[Gluster-users] Extremely slow NFS access from Windows

[Nux!]

On 31.07.2013 18:14, Anand Avati wrote:
> On Wed, Jul 31, 2013 at 8:57 AM, Nux! <nux at li.nux.ro> wrote:
> 
>> On 31.07.2013 16:21, Nux! wrote:
>> 
>>> On 31.07.2013 12:29, Nux! wrote:
>>> 
>>>> Hello,
>>>> I'm trying to use a volume on Windows via NFS and every operation 
>>>> is
>>>> very slow and in the nfs.log I see the following:
>>>> [2013-07-31 11:26:22.644794] W [socket.c:514:__socket_rwv]
>>>> 0-socket.nfs-server: writev failed (Invalid argument)
>>>> [2013-07-31 11:26:34.738955] W [socket.c:514:__socket_rwv]
>>>> 0-socket.nfs-server: writev failed (Invalid argument)
>>>> [2013-07-31 11:26:46.816790] W [socket.c:514:__socket_rwv]
>>>> 0-socket.nfs-server: writev failed (Invalid argument)
>>>> [2013-07-31 11:26:56.466939] W 
>>>> [rpcsvc.c:180:rpcsvc_program_**actor]
>>>> 0-rpc-service: RPC program version not available (req 100003 2)
>>>> [2013-07-31 11:26:56.466993] E
>>>> [rpcsvc.c:448:rpcsvc_check_**and_reply_error] 0-rpcsvc: rpc actor 
>>>> failed
>>>> to complete successfully
>>> 
>>> 
> 
> Looks like Windows is trying to connect to an NFSv2 server. Gluster 
> support
> NFSv3 only. The "Invalid argument" errors showing up prior also look
> suspicious. Can you get trace logs?
> 
> Avati

I'll see what I can do.
Just to rule it out, just tested Windows 2008 R2 with Centos 6 NFSv4 
server and it works very well.

-- 
Sent from the Delta quadrant using Borg technology!

Nux!
www.nux.ro