Re: [Openstack] Suggestions for shared-storage cluster file system

[Razique Mahroua]

Excellent, good to know,thank you Diego :)
Razique Mahroua - Nuage & Corazique.mahr...@gmail.comTel : +33 9 72 37 94 15

Le 19 févr. 2013 à 22:22, Diego Parrilla Santamaría  a écrit :We have used Gluster for small deployments, but lately we have changed our mind.  Basically we have bet on Gluster for 2013 because of:- 10GbE everywhere, and Gluster MUST run in 10GbE (or Infiniband)

- 3.3 release fixes some issues when locking big files: Granular locking- libgfapi reborn, no more FUSE overhead- QEMU 1.3 comes with GlusterFS block driver http://raobharata.wordpress.com/2012/10/29/qemu-glusterfs-native-integration/

- Success cases everywhereRegarding our tests, NetApp and Nexenta outperforms Gluster, but let's say we now can live with this performance penalty because cost per bit and horizontal scalability are really good.

CheersDiego -- 

Diego ParrillaCEO

www.stackops.com |  diego.parri...@stackops.com | +34 649 94 43 29 | skype:diegoparrilla




On Tue, Feb 19, 2013 at 9:57 PM, Razique Mahroua  wrote:

Hey Marco, have you been able to run some performance test on your Gluster cluster?Thanks :)
Razique Mahroua - Nuage & Co

razique.mahr...@gmail.comTel : +33 9 72 37 94 15





Le 18 févr. 2013 à 14:20, Marco CONSONNI  a écrit :Hello Sam,

I've tried two of them: NFS and Gluster.Some problems with the former (migration didn't work properly), no problem with the latter.I vote for Gluster.Hope it helps,Marco.
On Fri, Feb 15, 2013 at 4:40 PM, Samuel Winchenbach  wrote:


Hi All,Can anyone give me a recommendation for a good shared-storage cluster filesystem?   I am running kvm-libvirt and would like to enable live migration.




I have a number of hosts (up to 16) each with 2xTB drives.  These hosts are also my compute/network/controller nodes.  The three I am considering are:GlusterFS - I have the most experience with this, and it seems the easiest.




CephFS/RADOS - Interesting because glance supports the rbd backend.  Slightly worried because of this though "Important:




 Mount the CephFS filesystem on the client machine, not the cluster machine." (I wish it said why...)  and "CephFS is not quite as stable as the block device and the object storage gateway."





Lustre - A little hesitant now that Oracle is involved with it.

If anyone has any advice, or can point out another that I should consider it would be greatly appreciated.



Thanks!



Sam
___
Mailing list: https://launchpad.net/~openstack
Post to     : openstack@lists.launchpad.net
Unsubscribe : https://launchpad.net/~openstack
More help   : https://help.launchpad.net/ListHelp

___Mailing list: https://launchpad.net/~openstackPost to : openstack@lists.launchpad.net

Unsubscribe : https://launchpad.net/~openstackMore help   : https://help.launchpad.net/ListHelp

___
Mailing list: https://launchpad.net/~openstack
Post to     : openstack@lists.launchpad.net
Unsubscribe : https://launchpad.net/~openstack
More help   : https://help.launchpad.net/ListHelp

___
Mailing list: https://launchpad.net/~openstack
Post to : openstack@lists.launchpad.net
Unsubscribe : https://launchpad.net/~openstack
More help   : https://help.launchpad.net/ListHelp

Re: [Openstack] Openstack] Suggestions for shared-storage cluster file system

[Greg Chavez]

So it sounds like what we're talking about here is running a Ceph or
GlusterFS node alongside the compute node (ie, on the same physical
system).  I assume then that VMs access their volumes via NFS or iSCSI from
Cinder on the controller node, and in turn, Cinder reads and writes to the
cluster FS, which is spread out among the physical data volumes on the
compute nodes.  Is this correct?


