VT MPI within EGI

General Project Information

• Leader: Alvaro Simon (CESGA, Spain) and Zdenek Sustr (CESNET, Czech Republic)
• Mailing List: vt-mpi at mailman.egi.eu
• Status: Active
• Start Date: 10/Nov/2011
• End Date: 31/May/2012
• Meetings: MPI Virtual team meetings:
  • 12/12/2011 - MPI VT Management meeting
  • 06/02/12 2nd MPI VT meeting
  • 17/02/2012 MPI VT nagios probes meeting
  • 29/02/2012 3rd MPI VT meeting

Motivation

Despite a dedicated SA3 activity to support MPI there still seem to be significant issues in uptake and satisfaction amongst the user communities. This VT

• Works with user communities and projects that use MPI resources (e.g. ITER, MAPPER, A&A, etc) to demonstrate that MPI can work successfully in EGI.
• Sets up a VO on EGI with sites committed to support MPI jobs.
• Improve the communication between MPI users and developers of MPI support within EGI SA3.

Output

The VT is expected to produce the following outputs:

• Materials (tutorials, white papers, etc) about successful use cases of MPI on EGI that can be used by new communities to use MPI on EGI.
• An MPI VO that provides:
  • dedicated CPUs for MPI jobs
  • MPI specific test probes can run on all sites using the VO Monitoring services of Ibergrid (EGI-InSPIRE VO Services group)
  • accounting for MPI jobs
  • user support
• Improved communication channels with MPI users
• The above set of resources and feedback to resource centers, user communities and technology providers on how to improve MPI within EGI.

Tasks

• Task 1
• Task 2
• ...
• Task N

Members

• NGIs - confirmed:
  • BG: Aneta Karaivanova
  • CZ: Zdenek Sustr (leader)
  • ES/IBERGRID: Alvaro Simon (leader), Enol Fernandez, Iván Díaz, Alvaro Lopez, Pablo Orviz, Isabel Campos, Roberto Rosende Dopazo
  • GR: Dimitris Dellis, Marios Chatziangelou, Paschalis Korosoglou
  • HR: Emir Imamagic, Luko Gjenero
  • IE: John Walsh
  • IT: Daniele Cesini, Alessandro Costantini, Vania Boccia, Marco Bencivenni
  • PT: Gonçalo Borges
  • SK: Viera Sipkova, Viet Tran, Jan Astalos
  • UK: John Gordon
• EGI.eu: Gergely Sipos, Karolis Eigelis, Tiziana Ferrari, Peter Solagna

Resources

VO MPI-Kickstart

The MPI-Kicktart Virtual Organization brings together sites and users inetrested in improving MPI reliability across EGI.

Useful Links

• Home Page https://www.metacentrum.cz/en/VO/MPI/index.html
• Registration https://egee.cesnet.cz/mpi/registration/prihlaska_priprav.php
• Mailing List mpi-kickstart at metacentrum.cz

Environment Settings

VO_MPI_VOMS_SERVERS="'vomss://voms1.egee.cesnet.cz:8443/voms/mpi?/mpi'"
VO_MPI_QUEUES=""
VO_MPI_SW_DIR="$VO_SW_DIR/mpi"
VO_MPI_DEFAULT_SE=""
VO_MPI_STORAGE_DIR=""
VO_MPI_VOMSES="'mpi voms1.egee.cesnet.cz 15030 /DC=cz/DC=cesnet-ca/O=CESNET/CN=voms1.egee.cesnet.cz mpi 24'"
VO_MPI_VOMS_POOL_PATH=""
VO_MPI_VOMS_CA_DN="'/DC=cz/DC=cesnet-ca/O=CESNET CA/CN=CESNET CA 3'"
VO_MPI_WMS_HOSTS="wms1.egee.cesnet.cz wms2.egee.cesnet.cz" 

Progress

Task 1: MPI documentation

• Changed and updated MPI documetation based on sites and MPI VT feedback: https://wiki.egi.eu/wiki/MAN03

Task 2: Nagios probes

• Created new MPI nagios probes specifications available at: https://wiki.egi.eu/wiki/VT_MPI_within_EGI:Nagios

Task 3: Information system

• Checked current GLUE2 schema to find MPI static values.
  • MaxSlotsPerJobs Can be used for MPI jobs:The maximum number of slots which could be allocated to a single job. This value is not filled by the current LRMS Information Providers.
  • Raise a request to EMI. Include MaxSlotsPerJobs as a new value to be published by batch system IPs.

Task 5: Batch system status

• MAUI issue (https://ggus.eu/ws/ticket_info.php?ticket=67870) will fixed in the next EMI2 release.
  • LRMS is a 3th party product not updated directly by EMI members.

Task 6: Gather information from MPI sites

• Created the new MPI kickstart VO
  • CESNET and CESGA are providing resources to test the new VO.
• Gathered information from NGIs. MPI survey and sites status: https://www.egi.eu/indico/conferenceDisplay.py?confId=828 29/02/2012