Qumulo Drive Failure Protection

Important! Additional drive failures may be considered safe within the following scenarios depending on your cluster configuration and which drives have failed. Refer to the Qumulo Core Web UI for more details to confirm the most accurate state of your system.

REQUIREMENTS

Cluster with 4 or more nodes running Qumulo Core for 2 Drive Failure Protection
Cluster with 5 or more nodes running Qumulo Core 2.7.10 and above for 3 Drive Failure Protection
Cluster with 50 or more nodes running Qumulo Core 2.13.4 and above for 4 drive Failure Protection.

NOTE: The recommended 2 or 3 drive protection level will be selected by default based on the cluster size and node type at cluster creation while 4 drive failure protection requires the QQ CLI to configure. For more information, reference the Create a Qumulo Cluster with 2.7.10 and above article.

2 DRIVE FAILURE PROTECTION

Protection State	Severity	Failure Scenarios
Data is Protected and Balanced	None	Nodes & Drives are fully operational
Data is Protected and Balanced You may replace a failed drive at any time.	Medium	1 drive failure 2 drive failures
Data is Reprotecting You may replace a failed drive at any time. The cluster will complete reprotection and rebalance.	Medium	1 drive failure 2 drive failures
Data is Protected	Medium	1 node offline
Data is available, but we are unable to run reprotect	High	More than 2 drive failures
Data is unavailable, but intact	Very High	1 drive failure & 1 node offline 2 or more nodes offline 2 or more drive failures & any node offline

3 DRIVE FAILURE PROTECTION

Protection State	Severity	Failure Scenarios
Data is Protected and Balanced	None	Nodes & Drives are fully operational
Data is Protected and Balanced You may replace a failed drive at any time.	Medium	1 drive failure 2 drive failures 3 drive failures
Data is Reprotecting You may replace a failed drive at any time. The cluster will complete reprotection and rebalance.	Medium	1 drive failure 2 drive failures 3 drive failures
Data is Protected	Medium	1 node offline
Data is Reprotecting You may replace a failed drive at any time. The cluster will complete reprotection and rebalance.	High	3 drive failures
Data is Protected Data is available but reprotection is unavailable until the node is brought back online.	High	1 drive failure and 1 node offline
Data is unavailable, but intact	Very High	2 or more nodes offline 2 or more drive failures & any node offline

4 DRIVE FAILURE PROTECTION

Protection State	Severity	Failure Scenarios
Data is Protected and Balanced	None	Nodes & Drives are fully operational
Data is Protected and Balanced You may replace a failed drive at any time.	Medium	1 drive failure 2 drive failures 3 drive failures 4 drive failures
Data is Reprotecting You may replace a failed drive at any time. The cluster will complete reprotection and rebalance.	Medium	1 drive failure 2 drive failures 3 drive failures
Data is Protected	Medium	1 node offline
Data is Reprotecting You may replace a failed drive at any time. The cluster will complete reprotection and rebalance.	High	4 drive failures
Data is Protected Data is available but reprotection is unavailable until the node is brought back online.	High	1 drive failure and 1 node offline
Data is unavailable, but intact	Very High	2 or more nodes offline 2 or more drive failures & any node offline

RESOLUTION

You should now have an overall understanding of 2, 3, and 4 drive failure protection in Qumulo Core

ADDITIONAL RESOURCES

Create a Qumulo Cluster with 2.7.10 and above

Qumulo Care Proactive Monitoring

QQ CLI: Cluster Configuration

Video: HDD Field Replacement Unit

Like what you see? Share this article with your network!

Was this article helpful?

0 out of 1 found this helpful

Comments

0 comments

Please sign in to leave a comment.