On Fri, Feb 15, 2013 at 2:29 PM, Sébastien Han wrote:

> Hi,
>
>
> Important: Mount the CephFS filesystem on the client machine, not the
>> cluster machine.
>
>
> It's just like NFS, if you mount an NFS export on the NFS server, you get
> kernel locks.
>
> Unfortunately even if love Ceph far more than the other, I won't go with
> CephFS, at least not know. But if are in a hurry and looking for a DFS then
> GlusterFS seems to be a good candidate. NFS works pretty well too.
>
> Cheers.
>
> --
> Regards,
> Sébastien Han.
>
>
> On Fri, Feb 15, 2013 at 4:49 PM, JuanFra Rodriguez Cardoso <
> juanfra.rodriguez.card...@gmail.com> wrote:
>
>> Another one:
>>
>>  - MooseFS (
>> http://docs.openstack.org/trunk/openstack-compute/admin/content/installing-moosefs-as-backend.html
>> )
>>  - GlusterFS
>>  - Ceph
>>  - Lustre
>>
>> Regards,
>> JuanFra
>>
>>
>> 2013/2/15 Samuel Winchenbach 
>>
>>>  Hi All,
>>>
>>> Can anyone give me a recommendation for a good shared-storage cluster
>>> filesystem?   I am running kvm-libvirt and would like to enable live
>>> migration.
>>>
>>> I have a number of hosts (up to 16) each with 2xTB drives.  These hosts
>>> are also my compute/network/controller nodes.
>>>
>>> The three I am considering are:
>>>
>>> GlusterFS - I have the most experience with this, and it seems the
>>> easiest.
>>>
>>> CephFS/RADOS - Interesting because glance supports the rbd backend.
>>>  Slightly worried because of this though "Important:
>>> Mount the CephFS filesystem on the client machine, not the cluster
>>> machine."
>>> (I wish it said why...)  and "CephFS is not quite as stable as the block
>>> device and the object storage gateway."
>>>  Lustre - A little hesitant now that Oracle is involved with it.
>>>
>>>
>>> If anyone has any advice, or can point out another that I should
>>> consider it would be greatly appreciated.
>>>
>>> Thanks!
>>>
>>> Sam
>>>
>>>
>>> ___
>>> Mailing list: https://launchpad.net/~openstack
>>> Post to : openstack@lists.launchpad.net
>>> Unsubscribe : https://launchpad.net/~openstack
>>> More help   : https://help.launchpad.net/ListHelp
>>>
>>>
>>
>> ___
>> Mailing list: https://launchpad.net/~openstack
>> Post to : openstack@lists.launchpad.net
>> Unsubscribe : https://launchpad.net/~openstack
>> More help   : https://help.launchpad.net/ListHelp
>>
>>
>
> ___
> Mailing list: https://launchpad.net/~openstack
> Post to : openstack@lists.launchpad.net
> Unsubscribe : https://launchpad.net/~openstack
> More help   : https://help.launchpad.net/ListHelp
>
>


-- 
\*..+.-
--Greg Chavez
+//..;};



-- 
\*..+.-
--Greg Chavez
+//..;};
___
Mailing list: https://launchpad.net/~openstack
Post to : openstack@lists.launchpad.net
Unsubscribe : https://launchpad.net/~openstack
More help   : https://help.launchpad.net/ListHelp

Re: [Openstack] Suggestions for shared-storage cluster file system

[Diego Parrilla Santamaría]

We have used Gluster for small deployments, but lately we have changed our
mind.  Basically we have bet on Gluster for 2013 because of:

- 10GbE everywhere, and Gluster MUST run in 10GbE (or Infiniband)
- 3.3 release fixes some issues when locking big files: Granular locking
- libgfapi reborn, no more FUSE overhead
- QEMU 1.3 comes with GlusterFS block driver
http://raobharata.wordpress.com/2012/10/29/qemu-glusterfs-native-integration/
- Success cases everywhere

Regarding our tests, NetApp and Nexenta outperforms Gluster, but let's say
we now can live with this performance penalty because cost per bit and
horizontal scalability are really good.

Cheers
Diego

 --
Diego Parrilla
*CEO*
*www.stackops.com | * diego.parri...@stackops.com** | +34 649 94 43 29 |
skype:diegoparrilla*
* 
*

*



On Tue, Feb 19, 2013 at 9:57 PM, Razique Mahroua
wrote:

> Hey Marco,
> have you been able to run some performance test on your Gluster cluster?
>
> Thanks :)
>
> *Razique Mahroua** - **Nuage & Co*
> razique.mahr...@gmail.com
> Tel : +33 9 72 37 94 15
>
>
> Le 18 févr. 2013 à 14:20, Marco CONSONNI  a écrit :
>
> Hello Sam,
>
> I've tried two of them: NFS and Gluster.
>
> Some problems with the former (migration didn't work properly), no problem
> with the latter.
> I vote for Gluster.
>
> Hope it helps,
> Marco.
>
>
>
> On Fri, Feb 15, 2013 at 4:40 PM, Samuel Winchenbach wrote:
>
>> Hi All,
>>
>> Can anyone give me a recommendation for a good shared-storage cluster
>> filesystem?   I am running kvm-libvirt and would like to enable live
>> migration.
>>
>> I have a number of hosts (up to 16) each with 2xTB drives.  These hosts
>> are also my compute/network/controller nodes.
>>
>> The three I am considering are:
>>
>> GlusterFS - I have the most experience with this, and it seems the
>> easiest.
>>
>> CephFS/RADOS - Interesting because glance supports the rbd backend.
>>  Slightly worried because of this though "Important:
>> Mount the CephFS filesystem on the client machine, not the cluster
>> machine."
>> (I wish it said why...)  and "CephFS is not quite as stable as the block
>> device and the object storage gateway."
>>  Lustre - A little hesitant now that Oracle is involved with it.
>>
>> If anyone has any advice, or can point out another that I should consider
>> it would be greatly appreciated.
>>
>> Thanks!
>>
>> Sam
>>
>>
>> ___
>> Mailing list: https://launchpad.net/~openstack
>> Post to : openstack@lists.launchpad.net
>> Unsubscribe : https://launchpad.net/~openstack
>> More help   : https://help.launchpad.net/ListHelp
>>
>>
> ___
> Mailing list: https://launchpad.net/~openstack
> Post to : openstack@lists.launchpad.net
> Unsubscribe : https://launchpad.net/~openstack
> More help   : https://help.launchpad.net/ListHelp
>
>
>
> ___
> Mailing list: https://launchpad.net/~openstack
> Post to : openstack@lists.launchpad.net
> Unsubscribe : https://launchpad.net/~openstack
> More help   : https://help.launchpad.net/ListHelp
>
>
___
Mailing list: https://launchpad.net/~openstack
Post to : openstack@lists.launchpad.net
Unsubscribe : https://launchpad.net/~openstack
More help   : https://help.launchpad.net/ListHelp

Re: [Openstack] Suggestions for shared-storage cluster file system

[Razique Mahroua]

Hey Marco, have you been able to run some performance test on your Gluster cluster?Thanks :)
Razique Mahroua - Nuage & Corazique.mahr...@gmail.comTel : +33 9 72 37 94 15

Le 18 févr. 2013 à 14:20, Marco CONSONNI  a écrit :Hello Sam,I've tried two of them: NFS and Gluster.Some problems with the former (migration didn't work properly), no problem with the latter.I vote for Gluster.Hope it helps,Marco.
On Fri, Feb 15, 2013 at 4:40 PM, Samuel Winchenbach  wrote:
Hi All,Can anyone give me a recommendation for a good shared-storage cluster filesystem?   I am running kvm-libvirt and would like to enable live migration.


I have a number of hosts (up to 16) each with 2xTB drives.  These hosts are also my compute/network/controller nodes.  The three I am considering are:GlusterFS - I have the most experience with this, and it seems the easiest.


CephFS/RADOS - Interesting because glance supports the rbd backend.  Slightly worried because of this though "Important:


 Mount the CephFS filesystem on the client machine, not the cluster machine." (I wish it said why...)  and "CephFS is not quite as stable as the block device and the object storage gateway."



Lustre - A little hesitant now that Oracle is involved with it.

If anyone has any advice, or can point out another that I should consider it would be greatly appreciated.

Thanks!

Sam
___
Mailing list: https://launchpad.net/~openstack
Post to     : openstack@lists.launchpad.net
Unsubscribe : https://launchpad.net/~openstack
More help   : https://help.launchpad.net/ListHelp

___Mailing list: https://launchpad.net/~openstackPost to : openstack@lists.launchpad.netUnsubscribe : https://launchpad.net/~openstackMore help   : https://help.launchpad.net/ListHelp___
Mailing list: https://launchpad.net/~openstack
Post to : openstack@lists.launchpad.net
Unsubscribe : https://launchpad.net/~openstack
More help   : https://help.launchpad.net/ListHelp

Re: [Openstack] Suggestions for shared-storage cluster file system

[Marco CONSONNI]

Hello Sam,

I've tried two of them: NFS and Gluster.

Some problems with the former (migration didn't work properly), no problem
with the latter.
I vote for Gluster.

Hope it helps,
Marco.



