Gluster users - Sep 2017 - how many hosts could be down in a 12x(4+2) distributed dispersed volume?

Dear All,

I just implemented a (6x(4+2)) DISTRIBUTED DISPERSED gluster (v.3.10) volume
based on the following hardware:

- 3 gluster servers (each server with 2 CPU 10 cores, 64GB RAM, 12 hard disk SAS
12Gb/s, 10GbE storage network)

Now, we need to add 3 new servers with the same hardware configuration
respecting the current volume topology.
If I'm right, we will obtain a DITRIBUTED DISPERSED gluster volume with 12
subvolumes, each volume will contain (4+2) bricks, that is a [12x(4+2)] volume.

My question is: in the current volume configuration, only 2 bricks per subvolume
or one host could be down without losing data. What it will happen in the next
configuration? How many hosts could be down without losing data?

Thank you very much.
Mauro Tridici

If you add bricks to existing volume one host could be down in each
three host group, If you recreate the volume with one brick on each
host, then two random hosts can be tolerated.
Assume s1,s2,s3 are current servers and you add s4,s5,s6 and extend
volume. If any two servers in each group goes down you loose data. If
you chose random two host the probability you loose data will be %20
in this case.
If you recreate volume with s1,s2,s3,s4,s5,s6 with one brick on each
host any random two servers can go down. If you chose random two host
the probability you loose data will be %0 in this case.

On Mon, Sep 18, 2017 at 10:39 PM, Mauro Tridici <mauro.tridici at cmcc.it>
wrote:
> Dear All,
>
> I just implemented a (6x(4+2)) DISTRIBUTED DISPERSED gluster (v.3.10)
volume based on the following hardware:
>
> - 3 gluster servers (each server with 2 CPU 10 cores, 64GB RAM, 12 hard
disk SAS 12Gb/s, 10GbE storage network)
>
> Now, we need to add 3 new servers with the same hardware configuration
respecting the current volume topology.
> If I'm right, we will obtain a DITRIBUTED DISPERSED gluster volume with
12 subvolumes, each volume will contain (4+2) bricks, that is a [12x(4+2)]
volume.
>
> My question is: in the current volume configuration, only 2 bricks per
subvolume or one host could be down without losing data. What it will happen in
the next configuration? How many hosts could be down without losing data?
>
> Thank you very much.
> Mauro Tridici
>
> _______________________________________________
> Gluster-users mailing list
> Gluster-users at gluster.org
> http://lists.gluster.org/mailman/listinfo/gluster-users

After adding 3 more nodes you will have 6 nodes and 2 HD on each nodes. 
It depends on the way you are going to add new bricks on the existing volume
'vol"
I think you should remember that in a given EC sub volume of 4+2, at any point
of time 2 bricks could be down.
When you make 6 * (4+2) to 12 * (4+2) you have to provide path of the bricks you
want to add.

Suppose you want to add 6 bricks and all the 6 bricks are on 3 new nodes (2
each) then with respect to that sub volume you can tolerate 1 node going down.
If you are creating a 12 * (4+2) volume from the scratch and providing 12 bricks
from each server then in that case even 2 nodes can go down without any issue.

I think You should focus more on the number of Hard Drive in a sub volume. You
should ask yourself "How many bricks (HD) with in a sub volume will be
unavailable if 1 or 2 nodes are going down?"

Ashish 




----- Original Message -----

From: "Mauro Tridici" <mauro.tridici at cmcc.it> 
To: gluster-users at gluster.org 
Sent: Tuesday, September 19, 2017 1:09:06 AM 
Subject: [Gluster-users] how many hosts could be down in a 12x(4+2) distributed
dispersed volume?

Dear All, 

I just implemented a (6x(4+2)) DISTRIBUTED DISPERSED gluster (v.3.10) volume
based on the following hardware:

- 3 gluster servers (each server with 2 CPU 10 cores, 64GB RAM, 12 hard disk SAS
12Gb/s, 10GbE storage network)

Now, we need to add 3 new servers with the same hardware configuration
respecting the current volume topology.


My question is: in the current volume configuration, only 2 bricks per subvolume
or one host could be down without losing data. What it will happen in the next
configuration? How many hosts could be down without losing data?

Thank you very much. 
Mauro Tridici 

_______________________________________________ 
Gluster-users mailing list 
Gluster-users at gluster.org 
http://lists.gluster.org/mailman/listinfo/gluster-users 

-------------- next part --------------
An HTML attachment was scrubbed...
URL:
<http://lists.gluster.org/pipermail/gluster-users/attachments/20170920/9a0c029a/attachment.html>

Hi Mauro Tridici,
>From the information provided it appears like you have placed 2 bricks of a
subvolume on one host. Please confirm.

