RAL Tier1 Operations Report for 11th June 2014
| Review of Issues during the fortnight 28th May to 11th June 2014.
|
- On Sunday 1st June there was a problem with the argus server affecting job submissions. The on-call team resolved the problem.
- During the afternoon of Thursday 5th June a problem on one of the network switch stacks stopped access to some disk servers that provide the caches for Atlas and LHCb tape (D0T1) service classes. This was declared in the GOC DB. The problem lasted around 75 minutes.
- There was a further problem with the argus server affecting job submission this morning (11th June).
- The problems with the WMSs reported in previous weeks are no longer present. The WMS developers were involved in looking at the problems although they were not finally understood.
| Resolved Disk Server Issues
|
- GDSS586 (AtlasDataDisk - D1T0) failed to restart after kernel/errata updates applied during the Castor update on 10th June. It was returned to production just befor this meeting (11th June).
| Current operational status and issues
|
| Ongoing Disk Server Issues
|
| Notable Changes made this last week.
|
- Yesterday (10th June) the Castor namserver was updated to version 2.1.14-13. While Castor was down the opportunity was taken to update the firmware in some network switches and apply kernel/errata updates to the Castor disk servers.
- A new ARC CE, arc-ce04 has been brought into production.
- ARC CEs arc-ce02 & arc-ce03 have been upgraded to version 4.1.0. (All ARC CEs now updated).
- The host certificate on arc-ce02 has been updated andthe new certificate is SHA-2 signed. There was an initial error during the application of this certificate, but that was corrected and the service is now running OK with the new (SHA-2) certificate.
- On the 2nd June LHCb access was removed from cream-ce01.
- Today (11th June) a new tape controller system (ACSLS) is being installed. There have been some problems with the new server. However, last test (last week) was successful.
| Advanced warning for other interventions
|
| The following items are being discussed and are still to be formally scheduled and announced.
|
- Dates for the Castor 2.1.14 stager upgrades: CMS- Tue 17th June; LHCb - Thu 19th June; GEN - Tue 24th June; Atlas - Thu 26th June.
- We are starting to plan the termination of the FTS2 service now that almost all use is on FTS3.
Listing by category:
- Databases:
- Switch LFC/FTS/3D to new Database Infrastructure.
- Castor:
- The Castor 2.1.14 upgrade is underway. Some checks are ongoing before finally deciding whether the stagers will go directly to minor version 2.1.14-13 (rather than 2.1.14-11 as previously planned).
- CIP-2.2.15 publishes online resources correctly for CASTOR 2.1.14 but not nearline (they appear as zero, due to a modification to how data is held in CASTOR). CIP will be updated. We can double check the Rajanian Problem at the same time which was understood and fixed earlier.
- Networking:
- Move switches connecting the 2011 disk servers batches onto the Tier1 mesh network.
- Make routing changes to allow the removal of the UKLight Router.
- Fabric
- We are phasing out the use of the software server used by the small VOs.
- Firmware updates on remaining EMC disk arrays (Castor, FTS/LFC)
- There will be circuit testing of the remaining (i.e. non-UPS) circuits in the machine room during 2014.
| Entries in GOC DB starting between the 28th May and 11th June 2014.
|
| Service
|
Scheduled?
|
Outage/At Risk
|
Start
|
End
|
Duration
|
Reason
|
| Castor (all SRM endpoints) and batch (all CEs)
|
SCHEDULED
|
OUTAGE
|
10/06/2014 08:50
|
10/06/2014 12:45
|
3 hours and 55 minutes
|
Castor and batch services down during upgrade of Castor Nameserver to version 2.1.14.
|
| arc-ce04.gridpp.rl.ac.uk
|
UNSCHEDULED
|
OUTAGE
|
10/06/2014 07:05
|
10/06/2014 12:45
|
5 hours and 40 minutes
|
Stopping work on new CE around upgrade of Castor Storage System.
|
| Castor (all SRM endpoints) and batch (all CEs)
|
SCHEDULED
|
OUTAGE
|
10/06/2014 06:50
|
10/06/2014 08:50
|
2 hours
|
Castor and batch services down for Networking Change before upgrade of Castor Nameserver to version 2.1.14.
|
| cream-ce01.gridpp.rl.ac.uk,
|
SCHEDULED
|
OUTAGE
|
07/06/2014 10:00
|
10/06/2014 12:00
|
3 days, 2 hours
|
EMI-3 update 14 upgrade
|
| srm-lhcb-tape.gridpp.rl.ac.uk,
|
UNSCHEDULED
|
OUTAGE
|
05/06/2014 15:25
|
05/06/2014 16:42
|
1 hour and 17 minutes
|
Problem affecting disk cache in front of tape.
