8 a.m.
--_000_D1921574DA47soerenmalchowmconnet_
Content-Type: text/plain; charset="windows-1251"
Content-Transfer-Encoding: quoted-printable
Hi
You can have 150MB/s for a while, but evetually the replication has to catc=
h up and you will have more and more blocks out of sync.
If you really need that much speed you need to go for 10GBit links
There are some switches e.g .the ones compatible with Open Network Linux th=
at are relativley cheap when it comes to 10Gbit ( http://opennetlinux.org/h=
cl )
Cheers
Soeren
From: =DE=F0=E8=E9 =CF=EE=EB=F2=EE=F0=E0=F6=EA=E8=E9 <y.poltoratskiy(a)gmail.=
com<mailto:y.poltoratskiy@gmail.com> Date:
Monday 1 June 2015 08:56
To: Soeren Malchow <soeren.malchow@mcon.net<mailto:soeren.malchow@mcon.net>=
Cc: "users@ovirt.org<mailto:users@ovirt.org>"
<users@ovirt.org<mailto:users=
@ovirt.org> Subject: Re: [ovirt-users] gluster
config in 4 node cluster
2015-06-01 2:32 GMT+03:00 Soeren Malchow <soeren.malchow@mcon.net<mailto:so=
eren.malchow(a)mcon.net>>:
Hi
For a production environment i would not build a 2 node gluster, i would bu=
ild at least 3 nodes to have it much easier with the quorum.
Taking into account that you can use commodity hardware i would also sugges=
t to split the services, but i would go for at least 3 gluster nodes =96 wh=
ich add up to at least 5 nodes for a HA system.
If you want 4 in any case, then my suggestion would be to go for 4 replicas=
, each node has anything that it needs to run and you can basically use NFS=
to localhost for the storage which would make the nodes always access the =
local storage for the VMS, availability wise it makes no difference.
I have data center with one cluster based on 3 nodes with both services: vi=
rt and gluster, and GlusterFS as a data domain. Every node has a single HDD=
as a brick (replica 3) and 2x1G nics with bonding on top (src-dst-ip). I h=
ave 2 vlans: 1 - management, 2 - VMs.
If in a VM I run something like 'dd if=3D/dev/zero of=3D/tmp/tmp' I have ar=
ound 80+ MB/s write speed, at this moment on SPM node i run 'iftop -i bond0=
.1' and can see two flows with around 900 Mb/s each of them to the second a=
nd to the third nodes (thanks to the bonding that every flow can be done th=
rough separate nic). All of this is expected result and in this case we rea=
ch a limit of bandwidth our nics. And even if HDD of a node has 150+ MB/s l=
inear write speed I can not reach such speed of write in VMs.
What result would I get with 4 nodes and gluster replica 4? I expect that w=
rite speed in VM will be much slower, because now SPM node will generate th=
ree flows, and two of them will go through one nic and we will have only 50=
0Mb/s per flow and in this way the write speed of VM will be twice lower.
Am I wrong?
Cheers
Soeren
From: =DE=F0=E8=E9 =CF=EE=EB=F2=EE=F0=E0=F6=EA=E8=E9 <y.poltoratskiy(a)gmail.=
com<mailto:y.poltoratskiy@gmail.com> Date:
Sunday 31 May 2015 18:32
To: "users@ovirt.org<mailto:users@ovirt.org>"
<users@ovirt.org<mailto:users=
@ovirt.org> Subject: Re: [ovirt-users] gluster
config in 4 node cluster
Hi,
As for me, I would build one cluster with gluster service only based on two=
nodes (replica 2), and the other one with virt service only based on other=
two nodes. I think this variant is more scalable in future.
PS. I am a new in oVirt, so do not except that I am wrong.
28.05.2015 23:11, paf1@email.cz<mailto:paf1@email.cz> =EF=E8=F8=E5=F2:
Hello,
How to optimal configure 4 node cluster for any one node goes to maintena=
nce without stopping VM ??
a) replica 4 - but it takes a lot of space
b) disperse 3+1 ( raid 5 ) - but bad performance and not visible by oVirt 3=
.7.2
c) stripe2+replica2 =3D but VM paused
any other idea ?
regs.
Pa.
