DROP SCHEMA IF EXISTS activity_hist ;
CREATE SCHEMA activity_hist AUTHORIZATION monitor ;
重要提示:架构不是在目标数据库中创建的,而是在监控数据库中创建的。
pg_stat_activity 查看历史记录
表用于存储 pg_stat_activity 视图的当前快照
Activity_hist.history_pg_stat_activity :
--ACTIVITY_HIST.HISTORY_PG_STAT_ACTIVITY
DROP TABLE IF EXISTS activity_hist.history_pg_stat_activity;
CREATE TABLE activity_hist.history_pg_stat_activity
(
timepoint timestamp without time zone ,
datid oid ,
datname name ,
pid integer,
usesysid oid ,
usename name ,
application_name text ,
client_addr inet ,
client_hostname text ,
client_port integer,
backend_start timestamp with time zone ,
xact_start timestamp with time zone ,
query_start timestamp with time zone ,
state_change timestamp with time zone ,
wait_event_type text ,
wait_event text ,
state text ,
backend_xid xid ,
backend_xmin xid ,
query text ,
backend_type text ,
queryid bigint
);
为了加快插入速度 - 无索引或限制。
为了存储历史记录本身,使用分区表:
Activity_hist.archive_pg_stat_activity :
DROP TABLE IF EXISTS activity_hist.archive_pg_stat_activity;
CREATE TABLE activity_hist.archive_pg_stat_activity
(
timepoint timestamp without time zone ,
datid oid ,
datname name ,
pid integer,
usesysid oid ,
usename name ,
application_name text ,
client_addr inet ,
client_hostname text ,
client_port integer,
backend_start timestamp with time zone ,
xact_start timestamp with time zone ,
query_start timestamp with time zone ,
state_change timestamp with time zone ,
wait_event_type text ,
wait_event text ,
state text ,
backend_xid xid ,
backend_xmin xid ,
query text ,
backend_type text ,
queryid bigint
)
PARTITION BY RANGE (timepoint);
由于本例中对插入速度没有要求,因此创建了一些索引来加快报告的创建速度。
会话阻塞历史记录
表用于存储会话锁的当前快照:
Activity_hist.history_locking :
--ACTIVITY_HIST.HISTORY_LOCKING
DROP TABLE IF EXISTS activity_hist.history_locking;
CREATE TABLE activity_hist.history_locking
(
timepoint timestamp without time zone ,
locktype text ,
relation oid ,
mode text ,
tid xid ,
vtid text ,
pid integer ,
blocking_pids integer[] ,
granted boolean
);
此外,为了加快插入速度,没有索引或限制。
为了存储历史记录本身,使用分区表:
Activity_hist.archive_locking:
DROP TABLE IF EXISTS activity_hist.archive_locking;
CREATE TABLE activity_hist.archive_locking
(
timepoint timestamp without time zone ,
locktype text ,
relation oid ,
mode text ,
tid xid ,
vtid text ,
pid integer ,
blocking_pids integer[] ,
granted boolean
)
PARTITION BY RANGE (timepoint);
CREATE OR REPLACE FUNCTION activity_hist.get_current_activity( current_host text , current_s_name text , current_s_pass text ) RETURNS BOOLEAN AS $$
DECLARE
database_rec record;
dblink_str text ;
BEGIN
EXECUTE 'SELECT dblink_connect(''LINK1'',''host='||current_host||' port=5432 dbname=postgres'||
' user='||current_s_name||' password='||current_s_pass|| ' '')';
--------------------------------------------------------------------
--GET pg_stat_activity stats
INSERT INTO activity_hist.history_pg_stat_activity
(
SELECT * FROM dblink('LINK1',
'SELECT
now() ,
datid ,
datname ,
pid ,
usesysid ,
usename ,
application_name ,
client_addr ,
client_hostname ,
client_port ,
backend_start ,
xact_start ,
query_start ,
state_change ,
wait_event_type ,
wait_event ,
state ,
backend_xid ,
backend_xmin ,
query ,
backend_type
FROM pg_stat_activity
')
AS t (
timepoint timestamp without time zone ,
datid oid ,
datname name ,
pid integer,
usesysid oid ,
usename name ,
application_name text ,
client_addr inet ,
client_hostname text ,
client_port integer,
backend_start timestamp with time zone ,
xact_start timestamp with time zone ,
query_start timestamp with time zone ,
