General Documentation

LSF Primer

Lilac Cluster Guide

Juno Cluster Guide

Cloud Resources

Backup Policy on server/node local drives

File lists

Versions Compared

Old Version 12

changes.mady.by.user Lohit Valleru

Saved on

compared with

New Version Current

changes.mady.by.user Joanne Edington

Saved on

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.

...

    • Description : GPFS shared parallel filesystem, not replicated, and not backed up.
    • Purpose: For jobs to read and write compute data from login and compute nodes, default quota size is larger with flexibility to request larger quota.
    • Mount: /data/<lab group>
    • Access: All Lilac nodes, including compute storage and login nodes.
    • Default quota: 5TB 1TB ( Increased/Decreased on request )
    • Snapshots: 7 days of snapshots. ( not backed up ). Can be accessed in /data/.snapshots/<date>/<lab group>
    • Replicated: no

...

    • Description : GPFS shared parallel filesystem, not replicated but will be replicated in near future, and not backed up. Comparatively slower than lilac compute storage.
    • Purpose: To store long term data. Only accessible from login nodes and cannot be accessed from compute nodes.
    • Mount: /warm/<lab group>
    • Access: Only lilac and luna login nodes.
    • Default quota: 5TB 1TB ( Increased/Decreased on request )
    • Snapshots: 7 days of snapshots. ( not backed up ). Can be accessed in /warm/.snapshots/<date>/<lab group>
    • Replicated: no ( will be replicated in near future )

...

    • Description : XFS filesystem, not replicated, and not backed up. Local and not a shared filesystem, slower than GPFS.
    • Purpose: To store local temporary data related to compute jobs. Since this is not a shared filesystem, the temporary data needs to be cleaned up and copied back to shared filesystem after job completion.
    • Mount: /scratch/
    • Access: Only lilac compute nodes.
    • Default quota: No quota and limited to free disk space in /scratch.
    • Snapshots: No snapshots.
    • Replicated: no

How to :

Check Quota for GPFS filesystem:

...

    • Lilac home storage :

      Code Block
      languagebash
      themeMidnight
      firstline1
      titleCommand line
      linenumberstrue
      mmlsquota lilac:home --block-size auto


    • Lilac compute storage : 

      Code Block
      languagebash
      themeMidnight
      firstline1
      titleCommand line
      linenumberstrue
      mmlsquota -j data_<lab group name> lilac --block-size auto
 lilac



    • Lilac warm storage (oscar) :

      Code Block
      languagebash
      themeMidnight
      firstline1
      titleCommand line
      linenumberstrue
      mmlsquota -j warm_<lab group name> oscar --block-size auto oscar



Tip

mmlsquota gives information about quota on number of files too, along with information about block quota.

FilesystemFilesettypeblocksquotalimitin_doubtgrace|filesquotalimitin_doubtgraceRemarks
Filesystem nameFileset namefileset/usr/grpBlocks currently occupiedYour block quotaYour limit for "7 days" beyond quota.

Blocks in doubt that will be counted towards your quota.

Happens when many files are added/deleted recently.

Countdown of 7 days is set once you occupy more blocks than mentioned in quota.
Number of files currently presentYour quota on number of filesYour limit on number of files for "7 days" beyond quota.Number of files in doubt that will be counted towards your quota.Countdown of 7 days is set once you occupy more files than mentioned in quota.


Once the number of blocks or number of files reach the value mentioned in "quota" - Storage system will give 7 days as a grace period, to fill up until the max value mentioned in "limit" is reached. Storage system will not allow any more data to be written when:

  1. The block limit/file limit is reached.
  2. 7 days have passed since the blocks/files have occupied more than "quota". The grace field will show you the number of days left, before which the number of blocks/files need to go less than the value mentioned in "quota".

...

2. Copy files from other clusters:

Info

HAL cluster is outside the firewall, so lilac cannot be accessed directly from HAL cluster

    • SABA/LUNA/LUXJuno: 
      To copy files from other clusters, first ssh -A into the other cluster to forward your keys.

      Code Block
      languagebash
      themeMidnight
      firstline1
      titleCommand line
      linenumberstrue
      ssh -A $USERNAME@$CLUSTER

      We recommend rsync -va to copy files and directories.

      Make note of the source directory/source files and destination directory/files on Lilac and copy them as below:

      Code Block
      languagebash
      themeMidnight
      firstline1
      titleCommand line
      linenumberstrue
      rsync -av --progress $SOURCEPATH lilac:$DESTPATH
      • HAL:
      Remember that the hal cluster is outside the MSKCC network, and does not have access to lilac. 


    • First - Make note of the source directory/source files on HAL and destination directory/files on Lilac:
      To transfer data, ssh into lilac as below :
       Code Block
      languagebash
      themeMidnight
      firstline1
      titleCommand line
      linenumberstrue
      ssh -A $USERNAME@lilac.mskcc.org
      Then pull files from HAL:
       Code Block
      languagebash
      themeMidnight
      firstline1
      titleCommand line
      linenumberstrue
      rsync -av --progress hal:$SOURCEPATH $DESTPATH
       Tip
      • Depending on the size and number of files to copy, you may run multiple rsync commands simultaneously to copy different directories.
      • The HPC private network is faster than the MSKCC campus network, so using short names (lilac, saba, luna, selene, etc.) like lilac will often make transfers faster than using the fully qualified domain names such as lunaname liilac.mskcc.org. This does not apply to hal, though