Project

General

Profile

Actions

Support #6238

closed

About the data migration in Ceph

Added by chen atrmat over 10 years ago. Updated over 10 years ago.

Status:
Rejected
Priority:
Normal
Assignee:
-
Category:
OSDMap
Target version:
-
% Done:

0%

Tags:
Reviewed:
Affected Versions:
Pull request ID:

Description

Hi all,
recently i read the source code and paper, and i have some questions about the data movement:
1. when OSD's add or removal, how Ceph do this data migration and rebalance the crush map? is it the rados modify the crush map or cluster map, and the primary OSD does the data movement according to the cluster map? how to found it in the source code?

2. when OSD's down or failed, how Ceph recover the data in other OSDs? is it the primary OSD copy the PG to the new located OSD?
3. the OSD has 4 status bits: up,down,in,out. But i can't found the defined status-- CEPH_OSD_DOWN, is it the OSD call the function mark_osd_down() to modify the OSD status in OSDMap?
Very appreciate ur kindly reply!
Thx!
Actions #1

Updated by Greg Farnum over 10 years ago

  • Status changed from New to Rejected

These sorts of questions are appropriate for the ceph-users list. Please send them there. :)

Actions #2

Updated by chen atrmat over 10 years ago

Greg Farnum wrote:

These sorts of questions are appropriate for the ceph-users list. Please send them there. :)

Hi Greg,
Thx, and the ceph-users list is in where ?

Actions #3

Updated by Ian Colle over 10 years ago

You can find all the information on signing up for the mailing lists here:

http://ceph.com/resources/mailing-list-irc/

Actions

Also available in: Atom PDF