[prev in list] [next in list] [prev in thread] [next in thread] 

List:       ceph-devel
Subject:    Re: cuttlefish ceph-fuse writes make for frequent inconsistent pgs
From:       Gregory Farnum <greg () inktank ! com>
Date:       2013-05-28 17:15:36
Message-ID: CAPYLRzjxc_0obVo5yLDuJXZgtfDrv-Y=RUFK4=qqtLbr-HafWQ () mail ! gmail ! com
[Download RAW message or body]

On Tue, May 28, 2013 at 2:50 AM, Alexandre Oliva <oliva@gnu.org> wrote:
> On May 27, 2013, Samuel Just <sam.just@inktank.com> wrote:
>
>> Thanks for the detailed information!  Xfs?
>
> btrfs.
>
>> Were there any osd restarts/power cycles?
>
> I can't rule that out, but I'm afraid it was a while ago, and my logs
> don't go that far back.

In general I can't imagine a mechanism by which the client could have
caused the symptoms you're describing — it's supposed to be
impossible, and the ceph-fuse client doesn't use any of the access
methods which are more likely to break the safety invariants.

Do you have the bad file data or anything? Solving this sounds like it
would be a forensic journey through the OSD encoding and transmission
infrastructure. :/
-Greg
Software Engineer #42 @ http://inktank.com | http://ceph.com
--
To unsubscribe from this list: send the line "unsubscribe ceph-devel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
[prev in list] [next in list] [prev in thread] [next in thread]