[Hps-analysis] Fwd: CCPR 155445 UPDATE (files are failed to be staged out)

[Rafayel Paremuzyan]

FYI

Rafo


-------- Forwarded Message --------
Subject: 	CCPR 155445 UPDATE (files are failed to be staged out)
Date: 	Wed, 21 Feb 2018 14:57:41 -0500 (EST)
From: 	ccpr_reply at jlab.org
To: 	rafopar at jlab.org, philpott at jlab.org
CC: 	kelvin at jlab.org, larrieu at jlab.org, philpott at jlab.org, 
seitz at jlab.org, letta at jlab.org, rackley at jlab.org, strosahl at jlab.org, 
ychen at jlab.org



Here is an update to the help request you submitted.
When you reply to THIS message, Please DO NOT include the original text below.

Mod Date:   2018/02/21
Mod Time:   14:57:40
Mod User:   philpott
Current State:   COMPLETE
STATE changed from (RECEIVED) to COMPLETE.


--------------------------------------------------------------

Overnight a disk server hung; the issue was resolved this morning.  If
you are using SWIF, those jobs can be rerun automatically, or you
may need to resubmit them manually.

Regards,
Sandy

									
--------------------------------------------------------------		
Here is a copy of your Original Request:
	
Email:     rafopar at jlab.org
Name:      Rafayel Paremuzyan
Username:  rafopar
Staff:	   philpott
Platform:  other,Netscape,537.36 (KHTML, like Gecko) Chrome
Building:  12_2
Room:      F292-9
Hostname:  129.57.113.47
Category:  SCIENTIFIC COMPUTING
Subject:   files are failed to be staged out
Submitted: 2/21/2018 11:05 AM
			
Request:
Hi,

We (hps) started cooking of data yesterday,
and we noticed significant amount of jobs that failed because files were not properly staged out to disk or to tape.
Below are single example job IDs from different kind of failures.

JOBID: 49355427  Failed to transfer file to disk: hps_005563.13_dst_v4.0.2-pre.root, looking into log file, shows that file was produced properly and has non-zero size.
JOBID: 49355585  Failed to transfer file to tape, Status is ' (COPYING)', file has non-zero size
JOBID: 49355583  Failed to transfer file to tape, Status is ' (FAILED)', file has non-zero size
JOBID  49355581  there is no even log file neither in ~/.farmout nor in our logfile directory, the status shows as 'FAILED (No job status in batch system and we never recorded a finish.)'

The following link will bring you to a list of open CCPR's

http://mis.jlab.org/mis/ccpr/ccpr_user/ccprframe_user.html
	

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mailman.jlab.org/pipermail/hps-analysis/attachments/20180221/6ae5e11b/attachment.html>