[LU-17060] conf-sanity test_21c: Unable to start OST2 - MGS refuses to allow this server to start

• Type: Bug
• Resolution: Unresolved
• Priority: Minor
• Severity: 3
• Assignee: James A Simmons
• Reporter: Maloo

Description

This issue was created by maloo for Andreas Dilger <[e-mail]>

This issue relates to the following test suite run: https://testing.whamcloud.com/test_sets/57f0b610-268d-4d1e-be2b-d1898e8431b1

test_21c failed with the following error in the test logs:

trevis-98vm3 mkdir -p /mnt/lustre-ost2; mount -t lustre -o localrecov  /dev/mapper/ost2_flakey /mnt/lustre-ost2
trevis-98vm3: mount.lustre: mount /dev/mapper/ost2_flakey at /mnt/lustre-ost2 failed: Invalid argument
trevis-98vm3: This may have multiple causes.
trevis-98vm3: Are the mount options correct?
trevis-98vm3: Check the syslog for more info.

The OST console log shows:

Lustre: DEBUG MARKER: mkdir -p /mnt/lustre-ost2; mount -t lustre -o localrecov  /dev/mapper/ost2_flakey /mnt/lustre-ost2
LDISKFS-fs (dm-11): file extents enabled, maximum tree depth=5
LDISKFS-fs (dm-11): mounted filesystem with ordered data mode. Opts: errors=remount-ro
LDISKFS-fs (dm-11): file extents enabled, maximum tree depth=5
LDISKFS-fs (dm-11): mounted filesystem with ordered data mode. Opts: errors=remount-ro,no_mbcache,nodelalloc
LustreError: 160-7: lustre-OST0001: the MGS refuses to allow this server to start: rc = -22. Please see messages on the MGS.
LustreError: 30487:0:(tgt_mount.c:2216:server_fill_super()) Unable to start targets: -22
LustreError: 30487:0:(tgt_mount.c:1752:server_put_super()) no obd lustre-OST0001
LustreError: 30487:0:(tgt_mount.c:132:server_deregister_mount()) lustre-OST0001 not registered
Lustre: server umount lustre-OST0001 complete
LustreError: 30487:0:(super25.c:188:lustre_fill_super()) llite: Unable to mount <unknown>: rc = -22

The MGS console log shows:

LustreError: 14228:0:(mgs_llog.c:4541:mgs_write_log_target()) Can't write logs for lustre-OST0001 (-22)
LustreError: 14228:0:(mgs_handler.c:518:mgs_target_reg()) Failed to write lustre-OST0001 log (-22)
Lustre: DEBUG MARKER: /usr/sbin/lctl mark  conf-sanity test_21c: @@@@@@ FAIL: Unable to start OST2 
Lustre: DEBUG MARKER: conf-sanity test_21c: @@@@@@ FAIL: Unable to start OST2

Test session details:
clients: https://build.whamcloud.com/job/lustre-master/4455 - 4.18.0-477.15.1.el8_8.x86_64
servers: https://build.whamcloud.com/job/lustre-master/4455 - 4.18.0-477.15.1.el8_lustre.x86_64

It appears that the "Unable to start OST2" problem started on 2023-08-19. There were previous intermittent failures with "Unable to start OST1" but these were all fallout from earlier failures.

https://testing.whamcloud.com/search?status%5B%5D=FAIL&test_set_script_id=7f66aa20-3db2-11e0-80c0-52540025f9af&sub_test_script_id=8104001c-3db2-11e0-80c0-52540025f9af&start_date=2023-05-22&end_date=2023-08-29&source=sub_tests#redirect

VVVVVVV DO NOT REMOVE LINES BELOW, Added by Maloo for auto-association VVVVVVV
conf-sanity test_21c - Unable to start OST2

Issue Links

• is related to: LU-13306 allow clients to accept mgs_nidtbl_entry with IPv6 NIDs