[Gluster-users] Problems with Glusterfs and OpenVz

Shain Miley smiley at npr.org
Wed Dec 15 19:14:30 UTC 2010


Below is the procedure that I used to get Gluster working with openvz,  
I believe that I successfully got 3.0.5 and 3.1.1 working...but way more 
testing was done using 3.0.5 then 3.1.1.

http://forum.proxmox.com/threads/1252-Proxmox-GlusterFS-2-and-FUSE


In terms of performance, I did not do too much benchmarking vs our 
non-vm setup...but if I get a change to do so soon I will.

Shain

On 12/15/2010 02:10 PM, Pablo Godel wrote:
> I tried this some months ago and it worked, but performance suffered,
> specially with PHP and APC enabled which tried to use shared memory.
>
> I guess  since you are not able to fully test, you don't know yet, I would
> like to know what is the performance you are experiencing.
>
> any others with comments regarding this?
>
> Thanks
> Pablo
>
>
> On Wed, Dec 15, 2010 at 1:55 PM, Alessandro Iurlano<
> alessandro.iurlano at gmail.com>  wrote:
>
>> Hello again.
>>
>> I just managed to install Proxmox on a new 64 bit machine. I then
>> removed the 32bit brick and peer from the gluster cluster and added
>> this new machine and rebalanced the volume.
>> Then I mounted the volume and started an OpenVZ container and I got
>> the same results (transport endpoint not connectd).
>> Tomorrow I will try recreating the volume from scratch on both the 64
>> bit machines.
>> Any other tests I might try?
>>
>> Thanks,
>> Alessandro
>>
>> On Tue, Dec 14, 2010 at 1:55 PM, Shain Miley<SMiley at npr.org>  wrote:
>>> I too had problems in a mixed/OpenVZ setup recently, but as  soon as I
>>> started using a 64-bit on all nodes the problems went away.  This was
>> using
>>> the 3.0.5 branch however.
>>>
>>> Shain
>>>
>>>
>>> -----Original Message-----
>>> From: gluster-users-bounces at gluster.org on behalf of Alessandro Iurlano
>>> Sent: Tue 12/14/2010 6:51 AM
>>> To: Amar Tumballi
>>> Cc: gluster-users at gluster.org
>>> Subject: Re: [Gluster-users] Problems with Glusterfs and OpenVz
>>>
>>> Hello again Amar.
>>>
>>> I have managed to try the latest commit from git://
>> git.gluster.com/glusterfs
>>> The problem happened again though this time it lasted much longer,
>>> allowing me to do an apt-get upgrade and some other minor things. But
>>> then the container stopped working and I get Transport endpoint is not
>>> connected.
>>>
>>> I am using a mixed environment for the tests. In particular, due to
>>> hardware shortage, the gluster and OpenVz server is a 64bit machine
>>> and the other gluster server is an old Pentium4 32bit only. Could this
>>> mixed 32/64 bit environment be related?
>>>
>>> Thanks for any help,
>>> Alessandro
>>>
>>> On Mon, Dec 13, 2010 at 3:48 PM, Alessandro Iurlano
>>> <alessandro.iurlano at gmail.com>  wrote:
>>>> Hello Amar.
>>>>
>>>> I have just tried version 3.1.2qa2 but the problem is still there.
>>>> Should I download the git version? If so, could you provide the git
>>>> url of the latest version?
>>>>
>>>> Thanks,
>>>> Alessandro
>>>>
>>>> On Mon, Dec 13, 2010 at 3:04 PM, Amar Tumballi<amar at gluster.com>
>> wrote:
>>>>> Hi Alessandro,
>>>>>
>>>>>>> This is an extract from an error log http://pastebin.com/66ipxbnA
>>>>> Thanks for the bug report. We found the reason for the crash reported,
>>>>> and
>>>>> fixes are already in repository. You can either wait for newer release,
>>>>> or
>>>>> checkout the latest repository code for the fix.
>>>>> Regards,
>>>>> Amar
>>>>>
>>>>> On Fri, Dec 10, 2010 at 4:38 PM, Alessandro Iurlano
>>>>> <alessandro.iurlano at gmail.com>  wrote:
>>>>>> Hello everybody
>>>>>>
>>>>>> I am evaluating Gluster as storage backend for our virtualization
>>>>>> infrastructure but I am having problems using Glusterfs with OpenVZ.
>>>>>> What I want to do is to store OpenVZ containers on Glusterfs
>>>>>> filesystem and not to mount Glusterfs volumes from inside OpenVZ
>>>>>> containers that appears to be what everyone does, according to Google
>>>>>> results.
>>>>>>
>>>>>> Basically I have setup an OpenVZ server (with Proxmox) and a
>>>>>> replicated Glusterfs volume from that server and another debian
>>>>>> machine.
>>>>>> I have been able to create an OpenVZ container on the Glusterfs
>>>>>> filesystem without problems with the latest Glusterfs version 3.1.2qa1
>>>>>> (due to the mknod bug
>>>>>> http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2145). But
>>>>>> whenever I start this new container it lasts only a couple of minutes
>>>>>> (just the time to boot and a couple commands) and then Glusterfs hangs
>>>>>> and I get the error Transport Endpoint is not connected.
>>>>>>
>>>>>> The Gluster volume is not accessible anymore from the OpenVz server
>>>>>> (even though this server is a gluster server itself), the container
>>>>>> completely stops working and killing glusterfs processes does not help
>>>>>> to recover the situation. The only way is to reboot the machine.
>>>>>>
>>>>>> This is an extract from an error log http://pastebin.com/66ipxbnA
>>>>>>
>>>>>> Any suggestions?
>>>>>> Does anybody have any successful experience with OpenVZ and Gluster or
>>>>>> know of any howto / documentation?
>>>>>>
>>>>>> Thanks in advance,
>>>>>> Alessandro
>>>>>> _______________________________________________
>>>>>> Gluster-users mailing list
>>>>>> Gluster-users at gluster.org
>>>>>> http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
>>>>>
>>> _______________________________________________
>>> Gluster-users mailing list
>>> Gluster-users at gluster.org
>>> http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
>>>
>>>
>>>
>> _______________________________________________
>> Gluster-users mailing list
>> Gluster-users at gluster.org
>> http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
>>
>
>
> _______________________________________________
> Gluster-users mailing list
> Gluster-users at gluster.org
> http://gluster.org/cgi-bin/mailman/listinfo/gluster-users



More information about the Gluster-users mailing list