[Gluster-users] KVM guest I/O errors with xfs backed gluster volumes

Jacob Yundt jyundt at gmail.com
Sat Jul 6 18:14:37 UTC 2013


I was curious about that myself.  However, the version (3.4.0beta4)
seems to be correctly identified at the top of the glusterfsd log:

[2013-07-04 19:07:55.146042] I [glusterfsd.c:1878:main]
0-/usr/sbin/glusterfsd: Started running /usr/sbin/glusterfsd version
3.4.0beta4 (/usr/sbin/glusterfsd -s 1jane --volfile-id
xfs.1jane.gluster-xfs -p
/var/lib/glusterd/vols/xfs/run/1jane-gluster-xfs.pid -S
/var/run/1d5719178c3494e8d8b9da644b56814e.socket --brick-name
/gluster/xfs -l /var/log/glusterfs/bricks/gluster-xfs.log
--xlator-option
*-posix.glusterd-uuid=941dc521-bdb1-4281-a24f-2e71f93ee585
--brick-port 49152 --xlator-option xfs-server.listen-port=49152)
[2013-07-04 19:07:55.149065] I [socket.c:3480:socket_init]
0-socket.glusterfsd: SSL support is NOT enabled
[2013-07-04 19:07:55.149105] I [socket.c:3495:socket_init]
0-socket.glusterfsd: using system polling thread
[2013-07-04 19:07:55.149260] I [socket.c:3480:socket_init]
0-glusterfs: SSL support is NOT enabled
[2013-07-04 19:07:55.149276] I [socket.c:3495:socket_init]
0-glusterfs: using system polling thread
[2013-07-04 19:07:55.156295] I [graph.c:239:gf_add_cmdline_options]
0-xfs-server: adding option 'listen-port' for volume 'xfs-server' with
value '49152'
[2013-07-04 19:07:55.156317] I [graph.c:239:gf_add_cmdline_options]
0-xfs-posix: adding option 'glusterd-uuid' for volume 'xfs-posix' with
value '941dc521-bdb1-4281-a24f-2e71f93ee585'
[2013-07-04 19:07:55.157570] W [options.c:848:xl_opt_validate]
0-xfs-server: option 'listen-port' is deprecated, preferred is
'transport.socket.listen-port', continuing with correction
[2013-07-04 19:07:55.157606] I [socket.c:3480:socket_init]
0-tcp.xfs-server: SSL support is NOT enabled
[2013-07-04 19:07:55.157618] I [socket.c:3495:socket_init]
0-tcp.xfs-server: using system polling thread
[2013-07-04 19:07:55.157712] D
[options.c:1111:xlator_option_init_path] 0-xfs-index: option
index-base using set value /gluster/xfs/.glusterfs/indices
[2013-07-04 19:07:55.157812] T
[options.c:1105:xlator_option_init_int32] 0-xfs-io-threads: option
thread-count using default value 16
[2013-07-04 19:07:55.157839] T
[options.c:1105:xlator_option_init_int32] 0-xfs-io-threads: option
high-prio-threads using default value 16
[2013-07-04 19:07:55.157852] T
[options.c:1105:xlator_option_init_int32] 0-xfs-io-threads: option
normal-prio-threads using default value 16
[2013-07-04 19:07:55.157863] T
[options.c:1105:xlator_option_init_int32] 0-xfs-io-threads: option
low-prio-threads using default value 16
[2013-07-04 19:07:55.157890] T
[options.c:1105:xlator_option_init_int32] 0-xfs-io-threads: option
least-prio-threads using default value 1
[2013-07-04 19:07:55.157901] T
[options.c:1105:xlator_option_init_int32] 0-xfs-io-threads: option
idle-time using default value 120
[2013-07-04 19:07:55.157911] T
[options.c:1109:xlator_option_init_bool] 0-xfs-io-threads: option
enable-least-priority using default value on
[2013-07-04 19:07:55.157923] T
[options.c:1105:xlator_option_init_int32] 0-xfs-io-threads: option
least-rate-limit using default value 0
[2013-07-04 19:07:55.157933] T
[options.c:77:xlator_option_validate_int] 0-xfs-io-threads: no range
check required for 'option least-rate-limit 0'
[2013-07-04 19:07:55.157994] D [io-threads.c:2440:__iot_workers_scale]
0-xfs-io-threads: scaled threads to 1 (queue_size=0/1)
[2013-07-04 19:07:55.158026] T
[options.c:1104:xlator_option_init_uint32] 0-xfs-access-control:
option super-uid using default value 0
[2013-07-04 19:07:55.158041] T
[options.c:77:xlator_option_validate_int] 0-xfs-access-control: no
range check required for 'option super-uid 0'
[2013-07-04 19:07:55.164366] T
[options.c:1104:xlator_option_init_uint32] 0-xfs-posix: option
brick-uid not set
[2013-07-04 19:07:55.164396] T
[options.c:1104:xlator_option_init_uint32] 0-xfs-posix: option
brick-gid not set
[2013-07-04 19:07:55.164421] T
[options.c:1109:xlator_option_init_bool] 0-xfs-posix: option linux-aio
using default value off
Given volfile:
+------------------------------------------------------------------------------+
  1: volume xfs-posix
  2:     type storage/posix
  3:     option volume-id f456ec63-3b6f-4aae-875a-a661e7b6f581
  4:     option directory /gluster/xfs
  5: end-volume
  6:
  7: volume xfs-access-control
  8:     type features/access-control
  9:     subvolumes xfs-posix
 10: end-volume
 11:
 12: volume xfs-locks
 13:     type features/locks
 14:     subvolumes xfs-access-control
 15: end-volume
 16:
 17: volume xfs-io-threads
 18:     type performance/io-threads
 19:     subvolumes xfs-locks
 20: end-volume
 21:
 22: volume xfs-index
 23:     type features/index
 24:     option index-base /gluster/xfs/.glusterfs/indices
 25:     subvolumes xfs-io-threads
 26: end-volume
 27:
 28: volume xfs-marker
 29:     type features/marker
 30:     option quota off
 31:     option xtime off
 32:     option timestamp-file /var/lib/glusterd/vols/xfs/marker.tstamp
 33:     option volume-uuid f456ec63-3b6f-4aae-875a-a661e7b6f581
 34:     subvolumes xfs-index
 35: end-volume
 36:
 37: volume /gluster/xfs
 38:     type debug/io-stats
 39:     option count-fop-hits off
 40:     option latency-measurement off
 41:     option log-level TRACE
 42:     subvolumes xfs-marker
 43: end-volume
 44:
 45: volume xfs-server
 46:     type protocol/server
 47:     option auth.addr./gluster/xfs.allow *
 48:     option
auth.login.ee4ce610-1508-41a1-ac64-9fa269421378.password
ee805b73-1d1e-472b-829f-e227978690ec
 49:     option auth.login./gluster/xfs.allow
ee4ce610-1508-41a1-ac64-9fa269421378
 50:     option transport-type tcp
 51:     subvolumes /gluster/xfs
 52: end-volume

