Search results

Hi Folks, Just migrated ceph totally to bluestore a test with windows2016 Server has good results, but i think limiting component is virtio driver! see also https://forum.proxmox.com/threads/virtio-ethernet-driver-speed-10gbite.35881/ concering Ethernet speed ... I see no "tunables" to...

hmm no answer ? am I alone ?

tom, just forgot to adopt my signature .... please pardon my dust :)

Tom, Cluster is up-to-date with latest fixes from today. all 4 nodes rebooted ( this fixes the refresh problem in gui as stated earlier ....) I followed ceph instructions as stated in my initial post ... and i asked shall i do so or which recommendations do you have .... how to accomplish a...

Tom, just updated cluster and now I perform a inplace upgrade to bluestore some strange results in gui! only after shift reload in chrome i get ceph health results .... my procedure for each osd will be: ID=$1 echo "ceph osd out $ID" ceph osd out $ID # wait to start ceph remapping all things...

shall i change sources in apt ? current: cat ceph.list deb http://download.proxmox.com/debian/ceph-luminous stretch main to pvetest instead of main ?

Hi Tom, any exact release dates for 12.2 ? this week is almost gone .... regards Gerhard

Fine Tom ! would you recommend these steps in ceph documentation ? also a question aside this... are my x3pro mellanox cards RDMA capable ? this would speed up ceph significant i guess ...

Hi Folks, shall i migrate from filestore to bluestore following this article ? http://docs.ceph.com/docs/master/rados/operations/bluestore-migration/ or wait for ceph 12.2.x ? currenty pve has 12.1.2 luminous rc ... but how long to wait ? any release plans for 12.2 ? regards

ivan, thanks for bringing this up, same here, we have to disable iothread to be able to backup our rbd v-disks, really annoying :(

traffic on mellanox 56GbitE is no issue i guess why should i remove redundancy ?

dietmar, why not all 4 nodes ? any technical reason ?

just started a all scrub ... to force things to be clean ... hopefully :) ceph pg dump | grep -i active+clean | awk '{print $1}' | while read i; do ceph pg deep-scrub ${i}; done

ok i have done this on all 4 nodes now. shall i wait for end of scrubbing ? and then reboot whole cluster ? ceph -s cluster: id: cb0aba69-bad9-4d30-b163-c19f0fd1ec53 health: HEALTH_WARN 68 pgs not deep-scrubbed for 86400 417 pgs not scrubbed for 86400...

Hi I installed v5 beta and then v5 release. i had no problems with updates so far, exept this morning. I scanned for new updates, and alot of ceph updates popped up.... i installed them on all 4 machines .. now i have no active mgr in gui, i suppose i shredded ceph completly.... osds an mons...

Petr, perhaps this is a arp problem within migration task ? would be nice someone from staff came across with a explanation :(

icmp from a cluster host to vm ping 192.168.221.151 PING 192.168.221.151 (192.168.221.151) 56(84) bytes of data. 64 bytes from 192.168.221.151: icmp_seq=1 ttl=128 time=0.232 ms 64 bytes from 192.168.221.151: icmp_seq=2 ttl=128 time=0.224 ms 64 bytes from 192.168.221.151: icmp_seq=3 ttl=128...

hm must be bios issue in your case ... can you see device(s) in bios ? perhaps you need a bios update to operate also nmve disks ? or have you plugged in the device on wrong pci slot ?

I have no issue on my cluster this is lightning fast :) all on shared ceph storage, no zfs involved. task started by HA resource agent 2017-07-25 15:00:53 starting migration of VM 101 to node 'pve03' (192.168.221.143) 2017-07-25 15:00:53 copying disk images 2017-07-25 15:00:53 starting VM 101...

only my manually compiling the crush map for my knowledge ... gui has no feature to accomplish this :( good luck !