GRID technology by SZTAKI

1
GRID technologyby SZTAKI

• Peter Kacsuk
• MTA SZTAKI
• Laboratory of Parallel and Distributed Systems
• www.lpds.sztaki.hu

2
Contents

• SZTAKI participation in EU and Hungarian Grid
  projects
• P-GRADE (Parallel GRid Application Development
  Environment)
• Integration of P-GRADE and Condor
• TotalGrid
• Meteorology application by TotalGrid
• Grid version of GRM/PROVE in the DataGrid project

3
EU Grid projects of SZTAKI

• DataGrid performance monitoring and
  visualization
• GridLab grid monitoring and information system
• APART-2 leading the Grid performance analysis
  WP
• SIMBEX developing a European metacomputing
  system for chemists based on P-GRADE

4
Hungarian Grid projects of SZTAKI

• VISSZKI
• explore and adopt Globus and Condor
• DemoGrid
• grid and performance monitoring and visualization
• SuperGrid (Hungarian Supercomputing Grid)
• integrating P-GRADE with Condor and Globus in
  order to provide a high-level program development
  environment for the Grid
• Hungarian Cluster Grid Initiative
• To provide a nation-wide cluster Grid for
  universities

5
Hungarian and international GRID projects
EU DataGrid

• VISSZKI
• Globus test
• Condor test

• DemoGrid
• - file system
• monitoring
• applications

Cactus
CERN LHC Grid

• SuperGrid
• - P-GRADE
• portal
• security
• accounting

Condor
APART-2
EU COST SIMBEX
EU GridLab
6
Structure of the Hungarian Supercomputing Grid
2.5 Gb/s Internet
7
The Hungarian Supercomputing GRID project
GRID application
GRID application
Web based GRID access
GRID portal
High-level parallel development layer
P-GRADE
Low-level parallel development
PVM
MW
MPI
Grid level job management
Condor-G
Grid middleware
Globus
Grid fabric
Condor, SGE
Condor, SGE
Condor, SGE
Condor, SGE
Compaq Alpha Server
Compaq Alpha Server
SUN HPC
Clusters
8
Distributed supercomputing P-GRADE

• P-GRADE (Parallel GRid Application Development
  Environment)
• A highly integrated parallel Grid application
  development system
• Provides
• Parallel, supercomputing programming for the Grid
  
• Fast and efficient development of Grid programs
• Observation and visualization of Grid programs
• Fault and performance analysis of Grid programs
• Further development in the Hungarian
  Supercomputing Grid project

9
Three layers of GRAPNEL
10
Communication Templates

• Pre-defined regular process topologies
• process farm
• pipeline
• 2D mesh

• User defines
• representative processes
• actual size
• Automatic scaling

11
Mesh Template
12
Hierarchical Debuggingby DIWIDE
13
Macrostep Debugging

• Support for systematic debugging to handle
  non-deterministic behaviour of parallel
  applications
• Automatic dead-lock detection
• Replay technique with collective breakpoints
• Systematic and automatic generation of Execution
  Trees
• Testing parallel programs for every time condition

14
GRM semi-on-line monitor

• Monitoring and visualising parallel programs at
  GRAPNEL level.
• Evaluation of long-running programs
• Support for debugger in P-GRADE with execution
  visualisation
• Collection of both statistics and event trace
• No lost of trace data at program abortion. The
  execution to the point of abortion can be
  visualised.
• Execution (and monitoring) remotely from the user
  environment -gt first step towards the Grid

15
GRM semi-on-line monitor

• Semi-on-line
• stores trace events in local storage (off-line)
• makes it available for analysis at any time
  during execution for user or system request
  (on-line pull model)
• Advantages
• analyse the state (performance) of the
  application at any time
• scalability analyse trace data in smaller
  sections and delete them if they are not longer
  needed
• Less overhead/intrusion to the execution system
  than with on-line collection (see NetLogger)
• Less network traffic pull model instead of push
  model. Collections initiated only from top.

16
PROVE Statistics Windows

• Profiling based on counters
• Analysis of very long running programs is enabled

17
PROVE Visualization of Event Traces

• User controlled focus on processors, processes
  and messages
• Scrolling visualization windows forward and
  backwards

18
Integration of Macrostep Debugging and PROVE
19
Features of P-GRADE

• Designed for non-specialist programmers
• Enables fast reengineering of sequential programs
  for parallel computers and Grid systems
• Unified graphical support in program design,
  debugging and performance analysis
• Portability on
• supercomputers
• heterogeneous clusters
• components of the Grid
• Two execution modes
• Interactive
• Job level