The number of hosts that could go down without losing access to data can be
derived based on the brick configuration/distribution. Please let us know
the brick distribution plan.

Regards,

Sunil kumar Acharya

Senior Software Engineer

Red Hat

<https://www.redhat.com>

T: +91-8067935170 <http://redhatemailsignature-marketing.itos.redhat.com/>

<https://red.ht/sig>
TRIED. TESTED. TRUSTED. <https://redhat.com/trusted>


On Tue, Sep 19, 2017 at 1:09 AM, Mauro Tridici <mauro.tridici at cmcc.it>
wrote:
> Dear All,
>
> I just implemented a (6x(4+2)) DISTRIBUTED DISPERSED gluster (v.3.10)
> volume based on the following hardware:
>
> - 3 gluster servers (each server with 2 CPU 10 cores, 64GB RAM, 12 hard
> disk SAS 12Gb/s, 10GbE storage network)
>
> Now, we need to add 3 new servers with the same hardware configuration
> respecting the current volume topology.
> If I'm right, we will obtain a DITRIBUTED DISPERSED gluster volume with
12
> subvolumes, each volume will contain (4+2) bricks, that is a [12x(4+2)]
> volume.
>
> My question is: in the current volume configuration, only 2 bricks per
> subvolume or one host could be down without losing data. What it will
> happen in the next configuration? How many hosts could be down without
> losing data?
>
> Thank you very much.
> Mauro Tridici
>
> _______________________________________________
> Gluster-users mailing list
> Gluster-users at gluster.org
> http://lists.gluster.org/mailman/listinfo/gluster-users
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL:
<http://lists.gluster.org/pipermail/gluster-users/attachments/20170920/f8d287a9/attachment.html>

Dear Ashish,

thank you very much for the information and for the provided examples. They
really help.

I think that it may be useful to stick a label on each server in order to
identify the group they belong to.
For example:

server n.01 (label: Group 01)
server n.02 (label: Group 01)
server n.03 (label: Group 01)

server n.04 (label: Group 02)
server n.05 (label: Group 02)
server n.06 (label: Group 02)

So, if server n.01 and server n.06 go down I know that there will be no problem
for the data.
But, if server n.05 and n.06 go down, I can start to cry.

Thank you again,
Mauro Tridici
> Il giorno 20 set 2017, alle ore 09:33, Ashish Pandey <aspandey at
redhat.com> ha scritto:
> 
> 
> After adding 3 more nodes you will have 6 nodes and 2 HD on each nodes.
> It depends on the way you are going to add new bricks on the existing
volume 'vol"
> I think you should remember that in a given EC sub volume of 4+2, at any
point of time 2 bricks could be down.
> When you make 6 * (4+2) to 12 * (4+2) you have to provide path of the
bricks you want to add.
> 
> Suppose you want to add 6 bricks and all the 6 bricks are on 3 new nodes (2
each) then with respect to that sub volume  you can tolerate 1 node going down.
> If you are creating a 12 * (4+2) volume from the scratch and providing 12
bricks from each server then in that case even 2 nodes can go down without any
issue.
> 
> I think You should focus more on the number of Hard Drive in a sub volume.
You should ask yourself "How many bricks (HD) with in a  sub volume will be
unavailable if 1 or 2 nodes are going down?"
> 
> Ashish
> 
> 
> 
> 
> From: "Mauro Tridici" <mauro.tridici at cmcc.it>
> To: gluster-users at gluster.org
> Sent: Tuesday, September 19, 2017 1:09:06 AM
> Subject: [Gluster-users] how many hosts could be down in a 12x(4+2)       
distributed dispersed volume?
> 
> Dear All,
> 
> I just implemented a (6x(4+2)) DISTRIBUTED DISPERSED gluster (v.3.10)
volume based on the following hardware:
> 
> - 3 gluster servers (each server with 2 CPU 10 cores, 64GB RAM, 12 hard
disk SAS 12Gb/s, 10GbE storage network)
> 
> Now, we need to add 3 new servers with the same hardware configuration
respecting the current volume topology.
> 
> 
> My question is: in the current volume configuration, only 2 bricks per
subvolume or one host could be down without losing data. What it will happen in
the next configuration? How many hosts could be down without losing data?
> 
> Thank you very much.
> Mauro Tridici
> 
> _______________________________________________
> Gluster-users mailing list
> Gluster-users at gluster.org
> http://lists.gluster.org/mailman/listinfo/gluster-users
> 

-------------------------
Mauro Tridici

Fondazione CMCC
CMCC Supercomputing Center
presso Complesso Ecotekne - Universit? del Salento -
Strada Prov.le Lecce - Monteroni sn
73100 Lecce  IT
http://www.cmcc.it

mobile: (+39) 327 5630841
email: mauro.tridici at cmcc.it

-------------- next part --------------
An HTML attachment was scrubbed...
URL:
<http://lists.gluster.org/pipermail/gluster-users/attachments/20170920/363f8a1b/attachment.html>

Dear Serkan,

thank you very much for your support and explanation.
I really appreciated the information you provided.