state_change timestamp with time zone ,
wait_event_type text ,
wait_event text ,
state text ,
backend_xid xid ,
backend_xmin xid ,
query text ,
backend_type text
)
);
---------------------------------------
--ACTIVITY_HIST.HISTORY_LOCKING
INSERT INTO activity_hist.history_locking
(
SELECT * FROM dblink('LINK1',
'SELECT
now() ,
lock.locktype,
lock.relation,
lock.mode,
lock.transactionid as tid,
lock.virtualtransaction as vtid,
lock.pid,
pg_blocking_pids(lock.pid),
lock.granted
FROM pg_catalog.pg_locks lock LEFT JOIN pg_catalog.pg_database db ON db.oid = lock.database
WHERE NOT lock.pid = pg_backend_pid()
')
AS t (
timepoint timestamp without time zone ,
locktype text ,
relation oid ,
mode text ,
tid xid ,
vtid text ,
pid integer ,
blocking_pids integer[] ,
granted boolean
)
);
PERFORM dblink_disconnect('LINK1');
RETURN TRUE ;
END
$$ LANGUAGE plpgsql;
为了收集视图快照,使用了 systemd 服务和两个脚本:
pg_current_activity.service
# /etc/systemd/system/pg_current_activity.service
[Unit]
Description=Collect history of pg_stat_activity , pg_locks
Wants=pg_current_activity.timer
[Service]
Type=forking
StartLimitIntervalSec=0
ExecStart=/home/postgres/pgutils/demon/get_current_activity.sh 10.124.70.40 postgres postgres
[Install]
WantedBy=multi-user.target
pg_current_activity.timer
# /etc/systemd/system/pg_current_activity.timer
[Unit]
Description=Run pg_current_activity.sh every 1 second
Requires=pg_current_activity.service
[Timer]
Unit=pg_current_activity.service
OnCalendar=*:*:0/1
AccuracySec=1
[Install]
WantedBy=timers.target
WITH hist AS
(
SELECT
aa.query ,aa.queryid ,
count(*) * interval '1 second' AS duration
FROM activity_hist.archive_pg_stat_activity aa
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 backend_type = 'client backend' AND datname != 'postgres' AND ( aa.wait_event_type IS NULL ) ANDaa.state = 'active'
GROUP BY aa.wait_event_type , aa.wait_event , aa.query ,aa.queryid
UNION
SELECT
ha.query ,ha.queryid,
count(*) * interval '1 second' AS duration
FROM activity_hist.history_pg_stat_activity_for_reports ha
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 backend_type = 'client backend' AND datname != 'postgres' AND ( ha.wait_event_type IS NULL )AND ha.state = 'active'
GROUP BY ha.wait_event_type , ha.wait_event , ha.query ,ha.queryid
)
SELECT query , queryid , SUM( duration ) as duration
FROM hist
GROUP BY query , queryid
ORDER BY 3 DESC
WITH hist AS
(
SELECT
aa.query ,aa.queryid ,
count(*) * interval '1 second' AS duration
FROM activity_hist.archive_pg_stat_activity aa
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
backend_type = 'client backend' AND datname != 'postgres' AND
( aa.wait_event_type IS NOT NULL )
GROUP BY aa.wait_event_type , aa.wait_event , aa.query ,aa.queryid
UNION
SELECT
ha.query ,ha.queryid,
count(*) * interval '1 second' AS duration
FROM activity_hist.history_pg_stat_activity_for_reports ha
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
backend_type = 'client backend' AND datname != 'postgres' AND
( ha.wait_event_type IS NOT NULL )
GROUP BY ha.wait_event_type , ha.wait_event , ha.query ,ha.queryid
)
SELECT query , queryid , SUM( duration ) as duration
FROM hist
GROUP BY query , queryid
ORDER BY 3 DESC
WITH hist AS
(
SELECT
aa.wait_event_type , aa.wait_event
FROM activity_hist.archive_pg_stat_activity aa
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
backend_type = 'client backend' AND datname != 'postgres' AND
aa.wait_event IS NOT NULL
GROUP BY aa.wait_event_type , aa.wait_event
