Locked History Actions

Diff for "Computing/LIP_Lisbon_Farm/3_Data_Management"

Differences between revisions 11 and 36 (spanning 25 versions)
Revision 11 as of 2016-12-07 15:49:09
Size: 3360
Editor: jpina
Comment:
Revision 36 as of 2024-03-07 11:37:09
Size: 4925
Editor: martinsj
Comment:
Deletions are marked like this. Additions are marked like this.
Line 1: Line 1:
## page was renamed from Computing/LIP_Lisbon_Farm/Data_Management
Line 4: Line 5:
= File systems available =

 * The users have at there disposal three types of filesystem:
  * A '''common NFS filesystem''' for homes not shared with workernodes
  * A '''lustre filesystem''' for some groups shared filesystem with the workernodes
  * A '''CVMFS read-only filesystem''' for software provision
 * Groups involved in WLCG transfer data using grid technologies can also use the Tier-3 storage areas and dedicated software areas (CVMFS) made available by there communities.

= Access Policy =

 * By default both lustre and nfs individual group areas can be accessed (read only) by users of the same group.

Line 5: Line 19:
 * The fermi machines provide a wide set of filesystems so that users can access their data and applications.
Line 7: Line 20:
 * The available filesystems in login machines are: The '''pauli''' machines provide a wide set of filesystems so that users can access their data and applications.

== NFS Home directories ==

Users home mounts are not shared with workernodes, they can be found only on submission nodes:
Line 10: Line 27:
# df -h
Filesystem Size Used Avail Use% Mounted on
nfs01:/exports/exper-sw 2.8T 2.0T 767G 73% /exper-sw ---> NFS fs for local software
se16:/ams 200G 33M 200G 1% /home/ams ---> NFS fs LIP homes and data
se16:/comp 600G 6.8G 594G 2% /home/comp ---> NFS fs LIP homes and data
se16:/cosmo 600G 8.8G 591G 2% /home/cosmo ---> NFS fs LIP homes and data
se16:/feno 200G 33M 200G 1% /home/feno ---> NFS fs LIP homes and data
se16:/nucria 600G 33M 600G 1% /home/nucria ---> NFS fs LIP homes and data
se16:/pet 200G 33M 200G 1% /home/pet ---> NFS fs LIP homes and data
se16:/sno 200G 8.2G 192G 5% /home/sno ---> NFS fs LIP homes and data
se16:/t3atlas 200G 151G 49G 76% /home/t3atlas ---> NFS fs LIP homes and data
se16:/t3cms 200G 29G 172G 15% /home/t3cms ---> NFS fs LIP homes and data
se17:/x 4.6T 4.4T 165G 97% /x ---> NFS fs LIP ATLAS users
mdt02@tcp:/t3atlas 61T 24T 34T 42% /gstore/t3atlas ---> Lustre FS Tier-3 LIP ATLAS users
mdt02@tcp:/T3CMS 81T 11T 66T 15% /gstore/t3cms ---> Lustre FS Tier-3 LIP CMS users
mdt03@tcp:/calo 72T 62T 6.6T 91% /lstore/calo ---> Lustre FS for ATLAS users
mdt02@tcp:/cmslocal 6.4T 5.6T 541G 92% /lstore/cms ---> Lustre FS for CMS users
mdt03@tcp:/comp 41T 9.0T 30T 24% /lstore/comp ---> Lustre FS for COMP users
mdt03@tcp:/sno 10T 6.4T 3.2T 67% /lstore/sno ---> Lustre FS for SNOW users
se27:/ams 11T 5.9T 4.2T 59% /z/ams ---> NFS FS for AMS users
se27:/comp 11T 3.8T 6.3T 38% /z/comp ---> NFS FS for COMP users
se16:/csys 200G 33M 200G 1% /home/csys ---> Lustre FS for AUGER users
mdt04@tcp:/auger 36T 22T 12T 65% /lstore/auger ---> Lustre FS for AUGER users
mdt04@tcp:/hpclip 6.4T 546M 6.0T 1% /lstore/hpclip ---> Lustre FS for HPC users
mdt04@tcp:/lattes 5.9T 86G 5.5T 2% /lstore/lattes ---> Lustre FS for LATTS users
mdt04@tcp:/pet 461G 115G 323G 27% /lstore/pet ---> Lustre FS for PET users
cvmfs2 20G 17G 3.3G 84% /cvmfs/cms.cern.ch ---> CVMFS FS for CMS users
cvmfs2 20G 6.1G 14G 32% /cvmfs/atlas.cern.ch ---> CVFMS FS for ATLAS users
FILESYSTEM MOUNTED ON SCOPE
se63:/user /user LIP groups
}}}

== NFS Data directories ==

Projects specific data NFS mounts are not shared with workernodes and are found only on submission nodes:

