General updates
|
Monday 13th February
Monday 6th February
- There is a Benchmarking Working Group F2F in the pre-GDB slot this Tuesday. It covers experiment views (including benchmarking with production jobs), cloud benchmarking, issues with Haswell processors (magic boost investigation).
- The GDB for February is this Wednesday. Topics include AFS phase-out, benchmarking, feedback on the EOS workshop and a baseline for WLCG T1 operations.
- January R/A figures for the Tier-2 sites have been circulated:
- ALICE. All OK
- ATLAS
- Sheffield 80%:82%
- ECDF 87%:98%
- RALPP 80%:80%
- CMS. All OK
- LHCb
- Sheffield 71%:73%
- ECDF 88%:100%
- RALPP 83%:84%
- Site responses so far:
- RALPP reports that the load on their dCache is causing intermittent SAM failures.
- Sheffield had an issue with ARGUS.
- There was a short downtime to undertake updates of the GridPP website and the Vac websites on Friday 3rd February. No issues reported.
- Cambridge/John: avoid frontier-squid-3.5.23-4.1
- Winnie: Help to debug ARC-CE "This metric ... cannot be executed independently"
- Minutes from the WLCG weekly ops meeting are available.
Monday 30th January
|
WLCG Operations Coordination - AgendasWiki Page
|
Monday 6th February
- Minutes from the WLCG Data Steering Group meeting of 2nd February are available on the meeting agenda page.
Tuesday 31st January
- There was a WLCG ops coordination meeting last Thursday 26th. Agenda | Minutes.
- The next related meeting will be on 2nd February and this is the WLCG Data Steering Group. (Closed meeting).
Monday 16th January
- The next WLCG ops coordination meeting is on 26th.
- Downtimes proposal followup --> please send feedback by Jan 20;
- Tape usage performance analysis.
|
Tier-1 - Status Page
|
Tuesday 14th February
A reminder that there is a weekly Tier-1 experiment liaison meeting. Notes from the last meeting here
- As reported last week the Castor 2.1.15 upgrade has been completed. However, there have been problems with CMS xroot redirection tests following this. The next change for Castor is to to update the SRMs.
- The migration of LHCb data to the T10KD tape media has been completed. All Tier1 data is now on this media.
|
Storage & Data Management - Agendas/Minutes
|
Wednesday 18 Jan
- Continued ZFS discussion
- Updates from the non-LHC VOs, data-wise. Mostly no news, except for DiRAC, Cambridge HPC and Edingburgh EPCC are debugging and testing; LSST expecting to do MC workflows end of Jan.
Wednesday 11 Jan
- ZFS presentation/discussion
Wednesday 04 Jan 2017
- Happy! Generally everything ticked along nicely over the break
- Interesting topics to pick up? Interest in ZFS again (see also Marcus's blog posts on the topic. GLUE2 for accounting?
Wednesday 21 Dec 2016
- Report from Computing Insights UK (nee MEW)
- Highlights and lowlights of the year (storage and data management only - which seems to have fared better than the world in general)
Wednesday 07 Dec
- Good GridPP presence at the CLOUD-SIG workshop at Crick last week. Real Work™ included GridFTP-endpoint-in-the-cloud and Jupyter notebooks. How do you get data into a Jupyter notebook (from the grid)?
- Opportunity to do more with data transfer between infrastructures.
|
Tier-2 Evolution - GridPP JIRA
|
Friday 3 February 2017
- ATLAS MCORE VMs now successfully running PanDA production jobs.
Tuesday 31 January 2017
- Vac 02.00 deployed at Liverpool and Manchester, and being used for installation underway at Birmingham.
- ATLAS MCORE VMs in testing. Correctly fetch HTCondor jobs associated with MCOREVAC PanDA queues.
- LHCb interruptible MC jobs in testing in VMs (and on LHCb HLT.) This will provide multiprocessor VMs that are flexible in duration and number of processors to fit available space.
