PostgreSQL中获取锁历史的方法之一

文章继续“尝试为 PostgreSQL 创建 ASH 类似物 «。

本文将使用特定的查询和示例来检查并展示使用 pg_locks 视图的历史记录可以获得哪些有用的信息。

警告。
由于主题新颖且测试期尚未完成,文章可能包含错误。 强烈欢迎和期待批评和意见。

输入数据

pg_locks 表示的历史

归档锁定

CREATE TABLE archive_locking 
(       timepoint timestamp without time zone ,
	locktype text ,
	relation oid ,
	mode text ,
	tid xid ,
	vtid text ,
	pid integer ,
	blocking_pids integer[] ,
	granted boolean ,
        queryid bigint 
);

本质上,该表与该表类似 archive_pg_stat_activity,这里有更详细的描述 - pg_stat_statements + pg_stat_activity + loq_query = pg_ash? 和这里 - 尝试为 PostgreSQL 创建 ASH 的类似物。

填充一列 查询ID 使用函数

update_history_locking_by_queryid

--update_history_locking_by_queryid.sql
CREATE OR REPLACE FUNCTION update_history_locking_by_queryid() RETURNS boolean AS $$
DECLARE
  result boolean ;
  current_minute double precision ; 
  
  start_minute integer ;
  finish_minute integer ;
  
  start_period timestamp without time zone ;
  finish_period timestamp without time zone ;
  
  lock_rec record ; 
  endpoint_rec record ; 
  
  current_hour_diff double precision ;
BEGIN
  RAISE NOTICE '***update_history_locking_by_queryid';
  
  result = TRUE ;
  
  current_minute = extract ( minute from now() );

  SELECT * FROM endpoint WHERE is_need_monitoring
  INTO endpoint_rec ;
  
  current_hour_diff = endpoint_rec.hour_diff ;
  
  IF current_minute < 5 
  THEN
	RAISE NOTICE 'Current time is less than 5 minute.';
	
	start_period = date_trunc('hour',now()) + (current_hour_diff * interval '1 hour');
    finish_period = start_period - interval '5 minute' ;
  ELSE 
    finish_minute =  extract ( minute from now() ) / 5 ;
    start_minute =  finish_minute - 1 ;
  
    start_period = date_trunc('hour',now()) + interval '1 minute'*start_minute*5+(current_hour_diff * interval '1 hour');
    finish_period = date_trunc('hour',now()) + interval '1 minute'*finish_minute*5+(current_hour_diff * interval '1 hour') ;
    
  END IF ;  
  
  RAISE NOTICE 'start_period = %', start_period;
  RAISE NOTICE 'finish_period = %', finish_period;

	FOR lock_rec IN   
	WITH act_queryid AS
	 (
		SELECT 
				pid , 
				timepoint ,
				query_start AS started ,			
				MAX(timepoint) OVER (PARTITION BY pid ,	query_start   ) AS finished ,			
				queryid 
		FROM 
				activity_hist.history_pg_stat_activity 			
		WHERE 			
				timepoint BETWEEN start_period and 
								  finish_period
		GROUP BY 
				pid , 
				timepoint ,  
				query_start ,
				queryid 
	 ),
	 lock_pids AS
		(
			SELECT
				hl.pid , 
				hl.locktype  ,
				hl.mode ,
				hl.timepoint , 
				MIN ( timepoint ) OVER (PARTITION BY pid , locktype  ,mode ) as started 
			FROM 
				activity_hist.history_locking hl
			WHERE 
				hl.timepoint between start_period and 
								     finish_period
			GROUP BY 
				hl.pid , 
				hl.locktype  ,
				hl.mode ,
				hl.timepoint 
		)
	SELECT 
		lp.pid , 
		lp.locktype  ,
		lp.mode ,
		lp.timepoint ,     
		aq.queryid 
	FROM lock_pids 	lp LEFT OUTER JOIN act_queryid aq ON ( lp.pid = aq.pid AND lp.started BETWEEN aq.started AND aq.finished )
	WHERE aq.queryid IS NOT NULL 
	GROUP BY  
		lp.pid , 
		lp.locktype  ,
		lp.mode ,
		lp.timepoint , 
		aq.queryid
	LOOP
		UPDATE activity_hist.history_locking SET queryid = lock_rec.queryid 
		WHERE pid = lock_rec.pid AND locktype = lock_rec.locktype AND mode = lock_rec.mode AND timepoint = lock_rec.timepoint ;	
	END LOOP;    
  
  RETURN result ;
END
$$ LANGUAGE plpgsql;

