Re: changing from default journals to external journals

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



On Mon, 21 Oct 2013, Snider, Tim wrote:
> 
> Your reply seems to contradict the reply from Sage:
> 
>     > Sage -
> 
>     > The journal device needs a file system created does that device need
> to be mounted?
> 
>         Yes.. the mkjournal step needs to writes to the journal (wehther
> it's a file or block device).

We just need to read/write whatever the journal symlink points to. Ideally 
that is a raw partition/block device.  If it's a file, the containing file 
system needs to be mounted so that the file is accesible.

As Kurt suggests, though, a raw partition is preferable!

sage


> 
> Tim
> 
>  
> 
> From: Kurt Bauer [mailto:kurt.bauer@xxxxxxxxxxxx]
> Sent: Monday, October 21, 2013 10:16 AM
> To: Snider, Tim
> Cc: ceph-users@xxxxxxxxxxxxxx
> Subject: Re:  changing from default journals to external
> journals
> 
>  
> 
> Hi,
> 
> neither do you need a filesystem on the partition, nor does it have to be
> mounted. You can link the journal against the raw partition.
> 
> Best regards,
> Kurt
> 
> Snider, Tim schrieb:
> 
> Sage - 
> 
> The journal device needs a file system created does that device need to be m
> ounted?
> 
> Tim
> 
>  
> 
> -----Original Message-----
> 
> From: Sage Weil [mailto:sage@xxxxxxxxxxx] 
> 
> Sent: Thursday, October 17, 2013 11:02 AM
> 
> To: Snider, Tim
> 
> Cc: ceph-users@xxxxxxxxxxxxxx
> 
> Subject: RE:  changing from default journals to external journal
> s
> 
>  
> 
> On Thu, 17 Oct 2013, Snider, Tim wrote:
> 
> /var/lib/ceph/osd/ceph-NNN/journal is a "real" file on my system:
> 
>      ls -l  /var/lib/ceph/osd/ceph-0/journal 
> 
>      -rw-r--r-- 1 root root 1073741824 Oct 17 06:47 
> 
> /var/lib/ceph/osd/ceph-0/journal
> 
>  
> 
> Any problems with my proposed added steps (3 - 5)?
> 
>  
> 
> 1.       stop a ceph-osd daemon
> 
> 2.       ceph-osd --flush-journal -i NNN
> 
> 3.       (+) cp /var/lib/ceph/osd/ceph-NNN/journal /var/lib/ceph/osd/ceph-NN
> N/journal.saved
> 
> 4.       (+) create a new empty journal file: 
> 
>          touch /mount/sdzNNN/journal
> 
> 5.       (+) Create the symbolic link for Ceph:
> 
>          ln -s /mount/sdzNNN/journal     var/lib/ceph/osd/ceph-NNN/journal
> 
>  
> 
> 3. mv journal journal.old
> 
> 4. ln -s /dev/whatever journal
> 
>  
> 
> (you're better off using a raw partition or other block device than a
> 
> file.)  or,
> 
>  
> 
> 4. touch /new/path
> 
> 5. ln -s /other/path journal
> 
>  
> 
> 6.       ceph-osd --mkjournal -i NNN
> 
> 7.       start ceph-osd
> 
>  
> 
> Tim
> 
> -----Original Message-----
> 
> From: Sage Weil [mailto:sage@xxxxxxxxxxx]
> 
> Sent: Wednesday, October 16, 2013 5:02 PM
> 
> To: Snider, Tim
> 
> Cc: ceph-users@xxxxxxxxxxxxxx
> 
> Subject: Re:  changing from default journals to external 
> 
> journals
> 
>  
> 
> On Wed, 16 Oct 2013, Snider, Tim wrote:
> 
> I configured my cluster using the default journal location for my 
> 
> osds. Can I migrate the default journals to explicit separate 
> 
> devices without a complete cluster teardown and reinstallation? How?
> 
> - stop a ceph-osd daemon, then
> 
> - ceph-osd --flush-journal -i NNN
> 
> - set/adjust the journal symlink at /var/lib/ceph/osd/ceph-NNN/journal to
> 
>   point wherever you want
> 
> - ceph-osd --mkjournal -i NNN
> 
> - start ceph-osd
> 
>  
> 
> This won't set up the udev magic on the journal device, but that doesn't rea
> lly matter if you're not hotplugging devices.
> 
>  
> 
> sage
> 
>  
> 
>  
> 
> _______________________________________________
> 
> ceph-users mailing list
> 
> ceph-users@xxxxxxxxxxxxxx
> 
> http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
> 
> 
_______________________________________________
ceph-users mailing list
ceph-users@xxxxxxxxxxxxxx
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com

[Index of Archives]     [Information on CEPH]     [Linux Filesystem Development]     [Ceph Development]     [Ceph Large]     [Linux USB Development]     [Video for Linux]     [Linux Audio Users]     [Yosemite News]     [Linux Kernel]     [Linux SCSI]     [xfs]


  Powered by Linux