[Gluster-users] smth wrongs with glusterfs
Hello, again Smth wrong with my install gluster OS:Debian cat /etc/debian_version 7.6 Package: glusterfs-server Versions: 3.2.7-3+deb7u1 Description: I have 3 servers with bricks (192.168.1.1 - node1,192.168.1.2 - node2, 192.168.1.3 - node3) volume create by: gluster volume create opennebula transport tcp node1:/data node2:/data node3:/data 192.168.1.4 - client # volume info gluster volume info Volume Name: opennebula Type: Replicate Status: Started Number of Bricks: 3 Transport-type: tcp Bricks: Brick1: node1:/data Brick2: node2:/data Brick3: node3:/data Options Reconfigured: server.allow-insecure: on #peer info gluster peer show unrecognized word: show (position 1) root@node1:/data# gluster peer status Number of Peers: 2 Hostname: node3 Uuid: 355f676d-044c-453d-8e82-13b810c089bb State: Peer in Cluster (Connected) Hostname: node2 Uuid: bfed0b59-6b2f-474e-a3d7-18b0eb0b1c77 State: Peer in Cluster (Connected) # on client i mounted volume by: mount.glusterfs node1:/opennebula /var/lib/one/ ls -al /var/lib/one - show files, but after 1 mins ls -al /var/lib/one - hangs up log [2014-12-05 13:28:53.290981] I [fuse-bridge.c:3461:fuse_graph_setup] 0-fuse: switched to graph 0 [2014-12-05 13:28:53.291223] I [fuse-bridge.c:3049:fuse_init] 0-glusterfs-fuse: FUSE inited with protocol versions: glusterfs 7.13 kernel 7.17 [2014-12-05 13:28:53.291800] I [afr-common.c:1522:afr_set_root_inode_on_first_lookup] 0-opennebula-replicate-0: added root inode [2014-12-05 13:29:16.355469] C [client-handshake.c:121:rpc_client_ping_timer_expired] 0-opennebula-client-0: server 192.168.1.1:24009 has not responded in the last 42 seconds, disconnecting. [2014-12-05 13:29:16.355684] E [rpc-clnt.c:341:saved_frames_unwind] (-->/usr/lib/libgfrpc.so.0(rpc_clnt_notify+0xb0) [0x7f7020ccec60] (-->/usr/lib/libgfrpc.so.0(rpc_clnt_connection_cleanup+0x7e) [0x7f7020cce8fe] (-->/usr/lib/libgfrpc.so.0(saved_frames_destroy+0xe) [0x7f7020cce85e]))) 0-opennebula-client-0: forced unwinding frame type(GlusterFS 3.1) op(READDIRP(40)) called at 2014-12-05 13:27:10.345569 [2014-12-05 13:29:16.355754] E [client3_1-fops.c:1937:client3_1_readdirp_cbk] 0-opennebula-client-0: remote operation failed: Transport endpoint is not connected [2014-12-05 13:29:16.355772] I [afr-self-heal-entry.c:1846:afr_sh_entry_impunge_readdir_cbk] 0-opennebula-replicate-0: readdir of / on subvolume opennebula-client-0 failed (Transport endpoint is not connected) [2014-12-05 13:29:16.356073] I [socket.c:2275:socket_submit_request] 0-opennebula-client-0: not connected (priv->connected = 0) [2014-12-05 13:29:16.356091] W [rpc-clnt.c:1417:rpc_clnt_submit] 0-opennebula-client-0: failed to submit rpc-request (XID: 0x112x Program: GlusterFS 3.1, ProgVers: 310, Proc: 33) to rpc-transport (opennebula-client-0) [2014-12-05 13:29:16.356107] I [afr-self-heal-entry.c:129:afr_sh_entry_erase_pending_cbk] 0-opennebula-replicate-0: /: failed to erase pending xattrs on opennebula-client-0 (Transport endpoint is not connected) [2014-12-05 13:29:16.356209] E [rpc-clnt.c:341:saved_frames_unwind] (-->/usr/lib/libgfrpc.so.0(rpc_clnt_notify+0xb0) [0x7f7020ccec60] (-->/usr/lib/libgfrpc.so.0(rpc_clnt_connection_cleanup+0x7e) [0x7f7020cce8fe] (-->/usr/lib/libgfrpc.so.0(saved_frames_destroy+0xe) [0x7f7020cce85e]))) 0-opennebula-client-0: forced unwinding frame type(GlusterFS Handshake) op(PING(3)) called at 2014-12-05 13:27:52.348889 [2014-12-05 13:29:16.356227] W [client-handshake.c:264:client_ping_cbk] 0-opennebula-client-0: timer must have expired [2014-12-05 13:29:16.356257] E [rpc-clnt.c:341:saved_frames_unwind] (-->/usr/lib/libgfrpc.so.0(rpc_clnt_notify+0xb0) [0x7f7020ccec60] (-->/usr/lib/libgfrpc.so.0(rpc_clnt_connection_cleanup+0x7e) [0x7f7020cce8fe] (-->/usr/lib/libgfrpc.so.0(saved_frames_destroy+0xe) [0x7f7020cce85e]))) 0-opennebula-client-0: forced unwinding frame type(GlusterFS 3.1) op(STATFS(14)) called at 2014-12-05 