override = default;
|
|
std::optional<cql3::description> describe(const index_metadata& im, const schema& base_schema) const override;
|
|
bool view_should_exist() const override;
|
|
void validate(const schema &schema, const cql3::statements::index_specific_prop_defs &properties,
|
|
const std::vector<::shared_ptr<cql3::statements::index_target>> &targets, const gms::feature_service& fs,
|
|
const data_dictionary::database& db) const override;
|
|
utils::UUID index_version(const schema& schema) override;
|
|
static bool has_vector_index(const schema& s);
|
|
static bool has_vector_index_on_column(const schema& s, const sstring& target_name);
|
|
static bool is_vector_index_on_column(const index_metadata& im, const sstring& target_name);
|
|
static void check_cdc_options(const schema& schema);
|
|
|
|
static sstring serialize_targets(const std::vector<::shared_ptr<cql3::statements::index_target>>& targets);
|
|
static sstring get_target_column(const sstring& targets);
|
|
|
|
static bool is_rescoring_enabled(const index_options_map& properties);
|
|
static float get_oversampling(const index_options_map& properties);
|
|
static sstring get_cql_similarity_function_name(const index_options_map& properties);
|
|
private:
|
|
void check_uses_tablets(const schema& schema, const data_dictionary::database& db) const;
|
|
void check_cdc_not_explicitly_disabled(const schema& schema) const;
|
|
void check_target(const schema& schema, const std::vector<::shared_ptr<cql3::statements::index_target>>& targets) const;
|
|
void check_index_options(const cql3::statements::index_specific_prop_defs& properties) const;
|
|
};
|
|
|
|
std::unique_ptr<secondary_index::custom_index> vector_index_factory();
|
|
}
|