[LU-1104] Fail to mount MDS after downgrade from 2.1.55 to 2.1.0 Created: 14/Feb/12  Updated: 15/Feb/12  Resolved: 15/Feb/12

Status: Resolved
Project: Lustre
Component/s: None
Affects Version/s: None
Fix Version/s: None

Type: Bug Priority: Minor
Reporter: Sarah Liu Assignee: WC Triage
Resolution: Won't Fix Votes: 0
Labels: None

Severity: 3
Rank (Obsolete): 6458

 Description   

The system configuration are one MDS, two OSS, two clients.Before downgrade, MDS, OSTS and clients are running 2.1.55 RHEL6-x86_64.
After downgrade:
client1 is 2.1.0-RHEK6-x86_64,client2 is 2.1.0-RHEL5-x86_64;
MDS is 2.1.0-RHEL6-x86_64;
OSS1 is 1.8.7-RHEL5-x86_64; OSS2 is 2.1.0-RHEL6-x86_64

After the whole system is downgraded, cannot mount MDS:

LustreError: 1345:0:(mdt_recovery.c:409:mdt_server_data_init()) lustre-MDT0000: unsupported incompat filesystem feature(s) 200
LustreError: 1345:0:(obd_config.c:522:class_setup()) setup lustre-MDT0000 failed (-22)
LustreError: 1345:0:(obd_config.c:1361:class_config_llog_handler()) Err -22 on cfg command:
Lustre: cmd=cf003 0:lustre-MDT0000 1:lustre-MDT0000_UUID 2:0 3:lustre-MDT0000-mdtlov 4:f
LustreError: 15b-f: MGC10.10.4.131@tcp: The configuration from log 'lustre-MDT0000'failed from the MGS (-22). Make sure this client and the MGS are running compatible versions of Lustre.
LustreError: 15c-8: MGC10.10.4.131@tcp: The configuration from log 'lustre-MDT0000' failed (-22). This may be the result of communication errors between this node and the MGS, a bad configuration, or other errors. See the syslog for more information.
LustreError: 1279:0:(obd_mount.c:1192:server_start_targets()) failed to start server lustre-MDT0000: -22
LustreError: 1279:0:(obd_mount.c:1719:server_fill_super()) Unable to start targets: -22
LustreError: 1279:0:(obd_config.c:567:class_cleanup()) Device 3 not setup
LustreError: 1279:0:(ldlm_request.c:1172:ldlm_cli_cancel_req()) Got rc -108 from cancel RPC: canceling anyway
Lustre: MGS has stopped.
LustreError: 1279:0:(ldlm_request.c:1799:ldlm_cli_cancel_list()) ldlm_cli_cancel_list: -108
Lustre: 1279:0:(client.c:1778:ptlrpc_expire_one_request()) @@@ Request x1393773299892268 sent from MGC10.10.4.131@tcp to NID 0@lo has timed out for slow reply: [sent 1329253215] [real_sent 1329253215] [current 1329253221] [deadline 6s] [delay 0s] req@ffff88061a810c00 x1393773299892268/t0(0) o-1->MGS@MGC10.10.4.131@tcp_0:26/25 lens 192/192 e 0 to 1 dl 1329253221 ref 2 fl Rpc:XN/ffffffff/ffffffff rc 0/-1
Lustre: server umount lustre-MDT0000 complete
LustreError: 1279:0:(obd_mount.c:2160:lustre_fill_super()) Unable to mount (-22)
mount.lustre: mount /dev/sdc1 at /mnt/mds1 failed: Invalid argument
This may have multiple causes.
Are the mount options correct?
Check the syslog for more info.

 Comments   
Comment by Andreas Dilger [ 15/Feb/12 ]

Was the filesystem originally formatted with 2.1.0, then upgraded to 2.1.55, then downgraded to 2.1.0 again? This is supported.

If the filesystem was formatted with 2.1.55, then downgraded to 2.1.0, this is not supported. The "multi OI" feature was enabled for new filesystems for 2.2, and this is not understood by older Lustre MDS code.

Comment by Sarah Liu [ 15/Feb/12 ]

ah, I see, the system was formatted with 2.1.55 and then downgrade to 2.1.0

Comment by Peter Jones [ 15/Feb/12 ]

ok so it sounds like this is expected behaviour then

Comment by Sarah Liu [ 15/Feb/12 ]

unexpected, I think you mean, Peter. Anyway I will rerun the test again.

Generated at Sat Feb 10 01:13:32 UTC 2024 using Jira 9.4.14#940014-sha1:734e6822bbf0d45eff9af51f82432957f73aa32c.