You can use qlogin on the HPC cluster systems system to get an interactive SGE session. Qlogin will use the SGE scheduler to select the next available host on the cluster and mark the slots as active as in any other job. It can select hosts based on complexes, etc. just like the qsub command can, including selecting parallel environments. This can be useful for development and prototyping to get an environment on identical hardware to what your production job will run on. Some examples of this would be
...
| Info |
|---|
It is possible to run X11 programs via qlogin. First, log in to to the cluster with X11 forwarding enabled ssh -Y neonargon.hpc.uiowa.edu Then, launch your qlogin session. Once it is established then you can run programs that need X11. This is likely only to be usable from an on-campus connection for performance reasons. If you use FastX then X11 forwarding is already in place. |
It is important to remember that a qlogin job is just like any other job that is submitted via SGE. You can request resources in exactly the same way, including parallel environments with the appropriate number of slots. However, in the end, the qlogin session is an ssh session connection to one of the compute nodes. This means that the environment that the user is in at the shell prompt is a "fresh" environment. None of the special SGE variables that are used during a normal batch job are present in the qlogin environment. Probably the most important of these is the $PE_HOSTFILE environment variable that contains the list of hosts selected by SGE to be used for a parallel job. To be clear, the hostfile created by SGE is still created, but the environment variable that points to it is not present in the environment of the interactive session.
...
| No Format |
|---|
local configuration neonargon-login-0-1.local not defined - using global configuration Your job 665450 ("QLOGIN") has been submitted waiting for interactive job to be scheduled ... Your interactive job 665450 has been successfully scheduled. Establishing builtin session to host compute-3-41.local ... |
...
These are the hosts, and the number of slots on each host, that have been allocated by SGE. It is up to the user you to make sure that any mpi job started in the qlogin session only uses these hosts, with the appropriate slot counts. In a batch job, openmpi detects the SGE environment and gets the total slots, hosts, and slots per host from the SGE environment. Since a qlogin session is not an SGE environment, this task must be done by the user. The above SGE hostfile must be converted to a format that openmpi can use. The following command will do this for openmpi:
...
Also, while the environment can be passed to hosts via the '-V' flag to qsub in a batch job, that does not apply to qlogin sessions. Thus, the user you must make sure to get the necessary environment variables passed to every node that will be used in the computation. OpenMPI provides a mechanism to do this with the '-x <env>' flag.
...
| Info | ||
|---|---|---|
| ||
Note that if you happen to request resources that are unavailable, or to which you do not have access (such as an Investor queue to which you are not a member), you may see a message such as the following: Your job 3747412 ("QLOGIN") has been submittedIf you attempt to qlogin to a queue to which you do not have access, you may see the above message again, even when resubmitting submitting your request to the proper queue. This is because the qlogin socket is left open for a short period of time after an unsuccessful request. The solution under both circumstances (lack of available nodes or improper queue request) is to simply wait a few minutes and then re-try retry your request to the appropriate queue. |
...