Hi Zhongliang,
you can find a lot of command on ceph official document!
于 2014/4/10 0:57, Zhongliang Zhao 写道:
Hi XIanxia,
Thanks a lot for the reply.
Since I am new to ceph, some parts of your reply is unclear to me. Is
it possible for you to make it more clear? Thanks a lot for your time.
On 02/28/2014 02:41 AM, Xianxia Xiao wrote:
May be able to meet your needs through rbd.
You can create multiple rules,and then specify a different pool to
use a different ruleset.
Where can I modify or creat the rule? On the monitor node? and how to
configure a pool to use a ruleset?
you can use crushtool export crush map,then modify the rule in crush map
,you can create new rules.
http://ceph.com/docs/master/rados/operations/crush-map/?highlight=crush%20map
you can use #ceph osd pool set {pool name} {key} {value}
the key is crush_ruleset,value is the rule num.
Then create multiple block images, and Specify image to different pools.
How this can be done?
you can see that in Block Device Command in ceph document.
http://ceph.com/docs/master/rbd/rados-rbd-cmds/
create file system on the block device and mount file system on
different positions,so that the different location of the file can
use different ruleset.
How do I know to where I should mount the file system?
You decide,mount command is the same to linux mount command.
Best regards,
Zhongliang Zhao
Best regards,
xian xia
-----原始邮件-----
发件人: Zhongliang Zhao<zhaozhongliang@xxxxxxxxx>
发送时间: 2014年2月27日 星期四
收件人: ceph-devel@xxxxxxxxxxxxxxx
抄送:
主题: location-aware file placement in Ceph
Dear all,
As new to ceph, may I ask in the crush algorithm, is there a way to
configure where the file to be stored, not randomly.
My requirement is to place the files that within the same
location(within a geographic area), into the same OSD, instead of
randomly placing them seperately.
I guess crush may support this. But to do this, I just have to
configure
some parameters in some ceph commands? or I have to modify the ceph
crush algorithm and re-compile ceph?
Many thanks for any helpful pointers.
Cheers, Giovanni
--
To unsubscribe from this list: send the line "unsubscribe
ceph-devel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
--
To unsubscribe from this list: send the line "unsubscribe ceph-devel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
