Ceph

05/11/2023

08:48 AM RADOS Bug #56707: pglog growing unbounded on EC with copy by ref

王子敬 wang wrote:
> I have also experienced this situation here
>
> - Create 30 objects in bucket1 using put
> - ... 王子敬 wang

03:32 AM RADOS Bug #56707: pglog growing unbounded on EC with copy by ref

I have also experienced this situation here
- Create 30 objects in bucket1 using put
- Using 30 objects as the s... 王子敬 wang

12/29/2022

07:26 AM bluestore Bug #53002: crash BlueStore::Onode::put from BlueStore::TransContext::~TransContext

(gdb) bt
#0 0x00007fc82cdb64aa in tc_newarray () from /lib64/libtcmalloc.so.4
#1 0x000055f6876050ba in ceph::buff... 王子敬 wang

12/26/2022

04:54 AM RADOS Bug #58356 (Need More Info): osd：segmentation fault in tcmalloc's ReleaseToCentralCache

osd crash. Program terminated with signal SIGSEGV, Segmentation fault Detailed stack information is in the attachme... 王子敬 wang

03:50 AM RADOS Bug #58355 (Need More Info): OSD: segmentation fault in tc_newarray

The osd core appears when cosbench uploads data. Detailed stack information is in the attachment， in Bluestore::_write. 王子敬 wang

12/13/2022

02:18 AM Ceph Bug #58120: watcher remains after "rados watch" is interrupted

Ilya Dryomov wrote:
> How does it write data to RBD? Does it use librbd API?
yes
"pkill -9 tfs-rep; systemctl ... 王子敬 wang

12/12/2022

10:50 AM Ceph Bug #58120: watcher remains after "rados watch" is interrupted

Ilya Dryomov wrote:
> I'm confused. What is tfs-rep? Can you describe what this process does and how that relates ... 王子敬 wang

05:36 AM Ceph Bug #58120: watcher remains after "rados watch" is interrupted

王子敬 wang wrote:
> Ilya Dryomov wrote:
> > > The client was killed.
> >
> > What was the client that got killed -... 王子敬 wang

03:49 AM Ceph Bug #58120: watcher remains after "rados watch" is interrupted

Ilya Dryomov wrote:
> > The client was killed.
>
> What was the client that got killed -- a QEMU VM, "rbd map" ma... 王子敬 wang

12/08/2022

02:11 AM Ceph Bug #58120: watcher remains after "rados watch" is interrupted

Ilya Dryomov wrote:
> > What I see from the analysis log is as follows, in the picture 32-590, not has watch->connec... 王子敬 wang