On Fri, Feb 15, 2013 at 4:40 PM, Samuel Winchenbach wrote:

> Hi All,
>
> Can anyone give me a recommendation for a good shared-storage cluster
> filesystem?   I am running kvm-libvirt and would like to enable live
> migration.
>
> I have a number of hosts (up to 16) each with 2xTB drives.  These hosts
> are also my compute/network/controller nodes.
>
> The three I am considering are:
>
> GlusterFS - I have the most experience with this, and it seems the easiest.
>
> CephFS/RADOS - Interesting because glance supports the rbd backend.
>  Slightly worried because of this though "Important:
> Mount the CephFS filesystem on the client machine, not the cluster
> machine."
> (I wish it said why...)  and "CephFS is not quite as stable as the block
> device and the object storage gateway."
>  Lustre - A little hesitant now that Oracle is involved with it.
>
>
> If anyone has any advice, or can point out another that I should consider
> it would be greatly appreciated.
>
> Thanks!
>
> Sam
>
>
> ___
> Mailing list: https://launchpad.net/~openstack
> Post to : openstack@lists.launchpad.net
> Unsubscribe : https://launchpad.net/~openstack
> More help   : https://help.launchpad.net/ListHelp
>
>
___
Mailing list: https://launchpad.net/~openstack
Post to : openstack@lists.launchpad.net
Unsubscribe : https://launchpad.net/~openstack
More help   : https://help.launchpad.net/ListHelp

Re: [Openstack] Suggestions for shared-storage cluster file system

[Sebastien HAN]

I haven't played that much with Glusterfs and pacemaker but I'm pretty sure 
that there is already a resource agent for this. Maybe the Filesystem RA can do 
it but you probably might have a look at the upstream version on the Cluster 
Lab Github. 

Cheers 

On 15 févr. 2013, at 20:54, Samuel Winchenbach  wrote:

> Thanks,
> 
> I think I will go with GlusterFS.   MooseFS looks interesting, but 
> maintaining a package outside the repo/cloud archive is not something I want 
> to deal with.
> 
> Along the same lines...   is it possible to mount a GlusterFS volume in 
> pacemaker?  I have tried both ocf:heartbeat:Filesystem and 
> ocf:redhat:netfs.sh without much luck.   I have managed to get the service 
> started with upstart though.
> 
> Thanks,
> Sam
> 
> 
> On Fri, Feb 15, 2013 at 2:29 PM, Sébastien Han  
> wrote:
>> Hi,
>> 
>> 
>>> Important: Mount the CephFS filesystem on the client machine, not the 
>>> cluster machine.
>> 
>> It's just like NFS, if you mount an NFS export on the NFS server, you get 
>> kernel locks.
>> 
>> Unfortunately even if love Ceph far more than the other, I won't go with 
>> CephFS, at least not know. But if are in a hurry and looking for a DFS then 
>> GlusterFS seems to be a good candidate. NFS works pretty well too.
>> 
>> Cheers.
>> 
>> --
>> Regards,
>> Sébastien Han.
>> 
>> 
>> On Fri, Feb 15, 2013 at 4:49 PM, JuanFra Rodriguez Cardoso 
>>  wrote:
>>> Another one:
>>> 
>>>  - MooseFS 
>>> (http://docs.openstack.org/trunk/openstack-compute/admin/content/installing-moosefs-as-backend.html)
>>>  - GlusterFS
>>>  - Ceph
>>>  - Lustre
>>> 
>>> Regards,
>>> JuanFra
>>> 
>>> 
>>> 2013/2/15 Samuel Winchenbach 
 Hi All,
 
 Can anyone give me a recommendation for a good shared-storage cluster 
 filesystem?   I am running kvm-libvirt and would like to enable live 
 migration.
 
 I have a number of hosts (up to 16) each with 2xTB drives.  These hosts 
 are also my compute/network/controller nodes.  
 
 The three I am considering are:
 
 GlusterFS - I have the most experience with this, and it seems the easiest.
 
 CephFS/RADOS - Interesting because glance supports the rbd backend.  
 Slightly worried because of this though "Important: Mount the CephFS 
 filesystem on the client machine, not the cluster machine." (I wish it 
 said why...)  and "CephFS is not quite as stable as the block device and 
 the object storage gateway."
 Lustre - A little hesitant now that Oracle is involved with it.
 
 If anyone has any advice, or can point out another that I should consider 
 it would be greatly appreciated.
 
 Thanks!
 
