If you are just playing around, you could roll everything onto a single server. Or, if you wanted, put the MON and OSD on a single server and the radosgw on a different server. You can accomplish this in a virtual machine if you don't have all the hardware you would like to test with.
> -----Original Message----- > From: [email protected] [mailto:ceph-users- > [email protected]] On Behalf Of Guang > Sent: Monday, September 16, 2013 6:14 AM > To: [email protected]; Ceph Development > Subject: [ceph-users] Deploy a Ceph cluster to play around with > > Hello ceph-users, ceph-devel, > Nice to meet you in the community! > Today I tried to deploy a Ceph cluster to play around with the API, and during > the deployment, i have a couple of questions which may need you help: > 1) How many hosts do I need if I want to deploy a cluster with RadosGW (so > that I can try with the S3 API)? Is it 3 OSD + 1 Mon + 1 GW = 5 hosts on > minimum? > > 2) I have a list of hardwares, however, my host only have 1 disk with two > partitions, one for boot and another for LVM members, is it possible to > deploy an OSD on such hardware (e.g. make a partition with ext4)? Or I will > need another disk to do so? > > -bash-4.1$ ceph-deploy disk list myserver.com [ceph_deploy.osd][INFO ] > Distro info: RedHatEnterpriseServer 6.3 Santiago [ceph_deploy.osd][DEBUG ] > Listing disks on myserver.com... > [repl101.mobstor.gq1.yahoo.com][INFO ] Running command: ceph-disk list > [repl101.mobstor.gq1.yahoo.com][INFO ] /dev/sda : > [repl101.mobstor.gq1.yahoo.com][INFO ] /dev/sda1 other, ext4, mounted > on /boot [repl101.mobstor.gq1.yahoo.com][INFO ] /dev/sda2 other, > LVM2_member > > Thanks, > Guang > _______________________________________________ > ceph-users mailing list > [email protected] > http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com _______________________________________________ ceph-users mailing list [email protected] http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