说明: queryid列的值会在history_locking表中更新,然后当为archive_locking表创建新分区时,该值将存储在历史值中。

产量

有关流程的一般信息。

按锁类型等待锁

请求

WITH
t AS
(
	SELECT 
		locktype  ,
		mode ,
		count(*) as total 
	FROM 
		activity_hist.archive_locking
	WHERE 
		timepoint between pg_stat_history_begin+(current_hour_diff * interval '1 hour') AND pg_stat_history_end+(current_hour_diff * interval '1 hour') AND 
		NOT granted
	GROUP BY 
		locktype  ,
		mode  
)
SELECT 
	locktype  ,
	mode ,
	total * interval '1 second' as duration			
FROM t 		
ORDER BY 3 DESC 

例子

| 按锁类型等待锁 +-----------+------------------------ --------+ ------------------- | 锁型| 模式| 持续时间+--------------------+-------------------------- - --+-------------------- | 交易ID| 共享锁| 19:39:26 | 00:03:35 元组| 访问专属锁| XNUMX:XNUMX:XNUMX +-------------------+------------------------ - -------+----------

按锁类型获取锁

请求

WITH
t AS
(
	SELECT 
		locktype  ,
		mode ,
		count(*) as total 
	FROM 
		activity_hist.archive_locking
	WHERE 
		timepoint between pg_stat_history_begin+(current_hour_diff * interval '1 hour') AND pg_stat_history_end+(current_hour_diff * interval '1 hour') AND 
		granted
	GROUP BY 
		locktype  ,
		mode  
)
SELECT 
	locktype  ,
	mode ,
	total * interval '1 second' as duration			
FROM t 		
ORDER BY 3 DESC 

例子

| 按锁类型获取锁 +--------------------------------+------------------------ --------+-------------------- | 锁型| 模式| 持续时间+--------------------+-------------------------- - --+-------------------- | 关系| 行独占锁| 51:11:10 | 虚拟xid| 专属锁| 48:10:43 | 44:24:53 交易ID| 专属锁| 20:06:13 | 17:58:47 关系| 访问共享锁| 01:40:41 | 00:26:41 元组| 访问专属锁| 00:00:01 | 00:00:01 元组| 专属锁| 00:00:01 | XNUMX:XNUMX:XNUMX 关系| 分享更新排他锁| XNUMX:XNUMX:XNUMX | XNUMX:XNUMX:XNUMX 对象| 行独占锁| XNUMX:XNUMX:XNUMX | 交易ID| 共享锁| XNUMX:XNUMX:XNUMX | 延伸| 专属锁| XNUMX:XNUMX:XNUMX +--------------------------------+------------------------ - -------+----------

有关特定 queryid 请求的详细信息

按查询 ID 的锁类型等待锁

请求

WITH
lt AS
(
	SELECT
		pid , 
		locktype  ,
		mode ,
		timepoint , 
		queryid , 
		blocking_pids ,
                MIN ( timepoint ) OVER (PARTITION BY pid , locktype  ,mode ) as started  
	FROM 
		activity_hist.archive_locking
	WHERE 
		timepoint between pg_stat_history_begin+(current_hour_diff * interval '1 hour') AND 
			                  pg_stat_history_end+(current_hour_diff * interval '1 hour') AND 
		NOT granted AND
	       queryid IS NOT NULL 
	GROUP BY 
	        pid , 
		locktype  ,
		mode ,
		timepoint ,
		queryid ,
		blocking_pids 
)
SELECT 
        lt.pid , 
	lt.locktype  ,
	lt.mode ,			
        lt.started ,
	lt.queryid  ,
	lt.blocking_pids ,
	COUNT(*)  * interval '1 second'	 as duration		
FROM lt 	
GROUP BY 
	lt.pid , 
        lt.locktype  ,
	lt.mode ,			
        lt.started ,
        lt.queryid ,
	lt.blocking_pids 
ORDER BY 4

