[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [HTCondor-users] Condor + Docker?
- Date: Thu, 10 Jul 2014 15:39:15 -0500
- From: Branden Timm <btimm@xxxxxxxxxxxxxxx>
- Subject: Re: [HTCondor-users] Condor + Docker?
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?
Wisconsin Energy Institute
On 07/10/2014 03:00 PM, Greg Thain wrote:
On 07/10/2014 01:57 PM, Branden Timm wrote:
This may be a better question for htcondor-devel, but I wonder if
anybody has thought of or tried using Condor in conjunction with
Docker? I can imagine several advantages that could be leveraged via
Docker, including -
1) Deploying jobs to containers running pre-configured images
containing all the software for that job (instead of, say, having
software pre-installed across your cluster or setting up/tearing down
requirements on job start/completion). Docker images tend to be
lightweight, and they're cached once they're downloaded, so on
repeated runs almost nothing would have to be transferred to the
2) Taking advantage of the underlying cgroups features of the Linux
kernel to actually limit jobs to the requirements specified in their
submit file while the system is under pressure (cpu, memory, and disk
IO can all be throttled). Of course, the other advantage is that
it's a share-based system, so you can guarantee a minimum amount of
CPU access while still allowing it to burst beyond that on an
otherwise idle system.
3) Complete namespace isolation (process, filesystem, and network) of
running jobs from the rest of the system.
Docker is a technology that us HTCondor folks are keeping an eye on.
Note that for bullet point #2 above, HTCondor today has support for
using cgroups to sandbox the cpu and memory usage of a job, and to
measure resource usage. HTCondor also optionally support process
isolation on Linux systems with kernel support.
HTCondor-users mailing list
To unsubscribe, send a message to htcondor-users-request@xxxxxxxxxxx
You can also unsubscribe by visiting
The archives can be found at: