Hi Daniel, When I encounter an OSD which I can start, but which then stops on its own after running for some period of time, then root cause has generally been sectors pending reallocation on the hard drive the OSD is using. The OSD will run fine until it attempts to read from the bad disk sectors and then it produces a read error and drops offline.
You can check the disk using smartmon-tools, and if there are sectors pending reallocation, remove the OSD from the cluster, use dd to write zeros over the drive (this will cause the drive to reallocate spare sectors to replace the bad sectors), then re-add the OSD to the cluster. -Steve On 02/05/2015 08:19 AM, Daniel Takatori Ohara wrote: > Hello Alex, > > Thank's for the answer. > > In the server's, i use CentOS 6.6 with kernel 2.6.32, and in the > clients i use Ubuntu 14 with kernel 3.16. > > And the version of the Ceph is 0.87. > > Thank's, > > Att. > > --- > Daniel Takatori Ohara. > System Administrator - Lab. of Bioinformatics > Molecular Oncology Center > Instituto Sírio-Libanês de Ensino e Pesquisa > Hospital Sírio-Libanês > Phone: +55 11 3155-0200 (extension 1927) > R: Cel. Nicolau dos Santos, 69 > São Paulo-SP. 01308-060 > http://www.bioinfo.mochsl.org.br > > > On Thu, Feb 5, 2015 at 10:43 AM, Alexis KOALLA > <alexis.koa...@orange.com <mailto:alexis.koa...@orange.com>> wrote: > > Hi Daniel > Could you be more precise on your issue please? > What is the OS under which your ceph is running and what is the > ceph version you are currently running? > > Anyway, I have exeprienced an issue that looks like yours. > I have installed and configured a small cluster "microceph" on my > PC for quick demo. AOn this cluster I have 4 OSDs and 1 MON . > There is no MDS. > I have written a script that starts the cluster. > In this script I start the monitor: ceph-mon -c > /path/to/yourceph/confile -i <mon_id> > I also start manually the 4 OSD like this :ceph-osd -c > /path/to/yourceph/confile -i <osd_id> > > I also forced the OSD to be "in" after the start. > Right now it works fine.But I don't think it's the right ay to > process(start manually the OSD and putting them in ) > May be it can give you an idea where to start investigation. > > Regards > Alex > > > Le 05/02/2015 11:29, Daniel Takatori Ohara a écrit : >> Hi, anyone help me please. >> >> I have a cluster with 4 OSD's, 1 MDS and 1 MON. >> >> The osd.3 was down, and i need restart in the host with the >> command /etc/init.d/ceph restart osd.3. >> >> The osd.0 is marked down sometimes, but he is marked up >> automatically. >> >> [ceph@ceph-admin my-cluster]$ ceph osd tree >> # id weight type name up/down reweight >> -1 50.63 root default >> -2 13.84 host ceph-osd1 >> 0 13.84 osd.0 up 1 >> -3 14.76 host ceph-osd2 >> 1 14.76 osd.1 up 1 >> -4 22.03 host ceph-osd3 >> 2 10.09 osd.2 up 0.8 >> 3 11.94 osd.3 down 0 >> >> Anyone, can help me, please? >> >> Thank's, >> >> Att. >> >> --- >> Daniel Takatori Ohara. >> System Administrator - Lab. of Bioinformatics >> Molecular Oncology Center >> Instituto Sírio-Libanês de Ensino e Pesquisa >> Hospital Sírio-Libanês >> Phone: +55 11 3155-0200 <tel:%2B55%2011%203155-0200> (extension 1927) >> R: Cel. Nicolau dos Santos, 69 >> São Paulo-SP. 01308-060 >> http://www.bioinfo.mochsl.org.br >> >> >> >> _______________________________________________ >> ceph-users mailing list >> ceph-users@lists.ceph.com <mailto:ceph-users@lists.ceph.com> >> http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com > > -- > > logo Orange <http://www.orange.com/> > > *Alexis KOALLA* > > Orange/IMT/OLPS/ASE/DAPI/CSE > > Spécialiste en Technologies/Cloud Storage Services & Plateformes > > Specialist in Technologies/Cloud Storage Services & Platforms > > Tel :+33(0) 299 124 939 / +33 670 698 929 > alexis.koa...@orange.com <mailto:alexis.koa...@orange.com> > > > > > _______________________________________________ > ceph-users mailing list > ceph-users@lists.ceph.com > http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com -- Steve Anthony LTS HPC Support Specialist Lehigh University sma...@lehigh.edu
signature.asc
Description: OpenPGP digital signature
_______________________________________________ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
