Active Cluster for File
Hello,
I have another question. I am currently implementing Active Cluster for FILE, but regarding the server interface configuration—specifically for the Realm server—I need to add the sub-interfaces for each array, correct? For example, I add `ct0.eth1` for Array 1; then, since `array1:ct0.eth1` is automatically replicated, I should edit it to add the `ct0.eth1` on Array 2, and likewise add the `Array2:ct0.eth1` interface on Array 1, right? To test this, I make the change using Bulk Edit, select the "Remediate" option, and I am able to ping the interface IP. Is this the correct procedure?
I didn't find any mention of this "Remediate" procedure in the articles, only in the GUI itself.
Thank you.
Hi Thomas,
It's preferable to configure the file VIF with multiple sub-interfaces per controller (e.g. two ethernet interfaces across different PCIe cards or slots per controller) and across both arrays that are hosting the stretched realm. This way, local failover between controllers is available, and remote failover in case of site-wide disaster is also available. The goal is to configure the file VIF (and the rest of the solution) so that there is no single point of failure.
The remediate command is one mechanism to test 'fail-over' via software. Using the remediate command changes which array process writes and makes the VIF's shares or exports available for mounting by clients on that side. When you perform it, it should issue a gratuitous ARP and tell the switches on the other side that the MAC address and IP address of the VIF are now active on the other ports. Syntax and usage of the remediate command is covered here a little more:
https://support.everpuredata.com/v/u/pdf/purity_fa_cli_guide_pdf_6122.pdf
Please let me know if you have more questions.
Cheers,
Quinn
