[LU-2960] DNE: "lfs mdts" prints strange index for second mdt Created: 13/Mar/13 Updated: 25/Mar/13 Resolved: 25/Mar/13 |
|
| Status: | Resolved |
| Project: | Lustre |
| Component/s: | None |
| Affects Version/s: | Lustre 2.4.0 |
| Fix Version/s: | Lustre 2.4.0 |
| Type: | Bug | Priority: | Blocker |
| Reporter: | Robert Read (Inactive) | Assignee: | Di Wang |
| Resolution: | Fixed | Votes: | 0 |
| Labels: | LB | ||
| Severity: | 3 |
| Rank (Obsolete): | 7217 |
| Description |
[root scratch]# lfs mdts MDTS: 0: scratch-MDT0000_UUID ACTIVE -1431271368: scratch-MDT0001_UUID ACTIVE |
| Comments |
| Comment by Robert Read (Inactive) [ 13/Mar/13 ] |
|
I setup another filesystem with 4 MDTs, and got this: [root]# lfs mdts MDTS: 0: scratch-MDT0000_UUID ACTIVE 1431808500: scratch-MDT0001_UUID ACTIVE 1431825256: scratch-MDT0002_UUID ACTIVE -1431707840: scratch-MDT0003_UUID ACTIVE |
| Comment by Peter Jones [ 16/Mar/13 ] |
|
Di Could you please comment on this one? Thanks Peter |
| Comment by Di Wang [ 17/Mar/13 ] |
|
Sure, it seems some garbage in the index entries. I will work on it. |
| Comment by Oleg Drokin [ 19/Mar/13 ] |
|
lu-2986 might be another impact of this bug at bigendian nodes, wangdi, can you please check that? |
| Comment by Di Wang [ 20/Mar/13 ] |
| Comment by Di Wang [ 20/Mar/13 ] |
|
Oleg, for this ticket, it just uses the wrong part to output of lfs mdts, and |
| Comment by Peter Jones [ 25/Mar/13 ] |
|
Landed for 2.4 |