Re: [Gluster-users] Cannot list `.snaps/` directory
...and here's the statedump of the client, snapd and brick snap processes from the 4.1 test cluster. (File names are as outputted from the GlusterD processes, so it looks like the `snapd` daemon has an off-by-one error in the statedump.) Thanks, Riccardo glusterdump.1726.dump.1532446976.gz Description: application/gzip run-gluster-snaps-39f9f186c67f418a989f783c3289d166-brick3.5446.dump.1532446840.gz Description: application/gzip napd-glusterfs.5482.dump.1532446843.gz Description: application/gzip ___ Gluster-users mailing list Gluster-users@gluster.org https://lists.gluster.org/mailman/listinfo/gluster-users
Re: [Gluster-users] Cannot list `.snaps/` directory
Let me try out the reproducible. By the time, can you try taking statedump of the client process, snapd process, snapshot brick process. Please refer to documentation [1] in case if you have any trouble in performing statedump operation. [1] : https://docs.gluster.org/en/v3/Troubleshooting/statedump/ Rafi KC - Original Message - From: "Riccardo Murri" To: "Mohammed Rafi K C" Cc: gluster-users@gluster.org Sent: Tuesday, July 24, 2018 6:42:44 PM Subject: Re: [Gluster-users] Cannot list `.snaps/` directory Hello, I have set up a test cluster with GlusterFS 4.1 and Ubuntu 16.04.5 and I get the same behavior: `ls .snaps/test/` hangs indefinitely in a getdents() system call. I can mount and list the snapshot just fine with `mount -t glusterfs`, it's just the USS feature that is not working. Is this a known bug? Any hints on how to work it around? Thanks, Riccardo ___ Gluster-users mailing list Gluster-users@gluster.org https://lists.gluster.org/mailman/listinfo/gluster-users
Re: [Gluster-users] Cannot list `.snaps/` directory
Hello, I have set up a test cluster with GlusterFS 4.1 and Ubuntu 16.04.5 and I get the same behavior: `ls .snaps/test/` hangs indefinitely in a getdents() system call. I can mount and list the snapshot just fine with `mount -t glusterfs`, it's just the USS feature that is not working. Is this a known bug? Any hints on how to work it around? Thanks, Riccardo ___ Gluster-users mailing list Gluster-users@gluster.org https://lists.gluster.org/mailman/listinfo/gluster-users
Re: [Gluster-users] Cannot list `.snaps/` directory
Re-sending the log files as attachments, to avoid MUAs corrupting them... Ciao, R ### client logs: [2018-07-19 13:30:10.206657] I [glusterfsd-mgmt.c:52:mgmt_cbk_spec] 0-mgmt: Volume file changed [2018-07-19 13:30:10.316710] I [MSGID: 114007] [client.c:2402:client_check_remote_host] 0-glusterfs-snapd-client: Remote host is not set. Assuming the volfile server as remote host [Invalid argument] [2018-07-19 13:30:10.316910] D [io-stats.c:3870:reconfigure] 0-glusterfs: reconfigure returning 0 [2018-07-19 13:30:10.316969] D [glusterfsd-mgmt.c:1920:mgmt_getspec_cbk] 0-glusterfsd-mgmt: No need to re-load volfile, reconfigure done [2018-07-19 13:30:31.823912] D [MSGID: 0] [io-threads.c:358:iot_schedule] 0-glusterfs-io-threads: STAT scheduled as fast fop [2018-07-19 13:30:31.837598] D [MSGID: 0] [io-threads.c:358:iot_schedule] 0-glusterfs-io-threads: FLUSH scheduled as normal fop [2018-07-19 13:30:33.174222] D [MSGID: 0] [io-threads.c:358:iot_schedule] 0-glusterfs-io-threads: LOOKUP scheduled as fast fop [2018-07-19 13:30:33.175564] D [MSGID: 0] [dht-common.c:1056:dht_revalidate_cbk] 0-glusterfs-dht: revalidate lookup of /opt returned with op_ret 0 [2018-07-19 13:30:35.546485] D [logging.c:1979:_gf_msg_internal] 0-logging-infra: Buffer overflow of a buffer whose size limit is 5. About to flush least recently used log message to disk The message "D [MSGID: 0] [io-threads.c:358:iot_schedule] 0-glusterfs-io-threads: STAT scheduled as fast fop" repeated 3 times between [2018-07-19 13:30:31.823912] and [2018-07-19 13:30:35.540106] [2018-07-19 13:30:35.546479] D [MSGID: 0] [io-threads.c:358:iot_schedule] 0-glusterfs-io-threads: OPENDIR scheduled as fast fop [2018-07-19 13:30:35.548707] D [MSGID: 0] [io-threads.c:358:iot_schedule] 0-glusterfs-io-threads: READDIRP scheduled as fast fop [2018-07-19 13:30:35.562717] D [logging.c:1979:_gf_msg_internal] 0-logging-infra: Buffer overflow of a buffer whose size limit is 5. About to flush least recently used log message to disk [2018-07-19 13:30:35.562298] D [MSGID: 0] [io-threads.c:358:iot_schedule] 0-glusterfs-io-threads: READDIRP scheduled as fast fop [2018-07-19 13:30:35.562713] D [MSGID: 0] [io-threads.c:358:iot_schedule] 0-glusterfs-io-threads: STAT scheduled as fast fop [2018-07-19 13:30:35.562919] D [MSGID: 0] [io-threads.c:358:iot_schedule] 0-glusterfs-io-threads: OPENDIR scheduled as fast fop [2018-07-19 13:30:35.564746] D [MSGID: 0] [io-threads.c:358:iot_schedule] 0-glusterfs-io-threads: READDIRP scheduled as fast fop [2018-07-19 13:30:35.574831] D [logging.c:1979:_gf_msg_internal] 0-logging-infra: Buffer overflow of a buffer whose size limit is 5. About to flush least recently used log message to disk [2018-07-19 13:30:35.570561] D [MSGID: 0] [io-threads.c:358:iot_schedule] 0-glusterfs-io-threads: READDIRP scheduled as fast fop [2018-07-19 13:30:35.574827] D [MSGID: 0] [io-threads.c:358:iot_schedule] 0-glusterfs-io-threads: STAT scheduled as fast fop [2018-07-19 13:30:35.575078] D [MSGID: 0] [io-threads.c:358:iot_schedule] 0-glusterfs-io-threads: OPENDIR scheduled as fast fop [2018-07-19 13:30:35.576864] D [MSGID: 0] [io-threads.c:358:iot_schedule] 0-glusterfs-io-threads: READDIRP scheduled as fast fop [2018-07-19 13:30:37.546586] D [logging.c:1855:gf_log_flush_timeout_cbk] 0-logging-infra: Log timer timed out. About to flush outstanding messages if present The message "D [MSGID: 0] [io-threads.c:358:iot_schedule] 0-glusterfs-io-threads: FLUSH scheduled as normal fop" repeated 2 times between [2018-07-19 13:30:31.837598] and [2018-07-19 13:30:31.838077] The message "D [MSGID: 0] [dht-common.c:1056:dht_revalidate_cbk] 0-glusterfs-dht: revalidate lookup of /opt returned with op_ret 0" repeated 4 times between [2018-07-19 13:30:33.175564] and [2018-07-19 13:30:33.176783] [2018-07-19 13:30:35.582728] D [MSGID: 0] [io-threads.c:358:iot_schedule] 0-glusterfs-io-threads: READDIRP scheduled as fast fop [2018-07-19 13:30:37.546747] D [logging.c:1817:__gf_log_inject_timer_event] 0-logging-infra: Starting timer now. Timeout = 120, current buf size = 5 [2018-07-19 13:30:38.647775] D [MSGID: 0] [io-threads.c:358:iot_schedule] 0-glusterfs-io-threads: STAT scheduled as fast fop [2018-07-19 13:30:38.650530] D [MSGID: 0] [io-threads.c:358:iot_schedule] 0-glusterfs-io-threads: OPENDIR scheduled as fast fop [2018-07-19 13:30:38.653807] D [MSGID: 