cluster/ha solves this problem as of now.. it is build to provide High Availability between two servers/interfaces etc.<br><br><a href="http://gluster.org/docs/index.php/AFR_single_process">http://gluster.org/docs/index.php/AFR_single_process</a> is the setup I am referring, where machine{1,2,} are servers, and all others are clients.<br>
<br>Regards,<br>Amar<br><br><div class="gmail_quote">2008/12/19 Keith Freedman <span dir="ltr"><<a href="mailto:freedman@freeformit.com">freedman@freeformit.com</a>></span><br><blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
thanks, looks good.<br>
<br>
I have one thought, that might be worthy of discussion:<br>
<br>
Personally I prefer server side AFR, because I don't want a<br>
mis-configured client to cause problems with replication.<br>
However, it seems the current only way to get high-availability to<br>
the client is for the client to run AFR so that if one server fails<br>
you still have access.<br>
<br>
so, having afr onthe servers AND the clients seems like it might just<br>
add weird overhead? would it even work well at all?<br>
<br>
and so I'm thinking, server side AFR is better and so there might be<br>
nice to have a multi-server translator or something where you can<br>
specify multiple servers and an access policy (like with unify-- rr,<br>
lru, etc.) to address the availability issue.??<br>
<div class="Ih2E3d"><br>
<br>
<br>
<br>
At 10:47 PM 12/17/2008, you wrote:<br>
>2008/12/18 Keith Freedman <<a href="mailto:freedman@freeformit.com">freedman@freeformit.com</a>>:<br>
> > I've unpacked the rc4 distribution from<br>
> > <a href="http://ftp.gluster.com/pub/gluster/glusterfs/1.4/" target="_blank">http://ftp.gluster.com/pub/gluster/glusterfs/1.4/</a> , there is no afr.pdf in<br>
> > the doc folder<br>
><br>
>Thanks for spotting. I had forgot to include it in the distribution<br>
>tarball. I've made the necessary changes and it will go out with<br>
>future releases. Until then please get it from either the repository<br>
>or<br>
><br>
><a href="http://gnu.zresearch.com/%7Evikas/afr.pdf" target="_blank">http://gnu.zresearch.com/~vikas/afr.pdf</a><br>
><br>
>Vikas<br>
>--<br>
>Engineer - Z Research<br>
><a href="http://gluster.com/" target="_blank">http://gluster.com/</a><br>
<br>
<br>
_______________________________________________<br>
</div><div><div></div><div class="Wj3C7c">Gluster-users mailing list<br>
<a href="mailto:Gluster-users@gluster.org">Gluster-users@gluster.org</a><br>
<a href="http://zresearch.com/cgi-bin/mailman/listinfo/gluster-users" target="_blank">http://zresearch.com/cgi-bin/mailman/listinfo/gluster-users</a><br>
<br>
</div></div></blockquote></div><br><br clear="all"><br>-- <br>Amar Tumballi<br>Gluster/GlusterFS Hacker<br>[bulde on #gluster/<a href="http://irc.gnu.org">irc.gnu.org</a>]<br><a href="http://www.zresearch.com">http://www.zresearch.com</a> - Commoditizing Super Storage!<br>