情景
某些 SQL 代理作业计划在一天中每隔几分钟运行一次。
有时它会错过下一个时间表，因为它仍在按上一个时间表运行。
每隔一段时间，一项工作可能会“挂起”。这不会产生失败（因为作业还没有停止）。发生这种情况时，可以手动停止作业并在下次运行时正常工作。它旨在从中断的地方重新开始。
什么是最有效的方法...？
我想要一种方法来确定名为“JobX”的 SQL 代理作业当前正在运行多长时间（以秒为单位）。如果它当前没有运行，我们可以返回零。
这样，如果作业的运行时间超过某个阈值，我可以停止作业。
我假设可以使用 xp_sqlagent_enum_jobs 和 sysjobhistory 的组合，但我很好奇是否有更好的解决方案......并且希望可以从你们其他人已经遇到并解决的障碍中受益。
该解决方案将起作用：
SELECT DATEDIFF(SECOND,aj.start_execution_date,GetDate()) AS Seconds
FROM msdb..sysjobactivity aj
JOIN msdb..sysjobs sj on sj.job_id = aj.job_id
WHERE aj.stop_execution_date IS NULL -- job hasn't stopped running
AND aj.start_execution_date IS NOT NULL -- job is currently running
AND sj.name = 'JobX'
and not exists( -- make sure this is the most recent run
select 1
from msdb..sysjobactivity new
where new.job_id = aj.job_id
and new.start_execution_date > aj.start_execution_date
)
这是一个更一般的检查，取决于系统表。如果您更喜欢自定义路线，则可以将作业插入到您创建的作业日志表中。
/**** FOR CURRENTLY RUNNING JOBS ****/
SELECT j.name AS Job_Name,DATEDIFF(ss,a.start_execution_date ,GETDATE ())
FROM msdb.dbo.sysjobactivity a INNER JOIN msdb.dbo.sysjobs j
ON a.job_id =j.job_id
WHERE CONVERT(DATE,a.start_execution_date )=CONVERT(DATE,GETDATE ())
AND a.stop_execution_date IS NULL
/*This code will give u the Name of currently running jobs and for how much time it is running & after that u can add filters to it as u wish*/
/*Thanks in advance*/
您手动执行的操作听起来像是所谓的“看门狗循环”。基本上，启动和/或监视代理作业的 SQL 作业，如果需要，将其杀死。
下面的代码取自这里，应该会有所帮助，如果它们已经运行了很长时间，则无需手动监视和终止作业：
/****************************************************************
--This SQL will take a list of SQL Agent jobs (names must match),
--start them so they're all running together, and then
--monitor them, not quitting until all jobs have completed.
--
--In essence, it's an SQL "watchdog" loop to start and monitor SQL Agent Jobs
--
--Code from http://cc.davelozinski.com/code/sql-watchdog-loop-start-monitor-sql-agent-jobs
--
****************************************************************/
SET NOCOUNT ON
-------- BEGIN ITEMS THAT NEED TO BE CONFIGURED --------
--The amount of time to wait before checking again
--to see if the jobs are still running.
--Should be in hh:mm:ss format.
DECLARE @WaitDelay VARCHAR(8) = '00:00:20'
--Job timeout. Eg, if the jobs are running longer than this, kill them.
DECLARE @TimeoutMinutes INT = 240
DECLARE @JobsToRunTable TABLE
(
JobName NVARCHAR(128) NOT NULL,
JobID UNIQUEIDENTIFIER NULL,
Running INT NULL
)
--Insert the names of the SQL jobs here. Last two values should always be NULL at this point.
--Names need to match exactly, so best to copy/paste from the SQL Server Agent job name.