13:28:20.214777 [2014-12-05 13:29:16.356274] I [client3_1-fops.c:637:client3_1_statfs_cbk] 0-opennebula-client-0: remote operation failed: Transport endpoint is not connected [2014-12-05 13:29:16.356304] I [client.c:1883:client_rpc_notify] 0-opennebula-client-0: disconnected [2014-12-05 13:29:16.356663] I [client-handshake.c:1090:select_server_supported_programs] 0-opennebula-client-0: Using Program GlusterFS 3.2.7, Num (1298437), Version (310) [2014-12-05 13:29:16.356966] W [rpc-common.c:64:xdr_to_generic] (-->/usr/lib/libgfrpc.so.0(rpc_clnt_notify+0x85) [0x7f7020ccec35] (-->/usr/lib/libgfrpc.so.0(rpc_clnt_handle_reply+0xa5) [0x7f7020cce295] (-->/usr/lib/glusterfs/3.2.7/xlator/protocol/client.so(client3_1_entrylk_cbk+0x52) [0x7f701da44122]))) 0-xdr: XDR decoding failed [2014-12-05 13:29:16.356993] E [client3_1-fops.c:1292:client3_1_
Re: [Gluster-users] [Gluster-devel] Proposal for more sub-maintainers
On Thursday 04 December 2014 08:32 PM, Niels de Vos wrote: On Fri, Nov 28, 2014 at 01:08:29PM +0530, Vijay Bellur wrote: Hi All, To supplement our ongoing effort of better patch management, I am proposing the addition of more sub-maintainers for various components. The rationale behind this proposal & the responsibilities of maintainers continue to be the same as discussed in these lists a while ago [1]. Here is the proposed list: Build - Kaleb Keithley & Niels de Vos DHT - Raghavendra Gowdappa & Shyam Ranganathan docs - Humble Chirammal & Lalatendu Mohanty gfapi - Niels de Vos & Shyam Ranganathan index & io-threads - Pranith Karampuri posix - Pranith Karampuri & Raghavendra Bhat I'm wondering if there are any volunteers for maintaining the FUSE component? And maybe rewrite it to use libgfapi and drop the mount.glusterfs script? I am interested. Thanks, Vijay Niels We intend to update Gerrit with this list by 8th of December. Please let us know if you have objections, concerns or feedback on this process by then. Thanks, Vijay [1] http://gluster.org/pipermail/gluster-devel/2014-April/025425.html ___ Gluster-devel mailing list gluster-de...@gluster.org http://supercolony.gluster.org/mailman/listinfo/gluster-devel ___ Gluster-devel mailing list gluster-de...@gluster.org http://supercolony.gluster.org/mailman/listinfo/gluster-devel ___ Gluster-users mailing list Gluster-users@gluster.org http://supercolony.gluster.org/mailman/listinfo/gluster-users
Re: [Gluster-users] [Gluster-devel] Proposal for more sub-maintainers
On Thursday 04 December 2014 08:32 PM, Niels de Vos wrote: On Fri, Nov 28, 2014 at 01:08:29PM +0530, Vijay Bellur wrote: Hi All, To supplement our ongoing effort of better patch management, I am proposing the addition of more sub-maintainers for various components. The rationale behind this proposal & the responsibilities of maintainers continue to be the same as discussed in these lists a while ago [1]. Here is the proposed list: Build - Kaleb Keithley & Niels de Vos DHT - Raghavendra Gowdappa & Shyam Ranganathan docs - Humble Chirammal & Lalatendu Mohanty gfapi - Niels de Vos & Shyam Ranganathan index & io-threads - Pranith Karampuri posix - Pranith Karampuri & Raghavendra Bhat I'm wondering if there are any volunteers for maintaining the FUSE component? And maybe rewrite it to use libgfapi and drop the mount.glusterfs script? Niels I am interested too. :) Regards, Raghavendra Bhat We intend to update Gerrit with this list by 8th of December. Please let us know if you have objections, concerns or feedback on this process by then. Thanks, Vijay [1] http://gluster.org/pipermail/gluster-devel/2014-April/025425.html ___ Gluster-devel mailing list gluster-de...@gluster.org http://supercolony.gluster.org/mailman/listinfo/gluster-devel ___ Gluster-users mailing list Gluster-users@gluster.org http://supercolony.gluster.org/mailman/listinfo/gluster-users ___ Gluster-users mailing list Gluster-users@gluster.org http://supercolony.gluster.org/mailman/listinfo/gluster-users
