[Gluster-users] NFS cann't use by esxi with Striped Volume

[higkoohk]

Error msg my useful:

@ /var/log/messages
GlusterFS[21413]: C [nfs.c:271:nfs_start_subvol_lookup_cbk] 0-nfs: Failed
to lookup root: Input/output error
GlusterFS[21434]: C [nfs.c:271:nfs_start_subvol_lookup_cbk] 0-nfs: Failed
to lookup root: Input/output error
GlusterFS[21460]: C [nfs.c:271:nfs_start_subvol_lookup_cbk] 0-nfs: Failed
to lookup root: Input/output error
GlusterFS[21488]: C [nfs.c:271:nfs_start_subvol_lookup_cbk] 0-nfs: Failed
to lookup root: Input/output error

@ /var/log/glusterfs/nfs.log
E [afr-self-heal-common.c:197:afr_sh_print_split_brain_log]
0-images-stripe-replicate-0: Unable to self-heal contents of '/' (possible
split-brain). Please delete the file from all but the preferred subvolume.-
Pending matrix:  [ [ 0 2 ] [ 2 0 ] ]
E [afr-self-heal-common.c:2212:afr_self_heal_completion_cbk]
0-images-stripe-replicate-0: background  meta-data self-heal failed on /
E [afr-self-heal-common.c:197:afr_sh_print_split_brain_log]
0-images-stripe-replicate-0: Unable to self-heal contents of '/' (possible
split-brain). Please delete the file from all but the preferred subvolume.-
Pending matrix:  [ [ 0 2 ] [ 2 0 ] ]
E [afr-self-heal-common.c:2212:afr_self_heal_completion_cbk]
0-images-stripe-replicate-0: background  meta-data self-heal failed on /
C [nfs.c:271:nfs_start_subvol_lookup_cbk] 0-nfs: Failed to lookup root:
Input/output error

No error in :
/var/log/glusterfs/bricks/data-glusterfs-images-stripe.log
/var/log/glusterfs/glustershd.log
/var/log/glusterfs/cli.log
/var/log/glusterfs/etc-glusterfs-glusterd.vol.log


2013/9/5 higkoohk <higkoohk at gmail.com>

> After some test , I confirm that Esxi cann't use Striped-Replicate volume
> on Glusterfs's nfs.
> But could success on Distributed-Replicate .
>
> Anyone know how or why ?
>
>
> 2013/9/5 higkoohk <higkoohk at gmail.com>
>
>> Thanks Vijay !
>>
>> It run success after 'volume set images-stripe nfs.nlm off'.
>>
>> Now I can use Esxi with Glusterfs's nfs export .
>>
>> Many thanks!
>>
>>
>> 2013/9/5 Anand Avati <avati at gluster.org>
>>
>>> This looks like it might be because you need -
>>>
>>> http://review.gluster.org/4591
>>>
>>> If you can confirm, we can backport it to 3.4.1.
>>>
>>> Thanks,
>>>
>>> Avati
>>>
>>> On Wed, Sep 4, 2013 at 9:03 PM, Vijay Bellur <vbellur at redhat.com> wrote:
>>>
>>>>  On 09/05/2013 04:55 AM, higkoohk wrote:
>>>> > yes,I'm using GlusterFS 3.4.0
>>>> >
>>>>
>>>> Can you try by turning off acl with nfs. Some performance numbers have
>>>> been better with acl turned off. This can be done through:
>>>>
>>>> volume set <volname> nfs.acl off
>>>>
>>>> If there is no improvement, opening a bug and attaching gluster logs to
>>>> that would be useful.
>>>>
>>>> -Vijay
>>>>
>>>> > 在 2013-9-5 上午3:12，"Vijay Bellur" <vbellur at redhat.com
>>>> > <mailto:vbellur at redhat.com>>写道：
>>>> >
>>>> >     On 09/04/2013 08:38 AM, higkoohk wrote:
>>>> >
>>>> >         Hello everyone:
>>>> >
>>>> >               When I use esxi mount nfs storage to gluster, mount
>>>> success!
>>>> >               But , It is very very slowly when create vm, then
>>>> failed !
>>>> >               I can see the vm's dir and files create successed. but
>>>> the
>>>> >         size is
>>>> >         zero.
>>>> >
>>>> >               Does anyone hit this ? What happened and how does me do
>>>> ?
>>>> >
>>>> >
>>>> >     Is this behavior being observed with GlusterFS 3.4.0?
>>>> >
>>>> >     -Vijay
>>>>
>>>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://supercolony.gluster.org/pipermail/gluster-users/attachments/20130905/76dbe743/attachment.html>