Re: [Gluster-users] ESXi & Gluster setup options
Chris Haumesser writes: > > > The native FUSE client has built-in failover if you mount using the server and volume name (e.g. `mount -t glusterfs server1:/foo /mnt/foo`). When mounting this way, the gluster client downloads a list of all the bricks, and if one goes down, automatically fails over to another available brick server.Note, however, that at mount-time, the client needs to be able to reach the brick server specified in the mount command. You could use simple roundrobin DNS to make sure your clients always reach an available brick.As others stated previously, NFS failover requires ucarp or an alternative ha framework.Cheers,-C- > On Thu, May 26, 2011 at 2:37 PM, paul simpson realisestudio.com> wrote:i'm also interested in this. is there any pro/con to using native gluster FUSE client for xen images? i would have thought that would mitigate the use of ucarp (apart from initial connect). > > > -p > > > > > > > On 26 May 2011 21:39, Whit Blauvelt wrote: > > On Thu, May 26, 2011 at 08:28:29PM +, Matt Temple wrote: > > We've been looking for a way to have HA for our VMWare datastore, too. (Our > > single server had a kernel panic last night and took down the VMs.) > > We're very much interested in a similar setup, using Gluster, but I have a > > question ... with Gluster NFS, don't you have to choose a specific > >address of a > > server to connect to? And if yes, if that node goes down, how does VMWare > > respond? > Pretty much the standard thing to do is use a virtual IP address with ucarp > handling reassignment if the primary node goes down. I've yet to run that > through thorough tests to see if how transparent it is in a case of failure. > It's simple to set up though. > There are, of course, plenty of more complicated alternatives to ucarp in > the HA world - heartbeat, pacemaker, corosync > Whit > > ___ > Gluster-users mailing listGluster-users gluster.orghttp://gluster.org/cgi-bin/mailman/listinfo/gluster-users > > > > > > > > > ___ > Gluster-users mailing listGluster-users@gluster.orghttp://gluster.org/cgi-bin/mailman/listinfo/gluster-users > > > > > > ___ > Gluster-users mailing list > Gluster-users@... > http://gluster.org/cgi-bin/mailman/listinfo/gluster-users > All, We just set up UCARP on our simple replicating 3.2 server, but when we tried to connect to the virtual address as an NFS store from VCenter, the connection was rejected. When we used the real ip address of the server, it connected. Is anyone successfully using UCARP/Gluster with VMWare for storage using NFSconnections. Or are we just doing something wrong? HA on the VMWare storagefor the VMDKs is pretty important and automatic NFS failover would really be terrific. Doesn't NFS have to much context to simply failover? (If this were KVM, I'm sure we'd be able to use a native gluster client, but that's another story.) Any help would be appreciated. We could document all the steps to a working example. Matt ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
Re: [Gluster-users] ESXi & Gluster setup options
Thanks for this. Is their any other advantage our disadvantage in using the fuse client? Speed, reliability? In fact, has the anyone run vm's off fuse? On May 26, 2011 11:56 PM, "Chris Haumesser" wrote: ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
Re: [Gluster-users] ESXi & Gluster setup options
The native FUSE client has built-in failover if you mount using the server and volume name (e.g. `mount -t glusterfs server1:/foo /mnt/foo`). When mounting this way, the gluster client downloads a list of all the bricks, and if one goes down, automatically fails over to another available brick server. Note, however, that at mount-time, the client needs to be able to reach the brick server specified in the mount command. You could use simple roundrobin DNS to make sure your clients always reach an available brick. As others stated previously, NFS failover requires ucarp or an alternative ha framework. Cheers, -C- On Thu, May 26, 2011 at 2:37 PM, paul simpson wrote: > i'm also interested in this. is there any pro/con to using native gluster > FUSE client for xen images? i would have thought that would mitigate the > use of ucarp (apart from initial connect). > > -p > > > > On 26 May 2011 21:39, Whit Blauvelt wrote: > >> On Thu, May 26, 2011 at 08:28:29PM +, Matt Temple wrote: >> >> > We've been looking for a way to have HA for our VMWare datastore, too. >> (Our >> > single server had a kernel panic last night and took down the VMs.) >> > We're very much interested in a similar setup, using Gluster, but I have >> a >> > question ... with Gluster NFS, don't you have to choose a specific >> address of a >> > server to connect to? And if yes, if that node goes down, how does >> VMWare >> > respond? >> >> Pretty much the standard thing to do is use a virtual IP address with >> ucarp >> handling reassignment if the primary node goes down. I've yet to run that >> through thorough tests to see if how transparent it is in a case of >> failure. >> It's simple to set up though. >> >> There are, of course, plenty of more complicated alternatives to ucarp in >> the HA world - heartbeat, pacemaker, corosync >> >> Whit >> ___ >> Gluster-users mailing list >> Gluster-users@gluster.org >> http://gluster.org/cgi-bin/mailman/listinfo/gluster-users >> > > > ___ > Gluster-users mailing list > Gluster-users@gluster.org > http://gluster.org/cgi-bin/mailman/listinfo/gluster-users > > ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
Re: [Gluster-users] ESXi & Gluster setup options