Re: [Gluster-users] [Gluster-devel] Proposal for more sub-maintainers
On 12/04/2014 08:32 PM, Niels de Vos wrote: On Fri, Nov 28, 2014 at 01:08:29PM +0530, Vijay Bellur wrote: Hi All, To supplement our ongoing effort of better patch management, I am proposing the addition of more sub-maintainers for various components. The rationale behind this proposal & the responsibilities of maintainers continue to be the same as discussed in these lists a while ago [1]. Here is the proposed list: Build - Kaleb Keithley & Niels de Vos DHT - Raghavendra Gowdappa & Shyam Ranganathan docs - Humble Chirammal & Lalatendu Mohanty gfapi - Niels de Vos & Shyam Ranganathan index & io-threads - Pranith Karampuri posix - Pranith Karampuri & Raghavendra Bhat I'm wondering if there are any volunteers for maintaining the FUSE component? I am interested in this work if you can guide me. Pranith And maybe rewrite it to use libgfapi and drop the mount.glusterfs script? Niels We intend to update Gerrit with this list by 8th of December. Please let us know if you have objections, concerns or feedback on this process by then. Thanks, Vijay [1] http://gluster.org/pipermail/gluster-devel/2014-April/025425.html ___ Gluster-devel mailing list gluster-de...@gluster.org http://supercolony.gluster.org/mailman/listinfo/gluster-devel ___ Gluster-devel mailing list gluster-de...@gluster.org http://supercolony.gluster.org/mailman/listinfo/gluster-devel ___ Gluster-users mailing list Gluster-users@gluster.org http://supercolony.gluster.org/mailman/listinfo/gluster-users
Re: [Gluster-users] Empty bricks .... :( df -h hangs
Yeah. sorry :) --- Старший Системный Администратор Алексей Шалин ОсОО "Хостер kg" - http://www.hoster.kg ул. Ахунбаева 123 (здание БГТС) h...@hoster.kg ___ Gluster-users mailing list Gluster-users@gluster.org http://supercolony.gluster.org/mailman/listinfo/gluster-users
Re: [Gluster-users] Empty bricks .... :( df -h hangs
On 12/04/2014 10:13 PM, Alexey Shalin wrote: seems issue was in auth.allow: 176.126.164.0/22 hmmm... client and nodes was from this subnet.. any way .. I recreated volume and now everything looks good The documentation states that " Valid IP address which includes wild card patterns including *, such as 192.168.1.*" not CIDR blocks. ___ Gluster-users mailing list Gluster-users@gluster.org http://supercolony.gluster.org/mailman/listinfo/gluster-users
Re: [Gluster-users] Empty bricks .... :( df -h hangs
seems issue was in auth.allow: 176.126.164.0/22 hmmm... client and nodes was from this subnet.. any way .. I recreated volume and now everything looks good thx --- Старший Системный Администратор Алексей Шалин ОсОО "Хостер kg" - http://www.hoster.kg ул. Ахунбаева 123 (здание БГТС) h...@hoster.kg ___ Gluster-users mailing list Gluster-users@gluster.org http://supercolony.gluster.org/mailman/listinfo/gluster-users
[Gluster-users] Empty bricks .... :( df -h hangs
Hello I create volume with next command: gluster volume create opennebula replica 3 transport tcp node1:/data node2:/data node3:/data # gluster volume info Volume Name: opennebula Type: Replicate Status: Started Number of Bricks: 3 Transport-type: tcp Bricks: Brick1: node1:/data Brick2: node2:/data Brick3: node3:/data Options Reconfigured: auth.allow: 176.126.164.0/22 then i mount it from client: root@master:/# mount.glusterfs node1:/opennebula /var/lib/one/datastores/0 root@master:/# root@master:/# df -h and hangs :( also on node1... root@node1:~# df -h also hangs :( But if will stop(kill) df -h on client, i'm able to do df -h on client Can you please help me ? Thx --- Старший Системный Администратор Алексей Шалин ОсОО "Хостер kg" - http://www.hoster.kg ул. Ахунбаева 123 (здание БГТС) h...@hoster.kg ___ Gluster-users mailing list Gluster-users@gluster.org http://supercolony.gluster.org/mailman/listinfo/gluster-users
[Gluster-users] Hello, small simple question about creating volume