UNION
SELECT
ha.wait_event_type , ha.wait_event
FROM activity_hist.history_pg_stat_activity_for_reports ha
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
backend_type = 'client backend' AND datname != 'postgres' AND
ha.wait_event IS NOT NULL
GROUP BY ha.wait_event_type , ha.wait_event
)
SELECT wait_event_type , wait_event
FROM hist
GROUP BY wait_event_type , wait_event
ORDER BY 1 ASC,2 ASC
----------------------------------------------------------------------
WITH hist AS
(
SELECT
aa.wait_event_type , aa.wait_event , aa.query ,aa.queryid ,
count(*) * interval '1 second' AS duration
FROM activity_hist.archive_pg_stat_activity aa
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
backend_type = 'client backend' AND datname != 'postgres' AND
( aa.wait_event_type = waitings_stat_rec.wait_event_type AND aa.wait_event = waitings_stat_rec.wait_event )
GROUP BY aa.wait_event_type , aa.wait_event , aa.query ,aa.queryid
UNION
SELECT
ha.wait_event_type , ha.wait_event , ha.query ,ha.queryid,
count(*) * interval '1 second' AS duration
FROM activity_hist.history_pg_stat_activity_for_reports ha
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
backend_type = 'client backend' AND datname != 'postgres' AND
( ha.wait_event_type = waitings_stat_rec.wait_event_type AND ha.wait_event = waitings_stat_rec.wait_event )
GROUP BY ha.wait_event_type , ha.wait_event , ha.query ,ha.queryid
)
SELECT query , queryid , SUM( duration ) as duration
FROM hist
GROUP BY query , queryid
ORDER BY 3 DESC
SELECT
MIN(date_trunc('second',timepoint)) AS started ,
count(*) * interval '1 second' as duration ,
pid , blocking_pids , relation , mode , locktype
FROM
activity_hist.archive_locking al
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
locktype = 'relation'
GROUP BY pid , blocking_pids , relation , mode , locktype
UNION
SELECT
MIN(date_trunc('second',timepoint)) AS started ,
count(*) * interval '1 second' as duration ,
pid , blocking_pids , relation , mode , locktype
FROM
activity_hist.history_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
locktype = 'relation'
GROUP BY pid , blocking_pids , relation , mode , locktype
ORDER BY 1
SELECT
blocking_pids
FROM
activity_hist.archive_locking al
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
locktype = 'relation'
GROUP BY blocking_pids
UNION
SELECT
blocking_pids
FROM
activity_hist.history_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
locktype = 'relation'
GROUP BY blocking_pids
ORDER BY 1
---------------------------------------------------------------
SELECT
pid , usename , application_name , datname ,
MIN(date_trunc('second',timepoint)) as started ,
count(*) * interval '1 second' as duration ,
state ,
query
FROM activity_hist.archive_pg_stat_activity
WHERE pid= current_pid AND
timepoint BETWEEN pg_stat_history_begin+(current_hour_diff * interval '1 hour') AND pg_stat_history_end+(current_hour_diff * interval '1 hour')
GROUP BY pid , usename , application_name ,
datname ,
state_change,
state ,
query
UNION
SELECT
pid , usename , application_name , datname ,
MIN(date_trunc('second',timepoint)) as started ,
count(*) * interval '1 second' as duration ,
state ,
query
FROM activity_hist.history_pg_stat_activity_for_reports
WHERE pid= current_pid AND
timepoint BETWEEN pg_stat_history_begin+(current_hour_diff * interval '1 hour') AND pg_stat_history_end+(current_hour_diff * interval '1 hour')
GROUP BY pid , usename , application_name ,
datname ,
state_change,
state ,
query
ORDER BY 5 , 1