Bug #247
closed
osd: allow separate interface for internal cluster traffic
Added by Sage Weil almost 14 years ago.
Updated over 13 years ago.
Description
One interface for external access (client i/o), one for cluster io (replication, recovery).
- Status changed from New to In Progress
- Assignee set to Greg Farnum
I'm just going to begin by setting up the OSD code to accept and work with multiple messengers.
Other parts may be a bit trickier:
1) the OSDMap will need to carry both addresses in an appropriate fashion
2) Origin detection (throughout the codebase) will probably need to be reworked to identify both addresses as the same OSD.
3) Other big issues I'm missing?
- Target version set to v0.22
- Status changed from In Progress to 7
Am running the osd_msgrs branch in qa today, unless that finds problems that weren't exposed by a bunch of system startups and rados benches I will probably merge this into unstable tomorrow.
- Status changed from 7 to Resolved
Merged this into unstable.
Also available in: Atom
PDF