Mailing List Archives
Authenticated access
|
|
|
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [Condor-users] Condor - condor_schedd daemon per pool or what?
- Date: Thu, 07 Jul 2011 16:16:10 -0500
- From: Todd Tannenbaum <tannenba@xxxxxxxxxxx>
- Subject: Re: [Condor-users] Condor - condor_schedd daemon per pool or what?
Michael O'Donnell wrote:
Sassy,
I am not expert, but one main advantage to having multiple schedds is
that a single machine can submit only so many jobs. This varies btw
OS/platform of course and at least on Windows it is related to the
desktop heap size (this can be increased, but there is a limit). I am
not as familiar with Mac/Linux/Unix, but for windows you can only have
so many people logged on to a machine. Therefore, if you want to submit
by remotely logging on to a machine you may run into limitations here as
well. The other thing to think about is that multiple schedds also
allows you to set up high availability (fail over). If one of the
schedds go down the queue can be transferred to a different schedd (this
has to be set up because Condor does not default to this set up).
Another advantage is convenience. In our department, for instance, we
run a schedd on every researcher's desktop. This allow researchers to
easily submit jobs directly from their desktop machine, which has
several nice properties:
- enables their jobs to read/write to data files stored on local disk.
- similar to the above, we have folks that install submit machines
(schedds) in their own labs on their own NATs so that their jobs have
access to file servers / databases etc that are private to that lab.
- when the researcher type "condor_q" etc, they just see their own
jobs, which is all many people care about (they can always type
"condor_q -global" if they wish to see job submitted on all schedds in
the pool).
-Todd