Hello I have 3 servers and 1 server (client) 3 servers having /data folder with size 300Gb Can you tell me the best combination to create volume? gluster volume create my_volume replica 3 transport tcp node1:/data node2:/data node3:/data is this ok for best performance ? Thx --- Старший Системный Администратор Алексей Шалин ОсОО "Хостер kg" - http://www.hoster.kg ул. Ахунбаева 123 (здание БГТС) h...@hoster.kg ___ Gluster-users mailing list Gluster-users@gluster.org http://supercolony.gluster.org/mailman/listinfo/gluster-users
[Gluster-users] A year's worth of Gluster
1 DHT volume comprising 16 50TB bricks spread across 4 servers. Each server has 10Gbit Ethernet. Each brick is a ZOL RADIZ2 pool with a single filesystem. ___ Gluster-users mailing list Gluster-users@gluster.org http://supercolony.gluster.org/mailman/listinfo/gluster-users
Re: [Gluster-users] replication and blanacing issues
As a follow up: I created another replicated striped volume - two brick replica, striped against two sets of servers (four servers in all) - same config as mentioned below. I started pouring data into it, and here's my output from `du`: peer1 - 47G peer2 - 47G peer3 - 47G peer4 - 24G Peer1 and Peer2 should be mirrored, and peer3 and peer4 should be mirrored. This time, data seems more balanced - EXCEPT that peer4 continues to lag FAR behind - like in the example below. Any suggestions would be appreciated. Jason From: gluster-users-boun...@gluster.org [mailto:gluster-users-boun...@gluster.org] On Behalf Of Kiebzak, Jason M. Sent: Thursday, December 04, 2014 10:08 AM To: gluster-users@gluster.org Subject: [Gluster-users] replication and blanacing issues It seems that I have two issues: 1) Data is not balanced between all bricks 2) one replication "pair" is not staying in sync I have four servers/peers, each with one brick, all running 3.6.1. There are two volumes, each running as distributed replicated volume. Below, I've included some info. All Daemon are running. The four peers were all added at the same time. Problem 1) for volume1, the peer1/peer2 set have 236G, while peer3 has 3.9T. Shouldn't it be split more evenly - close to 2T on each set of servers? A similar issue is seen with volume2, but the total data set (thus the diff) is not as large. Problem 2) peer3 and peer4 should be replicated to each other. Peer1 and peer2 have identical disk usage, where as peer3 and peer4 are egregiously out of sync. Data on both peer3 and peer4 continues to grow (I am actively migrating 50T to volume 1). `gluster volume info` give this: Volume Name: volume1 Type: Distributed-Replicate Volume ID: bf461760-c412-42df-9e1d-7db7f793d344 Status: Started Number of Bricks: 2 x 2 = 4 Transport-type: tcp Bricks: Brick1: ip1:/data/volume1 Brick2: ip2:/data/volume1 Brick3: ip3:/data/volume1 Brick4: ip4:/data/volume1 Options Reconfigured: features.quota: on auth.allow: serverip Volume Name: volume2 Type: Distributed-Replicate Volume ID: 54a8dbee-387f-4a61-9f67-3e2accb83072 Status: Started Number of Bricks: 2 x 2 = 4 Transport-type: tcp Bricks: Brick1: ip1:/data/volume2 Brick2: ip2:/data/volume2 Brick3: ip3:/data/volume2 Brick4: ip4:/data/volume2 Options Reconfigured: auth.allow: serverip If I do a `# du -h --max-dpeth=1` on each peer, I get this: Peer1 236G/data/volume1 177G/data/volume2 Peer2 236G/data/volume1 177G/data/volume2 Peer3 3.9T/data/volume1 179G/data/volume2 Peer4 524G/data/volume1 102G/data/volume2 ___ Gluster-users mailing list Gluster-users@gluster.org http://supercolony.gluster.org/mailman/listinfo/gluster-users
Re: [Gluster-users] Sudden interference between 2 independent gluster volumes
If the volumes had the same names, I have no idea what the result of that would be. If they had different names, it sounds like the volume data only sync'ed one direction. Theoretically, you can look in /var/lib/glusterd/vols and ensure that both volume directories exist on both servers (I would do this with glusterd stopped) without detaching them as peers. On 12/04/2014 08:31 AM, Peter B. wrote: Status update: Server "A" and "B" now consider themselves gluster peers: Each one lists the other one as peer ($ gluster peer status). However, "gluster volume info " only lists the bricks of "B". To solve my problem and restore autonomy of "A", I think I could do the following: On server "A": 1) gluster peer detach "B" 2) Re-add the local bricks on "A" (which were already part of the game, but ain't anymore) Could this work? Is there anything I must watch out for, before re-adding the bricks of "A" back to volume "A" again? Sorry for asking so many questions here, but I'm progressively understanding the problem/situation better as we speak. Therefore the changing questions :) Sorry... Thanks again, Peter ___ Gluster-users mailing list Gluster-users@gluster.org http://supercolony.gluster.org/mailman/listinfo/gluster-users ___ Gluster-users mailing list Gluster-users@gluster.org http://supercolony.gluster.org/mailman/listinfo/gluster-users
Re: [Gluster-users] Sudden interference between 2 independent gluster volumes
On 12/04/2014 09:08 PM, Peter B. wrote: > This is actually directly related to my problem is mentioned here on Monday: > "Folder disappeared on volume, but exists on bricks." > > I probed node "A" from server "B", which caused all this. My bad. > :( > > > No data is lost, but is there any way to recover the volume information in > /var/lib/glusterd on server "A", to separate it from "B" again? How are you saying that volume information is overlapping each other? If these volumes were created at different clusters they wouldn't have any common data, would they? ~Atin > > > Thank you very much in advance, > Pb > > ___ > Gluster-users mailing list > Gluster-users@gluster.org > http://supercolony.gluster.org/mailman/listinfo/gluster-users > ___ Gluster-users mailing list Gluster-users@gluster.org http://supercolony.gluster.org/mailman/listinfo/gluster-users
Re: [Gluster-users] Introducing gdash - A simple GlusterFS dashboard
Added --gluster option to specify the gluster path if you are using source install. If you already installed gdash, upgrade using `sudo pip install -U gdash` Usage: sudo gdash --gluster /usr/local/sbin/gluster Updated the same in blog: http://aravindavk.in/blog/introducing-gdash/ -- regards Aravinda http://aravindavk.in On Thu, Dec 4, 2014 at 7:33 AM, Aravinda wrote: Hi All, I created a small local installable web app called gdash, a simple dashboard for GlusterFS. "gdash is a super-young project, which shows GlusterFS volume information about local, remote clusters. This app is based on GlusterFS's capability of executing gluster volume info and gluster volume status commands for a remote server using --remote-host option." It is very easy to install using pip or easy_install. Check my blog post for more in detail(with screenshots). http://aravindavk.in/blog/introducing-gdash/ Comments and Suggestions Welcome. -- regards Aravinda http://aravindavk.in ___ Gluster-users mailing list Gluster-users@gluster.org http://supercolony.gluster.org/mailman/listinfo/gluster-users
Re: [Gluster-users] Problem starting glusterd on CentOS 6
On 04/12/14 16:05 +0100, Jan-Hendrik Zab wrote: > Here is also a complete debug log from starting glusterd: > > -jhz > > http://www.l3s.de/~zab/glusterfs.log Apparently we fixed that specific problem. We deactivated iptables and the glusterd can again communicate with the other processes. We didn't change the rules tho. And the glusterd was working find in the mean time, as far as we could tell anyway. -jhz pgp7kM8hz01H8.pgp Description: PGP signature ___ Gluster-users mailing list Gluster-users@gluster.org http://supercolony.gluster.org/mailman/listinfo/gluster-users
Re: [Gluster-users] Sudden interference between 2 independent gluster volumes
