[Gluster-devel] presentation slides used at devconf

[Sahina Bose]

On 02/11/2016 01:20 AM, Paul Cuzner wrote:
> Great presentation Prasanna.
>
> There are a couple of things that are difficult to make out solely 
> from the slides - could you shed some light on the following;
> - libgfapi vs fuse chart
>   - what was the I/O profile you were measuring
>   - for the georep results is this saying that with the i/o load 
> active, and georep active, this is the io latency as observed at the vm?
>   - for georep what was the change delta?

I/O profile used was the 80:20 random read:write fio workload. There 
were a total of 6 VMs running, 2 on each host, on a 3 node setup. 
(replica 3 gluster volume)

For the geo-rep results, yes - when geo-replication was active, this is 
the IO latency observed at the vm. The change delta is the ongoing data 
created by fio jobs (10g per VM)


>
> thanks,
>
> PC
>
>
> On Wed, Feb 10, 2016 at 9:42 AM, Prasanna Kumar Kalever 
> <pkalever at redhat.com <mailto:pkalever at redhat.com>> wrote:
>
>         On Wednesday, February 10, 2016 5:07:27 PM, Amye Scavarda wrote:
>
>         On Wed, Feb 10, 2016 at 12:28 PM, Samikshan Bairagya
>         <sbairagy at redhat.com <mailto:sbairagy at redhat.com>> wrote:
>
>
>
>             On 02/10/2016 04:40 PM, Michael Scherer wrote:
>
>                 Le mercredi 10 février 2016 à 12:11 +0530, Atin
>                 Mukherjee a écrit :
>
>                     It'd be better if you can send a PR to glusterdocs
>                     with the odp.
>
>
>                 *grmbl* top post *grmlb*
>
>                 I am not sure if that's a good idea to add all kind of
>                 binary files to
>                 the git repo. Since git will store it in the repo on
>                 clone, that might
>                 make it grow bigger with time, thus making it more and
>                 more annoying for
>                 people cloning the repo from zero with a bad internet
>                 connexion.
>
>             I think its a better option to have a document instead
>             that either contains a link to a page that contains all
>             the presentations, or a list of URLs for respective
>             presentations.
>
>
>             Regards,
>
>             Samikshan
>
>         Great!
>         That can be something we can add to gluster.org
>         <http://gluster.org> through a PR to the gluster.org
>         <http://gluster.org> github repo,  but that has nothing to do
>         with this current round of presentations being discussed.
>
>         Can we go back to the task at hand of helping to publicize
>         these beyond the mailing list? I'd love to be able to get
>         these out on the planet and the gluster.org
>         <http://gluster.org> blog.
>         Prasanna, would you be willing to do a post about this?
>          -amye
>
>     Amye, I am happy to make a post on this talk.
>     But please let me know what could be a better, meaning a video or
>     just a textual post (blog) explaining the presentation
>
>     Thanks,
>     -Prasanna
>
>                 _______________________________________________
>                 Gluster-devel mailing list
>                 Gluster-devel at gluster.org
>                 <mailto:Gluster-devel at gluster.org>
>                 http://www.gluster.org/mailman/listinfo/gluster-devel
>
>             _______________________________________________
>             Gluster-devel mailing list
>             Gluster-devel at gluster.org <mailto:Gluster-devel at gluster.org>
>             http://www.gluster.org/mailman/listinfo/gluster-devel
>
>
>
>
>         -- 
>         Amye Scavarda | amye at redhat.com <mailto:amye at redhat.com> |
>         Gluster Community Lead
>
>         _______________________________________________
>         Gluster-devel mailing list
>         Gluster-devel at gluster.org <mailto:Gluster-devel at gluster.org>
>         http://www.gluster.org/mailman/listinfo/gluster-devel
>
>
>
>     _______________________________________________
>     Gluster-devel mailing list
>     Gluster-devel at gluster.org <mailto:Gluster-devel at gluster.org>
>     http://www.gluster.org/mailman/listinfo/gluster-devel
>
>
>
>
> _______________________________________________
> Gluster-devel mailing list
> Gluster-devel at gluster.org
> http://www.gluster.org/mailman/listinfo/gluster-devel

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.gluster.org/pipermail/gluster-devel/attachments/20160211/c1e9535e/attachment.html>