Thanks a lot Maxime, I did the osd_crush_update_on_start = false on ceph.conf and push it to all the nodes, and then i create a map file:
# begin crush map
tunable choose_local_tries 0
tunable choose_local_fallback_tries 0
tunable choose_total_tries 50
tunable chooseleaf_descend_once 1
tunable chooseleaf_vary_r 1
tunable chooseleaf_stable 1
tunable straw_calc_version 1
tunable allowed_bucket_algs 54
# devices
device 0 osd.0
device 1 osd.1
device 2 osd.2
device 3 osd.3
device 4 osd.4
device 5 osd.5
device 6 osd.6
device 7 osd.7
device 8 osd.8
device 9 osd.9
device 10 osd.10
device 11 osd.11
device 12 osd.12
device 13 osd.13
device 14 osd.14
device 15 osd.15
device 16 osd.16
device 17 osd.17
device 18 osd.18
device 19 osd.19
device 20 osd.20
device 21 osd.21
device 22 osd.22
device 23 osd.23
device 24 osd.24
device 25 osd.25
device 26 osd.26
device 27 osd.27
device 28 osd.28
device 29 osd.29
device 30 osd.30
device 31 osd.31
device 32 osd.32
device 33 osd.33
device 34 osd.34
device 35 osd.35
device 36 osd.36
device 37 osd.37
device 38 osd.38
device 39 osd.39
device 40 osd.40
device 41 osd.41
device 42 osd.42
device 43 osd.43
device 44 osd.44
device 45 osd.45
device 46 osd.46
device 47 osd.47
# types
type 0 osd
type 1 node
type 2 rack
type 3 root
# buckets
node cpn01 {
id -1 # do not change unnecessarily
# weight 12.000
alg straw
hash 0 # rjenkins1
item osd.0 weight 1.000
item osd.1 weight 1.000
item osd.2 weight 1.000
item osd.3 weight 1.000
item osd.4 weight 1.000
item osd.5 weight 1.000
item osd.6 weight 1.000
item osd.7 weight 1.000
item osd.8 weight 1.000
item osd.9 weight 1.000
item osd.10 weight 1.000
item osd.11 weight 1.000
}
node cpn02 {
id -2 # do not change unnecessarily
# weight 12.000
alg straw
hash 0 # rjenkins1
item osd.12 weight 1.000
item osd.13 weight 1.000
item osd.14 weight 1.000
item osd.15 weight 1.000
item osd.16 weight 1.000
item osd.17 weight 1.000
item osd.18 weight 1.000
item osd.19 weight 1.000
item osd.20 weight 1.000
item osd.21 weight 1.000
item osd.22 weight 1.000
item osd.23 weight 1.000
}
node cpn03 {
id -3 # do not change unnecessarily
# weight 12.000
alg straw
hash 0 # rjenkins1
item osd.24 weight 1.000
item osd.25 weight 1.000
item osd.26 weight 1.000
item osd.27 weight 1.000
item osd.28 weight 1.000
item osd.29 weight 1.000
item osd.30 weight 1.000
item osd.31 weight 1.000
item osd.32 weight 1.000
item osd.33 weight 1.000
item osd.34 weight 1.000
item osd.35 weight 1.000
}
node cpn04 {
id -4 # do not change unnecessarily
# weight 12.000
alg straw
hash 0 # rjenkins1
item osd.36 weight 1.000
item osd.37 weight 1.000
item osd.38 weight 1.000
item osd.39 weight 1.000
item osd.40 weight 1.000
item osd.41 weight 1.000
item osd.42 weight 1.000
item osd.43 weight 1.000
item osd.44 weight 1.000
item osd.45 weight 1.000
item osd.46 weight 1.000
item osd.47 weight 1.000
}
rack rack1 {
id -5 # do not change unnecessarily
# weight 24.000
alg straw
hash 0 # rjenkins1
item cpn01 weight 12.000
item cpn03 weight 12.000
}
rack rack2 {
id -6 # do not change unnecessarily
# weight 24.000
alg straw
hash 0 # rjenkins1
item cpn02 weight 12.000
item cpn04 weight 12.000
}
root root {
id -7 # do not change unnecessarily
# weight 48.000
alg straw
hash 0 # rjenkins1
item rack1 weight 24.000
item rack2 weight 24.000
}
# rules
rule replicated_rule {
id 0
type replicated
min_size 1
max_size 10
step take root
step chooseleaf firstn 0 type node
step emit
}
# end crush map
and finally issue:
# crushtool -c map.txt -o crushmap
# ceph osd setcrushmap -i crushmap
since it's a new cluster no problem with rebalance
Best,
German
2017-09-13 13:46 GMT-03:00 Maxime Guyot <maxime@xxxxxxxxxxx>:
