similar to: Glusterfs performance with large directories

On Tue, Feb 27, 2018 at 12:00:29PM +0530, Karthik Subrahmanya wrote: > I will try to explain how you can end up in split-brain even with cluster > wide quorum: Yep, the explanation made sense. I hadn't considered the possibility of alternating outages. Thanks! > > > It would be great if you can consider configuring an arbiter or > > > replica 3 volume. > >

Hello Gluster users, Before I put Gluster into production, I am wondering how it determines whether a byte can be written, and where I should look in the source code to change these behaviors. My experiences are with glusterfs 3.2.4 on CentOS 6 64-bit. Suppose I have a Gluster volume made up of four 1 MB bricks, like this Volume Name: test Type: Distributed-Replicate Status: Started Number of

Well, it looks like I've stumped the list, so I did a bit of additional digging myself: azathoth replicates with yog-sothoth, so I compared their brick directories. `ls -R /var/local/brick0/data | md5sum` gives the same result on both servers, so the filenames are identical in both bricks. However, `du -s /var/local/brick0/data` shows that azathoth has about 3G more data (445G vs 442G) than

I'm using gluster for a virt-store with 3x2 distributed/replicated servers for 16 qemu/kvm/libvirt virtual machines using image files stored in gluster and accessed via libgfapi. Eight of these disk images are standalone, while the other eight are qcow2 images which all share a single backing file. For the most part, this is all working very well. However, one of the gluster servers

Hi! I am running a replica 3 volume. On server2 I wanted to move the brick to a new disk. I removed the brick from the volume: gluster volume remove-brick VOLUME rep 2 server2:/gluster/VOLUME/brick0/brick force I unmounted the old brick and mounted the new disk to the same location. I added the empty new brick to the volume: gluster volume add-brick VOLUME rep 3

Lets say you had 4 servers and you wanted to setup replicate and distribute. What methoid would be better: server sdb1 xen0 brick0 xen1 mirror0 xen2 brick1 xen3 mirror1 replicate block0 - brick0 mirror0 replicate block1 - brick1 mirror1 distribute unify - block0 block1 or server sdb1 sdb2 xen0 brick0 mirror3 xen1 brick1 mirror0 xen2 brick2 mirror1 xen3 brick3 mirror2 replicate block0 -

.gluster and attr already in that folder so it would not connect it as a brick I don't think there is option to "reconnect brick back" what I did many times - delete .gluster and reset attr on the folder, connect the brick and then update those attr. with stat commands example here http://lists.gluster.org/pipermail/gluster-users/2018-January/033352.html Vlad On Sun, Feb 25, 2018

Hi, community Please, help me with my trouble. I have 2 Gluster nodes, with 2 bricks on each. Configuration: Node1 brick1 replicated on Node0 brick0 Node0 brick1 replicated on Node1 brick0 Volume Name: gm0 Type: Distributed-Replicate Volume ID: 5e55f511-8a50-46e4-aa2f-5d4f73c859cf Status: Started Snapshot Count: 0 Number of Bricks: 2 x 2 = 4 Transport-type: tcp Bricks: Brick1:

Let me see if I understand this. Remove attrs from the brick and delete the .glusterfs folder. Data stays in place. Add the brick to the volume. Since most of the data is the same as on the actual volume it does not need to be synced, and the heal operation finishes much faster. Do I have this right? Kind regards, Mitja On 25/02/2018 17:02, Vlad Kopylov wrote: > .gluster and attr already in

Hello everybody, Please, help to fix me a problem. I have a distributed-replicated volume between two servers. On each server I have 2 RAID-10 arrays, that replicated between servers. Brick gl1:/mnt/brick1/gm0 49153 0 Y 13910 Brick gl0:/mnt/brick0/gm0 N/A N/A N N/A Brick gl0:/mnt/brick1/gm0 N/A

We're using gluster-2.0.1 and a nufa volume comprised of thirteen subvolumes across thirteen hosts. We've found today that there are some files in the local filesystem associated with the subvolume from one of the hosts that are not being seen in the nufa volume on any gluster client. I don't know how or when this happened, but now we have to do some work to get this gluster volume

Hey, all. I'm currently trying out GlusterFS 3.3. I've got two servers and four clients, all on separate boxes. I've got a Distributed-Replicated volume with 4 bricks, two from each server, and I'm using the FUSE client. I was trying out failover, currently testing for reads. I was reading a big file, using iftop to see which server was actually being read from. I put up an

I have 6 boxes with a client config (see below) across 6 boxes. I am using distribute across 3 replicate pairs. Since I am running xen I need to disable-direct-io and that slows things down quite a bit. My thought was to move the replicate / distribute to the backend server config so that self heal can happen on faster backend rather then frontend client with disable-direct-io. Does this

On Mon, Feb 26, 2018 at 05:45:27PM +0530, Karthik Subrahmanya wrote: > > "In a replica 2 volume... If we set the client-quorum option to > > auto, then the first brick must always be up, irrespective of the > > status of the second brick. If only the second brick is up, the > > subvolume becomes read-only." > > > By default client-quorum is

On Mon, Feb 26, 2018 at 6:14 PM, Dave Sherohman <dave at sherohman.org> wrote: > On Mon, Feb 26, 2018 at 05:45:27PM +0530, Karthik Subrahmanya wrote: > > > "In a replica 2 volume... If we set the client-quorum option to > > > auto, then the first brick must always be up, irrespective of the > > > status of the second brick. If only the second brick is up,

Hi, I have simple R question. I have a vector x that contains real numbers. I would like to create another vector col that is the same length of x such that: if x[i] < 250 then col[i] = "red" else if x[i] < 500 then col[i] = "blue" else if x[i] < 750 then col[i] = "green" else col[i] = "black" for all i I am convinced that there is probably a

On Tue, Feb 27, 2018 at 1:40 PM, Dave Sherohman <dave at sherohman.org> wrote: > On Tue, Feb 27, 2018 at 12:00:29PM +0530, Karthik Subrahmanya wrote: > > I will try to explain how you can end up in split-brain even with cluster > > wide quorum: > > Yep, the explanation made sense. I hadn't considered the possibility of > alternating outages. Thanks! > >

Venky Shankar, can you follow up on these questions? I too have this issue and cannot resolve the reference to '/nonexistent/gsyncd'. As Steve mentions, the nonexistent reference in the logs looks like the culprit especially seeing that the ssh command trying to be run is printed on an earlier line with the incorrect remote path. I have followed the configuration steps as documented in

Dear all, I'm running GlusterFS 3.4 alpha2 together with oVirt 3.2. This is solely a test system and it doesn't have much data or anything important in it. Currently it has only 2 VM's running and disk usage is around 15 GB. I have been trying to set up a geo-replication for disaster recovery testing. For geo-replication I did following: All machines are running CentOS 6.4 and using

Hi, Have you checked for any file system errors on the brick mount point? I once was facing weird io errors and xfs_repair fixed the issue. What about the heal? Does it report any pending heals? On Feb 15, 2018 14:20, "Dave Sherohman" <dave at sherohman.org> wrote: > Well, it looks like I've stumped the list, so I did a bit of additional > digging myself: > >