<br><br><div class="gmail_quote">2009/7/31 Raghavendra G <span dir="ltr"><<a href="mailto:raghavendra@gluster.com">raghavendra@gluster.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;">
<div><div></div><div class="h5">2009/7/31 Yi Ling <<a href="http://lingyi.pro" target="_blank">lingyi.pro</a>@<a href="http://gmail.com" target="_blank">gmail.com</a>>:<br>
><br>
><br>
> 2009/7/31 Harald Stürzebecher <<a href="mailto:haralds@cs.tu-berlin.de">haralds@cs.tu-berlin.de</a>><br>
>><br>
>> Hello!<br>
>><br>
>> 2009/7/31 Yi Ling <<a href="http://lingyi.pro" target="_blank">lingyi.pro</a>@<a href="http://gmail.com" target="_blank">gmail.com</a>>:<br>
>> > there is a section about metadata on page<br>
>> > <a href="http://www.gluster.com/news.php" target="_blank">http://www.gluster.com/news.php</a><br>
>> ><br>
>> > "No metadata dependencies - metadata management is frequently a source<br>
>> > of<br>
>> > performance bottlenecks, particularly when there are a very large number<br>
>> > of<br>
>> > files, and can be a single point of failure in traditional file systems.<br>
>> > GlusterFS eliminates this problem with intelligent data placement, an<br>
>> > automatic data distribution method that optimizes the use of resources<br>
>> > and<br>
>> > eliminates metadata bottlenecks."<br>
>> ><br>
>> > yes,it's a advantage of GlusterFS. but yet i found no more detailed<br>
>> > information about the "intelligent data placement" "an automatic data<br>
>> > distribution methed". could anyone explain it in detail? and something<br>
>> > about<br>
>> > file managemment~~~<br>
>><br>
>> AFAIK, the GlusterFS metadata is stored as extended attributes to the<br>
>> files in the underlying filesystem.<br>
>><br>
>> Hints can be found here:<br>
>><br>
>><br>
>> <a href="http://www.gluster.org/docs/index.php/Understanding_AFR_Translator#Locking_and_Change_Log" target="_blank">http://www.gluster.org/docs/index.php/Understanding_AFR_Translator#Locking_and_Change_Log</a><br>
>><br>
>><br>
>> <a href="http://www.gluster.org/docs/index.php/Setting_up_AFR_on_two_servers_with_pre-existing_data#Preparing_the_directories" target="_blank">http://www.gluster.org/docs/index.php/Setting_up_AFR_on_two_servers_with_pre-existing_data#Preparing_the_directories</a><br>
>><br>
>><br>
>> Harald Stürzebecher<br>
><br>
> thanks for replying~~ but im still confused~~~<br>
><br>
> in client, what's the routine of an operation like "create"/"read" ,from<br>
> client to server (even backend filesystem)?<br>
><br>
> "the GlusterFS metadata is stored as extended attributes to the files in the<br>
> underlying filesystem"<br>
> well, after storing, how could i read the file and how to know where the<br>
> file is located (or which server/brick the file is stored)<br>
<br>
</div></div>Distribute Translator provides the functionality of aggregating the<br>
storage from individual nodes and giving the unified view of the total<br>
storage. It stores the layout (which says, which file goes into which<br>
node) of the directory in extended attributes of the directory. And<br>
directories are created on all the nodes. Files are created on only<br>
one of the nodes.<br>
<br>
><br>
><br>
> _______________________________________________<br>
> Gluster-devel mailing list<br>
> <a href="mailto:Gluster-devel@nongnu.org">Gluster-devel@nongnu.org</a><br>
> <a href="http://lists.nongnu.org/mailman/listinfo/gluster-devel" target="_blank">http://lists.nongnu.org/mailman/listinfo/gluster-devel</a><br>
>y<br>
><br>
<br>
<br>
regards,<br>
--<br>
<font color="#888888">Raghavendra G<br>
</font></blockquote></div><br>yes, HDT translator depends on its name hash, and unify translator has separate namespace volume which is shared by all clients. as i know, "currently each translator has its own mechanism to maintain global namespace." but except from hdt and unify, how do the other tanslators implement the same operation (create, read,readdir ...) ... afr,map,ha,stripe etc.<br>
<br>now i have no common concept about the mechanism, so im so confused to understand the routine of different translator. thanks for your patience very much ~~~<br>