On Thursday 20 of May 2010 20:24:50 you wrote: > On Thu, 20 May 2010, Wido den Hollander wrote: > > Hi, > > > > On Thu, 2010-05-20 at 17:09 +0000, Sage Weil wrote: > > > > > I'd prefer the situation where i'd stripe over all 4 disks, giving > > > > > me and extra pro. In this situation i could configure my node to > > > > > panic whenever a disk is starting to give errors, so my cluster can > > > > > take over immediately. > > > > > > > > > > Am i right? Is this "the way to go"? > > > > > > > > I don't know the way to go. But I think that in the 1st case (1 OSD > > > > per hard disk) when a hard disk fails, it gets replicated elsewhere. > > > > During that time the other 3 OSDs on the same machine are still > > > > working fine and serving requests. And then some time later, you've > > > > got a brand new disk, you shutdown the machnie, that's 3 more OSDs > > > > down. In the 2nd case, as soon as 1 disk starts failing, your OSD > > > > (which is 4 disks) gets taken down, that's approximately equivalent > > > > to 4 OSDs going down at the same time if we compare to your 1st case. > > > > > > The other 3 osds don't have to rereplicate if you swap the failed disk > > > quickly, or otherwise inform the system that the failure is temporary. > > > By default there is a 5 minute timeout. That can be adjusted, or we > > > can add other administrative hooks to 'suspend' any declarations of > > > permanent failure for this sort of case. > > > > Ok, so upping this timeout to something like 10 minutes would be > > sufficient for swapping and OSD. > > > > This is done via the mon_osd_down_out_interval paramater i assume (found > > in config.cc) > > Yes. And you can modify this value on a running system (without modifying > the .conf and restarting the monitor) with > > $ ceph mon injectargs \* '--mon_osd_down_out_interval 600' > > on the latest unstable. > > > About more then one OSD on one machine, is there a way how you can bind > > an OSD to a specific IP? Can't seem to find any configuration for this. > > > > I assume you will need one IP per OSD on that machine? > > Not currently via the .conf, only via the --bind 1.2.3.4:123 command line > argument. Adding a bug for this. Is that one IP per cosd daemon really necessary? I'm currently running four osd nodes, two disk/cosd per each with single IP per node. So far it seems working:) > > And my journaling question, any views on that topic? > > I don't thank that turning the write cache off will affect btrfs too much, > but I haven't tested it. It does need to be off if you use a separate > partition. The other alternative is to put the journal file in btrfs, but > that is slower. > > sage > > > Thanks! > > > > > sage > > > -- > > > 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 > Michal Humpula -- 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