Hi,This is a common problem when doing custom CRUSHmap, the default behavior is to update the OSD node to location in the CRUSHmap on start. did you keep to the defaults there?If that is the problem, you can either:1) Disable the update on start option: "osd crush update on start = false" (see http://docs.ceph.com/docs/master/rados/operations/ )crush-map/#crush-location 2) Customize the script defining the location of OSDs with "crush location hook = /path/to/customized-ceph-crush- location" (see https://github.com/ceph/ceph/blob/master/src/ceph-crush- ).location.in Cheers,MaximeOn Wed, 13 Sep 2017 at 18:35 German Anders <ganders@xxxxxxxxxxxx> wrote:# ceph health detailHEALTH_OK# ceph osd stat48 osds: 48 up, 48 in# ceph pg stat3200 pgs: 3200 active+clean; 5336 MB data, 79455 MB used, 53572 GB / 53650 GB availGerman
______________________________2017-09-13 13:24 GMT-03:00 dE <de.techno@xxxxxxxxx>:On 09/13/2017 09:08 PM, German Anders wrote:
Hi cephers,
I'm having an issue with a newly created cluster 12.2.0 (32ce2a3ae5239ee33d6150705cdb24 d43bab910c) luminous (rc). Basically when I reboot one of the nodes, and when it come back, it come outside of the root type on the tree:
root@cpm01:~# ceph osd treeID CLASS WEIGHT TYPE NAME STATUS REWEIGHT PRI-AFF-15 12.00000 root default36 nvme 1.00000 osd.36 up 1.00000 1.0000037 nvme 1.00000 osd.37 up 1.00000 1.0000038 nvme 1.00000 osd.38 up 1.00000 1.0000039 nvme 1.00000 osd.39 up 1.00000 1.0000040 nvme 1.00000 osd.40 up 1.00000 1.0000041 nvme 1.00000 osd.41 up 1.00000 1.0000042 nvme 1.00000 osd.42 up 1.00000 1.0000043 nvme 1.00000 osd.43 up 1.00000 1.0000044 nvme 1.00000 osd.44 up 1.00000 1.0000045 nvme 1.00000 osd.45 up 1.00000 1.0000046 nvme 1.00000 osd.46 up 1.00000 1.0000047 nvme 1.00000 osd.47 up 1.00000 1.00000-7 36.00000 root root-5 24.00000 rack rack1-1 12.00000 node cpn010 1.00000 osd.0 up 1.00000 1.000001 1.00000 osd.1 up 1.00000 1.000002 1.00000 osd.2 up 1.00000 1.000003 1.00000 osd.3 up 1.00000 1.000004 1.00000 osd.4 up 1.00000 1.000005 1.00000 osd.5 up 1.00000 1.000006 1.00000 osd.6 up 1.00000 1.000007 1.00000 osd.7 up 1.00000 1.000008 1.00000 osd.8 up 1.00000 1.000009 1.00000 osd.9 up 1.00000 1.0000010 1.00000 osd.10 up 1.00000 1.0000011 1.00000 osd.11 up 1.00000 1.00000-3 12.00000 node cpn0324 1.00000 osd.24 up 1.00000 1.0000025 1.00000 osd.25 up 1.00000 1.0000026 1.00000 osd.26 up 1.00000 1.0000027 1.00000 osd.27 up 1.00000 1.0000028 1.00000 osd.28 up 1.00000 1.0000029 1.00000 osd.29 up 1.00000 1.0000030 1.00000 osd.30 up 1.00000 1.0000031 1.00000 osd.31 up 1.00000 1.0000032 1.00000 osd.32 up 1.00000 1.0000033 1.00000 osd.33 up 1.00000 1.0000034 1.00000 osd.34 up 1.00000 1.0000035 1.00000 osd.35 up 1.00000 1.00000-6 12.00000 rack rack2-2 12.00000 node cpn0212 1.00000 osd.12 up 1.00000 1.0000013 1.00000 osd.13 up 1.00000 1.0000014 1.00000 osd.14 up 1.00000 1.0000015 1.00000 osd.15 up 1.00000 1.0000016 1.00000 osd.16 up 1.00000 1.0000017 1.00000 osd.17 up 1.00000 1.0000018 1.00000 osd.18 up 1.00000 1.0000019 1.00000 osd.19 up 1.00000 1.0000020 1.00000 osd.20 up 1.00000 1.0000021 1.00000 osd.21 up 1.00000 1.0000022 1.00000 osd.22 up 1.00000 1.0000023 1.00000 osd.23 up 1.00000 1.00000-4 0 node cpn04
Any ideas of why this happen? and how can I fix it? It supposed to be inside rack2
Thanks in advance,
Best,
German
_______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/ listinfo.cgi/ceph-users-ceph. com Can we see the output of ceph health detail. Maybe they're under the process of recovery.
Also post the output of ceph osd stat so we can see what nodes are up/in etc... and ceph pg stat to see the status of various PGs (a pointer to the recovery process).
_________________
ceph-users mailing list
ceph-users@xxxxxxxxxxxxxx
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph. com
_______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
