Project

General

Profile

Activity

From 09/22/2014 to 10/21/2014

10/21/2014

11:10 AM Bug #9507 (Resolved): calling llistxattr(2) on a symlink crashes the client
Zheng Yan
08:09 AM Bug #9561 (Rejected): libceph: do not crash if auth reply is not understood
I believe the code is correct as is and I misdiagnosed the original issue. :( Sage Weil
08:09 AM Bug #9560 (Rejected): libceph: msg kmalloc failure handling on the reply path
I believe the code is correct as is and I misdiagnosed the original issue. Sage Weil

10/20/2014

11:07 AM Bug #9458 (Resolved): client wrongly fenced
Zheng Yan
11:06 AM Bug #1513 (Resolved): kclient: cap migration can race with cap addition on client
now cap import/export are ordered.
(commit 186e4f7a4b1883f3f46aa15366c0bcebc28fdda7, 4ee6a914edbbd2543884f0ad7d58ea4...
Zheng Yan
01:42 AM Bug #9749: kcephfs: kernel divide-by-zero crash in __validate_layout (fs/ceph/ioctl.c)
I guess we are just not used to doing it - I think we haven't filed any CVEs for ceph kernel bits (and kcephfs in par... Ilya Dryomov

10/19/2014

02:26 PM Bug #9749: kcephfs: kernel divide-by-zero crash in __validate_layout (fs/ceph/ioctl.c)
This bug appears to be exploitable by unprivileged local users and will cause a machine-wide DoS. Is there some reaso... David Ramos

10/14/2014

02:14 PM Feature #9779: libceph: sync up with objecter
Make sure not to break existing (correct!) behavior: we need to resent watch or notify when *any* member of the actin... Ilya Dryomov
02:10 PM Feature #9779 (Resolved): libceph: sync up with objecter
- the way we resend lingering requests isn't quite the same
- __map_request() is too aggressive about resending:
...
Ilya Dryomov
02:04 PM Bug #8806 (Resolved): libceph: must use new tid when watch is resent
Ilya Dryomov
09:12 AM Feature #190 (Resolved): krbd: DISCARD support
Ian Colle
12:42 AM Bug #9749 (Resolved): kcephfs: kernel divide-by-zero crash in __validate_layout (fs/ceph/ioctl.c)
fixed by "ceph: fix divide-by-zero in __validate_layout()" in the testing branch Zheng Yan

10/13/2014

12:45 PM Feature #190: krbd: DISCARD support
This should go upstream to Linus in the next day or two (for 3.18-rc1). Sage Weil
11:29 AM Feature #190: krbd: DISCARD support
Alphe Salas wrote:
> I agree with Kyle and Brian. This feature is necessary. I would like to have more information a...
Alphe Salas
11:27 AM Feature #190: krbd: DISCARD support
I agree with Kyle and Brian. This feature is necessary. I would like to have more information about the status of thi... Alphe Salas
10:19 AM Bug #9749: kcephfs: kernel divide-by-zero crash in __validate_layout (fs/ceph/ioctl.c)
Ilya Dryomov
01:07 AM Bug #9355 (Closed): rbd: map fails with EINVAL inside a container
Opened #9753. Ilya Dryomov
01:06 AM Feature #9753 (Resolved): libceph: allow custom network namespaces
See the bottom of #9355. Ilya Dryomov
12:57 AM Bug #9192: krbd: poor read (about 10%) vs write performance
Hi Eric,
Thanks for doing this. I was concerned about this being a regression after the queueing changes, but it ...
Ilya Dryomov

10/12/2014

02:44 PM Bug #9192: krbd: poor read (about 10%) vs write performance
I was able to get some dedicated test time on one of our Ceph test clusters to rerun the kernel RBD read/write tests ... Eric Eastman

10/11/2014

10:33 PM Bug #9749 (Resolved): kcephfs: kernel divide-by-zero crash in __validate_layout (fs/ceph/ioctl.c)
Our UC-KLEE tool discovered a Linux kernel divide-by-zero crash in the Ceph
client driver. I found the bug on kernel...
David Ramos

10/09/2014

09:30 AM Bug #9355: rbd: map fails with EINVAL inside a container
Thanks for the update, Ilya! You actually gave me a hint as to a workaround - run the container with `--net host` so ... Chris Armstrong
08:59 AM Bug #9355: rbd: map fails with EINVAL inside a container
The... Ilya Dryomov

10/07/2014

09:32 AM Bug #4689: libceph: don't have alloc_msg methods limit length
Related to #9560, #9561? Ilya Dryomov
09:00 AM Bug #9355: rbd: map fails with EINVAL inside a container
Ilya Dryomov

10/06/2014

10:53 PM Bug #9355: rbd: map fails with EINVAL inside a container
Note that we only see the debug output when we're trying to write to the RBD bus directly on the host - from within t... Chris Armstrong
10:32 PM Bug #9355: rbd: map fails with EINVAL inside a container
Here's some debugging after disabling auth.
As root on the CoreOS host, echoing directly into the RBD bus also doe...
Chris Armstrong
10:04 PM Bug #9355: rbd: map fails with EINVAL inside a container
For posterity, recording my conversation with Josh here. http://irclogs.ceph.widodh.nl/index.php?date=2014-09-04
<...
Chris Armstrong
10:03 PM Bug #9355: rbd: map fails with EINVAL inside a container
Seeing the same issue on a 3.16.2 kernel: ... Chris Armstrong
08:55 PM Bug #9355: rbd: map fails with EINVAL inside a container
A fellow member of the CoreOS community is also running into this: https://groups.google.com/forum/#!topic/coreos-use... Chris Armstrong

09/23/2014

02:00 PM Bug #8568: libceph: kernel BUG at net/ceph/osd_client.c:885
BUG_ON(!list_empty(&req->r_req_lru_item)) in __kick_osd_requests()
Can't reproduce but need to look harder into ho...
Ilya Dryomov
09:39 AM Bug #9573 (New): krbd: investigate a dd-in-a-loop slowdown
Reported at the bottom of #8818. Ilya Dryomov

09/22/2014

04:08 AM Bug #8979 (Resolved): GPF kernel panics - auth?
Landed in 3.17-rc5. Opened #9560 and #9561 for the issues mentioned above. Ilya Dryomov
04:04 AM Bug #9561 (Rejected): libceph: do not crash if auth reply is not understood
Ilya Dryomov
04:02 AM Bug #9560 (Rejected): libceph: msg kmalloc failure handling on the reply path
Ilya Dryomov
 

Also available in: Atom