_______________________________________________
Users mailing list
Users@ovirt.org<mailto:Users@ovirt.org>http://lists.ovirt.org/mailman/listi=
nfo/users
--_000_D1921574DA47soerenmalchowmconnet_
Content-Type: text/html; charset="windows-1251"
Content-ID: <506E2D25886427489658B38CE569CCCB(a)liquidcampaign.com Content-Transfer-Encoding: quoted-printable
<html <head <meta http-equiv=3D"Content-Type"
content=3D"text/html; charset=3Dwindows-1=
251" </head <body style=3D"word-wrap: break-word;
-webkit-nbsp-mode: space; -webkit-lin=
e-break: after-white-space; color: rgb(0, 0, 0); font-size: 14px; font-fami=
ly: Calibri, sans-serif;" <div>Hi</div <div><br
</div <div>You can have 150MB/s for
a while, but evetually the replication has to=
catch up and you will have more and more blocks out of sync.</div <div><br
</div <div>If you really need that
much speed you need to go for 10GBit links</di=
v <div><br
</div <div>There are some switches
e.g .the ones compatible with Open Network Lin=
ux that are relativley cheap when it comes to 10Gbit ( <a href=3D"http=
://opennetlinux.org/hcl">http://opennetlinux.org/hcl</a> )</div <div><br
</div <div>Cheers</div <div>Soeren </div <div><br
</div <span
id=3D"OLK_SRC_BODY_SECTION" <div
style=3D"font-family:Calibri; font-size:11pt; text-align:left; color:b=
lack; BORDER-BOTTOM: medium none; BORDER-LEFT: medium none; PADDING-BOTTOM:=
0in; PADDING-LEFT: 0in; PADDING-RIGHT: 0in; BORDER-TOP: #b5c4df 1pt solid;=
BORDER-RIGHT: medium none; PADDING-TOP: 3pt" <span
style=3D"font-weight:bold">From: </span>=DE=F0=E8=E9 =CF=EE=EB=F2=EE=
=F0=E0=F6=EA=E8=E9 <<a
href=3D"mailto:y.poltoratskiy@gmail.com">y.poltor=
atskiy(a)gmail.com</a>&gt;<br <span
style=3D"font-weight:bold">Date: </span>Monday 1 June 2015
08:56<br <span
style=3D"font-weight:bold">To: </span>Soeren Malchow <<a
href=3D"m=
ailto:soeren.malchow@mcon.net">soeren.malchow@mcon.net</a>><br <span style=3D"font-weight:bold">Cc:
</span>"<a href=3D"mailto:users@o=
virt.org">users(a)ovirt.org</a>&quot; <<a
href=3D"mailto:users@ovirt.org">=
users(a)ovirt.org</a>&gt;<br <span
style=3D"font-weight:bold">Subject: </span>Re: [ovirt-users] gluster =
config in 4 node cluster<br </div <div><br
</div <div
<div <div dir=3D"ltr" <div class=3D"gmail_extra"><br <div class=3D"gmail_quote">2015-06-01 2:32
GMT+03:00 Soeren Malchow <sp=
an dir=3D"ltr" <<a
href=3D"mailto:soeren.malchow@mcon.net"
target=3D"_blank">soeren.mal=
chow@mcon.net</a>></span>:<br
<blockquote class=3D"gmail_quote" style=3D"margin:0px 0px 0px
0.8ex;border-=
left:1px solid rgb(204,204,204);padding-left:1ex" <div
style=3D"word-wrap:break-word;color:rgb(0,0,0);font-size:14px;font-fam=
ily:Calibri,sans-serif" <div>Hi</div <div><br
</div <div>For a production
environment i would not build a 2 node gluster, i wou=
ld build at least 3 nodes to have it much easier with the quorum.</div <div><br
</div <div>Taking into account that
you can use commodity hardware i would also s=
uggest to split the services, but i would go for at least 3 gluster nodes =
=96 which add up to at least 5 nodes for a HA system.</div
<div><br </div <div>If you want 4 in any case, then my suggestion would
be to go for 4 rep=
licas, each node has anything that it needs to run and you can basically us=
e NFS to localhost for the storage which would make the nodes always access=
the local storage for the VMS,
availability wise it makes no difference.</div
</div </blockquote <div><br
</div <div>I have data center with
one cluster based on 3 nodes with both service=
s: virt and gluster, and GlusterFS as a data domain. Every node has a singl=