0] [io-threads.c:358:iot_schedule] 0-glusterfs-io-threads: READDIRP scheduled as fast fop [2018-07-19 13:30:38.678216] D [MSGID: 0] [io-threads.c:358:iot_schedule] 0-glusterfs-io-threads: LOOKUP scheduled as fast fop [2018-07-19 13:30:38.680700] D [rpc-clnt-ping.c:99:rpc_clnt_remove_ping_timer_locked] (--> /usr/lib/x86_64-linux-gnu/libglusterfs.so.0(_gf_log_callingfn+0x13b)[0x7f396011b4bb] (--> /usr/lib/x86_64-linux-gnu/libgfrpc.so.0(rpc_clnt_remove_ping_timer_locked+0x84)[0x7f395feec524] (--> /usr/lib/x86_64-linux-gnu/libgfrpc.so.0(+0x12c4d)[0x7f395feecc4d] (-->
Re: [Gluster-users] Cannot list `.snaps/` directory
Hello Rafi, many thanks for your prompt reply. I have now tried to do: ls /data/opt/.snaps/test_*/ which hung and I interrupted it with Ctrl+C a few moments later. I attach below the DEBUG-level logs of 1 brick and the client. When should I take the statedump and how do I send them? Thanks, Riccardo ### client logs: [2018-07-19 13:30:10.206657] I [glusterfsd-mgmt.c:52:mgmt_cbk_spec] 0-mgmt: Volume file changed [2018-07-19 13:30:10.316710] I [MSGID: 114007] [client.c:2402:client_check_remote_host] 0-glusterfs-snapd-client: Remote host is not set. Assuming the volfile server as remote host [Invalid argument] [2018-07-19 13:30:10.316910] D [io-stats.c:3870:reconfigure] 0-glusterfs: reconfigure returning 0 [2018-07-19 13:30:10.316969] D [glusterfsd-mgmt.c:1920:mgmt_getspec_cbk] 0-glusterfsd-mgmt: No need to re-load volfile, reconfigure done [2018-07-19 13:30:31.823912] D [MSGID: 0] [io-threads.c:358:iot_schedule] 0-glusterfs-io-threads: STAT scheduled as fast fop [2018-07-19 13:30:31.837598] D [MSGID: 0] [io-threads.c:358:iot_schedule] 0-glusterfs-io-threads: FLUSH scheduled as normal fop [2018-07-19 13:30:33.174222] D [MSGID: 0] [io-threads.c:358:iot_schedule] 0-glusterfs-io-threads: LOOKUP scheduled as fast fop [2018-07-19 13:30:33.175564] D [MSGID: 0] [dht-common.c:1056:dht_revalidate_cbk] 0-glusterfs-dht: revalidate lookup of /opt returned with op_ret 0 [2018-07-19 13:30:35.546485] D [logging.c:1979:_gf_msg_internal] 0-logging-infra: Buffer overflow of a buffer whose size limit is 5. About to flush least recently used log message to disk The message "D [MSGID: 0] [io-threads.c:358:iot_schedule] 0-glusterfs-io-threads: STAT scheduled as fast fop" repeated 3 times between [2018-07-19 13:30:31.823912] and [2018-07-19 13:30:35.540106] [2018-07-19 13:30:35.546479] D [MSGID: 0] [io-threads.c:358:iot_schedule] 0-glusterfs-io-threads: OPENDIR scheduled as fast fop [2018-07-19 13:30:35.548707] D [MSGID: 0] [io-threads.c:358:iot_schedule] 0-glusterfs-io-threads: READDIRP scheduled as fast fop [2018-07-19 13:30:35.562717] D [logging.c:1979:_gf_msg_internal] 0-logging-infra: Buffer overflow of a buffer whose size limit is 5. About to flush least recently used log message to disk [2018-07-19 13:30:35.562298] D [MSGID: 0] [io-threads.c:358:iot_schedule] 0-glusterfs-io-threads: READDIRP scheduled as fast fop [2018-07-19 13:30:35.562713] D [MSGID: 0] [io-threads.c:358:iot_schedule] 0-glusterfs-io-threads: STAT scheduled as fast fop [2018-07-19 13:30:35.562919] D [MSGID: 0] [io-threads.c:358:iot_schedule] 0-glusterfs-io-threads: OPENDIR scheduled as fast fop [2018-07-19 13:30:35.564746] D [MSGID: 0] [io-threads.c:358:iot_schedule] 0-glusterfs-io-threads: READDIRP scheduled as fast