CMS staging from tape Natalia Ratnikova, Fermilab

Slides:



Advertisements
Similar presentations
LCG Tiziana Ferrari - SC3: INFN installation status report 1 Service Challenge Phase 3: Status report Tiziana Ferrari on behalf of the INFN SC team INFN.
Advertisements

December Pre-GDB meeting1 CCRC08-1 ATLAS’ plans and intentions Kors Bos NIKHEF, Amsterdam.
Bookkeeping data Monitoring info Get jobs Site A Site B Site C Site D Agent Production service Monitoring service Bookkeeping service Agent © Andrei Tsaregorodtsev.
1 INDIACMS-TIFR TIER-2 Grid Status Report IndiaCMS Meeting, Sep 27-28, 2007 Delhi University, India.
CERN - IT Department CH-1211 Genève 23 Switzerland t Monitoring the ATLAS Distributed Data Management System Ricardo Rocha (CERN) on behalf.
Go to the MTSD Home Page In the URL add “/admin”
September 29, 2009Computer Security Awareness Day1 Fermilab.
D0 SAM – status and needs Plagarized from: D0 Experiment SAM Project Fermilab Computing Division.
3rd June 2004 CDF Grid SAM:Metadata and Middleware Components Mòrag Burgon-Lyon University of Glasgow.
Experiment Support CERN IT Department CH-1211 Geneva 23 Switzerland t DBES PhEDEx Monitoring Nicolò Magini CERN IT-ES-VOS For the PhEDEx.
PanDA Summary Kaushik De Univ. of Texas at Arlington ADC Retreat, Naples Feb 4, 2011.
UMD TIER-3 EXPERIENCES Malina Kirn October 23, 2008 UMD T3 experiences 1.
Owen SyngeTitle of TalkSlide 1 Storage Management Owen Synge – Developer, Packager, and first line support to System Administrators. Talks Scope –GridPP.
LHCb The LHCb Data Management System Philippe Charpentier CERN On behalf of the LHCb Collaboration.
CASTOR evolution Presentation to HEPiX 2003, Vancouver 20/10/2003 Jean-Damien Durand, CERN-IT.
1 LHCb File Transfer framework N. Brook, Ph. Charpentier, A.Tsaregorodtsev LCG Storage Management Workshop, 6 April 2005, CERN.
CERN - IT Department CH-1211 Genève 23 Switzerland t High Availability Databases based on Oracle 10g RAC on Linux WLCG Tier2 Tutorials, CERN,
XROOTD AND FEDERATED STORAGE MONITORING CURRENT STATUS AND ISSUES A.Petrosyan, D.Oleynik, J.Andreeva Creating federated data stores for the LHC CC-IN2P3,
EGI-InSPIRE EGI-InSPIRE RI DDM solutions for disk space resource optimization Fernando H. Barreiro Megino (CERN-IT Experiment Support)
Data Transfer Service Challenge Infrastructure Ian Bird GDB 12 th January 2005.
Distributed Data Management Miguel Branco 1 DQ2 discussion on future features BNL workshop October 4, 2007.
Handling of T1D0 in CCRC’08 Tier-0 data handling Tier-1 data handling Experiment data handling Reprocessing Recalling files from tape Tier-0 data handling,
Kati Lassila-Perini EGEE User Support Workshop Outline: – CMS collaboration – User Support clients – User Support task definition – passive support:
Testing CernVM-FS scalability at RAL Tier1 Ian Collier RAL Tier1 Fabric Team WLCG GDB - September
Distributed Physics Analysis Past, Present, and Future Kaushik De University of Texas at Arlington (ATLAS & D0 Collaborations) ICHEP’06, Moscow July 29,
Enabling Grids for E-sciencE INFSO-RI Enabling Grids for E-sciencE Gavin McCance GDB – 6 June 2007 FTS 2.0 deployment and testing.
D0 File Replication PPDG SLAC File replication workshop 9/20/00 Vicky White.
ASCC Site Report Eric Yen & Simon C. Lin Academia Sinica 20 July 2005.
CMS: T1 Disk/Tape separation Nicolò Magini, CERN IT/SDC Oliver Gutsche, FNAL November 11 th 2013.
BNL dCache Status and Plan CHEP07: September 2-7, 2007 Zhenping (Jane) Liu for the BNL RACF Storage Group.
CASTOR in SC Operational aspects Vladimír Bahyl CERN IT-FIO 3 2.
VO Box discussion ATLAS NIKHEF January, 2006 Miguel Branco -
Joe Foster 1 Two questions about datasets: –How do you find datasets with the processes, cuts, conditions you need for your analysis? –How do.
VO Experiences with Open Science Grid Storage OSG Storage Forum | Wednesday September 22, 2010 (10:30am)
HEPiX IPv6 Working Group David Kelsey (STFC-RAL) GridPP33 Ambleside 22 Aug 2014.
WLCG Operations Coordination Andrea Sciabà IT/SDC GDB 11 th September 2013.
The CMS Beijing Tier 2: Status and Application Xiaomei Zhang CMS IHEP Group Meeting December 28, 2007.
CERN IT Department CH-1211 Genève 23 Switzerland t EGEE09 Barcelona ATLAS Distributed Data Management Fernando H. Barreiro Megino on behalf.
Baseline Services Group Status of File Transfer Service discussions Storage Management Workshop 6 th April 2005 Ian Bird IT/GD.
CTA: CERN Tape Archive Rationale, Architecture and Status
CMS-specific services and activities at CC-IN2P3 Farida Fassi October 23th.
HTCondor Accounting Update
Federating Data in the ALICE Experiment
Simulation Production System
Xiaomei Zhang CMS IHEP Group Meeting December
SQL Replication for RCSQL 4.5
LCG Service Challenge: Planning and Milestones
Report from WLCG Workshop 2017: WLCG Network Requirements GDB - CERN 12th of July 2017
ATLAS Use and Experience of FTS
BNL Tier1 Report Worker nodes Tier 1: added 88 Dell R430 nodes
Service Challenge 3 CERN
Jan 12, 2005 Improving CMS data transfers among its distributed Computing Facilities N. Magini CERN IT-ES-VOS, Geneva, Switzerland J. Flix Port d'Informació.
The Status of Beijing site, and CMS local DBS
ATLAS activities in the IT cloud in April 2008
Update on Plan for KISTI-GSDC
Taming the protocol zoo
CMS transferts massif Artem Trunov.
Farida Fassi, Damien Mercie
PanDA in a Federated Environment
Evolution of the distributed computing model The case of CMS
Summary from last MB “The MB agreed that a detailed deployment plan and a realistic time scale are required for deploying glexec with setuid mode at WLCG.
Conditions Data access using FroNTier Squid cache Server
Ákos Frohner EGEE'08 September 2008
Storage information and the Site Status Board
Data Management cluster summary
Backup Monitoring – EMC NetWorker
Backup Monitoring – EMC NetWorker
Roadmap for Data Management and Caching
The LHCb Computing Data Challenge DC06
Presentation transcript:

CMS staging from tape Natalia Ratnikova, Fermilab for WLCG pre-GDB Storage meeting CERN, 12 September 2017

Outline CMS data organization Data transfers workflow CMS storage sites topology CMS local staging and transfers details Staging tests status and work in progress 9/12/17 Natalia Ratnikova | WLCG pre-GDB Storage | CMS staging from tape

CMS data organization … CMS data are organized into datasets by physics content Dataset size varies: 0.1 - 100 TB Within a dataset, files are organized into blocks of 1–1000 for scalability Small files are merged after processing to help scalability of storage and catalogs Typical file size is ~ 2.5 G, but there are some quite large files CMS data management tools can manipulate individual blocks as well as full dataset. Data transfers are driven by subscribing datasets or blocks to the Files … Dataset Blocks 9/12/17 Natalia Ratnikova | WLCG pre-GDB Storage | CMS staging from tape

Data transfers workflow Powered by PhEDEx: FTS3 Client GFAL Site Agents 9/12/17 Natalia Ratnikova | WLCG pre-GDB Storage | CMS staging from tape

CMS storage sites topology CMS uses tape storage at 8 sites: T0_CH_CERN T1_US_FNAL T1_DE_KIT T1_RU_JINR T1_ES_PIC T1_IT_CNAF T1_FR_CCIN2P3 T1_UK_RAL During Run 1 CMS data needed for production at Tier-1 sites have been pre-staged manually by the site admins. After Run1 all CMS Tier-1s sites deployed separate endpoints for disk and tape storage Tape storage is used mainly for archiving purpose. Data needed for production are subscribed to Disk by the production operators/tools. 9/12/17 Natalia Ratnikova | WLCG pre-GDB Storage | CMS staging from tape

CMS local staging and transfers details Data are routed from the available sources to the destination, taking into account the link costs, performance and subscription priorities, using priority-window up to a fixed data volume. Sites are using FTS3 as a transport layer to download the routed data. T0/T1 sites run a special local Stager agent to check for data routed from MSS, call local plugins to stage the files and check the status, and mark the staged files as available for the download. Routing, staging, and download are performed asynchronously. 9/12/17 Natalia Ratnikova | WLCG pre-GDB Storage | CMS staging from tape

Staging tests status and work in progress Performed by CMS data operations to test the throughput between T1 MSS/Buffer abd T1 Disk end points the throughput goals reached too many tape mounts reported by the sites fine tuning of the agents configuration to increase the number of staging requests and let MSS system to optimize Triple increase of the router priority windows adjustments on the MSS system side experimenting with the stager idle time to create larger request volume All detailed info is only in the local stager logs: experimenting with FTS3 staging to benefit from central monitoring. 9/12/17 Natalia Ratnikova | WLCG pre-GDB Storage | CMS staging from tape