Regards,
Mauro
> Il giorno 20 set 2017, alle ore 08:26, Serkan ?oban <cobanserkan at
gmail.com> ha scritto:
> 
> If you add bricks to existing volume one host could be down in each
> three host group, If you recreate the volume with one brick on each
> host, then two random hosts can be tolerated.
> Assume s1,s2,s3 are current servers and you add s4,s5,s6 and extend
> volume. If any two servers in each group goes down you loose data. If
> you chose random two host the probability you loose data will be %20
> in this case.
> If you recreate volume with s1,s2,s3,s4,s5,s6 with one brick on each
> host any random two servers can go down. If you chose random two host
> the probability you loose data will be %0 in this case.
> 
> On Mon, Sep 18, 2017 at 10:39 PM, Mauro Tridici <mauro.tridici at
cmcc.it> wrote:
>> Dear All,
>> 
>> I just implemented a (6x(4+2)) DISTRIBUTED DISPERSED gluster (v.3.10)
volume based on the following hardware:
>> 
>> - 3 gluster servers (each server with 2 CPU 10 cores, 64GB RAM, 12 hard
disk SAS 12Gb/s, 10GbE storage network)
>> 
>> Now, we need to add 3 new servers with the same hardware configuration
respecting the current volume topology.
>> If I'm right, we will obtain a DITRIBUTED DISPERSED gluster volume
with 12 subvolumes, each volume will contain (4+2) bricks, that is a [12x(4+2)]
volume.
>> 
>> My question is: in the current volume configuration, only 2 bricks per
subvolume or one host could be down without losing data. What it will happen in
the next configuration? How many hosts could be down without losing data?
>> 
>> Thank you very much.
>> Mauro Tridici
>> 
>> _______________________________________________
>> Gluster-users mailing list
>> Gluster-users at gluster.org
>> http://lists.gluster.org/mailman/listinfo/gluster-users

Dear Sunil Kumar Acharya,

yes, I can confirm that I placed 2 bricks per subvolume per host.

Thank you very much for your support.
Regards,
Mauro tridici


> Il giorno 20 set 2017, alle ore 09:34, Sunil Kumar Heggodu Gopala Acharya
<sheggodu at redhat.com> ha scritto:
> 
> Hi Mauro Tridici,
> 
> From the information provided it appears like you have placed 2 bricks of a
subvolume on one host. Please confirm.
> 
> The number of hosts that could go down without losing access to data can be
derived based on the brick configuration/distribution. Please let us know the
brick distribution plan.
> 
> Regards,
> SUNIL KUMAR ACHARYA
> SENIOR SOFTWARE ENGINEER
> Red Hat 
> 
>  <https://www.redhat.com/>
> T: +91-8067935170
<http://redhatemailsignature-marketing.itos.redhat.com/>
> 
>   <https://red.ht/sig>
> TRIED. TESTED. TRUSTED. <https://redhat.com/trusted>
> 
> On Tue, Sep 19, 2017 at 1:09 AM, Mauro Tridici <mauro.tridici at cmcc.it
<mailto:mauro.tridici at cmcc.it>> wrote:
> Dear All,
> 
> I just implemented a (6x(4+2)) DISTRIBUTED DISPERSED gluster (v.3.10)
volume based on the following hardware:
> 
> - 3 gluster servers (each server with 2 CPU 10 cores, 64GB RAM, 12 hard
disk SAS 12Gb/s, 10GbE storage network)
> 
> Now, we need to add 3 new servers with the same hardware configuration
respecting the current volume topology.
> If I'm right, we will obtain a DITRIBUTED DISPERSED gluster volume with
12 subvolumes, each volume will contain (4+2) bricks, that is a [12x(4+2)]
volume.
> 
> My question is: in the current volume configuration, only 2 bricks per
subvolume or one host could be down without losing data. What it will happen in
the next configuration? How many hosts could be down without losing data?
> 
> Thank you very much.
> Mauro Tridici
> 
> _______________________________________________
> Gluster-users mailing list
> Gluster-users at gluster.org <mailto:Gluster-users at gluster.org>
> http://lists.gluster.org/mailman/listinfo/gluster-users
<http://lists.gluster.org/mailman/listinfo/gluster-users>
> 

-------------- next part --------------
An HTML attachment was scrubbed...
URL:
<http://lists.gluster.org/pipermail/gluster-users/attachments/20170920/801fc16c/attachment.html>