Hi Fabio, have a look here: https://github.com/ceph/ceph/blob/luminous/src/common/options.cc#L2355 <https://github.com/ceph/ceph/blob/luminous/src/common/options.cc#L2355>
It’s designed to relieve the pressure generated by the recovery and backfill on both the drives and the network as it slows down these activities by introducing a sleep after these respectives ops. Regards JC > On Feb 18, 2019, at 09:28, Fabio Abreu <[email protected]> wrote: > > Hi Everybody ! > > I finding configure my cluster to receives news disks and pgs and after > configure the main standard configuration too, I look the parameter "osd > sleep recovery" to implement in production environment but I find just sample > doc about this config. > > Someone have experience with this parameter ? > > Only discussion in the internet about this : > http://lists.ceph.com/pipermail/ceph-users-ceph.com/2018-March/025574.html > <http://lists.ceph.com/pipermail/ceph-users-ceph.com/2018-March/025574.html> > > My main configuration to receive new osds in Jewel 10.2.7 cluster : > > Before include new nodes : > $ ceph tell osd.* injectargs '--osd-max-backfills 2' > $ ceph tell osd.* injectargs '--osd-recovery-threads 1' > $ ceph tell osd.* injectargs '--osd-recovery-op-priority 2' > $ ceph tell osd.* injectargs '--osd-client-op-priority 63' > $ ceph tell osd.* injectargs '--osd-recovery-max-active 2' > > After include new nodes > $ ceph tell osd.* injectargs '--osd-max-backfills 1' > $ ceph tell osd.* injectargs '--osd-recovery-threads 1' > $ ceph tell osd.* injectargs '--osd-recovery-op-priority 1' > $ ceph tell osd.* injectargs '--osd-client-op-priority 63' > $ ceph tell osd.* injectargs '--osd-recovery-max-active 1' > > > Regards, > > Fabio Abreu Reis > http://fajlinux.com.br <http://fajlinux.com.br/> > Tel : +55 21 98244-0161 > Skype : fabioabreureis > _______________________________________________ > 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
