[prev in list] [next in list] [prev in thread] [next in thread]
List: gluster-users
Subject: Re: [Gluster-users] [ovirt-users] slow performance with export storage on glusterfs
From: Jiří Sléžka <jiri.slezka () slu ! cz>
Date: 2017-11-29 9:08:21
Message-ID: 294d0d3c-59b2-0029-16c6-2881f4984b5b () slu ! cz
[Download RAW message or body]
[Attachment #2 (multipart/signed)]
Hello,
>
> If you use Gluster as FUSE mount it's always slower than you expect it
> to be.
> If you want to get better performance out of your oVirt/Gluster storage,
> try the following:
>
> - create a Linux VM in your oVirt environment, assign 4/8/12 virtual
> disks (Virtual disks are located on your Gluster storage volume).
> - Boot/configure the VM, then use LVM to create VG/LV with 4 stripes
> (lvcreate -i 4) and use all 4/8/12 virtual disks as PVS.
> - then install NFS server and export LV you created in previous step,
> use the NFS export as export domain in oVirt/RHEV.
>
> You should get wire speed when you use multiple stripes on Gluster
> storage, FUSE mount on oVirt host will fan out requests to all 4 servers.
> Gluster is very good at distributed/parallel workloads, but when you use
> direct Gluster FUSE mount for Export domain you only have one data
> stream, which is fragmented even more my multiple writes/reads that
> Gluster needs to do to save your data on all member servers.
Thanks for explanation, it is an interesting solution.
Cheers,
Jiri
>
>
>
> On Mon, Nov 27, 2017 at 8:41 PM, Donny Davis <donny@fortnebula.com
> <mailto:donny@fortnebula.com>> wrote:
>
> What about mounting over nfs instead of the fuse client. Or maybe
> libgfapi. Is that available for export domains
>
> On Fri, Nov 24, 2017 at 3:48 AM Jiří Sléžka <jiri.slezka@slu.cz
> <mailto:jiri.slezka@slu.cz>> wrote:
>
> On 11/24/2017 06:41 AM, Sahina Bose wrote:
> >
> >
> > On Thu, Nov 23, 2017 at 4:56 PM, Jiří Sléžka
> <jiri.slezka@slu.cz <mailto:jiri.slezka@slu.cz>
> > <mailto:jiri.slezka@slu.cz <mailto:jiri.slezka@slu.cz>>> wrote:
> >
> > Hi,
> >
> > On 11/22/2017 07:30 PM, Nir Soffer wrote:
> > > On Mon, Nov 20, 2017 at 5:22 PM Jiří Sléžka
> <jiri.slezka@slu.cz <mailto:jiri.slezka@slu.cz>
> <mailto:jiri.slezka@slu.cz <mailto:jiri.slezka@slu.cz>>
> > > <mailto:jiri.slezka@slu.cz <mailto:jiri.slezka@slu.cz>
> <mailto:jiri.slezka@slu.cz <mailto:jiri.slezka@slu.cz>>>> wrote:
> > >
> > > Hi,
> > >
> > > I am trying realize why is exporting of vm to export
> storage on
> > > glusterfs such slow.
> > >
> > > I am using oVirt and RHV, both instalations on
> version 4.1.7.
> > >
> > > Hosts have dedicated nics for rhevm network - 1gbps,
> data
> > storage itself
> > > is on FC.
> > >
> > > GlusterFS cluster lives separate on 4 dedicated
> hosts. It has
> > slow disks
> > > but I can achieve about 200-400mbit throughput in other
> > applications (we
> > > are using it for "cold" data, backups mostly).
> > >
> > > I am using this glusterfs cluster as backend for export
> > storage. When I
> > > am exporting vm I can see only about 60-80mbit
> throughput.
> > >
> > > What could be the bottleneck here?
> > >
> > > Could it be qemu-img utility?
> > >
> > > vdsm 97739 0.3 0.0 354212 29148 ? S<l
> 15:43 0:06
> > > /usr/bin/qemu-img convert -p -t none -T none -f raw
> > >
> >
> /rhev/data-center/2ff6d0ee-a10b-473d-b77c-be9149945f5f/ff3cd56a-1005-4426-8137-8f422 \
> c0b47c1/images/ba42cbcc-c068-4df8-af3d-00f2077b1e27/c57acd5f-d6cf-48cc-ad0c-4a7d979c0c1e
>
> > > -O raw
> > >
> >
> /rhev/data-center/mnt/glusterSD/10.20.30.41:_rhv__export/81094499-a392-4ea2-b081-7c6 \
> 288fbb636/images/ba42cbcc-c068-4df8-af3d-00f2077b1e27/c57acd5f-d6cf-48cc-ad0c-4a7d979c0c1e
>
> > >
> > > Any idea how to make it work faster or what
> throughput should I
> > > expected?
> > >
> > >
> > > gluster storage operations are using fuse mount - so
> every write:
> > > - travel to the kernel
> > > - travel back to the gluster fuse helper process
> > > - travel to all 3 replicas - replication is done on
> client side
> > > - return to kernel when all writes succeeded
> > > - return to caller
> > >
> > > So gluster will never set any speed record.
