Hi, On Wed, 2011-07-27 at 12:19 +0200, Sławomir Skowron wrote: > Thanks. > > 2011/7/27 Wido den Hollander <wido@xxxxxxxxx>: > > Hi, > > > > On Wed, 2011-07-27 at 07:58 +0200, Sławomir Skowron wrote: > >> Hello. I have some questions. > >> > >> 1. Is there any chance to change default 4MB object size to for > >> example 1MB or less ?? > > > > If you are using the filesystem, you can change the stripe-size per > > directory with the "cephfs" tool. > > Unfortunately i only use rados layer in this case, and i even don't > have any mds :) is there any chance to change this in rados layer ?? The RADOS gateway does NOT stripe over multiple objects. If you upload a 1GB object through the RADOS gateway it will be a 1GB object. Only the RBD (Rados Block Device) and the Ceph filesystem do striping over RADOS objects. RADOS itself doesn't stripe and the RADOS gateway is a almost 1:1 mapping of pools and objects. Wido > > >> > >> 2. I have create cluster of two mons, and 32 osd (1TB each) on two > >> machines. At this radosgw with apache2 for test. When i putting data > >> from s3 client to rados, everything is ok, but when one of osd is > >> going down all s3 clients going to be freeze for some seconds, before > >> ceph sign this osd as down, and then everything is starting working > >> again wit degraded osd. How can i tune this marking as a down for ms > >> or 0 :) and not for seconds freeze ?? > > > > Normally a OSD should be down within about 10 seconds and shouldn't > > affect all I/O operations. > > > > By default it takes 300 seconds before a OSD gets marked as "out", this > > is handled by "mon osd down out interval" > > > > If you want to change the "down" reporting behaviour you could do this > > with "osd min down reporters" and "osd min down reports". I'm not sure > > you really want to do this, as the default values should be ok. > > Ok. I will check this. > > > Wido > > > >> > >> My setup is debian 6.0, kernel 2.6.37.6 x86_64 and ceph version > >> 0.31-10 from stable repo. > >> > >> Best regards > >> > >> Slawomir Skowron > >> -- > >> 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