|
| srm-atlas.gridpp.rl.ac.uk,
|
UNSCHEDULED
|
WARNING
|
05/06/2014 15:25
|
05/06/2014 16:41
|
1 hour and 16 minutes
|
Problem affecting disk cache in front of tape. Non-Tape service clasess unaffected.
|
| All srm endpoints
|
SCHEDULED
|
WARNING
|
04/06/2014 08:00
|
04/06/2014 17:00
|
9 hours
|
Warning (At Risk) on tape systems during testing of new tape library controller.
|
| arc-ce02.gridpp.rl.ac.uk, arc-ce03.gridpp.rl.ac.uk
|
SCHEDULED
|
WARNING
|
02/06/2014 10:00
|
02/06/2014 12:00
|
2 hours
|
Upgrade arc-ce02 and arc-ce03 to v. 4.1.0.
|
| arc-ce01.gridpp.rl.ac.uk
|
SCHEDULED
|
WARNING
|
28/05/2014 10:00
|
28/05/2014 12:00
|
2 hours
|
Upgrade of ARC CE to version 4.1.0.
|
| All Castor (all srm endpoints): srm-alice, srm-atlas, srm-biomed, srm-cert, srm-cms, srm-dteam, srm-hone, srm-ilc, srm-lhcb, srm-mice, srm-minos, srm-na62, srm-preprod, srm-snoplus, srm-superb, srm-t2k
|
SCHEDULED
|
WARNING
|
28/05/2014 09:30
|
28/05/2014 11:30
|
2 hours
|
At Risk on Castor (All SRM endpoints) during small internal network change.
|
| Open GGUS Tickets (Snapshot during morning of meeting)
|
| GGUS ID |
Level |
Urgency |
State |
Creation |
Last Update |
VO |
Subject
|
| 106090
|
Green
|
Urgent
|
In Progress
|
2014-06-11
|
2014-06-11
|
Atlas
|
RAL-LCG2 DATADISK is failing as a source
|
| 105571
|
Yellow
|
Less Urgent
|
In Progress
|
2014-05-21
|
2014-06-02
|
LHCb
|
BDII and SRM publish inconsistent storage capacity numbers
|
| 105405
|
Red
|
Urgent
|
In Progress
|
2014-05-14
|
2014-06-10
|
|
please check your Vidyo router firewall configuration
|
| 105100
|
Red
|
Less Urgent
|
In Progress
|
2014-05-02
|
2014-05-30
|
CMS
|
T1_UK_RAL Consistency Check (May14)
|
| 98249
|
Red
|
Urgent
|
Waiting Reply
|
2013-10-21
|
2014-06-02
|
SNO+
|
please configure cvmfs stratum-0 for SNO+ at RAL T1
|
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
|
| 28/05/14 |
100 |
100 |
100 |
100 |
100 |
100 |
99 |
|
| 29/05/14 |
100 |
100 |
100 |
100 |
100 |
100 |
100 |
|
| 30/05/14 |
100 |
100 |
100 |
100 |
100 |
100 |
99 |
|
| 31/05/14 |
100 |
100 |
100 |
100 |
100 |
100 |
100 |
|
| 01/06/14 |
100 |
100 |
100 |
94.8 |
100 |
100 |
100 |
Problem with Argus server.
|
| 02/06/14 |
100 |
100 |
100 |
100 |
100 |
100 |
100 |
|
| 03/06/14 |
100 |
100 |
100 |
100 |
100 |
100 |
100 |
|
| 04/06/14 |
100 |
100 |
100 |
100 |
100 |
100 |
100 |
|
| 05/06/14 |
100 |
100 |
99.1 |
100 |
100 |
100 |
99 |
One SRM Delete test failure ([SRM_INVALID_PATH] No such file or directory)
|
| 06/06/14 |
100 |
100 |
100 |
100 |
100 |
100 |
98 |
|
| 07/06/14 |
100 |
100 |
100 |
100 |
100 |
100 |
100 |
|
| 08/06/14 |
100 |
100 |
100 |
100 |
100 |
100 |
100 |
|
| 09/06/14 |
100 |
100 |
100 |
100 |
100 |
99 |
99 |
|
| 10/06/14 |
86.2 |
77.5 |
75.3 |
75.3 |
75.3 |
91 |
99 |
Castor Namserver 2.1.14 update.
|
