home *** CD-ROM | disk | FTP | other *** search
- Xref: sparky comp.sys.sgi:18032 comp.unix.admin:6654
- Path: sparky!uunet!noc.near.net!hri.com!ukma!psuvax1!psuvm!kjb6
- From: KJB6@psuvm.psu.edu
- Newsgroups: comp.sys.sgi,comp.unix.admin
- Subject: QUEING LARGE JOBS
- Message-ID: <92350.105127KJB6@psuvm.psu.edu>
- Date: 15 Dec 92 15:51:27 GMT
- Organization: Penn State University
- Lines: 21
-
- Forgive me if this has been asked before, but I need to know if there are any
- scripts available to do what I am about to describe.
-
- We have a network of 27 SGI workstations running 4.0.4 OS with most of them
- having only 16 megs of memory (4 machines have either 32 or 48 megs). Some of
- the students in our environment will start large Ansys or Fidap jobs either in
- forground or background. When this is done, it really puts a strain on the
- network. Most of the students only have access to the machines with 16 megs of
- memory.
-
- Without having to have the students 'rlogin' to a machine with 32 or 48 meg of
- memory, is there a way to poll which of these machines (32/48 meg mach.) is not
- busy and run the job there. And if someone logs onto one of these machines, the
- job gets sent back to where it started??
-
- Any ideas would be appreciated.
-
-
- Ken Bauer
- Systems Analyst kjb6@psuvm.psu.edu
- PENN. STATE - ERIE, The Behrend College
-