[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [HTCondor-users] How to investigate matchmaking internals?
- Date: Fri, 15 Sep 2017 14:34:45 +0000
- From: Anthony R Tiradani <tiradani@xxxxxxxx>
- Subject: Re: [HTCondor-users] How to investigate matchmaking internals?
I donât know your setup, but we periodically run into a problem that sounds very similar (and once fixed we forget about it until next time). Do you have consumption policies set? Depending on your setup, that may be necessary.
For example: http://research.cs.wisc.edu/htcondor/manual/v8.7/3_5Configuration_Macros.html#25284
From: HTCondor-users <htcondor-users-bounces@xxxxxxxxxxx> on behalf of Thomas Hartmann <thomas.hartmann@xxxxxxx>
Reply-To: HTCondor-Users Mail List <htcondor-users@xxxxxxxxxxx>
Date: Friday, September 15, 2017 at 7:27 AM
To: "htcondor-users@xxxxxxxxxxx" <htcondor-users@xxxxxxxxxxx>
Subject: Re: [HTCondor-users] How to investigate matchmaking internals?
to add, that StartLog showed in that case no activity - not even
rejecting requests that the negotiator had matched??
On 2017-09-15 14:20, Thomas Hartmann wrote:
> yes, that's the problem :(
> For example, -better-analyze showed me the five machines to match the
> job's requested resources - however, the jobs did not start on the nodes
> although the they were empty?!