Scope

• This article describes a best practice on how to install and update JobScheduler on a Solaris machine
• Note that Solaris is not supported a supported platform (see article Which platforms is JobScheduler available for and what platform support is provided?), therefore there is no setup for installation on Solaris environments
• Therefore it It is recommended (due to analogies between operating systems) to perform the installation through a setup on a Linux environment and then transfer transfering the folder structure to the Solaris environment.
• In any case, it is required to compile the JobScheduler binaries in order to have a JobScheduler running for Solaris, see How to build the JobScheduler Engine and the JobScheduler components from the sources for Solaris.

• Jira
  server SOS JIRA columns key,summary,type,created,updated,due,assignee,reporter,priority,status,resolution serverId 6dc67751-9d67-34cd-985b-194a8cdc9602 key JS-1609

Best Practice: Recommended Steps

Step 1: Installing JobScheduler through setup on a Linux environment

In order to have a folder structure for the later installation of JobScheduler on Solaris (without a setup), it is highly recommended to do a first installation of JobScheduler in a Linux environment. We could do that on Solaris as well, however, errors would be thrown when using the setup, since some commands are not allowed on Solaris but on Linux.

...

Once the folder structure is ready and clean, adjust the rights giving the JobScheduler user the necessary rights for these folders.

Step 2: Compiling JobScheduler sources on a Solaris machine

The next step is compiling the JobScheduler sources on the Solaris machine. This step has to be done following the instructions on the article How to build the JobScheduler Engine and the JobScheduler components from the sources for Solaris.

...

1. scheduler-engine-doc
2. scheduler-engine


Step 3: Configuration after compiling sources

Once the JobScheduler sources have been compiled, the following has to be configured:

• From the compiled sources .\scheduler-engine\engine-setup\target\setup\scheduler.linux-x64\bin:
  • Replace library libjobscheduler-engine.so by the generated one under the folder lib
  • Replace the application scheduler by the generated one under the folder bin
• Within the folder bin:
  • Adapt to Solaris syntax the file jobscheduler_environment_variables.sh
  • Check the syntax for the start script jobscheduler.sh
• Check the configuration for the following files under the folder config:
  • factory.ini
    • Add mail adresses if required
    • Add SMTP server name if required
  • hibernate.cfg.xml
  • jetty.xml
  • scheduler.xml
  • sos.ini
  • sos_settings.ini
  • web.xml
• In case you could not use the same database during the installation on Linux, do the following to create the tables for this JobScheduler:
  • Edit HOSTNAME value in ./db/[dbms]/scheduler_instances_insert.sql
  • Execute ./install/scheduler_install_tables.sh
• Download SWT from Eclipse site
  • Extract the content
  • Select the file swt.jar
  • Substitute this file for the one under ./lib/3rd-party/org.eclipse.swt.gtk.linux.x86_64-4.3.jar

Step 4: Updating JobScheduler

A procedure should be implemented for updating JobScheduler in this case. The recommended from our side is the following:

1. Use the setup to update JobScheduler on the Linux machine
2. Write a script that would delete the folders as indicated on Step 1: Installing JobScheduler through setup
3. Use the same script to carry out any action done in Step 3: Configuration after compiling sources
4. Use the same script to stamp the files that have been replaced or modified with a "-template" at the end, for example "factory.ini-template". That way
   1. you have a template on a Linux machine
   2. moreover, the modified files are not overwritten when unpacking the tarball file on the Solaris machine