Clustered SCSI target using RBD Status » History » Revision 1
Revision 1/2
| Next »
Jessica Mack, 07/06/2015 10:03 PM
Clustered SCSI target using RBD Status¶
Summary¶
The goal of this project is to modify the Linux target layer, LIO, to be able to support active/active access to a device across multiple nodes running LIO. The changes to LIO are being done in a generic way to allow other cluster aware devices to be used, but our focus is on using RBD.
More info can be found in the Hammer blue print here:
https://wiki.ceph.com/Planning/Blueprints/Hammer/Clustered_SCSI_target_using_RBD
This will be a update on what has been completed and open issues.
Owners¶
- Name (Affiliation)
- Name (Affiliation)
- Name
Interested Parties¶
- Name (Affiliation)
- Name (Affiliation)
- Name
Current Status¶
Detailed Description¶
Open issues from the Hammer blue print include:
1. - SCSI task management (TMF) / Unit Attention (UA) / PREEMPT AND ABORT Handling.
This has not yet been worked on since the Hammer discussion.
2. Configuration and Device State.
- The current plan is to use pacemaker/corosync for the setup and syncing device state across nodes.
- For management, I am looking into implementing a libStorageMgmt (http://sourceforge.net/projects/libstoragemgmt/) plugin, so tools like lsmcli can manage the target.
Both of these need more research and discussion.
Work items¶
Coding tasks¶
- Task 1
- Task 2
- Task 3
Build / release tasks¶
- Task 1
- Task 2
- Task 3
Documentation tasks¶
- Task 1
- Task 2
- Task 3
Deprecation tasks¶
- Task 1
- Task 2
- Task 3
Updated by Jessica Mack almost 9 years ago · 1 revisions