+------------------------------------------------------------------------------+

On Sat, Jul 6, 2013 at 1:48 PM, John Mark Walker <johnmark at johnmark.org> wrote:
>
> On Jul 6, 2013 1:46 PM, "Jacob Yundt" <jyundt at gmail.com> wrote:
>>
>> I'm still getting the same errors with 3.4.0beta4.  I increased the
>> brick log level to TRACE and repeated my same tests.  I keep getting
>> these errors:
>>
>
>> 0-rpc-service: submitted reply for rpc-message (XID: 0x411x, Program:
>
>
>> GlusterFS 3.3, ProgVers: 330, Proc: 12) to rpc-transport
>> (tcp.xfs-server)
>
> Why does this show the version as 3.3? Is that supposed to be the case?
>
> -JM
>
>> [2013-07-04 19:10:13.915927] T [rpcsvc.c:498:rpcsvc_handle_rpc_call]
>> 0-rpcsvc: Client port: 1021
>> [2013-07-04 19:10:13.916011] T
>> [rpcsvc-auth.c:321:rpcsvc_auth_request_init] 0-rpc-service: Auth
>> handler: AUTH_GLUSTERFS-v2
>> [2013-07-04 19:10:13.916074] T [rpcsvc.c:388:rpcsvc_request_create]
>> 0-rpc-service: received rpc-message (XID: 0x19c, Ver: 2, Program:
>> 1298437, ProgVers: 330, Proc: 12) from rpc-transport (tcp.xfs-server)
>> [2013-07-04 19:10:13.916144] T
>> [auth-glusterfs.c:216:auth_glusterfs_v2_authenticate] 0-rpc-service:
>> Auth Info: pid: 7227, uid: 107, gid: 107, owner: ad582833abe8f286
>> [2013-07-04 19:10:13.916206] T [rpcsvc.c:214:rpcsvc_program_actor]
>> 0-rpc-service: Actor found: GlusterFS 3.3 - READ
>> [2013-07-04 19:10:13.916490] D [io-threads.c:326:iot_schedule]
>> 0-xfs-io-threads: READ scheduled as slow fop
>> [2013-07-04 19:10:13.916624] E [posix.c:1940:posix_readv] 0-xfs-posix:
>> read failed on fd=0x1e2e44c: Invalid argument
>>
>> I've updated the BZ
>> (https://bugzilla.redhat.com/show_bug.cgi?id=958781) with the full
>> glusterfsd logs, client logs and strace output.
>>
>> -Jacob
>>
>> On Wed, May 8, 2013 at 2:33 PM, Jacob Yundt <jyundt at gmail.com> wrote:
>> > Still having this problem on 3.4.0beta1.  I updated the RH BZ with
>> > more information (logs, straces, etc).
>> >
>> > -Jacob
>> _______________________________________________
>> Gluster-users mailing list
>> Gluster-users at gluster.org
>> http://supercolony.gluster.org/mailman/listinfo/gluster-users



More information about the Gluster-users mailing list