RAL Tier1 Operations Report for 11th June 2014
| Review of Issues during the fortnight 28th May to 11th June 2014.
|
- Maintenance on the diesel generator was carried out as planned on the morning of Thursday 22nd May.
- There were problems with tape access late Tuesday and Wednesday (20/21 May). On the Tuesday morning a new tape controller server (ACSLS) had been put into operation. Some six hours later problems started to appear. This change was reverted on Wednesday afternoon. The revertion was to put the old server back into service.
- This morning's planned network reconfiguration, with an 'at risk' on Castor ran into some problems causing a break in access to some disk servers for around 25 minutes. The affcted servers were the OCF'12 batch, which are in AtlasDataDisk, CMSDisk and LHCbDst. Castor recovered OK from this. The network change itself was carried out to completion.
| Resolved Disk Server Issues
|
| Current operational status and issues
|
- Grumbly problems with the WMSs reported last week ongoing. The developers have been contacted.
| Ongoing Disk Server Issues
|
- GDSS586 (AtlasDataDisk - D1T0) failed to restart after kernel/errata updates applied during the Castor update on 10th June. Currently under investigation.
| Notable Changes made this last week.
|
- Completion of roll out of CVMFS Client version 2.1.19 to whole farm.
- This morning (28th May) arc-ce01 was updated to version 4.1.0-1.
- This morning (28th May) two network switches that provide connectivity to the 2012 batches of Castor disk servers were moved to the mesh network.
- Although not a Tier1 issue we note that the UK EScience CA has switched to issuing SHA2 signed certificates this morning.
| 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 upgrade: Nameserver: Tuesday 10th June (now in GOC DB); Stagers: 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 2.1.14-11 upgrade is now scheduled. There is a further minor upgrade (to 2.1.14-13) that will be tested ahead of a later deployment.
- 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
|
| 105571
|
Green
|
Less Urgent
|
In Progress
|
2014-05-21
|
2014-05-27
|
LHCb
|
BDII and SRM publish inconsistent storage capacity numbers
|
| 105405
|
Yellow
|
Urgent
|
In Progress
|
2014-05-14
|
2014-05-15
|
|
please check your Vidyo router firewall configuration
|
| 105308
|
Yellow
|
Less Urgent
|
On Hold
|
2014-05-11
|
2014-05-27
|
Atlas
|
Jobs at RAL-LCG2_MCORE are failing with "Failed to open shared memory object: Permission denied"
|
| 105161
|
Amber
|
Less Urgent
|
In Progress
|
2014-05-05
|
2014-05-16
|
H1
|
hone jobs submitted into CREAM queues through lcgwms05.gridpp.rl.ac.uk & lcgwms06.gridpp.rl.ac.uk WMSs are are Ready status long time (more as 5 hours)
|
| 105100
|
Red
|
Urgent
|
In Progress
|
2014-05-02
|
2014-05-12
|
CMS
|
T1_UK_RAL Consistency Check (May14)
|
| 98249
|
Red
|
Urgent
|
Waiting Reply
|
2013-10-21
|
2014-05-21
|
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.
|
