General Documentation

LSF Primer

Lilac Cluster Guide

Juno Cluster Guide

Cloud Resources

Backup Policy on server/node local drives

File lists

Skip to end of metadata
Go to start of metadata

You are viewing an old version of this page. View the current version.

Compare with Current View Page History

« Previous Version 20 Next »

Why can’t my job run now?

Once you submit your job to LSF using bsub,  it enters the PENDING sate. You can see all your pending jobs with

bjobs -p 


You can see the status of a particular job with its JobID. Look for PENDING REASONS: in the output.

bjobs -p3 -l <jobid>

....

PENDING REASONS:

Job dependency condition not satisfied;

.....

It can be difficult to interpret the PENDING REASONS that LSF in the bjobs output.  The cluster may just be very busy. You can see the cluster activity at https://hpc-grafana.mskcc.org/

Other LSF commands such as bhosts, lshost and lshost -gpu will give you current information about the available nodes and resources on the command line. You can also use RTM to view LSF details as the guest user at  http://lila-rtm01.mskcc.orgg/cacti/index.php and http://juno-rtm01.mskcc.org/cacti/index.php

Things to Check: 

  • Typos in your bsub command.
  • Any requested GPU models exist.  lshost -gpu will list them with the correct syntax.
  • The requested memory requirement (-R rusage[mem=4]) is in GB (gigabytes) and is PER SLOT (-n) and not per job.
  • Make sure that you are in the SLA (Service Level Agreement) for any nodes that you specifically request.
  • Your job must be able to finish before any scheduled downtime reservation.

The more resources that you request, the longer it will take for the LSF accumulate the resources to satisfy them.  Jobs which request resources that the cluster does not possess will remain in the pending state indefinitely.  The maximum walltime on lilac is 7 days and on Juno is 31 days. Jobs that are less than 6 hours can run on any node. But those longer than 6 hours can only run on nodes with SLA or on a subset of the shared nodes.


Examples of different  pending reasons and how to check for them.

  1. Requested CPUs are not available for requested walltime. Cluster is busy.

    The job has been submitted to the ls03 host. ls03 doesn't have 30 free slots.


    bjobs -p3 -l 1135202


    Job <1135202>, User <sveta>, Project <default>, Application <default>, Service

                         Class <lgSC>, Status <PEND>, Queue <cpuqueue>, Job Priorit

                         y <12>, Command <sleep 200000>, Share group charged </svet

                         a>, Esub <memlimit>

    Fri May 14 15:32:55: Submitted from host <lilac-ln02>, CWD <$HOME>, 30 Task(s),

                          Specified Hosts <ls03>;

    Fri May 14 15:32:55: Reserved <30> job slots on host(s) <30*ls03> for <30> tasks;

    Fri May 21 05:11:04: Job will start no sooner than indicated time stamp;

    PENDING REASONS:

    Candidate host pending reasons (1 of 120 hosts):

       Affinity resource requirement cannot be met because there are not enough processor units to satisfy the job affinity request: ls03;


    Non-candidate host pending reasons (119 of 120 hosts):

       Not specified in job submission: lx10, lx11, lx12, lx13, lx14, boson, lt01, lt02, lt03, lt04, lt05, lt06, lt07, lt08, lt09, ld01, ld02,

                         ld03, ld04, ld05, ld07, lg01, lg02, lg03, lg05, lg06, lt0, lt11, lt12, lt13, lt14, lt15, lt17, lt18, lt19, lp01,

                         lp03, lp05, lp06, lp07, ls01, lp35, ls05, ls06, ls07, lv01, ls08, ls09, lt20, ly01, lt21, ly02, lt22, ly04, ly05, ly06, ly07, ly08, ly09, lp10, lp11, lp12, lp14, li01, lp16,

                         lp17, lp18, ls11, ls12, ls13,ls14, ls15, ls16, ls17, ls18, lp20, lu01, lu02, lu03, lp23, lu04, lp24, lu05, lp25, lu06, lu07, lp27, lx01, lu08, lu09, lx03, lx04, lx05, lx07, lx08, lx09, lu10, lp30, lp31,

                         lp33, lp34;

       Load information unavailable: lw01, lw02, ld06, lt16, lp04, lp09, ly03, ls10, lp19, lp26, lx06, lp32;

       Closed by LSF administrator: lg04, ls02, ls04, lx02;


  2. Requested RAM(memory) is not available for requested walltime. 



  3. Requested RAM(memory) doesn't exist on cluster per host. The output from bjobs won't tell directly this reason.  

    >bjobs -p3 -l …

    Tue Sep 8 16:05:23: Submitted from host ,

    CWD <$HOME>, 4 Task(s), Requested Resources <rusage[mem=200]>;

    PENDING REASONS: Candidate host pending reasons (99 of 123 hosts): Resource limit defined on host(s) and/or host group has been reached (Resource: mem, Limit Name: limit11, Limit Value: 95): lt15, lt17,lt18, lt19, lx14….

    Job's requirements for resource reservation not satisfied (Resource: mem): l x10, lx12, lx13, boson, lt05, lt08, lt09, lx08, lx07…. Host is reserved to honor SLA guarantees: lp34, lp32, lp01, lp03, lp05, lp06…..

    Non-candidate host pending reasons (24 of 123 hosts):

    Not specified in job submission: li01, lv01...

    Load information unavailable: lp21, ls18, lp26, ls10, lp09, lp08, lg05, ld06

    Closed by LSF administrator: lu04, lu05, ls05, lx09, lw02, lw01;

    MEMLIMIT 200 G

    RESOURCE REQUIREMENT DETAILS: Combined: select[(healthy=1) && (type == local)] order[!-slots:-maxslots] rusa ge[mem=200.00] span[hosts=1] same[model] affinity[thread(1 )*1]</rusage[mem=200]>


    This job won’t run on Lilac cluster, because it requested 4x200=800GB of RAM on the same host span[hosts=1]

    There is no host with 800GB on Lilac in cpuqueue.

    Please, check resources:

    >lshosts HOST_NAME type model cpuf ncpus maxmem maxswp

    ls01 X86_64 GTX1080 60.0 72 512G ..

    To check limits on resources:

    >bresource

    Begin Limit NAME = limit11 QUEUES = cpuqueue PER_HOST = ls-gpu/ lt-gpu/ lg-gpu/ lu-gpu/ lx-gpu/ lw-gpu/ ly-gpu/ SLOTS = 68 MEM = 95% ngpus_physical = 0 End Limit

  4. Requested GPUs are not available for requested walltime. 

    bjobs -p3 -l…..

    #BSUB -n 1;#BSUB -gpu 'num=1';#BSUB -R 'span[ptile=1] rusage[mem=30]';#BSUB -q gpuqueue;

    PENDING REASONS:

    Candidate host pending reasons (92 of 123 hosts):

    Job's requirements for resource reservation not satisfied (Resource: ngpus_physical): lx12, lx14, lt01, lt02, lt03, lt04, lt05, lt07, lt08, lt09, lu10, lx05, lx04, lx03, lg02, lu08, lt12, lt19...

    Affinity resource requirement cannot be met because there are not enough processor units to satisfy the job affinity request: lt10, lt11, lx10, lt13, lt14…

    Host is reserved to honor SLA guarantees: lp31, lp01, lp03, lp04, lp05, lp06, lp07, lp27, lp33, lp30, lp34, lp25, lp24, lp35, lp10… Non-candidate host pending reasons (32 of 123 hosts): J

    ob's resource requirements not satisfied: lu02, ls13, lv01, lg06, ld07, ld05. Load information unavailable: ls18, lp21, ls10, lp26, lp09, lp08, lg05, ld06 Closed by LSF administrator: lu04, lu05, ls05, lx09, lw02, lw01;

    Not enough GPUs on the hosts: ly03, lx01, lx02, lx06, lx11;

    ESTIMATION: Tue Sep 8 17:00:21:

    Started simulation-based estimation; Tue Sep 8 17:00:39: Simulated job start time on host(s) <1*lt03>


    This job is waiting for mainly gpu resources to be available in Lilac cluster.

