Evolution of the Atlas data and computing model for a Tier-2 in the EGI infrastructure

II IFICÁlvaro Fernández Casaní ISGC2012, Taipei, 2th March 2012

Evolution of the Atlas data and computing model for a Tier-2 in

the EGI infrastructureÁlvaro Fernández Casaní

on behalf of the IFIC Atlas computing group

II PCI2010 WorkshopValencia, 10th-12th January 2012

1


Outline• Introduction: IFIC and Atlas Tier2 SPAIN• Evolution of the Atlas computing model

– Flattening the model to a Mesh– Tier 2 duties– Data distribution: Tier2s policy

• Data shares ( site classification) • Availability and Connectivity• Networking

– Dynamic data distribution and caching– Remote data access

• Real Users example 2


ATLAS CENTERS

3

http://dashb-earth.cern.ch/dashboard/dashb-earth-atlas.kmz

II IFICÁlvaro Fernández Casaní ISGC2012, Taipei, 2th March 2012 4

Introduction


SPAIN CONTRIBUTION TO ATLAS


Spanish ATLAS Tier2

6


IFIC Computing Infrastructure Resources

7

EGI

CSIC resources (not experiment resources):25% IFIC users25% CSIC25% European Grid25% Iberian Grid

To migrate Scientific application to the GRID

ATLAS


Last year summary

8

• 3,579,606 Jobs• 6,038,754 CPU

consumption hours• 13,776,655 KSi2K

(CPU time normalised)

• Supporting 22 Virtual Organizations (VOs)


Prevision 2012For IFIC

9

• For 2012:– We already fulfil the CPU requirements– Increasing Disk:

• 230 TB => 4 SuperMicro x 57.6 (2 TB disks)

YEAR 2010 2011 2012 2013CPU(HS06) 6000 6950 6650 7223

DISK(TB) 500 940 1175 1325


EVOLUTION OF THE ATLAS COMPUTING MODEL

10


Previous ATLAS cloud model

• Hierarchical Model based on the Monarc network topology

• CLOUDS OF Tier-1 with its geographical related Tier-2

• Possible communications:• T0-T1• T1-T1• Intra-cloud T1-T2

• Forbidden communications:• Inter-cloud T1-T2• Inter-cloud T2-T2

Simone Campana Software & Computing Workshop (April’11)https://indico.cern.ch/conferenceDisplay.py?confId=119169


Shortcomings of Cloud Boundaries• Consolidation of User Analysis outputs problematic

– Analysis runs over many cloud– Consolidation needs to “hop” the data through the T1s

• MonteCarlo production must confine one task to one cloud– To facilitate the output aggregation at T1

• Replication of datasets (PD2P) more inflexible– Need to replicate from T1 to T2s of the same cloud– Or “hop” through a T1

• T2s can not really be used as storage of “primary” data– Issues in creating secondary copies at other T1s

• Tier-2 limited usability due to T1 downtimes– Dependency on LFC data catalog

More info: Simone Campana Software & Computing Workshop (April’11)https://indico.cern.ch/conferenceDisplay.py?confId=119169

DATA FLOWS

TOO STRICT

OPERATIONAL PROBLEMS


Solving issues

13

LFC Spanish Cloud planned

this week !

• Make Tier-2 activities more independent• Reduce service dependencies:

– Move Catalog (LFC) to CERN:• Backup at US . Another at UK • Remove from tier-1• Analysis jobs will be able to run during T1 downtime• Production jobs can keep running during T1 downtime

• Benefit from technology improvements:– The network model today does not really resemble the Monarc

model• Many T2s are connected very well with many T1s• Many T2s are not that well connected with their T1

– So it makes sense to break cloud boundaries.


Flattening the model

• to break cloud boundaries.– Let DDM freely transfer from every site to every site– Inter-cloud direct transfers– Multi-cloud production

• Not quite there– Some links simply have limited bandwidth– In those cases, several hops will anyway be needed

• Defining T2Ds is an attempt to break cloud boundaries “for the cases where it makes sense”

Network is a key component to optimize the use of the storage and CPU


Categorization of Sites: T2D

• T2Ds are the Tier-2 sites that can directly transfer any size of files (especially large files) not only from/to the T1 of the cloud (to which they are associated to) but also from/to the other T1s of the other clouds.

