<html><head><style type="text/css"><!-- DIV {margin:0px;} --></style></head><body><div style="font-family:times new roman,new york,times,serif;font-size:12pt"><div style="font-family: times new roman,new york,times,serif; font-size: 12pt;">Thanks for the reply.<br><br>While setting up RAID 0 would be a option, there must be more elegant solutions out there. Just because one disk out of the whole array dies breaking the whole array and drastically changing the size of the sheepdog cluster. <br>One problem I do see with starting many sheep daemons on the same server that has many disks is that (especially on small clusters) it is possible for all data for one or many Virtual Machine to be stored on one physical server. <br><br>Would it be possible to do say<br>sheep /store_disk0 /store_disk1 /store_disk2 /store_disk3 /store_disk4 /store_disk5 /store_disk6<br>So all mount points on a server would be handled by the same sheep using
multiple threads<br><br>Add a mount point <br>sheep -a /store_disk7<br><br>Remove a mount point<br>sheep -r /store_disk7<br><br>Hope that all makes sense, looking froward to seeing sheepdog grow and mature. <br><div style="font-family: arial,helvetica,sans-serif; font-size: 13px;"><font size="2" face="Tahoma"><hr size="1"><b><span style="font-weight: bold;">From:</span></b> MORITA Kazutaka <morita.kazutaka@lab.ntt.co.jp><br><b><span style="font-weight: bold;">To:</span></b> Ski Mountain <ski_the_mountain@yahoo.com><br><b><span style="font-weight: bold;">Cc:</span></b> sheepdog@lists.wpkg.org<br><b><span style="font-weight: bold;">Sent:</span></b> Thu, March 17, 2011 12:56:16 AM<br><b><span style="font-weight: bold;">Subject:</span></b> Re: [Sheepdog] sheepdog and RAID<br></font><br>
At Tue, 15 Mar 2011 20:42:46 -0700 (PDT),<br>Ski Mountain wrote:<br>> Sorry about prematurely sending the previous message by mistake.<br>> I have a question about setting up sheep dog. Since sheepdog takes care of data <br>> replication and node addition and subtraction. What do you do when you have <br>> multiple disks in a machine in the cluster. I assume you want to raid one the <br>> OS, but what is best practices for the directory that stores the objects. Is is <br>> best to start the sheep deamon on each mount point, or do you need to RAID the <br>> multiple disks. I figured that RAIDing the sheepdog disks would waste space <br>> making multiple copies would be a waste since sheepdog is RAIDing the data. So <br>> would be best for sheepdog to take care of the data distribution and replication <br>> or what is the best method. <br>> <br>> $ collie cluster format
--copies=3<br>> <br>> Method stated in documentation<br>> $ sheep /store_dir<br>> <br>> Or on each disk<br>> $ sheep /store_disk0<br>> $ sheep /store_disk1<br>> $ sheep /store_disk2<br>> $ sheep /store_disk3<br>> $ sheep /store_disk4<br>> $ sheep /store_disk5<br>> $ sheep /store_disk6<br>> <br><br>I think using RAID 0 (no redundancy) is the easiest way.<br><br>Of course you can start a sheep daemon for each disk. In that case,<br>please specify the different port number. For example:<br><br> $ sheep /store_disk0 -p 7000<br> $ sheep /store_disk1 -p 7001<br> $ sheep /store_disk2 -p 7002<br> $ sheep /store_disk3 -p 7003<br> $ sheep /store_disk4 -p 7004<br> $ sheep /store_disk5 -p 7005<br> $ sheep /store_disk6 -p 7006<br><br><br>Thanks,<br><br>Kazutaka<br></div></div>
</div><br>
</body></html>