RAL Tier1 Operations Report for 21st September 2016
Review of Issues during the week 14th to 21st September 2016.
|
- A brief power dip affected parts of the RAL site on Wedesday afternoon, 14th Sep. The R89 machine room was OK. However, it was seen by equipment in the Atlas building. This had no affect on our services.
- On Sunday (18th Sep) there was a problem with the CVMFS squids. High access rates were seen on the stratum1 server that correlate with the problems. Tuning of some parameters on the stratum1 has taken place and the version of cvmfs on all worker nodes was reverted to CVMFS 2.1.20.
- There is a problem on the OPN link with one of the links appearing to not work outbound. This is being investigated.
Resolved Disk Server Issues
|
- GDSS779 (LHCbDst - D1T0) reported problems on 14th September. It was returned to service in read-only mode the following day, then back to full service on Monday (19th). Three disks showing media errors were replaced.
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.
- The intermittent, low-level, load-related packet loss seen over external connections is still being tracked.
Ongoing Disk Server Issues
|
Notable Changes made since the last meeting.
|
- We continue to move services (including arc-ce03) to the Hyper-V 2012 infrastructure.
- Upgraded condor to 8.4.8 on some systems.
- HPE worker nodes have completed testing and other actions. They are now being used to to check their behaviour under SL7.
Service
|
Scheduled?
|
Outage/At Risk
|
Start
|
End
|
Duration
|
Reason
|
arc-ce04.gridpp.rl.ac.uk
|
SCHEDULED
|
OUTAGE
|
23/09/2016 10:00
|
30/09/2016 18:00
|
7 days, 8 hours
|
ARC-CE04 being drained ahead of a reconfiguration and move to run on different infrastructure.
|
Advanced warning for other interventions
|
The following items are being discussed and are still to be formally scheduled and announced.
|
Listing by category:
- Intervention on Tape Libraries - early November.
Listing by category:
- Castor:
- Update SRMs to new version, including updating to SL6. This will be done after the Castor 2.1.15 update.
- Update to Castor version 2.1.15. This awaits successful resolution and testing of the new version.
- Migration of LHCb data from T10KC to T10KD tapes.
- Networking:
- Replace the UKLight Router. Then upgrade the 'bypass' link to the RAL border routers to 2*40Gbit.
- Fabric
- Firmware updates on older disk servers.
Entries in GOC DB starting since the last report.
|
Service
|
Scheduled?
|
Outage/At Risk
|
Start
|
End
|
Duration
|
Reason
|
arc-ce03.gridpp.rl.ac.uk
|
SCHEDULED
|
OUTAGE
|
15/09/2016 13:00
|
22/09/2016 18:00
|
7 days, 5 hours
|
ARC-CE03 being drained ahead of a reconfiguration and move to run on different infrastructure.
|
Open GGUS Tickets (Snapshot during morning of meeting)
|
GGUS ID |
Level |
Urgency |
State |
Creation |
Last Update |
VO |
Subject
|
123504
|
Green
|
Less Urgent
|
Waiting for Reply
|
2016-08-19
|
2016-09-20
|
T2K
|
proxy expiration
|
122827
|
Green
|
Less Urgent
|
Waiting for Reply
|
2016-07-12
|
2016-09-14
|
SNO+
|
Disk area at RAL
|
122364
|
Green
|
Less Urgent
|
On Hold
|
2016-06-27
|
2016-08-23
|
|
cvmfs support at RAL-LCG2 for solidexperiment.org
|
121687
|
Red
|
Less Urgent
|
On Hold
|
2016-05-20
|
2016-05-23
|
|
packet loss problems seen on RAL-LCG perfsonar
|
120350
|
Yellow
|
Less Urgent
|
On Hold
|
2016-03-22
|
2016-08-09
|
LSST
|
Enable LSST at RAL
|
117683
|
Amber
|
Less Urgent
|
On Hold
|
2015-11-18
|
2016-04-05
|
|
CASTOR at RAL not publishing GLUE 2
|
Key: Atlas HC = Atlas HammerCloud (Queue ANALY_RAL_SL6, Template 729); CMS HC = CMS HammerCloud
Day |
OPS |
Alice |
Atlas |
CMS |
LHCb |
Atlas HC |
CMS HC |
Comment
|
14/09/16 |
100 |
99 |
100 |
100 |
100 |
N/A |
100 |
AliEn-SE test failures. Problem seen at other sites too.
|
15/09/16 |
100 |
81 |
100 |
92 |
100 |
N/A |
100 |
ALICE: AliEn-SE test failures. Problem seen at other sites too; CMS: Several SRM test failures because of a user timeout error
|
16/09/16 |
100 |
100 |
100 |
100 |
100 |
N/A |
100 |
|
17/09/16 |
100 |
100 |
100 |
100 |
100 |
N/A |
100 |
|
18/09/16 |
100 |
100 |
100 |
100 |
100 |
N/A |
100 |
|
19/09/16 |
100 |
100 |
100 |
96 |
100 |
N/A |
100 |
Two SRM test failures (could not open connection to srm-cms.gridpp.rl.ac.uk) plus CE test failures.
|
20/09/16 |
100 |
100 |
100 |
98 |
50 |
N/A |
100 |
CMS: Single SRM test failure (user timeout) plus CE test failures; LHCb: We have one CE down, others working OK. But the SAM results don't seem to allow for it correctly.
|