Hi Support,
I have recently finished a scan of  scratch. We are currently using version
2.5.1-1 on a lustre 1.8 filesystem. I am running an rbh-find to get a list
of files older than 90 days. After 15 minutes rbh-find gets stuck and does
not produce any ouput. I am not so sure why it gets stuck. I don't see any
error on the robinhood log files.This is the first time it happens to me.
Below are the commands executed for rbh-find

1. nohup rbh-find -f /etc/robinhood.d/tmpfs/lustre.conf -nobulk -type f
-atime +90d -ls > purge_list.txt &
2. nohup rbh-find -f /etc/robinhood.d/tmpfs/lustre.conf -type f -atime +90d
-ls > purge_list.txt &
3. rbh-find -f /etc/robinhood.d/tmpfs/lustre.conf -type f -atime +90d -ls

Command used to scan lustre filesytem:
nohup robinhood -S -O -f /etc/robinhood.d/tmpfs/lustre.conf &

I have also attached my lustre.conf file.

Regards,

-- 

*Wissam Ali*HPC System Administrator
Office Tel (UAE): +971-2-628-4751
Mobile Tel (UAE): +971-50-106-9689
Time Zone: GMT+4hrs
Weekends: Friday + Saturday
For HPC support please create a ticket at https://nyu.service-now.com

NYU Abu Dhabi, Saadiyat Campus
Computational Research Building A2
P.O. Box 129188
Abu Dhabi, United Arab Emirates
General
{

   fs_path       = "/scratch";
   fs_type       = lustre;
   check_mounted = true;
}

Log
{

   log_file    = "/var/log/robinhood/lustre_fs.log";
   report_file = "/var/log/robinhood/reports.log";
   alert_file  = "/var/log/robinhood/alerts.log";
   debug_level = EVENT;
}

ListManager
{
   commit_behavior = transaction;
   MySQL
   {
      server = localhost;
      socket = /state/partition1/mysql/mysql.sock;
      db     = robinhood_lustre;
      user   = robinhood;
      password_file = /etc/robinhood.d/.dbpassword;
   }

}

# Entry Processor configuration

EntryProcessor
{

    # nbr of worker threads for processing pipeline tasks
    nb_threads = 8 ;


    # Max number of operations in the Entry Processor pipeline.
    # If the number of pending operations exceeds this limit,
    # info collectors are suspended until this count decreases

    max_pending_operations = 1000 ;

   # Optionnaly specify a maximum thread count for each stage of the pipeline:
   # <stagename>_threads_max = <n> (0: use default)
   # STAGE_GET_FID_threads_max = 8 ;
   # STAGE_GET_INFO_DB_threads_max     = 8 ;
   # STAGE_GET_INFO_FS_threads_max     = 8 ;
   # STAGE_REPORTING_threads_max       = 8 ;
   # STAGE_DB_APPLY_threads_max        = 8 ;

   # if set to FALSE, classes will only be matched
   # at policy application time (not during a scan or reading changelog)
   #match_classes = TRUE;
}

# FS Scan configuration

FS_Scan
{
   # number of threads used for scanning the filesystem
   nb_threads_scan        =     8 ;
}

db_update_policy
{

   fileclass_update = always;
}


Purge_Trigger
{
   trigger_on         = periodic;
   check_interval     = 7day;
}

rmdir_policy
{
   # Remove directories that have been empty for more than 30 days
   age_rm_empty_dirs   = 30d;

   # don't remove dirs that owns to 'Reference Genomes' or whose depth < 2
   Ignore
   {
      depth < 2 or
      tree == "/scratch/hendra" or
      tree == "/scratch/benoit" or
      tree == "/scratch/jonarbo" or
      tree == "/scratch/stp2" or
      tree == "/scratch/Reference_Genomes" or
      tree == "/scratch/rse231/rosetta_dev_alt" or
      type == symlink
   }
}


Purge_Policies
{
   Ignore
   {
      last_access <= 90d or
      tree == "/scratch/hendra" or
      tree == "/scratch/beniot" or
      tree == "/scratch/jorge" or
      tree == "/scratch/Reference_Genomes" or
      tree == "/scratch/rse231/rosetta_dev_alt" or
      type == symlink
   }

   Policy default
   {
      condition
      {
         Last_access > 90d
      }
   }

}

# Resource Monitor configuration

Purge_Parameters
{
   # nbr of thread for performing purge operations
   nb_threads_purge      = 8 ;
   post_purge_df_latency = 1min ;

   # queue size (for leveraging purge threads load)
   purge_queue_size      = 4096 ;

   # Limit the size of database result sets (save memory)
   db_result_size_max    = 10000 ;
}

# Directory Remover configuration

Rmdir_Parameters
{
    # Interval for performing empty directory removal
    runtime_interval = 12h ;

    # Number of threads for performing rmdir operations
    nb_threads_rmdir = 8 ;

    # Queue size (for leveraging rmdir threads load)
    rmdir_queue_size = 256 ;

}
------------------------------------------------------------------------------
Don't Limit Your Business. Reach for the Cloud.
GigeNET's Cloud Solutions provide you with the tools and support that
you need to offload your IT needs and focus on growing your business.
Configured For All Businesses. Start Your Cloud Today.
https://www.gigenetcloud.com/
_______________________________________________
robinhood-support mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/robinhood-support

Reply via email to