Status update: Server "A" and "B" now consider themselves gluster peers: Each one lists the other one as peer ($ gluster peer status). However, "gluster volume info " only lists the bricks of "B". To solve my problem and restore autonomy of "A", I think I could do the following: On server "A": 1) gluster peer detach "B" 2) Re-add the local bricks on "A" (which were already part of the game, but ain't anymore) Could this work? Is there anything I must watch out for, before re-adding the bricks of "A" back to volume "A" again? Sorry for asking so many questions here, but I'm progressively understanding the problem/situation better as we speak. Therefore the changing questions :) Sorry... Thanks again, Peter ___ Gluster-users mailing list Gluster-users@gluster.org http://supercolony.gluster.org/mailman/listinfo/gluster-users
Re: [Gluster-users] Sudden interference between 2 independent gluster volumes
This is actually directly related to my problem is mentioned here on Monday: "Folder disappeared on volume, but exists on bricks." I probed node "A" from server "B", which caused all this. My bad. :( No data is lost, but is there any way to recover the volume information in /var/lib/glusterd on server "A", to separate it from "B" again? Thank you very much in advance, Pb ___ Gluster-users mailing list Gluster-users@gluster.org http://supercolony.gluster.org/mailman/listinfo/gluster-users
Re: [Gluster-users] Folder disappeared on volume, but exists on bricks.
I think I know now what happened: - 2 gluster volumes on 2 different servers: A and B. - A=production, B=testing - On server "B" we will soon expand, so I read up on how to add new nodes. - Therefore on server "B" I ran "gluster probe A", assuming that "probe" was just reading *if* A would be available. It seems that "probing" another node already writes configuration data onto them. That seems to be the reason why the data of the bricks didn't show up on the volume mountpoint on "A", because it was now already pointing to "B". Pb ___ Gluster-users mailing list Gluster-users@gluster.org http://supercolony.gluster.org/mailman/listinfo/gluster-users
Re: [Gluster-users] [Gluster-devel] Proposal for more sub-maintainers
On Fri, Nov 28, 2014 at 01:08:29PM +0530, Vijay Bellur wrote: > Hi All, > > To supplement our ongoing effort of better patch management, I am proposing > the addition of more sub-maintainers for various components. The rationale > behind this proposal & the responsibilities of maintainers continue to be > the same as discussed in these lists a while ago [1]. Here is the proposed > list: > > Build - Kaleb Keithley & Niels de Vos > > DHT - Raghavendra Gowdappa & Shyam Ranganathan > > docs - Humble Chirammal & Lalatendu Mohanty > > gfapi - Niels de Vos & Shyam Ranganathan > > index & io-threads - Pranith Karampuri > > posix - Pranith Karampuri & Raghavendra Bhat I'm wondering if there are any volunteers for maintaining the FUSE component? And maybe rewrite it to use libgfapi and drop the mount.glusterfs script? Niels > > We intend to update Gerrit with this list by 8th of December. Please let us > know if you have objections, concerns or feedback on this process by then. > > Thanks, > Vijay > > [1] http://gluster.org/pipermail/gluster-devel/2014-April/025425.html > > ___ > Gluster-devel mailing list > gluster-de...@gluster.org > http://supercolony.gluster.org/mailman/listinfo/gluster-devel pgpTVcRlm6igb.pgp Description: PGP signature ___ Gluster-users mailing list Gluster-users@gluster.org http://supercolony.gluster.org/mailman/listinfo/gluster-users
[Gluster-users] replication and blanacing issues