fop [2018-07-19 13:30:35.574831] D [logging.c:1979:_gf_msg_internal] 0-logging-infra: Buffer overflow of a buffer whose size limit is 5. About to flush least recently used log message to disk [2018-07-19 13:30:35.570561] D [MSGID: 0] [io-threads.c:358:iot_schedule] 0-glusterfs-io-threads: READDIRP scheduled as fast fop [2018-07-19 13:30:35.574827] D [MSGID: 0] [io-threads.c:358:iot_schedule] 0-glusterfs-io-threads: STAT scheduled as fast fop [2018-07-19 13:30:35.575078] D [MSGID: 0] [io-threads.c:358:iot_schedule] 0-glusterfs-io-threads: OPENDIR scheduled as fast fop [2018-07-19 13:30:35.576864] D [MSGID: 0] [io-threads.c:358:iot_schedule] 0-glusterfs-io-threads: READDIRP scheduled as fast fop [2018-07-19 13:30:37.546586] D [logging.c:1855:gf_log_flush_timeout_cbk] 0-logging-infra: Log timer timed out. About to flush outstanding messages if present The message "D [MSGID: 0] [io-threads.c:358:iot_schedule] 0-glusterfs-io-threads: FLUSH scheduled as normal fop" repeated 2 times between [2018-07-19 13:30:31.837598] and [2018-07-19 13:30:31.838077] The message "D [MSGID: 0] [dht-common.c:1056:dht_revalidate_cbk] 0-glusterfs-dht: revalidate lookup of /opt returned with op_ret 0" repeated 4 times between [2018-07-19 13:30:33.175564] and [2018-07-19 13:30:33.176783] [2018-07-19 13:30:35.582728] D [MSGID: 0] [io-threads.c:358:iot_schedule] 0-glusterfs-io-threads: READDIRP scheduled as fast fop [2018-07-19 13:30:37.546747] D [logging.c:1817:__gf_log_inject_timer_event] 0-logging-infra: Starting timer now. Timeout = 120, current buf size = 5 [2018-07-19 13:30:38.647775] D [MSGID: 0] [io-threads.c:358:iot_schedule] 0-glusterfs-io-threads: STAT scheduled as fast fop [2018-07-19 13:30:38.650530] D [MSGID: 0] [io-threads.c:358:iot_schedule] 0-glusterfs-io-threads: OPENDIR scheduled as fast fop [2018-07-19 13:30:38.653807] D [MSGID: 0] [io-threads.c:358:iot_schedule] 0-glusterfs-io-threads: READDIRP scheduled as fast fop [2018-07-19 13:30:38.678216] D [MSGID: 0] [io-threads.c:358:iot_schedule] 0-glusterfs-io-threads: LOOKUP scheduled as fast fop [2018-07-19 13:30:38.680700] D [rpc-clnt-ping.c:99:rpc_clnt_remove_ping_timer_locked] (--> /usr/lib/x86_64-linux-gnu/libglusterfs.so.0(_gf_log_callingfn+0x13b)[0x7f396011b4bb] (-->
Re: [Gluster-users] Cannot list `.snaps/` directory
On 07/19/2018 06:35 PM, Riccardo Murri wrote: > Hello Rafi, > > mounting as a regular volume works fine: > > ubuntu@slurm-master-001:/var/log/glusterfs$ sudo mount -t glusterfs > glusterfs-server-001:/snaps/test_GMT-2018.07.18-10.02.05/glusterfs > /mnt > > ubuntu@slurm-master-001:/var/log/glusterfs$ ls /mnt/ > active filesystem homes jobdaemon opt share > > ubuntu@slurm-master-001:/var/log/glusterfs$ ls /mnt/opt > Anaconda2-5.1.0-Linux-x86_64 bin lmod modulefiles > > Any hint why it should not work via USS? Let's figure it out :). Can you enable debug log for both client and brick. Also can you take statedump of client process and brick process Regards Rafi KC > > Thanks, > R ___ Gluster-users mailing list Gluster-users@gluster.org https://lists.gluster.org/mailman/listinfo/gluster-users
Re: [Gluster-users] Cannot list `.snaps/` directory
