[Gluster-devel] [Gluster-users] glusterfs ctdb issues

[Poornima Gurusiddaiah]

Daniel,

If filetransfer being interrupted is the only problem, then that is expected.
This is because the IP failover happens to a different node but the open file
descriptor is not transferred, to the node the IP is failed over to. Hence, the
IP failover feature provides a way of not having to umount and mount with a
different IP when the original node fails.

Once the filetranfer is interrupted and you re-initiate the transfer,
does it work fine? If so then its expected behavior.

Regards,
Poornima

----- Original Message -----
> From: "Daniel Filipazzi" <daniel.filipazzi at med.lu.se>
> To: pgurusid at redhat.com
> Sent: Thursday, March 31, 2016 6:22:00 PM
> Subject: Re: [Gluster-users] glusterfs ctdb issues
> 
> Hi again!
> I tried changing the lock file location but no sucsess.
> I also edited the files as in the guide.
> But no change just as before as soon as you shutdown one of the nodes,
> the filetransfer stops.
> 
> I have looked at several guides but no luck so far.
> 
> I would realy apriciate some help!
> 
> please let me know if theres anything you need.
> 
> Best Regards
> 
> --
> Daniel Filipazzi
> Division of Oncology
> Department of Clinical Sciences, Lund
> Lund University Cancer Center/Medicon Village
> Building 404:B3 Scheelevägen 2
> SE-223 81 Lund
> Sweden
> 
> Email: Daniel.filipazzi at med.lu.se
> 
> 
> 
> 
> 
> fre 2016-03-11 klockan 04:00 -0500 skrev Poornima Gurusiddaiah:
> > Hi,
> > 
> > So, you can find the documentation for configuring CTDB for gluster
> > backend here:
> > https://github.com/gluster/glusterdocs/blob/master/Administrator%20Gu
> > ide/Accessing%20Gluster%20from%20Windows.md
> > 
> > I guess you have missed creating CTDB volume and mounting it on all
> > nodes and using that volume to store ctdb lock file.
> > 
> > If that is the case, then that explains the 2 issues you are facing.
> > 
> > Also, once you follow the steps in the documentation, change the
> > ctdb.conf to:
> > CTDB_RECOVERY_LOCK=/gluster/lock
> > 
> > Will update the documentation to include this step as well.
> > 
> > Let us know if it helped.
> > 
> > Regards,
> > Poornima
> > 
> > From: "Daniel Filipazzi" <daniel.filipazzi at med.lu.se>
> > To: gluster-users at gluster.org
> > Sent: Thursday, March 10, 2016 7:17:09 PM
> > Subject: [Gluster-users] glusterfs ctdb issues
> > 
> > Ive installed glusterfs successfully and set up the ctdb module to
> > work with it.
> > When creating a new glusterfs volume glusterfs writes to smb.conf to
> > create a share automatically, the share does not work "Unable to
> > mount location".
> > I successfully created a share pointing to the gluster mount point
> > see below, but i cant get the HA feature to work.
> > 
> > 
> > This works!
> > [csmb]
> > comment = Clustered Samba
> > public = yes
> > path = /share/
> > writeable = yes
> > ea support = yes
> > 
> > And this does not.
> > 
> > [gluster-share]
> > comment = share
> > vfs objects = glusterfs
> > glusterfs:volume = share
> > glusterfs:logfile = /var/log/samba/glusterfs-share.%M.log
> > glusterfs:loglevel = 7
> > path = /
> > read only = no
> > guest ok = yes
> > 
> > I used 3 nodes with a replicated glusterfs share to test this.
> > So i have 2 issues i need solved.
> > 1. the config that glusterfs writes to smb.conf doesnt work why?
> > 2. when one of the nodes shutsdown while a client writes to a ctdb
> > share it stops completely and the client cant write to the share
> > anymore. How do i get around this?
> > The other nodes should take over so the client can be able to write
> > to the share when a node goes down.
> > 
> > The ctdb config:
> >  nodes:
> > 192.168.1.10
> > 192.168.1.11
> > 192.168.1.13
> > 
> > public_addresses:
> > 192.168.1.212/24 eth1
> > 
> > ctdb:
> > CTDB_RECOVERY_LOCK=/opt/samba-config/lockfile
> > CTDB_PUBLIC_ADDRESSES=/opt/samba-config/public_addresses
> > CTDB_MANAGES_SAMBA=yes
> > CTDB_MANAGES_WINBIND=yes
> > CTDB_LOGFILE=/var/log/log.ctdb
> > CTDB_SYSLOG=no
> > 
> > 
> > Overall im having a hard time to make ctdb work properly, i would
> > appreciate other peoples insight and thoughts around ctdb. To me it
> > doesnt realy feel like a stable product.
> > Would you advice me to use ctdb in an environment that's in
> > production?
> > 
> > Best regards
> >  
> > --
> > 
> > Daniel Filipazzi
> > Division of Oncology
> > Department of Clinical Sciences, Lund
> > Lund University Cancer Center/Medicon Village
> > Building 404:B3 Scheelevägen 2
> > SE-223 81 Lund
> > Sweden
> > 
> > Email: Daniel.filipazzi at med.lu.se
> > 
> > _______________________________________________
> > Gluster-users mailing list
> > Gluster-users at gluster.org
> > http://www.gluster.org/mailman/listinfo/gluster-users
> > 
> 
>