Here's my possibly unique method... I had 3 nodes with 12 disks each,
and when adding 2 more nodes, I had issues with the common method you
describe, totally blocking clients for minutes, but this worked great
for me:
> my own method
> - osd max backfills = 1 and osd recovery max active = 1
> - create them with crush weight 0 so no peering happens
> - (starting here the script below does it, eg. `ceph_activate_osds 6`
> will set weight 6)
> - after they're up, set them reweight 0
> - then set crush weight to the TB of the disk
> - peering starts, but reweight is 0 so it doesn't block clients
> - when that's done, reweight 1 and it should be faster than the
> previous peering and not bug clients as much
>
>
> # list osds with hosts next to them for easy filtering with awk
> (doesn't support chassis, rack, etc. buckets)
> ceph_list_osd() {
> ceph osd tree | awk '
> BEGIN {found=0; host=""};
> $3 == "host" {found=1; host=$4; getline};
> $3 == "host" {found=0}
> found || $3 ~ /osd\./ {print $0 " " host}'
> }
>
> peering_sleep() {
> echo "sleeping"
> sleep 2
> while ceph health | grep -q peer; do
> echo -n .
> sleep 1
> done
> echo
> sleep 5
> }
>
> # after an osd is already created, this reweights them to 'activate' them
> ceph_activate_osds() {
> weight="$1"
> host=$(hostname -s)
>
> if [ -z "$weight" ]; then
> # TODO: somehow make this automatic...
> # This assumes all disks are the same weight.
> weight=6.00099
> fi
>
> # for crush weight 0 osds, set reweight 0 so the crush weight
> non-zero won't cause as many blocked requests
> for id in $(ceph_list_osd | awk '$2 == 0 {print $1}'); do
> ceph osd reweight $id 0 &
> done
> wait
> peering_sleep
>
> # the harsh reweight which we do slowly
> for id in $(ceph_list_osd | awk -v host="$host" '$5 == 0 && $7 ==
> host {print $1}'); do
> echo ceph osd crush reweight "osd.$id" "$weight"
> ceph osd crush reweight "osd.$id" "$weight"
> peering_sleep
> done
>
> # the light reweight
> for id in $(ceph_list_osd | awk -v host="$host" '$5 == 0 && $7 ==
> host {print $1}'); do
> ceph osd reweight $id 1 &
> done
> wait
> }
_______________________________________________
ceph-users mailing list
[email protected]
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