- Vcycle with OpenStack ID v3 support being used to manage LHCb tenancy at Yandex.ru, and in production at CERN, IN2P3-CC and Datacentred Ltd.
Thursday 5 January 2017
- Vac 02.00 released, with SuperSlots mechanism for handling a mixture of different VM sizes on the same hypervisors.
|
Accounting - UK Grid Metrics HEPSPEC06 Atlas Dashboard HS06
|
Monday 16th January
- The discussion topic for next week will be accounting comparisons. Please note Alessandra's comments last week.
Monday 14th November
- Alessandra has written an FAQ to extract numbers from ATLAS and APEL avoiding the SSB.
Monday 26th September
- A problem with the APEL Pub and Sync tests developed last Tuesday and was resolved on Wednesday. This had a temporary impact on the accounting portal.
|
Documentation - KeyDocs
|
Monday 13th Febraury
- Please check the keydocs page. Would all owners please review their pages and prepare a short note on how they will bring things up-to-date in the coming months. This will be discussed at a core ops meeting (poll to be circulated shortly).
Monday 30th January
The fusion VO has been removed from GridPP Approved VOs.
Monday 9th January
- Tom put these together:
- A snapshot of the GridPP UserGuide is now available as an offline document in the Zenodo repository:
- ...and the v1.0 release of the LaTeX code used to compile it is here.
- There are some minor differences (mainly hyperlink-related) to the online version [1], which has also had a v1.0 release here.
Tue 22nd Nov
- More on Accounting audit tools
The process for ARC, Toque and VAC is now documented here.
https://github.com/gridpp/audit/wiki
General note
See the worst KeyDocs list for documents needing review now and the names of the responsible people.
|
Interoperation - EGI ops agendas
|
Monday 16th January
- There was an ops meeting on 9th January. Agenda.
Monday 7th November
- There was an EGI Ops meeting today: agenda
- UMD 3.14.5 released today
- VOMS 3.5.0, which makes RFC proxies the default for voms-proxy-init
- UMD 4.3.0 'October' release, release candidate ready, to be released by end of this week, including:
- ARC, GFAL2, XROOT, Davix, dCache, ARGUS, Gridsite, edg-mkgrid, umd-release for CentOS7
- please start using UMD4/SL6 or UMD4/CentOS7 instead of UMD3/SL6 & please don't use anymore EMI3
- (think there may be a campaign around this soon)
- Downtimes due to the vulnerability CVE-2016-5195: request an A/R recomputation
- All the resource centres that were affected by the vulnerability CVE-2016-5195 and that declared a downtime between 2016-10-20 16:00 UTC and 2016-10-31 18:00 UTC are invited to request a recomputation of A/R figures for the days in which the downtime was ongoing.
- ARGO proposal to use GOCDB as the only source of topology information
- VAPOR 2.1 released in September, it replaces GSTAT
|
Monitoring - Links MyWLCG
|
Monday 13th Febraury
- This category is pretty much inactive. Are there any topics under "monitoring" that anyone wants reported at this ops meeting? If not we will remove this section from the regular updates area of the bulletin and just leave the main links.
Tuesday 1st December
Tuesday 16th June
- F Melaccio & D Crooks decided to add a FAQs section devoted to common monitoring issues under the monitoring page.
- Feedback welcome.
|
On-duty - Dashboard ROD rota
|
Monday 16th January
- Rota to be updated this week. Gordon is on shift this week.
Monday 9th January
- Daniela posted on 25th Dec to say: "there's quite a lot of tickets - I tried to extend them all into January.
Otherwise apparently the grid is still standing."
Monday 5th December
- Another fairly quiet week. There were a few new tickets, which are mostly now resolved. There was an intermittent SRM alarm at RALPP which sporadically appeared then disappeared; it finally hung around long enough today to raise a ticket.
|
Rollout Status WLCG Baseline
|
Monday 13th February
- Please can we hear something from Raul and Sam (or others contributing to the middleware readiness work) about news in this area at the ops meeting next week? Thank you.