• T2Ds are candidates for – multi-cloud production sites – primary replica repository sites (T2PRR)

https://twiki.cern.ch/twiki/bin/view/Atlas/T2D


https://twiki.cern.ch/twiki/bin/view/Atlas/T2PRR


ATLAS Tier2 Share Revision• In 2010, many Tier2s got full; T2 data distribution share revision• The data distribution to Tier-2 (and Tier-3g) sites should take into account • the network connectivity of the sites (thus, T2Ds should have more data) • the availability for analysis. • Introduced at Software & Computing Workshop 20 July 2011

– Up to ADC Ops to define the distribution policy among T2s: Preference to • Reliable sites for analysis (fraction of time with analysis queue online) • Well connected sites (T2Ds) to transfer datasets quickly

– Started from summer 2011 • Based on T2D list defined on 1st July 2011

– Simplified with 4 groups treated equally : • Alpha (60% share-17 sites) : T2Ds with > 90 % reliability (60%) • Bravo (30 % share-21 sites) : non-T2Ds with > 90% reliability • Charlie (10 % share-12 sites) : Any T2 with 80%<reliability<90% • Delta (0% share-13 sites): Any T2 with reliability < 80 %

– one single list both for pre-placement and dynamic data

16


https://indico.cern.ch/contributionDisplay.py?contribId=104&sessionId=13&confId=119170





ATLAS Tier2

•

17


Spanish Cloud Data shares Last Month

http://atladcops.cern.ch:8000/drmon/crmon_TiersInfo.html

18

IFIC

IFIC is alpha T2D site -> also candidates for more

datasets in PD2P ( see later)


Availability

19

http://dashb-atlas-ssb.cern.ch/dashboard/request.py/siteviewhistorywithstatistics?columnid=564&view=shifter%20view

LAST MONTH

Hammercloud: for ATLAS• Distributed Analysis testing system• For avoiding jobs go to problematic sites• Can exclude sites if test jobs are not passed

EGI has own different availability tools:• Based on ops VO• Can have conflicting results:

Last month IFIC was ATLAS ALPHA SITE ( >90 % availability)But had just 64% ops egi availability due to a config issue


Connectivity• Inter-cloud direct transfers

20

Transfer monitoring


Services

• User Interfaces:– UI00: (LVSDR)

• UI04: SL 5 64 bits• UI05: SL 4 64 bits• UI06: SL 5 64 bits

• Computing Elements (cream-ce) and Worker nodes :– WN (CE02): SL 5 64 bits Glite 3.2 with MPI

and shared home in Lustre– WN (CE03): SL 5 64 bits Glite 3.2 (puppet) – WN (CE05): SL 5 64 bits Glite 3.2 (puppet)

21


Job Distribution at Tier-2• Tier 2 usage in data processing

– More job slots used at Tier2s than at Tier1• Large part of MC production and analysis done at Tier2s

• More ‘digi+reco’ jobs and “group production” at Tier-2s– less weight at Tier-1s

• Production shares to be implemented to limit “group production” jobs at Tier-1, and run at Tier-2s

• Analysis share reduced at Tier-1s

22

PIC TIER-1 – 2012

More Analisys jobs at IFIC TIER 2


Datadisk in tier2

• Tier 2 usage disk space– T2_datadisk ≈ T1_datadisk in volume– T2_datadisk ≈ input for data processing (secondary

replicas)

23

http://bourricot.cern.ch/dq2/accounting/atlas_stats/0/

T2_datadisk

T1_datadisk

20PB

Total Capacity (Usable/Margin)

primary

February ‘12

secondary

Used (according SRM)

Used (according dq2)


For Spanish Sites

24

http://bourricot.cern.ch/dq2/accounting/t2_spacetoken_view/SPAINSITES/datadisk/30/

February ‘12


IFIC Storage resources

• Based in SUN:– X4500 + X4540– Lustre v1.8

– New Disk servers:• SuperMicro, SAS disks, capacity 2 TB

per disk and 10 Gbe connectivity

– Srmv2 (STORM)– 3 x gridftp servers

25


Storage resources

26

Pledges


Storage resources

27


IFIC Lustre Filesystems and Pools

• With the Lustre release 1.8.1, we have added pool capabilities to the installation.• Allows us to partition the HW inside a given Filesystem

– Better data management– Assign determined OSTs to a application/group of users– Can separate heterogeneous disks in the future

CVMFS FOR ATLAS

4 Filesystems with various pools:/lustre/ific.uv.es Read Only on WNs and UI. RW on GridFTP + SRM

/lustre/ific.uv.es/sw. Software: ReadWrite on WNs, UI (ATLAS USES CVMFS)

/lustre/ific.uv.es/grid/atlas/t3 Space for T3 users: ReadWrite on WNs and UI

xxx.ific.uv.es@tcp:/homefs on /rhome type lustre. Shared Home for users and mpi applications: ReadWrite on WNs and UI

• Different T2 / T3 ATLAS pools , and separated

from other Vos• Better Management

and Performance


CERN CVMFS • CVMFS: A caching, http based read-only

filesystem optimised for delivering experiment software to (virtual) machines.

