Salut, Ce valori ai folosit pentru pg_num si pgp_num?
Ceva documentatie utila: https://access.redhat.com/documentation/en/red-hat-ceph-storage/1.3/storage-strategies/chapter-14-pg-count#pg-count-for-small-clusters http://www.sebastien-han.fr/blog/2015/06/16/ceph-is-complaining-too-many-pgs/ Multumesc, Marius On Sun, Feb 7, 2016 at 7:02 PM, Mircea MITU <mir...@sigu.ro> wrote: > Salut > > Pe un sistem (centos6) mereu cand incarc sa creez un ceph storage (din 2 > osd-uri) il creez in status health_warn ca mai jos > > # ceph -w > cluster idxxxx > health HEALTH_WARN > too many PGs per OSD (576 > max 300) > monmap e1: 1 mons at {x=1.2.3.4:6789/0} > election epoch 1, quorum 0 vditest > osdmap e58: 2 osds: 2 up, 2 in > pgmap v35876: 576 pgs, 5 pools, 7506 MB data, 949 objects > 25335 MB used, 1837 GB / 1862 GB avail > 576 active+clean > client io 40918 kB/s wr, 9 op/s > > Indiferent ce as face (scot osd-urile, adaug, refac de la zero), raman cu too > many PGs per OSD (576 > max 300) si 576 active+clean > Are cineva idee unde ma mai pot uita? > > > > Multumesc, > Mircea > _______________________________________________ > RLUG mailing list > RLUG@lists.lug.ro > http://lists.lug.ro/mailman/listinfo/rlug _______________________________________________ RLUG mailing list RLUG@lists.lug.ro http://lists.lug.ro/mailman/listinfo/rlug