It seems that I have two issues: 1) Data is not balanced between all bricks 2) one replication "pair" is not staying in sync I have four servers/peers, each with one brick, all running 3.6.1. There are two volumes, each running as distributed replicated volume. Below, I've included some info. All Daemon are running. The four peers were all added at the same time. Problem 1) for volume1, the peer1/peer2 set have 236G, while peer3 has 3.9T. Shouldn't it be split more evenly - close to 2T on each set of servers? A similar issue is seen with volume2, but the total data set (thus the diff) is not as large. Problem 2) peer3 and peer4 should be replicated to each other. Peer1 and peer2 have identical disk usage, where as peer3 and peer4 are egregiously out of sync. Data on both peer3 and peer4 continues to grow (I am actively migrating 50T to volume 1). `gluster volume info` give this: Volume Name: volume1 Type: Distributed-Replicate Volume ID: bf461760-c412-42df-9e1d-7db7f793d344 Status: Started Number of Bricks: 2 x 2 = 4 Transport-type: tcp Bricks: Brick1: ip1:/data/volume1 Brick2: ip2:/data/volume1 Brick3: ip3:/data/volume1 Brick4: ip4:/data/volume1 Options Reconfigured: features.quota: on auth.allow: serverip Volume Name: volume2 Type: Distributed-Replicate Volume ID: 54a8dbee-387f-4a61-9f67-3e2accb83072 Status: Started Number of Bricks: 2 x 2 = 4 Transport-type: tcp Bricks: Brick1: ip1:/data/volume2 Brick2: ip2:/data/volume2 Brick3: ip3:/data/volume2 Brick4: ip4:/data/volume2 Options Reconfigured: auth.allow: serverip If I do a `# du -h --max-dpeth=1` on each peer, I get this: Peer1 236G/data/volume1 177G/data/volume2 Peer2 236G/data/volume1 177G/data/volume2 Peer3 3.9T/data/volume1 179G/data/volume2 Peer4 524G/data/volume1 102G/data/volume2 ___ Gluster-users mailing list Gluster-users@gluster.org http://supercolony.gluster.org/mailman/listinfo/gluster-users
Re: [Gluster-users] Problem starting glusterd on CentOS 6
Here is also a complete debug log from starting glusterd: -jhz http://www.l3s.de/~zab/glusterfs.log pgpsXcscEmQG5.pgp Description: PGP signature ___ Gluster-users mailing list Gluster-users@gluster.org http://supercolony.gluster.org/mailman/listinfo/gluster-users
[Gluster-users] Sudden interference between 2 independent gluster volumes
Hi all, Since the strange "hickup" I had on Monday (files disappearing from the volume, although existing on the bricks), another very strange (and horrible) thing happened: Out of the blue, gluster "Volume-A" is now pointing to the bricks of another, completely separate and independent "Volume-B". Ouch! O.o Running "gluster volume info volume-a" and the same for "volume-b", both list the bricks of "volume-b". They even show the identical volume ID. Regardless of "why" that happened, does anyone here have any idea how I can properly fix this and separate the volumes again? I'm very grateful for any help! Thanks in advance, Peter ___ Gluster-users mailing list Gluster-users@gluster.org http://supercolony.gluster.org/mailman/listinfo/gluster-users
[Gluster-users] Problem starting glusterd on CentOS 6
Hello, we have a glusterfs 3.6.1 installation on CentOS 6 with two servers and one brick each. We just saw some trouble with inodes not being able to be read and decided to shut down one of our servers and run a xfs_repair and the filesystem. (This turned up nothing.) After which we tried to start the glusterd server again, but we only got a few error messages in the logs and I'm not sure what to do next. Any help would be very appreciated. Our systems are gluster1/2 and each has a brick named brick0. If you need any further information please ask. The log messages fro gluster2 follow: data-brick0-brick.log: [2014-12-04 13:54:54.862104] I [MSGID: 100030] [glusterfsd.c:2018:main] 0-/usr/sbin/glusterfsd: Started running /usr/sbin/glusterfsd version 3.6.1 (args: /usr/sbin/glusterfsd -s gluster2 --volfile-id data.gluster2.data-brick0-brick -p /var/lib/glusterd/vols/data/run/gluster2-data-brick0-brick.pid -S /var/run/75e81344cb7da77f1168ab31c31bfebd.socket --brick-name /data/brick0/brick -l /var/log/glusterfs/bricks/data-brick0-brick.log --xlator-option *-posix.glusterd-uuid=1ad5077c-4314-43f1-84ef-e560ca62e155 --brick-port 49154 --xlator-option data-server.listen-port=49154) [2014-12-04 13:55:57.868573] E [socket.c:2267:socket_connect_finish] 0-glusterfs: