RAL Tier1 Operations Report for 20th January 2016
| Review of Issues during the week 20th to 27th January 2016.
|
- On Friday morning (22nd Jan) there was a problem with the link between the UKLight router and the Tier1 core network. This link is made up of four 10Gbit links. One of these stopped transferring packets in one direction giving intermittent problems that affected data transfers. This was fixed during that morning - the problem having lasted a few hours.
- We note a significant number of disk server problems over recent weeks/months. Although this last week did not have any disk server failures we have reviewed the situation - particularly looking at one batch of systems which show very high drive failure rates.
- Significant file loss was reported to Atlas following a triple disk failure on GDSS667 (AtlasScratchDisk - D1T0). A small number (hundreds) of files were successfully recovered from this server - but the majority were lost.
| Resolved Disk Server Issues
|
- GDSS648 (LHCbUser - D1T0) Failed on Tuesday 19th January. Several disks were reporting problems. It was returned to service the following day (20th Jan).
- GDSS732(LHCbDst - D1T0). FSProbe reported problems which suggested a hardware fault on Tuesday 19th January and was taken out of service. One disk was showing a lot of errors. That was replaced and the system returned to service the following day (20th Jan).
- GDSS676 (CMSTape - D0T1). This server was taken out of service on Wednesday (20th Jan). It had been drained of files needing migration following a double disk failure. It was returned to service on Friday 22nd Jan.
| Current operational status and issues
|
- There is a problem seen by LHCb of a low but persistent rate of failure when copying the results of batch jobs to Castor. There is also a further problem that sometimes occurs when these (failed) writes are attempted to storage at other sites. A recent modification has improved, but not completed fixed this.
- The intermittent, low-level, load-related packet loss seen over external connections is still being tracked. Likewise we have been working to understand some remaining low level of packet loss seen within a part of our Tier1 network.
| Ongoing Disk Server Issues
|
- GDSS620 (GenTape - D0T1) failed on the first January. This server has failed before recently. Investigations ongoing.
- GDSS667 (AtlasScratchDisk - D1T0) Failed on Monday 18th Jan with a read-only file system. On investigation three disks in the RAID set had problems. Following a lot of work a small number of files were recovered from the server. However, the large majority of the files were declared lost to Atlas.
| Notable Changes made since the last meeting.
|
- ARC-CE01 was upgraded to version 5.0.5 on Thursday (21st Jan).
| Service
|
Scheduled?
|
Outage/At Risk
|
Start
|
End
|
Duration
|
Reason
|
| arc-ce04.gridpp.rl.ac.uk
|
SCHEDULED
|
WARNING
|
01/02/2016 11:00
|
01/02/2016 12:00
|
1 hour
|
Upgrade ARC-CE04 to version 5.0.5
|
| arc-ce02.gridpp.rl.ac.uk & arc-ce03.gridpp.rl.ac.uk,
|
SCHEDULED
|
WARNING
|
28/01/2016 12:00
|
28/01/2016 13:00
|
1 hour
|
Upgrading ARC-CE02 & ARC-CE03 to version 5.0.5
|
| Advanced warning for other interventions
|
| The following items are being discussed and are still to be formally scheduled and announced.
|
Listing by category:
- Databases:
- Switch LFC/3D to new Database Infrastructure.
- Castor:
- Update SRMs to new version (includes updating to SL6).
- Update to Castor version 2.1.15.
- Migration of data from T10KC to T10KD tapes (affects Atlas & LHCb data).
- Networking:
- Replace the UKLight Router.
- Fabric
- Firmware updates on remaining EMC disk arrays (Castor, LFC)
| Entries in GOC DB starting since the last report.
|
| Service
|
Scheduled?
|
Outage/At Risk
|
Start
|
End
|
Duration
|
Reason
|
| arc-ce01.gridpp.rl.ac.uk
|
SCHEDULED
|
WARNING
|
21/01/2016 11:00
|
21/01/2016 12:00
|
1 hour
|
Warning during upgrade of this ARC-CE to version 5.0.5.
|
| Open GGUS Tickets (Snapshot during morning of meeting)
|
| GGUS ID |
Level |
Urgency |
State |
Creation |
Last Update |
VO |
Subject
|
| 118809
|
Green
|
Urgent
|
On Hold
|
2016-01-05
|
2016-01-13
|
|
Towards a recommendation on how to configure memory limits for batch jobs
|
| 117683
|
Green
|
Less Urgent
|
In Progress
|
2015-11-18
|
2016-01-05
|
|
CASTOR at RAL not publishing GLUE 2
|
| 116864
|
Red
|
Urgent
|
In Progress
|
2015-10-12
|
2015-12-16
|
CMS
|
T1_UK_RAL AAA opening and reading test failing again...
|
Key: Atlas HC = Atlas HammerCloud (Queue ANALY_RAL_SL6, Template 508); CMS HC = CMS HammerCloud
| Day |
OPS |
Alice |
Atlas |
CMS |
LHCb |
Atlas HC |
CMS HC |
Comment
|
| 20/01/16 |
100 |
100 |
100 |
100 |
100 |
75 |
100 |
|
| 21/01/16 |
100 |
100 |
100 |
100 |
100 |
93 |
100 |
|
| 22/01/16 |
100 |
100 |
100 |
95 |
96 |
100 |
100 |
Problem on the link between the UKLight router and the Tier1 core.
|
| 23/01/16 |
100 |
100 |
100 |
100 |
100 |
68 |
100 |
|
| 24/01/16 |
100 |
100 |
100 |
100 |
100 |
83 |
100 |
|
| 25/01/16 |
100 |
100 |
100 |
100 |
100 |
68 |
100 |
|
| 26/01/16 |
100 |
100 |
100 |
100 |
100 |
67 |
100 |
|