- Does anyone want specific questions in this area tackled in a roundtable discussion?
Tuesday 7th December
- Raul reports: validation of site BDII on Centos 7 done.
Tuesday 15th September
Tuesday 12th May
- MW Readiness WG meeting Wed May 6th at 4pm. Attended by Raul, Matt, Sam and Jeremy.
References
|
Security - Incident Procedure Policies Rota
|
Monday 13th Febraury
- EGI-SVG-2017-12391 - Just a check (JC). Attacks on Hadoop installations - sites should check they are securely configured.
- Security team meeting this afternoon.
Monday 6th February
- One security incident reported by EGI CSIRT labelled EGI-20170107-01. Not known to affect any UK site.
- Closure report circulated for incident EGI-20161214-01. Not known to affect any UK site.
- Advisory-SVG-CVE-2016-9587: Up to 'HIGH' risk input validation vulnerability concerning Ansible reported by EGI SVG [1](see also Bulletin report 17-Jan below)
- Summary of last week's EUGridPMA meeting by David Groep here [2]
The EGI security dashboard.
|
|
Services - PerfSonar production dashboard |PerfSonar development dashboard | GridPP VOMS
|
- This includes notifying of (inter)national services that will have an outage in the coming weeks or will be impacted by work elsewhere. (Cross-check the Tier-1 update).
Tuesday 14th February
- The development dashboard is now operational again. However the production dashboard is not currently displaying latency results (OSG ticket submitted).
- Birmingham pS host had lost its entire network connection and both Lancaster's hosts their IPv6 connection. Durham results are incomplete, GGUS ticket submitted (#126587).
Tuesday 25th October
- Duncan has recreated the UK perfSONAR mesh. Link here!
|
Tickets
|
Monday 13th February 2017, 16.00 GMT
25 Open UK Tickets this Week
ATLAS want your INPUT
126184 (26/1)
Atlas request for input on sites monitoring. In last week's cloud meeting Alastair asked if anyone had any input for this. If you do feel free to add to the google doc linked in the ticket or email your points to the cloud support mailing lists. In progress (7/2)
TOKEN AFFECTION
126554 (10/2)
Sno+ jobs failed at Liverpool, and once again John B had to educate a user group that space tokens are a thing (thanks John!). Would everyone who supports Sno+ be willing to roll out a space token for them? We don't know at this stage how much space would be needed, at this point it mainly seems for job stage back. In progress (13/2)
UNRELIABLE AVAILABILITY
126349 - ECDF
125743- RALPP
Both of these availability tickets are confusing the sites and myself (although the latter is still quite easy to do). ECDF are getting negative results again (and a lot of unknowns) and RALPP seem to be not updating results very often at all, suffering a several day lag by the looks of it.
|
Site Updates
|
Tuesday 23rd February
ALICE:
All okay.
RHUL 89%:89%
Lancaster 0%:0%
RALPP: 80%::80%
RALPP: 77%:77%
- RHUL: The largest problem was related to the SRM. The DPM version was upgraded and it took several weeks to get it working again (13 Jan onwards). Several short-lived occurrences of running out of space on the SRM for non-ATLAS VOs. For around 3 days (15-17 Jan) the site suffered from a DNS configuration error by their site network manager which removed their SRM from the DNS, causing external connections such as tests and transfers to fail. For one day (25 Jan) the site network was down for upgrade to the 10Gb link to JANET. Some unexpected problems occurred extending the interruption from an hour to a day. The link has been successfully commissioned.
- Lancaster: The ASAP metric for Lancaster for January is 97.5 %. There is a particular problem with ATLAS SAM tests which doesn’t affect the site activity in production and analysis and this relates to the path name being too long. A re-calculation has been performed.
- RALPP: Both CMS and LHCb low figures are due to specific CMS jobs overloading the site SRM head node. The jobs should have stopped now.
|
|