Hmm, I *think* this might be something we've seen before and is the result
of our recursive statistics (ie, the thing that makes directory sizes
reflect the data within them instead of 1 block size). If that's the case
it should resolve within a few seconds to maybe tens of seconds under
stress?
But there's also some work to force a full flush of those rstats up the
tree to enable good differential backups. Not sure what the status of that
is.
-Greg

On Fri, Sep 7, 2018 at 11:06 AM David Turner <[email protected]> wrote:

> We have an existing workflow that we've moved from one server sharing a
> local disk via NFS to secondary servers to all of them mounting CephFS.
> The primary server runs a script similar to [1] this, but since we've moved
> it into CephFS, we get [2] this error.  We added the sync in there to try
> to help this, but it didn't have an effect.
>
> Does anyone have a suggestion other than looping over a sleep to wait for
> the tar to succeed?  Waiting just a few seconds to run tar does work, but
> during a Ceph recovery situation, I can see that needing to be longer and
> longer.
>
>
> [1] #!/bin/bash
> cp -R /tmp/17857283/db.sql /cephfs/17857283/
> sync
> tar --ignore-failed-read -cvzf /cephfs/17857283.tgz /cephfs/17857283
>
> [2] tar: Removing leading `/' from member names
> /cephfs/17857283/
> /cephfs/17857283/db.sql
> tar: /cephfs/17857283: file changed as we read it
> _______________________________________________
> ceph-users mailing list
> [email protected]
> http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
>
_______________________________________________
ceph-users mailing list
[email protected]
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com

Reply via email to