INSERT INTO @JobsToRunTable (JobName, JobID, Running) VALUES ('NameOfFirstSQLAgentJobToRun',NULL,NULL)
INSERT INTO @JobsToRunTable (JobName, JobID, Running) VALUES ('NameOfSecondSQLAgentJobToRun',NULL,NULL)
INSERT INTO @JobsToRunTable (JobName, JobID, Running) VALUES ('NameOfXSQLAgentJobToRun',NULL,NULL)
-------- NOTHING FROM HERE DOWN SHOULD NEED TO BE CONFIGURED --------
DECLARE @ExecutionStatusTable TABLE
(
JobID UNIQUEIDENTIFIER PRIMARY KEY, -- Job ID which will be a guid
LastRunDate INT, LastRunTime INT, -- Last run date and time
NextRunDate INT, NextRunTime INT, -- Next run date and time
NextRunScheduleID INT, -- an internal schedule id
RequestedToRun INT, RequestSource INT, RequestSourceID VARCHAR(128),
Running INT, -- 0 or 1, 1 means the job is executing
CurrentStep INT, -- which step is running
CurrentRetryAttempt INT, -- retry attempt
JobState INT -- 0 = Not idle or suspended, 1 = Executing, 2 = Waiting For Thread,
-- 3 = Between Retries, 4 = Idle, 5 = Suspended,
-- 6 = WaitingForStepToFinish, 7 = PerformingCompletionActions
)
DECLARE @JobNameToRun NVARCHAR(128) = NULL
DECLARE @IsJobRunning BIT = 1
DECLARE @AreJobsRunning BIT = 1
DECLARE @job_owner sysname = SUSER_SNAME()
DECLARE @JobID UNIQUEIDENTIFIER = null
DECLARE @StartDateTime DATETIME = GETDATE()
DECLARE @CurrentDateTime DATETIME = null
DECLARE @ExecutionStatus INT = 0
DECLARE @MaxTimeExceeded BIT = 0
--Loop through and start every job
DECLARE dbCursor CURSOR FOR SELECT JobName FROM @JobsToRunTable
OPEN dbCursor FETCH NEXT FROM dbCursor INTO @JobNameToRun
WHILE @@FETCH_STATUS = 0
BEGIN
EXEC [msdb].[dbo].sp_start_job @JobNameToRun
FETCH NEXT FROM dbCursor INTO @JobNameToRun
END
CLOSE dbCursor
DEALLOCATE dbCursor
print '*****************************************************************'
print 'Jobs started. ' + CAST(@StartDateTime as varchar)
print '*****************************************************************'
--Debug (if needed)
--SELECT * FROM @JobsToRunTable
WHILE 1=1 AND @AreJobsRunning = 1
BEGIN
--This has to be first with the delay to make sure the jobs
--have time to actually start up and are recognized as 'running'
WAITFOR DELAY @WaitDelay
--Reset for each loop iteration
SET @AreJobsRunning = 0
--Get the currently executing jobs by our user name
INSERT INTO @ExecutionStatusTable
EXECUTE [master].[dbo].xp_sqlagent_enum_jobs 1, @job_owner
--Debug (if needed)
--SELECT 'ExecutionStatusTable', * FROM @ExecutionStatusTable
--select every job to see if it's running
DECLARE dbCursor CURSOR FOR
SELECT x.[Running], x.[JobID], sj.name
FROM @ExecutionStatusTable x
INNER JOIN [msdb].[dbo].sysjobs sj ON sj.job_id = x.JobID
INNER JOIN @JobsToRunTable jtr on sj.name = jtr.JobName
OPEN dbCursor FETCH NEXT FROM dbCursor INTO @IsJobRunning, @JobID, @JobNameToRun
--Debug (if needed)
--SELECT x.[Running], x.[JobID], sj.name
-- FROM @ExecutionStatusTable x
-- INNER JOIN msdb.dbo.sysjobs sj ON sj.job_id = x.JobID
-- INNER JOIN @JobsToRunTable jtr on sj.name = jtr.JobName
WHILE @@FETCH_STATUS = 0
BEGIN
--bitwise operation to see if the loop should continue
SET @AreJobsRunning = @AreJobsRunning | @IsJobRunning
UPDATE @JobsToRunTable
SET Running = @IsJobRunning, JobID = @JobID
WHERE JobName = @JobNameToRun
--Debug (if needed)
--SELECT 'JobsToRun', * FROM @JobsToRunTable
SET @CurrentDateTime=GETDATE()
IF @IsJobRunning = 1
BEGIN -- Job is running or finishing (not idle)
IF DATEDIFF(mi, @StartDateTime, @CurrentDateTime) > @TimeoutMinutes
BEGIN
print '*****************************************************************'
print @JobNameToRun + ' exceeded timeout limit of ' + @TimeoutMinutes + ' minutes. Stopping.'
--Stop the job
EXEC [msdb].[dbo].sp_stop_job @job_name = @JobNameToRun
END
ELSE
BEGIN
print @JobNameToRun + ' running for ' + CONVERT(VARCHAR(25),DATEDIFF(mi, @StartDateTime, @CurrentDateTime)) + ' minute(s).'
END
END
IF @IsJobRunning = 0
BEGIN
--Job isn't running
print '*****************************************************************'
print @JobNameToRun + ' completed or did not run. ' + CAST(@CurrentDateTime as VARCHAR)
END
FETCH NEXT FROM dbCursor INTO @IsJobRunning, @JobID, @JobNameToRun
END -- WHILE @@FETCH_STATUS = 0
CLOSE dbCursor
DEALLOCATE dbCursor
--Clear out the table for the next loop iteration
DELETE FROM @ExecutionStatusTable
print '*****************************************************************'
END -- WHILE 1=1 AND @AreJobsRunning = 1
SET @CurrentDateTime = GETDATE()
print 'Finished at ' + CAST(@CurrentDateTime as varchar)
print CONVERT(VARCHAR(25),DATEDIFF(mi, @StartDateTime, @CurrentDateTime)) + ' minutes total run time.'