Setup

ipp user

Operations are generally performed as the ipp user on the Production Cluster. You should add your ssh public key to ~ipp/.ssh/authorized_keys for ease of access.

Pantasks

Pantasks runs in the server/client mode, so that it can easily be accessed by multiple people.

To distribute the load, we use the following for the server:

• summit copy: ippc07
• registration: ippc09
• standard science: ippc10
• publishing: ippc08

The client can be run on any machine, so long as you're in the appropriate directory (which contain a ptolemy.rc file that selects the correct server to contact).

Server Scripts

The input scripts used by the different pantasks servers are maintained in svn under 'operations'. Like 'ippMonitor', the installation of this directory requires site specific information:

% cd ~ipp/ipp-svn/operations
% configure --opsdir ~ipp
% make install

Pantasks Servers

Summit Copy

• Check which machine to use for the server, above.

• Start the server:

  % ssh ipp@ippc07
  % cd summitcopy
  % pantasks_server &
  

• Start the client:

  % cd ~ipp/summitcopy
  % pantasks_client
  pantasks: server input input
  pantasks: setup
  pantasks: run
  

Registration

• Check which machine to use for the server, above.

• Start the server:

  % ssh ipp@ippc09
  % cd registration
  % pantasks_server &
  

• Start the client:

  % cd ~ipp/registration
  % pantasks_client
  pantasks: server input input
  pantasks: setup
  pantasks: run
  

Replication

• Check which machine to use for the server, above.

• Start the server:

  % ssh ipp@ippc004
  % cd replication
  % pantasks_server &
  

• Start the client:

  % cd ~ipp/replication
  % pantasks_client
  pantasks: server input input
  pantasks: setup
  pantasks: run
  

Standard science

• Check which machine to use for the server, above.

• Start the server:

  % ssh ipp@ippc10
  % cd stdscience
  % pantasks_server &
  

• Start the client:

  % cd ~ipp/stdscience
  % pantasks_client
  pantasks: server input input
  pantasks: setup
  pantasks: load.hosts.wave1
  pantasks: load.hosts.wave2
  pantasks: load.hosts.wave3
  pantasks: load.hosts.compute
  pantasks: run
  pantasks: add.label (label)
  

Add as many hosts as needed. Something like 1x1, 3x2, 4x3, 4xC is probably needed full full-scale operations.

• Add the survey automation information:

  pantasks: survey.add.diff (label) (dist_group) (workdir)
  pantasks: survey.add.magic (label) (workdir) 
  pantasks: survey.add.destreak (label) (workdir)
  pantasks: survey.add.dist (label)
  

Note that the magic and destreak workdir values currently must not be nebulous names, but UNIX paths. For example:

pantasks: survey.add.diff throughput.20091104 throughput.20091104 neb://@HOST@.0/gpc1/throughput.20091104
pantasks: survey.add.magic throughput.20091104 /data/ipp050.0/gpc1_destreak/throughput.20091104
pantasks: survey.add.destreak throughput.20091104 /data/ipp050.0/gpc1_destreak/throughput.20091104
pantasks: survey.add.dist throughput.20091104

Detection publication

• Check which machine to use for the server, above.

• Start the server:

  % ssh ipp@ippc08
  % cd publishing
  % pantasks_server &
  

• Start the client:

  % cd ~ipp/publishing
  % pantasks_client
  pantasks: server input input
  pantasks: setup
  pantasks: run
  

Postage Stamp Server

• Check which machine to use for the server, above.

• Start the server:

  % ssh ipp@ipp049
  % cd pstamp
  % pantasks_server &
  

• Start the client:

  % cd ~ipp/pstamp
  % pantasks_client
  pantasks: server input input
  pantasks: setup
  pantasks: add.hosts
  pantasks: run
  

Detrend Creation

• Check which machine to use for the server, above.

• Start the server:

  % ssh ipp@ippc06
  % cd detrend
  % pantasks_server &
  

• Start the client:

  % cd ~ipp/detrend
  % pantasks_client
  pantasks: server input input
  pantasks: setup
  pantasks: run
  

IPP User backup and restore

Important files in the home directory of the IPP user on the MHPCC cluster are saved to a backup with the script ~ipp/make.backup. This uses rsync to save copies to a target backup location (currently /data/ipp004.0/ipp/operations). To restore from this directory, use rsync.

Updating Magic Code

The magic and related software is stored in ~ipp/magic_tarballs with names like magic.20091023.tgz and ssa-core-cpp.20091023.tgz. The active release is linked to ~ipp/magic.tgz and ~ipp/ssa-core-cpp.tgz. If a magic update is provided, place the source code in magic_tarballs with an equivalent name and update the ~ipp link. To build the new code, it is necessary to update the tree in the ipp build directory. Go to the top-level magic directory in the tree (eg, ~ipp/ipp-svn/magic) and do the following steps:

psconfigure
make update
make all
make install

The 'make update' step is the critical one here: it untars the code from ~ipp/magic.tgz and ~ipp/ssa-core-cpp.tgz. If the code is present, magic will be build by the standard IPP build system.