Bug #10762: mon: osd gets marked down twice - Ceph - Ceph

Actions

Copy link

Bug #10762

closed

mon: osd gets marked down twice

Added by Sage Weil about 9 years ago. Updated about 9 years ago.

Status:

Resolved

Priority:

Urgent

Assignee:

Category:

Target version:

% Done:

Source:

Q/A

Tags:

Backport:

giant,firefly

Regression:

Severity:

3 - minor

Reviewed:

Affected Versions:

ceph-qa-suite:

Pull request ID:

Crash signature (v1):

Crash signature (v2):

Description

- osd has intermittnet network issue
- gets marked down
- network fixed
- osd comes back up
- mon election (or something loady on the mons)
- osd marked down again
- osd comes back

The bug is that hte preprocess_failure checks for is_down() but doesn't verify that the reproting epoch is after get_up_from, leading to dups.

Actions

Copy link

Updated by Sage Weil about 9 years ago

https://www.dropbox.com/s/vdzl005n2qiwlee/ceph.log.gz?dl=0
https://www.dropbox.com/s/to26i8k11vp9t8k/ceph-mon.0.log.gz?dl=0
https://www.dropbox.com/s/j5e3rujs7qjouzh/ceph-mon.2.log.gz?dl=0

(logs from dan)

Actions

Copy link