connection to 192.168.1.19:24007 failed (Connection timed out) [2014-12-04 13:55:57.868696] E [glusterfsd-mgmt.c:1811:mgmt_rpc_notify] 0-glusterfsd-mgmt: failed to connect with remote-host: gluster2 (Transport endpoint is not connected) [2014-12-04 13:55:57.868722] I [glusterfsd-mgmt.c:1817:mgmt_rpc_notify] 0-glusterfsd-mgmt: Exhausted all volfile servers [2014-12-04 13:55:57.869050] W [glusterfsd.c:1194:cleanup_and_exit] (--> 0-: received signum (1), shutting down [2014-12-04 13:55:57.875266] W [rpc-clnt.c:1562:rpc_clnt_submit] 0-glusterfs: failed to submit rpc-request (XID: 0x1 Program: Gluster Portmap, ProgVers: 1, Proc: 5) to rpc-transport (glusterfs) etc-glusterfs-glusterd.vol.log (we get a lot of the following wiht different UUIDs): [2014-12-04 14:03:16.431380] W [socket.c:611:__socket_rwv] 0-management: readv on /var/run/75e81344cb7da77f1168ab31c31bfebd.socket failed (Invalid argument) glustershd.log: [2014-12-04 13:55:57.891652] E [socket.c:2267:socket_connect_finish] 0-data-client-1: connection to 192.168.1.19:24007 failed (Connection timed out) pgptmNTUkmT5C.pgp Description: PGP signature ___ Gluster-users mailing list Gluster-users@gluster.org http://supercolony.gluster.org/mailman/listinfo/gluster-users
Re: [Gluster-users] Introducing gdash - A simple GlusterFS dashboard
Very nice! I see a small Puppet module and a Vagrant setup in my immediate future for using this. Thanks for sharing! -- Gene Liverman Systems Administrator Information Technology Services University of West Georgia glive...@westga.edu ITS: Making Technology Work for You! This e-mail and any attachments may contain confidential and privileged information. If you are not the intended recipient, please notify the sender immediately by return mail, delete this message, and destroy any copies. Any dissemination or use of this information by a person other than the intended recipient is unauthorized and may be illegal or actionable by law. On Dec 3, 2014 9:03 PM, "Aravinda" wrote: > Hi All, > > I created a small local installable web app called gdash, a simple > dashboard for GlusterFS. > > "gdash is a super-young project, which shows GlusterFS volume information > about local, remote clusters. This app is based on GlusterFS's capability > of executing gluster volume info and gluster volume status commands for a > remote server using --remote-host option." > > It is very easy to install using pip or easy_install. > > Check my blog post for more in detail(with screenshots). > http://aravindavk.in/blog/introducing-gdash/ > > Comments and Suggestions Welcome. > > -- > regards > Aravinda > http://aravindavk.in > > > ___ > Gluster-users mailing list > Gluster-users@gluster.org > http://supercolony.gluster.org/mailman/listinfo/gluster-users > ___ Gluster-users mailing list Gluster-users@gluster.org http://supercolony.gluster.org/mailman/listinfo/gluster-users
Re: [Gluster-users] Introducing gdash - A simple GlusterFS dashboard
Wow cool thanks. Would be good to have it as a ovirt plugin. A. On Dec 4, 2014 3:03 AM, "Aravinda" wrote: > Hi All, > > I created a small local installable web app called gdash, a simple > dashboard for GlusterFS. > > "gdash is a super-young project, which shows GlusterFS volume information > about local, remote clusters. This app is based on GlusterFS's capability > of executing gluster volume info and gluster volume status commands for a > remote server using --remote-host option." > > It is very easy to install using pip or easy_install. > > Check my blog post for more in detail(with screenshots). > http://aravindavk.in/blog/introducing-gdash/ > > Comments and Suggestions Welcome. > > -- > regards > Aravinda > http://aravindavk.in > > > ___ > Gluster-users mailing list > Gluster-users@gluster.org > http://supercolony.gluster.org/mailman/listinfo/gluster-users > ___ Gluster-users mailing list Gluster-users@gluster.org http://supercolony.gluster.org/mailman/listinfo/gluster-users