[LU-16722] LMR1a: MGS config log restructuring and redundancy

• Type: Improvement
• Resolution: Unresolved
• Priority: Minor
• Fix Version/s: Lustre 2.17.0
• Affects Version/s: Lustre 2.16.0
• Labels: config medium
• Assignee: Andreas Dilger
• Reporter: Colin Faber

Description

Restructure the MGS config management system to better handle modern environments.

Allowing multiple redundant MGS/MGT devices in a filesystem (e.g. one replica running on each of 4 separate MDS nodes that the clients can use for initial mounting as well as Imperative Recovery notification of server failover) would significantly improve reliability, since clients could still mount in the face of an MGS failure, and imperative recovery would continue to work if the node running the (single) MGS was the one that failed.

Issue Links

• is related to: LU-16475 Reusing OST indexes after lctl del_ost
• is related to: LU-16738 Improve mount.lustre with many MGS NIDs
• is related to: LU-17691 add interface to deregister file system/targets on MGS
• is related to: LU-18164 MGS should dynamically track server NIDs
• is related to: LU-10360 use Imperative Recovery logs for client->MDT/OST connections
• is related to: LU-17819 LMR1a: Replicate MDT0000 Services to Other MDS
• is related to: LU-13306 allow clients to accept mgs_nidtbl_entry with IPv6 NIDs
• is related to: LU-13308 update changelog_ext_nid to handle IPv6 addresses