> > >
> > > Additionally, you are copying from raw lv on FC -
> qemu-img cannot do
> > > anything
> > > smart and avoid copying unused clusters. Instead if copies
> > gigabytes of
> > > zeros
> > > from FC.
> >
> > ok, it does make sense
> >
> > > However 7.5-10 MiB/s sounds too slow.
> > >
> > > I would try to test with dd - how much time it takes to copy
> > > the same image from FC to your gluster storage?
> > >
> > > dd
> > >
> if=/rhev/data-center/2ff6d0ee-a10b-473d-b77c-be9149945f5f/ff3cd56a-1005-4426-8137-8f \
> 422c0b47c1/images/ba42cbcc-c068-4df8-af3d-00f2077b1e27/c57acd5f-d6cf-48cc-ad0c-4a7d979c0c1e
>
> > >
> of=/rhev/data-center/mnt/glusterSD/10.20.30.41:_rhv__export/81094499-a392-4ea2-b081-7c6288fbb636/__test__
>
> > > bs=8M oflag=direct status=progress
> >
> > unfrotunately dd performs the same
> >
> > 1778384896 bytes (1.8 GB) copied, 198.565265 s, 9.0 MB/s
> >
> >
> > > If dd can do this faster, please ask on qemu-discuss
> mailing list:
> > > https://lists.nongnu.org/mailman/listinfo/qemu-discuss
> <https://lists.nongnu.org/mailman/listinfo/qemu-discuss>
> > <https://lists.nongnu.org/mailman/listinfo/qemu-discuss
> <https://lists.nongnu.org/mailman/listinfo/qemu-discuss>>
> > >
> > > If both give similar results, I think asking in gluster
> mailing list
> > > about this can help. Maybe your gluster setup can be
> optimized.
> >
> > ok, this is definitly on the gluster side. Thanks for your
> guidance.
> >
> > I will investigate the gluster side and also will try
> Export on NFS
> > share.
> >
> >
> > [Adding gluster users ml]
> >
> > Please provide "gluster volume info" output for the rhv_export
> gluster
> > volume and also volume profile details (refer to earlier mail
> from Shani
> > on how to run this) while performing the dd operation above.
>
> you can find all this output on https://pastebin.com/sBK01VS8
>
> as mentioned in other posts. Gluster cluster uses really slow
> (green)
> disks but without direct io it can achieve throughput around
> 400mbit/s.
>
> This storage is used mostly for backup purposes. It is not used
> as a vm
> storage.
>
> In my case it would be nice not to use direct io in export case
> but I
> understand why it might not be wise.
>
> Cheers,
>
> Jiri
>
> >
> >
> >
> >
> > Cheers,
> >
> > Jiri
> >
> >
> > >
> > > Nir
> > >
> > >
> > >
> > > Cheers,
> > >
> > > Jiri
> > >
> > >
> > > _______________________________________________
> > > Users mailing list
> > > Users@ovirt.org <mailto:Users@ovirt.org>
> <mailto:Users@ovirt.org <mailto:Users@ovirt.org>>
> > <mailto:Users@ovirt.org <mailto:Users@ovirt.org>
> <mailto:Users@ovirt.org <mailto:Users@ovirt.org>>>
> > > http://lists.ovirt.org/mailman/listinfo/users
> <http://lists.ovirt.org/mailman/listinfo/users>
> > <http://lists.ovirt.org/mailman/listinfo/users
> <http://lists.ovirt.org/mailman/listinfo/users>>
> > >
> >
> >
> >
> > _______________________________________________
> > Users mailing list
> > Users@ovirt.org <mailto:Users@ovirt.org>
> <mailto:Users@ovirt.org <mailto:Users@ovirt.org>>
> > http://lists.ovirt.org/mailman/listinfo/users
> <http://lists.ovirt.org/mailman/listinfo/users>
> > <http://lists.ovirt.org/mailman/listinfo/users
> <http://lists.ovirt.org/mailman/listinfo/users>>
> >
> >
>
>
> _______________________________________________
> Users mailing list
> Users@ovirt.org <mailto:Users@ovirt.org>
> http://lists.ovirt.org/mailman/listinfo/users
> <http://lists.ovirt.org/mailman/listinfo/users>
>
>
> _______________________________________________
> Gluster-users mailing list
> Gluster-users@gluster.org <mailto:Gluster-users@gluster.org>
> http://lists.gluster.org/mailman/listinfo/gluster-users
> <http://lists.gluster.org/mailman/listinfo/gluster-users>
>
>
["smime.p7s" (application/pkcs7-signature)]
_______________________________________________
Gluster-users mailing list
Gluster-users@gluster.org
http://lists.gluster.org/mailman/listinfo/gluster-users
[prev in list] [next in list] [prev in thread] [next in thread]
Configure |
About |
News |
Add a list |
Sponsored by KoreLogic