{{{
FILESYSTEM MOUNTED ON SCOPE
se34:/sno /n/sno SNO+ data
se51:/sno /s/sno SNO+ data
se27:/ams /z/ams AMS data
se27:/comp /z/comp COMPASS data
}}}

== LUSTRE Data directories ==

Projects specific data LUSTRE mounts are shared with workernodes:

{{{
FILESYSTEM MOUNTED ON SCOPE
mdt02@tcp:/t3atlas /gstore/t3atlas ATLAS Tier-3
mdt02@tcp:/T3CMS /gstore/t3cms CMS Tier-3
mdt04@tcp:/auger /lstore/auger AUGER
mdt04@tcp:/calo /lstore/calo ATLAS Lisboa
mdt02@tcp:/cmslocal /lstore/cms CMS
mdt03@tcp:/comp /lstore/comp COMP
mdt04@tcp:/lattes /lstore/lattes LATTES
mdt04@tcp:/nucria /lstore/nucria NUCRIA
mdt04@tcp:/pet /lstore/pet PET
mdt10@tcp:/sno /lstore/sno SNO PLUS
mds22@tcp:/titan /lstore/titan ATLAS
mds-feno@tcp:/feno /lstore/feno Phenomenology
mds-share@tcp:/share /share Shared with Atlas, Auger, CMS, Compass, NUCRIA, SPAC and SWGO
}}}

== CVMFS Software provision ==

The '''CVMFS''' is a read-only filesystem with cache local to clients optimal for software provision:

{{{
FILESYSTEM MOUNTED ON SCOPE
cvmfs2 /cvmfs/cms.cern.ch CMS VO
cvmfs2 /cvmfs/atlas.cern.ch ATLAS VO
cvmfs2 /cvmfs/sw.el7 LIP
Line 41: Line 76:

==
= Important Disclaimer ===
= Important Disclaimer =
Line 46: Line 80:

= Access your data by SSHFS =

== Install sshfs package ==

On Ubuntu/debian:
{{{
# sudo apt-get install sshfs
}}}

On RHEL/CentOS/Fedora:
{{{
# sudo yum install fuse-sshfs
}}}


== Create a local directory ==
{{{
# mkdir ~/homeNCG
}}}

== Mount your remote folder ==
{{{
# sshfs martinsj@fermi.ncg.ingrid.pt: ~/homeNCG
}}}

== When you're done, you can unmount it ==
{{{
# fusermount -u ~/homeNCG
}}}

== .bashrc tunning ==

In case you're dealing with very long paths, as a suggestion, you can add to your ~/.bashrc file the following:

{{{
alias mfermi='f(){ dir=$1 ; [ -n "$dir" ] || dir=homeNCG ; [ -d ~/$dir ] || mkdir -p ~/$dir ; sshfs fermi.ncg.ingrid.pt: ~/$dir ; unset -f f; }; f'
alias ufermi='f(){ dir=$1 ; [ -n "$dir" ] || dir=homeNCG ; [ -d ~/$dir ] && fusermount -u ~/$dir ; [ -d ~/$dir ] && rmdir ~/$dir ; unset -f f; }; f'

alias mncg='f(){ dir=$1 ; [ -n "$dir" ] && ldir=`basename $dir` ; [ -d ~/$ldir ] || mkdir -p ~/$ldir ; [ -n "$dir$ldir" ] && sshfs fermi.ncg.ingrid.pt:$dir ~/$ldir ; unset -f f; }; f'
alias uncg='f(){ dir=$1 ; [ -n "$dir" ] && ldir=`basename $dir` ; ldir=`echo $ldir ; [ -d ~/$ldir ] && fusermount -u ~/$ldir ; [ -d ~/$ldir ] && rmdir ~/$ldir ; unset -f f; }; f'

alias mcalo='f(){ [ -d lcalo ] || mkdir ~/lcalo ; sshfs fermi.ncg.ingrid.pt:/lstore/calo ~/lcalo ; unset -f f; }; f'
alias ucalo='f(){ [ -d ~/lcalo ] && fusermount -u ~/lcalo ; [ -d ~/$ldir ] && rmdir ~/lcalo ; unset -f f; }; f'
}}}

This is how you can use it:

{{{
$ mfermi homeNCG
$ df
Filesystem 1K-blocks Used Available Use% Mounted on
fermi.ncg.ingrid.pt: 209612800 3504112 206108688 2%
/home/martinsj/homeNCG
$ ufermi homeNCG

$ mncg /lstore/calo
...
$ uncg /lstore/calo

}}}

File systems available

  • The users have at there disposal three types of filesystem:
    • A common NFS filesystem for homes not shared with workernodes

    • A lustre filesystem for some groups shared filesystem with the workernodes

    • A CVMFS read-only filesystem for software provision

  • Groups involved in WLCG transfer data using grid technologies can also use the Tier-3 storage areas and dedicated software areas (CVMFS) made available by there communities.

Access Policy

  • By default both lustre and nfs individual group areas can be accessed (read only) by users of the same group.