20
P-GRADE Interactive Mode on Clusters
P-GRADE Interactive mode
21
P-GRADE Job Mode for the Grid
22
Condor/P-GRADE on the whole range of parallel
and distributed systems
GFlops
Super-computers
23
Berlin CCGrid Grid Demo workshop Flocking of
P-GRADE programs by Condor
P-GRADE
Budapest
m0
m1
n0
n1
Budapest
Madison
p0
p1
Westminster
24
Next step Check-pointing and migration of
P-GRADE programs
Wisconsin
P-GRADE GUI
Budapest
London
m0
m1
n0
n1
25
Further develoment TotalGrid

• TotalGrid is a total Grid solution that
  integrates the different software layers of a
  Grid (see next slide) and provides for companies
  and universities
• exploitation of free cycles of desktop machines
  in a Grid environment after the working/labor
  hours
• achieving supercomputer capacity using the actual
  desktops of the institution without further
  investments
• Development and test of Grid programs

26
Layers of TotalGrid
P-GRADE
PERL-GRID
Condor or SGE
PVM or MPI
Internet
Ethernet
27
PERL-GRID

• A thin layer for
• Grid level job management between P-GRADE and
  various local job managers like
• Condor
• SGE, etc.
• file staging
• job observation
• Application in the Hungarian Cluster Grid

28
Hungarian Cluster Grid Initiative

• Goal To connect the new clusters of the
  Hungarian higher education institutions into a
  Grid
• By autumn 42 new clusters will be established at
  various universities of Hungary.
• Each cluster contains 20 PCs and a network server
  PC.
• Day-time the components of the clusters are used
  for education
• At night all the clusters are connected to the
  Hungarian Grid by the Hungarian Academic network
  (2.5 Gbit/sec)
• Total Grid capacity in 2002 882 PCs
• In 2003 further 57 similar clusters will join the
  Hungarian Grid
• Total Grid capacity in 2003 2079 PCs
• Open Grid other clusters can join at any time

29
Structure of the Hungarian Cluster Grid
2002 4221 PC Linux clusters, total 882 PCs
TotalGrid
2003 9921 PC Linux clusters, total 2079 PCs
TotalGrid
2.5 Gb/s Internet
TotalGrid
30
Live demonstration of TotalGrid

• MEANDER Nowcast Program Package
• Goal Ultra-short forecasting (30 mins) of
  dangerous weather situations (storms, fog, etc.)
• Method Analysis of all the available meteorology
  information for producing parameters on a regular
  mesh (10km-gt1km)
• Collaborative partners
• OMSZ (Hungarian Meteorology Service)
• MTA SZTAKI

31
Structure of MEANDER
First guess data ALADIN
SYNOP data
Satelite
Radar
Lightning
CANARI
Delta analysis
decode
Basic fields pressure, temperature, humidity,
wind.
Radar to grid
Rainfall state
Derived fields Type of clouds, visibility, etc.
Satelite to grid
Visibility
Overcast
GRID
Type of clouds
Current time
Visualization
For meteorologistsHAWK
For users GIF
32
P-GRADE version of MEANDER
33
Live demo of MEANDER based on TotalGrid
Parallel execution
34
Results of the delta method

• Temperature fields at 850 hPa pressure
• Wind speed and direction
• on the 3D mesh of the MEANDER system

35
On-line Performance Visualization in TotalGrid
Parallel execution and GRM
36
PROVE visualization of the delta method
37
GRM/PROVE in the DataGrid project

• Basic tasks
• step 1 To create a GRM/PROVE version that is
  independent from P-GRADE and runable in the Grid
• step 2 To connect the GRM monitor to the R-GMA
  information system

38
GRM in the grid
Submit machine
Main MonitorMM
Trace file
PROVE
Pull model gt smaller network traffic than in
NetLogger
Site 1
Local monitor gt more scalable than NetLogger
Site 2
PC 1
PC 2
PC 1
Local MonitorLM
Local MonitorLM
Local MonitorLM
shm
shm
shm
App. Process
App. Process
App. Process
App. Process
39
Start-up of Local Monitors
This mechanism is used in TotalGrid and in the
live demo
Grid broker
Local job manager
LAN
WAN
application process2
application process1
Local Monitor
Local Monitor
40
Client machine
Main Monitor
PROVE
2nd step Integration with R-GMA
R-GMA
Site
Machine 1
Machine 2
App.Process
App.Process
App.Process
41
R-GMA
Integration with R-GMA
XML
SQL SELECT
SQL CREATE TABLE SQL INSERT
42
Conclusions

• SZTAKI participates in several EU and Hungarian
  Grid projects
• Main results
• P-GRADE (SuperGrid project)
• Integration of P-GRADE and Condor (SuperGrid,
  GridLab)
• demo at Berlin CCGrid
• TotalGrid (Hungarian Cluster Grid)
• Grid version of GRM/PROVE (DataGrid)
• Meteorology application in the Grid
• continuos live demo in the registration hall

43

Thanks for your attention
?
Further information www.lpds.sztaki.hu