(r7) BatchSystem < Computing/Documentation

Tags: view all tags
---+ The PPD Batch System

The PPD Batch Systems are shared between the Grid Tier 2 and Local usage (often referred to as Tier 3). We now have two batch system, the legacy Scientific Linux 5 system uses the torque batch system (an evolution of PBS) and the Maui scheduler to allocate the job slots fairly. While the newer Scientific Linux 6 services use Condor.

---++ Resources

The PPD Batch Cluster currently has a nominal capacity of 2700 job slots (one for each of the 2700 CPUs) on 240 nodes. The power of the CPUs are measured using a benchmark called HEPSPEC06, the individual CPUs range from a HEPSPEC06 rating of 8.18 for the oldest CPUs to 12.67 for the newest. The nominal total HEPSPEC06 rating of the cluster is 28,000

At the moment approximately 1800 jobs slots are assigned to the SL6 Condor service with about 900 of the older CPU allocated to the SL5 Torque/Maui service.

---++ Allocations

The system tries to "fairly" share out jobs starts between different users, it uses a number of different factors to try to do this. Amongst them are whether it is a "local" or grid job, the Grid VO, groups within the VOs and individual user accounts. These are compared to the usage over the last 14 days.

Grid submission to the SL5 Cluster is now switched off so 100% of the remaining resources are available for local Tier 3 jobs. 

For the SL6 Condor service the current highest level Shares are:

|  Local  |  15%  |
|  Grid  |  85% |

There are currently no group shares in the Local partition, for the grid jobs the split below the Grid partition is as follows:

|  CMS  |  13%  |
|  Atlas  |  54%  |
|  LHCb  |  20%  |
|  Other  |  3% |

---++ Using the PPD batch systems

---+++ Condor

[[BatchUsageCondor][Submitting and monitoring Condor jobs]]

---+++ Torque
[[BatchUsage][Submitting and monitoring Torque jobs]]


-- Main.ChrisBrew - 2009-11-17
Topic revision: r7 - 2014-03-26 - ChrisBrew