Service Reliability
The hardware employed to provide the StorWIS service is specifically designed for high availability. Redundancy is therefore provided for the following components:
- Storage array controllers
- Power & network connectivity
- Data on disk is also protected via various protection mechanisms, including hardware-level health checks, with support for automated 'call-home' to the manufacturer's support center
All arrays are monitored with alarming for errors and any potential failure 24 hours a day, 7 days a week. This high level of monitoring, combined with redundancy built into the storage controller arrays, allows us to assure the highest possible solution availability.
Service Availability
The StorWIS storage service is operated by our IT staff to guarantee 99.9% availability, and is intended to remain accessible to all research groups at all times, except during scheduled maintenance windows and preventive maintenance updates.
Thanks to the service’s resilient design, outages are expected to be relatively rare, and will be limited to patches and upgrades requiring entire arrays to be shut down, and/or infrastructure (network, power) related interruptions. Any outages – whether planned or unscheduled – will be posted on our System Health and Bulletin Board, which is accessible via our site’s homepage.