[LU-9127] too many debug messages from tgt_cb_last_committed() Created: 15/Feb/17 Updated: 05/Aug/20 Resolved: 18/Mar/17 |
|
| Status: | Resolved |
| Project: | Lustre |
| Component/s: | None |
| Affects Version/s: | Lustre 2.7.0 |
| Fix Version/s: | Lustre 2.10.0 |
| Type: | Bug | Priority: | Minor |
| Reporter: | Andrew Perepechko | Assignee: | WC Triage |
| Resolution: | Fixed | Votes: | 0 |
| Labels: | patch | ||
| Attachments: |
|
||||
| Issue Links: |
|
||||
| Severity: | 3 | ||||
| Rank (Obsolete): | 9223372036854775807 | ||||
| Description |
|
tgt_cb_last_committed() prints a D_HA message even if last_committed was not updated. The problem is the cpu overhead associated with a bunch of similar (and mostly useless) messages and potential Lustre debug log overflow. A trivial patch will be uploaded shortly. |
| Comments |
| Comment by Gerrit Updater [ 15/Feb/17 ] |
|
Andrew Perepechko (andrew.perepechko@seagate.com) uploaded a new patch: https://review.whamcloud.com/25469 |
| Comment by Andreas Dilger [ 15/Feb/17 ] |
|
Is this different from patch http://review.whamcloud.com/14611: LU-6527 ext4: journal_commit_callback optimization
Don't take spinlock in tgt_cb_last_committed, if
exp_last_committed was updated with higher trasno.
Also change list_add_tail to list_add. It gives
advantages to ldiskfs in tgt_cb_last_committed.
In the beginning of list will be placed thandles
with the highest transaction numbers. So at the
first iterations we will have the highest transno.
It will save from extra call of ptlrpc_commit_replies.
Signed-off-by: Sergey Cheremencev <sergey.cheremencev@seagate.com>
Xyratex-bug-id: MRP-2575
That was landed to master for 2.7.61 but and the backport for b2_7_fe is https://review.whamcloud.com/19904 |
| Comment by Andreas Dilger [ 15/Feb/17 ] |
|
Ah, I see it now... |
| Comment by Gerrit Updater [ 01/Mar/17 ] |
|
Oleg Drokin (oleg.drokin@intel.com) merged in patch https://review.whamcloud.com/25469/ |
| Comment by Peter Jones [ 18/Mar/17 ] |
|
Landed for 2.10 |