Launching FLUENT if you are using Microsoft's Compute Cluster Server (CCS)
|
This document assumes that you have installed and configured Microsoft Compute Cluster Server properly and that the compute nodes can access the headnode. If Microsoft Compute Cluster Server is not configured properly then contact Microsoft for support before you attempt to run FLUENT. Launching FLUENT using the Microsoft Job Scheduler You can submit FLUENT jobs using the Microsoft Job Scheduler by using the -ccp flag in the FLUENT startup command. Make sure that you have followed all of the instructions in the document titled Configuring FLUENT Network Parallel - FLUENT 6.3first. Method 1: 1.Open up a command prompt and CD to the directory where your case and data file is located. 2.Type: fluent 3d -ccp headnode -tnprocs (Where headnode) is the name of the headnode. Where -tnprocs is the number of processors you want to use. For example, -t4 would launch FLUENT using 4 available processors on the cluster and submit the job to the Microsoft Job Scheduler. The command would look like the following example. Method 2: 1.Open up a command prompt and browse to your working directory and type: fluent 3d -ccp headnode -tnprocs -jobid=-1 Adding the -jobid=-1 to the startup command will instruct FLUENT to wait until there are nodes available to run the job on and will NOT consume a FLUENT license while it is waiting. As soon as there are nodes available FLUENT will submit the job to the job scheduler. Method 3: Another way to use the Microsoft Job Scheduler is to reserve resources from the scheduler first. After the resources have been allocated you can reuse the allocated resources with any FLUENT session until you have canceled the job. 1.Open up a command prompt and browse to your working directory and type: job new /scheduler:headnode /numprocessors:4 /rununtilcanceled:true Where headnode is the computer name of the headnode and numprocessors is the number of processors you want to allocate. (In the above example you have asked for 4 processors to be allocated). 2.When you are ready to submit the job type: job submit /schedulerheadnode /id:31 (Where 31 in this example is the Microsoft Job Scheduler auto generated ID as shown in the image above). 3.You can monitor the status of the submitted job either by the Microsoft Job Scheduler GUI or from the command line. Method 4 : Run the job in batch mode without showing the FLUENT GUI This method can be used if you have 32-bit client machines and want to run the 64-bit version of FLUENT on a 64-bit Windows cluster. You will need to have a journal file in order to run in batch mode. 1.Open up a command prompt and browse to your working directory and type: job submit /scheduler:headnode /numprocessors:4 /workdir:C:Fluent_Data headnodentbinwin64fluent.exe -t1 -awin64 -pmsmpi -ccp -1 -i journal_file.jou -wait Where Fluent_Data is your working directory. This directory name is just an example. Where journal_file.jou is your actual journal file. 2. ________________________________________ Command Line Viewing Type: job view 31 /scheduler:headnode When the jobs "status" indicates that the job is running, you may start FLUENT with the jobid. For example: fluent 3d -ccp headnode -t4 -jobid=31 The Jobid can be reused over and over again until the job is cancelled by the user. Canceling the FLUENT Job You can cancel the job through the Microsoft Job Scheduler GUI by right-clicking on the job and choosing cancel or from the command line. Command Line Job Canceling Type: job cancel 31 /scheduler:headnode |
||
|