RAL Tier1 Operations Report for 3rd January 2018
Review of Issues during the week 21st December 2017 to 3rd January 2018
|
- Network connectivity issues on Stack 9 in the UPS room overnight Thursday/Friday 21/22 December affected some internal systems (mainly monitoring). A member of staff attended overnight and a faulty transceiver was found the be the cause and replaced. External services were unaffected.
- Operations over the Christmas and New year holiday were generally stable although not completely quiet for the oncall team. There were some Castor disk server failures and staff did attend site over the holiday to replace failed disk drives. Our monitoring flagged problems with LHCb SAM tests - although these turned out to be a caused by a problem with a LHCb certificate.
- The number of Atlas batch jobs being run is lower than expected. The batch (Condor) scheduling will be looked at to try and understand and improve this.
Current operational status and issues
|
Resolved Castor Disk Server Issues
|
- GDSS688 (cmsDisk - D1T0) is back in production.
- GDSS743 (atlasStripInput - D1T0) is back in production.
Ongoing Castor Disk Server Issues
|
- GDSS757 (cmsDisk - D1T0) not in production.
- GDSS756 (cmsDisk - D1T0) not in production.
Limits on concurrent batch system jobs.
|
Notable Changes made since the last meeting.
|
• The ATLAS quota on Echo was increated by 500TB yesterday (2nd Jan).
- A round of Linux kernel patching of back-end database systems has been completed.
Entries in GOC DB starting since the last report.
|
No downtime scheduled in the GOCDB between 2017-12-20 and 2018-01-0
Advanced warning for other interventions
|
The following items are being discussed and are still to be formally scheduled and announced.
|
Ongoing or Pending - but not yet formally announced:
Listing by category:
- Castor:
- Update systems (initially tape servers) to use SL7 and configured by Quattor/Aquilon.
- Move to generic Castor headnodes.
- Echo:
- Update to next CEPH version ("Luminous").
- Networking
- Extend the number of services on the production network with IPv6 dual stack. (Done for Perfsonar, FTS3, all squids and the CVMFS Stratum-1 servers).
- Services
- Internal
- DNS servers will be rolled out within the Tier1 network.
Open GGUS Tickets (Snapshot during morning of meeting)
|
Ticket-ID
|
Type
|
VO
|
Notified Site
|
Resp. Unit
|
Status
|
Priority
|
Creation
|
Last Update
|
ToI
|
Subject
|
132589
|
TEAM
|
lhcb
|
RAL-LCG2
|
NGI_UK
|
in progress
|
very urgent
|
2017-12-21 06:45:00
|
2017-12-21 16:22:00
|
Local Batch System
|
Killed pilots at RAL
|
132540
|
TEAM
|
lhcb
|
RAL-LCG2
|
NGI_UK assign to:lcg-support@gridpp.rl.ac.uk
|
in progress
|
top priority
|
2017-12-18 09:32:00
|
2017-12-23 10:13:00
|
Other
|
Upload problems at RAL
|
131815
|
USER
|
t2k.org
|
RAL-LCG2
|
NGI_UK
|
in progress
|
less urgent
|
2017-11-13 14:42:00
|
2017-12-01 19:30:00
|
Storage Systems
|
Extremely long download times for T2K files on tape at RAL
|
130207
|
USER
|
mice
|
RAL-LCG2
|
NGI_UK assign to:lcg-support@gridpp.rl.ac.uk
|
on hold
|
urgent
|
2017-08-24 09:46:00
|
2017-12-18 17:22:00
|
Network problem
|
Timeouts when copyiing MICE reco data to CASTOR
|
127597
|
USER
|
cms
|
RAL-LCG2
|
NGI_UK assign to:lcg-support@gridpp.rl.ac.uk share with:sexton@fnal.gov
|
on hold
|
urgent
|
2017-04-07 10:34:00
|
2017-10-05 09:14:00
|
File Transfer
|
Check networking and xrootd RAL-CERN performance
|
124876
|
USER
|
ops
|
RAL-LCG2
|
NGI_UK assign to:lcg-support@gridpp.rl.ac.uk
|
on hold
|
less urgent
|
2016-11-07 12:06:00
|
2017-11-13 16:55:00
|
Operations
|
[Rod Dashboard] Issue detected : hr.srce.GridFTP-Transfer-ops@gridftp.echo.stfc.ac.uk
|
117683
|
USER
|
none
|
RAL-LCG2
|
NGI_UK assign to:lcg-support@gridpp.rl.ac.uk
|
on hold
|
less urgent
|
2015-11-18 11:36:00
|
2017-11-06 16:59:00
|
Information System
|
CASTOR at RAL not publishing GLUE 2
|
Day |
OPS |
Alice |
Atlas |
CMS |
LHCb |
Atlas Echo |
Comment
|
20/12/17 |
100 |
100 |
100 |
100 |
100 |
100 |
|
21/12/17 |
100 |
100 |
100 |
100 |
100 |
100 |
|
22/12/17 |
100 |
100 |
100 |
100 |
100 |
100 |
|
23/12/17 |
100 |
100 |
100 |
100 |
53 |
100 |
|
24/12/17 |
100 |
100 |
100 |
98 |
100 |
100 |
|
25/12/17 |
100 |
100 |
100 |
100 |
100 |
100 |
|
26/12/17 |
100 |
100 |
100 |
100 |
100 |
100 |
|
27/12/17 |
100 |
100 |
100 |
100 |
100 |
100 |
|
28/12/17 |
100 |
100 |
100 |
100 |
100 |
100 |
|
29/12/17 |
100 |
100 |
100 |
100 |
100 |
100 |
|
30/12/17 |
100 |
100 |
100 |
100 |
100 |
100 |
|
31/12/17 |
100 |
100 |
100 |
100 |
100 |
100 |
|
01/01/18 |
100 |
100 |
100 |
100 |
100 |
100 |
|
02/01/18 |
100 |
100 |
100 |
100 |
100 |
100 |
|
Key: Atlas HC = Atlas HammerCloud (Queue ANALY_RAL_SL6, Template 845); Atlas HC Echo = Atlas Echo (Template 841);CMS HC = CMS HammerCloud
Day |
Atlas HC |
Atlas HC Echo |
CMS HC |
Comment
|
20/12/17 |
100 |
0 |
100 |
Atlas HC Echo - No test run in time bin
|
21/12/17 |
98 |
0 |
100 |
Atlas HC Echo - No test run in time bin
|
22/12/17 |
100 |
0 |
98 |
Atlas HC Echo - No test run in time bin
|
23/12/17 |
100 |
0 |
100 |
Atlas HC Echo - No test run in time bin
|
24/12/17 |
0 |
0 |
100 |
Atlas HC Echo - No test run in time bin
|
25/12/17 |
100 |
0 |
100 |
Atlas HC Echo - No test run in time bin
|
26/12/17 |
100 |
0 |
100 |
Atlas HC Echo - No test run in time bin
|
27/12/17 |
100 |
0 |
100 |
Atlas HC Echo - No test run in time bin
|
28/12/17 |
100 |
0 |
100 |
Atlas HC Echo - No test run in time bin
|
29/12/17 |
100 |
0 |
100 |
Atlas HC Echo - No test run in time bin
|
30/12/17 |
93 |
0 |
100 |
Atlas HC Echo - No test run in time bin
|
31/12/17 |
100 |
0 |
100 |
Atlas HC Echo - No test run in time bin
|
01/01/18 |
100 |
0 |
100 |
Atlas HC Echo - No test run in time bin
|
02/01/18 |
100 |
0 |
100 |
Atlas HC Echo - No test run in time bin
|