[ceph-users] cephfs is growing up rapidly

Zhenshi Zhou deaderzzs at gmail.com
Fri Sep 14 03:05:56 PDT 2018


Hi,

I use rsync to back up filse. I'm not sure if it update files by removing
and retransfering or by overwiriting the files. Options of rsync command
include '-artuz', and I'm trying to figure out how it works.

MDS logs has nothing error as I think it's not the same bug (or it's not
a bug).

Also, I checked the performance counters of MDS:

    "mds_cache": {
        "num_strays": 1,
        "num_strays_delayed": 0,
        "num_strays_enqueuing": 0,
        "strays_created": 604527,
        "strays_enqueued": 604528,
        "strays_reintegrated": 0,
        "strays_migrated": 0,
        "num_recovering_processing": 0,
        "num_recovering_enqueued": 0,
        "num_recovering_prioritized": 0,
        "recovery_started": 7,
        "recovery_completed": 7,
        "ireq_enqueue_scrub": 0,
        "ireq_exportdir": 0,
        "ireq_flush": 0,
        "ireq_fragmentdir": 0,
        "ireq_fragstats": 0,
        "ireq_inodestats": 0
    }

    "purge_queue": {
        "pq_executing_ops": 0,
        "pq_executing": 0,
        "pq_executed": 604533
    }

John Spray <jspray at redhat.com> 于2018年9月14日周五 下午5:19写道:

> On Fri, Sep 14, 2018 at 7:25 AM Zhenshi Zhou <deaderzzs at gmail.com> wrote:
> >
> > Hi,
> >
> > I have a ceph cluster of version 12.2.5 on centos7.
> >
> > I created 3 pools, 'rbd' for rbd storage, as well as 'cephfs_data'
> > and 'cephfs_meta' for cephfs. Cephfs is used for backing up by
> > rsync and volumes mounting by docker.
> >
> > The size of backup files is 3.5T. Besides, docker use less than
> > 60G spaces. 'cephfs df' shows no more than 3.6T at first. But the
> > used size is 3.9T now. And according to my observation, the used
> > size (cephfs df) is growing 60-100G everyday. As I check the origin
> > files, the whole size is almost the same size as the beginning does.
> >
> > Does anybody encounter the same issue?
>
> Presumably your workload is deleting the previous backup before
> creating a new one?
>
> The most similar sounding bug is http://tracker.ceph.com/issues/24533,
> where the deletion path could get stuck.  You can check your MDS logs
> for errors to see if it's the same.
>
> You can also look at the MDS performance counters (`ceph daemon
> mds.<id> perf dump`) and show us the "num_strays" fields and the
> purge_queue section.
>
> John
>
>
>
>
>
> > _______________________________________________
> > ceph-users mailing list
> > ceph-users at lists.ceph.com
> > http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.ceph.com/pipermail/ceph-users-ceph.com/attachments/20180914/46bf13df/attachment.html>


More information about the ceph-users mailing list