gordon-quad's questions

I am considering an option of ceph as distributed filesystem for my home-made MAID (massive array of idle drives).

As far as I understand, Ceph oriented for cluster use and spread data evenly over OSDs (with respect to CRUSH maps) and tries to utilize parallelism of read operations over different nodes.

In my case I don't need to maximize spread and throughput, in ideal case it should fill first N OSDs (where N is replication factor) and only then start filling next N OSDs, to minimize amount of required active drives for adjacent data retrieval.

Can I somehow achieve such behaviour by tweaking placement groups count and CRUSH maps? Or if it is not possible can I at least make ceph stop splitting files into more than one block?

I need to change some mount options for parts of the root filesystem, such as /tmp /var and /home (add nodev,nosuid and quota), but I haven't ability to make a separate partition and I have not enough RAM to mount /tmp as tmpfs. I've tried mount -o bind,noexec,nodev,nosuid /tmp /tmp, but it seems not working because after that I still can exec files from /tmp and make device nods on it. Is there other way to do that?

How can I restrict access to some web-app deployed in Glassfish from certain IPs ? Are there any internal access control in Glassfish or I need to proxy it with external nginx or Apache ?