Hello Rafi, mounting as a regular volume works fine: ubuntu@slurm-master-001:/var/log/glusterfs$ sudo mount -t glusterfs glusterfs-server-001:/snaps/test_GMT-2018.07.18-10.02.05/glusterfs /mnt ubuntu@slurm-master-001:/var/log/glusterfs$ ls /mnt/ active filesystem homes jobdaemon opt share ubuntu@slurm-master-001:/var/log/glusterfs$ ls /mnt/opt Anaconda2-5.1.0-Linux-x86_64 bin lmod modulefiles Any hint why it should not work via USS? Thanks, R ___ Gluster-users mailing list Gluster-users@gluster.org https://lists.gluster.org/mailman/listinfo/gluster-users
Re: [Gluster-users] Cannot list `.snaps/` directory
Can you try mounting snapshot just like we mount a regular volume? syntax mount -t glusterfs host1:/snaps// Regards Rafi KC - Original Message - From: "Riccardo Murri" To: gluster-users@gluster.org Sent: Wednesday, July 18, 2018 3:58:34 PM Subject: [Gluster-users] Cannot list `.snaps/` directory Hello, I am trying the USS snapshots on an existing cluster (GlusterFS 3.12.9 on Ubuntu 16.04, installed from the DEB packages on GlusterFS.org). I can successfully create a snapshot, and it is correctly listed under the volume's `.snaps` directory everywhere; for example: $ stat .snaps/test_GMT-2018.07.18-10.02.05 File: '.snaps/test_GMT-2018.07.18-10.02.05' Size: 4096Blocks: 8 IO Block: 131072 directory Device: 2bh/43d Inode: 11895042009497816687 Links: 6 Access: (0755/drwxr-xr-x) Uid: (0/root) Gid: (0/root) Access: 2018-07-16 13:33:29.649519330 + Modify: 2018-07-16 13:33:29.548396587 + Change: 2018-07-16 13:33:29.645519332 + Birth: - However running: ls .snaps/test_GMT-2018.07.18-10.02.05/ just hangs forever. Running the same command under `strace` shows that it's stuck repeatedly just doing this `getdents system call:: getdents(3, [{d_ino=15424314298293051273, d_off=9223372036854775805, d_reclen=32, d_name="modulefiles", d_type=DT_DIR}, {d_ino=1, d_off=7346686173273481909, d_reclen=24, d_name="..", d_type=DT_DIR}, {d_ino=13594788684206387598, d_off=7356868894832018317, d_reclen=24, d_name=".", d_type=DT_DIR}, {d_ino=9350865815378619609, d_off=9223372036854775805, d_reclen=24, d_name="bin", d_type=DT_DIR}], 131072) = 104 Looking in the server-side logs shows no issue (I am attaching the last lines of logs and other config commands below). What could be the problem here? Thanks, Riccardo (Note for the logs: snap was created at 10:02 UTC.) $ tail glusterd.log bricks/run-gluster-snaps*log snaps/glusterfs/snapd.log [2018-07-18 10:02:07.183666] I [glusterd-utils.c:6047:glusterd_brick_start] 0-management: starting a fresh brick process for brick /run/gluster/snaps/2bd07d5165de4277be94d3bc2b4a6ff4/brick4 [2018-07-18 10:02:07.194801] I [rpc-clnt.c:1044:rpc_clnt_connection_init] 0-management: setting frame-timeout to 600 [2018-07-18 10:02:07.296262] I [socket.c:2474:socket_event_handler] 0-transport: EPOLLERR - disconnecting now [2018-07-18 10:02:07.297582] I [MSGID: 106005] [glusterd-handler.c:6071:__glusterd_brick_rpc_notify] 0-management: Brick glusterfs-server-001:/run/gluster/snaps/2bd07d5165de4277be94d3bc2b4a6ff4/brick4 has disconnected from glusterd. [2018-07-18 10:02:07.298327] W [MSGID: 106057] [glusterd-snapshot-utils.c:410:glusterd_snap_volinfo_find] 0-management: Snap volume 2bd07d5165de4277be94d3bc2b4a6ff4.glusterfs-server-001.run-gluster-snaps-2bd07d5165de4277be94d3bc2b4a6ff4-brick4 not found [Invalid argument] [2018-07-18 10:02:07.587928] I [MSGID: 106143] [glusterd-pmap.c:295:pmap_registry_bind] 0-pmap: adding brick /run/gluster/snaps/2bd07d5165de4277be94d3bc2b4a6ff4/brick4 on port 49154 ==> bricks/run-gluster-snaps-2bd07d5165de4277be94d3bc2b4a6ff4-brick4.log <== 166: option transport.socket.keepalive-interval 2 167: option transport.socket.keepalive-count 9 168: option transport.listen-backlog 10 169: subvolumes /run/gluster/snaps/2bd07d5165de4277be94d3bc2b4a6ff4/brick4 170: end-volume 171: +--+ [2018-07-18 10:02:50.156027] I [addr.c:55:compare_addr_and_update] 0-/run/gluster/snaps/2bd07d5165de4277be94d3bc2b4a6ff4/brick4: allowed = "*", received addr = "172.23.62.200" [2018-07-18 10:02:50.156366] I [login.c:111:gf_auth] 0-auth/login: allowed user names: f75e457a-7898-4863-9754-2209ddf47573 [2018-07-18 10:02:50.156402] I [MSGID: 115029] [server-handshake.c:793:server_setvolume] 0-2bd07d5165de4277be94d3bc2b4a6ff4-server: accepted client from glusterfs-server-005-16843-2018/07/18-10:02:50:142015-glusterfs-client-12-0-0 (version: 3.12.9) ==> snaps/glusterfs/snapd.log <== [2018-07-18 08:27:43.710242] I [addr.c:55:compare_addr_and_update] 0-snapd-glusterfs: allowed = "*", received addr = "172.23.62.189" [2018-07-18 08:27:43.710291] I [MSGID: 115029] [server-handshake.c:793:server_setvolume] 0-glusterfs-server: accepted client from slurm-master-001-28933-2018/06/11-14:28:30:530655-glusterfs-snapd-client-45-0 (version: 3.12.9) [2018-07-18 08:27:43.713616] E [server-handshake.c:385:server_first_lookup] 0-snapd-glusterfs: lookup on root failed: Success [2018-07-18 08:27:43.729767] I [addr.c:55:compare_addr_and_update] 0-snapd-glusterfs: allowed = "*", received addr = "172.23.62.189" [2018-07-18 08:27:43.729809] I [MSGID: 115029] [server-handshake.c:793:server_setvolume] 0-glusterfs-server: accepted client from slurm-master-001-9204-2018/07/10-12:11:24:974712-glusterfs-snapd-client-18-0 (vers
[Gluster-users] Cannot list `.snaps/` directory
Hello, I am trying the USS snapshots on an existing cluster (GlusterFS 3.12.9 on Ubuntu 16.04, installed from the DEB packages on GlusterFS.org). I can successfully create a snapshot, and it is correctly listed under the volume's `.snaps` directory everywhere; for example: $ stat .snaps/test_GMT-2018.07.18-10.02.05 File: '.snaps/test_GMT-2018.07.18-10.02.05' Size: 4096Blocks: 8 IO Block: 131072 directory Device: 2bh/43d Inode: 11895042009497816687 Links: 6 Access: (0755/drwxr-xr-x) Uid: (0/root) Gid: (0/root) Access: 2018-07-16 13:33:29.649519330 + Modify: 2018-07-16 13:33:29.548396587 + Change: 2018-07-16 13:33:29.645519332 + Birth: - However running: ls .snaps/test_GMT-2018.07.18-10.02.05/ just hangs forever. Running the same command under `strace` shows that it's stuck repeatedly just doing this `getdents system call:: getdents(3, [{d_ino=15424314298293051273, d_off=9223372036854775805, d_reclen=32, d_name="modulefiles", d_type=DT_DIR}, {d_ino=1, d_off=7346686173273481909, d_reclen=24, d_name="..", d_type=DT_DIR}, {d_ino=13594788684206387598, d_off=7356868894832018317, d_reclen=24, d_name=".", d_type=DT_DIR}, {d_ino=9350865815378619609, d_off=9223372036854775805, d_reclen=24, d_name="bin", d_type=DT_DIR}], 131072) = 104 Looking in the server-side logs shows no issue (I am attaching the last lines of logs and other config commands below). What could be the problem here? Thanks, Riccardo (Note for the logs: snap was created at 10:02 UTC.) $ tail glusterd.log