i'm also interested in this. is there any pro/con to using native gluster FUSE client for xen images? i would have thought that would mitigate the use of ucarp (apart from initial connect). -p On 26 May 2011 21:39, Whit Blauvelt wrote: > On Thu, May 26, 2011 at 08:28:29PM +, Matt Temple wrote: > > > We've been looking for a way to have HA for our VMWare datastore, too. > (Our > > single server had a kernel panic last night and took down the VMs.) > > We're very much interested in a similar setup, using Gluster, but I have > a > > question ... with Gluster NFS, don't you have to choose a specific > address of a > > server to connect to? And if yes, if that node goes down, how does > VMWare > > respond? > > Pretty much the standard thing to do is use a virtual IP address with ucarp > handling reassignment if the primary node goes down. I've yet to run that > through thorough tests to see if how transparent it is in a case of > failure. > It's simple to set up though. > > There are, of course, plenty of more complicated alternatives to ucarp in > the HA world - heartbeat, pacemaker, corosync > > Whit > ___ > Gluster-users mailing list > Gluster-users@gluster.org > http://gluster.org/cgi-bin/mailman/listinfo/gluster-users > ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
Re: [Gluster-users] ESXi & Gluster setup options
On Thu, May 26, 2011 at 08:28:29PM +, Matt Temple wrote: > We've been looking for a way to have HA for our VMWare datastore, too. (Our > single server had a kernel panic last night and took down the VMs.) > We're very much interested in a similar setup, using Gluster, but I have a > question ... with Gluster NFS, don't you have to choose a specific address of > a > server to connect to? And if yes, if that node goes down, how does VMWare > respond? Pretty much the standard thing to do is use a virtual IP address with ucarp handling reassignment if the primary node goes down. I've yet to run that through thorough tests to see if how transparent it is in a case of failure. It's simple to set up though. There are, of course, plenty of more complicated alternatives to ucarp in the HA world - heartbeat, pacemaker, corosync Whit ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
Re: [Gluster-users] ESXi & Gluster setup options
Krishna Srinivas writes: > > Troy, > > Yes it would work, you can setup 4 servers in a distributed replicated > setup acting as NFS data store for VMWare. If any one of the storage > node goes down it will not be seen by the ESX hosts. Many users use > this type of config for storage HA for NFS datastores. > > You can use SATA or SAS. > > Since you are using 10gb performance should not be a problem. Backend > disks would be the bottleneck and hence you should experiment with a > good raid setup to get maximum backend disk throughput. > > On Thu, Apr 21, 2011 at 9:54 PM, Troy Swaine wrote: > > All, > > > > > > > > We are in the process of determining a virtualized infrastructure and > > wanted to hear from > > > > current users of Gluster and VMWare. What we were looking to setup was an HA > > ESXi cluster > > > > (2 heads) with gluster backend (4 bricks to start, replicated/distributed), > > all backend connectivity > > would be 10Gbe. Mainly the storage would be for VM images but may include > > NAS files later. > > > > Thanks, > > > > Troy Hello, We've been looking for a way to have HA for our VMWare datastore, too. (Our single server had a kernel panic last night and took down the VMs.) We're very much interested in a similar setup, using Gluster, but I have a question ... with Gluster NFS, don't you have to choose a specific address of a server to connect to? And if yes, if that node goes down, how does VMWare respond? Matt Temple ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
Re: [Gluster-users] ESXi & Gluster setup options
Troy, Yes it would work, you can setup 4 servers in a distributed replicated setup acting as NFS data store for VMWare. If any one of the storage node goes down it will not be seen by the ESX hosts. Many users use this type of config for storage HA for NFS datastores. You can use SATA or SAS. Since you are using 10gb performance should not be a problem. Backend disks would be the bottleneck and hence you should experiment with a good raid setup to get maximum backend disk throughput. On Thu, Apr 21, 2011 at 9:54 PM, Troy Swaine wrote: > All, > > > > We are in the process of determining a virtualized infrastructure and > wanted to hear from > > current users of Gluster and VMWare. What we were looking to setup was an HA > ESXi cluster > > (2 heads) with gluster backend (4 bricks to start, replicated/distributed), > all backend connectivity > > would be 10Gbe. Mainly the storage would be for VM images but may include > NAS files later. > > So our questions are… > > > > Has someone setup something similar? > > > > What did the layout look like? > > > > How was performance? > > > > Drives used in bricks(SATA / SAS)? > > > > Experiences / Ideas? > > > > Thanks, > > > > Troy > > ___ > Gluster-users mailing list > Gluster-users@gluster.org > http://gluster.org/cgi-bin/mailman/listinfo/gluster-users > > ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
[Gluster-users] ESXi & Gluster setup options
All, We are in the process of determining a virtualized infrastructure and wanted to hear from current users of Gluster and VMWare. What we were looking to setup was an HA ESXi cluster (2 heads) with gluster backend (4 bricks to start, replicated/distributed), all backend connectivity would be 10Gbe. Mainly the storage would be for VM images but may include NAS files later. So our questions are... Has someone setup something similar? What did the layout look like? How was performance? Drives used in bricks(SATA / SAS)? Experiences / Ideas? Thanks, Troy ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users