Ceph

10/15/2018

07:19 PM Ceph Bug #15386: bluestore+spdk results in osd abort with _read_fsid unparsable uuid

Tracing through the source code it looks like I'm barking up the wrong tree. I believe this is saying the /var/lib/c... Chris Holcombe

07:04 PM Ceph Bug #15386: bluestore+spdk results in osd abort with _read_fsid unparsable uuid

Note this also occurs with ceph 12.2.7 on bionic. It was installed via cloud archive:... Chris Holcombe

06:00 PM Ceph Bug #15386: bluestore+spdk results in osd abort with _read_fsid unparsable uuid

I was able to reproduce this locally on a virtual machine with lvm on ubuntu 18.04. It seems that LVM produces UUID'... Chris Holcombe

04/17/2018

02:09 AM RADOS Documentation #23765 (New): librbd hangs if permissions are incorrect

I've been building rust bindings for librbd against ceph jewel and luminous. I found out by accident that if a cephx... Chris Holcombe

10/02/2017

05:52 PM Ceph Bug #18478: "FAILED assert(crypto_context != __null)" in rados-kraken-distro-basic-smithi

I'm also seeing this on jewel radosgw's:... Chris Holcombe

11/08/2016

09:35 PM Ceph Bug #17829 (Closed): CephFS does not support setting extended attributes

I deployed a jewel ceph cluster with CephFS and mounted it with ceph-fuse. Using setfattr I was unable to set any ex... Chris Holcombe

09:25 PM CephFS Bug #17828 (Need More Info): libceph setxattr returns 0 without setting the attr

Using the jewel libcephfs python bindings I ran the following code snippet:... Chris Holcombe

07/21/2016

03:27 PM Ceph Bug #16755: ceph-disk: encryption assumes admin key is present

Put up a PR: https://github.com/ceph/ceph/pull/10382 Chris Holcombe

07/20/2016

03:33 PM Ceph Bug #16755 (Resolved): ceph-disk: encryption assumes admin key is present

When testing the ceph-disk in jewel new behavior was noticed where it assumes an admin key is present on all the osd ... Chris Holcombe

12/03/2015

06:34 PM Ceph Bug #13972: osd/ECUtil.h: 117: FAILED assert(old_size == total_chunk_size) in 0.80.10

After rolling the rgw nodes the cluster went back to active+clean and the osds aren't crashing anymore. Chris Holcombe