bricks/run-gluster-snaps*log snaps/glusterfs/snapd.log [2018-07-18 10:02:07.183666] I [glusterd-utils.c:6047:glusterd_brick_start] 0-management: starting a fresh brick process for brick /run/gluster/snaps/2bd07d5165de4277be94d3bc2b4a6ff4/brick4 [2018-07-18 10:02:07.194801] I [rpc-clnt.c:1044:rpc_clnt_connection_init] 0-management: setting frame-timeout to 600 [2018-07-18 10:02:07.296262] I [socket.c:2474:socket_event_handler] 0-transport: EPOLLERR - disconnecting now [2018-07-18 10:02:07.297582] I [MSGID: 106005] [glusterd-handler.c:6071:__glusterd_brick_rpc_notify] 0-management: Brick glusterfs-server-001:/run/gluster/snaps/2bd07d5165de4277be94d3bc2b4a6ff4/brick4 has disconnected from glusterd. [2018-07-18 10:02:07.298327] W [MSGID: 106057] [glusterd-snapshot-utils.c:410:glusterd_snap_volinfo_find] 0-management: Snap volume 2bd07d5165de4277be94d3bc2b4a6ff4.glusterfs-server-001.run-gluster-snaps-2bd07d5165de4277be94d3bc2b4a6ff4-brick4 not found [Invalid argument] [2018-07-18 10:02:07.587928] I [MSGID: 106143] [glusterd-pmap.c:295:pmap_registry_bind] 0-pmap: adding brick /run/gluster/snaps/2bd07d5165de4277be94d3bc2b4a6ff4/brick4 on port 49154 ==> bricks/run-gluster-snaps-2bd07d5165de4277be94d3bc2b4a6ff4-brick4.log <== 166: option transport.socket.keepalive-interval 2 167: option transport.socket.keepalive-count 9 168: option transport.listen-backlog 10 169: subvolumes /run/gluster/snaps/2bd07d5165de4277be94d3bc2b4a6ff4/brick4 170: end-volume 171: +--+ [2018-07-18 10:02:50.156027] I [addr.c:55:compare_addr_and_update] 0-/run/gluster/snaps/2bd07d5165de4277be94d3bc2b4a6ff4/brick4: allowed = "*", received addr = "172.23.62.200" [2018-07-18 10:02:50.156366] I [login.c:111:gf_auth] 0-auth/login: allowed user names: f75e457a-7898-4863-9754-2209ddf47573 [2018-07-18 10:02:50.156402] I [MSGID: 115029] [server-handshake.c:793:server_setvolume] 0-2bd07d5165de4277be94d3bc2b4a6ff4-server: accepted client from glusterfs-server-005-16843-2018/07/18-10:02:50:142015-glusterfs-client-12-0-0 (version: 3.12.9) ==> snaps/glusterfs/snapd.log <== [2018-07-18 08:27:43.710242] I [addr.c:55:compare_addr_and_update] 0-snapd-glusterfs: allowed = "*", received addr = "172.23.62.189" [2018-07-18 08:27:43.710291] I [MSGID: 115029] [server-handshake.c:793:server_setvolume] 0-glusterfs-server: accepted client from slurm-master-001-28933-2018/06/11-14:28:30:530655-glusterfs-snapd-client-45-0 (version: 3.12.9) [2018-07-18 08:27:43.713616] E [server-handshake.c:385:server_first_lookup] 0-snapd-glusterfs: lookup on root failed: Success [2018-07-18 08:27:43.729767] I [addr.c:55:compare_addr_and_update] 0-snapd-glusterfs: allowed = "*", received addr = "172.23.62.189" [2018-07-18 08:27:43.729809] I [MSGID: 115029] [server-handshake.c:793:server_setvolume] 0-glusterfs-server: accepted client from slurm-master-001-9204-2018/07/10-12:11:24:974712-glusterfs-snapd-client-18-0 (version: 3.12.9) [2018-07-18 08:27:43.730260] E [server-handshake.c:385:server_first_lookup] 0-snapd-glusterfs: lookup on root failed: Success [2018-07-18 08:28:49.401381] I [snapview-server-mgmt.c:22:mgmt_cbk_snap] 0-mgmt: list of snapshots changed [2018-07-18 09:57:29.838877] I [snapview-server-mgmt.c:22:mgmt_cbk_snap] 0-mgmt: list of snapshots changed [2018-07-18 09:58:28.026000] I [snapview-server-mgmt.c:22:mgmt_cbk_snap] 0-mgmt: