[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [HTCondor-users] Condor + Docker?
- Date: Thu, 10 Jul 2014 15:47:51 -0500
- From: Greg Thain <gthain@xxxxxxxxxxx>
- Subject: Re: [HTCondor-users] Condor + Docker?
On 07/10/2014 03:39 PM, Branden Timm wrote:
That's great, I hadn't noticed the existing cgroup support in the
One question about the documentation. It states that each job will be
started in it's own cgroup named using the job's attributes by
job_<ClusterID>_<ProcID>, but it also states that you must create a
condor group either manually, using cgconfig, or with systemd.
1) Does that mean that each cgroup condor creates for a job will be
nested under the statically defined condor cgroup?
2) If so, is there a way to pass options to cgcreate for the job to
influence the cpu/memory/blkio share reservations? Or is it simply
used for accounting at this point?
The idea is that the size of the cgroups will reflect the size of the
slot. So, for memory, the cgroup memory controller limit will be based
on the Memory attribute of the slot. This may be controlled
(indirectly) by the job with the Request_memory job attribute.