29

http://atlas-install.roma1.infn.it/atlas_install/usage_plots.php


CVMFS at IFIC (+SQUID)

30

• Installed in all our WNs and UIs since September 2011• Easy installation (only 2 configuration files)• 20 GB/repository• There is not a dedicated partition

• Using the same SQUID as frontier (sq5.ific.uv.es)• the squid server is pointing to the public replicas

(CERN, BNL, RAL) • The performance until now is so good.• We are monitoring SQUID via CACTI (SNMP)

Sept’2011Sept’2011

• Reduced job setup time• Better performance for

analysis jobs• Reduced load on Lustre

MDS


Storm SRM server• Access like a local file system, so it can create and control all the data available

in disk with a SRM interface.• Coordinate data transfers, real data streams are transferred with a

gridFTPserver in another physical machine.• Enforce authorization policies defined by the site and the VO.• Developed Authorization plugin to respect local file system with the

corresponding user mappings and ACL's


IFIC Network

Cisco 4500 – core centre infrastructure.

Cisco 6500 – scientific computing infrastructure

Data servers:• Sun with 1GB

connection. Channel bonding tests were made aggregation 2 channels

• SuperMicro with 10 Gbe WNs and GridFTP servers

with 1GB10 Gbe

• Data Network based on gigabyte ethernet. • 10GBe uplink to the backbone network

reach 1Gbit per data server

Recent Upgrade FTP servers to satisfy

requirements for alpha sites


Data Distribution: dynamic data distribution and caching

33


Atlas presentation – Michael Ernst – BNL – LHCONE 12 May 2011, Washington


PandaDynamicDataPlacement (PD2P)

• resources utilization policy evolved during First year of data taking:– “jobs go to data” “data and jobs move to the available CPU

resources”. • Also a dynamic data placement approach has been employed• Tier-1 algorithm

– Primary copy at tier-1 basend on Planned data placement– Secondary copy when data popular, with location based on

pledges• Tier-2 algoritm:

– Jobs submitted to Panda trigger PD2P– Replicates popular datasets to a Tier2 with highest weight

• More details:https://twiki.cern.ch/twiki/bin/viewauth/Atlas/PandaDynamicDataPlacement

35


A further step: caching

• PD2P makes data movement more dynamic and user-driven, but replication of dataset may suffer from other problems for the users:– Latency to finally access the data– Complexity of the tools

• Still works on the idea of datasets replication• Explore the possibility to access to file or subfile

dynamically without explicit replication– Xrootd allows federation of resources and to redirect the client

to the data source.– Shorten latencies by caching in the xrootd server– To work correctly, there has to be efficient event data I/O with

minimal transactions between application and storage36


PD2P in Es-Cloud last month

37

http://panda.cern.ch/server/pandamon/query?mode=pd2p&action=plots

• Es-Cloud Tier 2 sites getting more datasets

• Bit more that Tier-1 PicIFIC 49

ES 166

• EsCloud T2Ds = IFIC and IFAE


User Example

38


Example; Grid & Physics Analysis

39

• Distributed Computing and Data Management Tools based on GRID technologies have been used by the IFIC physicists to obtain their results

• As an example, the Boosted Top candidate presented by M. Villaplana


Distributed Analysis in ATLAS

• ATLAS has a specifically system for Production and Distributed Analysis (PANDA):– Including all ATLAS

requirements– Highly automated– Low manpower– Unifies the different grid

environments (EGI-Glite, OSG and EGI-ARC)

– Monitoring web pages• Reference:

http://panda.cern.ch

40

http://panda.cern.ch/



• For ATLAS users, GRID tools have been developed:– For Data management

• Don Quijote 2 (DQ2)– Data info: name, files, sites, number,…– Download and register files on GRID,..

