[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [HTCondor-users] Negotiator fails to match the jobs even when -better-analyze succeeds



Hi Christoph,

 ÂI tried with one of the jobs,Â
condor_q -better-analyze -reverse -machine t3btch001.mit.edu 115253.5

It shows as below(for one of the slots).

 What does it mean when it mathes the slot requirements but not the job requirements?

Sincerely,
Zhangqier Wang
-- Slot: slot1_6@xxxxxxxxxxxxxxxxx : Analyzing matches for 1 Jobs in 1 autoclusters
The Requirements _expression_ for this slot is
  (START) && (IsValidCheckpointPlatform) &&
      (WithinResourceLimits)
 START is
  (regexp(".*t3btch[0-9]*\\.mit\\.edu$",Name,"i") ||
         ((LoadAvg - CondorLoadAvg) <= 3.000000000000000E-01) ||
         (State != "Unclaimed" &&
        State != "Owner"))
 IsValidCheckpointPlatform is
  (TARGET.JobUniverse isnt 1 ||
      ((MY.CheckpointPlatform isnt undefined) &&
        ((TARGET.LastCheckpointPlatform is MY.CheckpointPlatform) ||
          (TARGET.NumCkpts == 0))))
 WithinResourceLimits is
  (ifThenElse(TARGET._condor_RequestCpus isnt undefined,MY.Cpus > 0 &&
    TARGET._condor_RequestCpus <= MY.Cpus,ifThenElse(TARGET.RequestCpus isnt undefined,MY.Cpus > 0 &&
     TARGET.RequestCpus <= MY.Cpus,1 <= MY.Cpus)) &&
   ifThenElse(TARGET._condor_RequestMemory isnt undefined,MY.Memory > 0 &&
    TARGET._condor_RequestMemory <= MY.Memory,ifThenElse(TARGET.RequestMemory isnt undefined,MY.Memory > 0 &&
     TARGET.RequestMemory <= MY.Memory,false)) &&
   ifThenElse(TARGET._condor_RequestDisk isnt undefined,MY.Disk > 0 &&
    TARGET._condor_RequestDisk <= MY.Disk,ifThenElse(TARGET.RequestDisk isnt undefined,MY.Disk > 0 &&
     TARGET.RequestDisk <= MY.Disk,false)))
This slot defines the following attributes:
  CheckpointPlatform = "LINUX X86_64 3.10.0-1127.19.1.el7.x86_64 normal N/A ssse3 sse4_1"
  CondorLoadAvg = 0.0
  Cpus = 1
  Disk = 608514
  LoadAvg = 0.0
  Memory = 128
  Name = "slot1_6@xxxxxxxxxxxxxxxxx"
  State = "Claimed"
Job 115253.5 has the following attributes:
  TARGET.JobUniverse = 5
 ÂÂTARGET.NumCkpts = 0
  TARGET.RequestCpus = 1
  TARGET.RequestDisk = 3
  TARGET.RequestMemory = 1
The Requirements _expression_ for this slot reduces to these conditions:
   ÂClusters
Step  ÂMatched ÂCondition
----- Â-------- Â---------
[8] Â Â Â Â Â 1 ÂIsValidCheckpointPlatform
[10] Â Â Â Â Â1 ÂWithinResourceLimits
slot1_6@xxxxxxxxxxxxxxxxx: Run analysis summary of 1 jobs.
  0 (0.00 %) match both slot and job requirements.
  1 match the requirements of this slot.
  0 have job requirements that match this slot.
Â


On Wed, Sep 8, 2021 at 1:22 AM <christoph.beyer@xxxxxxx> wrote:
Hi,

it seems the job conditions are not met by any slot, try:

condor_q -better-analyze 112848.0 -reverse -machine <fqdn>

to get an idea of what is going 'wrong' ...