 Sam
 
 
 ___
 Mailing list: https://launchpad.net/~openstack
 Post to : openstack@lists.launchpad.net
 Unsubscribe : https://launchpad.net/~openstack
 More help   : https://help.launchpad.net/ListHelp
>>> 
>>> 
>>> ___
>>> Mailing list: https://launchpad.net/~openstack
>>> Post to : openstack@lists.launchpad.net
>>> Unsubscribe : https://launchpad.net/~openstack
>>> More help   : https://help.launchpad.net/ListHelp
> 
___
Mailing list: https://launchpad.net/~openstack
Post to : openstack@lists.launchpad.net
Unsubscribe : https://launchpad.net/~openstack
More help   : https://help.launchpad.net/ListHelp

Re: [Openstack] Suggestions for shared-storage cluster file system

[John Griffith]

On Fri, Feb 15, 2013 at 1:08 PM, JR  wrote:

> Is there anyone using GPFS (General Parallel Filesystem) from IBM.  It's
> high performing, posix compliant, can do internal replication, etc...?
>
> To make it work, would one simply have to modify the nova-volume (or
> cinder) code that creates a volume-group using the corresponding GPFS
> commands?  Or, are there other complexities?  Which code would I look in
> to see what's involved?
>
> JR
>
>
> On 2/15/2013 2:54 PM, Samuel Winchenbach wrote:
> > Thanks,
> >
> > I think I will go with GlusterFS.   MooseFS looks interesting, but
> > maintaining a package outside the repo/cloud archive is not something I
> > want to deal with.
> >
> > Along the same lines...   is it possible to mount a GlusterFS volume in
> > pacemaker?  I have tried both ocf:heartbeat:Filesystem and
> > ocf:redhat:netfs.sh without much luck.   I have managed to get the
> > service started with upstart though.
> >
> > Thanks,
> > Sam
> >
> >
> > On Fri, Feb 15, 2013 at 2:29 PM, Sébastien Han  > > wrote:
> >
> > Hi,
> >
> >
> > Important: Mount the CephFS filesystem on the client machine,
> > not the cluster machine.
> >
> >
> > It's just like NFS, if you mount an NFS export on the NFS server,
> > you get kernel locks.
> >
> > Unfortunately even if love Ceph far more than the other, I won't go
> > with CephFS, at least not know. But if are in a hurry and looking
> > for a DFS then GlusterFS seems to be a good candidate. NFS works
> > pretty well too.
> >
> > Cheers.
> >
> > --
> > Regards,
> > Sébastien Han.
> >
> >
> > On Fri, Feb 15, 2013 at 4:49 PM, JuanFra Rodriguez Cardoso
> >  > > wrote:
> >
> > Another one:
> >
> >  - MooseFS
> > (
> http://docs.openstack.org/trunk/openstack-compute/admin/content/installing-moosefs-as-backend.html
> )
> >  - GlusterFS
> >  - Ceph
> >  - Lustre
> >
> > Regards,
> > JuanFra
> >
> >
> > 2013/2/15 Samuel Winchenbach  > >
> >
> > Hi All,
> >
> > Can anyone give me a recommendation for a good
> > shared-storage cluster filesystem?   I am running
> > kvm-libvirt and would like to enable live migration.
> >
> > I have a number of hosts (up to 16) each with 2xTB drives.
> >  These hosts are also my compute/network/controller nodes.
> >
> > The three I am considering are:
> >
> > GlusterFS - I have the most experience with this, and it
> > seems the easiest.
> >
> > CephFS/RADOS - Interesting because glance supports the rbd
> > backend.  Slightly worried because of this though "Important:
> > Mount the CephFS filesystem on the client machine, not the
> > cluster machine."
> > (I wish it said why...)  and "CephFS is not quite as stable
> > as the block device and the object storage gateway."
> > Lustre - A little hesitant now that Oracle is involved with
> it.
> >
> >
> > If anyone has any advice, or can point out another that I
> > should consider it would be greatly appreciated.
> >
> > Thanks!
> >
> > Sam
> >
> >
> > ___
> > Mailing list: https://launchpad.net/~openstack
> > Post to : openstack@lists.launchpad.net
> > 
> > Unsubscribe : https://launchpad.net/~openstack
> > More help   : https://help.launchpad.net/ListHelp
> >
> >
> >
> > ___
> > Mailing list: https://launchpad.net/~openstack
> > Post to : openstack@lists.launchpad.net
> > 
> > Unsubscribe : https://launchpad.net/~openstack
> > More help   : https://help.launchpad.net/ListHelp
> >
> >
> >
> >
> >
> > ___
> > Mailing list: https://launchpad.net/~openstack
> > Post to : openstack@lists.launchpad.net
> > Unsubscribe : https://launchpad.net/~openstack
> > More help   : https://help.launchpad.net/ListHelp
> >
>
> ___
> Mailing list: https://launchpad.net/~openstack
> Post to : openstack@lists.launchpad.net
> Unsubscribe : https://launchpad.net/~openstack
> More help   : https://help.launchpad.net/ListHelp
>
Don't know about folks that might have their own implementation, but
currently nothing in Cinder.  The closest thing to use to get an idea of
the driver is the pending Gluster work:
https://review.openstack.org/#/c/21342/