例子

| 按查询 ID 的锁类型等待锁 +------------+----------+----- --------------- +----------------------------------------+--- ----------------- -+--------------------+------------------------ --------- | PID| 锁型| 模式| 开始| 查询ID| 阻塞PID| 持续时间+----------+------------------------+--------- ----------+------------------------------------------+--------- -----------+--------------------+----------------- --- | 11288| 交易ID| 共享锁| 2019-09-17 10:00:00.302936| 389015618226997618| {11092}| 00:03:34 | 11626:2019:09 17| 交易ID| 共享锁| 10-00-21.380921 389015618226997618:12380:00| 00| {29}| 11626:2019:09 | 17:10:00 21.380921| 交易ID| 共享锁| 389015618226997618-11092-00 03:25:11626| 2019| {09}| 17:10:00 | 21.380921:389015618226997618:12213 00| 交易ID| 共享锁| 01-55-11626 2019:09:17| 10| {00}| 21.380921:389015618226997618:12751 | 00:00:01 11629| 交易ID| 共享锁| 2019-09-17 10:00:24.331935| 389015618226997618| {11092}| 00:03:22 | 11629| 交易ID| 共享锁| 2019-09-17 10:00:24.331935| 389015618226997618| {12007}| 00:00:01 | 12007:2019:09 17| 交易ID| 共享锁| 10-05-03.327933 389015618226997618:11629:00| 00| {13}| 12007:2019:09 | 17| 交易ID| 共享锁| 10-05-03.327933 389015618226997618:11092:00| 01| {10}| 12007:2019:09 | 17:10:05 03.327933| 交易ID| 共享锁| 389015618226997618-11288-00 00:05:12213| 2019| {09}| 17:10:06 | 07.328019:389015618226997618:12007 00| 交易ID| 共享锁| 00-10-XNUMX XNUMX:XNUMX:XNUMX| XNUMX| {XNUMX}| XNUMX:XNUMX:XNUMX | XNUMX:XNUMX:XNUMX XNUMX| 交易ID| 共享锁| XNUMX-XNUMX-XNUMX XNUMX:XNUMX:XNUMX| XNUMX| {XNUMX}| XNUMX:XNUMX:XNUMX

通过查询 ID 按锁类型获取锁

请求

WITH
lt AS
(
	SELECT
		pid , 
		locktype  ,
		mode ,
		timepoint , 
		queryid , 
		blocking_pids ,
                MIN ( timepoint ) OVER (PARTITION BY pid , locktype  ,mode ) as started  
	FROM 
		activity_hist.archive_locking
	WHERE 
		timepoint between pg_stat_history_begin+(current_hour_diff * interval '1 hour') AND 
			                  pg_stat_history_end+(current_hour_diff * interval '1 hour') AND 
		granted AND
		queryid IS NOT NULL 
	GROUP BY 
	        pid , 
		locktype  ,
		mode ,
		timepoint ,
		queryid ,
		blocking_pids 
)
SELECT 
        lt.pid , 
	lt.locktype  ,
	lt.mode ,			
        lt.started ,
	lt.queryid  ,
	lt.blocking_pids ,
	COUNT(*)  * interval '1 second'	 as duration			
FROM lt 	
GROUP BY 
	lt.pid , 
	lt.locktype  ,
	lt.mode ,			
        lt.started ,
	lt.queryid ,
	lt.blocking_pids 
ORDER BY 4

例子

| 通过查询 ID 按锁类型获取锁 +---------+------------+----- --------------+ ----------------------------+---------------- ----------------+ --------------------+------------------------ -------- | PID| 锁型| 模式| 开始| 查询ID| 阻塞PID| 持续时间+----------+------------------------+--------- ----------+------------------------------------------+--------- -----------+--------------------+----------------- --- | 11288| 关系| 行独占锁| 2019-09-17 10:00:00.302936| 389015618226997618| {11092}| 00:03:34 | 11092:2019:09 17| 交易ID| 专属锁| 10-00-00.302936 389015618226997618:00:03| 34| {}| 11288:2019:09 | 17:10:00 00.302936| 关系| 行独占锁| 389015618226997618-00-00 10:11092:2019| 09| {}| 17:10:00 | 00.302936:389015618226997618:00 03| 关系| 行独占锁| 34-11092-2019 09:17:10| 00| {}| 00.302936:389015618226997618:00 | 03:34:11288 2019| 虚拟xid| 专属锁| 09-17-10 00:00.302936:389015618226997618| 11092| {}| 00:03:34 | 11288:2019:09 17| 虚拟xid| 专属锁| 10-00-00.302936 389015618226997618:11092:00| 03| {34}| 11288:2019:09 | 17:10:00 00.302936| 交易ID| 专属锁| 389015618226997618-11092-00 03:34:XNUMX| XNUMX| {XNUMX}| XNUMX:XNUMX:XNUMX | XNUMX:XNUMX:XNUMX XNUMX| 元组| 访问专属锁| XNUMX-XNUMX-XNUMX XNUMX:XNUMX:XNUMX| XNUMX| {XNUMX}| XNUMX:XNUMX:XNUMX

使用锁定历史记录来分析性能事件。

  1. pid=389015618226997618的进程执行的queryid=11288的请求从2019-09-17 10:00:00开始等待阻塞3分钟。
  2. 锁被 pid=11092 的进程持有
  3. 从11092-389015618226997618-2019 09:17:10开始,pid=00的进程执行queryid=00的请求,持有锁3分钟。

现在,我希望,最有趣和最有用的部分将开始 - 收集统计数据并分析有关等待和阻塞历史的案例。

未来,我想相信,我们会得到一套一些笔记(类似于Oracle的metalink)。

一般来说,正是出于这个原因,所使用的方法论才会尽快提供给每个人。

我会尝试在不久的将来将项目发布到github上。

来源: habr.com

添加评论