fax deployment, service and storage integration
DESCRIPTION
FAX Deployment, Service and Storage Integration . Wei Yang. Overview. FAX Components and Services Redirector, LFC and monitoring Infrastructure Sites deployment Status Use cases Panda Cloud On-going Integration with Storage systems R&D Activities. Infrastructure and Services. - PowerPoint PPT PresentationTRANSCRIPT
US ATLAS Distributed Facility Meeting University of California Santa Cruz
1
FAX Deployment, Service and Storage Integration
Wei Yang
2012-11-13
US ATLAS Distributed Facility Meeting University of California Santa Cruz
2
Overview
FAX Components and Serviceso Redirector, LFC and monitoring Infrastructureo Sites deployment Status
Use caseso Pandao Cloud
On-going Integration with Storage systemsR&D Activities
2012-11-13
US ATLAS Distributed Facility Meeting University of California Santa Cruz
3
Infrastructure and Services• A Network/Tree of Redirectors
o Allow a user to start from anyway and reach everywhereo Multiple levels of redirectors
• Top level: EU & BNL• Country level: DE, FR, RU, UK• Regional level: US central (hosted by UC)• Site level: UC, SLAC
• Read-only LFC serviceso Hosted by BNL (for US sites) and CERN (for EU sites)
• Monitoring Data Collectorso Collect and send monitoring data to ATLAS dash board
• Site specific/unique file for validation
2012-11-13
US ATLAS Distributed Facility Meeting University of California Santa Cruz
42012-11-13
http://ivukotic.web.cern.ch/ivukotic/FAX/index.asp
BNL and EU redirectors are peers at top level due to network latency
US ATLAS Distributed Facility Meeting University of California Santa Cruz
5
The Monitoring Services• Availability Dashboard
o Current running at UC, will be migrated to ATLAS SSB• Detail Monitoring Collector
o A.K.A UCSD collector, collect info on every reado Aggregated info file level access infoo Send to ATLAS monitoring dashboard via ActiveMQ
• Summary Monitoring Collectoro Based on MonaLisa, aggregated at data server levelo Info used to compare with detail info and debugging
• ATLAS Monitoring Dashboard for FAXo Integrate with AGIS
2012-11-13
US ATLAS Distributed Facility Meeting University of California Santa Cruz
62012-11-13
https://uct3-xrdp.uchicago.edu:8443/rsv/
FAX Dashboard and ML FAX repository comparison
FAX Dashboard now includes EOS, which dominates over all other transfer/accessThis plot is showing overall traffic rate over last 12 hours group by source , excluding CERN (EOS)
Aggregated xrootd traffic rate over last 12 hours according to FAX ML repository, excludingMWT2_UC and SLAC which are missing in Dashboard
In general is a good agreement, as well as going site by site.Big progress over last couple of weeks
From Julia Andreeva
US ATLAS Distributed Facility Meeting University of California Santa Cruz
82012-11-13
http://dashb-atlas-xrootd-transfers.cern.ch/ui
US ATLAS Distributed Facility Meeting University of California Santa Cruz
9
Site Deployment
2012-11-13
https://twiki.cern.ch/twiki/bin/view/Atlas/FaxSiteCertification• 8 sites in the US (all sites)• 4 sites in the UK• 3 sites in DE• 2 sites in RU• 1 site in Prague, CZ• working with IT cloud
US ATLAS Distributed Facility Meeting University of California Santa Cruz
10
Use Cases• Interactive Access from Desktop/Laptop
o Xrdcp or ROOT/ProofLite• From Panda Jobs
o Prun: supply a list of files in global nameo Panda pilot support
• Phase I: replace missing files using FAX– See Paul’s talk. Expanding test to more Tier 2 sites
• Phase 2: use site cost matrix for job scheduling• Phase 3: beyond, a lot more opportunities … See Torre’s talk
• By the Cloudo FAX is a nature choice for jobs in the Cloud to consume datao Inbound data traffic is free/low cost (outbound is expensive)o No need for long term storage in the Cloud
2012-11-13
US ATLAS Distributed Facility Meeting University of California Santa Cruz
11
Storage System Integration• Have solutions for almost all ATLAS systems
o Basic idea:• A dedicated xrootd machine to help the site joining FAX
either as a helper, refer client to the site storageor a proxy, fetch data from site storage on client’s behave
• Translate global file name to site storage file name o Support POSIX (NFS, Lustre, GPFS, etc.), Xrootd (including EOS), dCache, DPMo Working on Castor (RAL)
• Supporto tWiki and mailing list
• https://twiki.cern.ch/twiki/bin/viewauth/Atlas/AtlasXrootdSystems• [email protected]
o Bi-weekly Vidyo meeting on deployment issueso Experts in the US for general Xrootd and dCache supporto UK/DPM team support DPM integration to FAXo Some sites are creative and self support (EOS)o Cloud level support: e.g. DE and UK clouds
2012-11-13
US ATLAS Distributed Facility Meeting University of California Santa Cruz
12
R&D
• Driven by feature request/Operation feedbacko Deployment and Operation are the focuso But some level of R&D is still needed for a whileo Have experts in many R&D area in US and EU
• R&D provideso New functions/features, e.g. f-streamo bug fixeso New models for site and ADC specific needs
2012-11-13
13
Federated Xrootd deployment timeline
…more dCache dev
…new monitoring stream & integration issues
As always, the docs could Be better
From Rob Gardner