John
___
Mailing list: https://launchpad.net/~openstack
Post to

Re: [Openstack] Suggestions for shared-storage cluster file system

[JR]

Is there anyone using GPFS (General Parallel Filesystem) from IBM.  It's
high performing, posix compliant, can do internal replication, etc...?

To make it work, would one simply have to modify the nova-volume (or
cinder) code that creates a volume-group using the corresponding GPFS
commands?  Or, are there other complexities?  Which code would I look in
to see what's involved?

JR


On 2/15/2013 2:54 PM, Samuel Winchenbach wrote:
> Thanks,
> 
> I think I will go with GlusterFS.   MooseFS looks interesting, but
> maintaining a package outside the repo/cloud archive is not something I
> want to deal with.
> 
> Along the same lines...   is it possible to mount a GlusterFS volume in
> pacemaker?  I have tried both ocf:heartbeat:Filesystem and
> ocf:redhat:netfs.sh without much luck.   I have managed to get the
> service started with upstart though.
> 
> Thanks,
> Sam
> 
> 
> On Fri, Feb 15, 2013 at 2:29 PM, Sébastien Han  > wrote:
> 
> Hi,
> 
> 
> Important: Mount the CephFS filesystem on the client machine,
> not the cluster machine.
> 
> 
> It's just like NFS, if you mount an NFS export on the NFS server,
> you get kernel locks.
> 
> Unfortunately even if love Ceph far more than the other, I won't go
> with CephFS, at least not know. But if are in a hurry and looking
> for a DFS then GlusterFS seems to be a good candidate. NFS works
> pretty well too.
> 
> Cheers.
> 
> --
> Regards,
> Sébastien Han.
> 
> 
> On Fri, Feb 15, 2013 at 4:49 PM, JuanFra Rodriguez Cardoso
>  > wrote:
> 
> Another one:
> 
>  - MooseFS
> 
> (http://docs.openstack.org/trunk/openstack-compute/admin/content/installing-moosefs-as-backend.html)
>  - GlusterFS
>  - Ceph
>  - Lustre
> 
> Regards,
> JuanFra
> 
> 
> 2013/2/15 Samuel Winchenbach  >
> 
> Hi All,
> 
> Can anyone give me a recommendation for a good
> shared-storage cluster filesystem?   I am running
> kvm-libvirt and would like to enable live migration.
> 
> I have a number of hosts (up to 16) each with 2xTB drives.
>  These hosts are also my compute/network/controller nodes.  
> 
> The three I am considering are:
> 
> GlusterFS - I have the most experience with this, and it
> seems the easiest.
> 
> CephFS/RADOS - Interesting because glance supports the rbd
> backend.  Slightly worried because of this though "Important:
> Mount the CephFS filesystem on the client machine, not the
> cluster machine."
> (I wish it said why...)  and "CephFS is not quite as stable
> as the block device and the object storage gateway."
> Lustre - A little hesitant now that Oracle is involved with it.
> 
> 
> If anyone has any advice, or can point out another that I
> should consider it would be greatly appreciated.
> 
> Thanks!
> 
> Sam
> 
> 
> ___
> Mailing list: https://launchpad.net/~openstack
> Post to : openstack@lists.launchpad.net
> 
> Unsubscribe : https://launchpad.net/~openstack
> More help   : https://help.launchpad.net/ListHelp
> 
> 
> 
> ___
> Mailing list: https://launchpad.net/~openstack
> Post to : openstack@lists.launchpad.net
> 
> Unsubscribe : https://launchpad.net/~openstack
> More help   : https://help.launchpad.net/ListHelp
> 
> 
> 
> 
> 
> ___
> Mailing list: https://launchpad.net/~openstack
> Post to : openstack@lists.launchpad.net
> Unsubscribe : https://launchpad.net/~openstack
> More help   : https://help.launchpad.net/ListHelp
> 

___
Mailing list: https://launchpad.net/~openstack
Post to : openstack@lists.launchpad.net
Unsubscribe : https://launchpad.net/~openstack
More help   : https://help.launchpad.net/ListHelp

Re: [Openstack] Suggestions for shared-storage cluster file system

[Samuel Winchenbach]

Thanks,

I think I will go with GlusterFS.   MooseFS looks interesting, but
maintaining a package outside the repo/cloud archive is not something I
want to deal with.

