在postgreSQL中启用查询缓存以提高性能

Question

我的应用程序是数据库密集型的,所以我试图减少数据库的负载.我使用PostgreSQLrdbms和python是编程语言.为了减少负载,我已经在应用程序中使用了缓存机制.我使用的缓存类型是服务器缓存,浏览器缓存.目前我正在调整PostgreSQL查询缓存,以使其符合在服务器上运行的查询的特性.

问题:

1. 是否可以在每个数据库级别上微调查询缓存？
2. 是否可以基于每个表微调查询缓存？
3. 请提供教程以学习PostgreSQL中的查询缓存.

Answer 1

我开发了一个缓存结果的系统，以加快从基于 Web 的解决方案查询结果的速度。我在下面重现了它的本质：

以下是通用缓存处理表和函数。

CREATE TABLE cached_results_headers (
  cache_id serial NOT NULL PRIMARY KEY,
  date timestamptz NOT NULL DEFAULT CURRENT_TIMESTAMP,
  last_access timestamptz NOT NULL DEFAULT CURRENT_TIMESTAMP,
  relid regclass NOT NULL,
  query text NOT NULL,
  rows int NOT NULL DEFAULT 0
  );
CREATE INDEX ON cached_results_headers (relid, md5(query));

CREATE TABLE cached_results (
  cache_id int NOT NULL,
  row_no int NOT NULL  
  );

CREATE OR REPLACE FUNCTION f_get_cached_results_header (p_cache_table text, p_source_relation regclass, p_query text, p_max_lifetime interval, p_clear_old_data interval) RETURNS cached_results_headers AS $BODY$
DECLARE
  _cache_id int;
  _rows int;
BEGIN
  IF p_clear_old_data IS NOT NULL THEN
    DELETE FROM cached_results_headers WHERE date < CURRENT_TIMESTAMP - p_clear_old_data;
  END IF;

  _cache_id := cache_id FROM cached_results_headers WHERE relid = p_source_relation AND md5(query) = md5(p_query) AND query = p_query AND date > CURRENT_TIMESTAMP - p_max_lifetime;
  IF _cache_id IS NULL THEN
    INSERT INTO cached_results_headers (relid, query) VALUES (p_source_relation, p_query) RETURNING cache_id INTO _cache_id;
    EXECUTE $$ INSERT INTO $$||p_cache_table||$$ SELECT $1, row_number() OVER (), r.r FROM ($$||p_query||$$) r $$ USING _cache_id;
    GET DIAGNOSTICS _rows = ROW_COUNT;
    UPDATE cached_results_headers SET rows = _rows WHERE cache_id = _cache_id;
  ELSE
    UPDATE cached_results_headers SET last_access = CURRENT_TIMESTAMP;
  END IF;
  RETURN (SELECT h FROM cached_results_headers h WHERE cache_id = _cache_id);
END;
$BODY$ LANGUAGE PLPGSQL SECURITY DEFINER;

以下是如何使用上面的表和函数的示例，对于以要在整数值范围内选择的my_view字段命名的给定视图。key您可以将以下所有内容替换为您的特定需求，并替换my_view为表、视图或函数。还可以根据需要更换过滤参数。

CREATE VIEW my_view AS SELECT ...; -- create a query with your data, with one of the integer columns in the result as "key" to filter by

CREATE TABLE cached_results_my_view (
  row my_view NOT NULL,
  PRIMARY KEY (cache_id, row_no),
  FOREIGN KEY (cache_id) REFERENCES cached_results_headers ON DELETE CASCADE
  ) INHERITS (cached_results);

CREATE OR REPLACE FUNCTION f_get_my_view_cached_rows (p_filter1 int, p_filter2 int, p_row_from int, p_row_to int) RETURNS SETOF my_view AS $BODY$
DECLARE
  _cache_id int;
BEGIN
  _cache_id := cache_id 
    FROM f_get_cached_results_header('cached_results_my_view', 'my_view'::regclass,
                                     'SELECT r FROM my_view r WHERE key BETWEEN '||p_filter1::text||' AND '||p_filter2::text||' ORDER BY key',
                                     '15 minutes'::interval, '1 day'::interval); -- cache for 15 minutes max since creation time; delete all cached data older than 1 day old

  RETURN QUERY
    SELECT (row).*
    FROM cached_results_my_view
    WHERE cache_id = _cache_id AND row_no BETWEEN p_row_from AND p_row_to
    ORDER BY row_no;
END;
$BODY$ LANGUAGE PLPGSQL;

示例：从缓存的 my_view 结果中检索按 过滤的 1 到 2000 行key BETWEEN 30044 AND 10610679。第一次运行，查询结果会缓存到 table 中cached_results_my_view，并返回前 2000 条记录。稍后再次运行它，将cached_results_my_view直接从表中检索结果，而不执行查询。

SELECT * FROM f_get_my_view_cached_rows(30044, 10610679, 1, 2000);