[Gluster-users] GlusterFS optimizations translators

[Stas Oskin]

By the way, I noticed that some examples specify the translators both in
client and server vol files.

Is this required, or I can use only the client vol file (if I use
client-based AFR)?

Regards.

2009/3/17 Stas Oskin <stas.oskin at gmail.com>

> Hi.
>
> I had some performance issues with GlusterFS, and added the following two
> performance translators (which settings I found on some article dedicated to
> GlusterFS):
>
> volume writebehind
>   type performance/write-behind
>   option aggregate-size 128KB
>   option window-size 1MB
>   subvolumes unify
> end-volume
>
> volume cache
>   type performance/io-cache
>   option cache-size 512MB
>   subvolumes writebehind
> end-volume
>
> I got a major performance boost, would like to know, if its possible to
> increase the performance further?
> What other performance translators I can enable, while preserving maximum
> reliability?
>
> Also, should the settings in these 2 translators be tuned further?
>
> Thanks!
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://supercolony.gluster.org/pipermail/gluster-users/attachments/20090317/9d15384e/attachment.html>