Re: Create more would increse performance?

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



I mean this one:
https://github.com/gluster/glusterfs-specs/blob/master/done/GlusterFS%203.5/libgfapi%20with%20qemu%20libvirt.md

libgfapi is a programatic way for qemu to access the volume without the FUSE.
As far as I know , one drawback is that you can't dynamically migrate your VMs from one storage to another.

For oVirt, enabling of libgfapi is a little bit different, as it's activated on Engine's level.

Best Regards,
Strahil Nikolov

On Sun, Mar 6, 2022 at 0:49, Gilberto Ferreira
<gilberto.nunes32@xxxxxxxxx> wrote:
That's nice to hear.

Regarding libgfapi you mean this:

# gluster volume set VOL_NAME server.allow-insecure on

Can you point some docs about create a gluster subvols?

Thanks 

Em sáb, 5 de mar de 2022 19:37, Strahil Nikolov <hunter86_bg@xxxxxxxxx> escreveu:
Sharding is created for virtualization and it  provides better performance in a distributed- replicated volumes, as each shard is "placed" ontop of DHT.
This way when the VM reads a large file (which spans over several shards), each shard can be read from a different brick -> speeding up the read.

Also, you can explore libgfapi which , despite it's drawbacks , brings a lot of performance (at least based on several reports in the oVirt list).

Overall, more subvolumes (replica sets) will bring better performance (most probably you will feel it in the reads) and with libgfapi the performance can go better.

Best Regards,
Strahil Nikolov

On Sun, Mar 6, 2022 at 0:23, Gilberto Ferreira
Hi

I'm working with kvm/qemu virtualization here.
I already activated virt group.
However I am considering make some changes.
Mostly it's work with really big files.


Em sáb, 5 de mar de 2022 18:21, Strahil Nikolov <hunter86_bg@xxxxxxxxx> escreveu:
It depends. What kind of workload do you have ?

Best Regards,
Strahil Nikolov

On Sat, Mar 5, 2022 at 17:22, Gilberto Ferreira
Hi there.
Usually I create one gluster volume and one brick, /mnt/data. If create more than on brick, like server1:/data1 server1:/data2 n.... would this increate overall performance??
Thanks
---
Gilberto Nunes Ferreira




________



Community Meeting Calendar:

Schedule -
Every 2nd and 4th Tuesday at 14:30 IST / 09:00 UTC
Bridge: https://meet.google.com/cpu-eiue-hvk
Gluster-users mailing list
Gluster-users@xxxxxxxxxxx
https://lists.gluster.org/mailman/listinfo/gluster-users
________



Community Meeting Calendar:

Schedule -
Every 2nd and 4th Tuesday at 14:30 IST / 09:00 UTC
Bridge: https://meet.google.com/cpu-eiue-hvk
Gluster-users mailing list
Gluster-users@xxxxxxxxxxx
https://lists.gluster.org/mailman/listinfo/gluster-users

[Index of Archives]     [Gluster Development]     [Linux Filesytems Development]     [Linux ARM Kernel]     [Linux ARM]     [Linux Omap]     [Fedora ARM]     [IETF Annouce]     [Bugtraq]     [Linux OMAP]     [Linux MIPS]     [eCos]     [Asterisk Internet PBX]     [Linux API]

  Powered by Linux