Re: [HTCondor-users] RESERVED_SWAP

[Mary Romelfanger <mary@xxxxxxxxx>]

Hi Brian,

    It looks like I have some reading to do.

   And we might be able to try this.   The servers running that software are Redhat 6 and they are at 2.6.32 – and it looks like 2.6.24 is when cgroups were introduced.     

      Thank You for the additional idea.

              Mary

From: HTCondor-users <htcondor-users-bounces@xxxxxxxxxxx> on behalf of Brian Bockelman <bbockelm@xxxxxxxxxxx>
Reply-To: HTCondor-Users Mail List <htcondor-users@xxxxxxxxxxx>
Date: Friday, February 19, 2016 at 3:40 PM
To: HTCondor-Users Mail List <htcondor-users@xxxxxxxxxxx>
Subject: Re: [HTCondor-users] RESERVED_SWAP

Hi Mary,

What platform do you use?

On modern Linux platforms, the best way forward is to enable cgroups.  This allows very precise, kernel-based management of RAM resources.  It may be a better way forward than trying to work with RESERVED_SWAP.

Brian

On Feb 18, 2016, at 11:10 AM, Mary Romelfanger <mary@xxxxxxxxx> wrote:

As we develop a new pipeline for a new set of instruments, we have found that we have one calibration job that is using more memory resources than we have typically had to work with before.  This has me exploring new to me knobs to try to prevent these specific jobs from taking too many resources and locking up the system.

I found and was all set to add the RESERVED_SWAP knob to my config file  — because yes we have thrown both more memory and more swap space onto the test systsem, and we think it is enough to handle just about every case, but it looked like this RESERVED_SWAP knob would be that last extra safety net (especially since the team writing the calibration software is not done yet :) ) ,    but I see in the v8.4 manual that a comment has been added that says "It is anticipated that this configuration variable will no longer be used in the near future. “

Is there a new knob/better option, that I should look at, that would stop new jobs from starting if the available real system swap space dipped to low?

          Thank You — Mary

Mary Romelfanger

Sr. Systems Software Engineer

.___.      

{o,o}      Phone 410-338-6708
/)__)     Cell      443-244-0191
-"-"-          mary@xxxxxxxxx

Space Telescope Science Institute

3700 San Martin Drive

Baltimore, MD 21218

_______________________________________________
HTCondor-users mailing list
To unsubscribe, send a message to htcondor-users-request@xxxxxxxxxxx with a
subject: Unsubscribe
You can also unsubscribe by visiting
https://lists.cs.wisc.edu/mailman/listinfo/htcondor-users

The archives can be found at:
https://lists.cs.wisc.edu/archive/htcondor-users/