Along the same lines...   is it possible to mount a GlusterFS volume in
pacemaker?  I have tried both ocf:heartbeat:Filesystem and
ocf:redhat:netfs.sh without much luck.   I have managed to get the service
started with upstart though.

Thanks,
Sam


On Fri, Feb 15, 2013 at 2:29 PM, Sébastien Han wrote:

> Hi,
>
>
> Important: Mount the CephFS filesystem on the client machine, not the
>> cluster machine.
>
>
> It's just like NFS, if you mount an NFS export on the NFS server, you get
> kernel locks.
>
> Unfortunately even if love Ceph far more than the other, I won't go with
> CephFS, at least not know. But if are in a hurry and looking for a DFS then
> GlusterFS seems to be a good candidate. NFS works pretty well too.
>
> Cheers.
>
> --
> Regards,
> Sébastien Han.
>
>
> On Fri, Feb 15, 2013 at 4:49 PM, JuanFra Rodriguez Cardoso <
> juanfra.rodriguez.card...@gmail.com> wrote:
>
>> Another one:
>>
>>  - MooseFS (
>> http://docs.openstack.org/trunk/openstack-compute/admin/content/installing-moosefs-as-backend.html
>> )
>>  - GlusterFS
>>  - Ceph
>>  - Lustre
>>
>> Regards,
>> JuanFra
>>
>>
>> 2013/2/15 Samuel Winchenbach 
>>
>>>  Hi All,
>>>
>>> Can anyone give me a recommendation for a good shared-storage cluster
>>> filesystem?   I am running kvm-libvirt and would like to enable live
>>> migration.
>>>
>>> I have a number of hosts (up to 16) each with 2xTB drives.  These hosts
>>> are also my compute/network/controller nodes.
>>>
>>> The three I am considering are:
>>>
>>> GlusterFS - I have the most experience with this, and it seems the
>>> easiest.
>>>
>>> CephFS/RADOS - Interesting because glance supports the rbd backend.
>>>  Slightly worried because of this though "Important:
>>> Mount the CephFS filesystem on the client machine, not the cluster
>>> machine."
>>> (I wish it said why...)  and "CephFS is not quite as stable as the block
>>> device and the object storage gateway."
>>>  Lustre - A little hesitant now that Oracle is involved with it.
>>>
>>>
>>> If anyone has any advice, or can point out another that I should
>>> consider it would be greatly appreciated.
>>>
>>> Thanks!
>>>
>>> Sam
>>>
>>>
>>> ___
>>> Mailing list: https://launchpad.net/~openstack
>>> Post to : openstack@lists.launchpad.net
>>> Unsubscribe : https://launchpad.net/~openstack
>>> More help   : https://help.launchpad.net/ListHelp
>>>
>>>
>>
>> ___
>> Mailing list: https://launchpad.net/~openstack
>> Post to : openstack@lists.launchpad.net
>> Unsubscribe : https://launchpad.net/~openstack
>> More help   : https://help.launchpad.net/ListHelp
>>
>>
>
___
Mailing list: https://launchpad.net/~openstack
Post to : openstack@lists.launchpad.net
Unsubscribe : https://launchpad.net/~openstack
More help   : https://help.launchpad.net/ListHelp

Re: [Openstack] Suggestions for shared-storage cluster file system

[Sébastien Han]

Hi,

Important: Mount the CephFS filesystem on the client machine, not the
> cluster machine.


It's just like NFS, if you mount an NFS export on the NFS server, you get
kernel locks.

Unfortunately even if love Ceph far more than the other, I won't go with
CephFS, at least not know. But if are in a hurry and looking for a DFS then
GlusterFS seems to be a good candidate. NFS works pretty well too.

Cheers.

--
Regards,
Sébastien Han.


