Jeff -
Thanks for the direct response.
1) The practice of disallowing rsh/ssh to all computational hosts is the "stick" used in several corporate environments to make sure users are submitting their jobs to the workload management system [WLM] (LSF in this case) instead of running directly on the systems. In an environment with 1000s of computational hosts and 1000s of users where it's very important to know who ran what for how long, getting people to use the WLM is important.
2) I'm working with a vendor of an application used by one of our mutual customers. This application uses LAM v6.3 today, but they are working on bringing it up to v7.1.2. Even with that library update though, how does the LSF integration work? On p73 of the 7.1.2 users guide, section 8.1.9 the "tm" module is stated to work with the PBS's and Torque. The documentation says that no command line parameters are required as the environment is detected, but "tm" can be forced by using:
lamboot -v -ssi boot_tm
I haven't tried to force the environment, but can easily do so if that is what you're suggesting. I didn't try this because of the statement on p74 "Since the tm boot module is designed to work with PBS/Torque jobs, it will fail if the tm module is manually specified and LAM is not currently running in a PBS/Torque job."
Please confirm your suggestion, and I'll give it a try.
chris
-----Original Message-----
From: lam-bounces_at_[hidden] [mailto:lam-bounces_at_[hidden]] On Behalf Of Jeff Squyres (jsquyres)
Sent: Thursday, April 27, 2006 6:52 AM
To: General LAM/MPI mailing list
Subject: Re: LAM: lamboot without rsh/ssh
That is correct -- Guangyu Wu's response was technically correct but misleading. The TM interface is for Torque/PBS integration, not LSF integration.
I think the outstanding questions are:
- What about your environment is disallowing the use of ssh? (it's surprising that ssh would not be allowed, but not unheard of)
- Can you upgrade your version of LAM? I honestly don't remember what job scheduler support we had for LSF way back then (years ago!), but I do remember that we had a bug in the LSF detection stuff for at least a little while (I don't remember what version(s) specifically). As far as I know, the LSF stuff is correct in the current version (7.1.2). Is there any possibility that you can upgrade?
> -----Original Message-----
> From: lam-bounces_at_[hidden]
> [mailto:lam-bounces_at_[hidden]] On Behalf Of Christopher Porter
> Sent: Thursday, April 27, 2006 9:32 AM
> To: General LAM/MPI mailing list
> Subject: Re: LAM: lamboot without rsh/ssh
>
> I have looked carefully through the LAM-MPI Users guide and can not
> find any integration notes for what must be done in an LSF environment
> to use the "TM" interface. The documentation for Torque / PBSpro
> states that the batch queueing system is automatically detected and
> the TM interface is used.
>
> So I have "tested" the integration with LSF by doing nothing special
> and trying to run a job. Nothing seemed to detect the LSF
> environment, the job failed saying that it could not contact the LAM
> daemons (because none were booted). So I believe this is an incorrect
> statement and the "TM" interface is not integrated with LSF.
>
> Someone prove me wrong? Please?
>
> chris
>
> -----Original Message-----
> From: lam-bounces_at_[hidden]
> [mailto:lam-bounces_at_[hidden]] On Behalf Of Guangyu Wu
> Sent: Wednesday, April 26, 2006 5:56 PM
> To: 'General LAM/MPI mailing list'
> Subject: ç”å¤: LAM: lamboot without rsh/ssh
>
> There is a TM interface integrated in WMS such as PBS Pro which could
> boot lam without rsh/ssh. I believe LSF also has such an integration
> with Lam.
> HTH
>
> -----邮件原件-----
> å‘件人: lam-bounces_at_[hidden] [mailto:lam-bounces_at_[hidden]]
> 代表 Phil Ehrens
> å‘é€æ—¶é—´: 2006å¹´4月25æ—¥ 3:44
> 收件人: General LAM/MPI mailing list
> 主题: Re: LAM: lamboot without rsh/ssh
>
> YoungHui Amend wrote:
> > I'm using an old versions (6.3) of LAM/MPI. In this
> version of LAM,
> > lamboot uses rsh to run hboot which forks lam demon (lamd). The
> > problem we are running in to is that rsh is not allowed
> (for security
> > reasons) on the cluster of machines connected to LSF. Ssh
> also causes
> > problems because it prompts you for the password. I know there's a
> > way to setup ssh so it doesn't prompt for a password, but
> it is not a viable option.
> > So, is there a way to fork lam demon without going through lamboot?
>
> You have an installation where rsh can't be used due to security
> concerns... and ssh can't be used because it's "not viable"?
>
> Do they make you communicate with you coworkers by blinking
> flashlights at them?
> _______________________________________________
> This list is archived at http://www.lam-mpi.org/MailArchives/lam/
>
>
>
>
>
>
> _______________________________________________
> This list is archived at http://www.lam-mpi.org/MailArchives/lam/
>
|
