Yeah, I think there was a bug. What upstream commit did you branch off from? -Greg Software Engineer #42 @ http://inktank.com | http://ceph.com On Wed, Mar 19, 2014 at 3:44 PM, Somnath Roy <Somnath.Roy@xxxxxxxxxxx> wrote: > I have tried with the following commands in this order and tried to map rbd > image everytime. > > > > ceph osd crush tunables bobtail > > ceph osd crush tunables argonaut > > ceph osd crush tunables legacy > > > > The cluster status after that.. > > > > ceph -s > > > > cluster d67fecd4-dd19-44cd-b69e-5b16a7b303e0 > > health HEALTH_WARN 1776 pgs degraded; 1776 pgs stuck unclean; recovery > 6553604/9830406 objects degraded (66.667%); crush map has non-optimal > tunables > > monmap e1: 1 mons at {a=10.196.123.24:6789/0}, election epoch 1, quorum > 0 a > > osdmap e27: 1 osds: 1 up, 1 in > > pgmap v2238: 1776 pgs, 6 pools, 200 GB data, 3200 kobjects > > 360 GB used, 1129 GB / 1489 GB avail > > 6553604/9830406 objects degraded (66.667%) > > 1776 active+degraded > > > > > > Thanks & Regards > > Somnath > > -----Original Message----- > From: Gregory Farnum [mailto:greg@xxxxxxxxxxx] > Sent: Wednesday, March 19, 2014 3:38 PM > To: Somnath Roy > Cc: Sage Weil (sage@xxxxxxxxxxx); Samuel Just (sam.just@xxxxxxxxxxx) > Subject: Re: rbd client map error > > > > Looking at http://tracker.ceph.com/issues/7208#change-33340, either you need > to set older CRUSH tunables (what settings have you tried?), or maybe > there's a bug at the point you branched from. It's not entirely clear to me > from that update; Sage? > > -Greg > > Software Engineer #42 @ http://inktank.com | http://ceph.com > > > > > > On Wed, Mar 19, 2014 at 3:30 PM, Somnath Roy <Somnath.Roy@xxxxxxxxxxx> > wrote: > >> Hi Greg/Sage/Sam, > >> > >> I am getting the following error in the sys log while I was trying to > >> map the rbd image to the ceph cluster running our optimized code base > >> rebased with latest ceph main. I am using kernel rbd client. > >> > >> > >> > >> Mar 19 14:54:18 emsserver1 kernel: [3766212.323266] libceph: mon0 > >> 10.196.123.24:6789 feature set mismatch, my 4a042a42 < server's > >> 104a042a42, missing 1000000000 > >> > >> Mar 19 14:54:18 emsserver1 kernel: [3766212.323280] libceph: mon0 > >> 10.196.123.24:6789 socket error on read > >> > >> > >> > >> Here is the kernel version... > >> > >> > >> > >> root@emsserver1:/home/ceph-wip-queueing-somnath-back/src# uname -a > >> > >> Linux emsserver1 3.11.0-tcp0copy1 #2 SMP Mon Feb 3 07:29:07 PST 2014 > >> x86_64 > >> x86_64 x86_64 GNU/Linux > >> > >> > >> > >> > >> > >> I saw there are some CRUSH tunable stuff you mentioned but trying > >> those also I was getting the error. So, given the client version I am > >> using which crush tunable value should I use ? > >> > >> > >> > >> ceph osd crush tunables > >> > >> > >> ________________________________ > >> > >> PLEASE NOTE: The information contained in this electronic mail message > >> is intended only for the use of the designated recipient(s) named > >> above. If the reader of this message is not the intended recipient, > >> you are hereby notified that you have received this message in error > >> and that any review, dissemination, distribution, or copying of this > >> message is strictly prohibited. If you have received this > >> communication in error, please notify the sender by telephone or > >> e-mail (as shown above) immediately and destroy any and all copies of > >> this message in your possession (whether hard copies or electronically >> stored copies). > >> > >> > > > > > ________________________________ > > PLEASE NOTE: The information contained in this electronic mail message is > intended only for the use of the designated recipient(s) named above. If the > reader of this message is not the intended recipient, you are hereby > notified that you have received this message in error and that any review, > dissemination, distribution, or copying of this message is strictly > prohibited. If you have received this communication in error, please notify > the sender by telephone or e-mail (as shown above) immediately and destroy > any and all copies of this message in your possession (whether hard copies > or electronically stored copies). > > -- 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