On Fri, Feb 15, 2013 at 4:49 PM, JuanFra Rodriguez Cardoso <
juanfra.rodriguez.card...@gmail.com> wrote:

> Another one:
>
>  - MooseFS (
> http://docs.openstack.org/trunk/openstack-compute/admin/content/installing-moosefs-as-backend.html
> )
>  - GlusterFS
>  - Ceph
>  - Lustre
>
> Regards,
> JuanFra
>
>
> 2013/2/15 Samuel Winchenbach 
>
>>  Hi All,
>>
>> Can anyone give me a recommendation for a good shared-storage cluster
>> filesystem?   I am running kvm-libvirt and would like to enable live
>> migration.
>>
>> I have a number of hosts (up to 16) each with 2xTB drives.  These hosts
>> are also my compute/network/controller nodes.
>>
>> The three I am considering are:
>>
>> GlusterFS - I have the most experience with this, and it seems the
>> easiest.
>>
>> CephFS/RADOS - Interesting because glance supports the rbd backend.
>>  Slightly worried because of this though "Important:
>> Mount the CephFS filesystem on the client machine, not the cluster
>> machine."
>> (I wish it said why...)  and "CephFS is not quite as stable as the block
>> device and the object storage gateway."
>>  Lustre - A little hesitant now that Oracle is involved with it.
>>
>>
>> If anyone has any advice, or can point out another that I should consider
>> it would be greatly appreciated.
>>
>> Thanks!
>>
>> Sam
>>
>>
>> ___
>> Mailing list: https://launchpad.net/~openstack
>> Post to : openstack@lists.launchpad.net
>> Unsubscribe : https://launchpad.net/~openstack
>> More help   : https://help.launchpad.net/ListHelp
>>
>>
>
> ___
> Mailing list: https://launchpad.net/~openstack
> Post to : openstack@lists.launchpad.net
> Unsubscribe : https://launchpad.net/~openstack
> More help   : https://help.launchpad.net/ListHelp
>
>
___
Mailing list: https://launchpad.net/~openstack
Post to : openstack@lists.launchpad.net
Unsubscribe : https://launchpad.net/~openstack
More help   : https://help.launchpad.net/ListHelp

Re: [Openstack] Suggestions for shared-storage cluster file system

[JuanFra Rodriguez Cardoso]

Another one:

 - MooseFS (
http://docs.openstack.org/trunk/openstack-compute/admin/content/installing-moosefs-as-backend.html
)
 - GlusterFS
 - Ceph
 - Lustre

Regards,
JuanFra


2013/2/15 Samuel Winchenbach 

> Hi All,
>
> Can anyone give me a recommendation for a good shared-storage cluster
> filesystem?   I am running kvm-libvirt and would like to enable live
> migration.
>
> I have a number of hosts (up to 16) each with 2xTB drives.  These hosts
> are also my compute/network/controller nodes.
>
> The three I am considering are:
>
> GlusterFS - I have the most experience with this, and it seems the easiest.
>
> CephFS/RADOS - Interesting because glance supports the rbd backend.
>  Slightly worried because of this though "Important:
> Mount the CephFS filesystem on the client machine, not the cluster
> machine."
> (I wish it said why...)  and "CephFS is not quite as stable as the block
> device and the object storage gateway."
>  Lustre - A little hesitant now that Oracle is involved with it.
>
>
> If anyone has any advice, or can point out another that I should consider
> it would be greatly appreciated.
>
> Thanks!
>
> Sam
>
>
> ___
> Mailing list: https://launchpad.net/~openstack
> Post to : openstack@lists.launchpad.net
> Unsubscribe : https://launchpad.net/~openstack
> More help   : https://help.launchpad.net/ListHelp
>
>
___
Mailing list: https://launchpad.net/~openstack
Post to : openstack@lists.launchpad.net
Unsubscribe : https://launchpad.net/~openstack
More help   : https://help.launchpad.net/ListHelp

[Openstack] Suggestions for shared-storage cluster file system

[Samuel Winchenbach]

Hi All,

Can anyone give me a recommendation for a good shared-storage cluster
filesystem?   I am running kvm-libvirt and would like to enable live
migration.

I have a number of hosts (up to 16) each with 2xTB drives.  These hosts are
also my compute/network/controller nodes.

The three I am considering are:

GlusterFS - I have the most experience with this, and it seems the easiest.

CephFS/RADOS - Interesting because glance supports the rbd backend.
 Slightly worried because of this though "Important:

Mount the CephFS filesystem on the client machine, not the cluster machine."

(I wish it said why...)  and "CephFS is not quite as stable as the block
device and the object storage gateway."


Lustre - A little hesitant now that Oracle is involved with it.


If anyone has any advice, or can point out another that I should consider
it would be greatly appreciated.

Thanks!

Sam
___
Mailing list: https://launchpad.net/~openstack
Post to : openstack@lists.launchpad.net
Unsubscribe : https://launchpad.net/~openstack
More help   : https://help.launchpad.net/ListHelp