e HDD as a brick (replica 3) and 2x1G nics with bonding on top (src-dst-ip)=
. I have 2 vlans: 1 - management,
2 - VMs.<br <br
</div <div>If in a VM I run
something like 'dd if=3D/dev/zero of=3D/tmp/tmp' I ha=
ve around 80+ MB/s write speed, at this moment on SPM node i run 'iftop=
-i bond0.1' and can see two flows with around 900 Mb/s each of them to the=
second and to the third nodes (thanks to
the bonding that every flow can be done through separate nic). All of this=
is expected result and in this case we reach a
<span id=3D"result_box" class=3D""
lang=3D"en"><span class=3D"">limit</span=
> of <span class=3D""
bandwidth</span></span> our nics. And even if HDD of a node has
150+ MB=
/s linear write speed I can not reach such speed of write in VMs.<br <br </div <div>What result would I get with 4 nodes and gluster
replica 4? I expect t=
hat write speed in VM will be much slower, because now SPM node will genera=
te three flows, and two of them will go through one nic and we will have on=
ly 500Mb/s per flow and in this
way the write speed of VM will be twice lower. <br
<br </div <div>Am I wrong?<br
</div <div><br </div
<blockquote class=3D"gmail_quote" style=3D"margin:0px 0px 0px
0.8ex;border-=
left:1px solid rgb(204,204,204);padding-left:1ex" <div
style=3D"word-wrap:break-word;color:rgb(0,0,0);font-size:14px;font-fam=
ily:Calibri,sans-serif" <div><br </div
<div>Cheers</div
<div>Soeren </div
<div><br </div <span <div
style=3D"font-family:Calibri;font-size:11pt;text-align:left;color:blac=
k;border-width:1pt medium medium;border-style:solid none none;border-color:=
rgb(181,196,223) -moz-use-text-color -moz-use-text-color;padding:3pt 0in 0i=
n" <span style=3D"font-weight:bold">From:
</span>=DE=F0=E8=E9 =CF=EE=EB=F2=EE=
=F0=E0=F6=EA=E8=E9 <<a href=3D"mailto:y.poltoratskiy@gmail.com"
target=
=3D"_blank">y.poltoratskiy(a)gmail.com</a>&gt;<br <span style=3D"font-weight:bold">Date:
</span>Sunday 31 May 2015 18:32<br <span
style=3D"font-weight:bold">To: </span>"<a
href=3D"mailto:users@o=
virt.org" target=3D"_blank">users(a)ovirt.org</a>&quot;
<<a href=3D"mailto=
:users@ovirt.org"
target=3D"_blank">users(a)ovirt.org</a>&gt;<br <span style=3D"font-weight:bold">Subject:
</span>Re: [ovirt-users] gluster =
config in 4 node cluster<br </div <div <div class=3D"h5" <div><br
</div <div <div
text=3D"#000000" bgcolor=3D"#FFFFFF"><br Hi,<br
<br As for me, I would build one cluster
with gluster service only based on two=
nodes (replica 2), and the other one with virt service only based on other=
two nodes. I think this variant is more scalable in future.
<br <br PS. I am a new in oVirt, so do not
except that I am wrong.<br <br
<br <div>28.05.2015 23:11, <a
href=3D"mailto:paf1@email.cz" target=3D"_blank">p=
af1(a)email.cz</a> =EF=E8=F8=E5=F2:<br
</div <blockquote
type=3D"cite">Hello,<br How to
optimal configure 4 node cluster for any one node goes to =
; maintenance without stopping VM ??<br
<br a) replica 4 - but it
takes a lot of space<br b) disperse 3+1 ( raid 5 ) -
but bad performance and not visible by oVi=
rt 3.7.2<br c) stripe2+replica2 =3D but
VM paused <br <br any other
idea ?<br regs.<br Pa.<br
<br <fieldset></fieldset>
<br <pre>_______________________________________________
Users mailing list
<a href=3D"mailto:Users@ovirt.org"
target=3D"_blank">Users(a)ovirt.org</a><a =
href=3D"http://lists.ovirt.org/mailman/listinfo/users"
target=3D"_blank">ht=
tp://lists.ovirt.org/mailman/listinfo/users</a></pre
</blockquote <br
</div </div </div
</div </span></div </blockquote
</div <br
</div </div </div
</div </span </body
</html
--_000_D1921574DA47soerenmalchowmconnet_--