Thanks! When creating the volume, nothing is printed in mnt-.storage1.log: # gluster volume create storage transport rdma julia:/mnt/.storage1 sandra:/mnt/.storage2 force volume create: storage: success: please start the volume to access data When trying to start it, this is what is printed: # gluster volume start storage volume start: storage: failed: Commit failed on localhost. Please check the log file for more details. mnt-.storage1.log: [2014-10-14 07:33:02.824540] I [glusterfsd.c:1959:main] 0-/usr/sbin/glusterfsd: Started running /usr/sbin/glusterfsd version 3.5.2 (/usr/sbin/glusterfsd -s julia --volfile-id storage.julia.mnt-.storage1 -p /var/lib/glusterd/vols/storage/run/julia-mnt-.storage1.pid -S /var/run/7eaed01afd14de7e3952eb902987f975.socket --brick-name /mnt/.storage1 -l /var/log/glusterfs/bricks/mnt-.storage1.log --xlator-option *-posix.glusterd-uuid=4d50f191-88be-44ac-9a36-06b562e3e8e3 --brick-port 49159 --xlator-option storage-server.listen-port=49159) [2014-10-14 07:33:02.828826] I [socket.c:3561:socket_init] 0-socket.glusterfsd: SSL support is NOT enabled [2014-10-14 07:33:02.828886] I [socket.c:3576:socket_init] 0-socket.glusterfsd: using system polling thread [2014-10-14 07:33:02.829086] I [socket.c:3561:socket_init] 0-glusterfs: SSL support is NOT enabled [2014-10-14 07:33:02.829109] I [socket.c:3576:socket_init] 0-glusterfs: using system polling thread [2014-10-14 07:33:02.843382] I [graph.c:254:gf_add_cmdline_options] 0-storage-server: adding option 'listen-port' for volume 'storage-server' with value '49159' [2014-10-14 07:33:02.843414] I [graph.c:254:gf_add_cmdline_options] 0-storage-posix: adding option 'glusterd-uuid' for volume 'storage-posix' with value '4d50f191-88be-44ac-9a36-06b562e3e8e3' [2014-10-14 07:33:02.844500] I [rpcsvc.c:2127:rpcsvc_set_outstanding_rpc_limit] 0-rpc-service: Configured rpc.outstanding-rpc-limit with value 64 [2014-10-14 07:33:02.845302] W [options.c:888:xl_opt_validate] 0-storage-server: option 'listen-port' is deprecated, preferred is 'transport.rdma.listen-port', continuing with correction [2014-10-14 07:33:02.845950] W [rdma.c:4194:__gf_rdma_ctx_create] 0-rpc-transport/rdma: rdma_cm event channel creation failed (No such device) [2014-10-14 07:33:02.845978] E [rdma.c:4482:init] 0-rdma.storage-server: Failed to initialize IB Device [2014-10-14 07:33:02.845991] E [rpc-transport.c:333:rpc_transport_load] 0-rpc-transport: 'rdma' initialization failed [2014-10-14 07:33:02.846044] W [rpcsvc.c:1535:rpcsvc_transport_create] 0-rpc-service: cannot create listener, initing the transport failed [2014-10-14 07:33:02.846065] W [server.c:912:init] 0-storage-server: creation of listener failed [2014-10-14 07:33:02.846078] E [xlator.c:403:xlator_init] 0-storage-server: Initialization of volume 'storage-server' failed, review your volfile again [2014-10-14 07:33:02.846093] E [graph.c:307:glusterfs_graph_init] 0-storage-server: initializing translator failed [2014-10-14 07:33:02.846105] E [graph.c:502:glusterfs_graph_activate] 0-graph: init failed [2014-10-14 07:33:02.846472] W [glusterfsd.c:1095:cleanup_and_exit] (-->/usr/lib64/libgfrpc.so.0(rpc_clnt_handle_reply+0xa5) [0x7f73d816f995] (-->/usr/sbin/glusterfsd(mgmt_getspec_cbk+0x320) [0x40bd50] (-->/usr/sbin/glusterfsd(glusterfs_process_volfp+0x106) [0x405146]))) 0-: received signum (0), shutting down So it looks like there is a problem with rdma. Sandra and Julia computers are successfully connected with Infiniband. 2014-10-13 18:21 GMT+02:00 Joe Julian <joe@xxxxxxxxxxxxxxxx>: > > On 10/13/2014 09:07 AM, Jesus Carretero wrote: >> >> I updated my CentOS gluster to version 3.5.2.1.el6, and now the volume >> doesn't start. >> >> This is the peer: >> >> # gluster peer status >> Number of Peers: 1 >> >> Hostname: sandra >> Uuid: a6234622-a205-4311-8f60-8e30236fdd72 >> State: Peer in Cluster (Connected) >> >> This is the volume: >> >> # gluster volume create storage transport rdma julia:/mnt/.storage1 >> sandra:/mnt/.storage2 force >> volume create: storage: success: please start the volume to access data >> >> # gluster volume info >> >> Volume Name: storage >> Type: Distribute >> Volume ID: 5ea2f8f5-c404-484b-b7b4-5a26fe66d6ac >> Status: Created >> Number of Bricks: 2 >> Transport-type: rdma >> Bricks: >> Brick1: julia:/mnt/.storage1 >> Brick2: sandra:/mnt/.storage2 >> >> This is what happens when I try to start the storage: >> >> # gluster volume start storage >> volume start: storage: failed: Commit failed on localhost. Please >> check the log file for more details. >> >> This is the log /var/log/glusterfs/etc-glusterfs-glusterd.vol.log : >> >> [2014-10-13 16:02:17.084383] I >> [glusterd-pmap.c:271:pmap_registry_remove] 0-pmap: removing brick >> (null) on port 49158 >> [2014-10-13 16:02:17.091475] E >> [glusterd-utils.c:4704:glusterd_brick_start] 0-management: Unable to >> start brick julia:/mnt/.storage1 >> [2014-10-13 16:02:17.091523] E >> [glusterd-syncop.c:1014:gd_commit_op_phase] 0-management: Commit of >> operation 'Volume Start' failed on localhost >> >> What could be happening? > > Look at the brick log on julia in > /var/log/glusterfs/bricks/mnt-.storage1.log > > julia:/mnt/.storage1 > > _______________________________________________ > Gluster-users mailing list > Gluster-users@xxxxxxxxxxx > http://supercolony.gluster.org/mailman/listinfo/gluster-users _______________________________________________ Gluster-users mailing list Gluster-users@xxxxxxxxxxx http://supercolony.gluster.org/mailman/listinfo/gluster-users
