Skip to content
GitLab
Projects Groups Topics Snippets
  • /
  • Help
    • Help
    • Support
    • Community forum
    • Submit feedback
  • Register
  • Sign in
  • EAR EAR
  • Project information
    • Project information
    • Activity
    • Labels
    • Members
  • Repository
    • Repository
    • Files
    • Commits
    • Branches
    • Tags
    • Contributor statistics
    • Graph
    • Compare revisions
  • Issues 0
    • Issues 0
    • List
    • Boards
    • Service Desk
    • Milestones
  • CI/CD
    • CI/CD
    • Pipelines
    • Jobs
    • Schedules
  • Deployments
    • Deployments
    • Releases
  • Wiki
    • Wiki
  • Activity
  • Graph
  • Create a new issue
  • Jobs
  • Commits
  • Issue Boards
Collapse sidebar
  • EAR_teamEAR_team
  • EAREAR
  • Wiki
  • High availability

High availability · Changes

Page history
ear-5.0 authored Sep 02, 2024 by Oriol Vidal Teruel's avatar Oriol Vidal Teruel
Show whitespace changes
Inline Side-by-side
High-availability.md 0 → 100644
View page @ 33467cc1
EAR is designed to provide support for those systems where High Availability (HA) of services/data is a must.
Currently, just the [EAR Database Manager](Architecture#ear-database-manager) and the [EAR Database](EAR-Database) components offer HA support.
The latter can be replaced by industry software like [Galera Cluster](https://galeracluster.com/).
# EAR Database Manager HA
Database daemons can be configured and deployed in pairs following a *server*/*mirror* schema.
Buffering before reporting to the Database is the main duty of this Daemon, so having a mirror ensures no data lose in the case the service stops or the node where it is being running fails unexpectedly.
Both services buffer data, but just the server inserts it to the Database.
If it fails, the mirror starts insertion process.
You can read how to configure two EAR Database Managers on the Configuration Guide's [Island description](Configuration#island-description) section.
# EAR Database HA
If the EAR Database is not deplyed on a HA system, you can manually configure EAR to report data on two databases.
Just three actions must be performed:
- Create two databases on two different servers. You have two ways:
1. Use *edb_create* command.
2. Use `edb_create -o` and redirect the output to a file. You will have the SQL query set saved to be executed directly in the DB server (mysql). \*
- Specify **DBSECIP** field in the `ear.conf` (and propagate changes).
- Restart Database Manager daemons.
- Only supported in mysql.
\* You must add a semi-colon (*;*) at the end of each line.
Clone repository
  • Home
  • User guide
    • Use cases
      • MPI applications
      • Non-MPI applications
      • Others
    • EAR data
    • Submission flags
    • Examples
    • Job accounting
    • Job energy optimization
    • Data visualization
  • Commands
    • Job accounting (eacct)
    • System energy report (ereport)
    • EAR control (econtrol)
    • Database management
    • erun
    • ear-info
  • Environment variables
    • Support for Intel(R) speed select technology
  • Admin Guide
    • Quick installation guide
    • Installation from RPM
    • Updating
  • Installation from source
  • Architecture/Services
  • High Availability support
  • Configuration
  • Learning phase
  • Plug-ins
  • Powercap
  • Report plug-ins
  • Database
    • Updating the database from previous EAR versions
    • Tables description
  • Supported systems
  • EAR Data Center Monitoring
  • CHANGELOG
  • FAQs
  • Known issues
  • Tutorial