<br><br><div class="gmail_quote">2012/4/18 David-Sarah Hopwood <span dir="ltr"><<a href="mailto:david-sarah@jacaranda.org">david-sarah@jacaranda.org</a>></span><br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
<div class="HOEnZb"><div class="h5">On 17/04/12 13:36, huang jun wrote:<br>
> Hi,everyone<br>
> Tahoe using hash to balance the overload and data distribution cross the storage grid,we<br>
> have an idea:<br>
> Assume the storage grid seperate in two sites A and B, there are gateway nodes in both<br>
> sites, and we want to store 4 shares of a file<br>
> on A, and 6 shares on B.so that when we read the file, we can direct the http request to<br>
> a nearest gateway of our computer, take B as example,<br>
> then request the storage nodes in site B and get 3 of 6 shares, now we got the file.<br>
><br>
> so do we have any ways to achieve this?<br>
<br>
</div></div>You can easily have multiple gateways to the same grid. Also, clients will automatically<br>
choose the nodes that respond fastest to download from, which are likely to be nodes on<br>
the nearest site in the situation you describe.<br>
<br>
What is not currently supported for this use case is to guarantee an even distribution<br>
of shares between sites. Also, if you have a mobile computer there is no way to<br>
automatically get it to connect to the nearest gateway.<br>
<span class="HOEnZb"><font color="#888888"><br></font></span></blockquote><div> thanks,</div><div>so if we want to achieve this, just selects the propotional servers in site A and B may not work well if some nodes did not accept shares.</div>
<div>but to adjust the peer selection algorithm seems not a easy way.</div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><span class="HOEnZb"><font color="#888888">
--<br>
David-Sarah Hopwood ⚥<br>
<br>
</font></span></blockquote></div><br><br clear="all"><div><br></div>-- <br>huangjun<br>