Hungarian ClusterGrid and its        applications     Szalai Ferenc, NIIF Institute            szferi@niif.hu             ...
History●    early 2002: Start, design phase●    Jul 2002: Condor based production system    started●    early 2003: Condor...
ClusterGrid Architecure●    ClusterGrid is a collection of individual clusters    and supercomputers integrating them with...
ClusterGrid ArchitectureNumbers:1000 nodes32 sites (cluster)22 TB storage
Storage●    Goal    –   build national distributed storage infrastucture for grid,        HPC, disastery recover backup   ...
ClusterGrid applications●    hunderd of registred users, dozens of active●    over 80% unitilization●    mainly parameter ...
Usecase: Virtual Screening●    Virtual screening: find molecules to be the base    of medicine with brute force technique●...
Grid UnderGround●    new generation ClusterGrid middleware.●    Since Feb 2006 using in the production system●    Design g...
GUG Architecture●    Pure python framework:    –   framework runs as a single daemon    –   manage threads    –   handle n...
Example serviceclass Test: def __init__(self, id, local_gis_url,   config):   pass def _get_description(self, site_id):   ...
GUG Core Services●    VOService (security)    –   every entity identified by X509 cert    –   every VO should set up at le...
GUG Core Services●    Storage management components:    –   file based arch.    –   Storage Controller: stores and gives b...
GUG Serives and UI●    Additional services:    –   Compiler service: create binaries from source to all        avalilable ...
Future: KnowARC●    EU funded FP6 project●    Goal: create ligthweight, interoperable,    standard based best grid middlew...
Upcoming SlideShare
Loading in …5
×

Hungarian ClusterGrid and its applications

220 views
180 views

Published on

year: 2006

Published in: Technology
0 Comments
0 Likes
Statistics
Notes
  • Be the first to comment

  • Be the first to like this

No Downloads
Views
Total views
220
On SlideShare
0
From Embeds
0
Number of Embeds
0
Actions
Shares
0
Downloads
1
Comments
0
Likes
0
Embeds 0
No embeds

No notes for slide

Hungarian ClusterGrid and its applications

  1. 1. Hungarian ClusterGrid and its applications Szalai Ferenc, NIIF Institute szferi@niif.hu http://www.clustergrid.hu http://gug.grid.niif.hu
  2. 2. History● early 2002: Start, design phase● Jul 2002: Condor based production system started● early 2003: Condor changed in the grid level to own middleware● Jul 2003: development of new operating system level services has been started● Nov 2005: development new generation ClusterGrid middleware (Grid Underground) has been started● Dec 2005: migration to the new operating system level services● Feb 2006: change to the new middleware
  3. 3. ClusterGrid Architecure● ClusterGrid is a collection of individual clusters and supercomputers integrating them with grid middleware● Network oriented arch – using MPLS VPN and 802.1q techniques for separation -> „small private internet”● Virtualized central services using XEN: – root DNS, monitoring (munin, nagios), Debian repository mirror, entry points● Distributed storage● Clusters: standard Beowulf diskless arch. based on GNU/Debian Linux distro
  4. 4. ClusterGrid ArchitectureNumbers:1000 nodes32 sites (cluster)22 TB storage
  5. 5. Storage● Goal – build national distributed storage infrastucture for grid, HPC, disastery recover backup – reach at least 100 TB, be clever and cheep :)● Solution: – IP (iSCSI) and/or ethernet (AoE) based storage elements – intelligent grid storage management using grid services● Current state: AoE based storage in two sites (NIIF, SZTAKI) 22 TB
  6. 6. ClusterGrid applications● hunderd of registred users, dozens of active● over 80% unitilization● mainly parameter scanning from – bioinformatics, statistical physics, information science, biochemistry etc.● main problem: users are not familiar with managing huge amount of job and data processing, and porting application to different paltforms (solaris, linux, etc.)● strong user support intergarted with normal helpdesk
  7. 7. Usecase: Virtual Screening● Virtual screening: find molecules to be the base of medicine with brute force technique● big virtual screening: find molecules for human histamin receptor 4 (HHR4) – known since 2001, member of GPCR group● using databases: 8 million molecule● using close source, binary only, liscenced application: Flexx (Biosolveit.de)● Takes 2 month total calcualtion
  8. 8. Grid UnderGround● new generation ClusterGrid middleware.● Since Feb 2006 using in the production system● Design goals: – pure web service based framework (no WSRF) – using selected GGF, W3C standards – simplify service development – focus on core services (info, storage, job management, security, monitoring) – KISS: Keep It Simple, Stupid – destop and HPC ware: low memory and cpu usage – open source development (http://www.sourceforge.net/projects/gug)
  9. 9. GUG Architecture● Pure python framework: – framework runs as a single daemon – manage threads – handle network communication over HTTP(S)/SOAP – every service is a dinamicaly loadable plugin of the framework, services use backends to separate interfaces and functions● Mandatory services: – Manager service: manage simple lifecycle of other services. Remote management also possible. – Grid Information System: p2p system to route advertisements, service descriptions of services (better than UDDI)
  10. 10. Example serviceclass Test: def __init__(self, id, local_gis_url,  config): pass def _get_description(self, site_id): return ”””<?xml version=1.0?> <ServiceDescription> <Site>%s</Site> </ServiceDescription> ””” % site_id def echo(self, x509, x): return x
  11. 11. GUG Core Services● VOService (security) – every entity identified by X509 cert – every VO should set up at least one VO service – manage authorization information, organize them into the tree – manage VO membership like a maling list● Job management components – Exec: run and manage job in SMP systems (useful on destops) – Job Controller: using GGF BES interface and GGF JSDL. Interface with common LRMS (eg: Condor, Exec etc), no scheduling – SuperScheduler: use the same interace and data model as Job Controller, its a grid level scheduler
  12. 12. GUG Core Services● Storage management components: – file based arch. – Storage Controller: stores and gives back files using transport independent protocol like SRM – ShareDirectory: directory and file sharing (same interface as Storage Controller) – File System Service: metadata catalog – Storage Manager: provides POSIX like interface (mkdir, ls, mv, cp etc.), create replicas on Storage Contollers, manage file system entity types as a plugin: file, directory, shared directory etc.
  13. 13. GUG Serives and UI● Additional services: – Compiler service: create binaries from source to all avalilable platforms. Use job management componets – SNMP based monitoring comming soon● User Interface: – modular command line interface: grid command: $ grid storage ls /grid/tmp ­R /grid/tmp: d   2006­04­12 14:04 proba /grid/tmp/proba: ­ 8 2006­04­12 14:05 szoveg ­ 8 2006­04­12 14:06 szoveg.1 ­ 8 2006­04­12 14:06 masnev $ grid job submit testjob.jsdl – graphical and web interface comming soon
  14. 14. Future: KnowARC● EU funded FP6 project● Goal: create ligthweight, interoperable, standard based best grid middleware ever, strong industrial support● Solution: merge best features of Nordugrid ARC and GUG● Partners: Oslo Univ. (NO), Lund Univ. (SE), Uppsala (SE), Lubeck (DE), NBI (DK), SUN (HU), s + c ag (DE), Geneve Hospital (CH), Josif Safarik Inst. (SK), NIIF● More information: http://www.knowarc.eu

×