Administrators Guide
Info@par-tec.com
ParaStation5 Administrators Guide
Table of Contents
Problem different groups of nodes are seen as up or down
History of ParaStation
Introduction
About this document
Runtime daemon
Technical overview
Libraries
Kernel modules
License
Hardware
Installation
Prerequisites
Kernel version
Directory structure
Software
Getting the ParaStation5 RPM packages
Installation via RPM packages
Man
Mpi2, mpi2-intel, mpi2-pgi, mpi2-psc
File Version
Installing the RPMs
Compiling the ParaStation5 packages from source
ParaStation entries
Installing the documentation
Etc/init.d/xinetd reload
Further steps
Installing MPI
# rpm -Uv psdoc-5.0.0-1.noarch.rpm
# rpm -Uv psmpi2.5.0.0-1.i586.rpm
Uninstalling ParaStation5
ParaStation5 Administrators Guide
Configuration of the ParaStation system
Configuration
Copy template
Define Number of nodes
Hostname id HWType runJob starter accounter
Enable optimized network drivers
# /opt/parastation/bin/testconfig
Testing the installation
# /opt/parastation/bin/testnodes -np nodes
# /opt/parastation/bin/psiadmin -s -c list
ParaStation5 pscom communication library
Insight ParaStation5
# cat /proc/sys/ps4/state/connections
# echo 10 /proc/sys/ps4/state/ResendTimeout
Directory /proc/sys/ps4/state
Directory /proc/sys/ps4/local
Controlling process placement
Exporting environment variables for a task
Using the ParaStation5 queuing facility
Using non-ParaStationapplications
Export LDPRELOAD=/opt/parastation/lib64/libp4tcp.so
Controlling ParaStation5 communication paths
Pspshm or Pspsharedmem
Authentication within ParaStation5
PSPP4S or PSPP4SOCK
Export PSPLIB=/opt/parastation/lib64/libpscomopenib.so
Single system view
Homogeneous user ID space
Parallel shell tool
Nodes and CPUs
Integrating external queuing systems
Integration with AFS
Tok2env
PSIRARGPRE0=/some/path/env2tok
Multicasts
Copying files in parallel
Using ParaStation accounting
# UseMCast
Route add -net 224.0.0.0 netmask 240.0.0.0 dev ethX
Using memory binding
Using ParaStation process pinning
Changing the default ports for psid8
Spawning processes belonging to all groups
Port
Problem node shown as down
Troubleshooting
Problem psiadmin returns error
Problem bad performance
Problem cannot start parallel task
Problem different groups of nodes are seen as up or down
Problem cannot start process on frontend
Problem psid does not startup, reports port in use
Problem pssh fails
Problem processes cannot access files on remote nodes
Reference Pages
ParaStation5 Administrators Guide
Parastation.conf
InstallDir inst-dir , InstallationDir inst-dir
Description
Parameters
Startscript
Setupscript
Stopscript
Statusscript
Openib
P4sock
Mvapi
Elan
NrOfNodes num
Accounter
$GENERATE 1-96 node$0,2 $0
Node node17 16 HWType ethernet p4sock starter yes runJobs no
DeadInterval num
SelectTime time
LogLevel num
MCastGroup group-num
CPUTime time
Core size
DataSize size
MemLock size
Proc
CPUmap map
Processes maxprocs
StatusTimeout ms
RdpTimeout ms
RdpClosedTimeout ms
RdpResendTimeout ms
See also
Errors
ParaStation5 Administrators Guide
Options
Psiadmin
Synopsis
Standard Input
Standard Error
Standard Output
Extended description
Allproc cnt count
Exit
All
Down
Count hw hw
Hardware
Load
Quit
Rdp
Summary max max
User nodes
Accounters nodes
Group nodes
Maxproc nodes
FreeOnSuspend nodes
Master nodes
HandleOldBins nodes
NodesSort nodes
Rlrss nodes
Cpumap nodes
StatusTimeout nodes
RdpTimeout nodes
RdpClosedTimeout nodes
RdpResendTimeout nodes
Restart nodes
Resolve nodes
Psiddebug mask nodes
Selecttime time nodes
Pattern Name Description
HandleOldBins 0 1 nodes
Rdpmaxretrans val nodes
StatusTimeout ms nodes
RdpTimeout ms nodes
RdpClosedTimeout ms nodes
RdpResendTimeout ms nodes
Quiet
Files
Normal
Verbose
Psid
Logfile=file
Configfile=file
Debug=level
Filename
Testconfig
Num
? , --usage Show a help message
ParaStation5 Administrators Guide
Np num
Testnodes
Cnt num
Map
ParaStation5 Administrators Guide
Testpse -npnum
Testpse
ParaStation5 Administrators Guide
Sock
P4stat
Net
?,--help
ParaStation5 Administrators Guide
Delete
P4tcp
Add
ParaStation5 Administrators Guide
Pattern Description
Psaccounter
Coredir=dir
Dumpcore
?, --help
Var/account/yyyymmdd Accounting files, one per day
Psaccview
Lu,--ltotuser
Lj,--ljobs
Lg,--ltotgroup
Ls,--ltotsum
Aqtime
Cpuweight
Cputime
End
Initialization file
Mlisten
ParaStation5 Administrators Guide
Appendix A. Quick Installation Guide
Testing
# /opt/parastation/bin/psiadmin psiadmin add
# chkconfig -a /etc/init.d/parastation
Appendix B. ParaStation license
Page
Page
Page
# psiadmin -s
Building and installing ParaStation5 packages
Appendix C. Upgrading ParaStation4 to ParaStation5
Changes to the runtime environment
Page
ARP
Glossary
See ParaStation Logger
To share a common address space within a node
ParaStation5 Administrators Guide