Directories and filesystems

The pauli machines provide a wide set of filesystems so that users can access their data and applications.

NFS Home directories

Users home mounts are not shared with workernodes, they can be found only on submission nodes:

FILESYSTEM            MOUNTED ON            SCOPE
se63:/user            /user                 LIP groups

NFS Data directories

Projects specific data NFS mounts are not shared with workernodes and are found only on submission nodes:

FILESYSTEM            MOUNTED ON            SCOPE
se34:/sno             /n/sno                SNO+ data
se51:/sno             /s/sno                SNO+ data
se27:/ams             /z/ams                AMS data
se27:/comp            /z/comp               COMPASS data

LUSTRE Data directories

Projects specific data LUSTRE mounts are shared with workernodes:

FILESYSTEM            MOUNTED ON            SCOPE
mdt02@tcp:/t3atlas    /gstore/t3atlas       ATLAS Tier-3
mdt02@tcp:/T3CMS      /gstore/t3cms         CMS Tier-3
mdt04@tcp:/auger      /lstore/auger         AUGER
mdt04@tcp:/calo       /lstore/calo          ATLAS Lisboa
mdt02@tcp:/cmslocal   /lstore/cms           CMS
mdt03@tcp:/comp       /lstore/comp          COMP
mdt04@tcp:/lattes     /lstore/lattes        LATTES
mdt04@tcp:/nucria     /lstore/nucria        NUCRIA
mdt04@tcp:/pet        /lstore/pet           PET
mdt10@tcp:/sno        /lstore/sno           SNO PLUS
mds22@tcp:/titan      /lstore/titan         ATLAS
mds-feno@tcp:/feno    /lstore/feno          Phenomenology
mds-share@tcp:/share  /share                Shared with Atlas, Auger, CMS, Compass, NUCRIA, SPAC and SWGO

CVMFS Software provision

The CVMFS is a read-only filesystem with cache local to clients optimal for software provision:

FILESYSTEM            MOUNTED ON            SCOPE
cvmfs2                /cvmfs/cms.cern.ch    CMS VO
cvmfs2                /cvmfs/atlas.cern.ch  ATLAS VO
cvmfs2                /cvmfs/sw.el7         LIP

Important Disclaimer

  • Manipulating huge sets of small files generates performance degradation issues in /lustre due to the lock management. Therefore, you should not
    • Compile anything under /lustre

    • Store and access databases under /lustre

Access your data by SSHFS

Install sshfs package

On Ubuntu/debian:

# sudo apt-get install sshfs

On RHEL/CentOS/Fedora:

# sudo yum install fuse-sshfs

Create a local directory

# mkdir ~/homeNCG

Mount your remote folder

# sshfs martinsj@fermi.ncg.ingrid.pt: ~/homeNCG

When you're done, you can unmount it

# fusermount -u ~/homeNCG

.bashrc tunning

In case you're dealing with very long paths, as a suggestion, you can add to your ~/.bashrc file the following:

alias mfermi='f(){ dir=$1 ; [ -n "$dir" ] || dir=homeNCG ; [ -d ~/$dir ] || mkdir -p ~/$dir ; sshfs fermi.ncg.ingrid.pt: ~/$dir ;  unset -f f; }; f'
alias ufermi='f(){ dir=$1 ; [ -n "$dir" ] || dir=homeNCG ; [ -d ~/$dir ] && fusermount -u ~/$dir ; [ -d ~/$dir ] && rmdir ~/$dir ;  unset -f f; }; f'

alias mncg='f(){ dir=$1 ; [ -n "$dir" ] && ldir=`basename $dir` ; [ -d ~/$ldir ] || mkdir -p ~/$ldir ; [ -n "$dir$ldir" ] && sshfs fermi.ncg.ingrid.pt:$dir ~/$ldir ;  unset -f f; }; f'
alias uncg='f(){ dir=$1 ; [ -n "$dir" ] && ldir=`basename $dir` ; ldir=`echo $ldir ; [ -d ~/$ldir ] && fusermount -u ~/$ldir ; [ -d ~/$ldir ] && rmdir ~/$ldir ;  unset -f f; }; f'

alias mcalo='f(){ [ -d lcalo ] || mkdir ~/lcalo ; sshfs fermi.ncg.ingrid.pt:/lstore/calo ~/lcalo ;  unset -f f; }; f'
alias ucalo='f(){ [ -d ~/lcalo ] && fusermount -u ~/lcalo ; [ -d ~/$ldir ] && rmdir ~/lcalo ;  unset -f f; }; f'

This is how you can use it:

$ mfermi homeNCG
$ df
Filesystem           1K-blocks    Used Available Use% Mounted on
fermi.ncg.ingrid.pt: 209612800 3504112 206108688   2%
/home/martinsj/homeNCG
$ ufermi homeNCG

$ mncg /lstore/calo
...
$ uncg /lstore/calo