• ATLAS Metadata Interface (AMI)– Data info: events number, availability– For simulation: generation parameter, …

• Data Transfer Request (DaTri)– Users make request a set of data (datasets) to create replicas in other

sites (under restrictions)– For Grid jobs

• PanDa Client– Tools from PanDa team for sending jobs in a easy way for user

• Ganga (Gaudi/Athena and Grid alliance)– A job management tool for local, batch system and the grid

41


Tier2 and Tier3 examples from Spain

• At IFIC the Tier3 resources are being split into two parts:– Resources coupled to IFIC Tier2

• Grid environment• Use by IFIC-ATLAS users• Resources are idle, used by the

ATLAS community

– A computer farm to perform interactive analysis (proof)

• outside the grid framework

• Reference: – ATL-SOFT-PROC-2011-018

42


Daily user activity in Distributed Analysis

• An example of Distributed Analysis in heavy exotic particles– Input files

– Work flow:

43


Daily user activity in Distributed Analysis• 1) A python script is created where requirements are defined

– Application address,– Input, Output– A replica request to IFIC– Splitting

• 2) Script executed with Ganga/Panda– Grid job is sent

• 3) Job finished successfully, output files are copied in the IFIC Tier3– Easy access for the user

44

Just in two weeks, 6 users for this analysis sent:• 35728 jobs, • 64 sites,• 1032 jobs ran in T2-ES

(2.89%),• Input: 815 datasets• Output: 1270 datasets

Just in two weeks, 6 users for this analysis sent:• 35728 jobs, • 64 sites,• 1032 jobs ran in T2-ES

(2.89%),• Input: 815 datasets• Output: 1270 datasets


User experience

• PD2P is transparent to users, but eventually they learn that it is in action:– “a job was finally sent to a destination that did not

originally had the requested dataset” – “I check later PD2P has copied my original dataset” – “ I just realized because I used dq2 previously to check

where the dataset was”

• Another question is that user datasets are not replicated:– “We see a failure because it is not replicating our

homemade D3PDs”

45


Summary

46


BACKUP SLIDES

47


A TIER 2 in ATLAS

48

Main activities

Main activities


Spanish Tier2 Number(more info: Pepe’s slides)

• The ATLAS Spanish Tier2 (T2-ES) consists in a federation of 3 Spanish Institutions (see Jose’s talk):– IFAE-Barcelona (25%)– UAM- Madrid (25%)– IFIC-Valencia (50%, coordinator)

• The T2-ES represents 5% of the ATLAS resources (between 60-70 T2s):

• References: – J. Phys. Conf. Ser. 219 072046

49


Summary

50


Summary

51


Migration of Scientific Applications to Grid at IFC

52


Migration of Scientific Applications to Grid at IFC

53


LHCONE for ATLAS

54


NETWORK• T2 network

55


For Spanish Sites

56

IFAEIFAE

IFICIFIC

UAMUAM

TIER2s DATADISK-SPAIN SITESTIER2s DATADISK-SPAIN SITES

http://bourricot.cern.ch/dq2/media/T2s/T2s-DATADISK-SPAINSITES.html


Availability• ES-Tier2 availability for ATLAS

57

http://hammercloud.cern.ch/atlas/autoexclusion/?cloud=20&site=


Availability• Hammercloud:

– Distributed Analysis testing system– For avoiding jobs go to problematic sites– Can excluded sites if test jobs are not passed– Reference:

• https://twiki.cern.ch/twiki/bin/view/IT/HammerCloud• ATLAS grid tools are improving day to day

– For instance: automatic jobs for merging output files– https://twiki.cern.ch/twiki/bin/viewauth/ATLAS/AnalysisJobOutput

Merging• ATLAS users can ask to Distributed Analysis Support Team

(DAST, [email protected]):– Problems with her/his jobs– Useful for developers

• Improve the tools and services

58

https://twiki.cern.ch/twiki/bin/view/IT/HammerCloud

https://twiki.cern.ch/twiki/bin/viewauth/ATLAS/AnalysisJobOutputMerging

https://twiki.cern.ch/twiki/bin/viewauth/ATLAS/AnalysisJobOutputMerging



59

References: http://twiki.cern.ch/twiki/bin/viewauth/Atlas/AtlasComputing

http://twiki.cern.ch/twiki/bin/viewauth/Atlas/AtlasComputing


Analysis Efficiency in SeptemberATLAS Tier0 + Tier1s

ANALY*_queues

60


Analysis Efficiency in SeptemberATLAS Tier2s (ANALY*_queues)

61

Evolution of the Atlas data and computing model for a Tier-2 in the EGI infrastructure

Documents

Transcript of Evolution of the Atlas data and computing model for a Tier-2 in the EGI infrastructure