    Estimated start time is :

    Simulated job start time on host(s) <1*lt03>

    bhosts -l lt03 HOST lt03 STATUS CPUF JL/U MAX NJOBS RUN SSUSP USUSP RSV DISPATCH_WINDOW ok 60.00 - 72 4 4 0 0 0 -

    CURRENT LOAD USED FOR SCHEDULING: r15s r1m r15m ut pg io ls it tmp swp mem slots ngpus Total 0.0 0.0 0.0 8% 0.0 19 1 76 48.7G 0G 269G 68 4.0 Reserved 0.0 0.0 0.0 0% 0.0 0 0 0 0G 0G 22G - 0.0 ngpus_physical healthy gpu_shared_avg_ut gpu_shared_avg_mut Total 0.0 1.0 44.0 1.0 Reserved 4.0 0.0 0.0 0.0

  5. GPU type doesn't exist on cluster.  

    > bjobs -p3 -l ..

    Tue Sep 8 16:01:28: Submitted from host , CWD <$HOME>,

    Requested Resources <select[gpu_model0=='geforcegtx1000']>, Requested GPU;

    PENDING REASONS: Candidate host pending reasons (0 of 123 hosts).

    Non-candidate host pending reasons (123 of 123 hosts):

    Job's resource requirements not satisfied: lp35, lx10, lx11, lx12, lx13, lx14, boson, lt01, lt02, lt03, lt04, lt05, lt06, lt07, lt08 …..

    Not specified in job submission: ld01, ld02, ld03, ld04, ld05, ld07, lv01, l i01, lila-sched01, lila-sched02;

    Load information unavailable: ld06, lg05, lp08, lp09, ls10, ls18, lp21, lp26

    Closed by LSF administrator: lw01, lw02, ls05, lu04, lu05, lx09;

    RUNLIMIT 10.0 min</select[gpu_model0=='geforcegtx1000']>


    This job won’t run because the gpu_model0 is not correct in bsub and this resource is not available on Lilac cluster :

    Candidate host : 0

    Correct name is GeForceGTX1080

    >lshosts -gpu

    HOST_NAME gpu_id gpu_model gpu_driver gpu_factor numa_id ls01 0

    GeForceGTX1080 440.33.01 6.1 0 1

    GeForceGTX1080 440.33.01 6.1 0 2

    GeForceGTX1080 440.33.01 6.1 1 3

    GeForceGTX1080 440.33.01 6.1 1

  6. Nodes are in system level reservation used for rolling upgrade or for scheduling cluster level downtime.

    bjobs -p3 -l ...


    Job <1117724>, User <sveta>, Project <default>, Application <default>, Queue <cpuqueue>, Job Priority <12>, Command <sleep 200000>, Esub <memlimit>

    Wed May 12 16:36:49: Submitted from host <lilac-ln02>, CWD </etc/security/limits.d>, 2 Task(s), Specified Hosts <lx10>;

    PENDING REASONS:

    Candidate host pending reasons (1 of 120 hosts):

       Not enough slots or resources for whole duration of the job: lx10;

    Non-candidate host pending reasons (119 of 120 hosts):

       Not specified in job submission: lp35, lx11, lx12, lx13, lx14, boson, lt01, lt02, lt03, lt04, lt05, lt06, lt07, lt08, lt09, ld01, ld02

                         ........


  7. Nodes are reserved under SLA.  




When will my job start to run?

bjobs -l <jobid>

Check  for“ESTIMATION” in the output

Details forthcoming


Why did my job exit abnormally?

bhist -l JID

bhist -n 0 -l JID

Details forthcoming