On 04/02/2013 06:18 AM, Varun Chandramouli wrote:
Hi All, I wanted to monitor the performance of a ceph cluster: the disk storage, cpu utilization, and mainly, the network traffic (data getting transferred between 2 OSDs). Could you suggest any tools/commands suited for this?
There are lots of tools that can do monitoring. I think DreamHost is using collectd with graphite for logging. For background monitoring on a large cluster, ganglia is another alternative. I personally use collectl on the command line for a lot of my testing. You can also use it in daemon mode for background monitoring, and it can integrate with ganglia if desired.
Lots of options!
Another question I had was regarding hadoop-MR on ceph. I believe that on HDFS, the jobtracker tries to schedule jobs locally, with necessary information from the namenode. When on ceph, how is this ensured, given that a file may be divided into multiple objects, which may be on different OSDs. Does the jobtracker get the locations of the objects from the mds, and schedule the jobs locally?
I'll let one of the hadoop guys chime in here.
Regards Varun _______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
_______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