Best
christoph


--
Christoph Beyer
DESY Hamburg
IT-Department

Notkestr. 85
Building 02b, Room 009
22607 Hamburg

phone:+49-(0)40-8998-2317
mail: christoph.beyer@xxxxxxx


Von: wangzqe@xxxxxxxxx
An: "htcondor-users" <htcondor-users@xxxxxxxxxxx>
Gesendet: Dienstag, 7. September 2021 22:08:10
Betreff: [HTCondor-users] Negotiator fails to match the jobs even whenÂÂÂÂÂÂÂÂ-better-analyze succeeds

Dear condor experts,

Dear condor experts,

Â

 ÂI have encountered a condor error, which the submitted job finds running slots according to "condor_q -better-analyze" but Negotiator fails to find the match. This happens when I tried to set up the bosco, but the error seems to come from the condor insteadÂof bosco. The info from the condor_q -better-analyze, and a cycle of the negotiator is shown below.Â


 ÂDo you know what is the problem? The condor version is 8.8.1Â


Sincerely,

Zhangqier Wang


condor_q -better-analyze 112848.0 -name t3home000.mit.edu

The Requirements _expression_ for job 112848.000 reduces to these conditions:

    ÂSlots
Step  Matched Condition
-----Â --------Â ---------
[0]Â Â Â Â Â Â5Â BOSCOCluster == "bosco_tier3@xxxxxxxxxxxxxxxxx/condor"
[2]Â Â Â Â Â Â5Â Arch == "X86_64"
[5]Â Â Â Â Â Â5Â TARGET.OpSys == "LINUX"
[7]Â Â Â Â Â Â5Â TARGET.Disk >= RequestDisk
[9]Â Â Â Â Â Â5Â TARGET.Memory >= RequestMemory
[11]Â Â Â Â Â 5Â TARGET.HasFileTransfer


No successful match recorded.
Last failed match: Wed Aug 25 18:43:43 2021

Reason for last match failure: no match foundÂ

112848.000: Run analysis summary ignoring user priority. Of 4 machines,
   0 are rejected by your job's requirements
   0 reject your job because of their own requirements
   0 match and are already running your jobs
   0 match but are serving other users
   4 are able to run your job


NegotiatorLog:

08/25/21 18:44:43 ---------- Started Negotiation Cycle ----------
08/25/21 18:44:43 Phase 1:Â Obtaining ads from collector ...
08/25/21 18:44:43Â ÂGetting startd private ads ...
08/25/21 18:44:43Â ÂGetting Scheduler, Submitter and Machine ads ...
08/25/21 18:44:43Â ÂSorting 11 ads ...
08/25/21 18:44:43 Got ads: 11 public and 0 private
08/25/21 18:44:43 Public ads include 1 submitter, 5 startd
08/25/21 18:44:43 Phase 2:Â Performing accounting ...
08/25/21 18:44:43 Phase 3:Â Sorting submitter ads by priority ...
08/25/21 18:44:43 Starting prefetch round; 1 potential prefetches to do.
08/25/21 18:44:43 Starting prefetch negotiation for analysis.wangzqe@xxxxxxx.
08/25/21 18:44:43Â Â ÂGot NO_MORE_JOBS;Â schedd has no more requests
08/25/21 18:44:43 Prefetch summary: 1 attempted, 1 successful.
08/25/21 18:44:43 Phase 4.1:Â Negotiating with schedds ...
08/25/21 18:44:43 0 seconds so far for this submitter
08/25/21 18:44:43 0 seconds so far for this schedd
08/25/21 18:44:43Â Â ÂRequest 112848.00000: autocluster 413 (request count 1 of 50)
08/25/21 18:44:43Â negotiateWithGroup resources used submitterAds length 0
08/25/21 18:44:43 ---------- Finished Negotiation Cycle ----------

_______________________________________________
HTCondor-users mailing list
To unsubscribe, send a message to htcondor-users-request@xxxxxxxxxxx with a
subject: Unsubscribe
You can also unsubscribe by visiting
https://lists.cs.wisc.edu/mailman/listinfo/htcondor-users

The archives can be found at:
https://lists.cs.wisc.edu/archive/htcondor-users/
_______________________________________________
HTCondor-users mailing list
To unsubscribe, send a message to htcondor-users-request@xxxxxxxxxxx with a
subject: Unsubscribe
You can also unsubscribe by visiting
https://lists.cs.wisc.edu/mailman/listinfo/htcondor-users

The archives can be found at:
https://lists.cs.wisc.edu/archive/htcondor-users/