Hi Jeremy. Since you say the mons fail, could you share the logs of the failing mons? It is hard to diagnostic with little information. 发件人: Jeremy Hansen<mailto:jeremy@xxxxxxxxxx> 发送时间: 2021年11月16日 19:27 收件人: ceph-users<mailto:ceph-users@xxxxxxx> 主题: Re: mons fail as soon as I attempt to mount No ideas on this? It has me stumped. I’m going to revert my kernel upgrades if there isn’t a more logical explanation. Thanks > On Monday, Nov 15, 2021 at 2:33 AM, Jeremy Hansen <jeremy@xxxxxxxxxx (mailto:jeremy@xxxxxxxxxx)> wrote: > This post references a kernel issue: > > https://lists.ceph.io/hyperkitty/list/ceph-users@xxxxxxx/thread/6JDAPD5IR46JI6R6YGWQORDJTZ5Z2FIU/ > > I recently updated my ceph nodes to 5.15.1. Could this be my issue? > > -jeremy > > > > > > On Sunday, Nov 14, 2021 at 4:37 PM, Jeremy Hansen <jeremy@xxxxxxxxxx (mailto:jeremy@xxxxxxxxxx)> wrote: > > I’m trying to mount a cephfs volume from a new machine. For some reason, it looks like all the mons fail when attempting to mount: > > > > [root@btc04 ~]# mount -t ceph :/ /mnt/ceph -o name=btc > > mount error: no mds server is up or the cluster is laggy > > [root@btc04 ~]# rpm -qa | grep ceph > > python3-cephfs-16.2.4-0.el8.x86_64 > > ceph-common-16.2.4-0.el8.x86_64 > > cephadm-16.2.4-0.el8.noarch > > python3-ceph-argparse-16.2.4-0.el8.x86_64 > > libcephfs2-16.2.4-0.el8.x86_64 > > python3-ceph-common-16.2.4-0.el8.x86_64 > > > > > > [ 51.105212] libceph: loaded (mon/osd proto 15/24) > > [ 51.145564] ceph: loaded (mds proto 32) > > [ 51.164266] libceph: mon3 (1)192.168.30.14:6789 session established > > [ 70.199453] libceph: mon3 (1)192.168.30.14:6789 socket closed (con state OPEN) > > [ 70.199464] libceph: mon3 (1)192.168.30.14:6789 session lost, hunting for new mon > > [ 70.204400] libceph: mon0 (1)192.168.30.11:6789 session established > > [ 70.771652] libceph: mon0 (1)192.168.30.11:6789 socket closed (con state OPEN) > > [ 70.771670] libceph: mon0 (1)192.168.30.11:6789 session lost, hunting for new mon > > [ 70.774588] libceph: mon4 (1)192.168.30.15:6789 session established > > [ 71.234037] libceph: mon4 (1)192.168.30.15:6789 socket closed (con state OPEN) > > [ 71.234055] libceph: mon4 (1)192.168.30.15:6789 session lost, hunting for new mon > > [ 77.904722] libceph: mon3 (1)192.168.30.14:6789 socket closed (con state V1_BANNER) > > [ 78.160614] libceph: mon3 (1)192.168.30.14:6789 socket closed (con state V1_BANNER) > > [ 78.664602] libceph: mon3 (1)192.168.30.14:6789 socket closed (con state V1_BANNER) > > [ 79.824787] libceph: mon3 (1)192.168.30.14:6789 socket closed (con state V1_BANNER) > > [ 81.808526] libceph: mon3 (1)192.168.30.14:6789 socket closed (con state V1_BANNER) > > [ 85.840430] libceph: mon3 (1)192.168.30.14:6789 socket closed (con state V1_BANNER) > > > > > > Not really sure why… > > > > [ceph: root@cn01 /]# ceph osd pool get cephfs.btc.data all > > size: 4 > > min_size: 2 > > pg_num: 32 > > pgp_num: 32 > > crush_rule: replicated_rule > > hashpspool: true > > nodelete: false > > nopgchange: false > > nosizechange: false > > write_fadvise_dontneed: false > > noscrub: false > > nodeep-scrub: false > > use_gmt_hitset: 1 > > fast_read: 0 > > pg_autoscale_mode: on > > [ceph: root@cn01 /]# ceph osd pool get cephfs.btc.meta all > > size: 4 > > min_size: 2 > > pg_num: 32 > > pgp_num: 32 > > crush_rule: replicated_rule > > hashpspool: true > > nodelete: false > > nopgchange: false > > nosizechange: false > > write_fadvise_dontneed: false > > noscrub: false > > nodeep-scrub: false > > use_gmt_hitset: 1 > > fast_read: 0 > > recovery_priority: 5 > > pg_autoscale_mode: on > > pg_num_min: 16 > > pg_autoscale_bias: 4 > > > > > > The cluster becomes unhealthy but then clears shortly after the client times out. > > > > [ceph: root@cn01 /]# ceph -s > > cluster: > > id: bfa2ad58-c049-11eb-9098-3c8cf8ed728d > > health: HEALTH_OK > > > > services: > > mon: 5 daemons, quorum cn05,cn02,cn03,cn04,cn01 (age 6m) > > mgr: cn05.vpuwau(active, since 6d), standbys: cn02.arszct > > mds: 2/2 daemons up, 4 standby > > osd: 35 osds: 35 up (since 2d), 35 in (since 6d) > > > > data: > > volumes: 2/2 healthy > > pools: 6 pools, 289 pgs > > objects: 6.73M objects, 4.3 TiB > > usage: 17 TiB used, 108 TiB / 126 TiB avail > > pgs: 289 active+clean > > > > io: > > client: 0 B/s rd, 105 KiB/s wr, 2 op/s rd, 13 op/s wr > > > > > > > > -jeremy > > > > > > _______________________________________________ ceph-users mailing list -- ceph-users@xxxxxxx To unsubscribe send an email to ceph-users-leave@xxxxxxx
 |