Uploaded image for project: 'Lustre'
  1. Lustre
  2. LU-2318

Remove "Found index ..., updating log" message

Details

    • Improvement
    • Resolution: Duplicate
    • Minor
    • None
    • Lustre 2.4.0
    • 5542

    Description

      What is the purpose of this message?

      2012-11-13 09:54:48 Lustre: Found index 0 for lstest-MDT0000, updating log
      

      I believe it's generated here:

      3009         if (rc == EALREADY) {                                                   
      3010                 LCONSOLE_WARN("Found index %d for %s, updating log\n",          
      3011                               mti->mti_stripe_index, mti->mti_svname);                    
      3012                 /* We would like to mark old log sections as invalid            
      3013                    and add new log sections in the client and mdt logs.         
      3014                    But if we add new sections, then live clients will           
      3015                    get repeat setup instructions for already running            
      3016                    osc's. So don't update the client/mdt logs. */               
      3017                 mti->mti_flags &= ~LDD_F_UPDATE;                                
      3018         }  
      

      I don't see it serving a useful purpose to a administrator, so lets remove it.

      Attachments

        Activity

          [LU-2318] Remove "Found index ..., updating log" message

          I'm closing this as it's covered in the different patch under LU-2156. sorry for confusion.

          bzzz Alex Zhuravlev added a comment - I'm closing this as it's covered in the different patch under LU-2156 . sorry for confusion.

          that's correct Prakash. literally there is no need to update the log every time.

          bzzz Alex Zhuravlev added a comment - that's correct Prakash. literally there is no need to update the log every time.

          Thanks Alex! I'm curious.. What is this log for? Is it part of the MGS and only needs to be updated when a filesystem configuration change happens, i.e. LDD_F_VIRGIN or LDD_F_WRITECONF?

          prakash Prakash Surya (Inactive) added a comment - Thanks Alex! I'm curious.. What is this log for? Is it part of the MGS and only needs to be updated when a filesystem configuration change happens, i.e. LDD_F_VIRGIN or LDD_F_WRITECONF ?
          bzzz Alex Zhuravlev added a comment - http://review.whamcloud.com/4631

          Console messages after boot on our test filesystem yesterday:

          2012-11-14 17:20:03 Mounting grove-mds1/mgs on /mnt/lustre/local/ls1-MGS0000
          2012-11-14 17:20:03 Lustre: Lustre: Build Version: 2.3.54-6chaos-6chaos--PRISTINE-2.6.32-220.23.1.2chaos.ch5.x86_64
          2012-11-14 17:20:05 Mounting grove-mds1/mdt0 on /mnt/lustre/local/ls1-MDT0000
          2012-11-14 17:20:05 Lustre: Found index 0 for ls1-MDT0000, updating log
          2012-11-14 17:20:05 LustreError: 31856:0:(mgc_request.c:248:do_config_log_add()) failed processing sptlrpc log: -2
          2012-11-14 17:20:05 LustreError: 31859:0:(sec_config.c:1024:sptlrpc_target_local_copy_conf()) missing llog context
          2012-11-14 17:20:09 Lustre: ls1-MDT0000: Temporarily refusing client connection from 0@lo
          2012-11-14 17:20:09 LustreError: 11-0: ls1-MDT0000-osp-MDT0000: Communicating with 0@lo, operation mds_connect failed with -11
          2012-11-14 17:20:09 LustreError: 31856:0:(mdd_lfsck.c:323:mdd_lfsck_setup()) ls1-MDD0000: Lustre LFSCK unsupported on this device.
          2012-11-14 17:20:09 Lustre: 31856:0:(fld_index.c:319:fld_index_init()) srv-ls1-MDT0000: File "fld" doesn't support range lookup, using stub. DNE and FIDs on OST will not work with this backend
          2012-11-14 17:20:10 grove-mds1 login: Lustre: ls1-MDT0000: Will be in recovery for at least 5:00, or until 3 clients reconnect.
          2012-11-14 17:20:34 LustreError: 11-0: ls1-MDT0000-osp-MDT0000: Communicating with 0@lo, operation mds_connect failed with -11
          2012-11-14 17:20:59 LustreError: 11-0: ls1-MDT0000-osp-MDT0000: Communicating with 0@lo, operation mds_connect failed with -11
          2012-11-14 17:21:49 LustreError: 11-0: ls1-MDT0000-osp-MDT0000: Communicating with 0@lo, operation mds_connect failed with -11
          2012-11-14 17:22:14 LustreError: 11-0: ls1-MDT0000-osp-MDT0000: Communicating with 0@lo, operation mds_connect failed with -11
          2012-11-14 17:22:58 grove-mds1 login: LustreError: 11-0: ls1-MDT0000-osp-MDT0000: Communicating with 0@lo, operation mds_connect failed with -11
          2012-11-14 17:23:29 LustreError: 11-0: ls1-MDT0000-osp-MDT0000: Communicating with 0@lo, operation mds_connect failed with -11
          2012-11-14 17:23:42 INFO: task tgt_recov:656 blocked for more than 120 seconds.
          2012-11-14 17:23:42 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
          2012-11-14 17:23:42 tgt_recov     D 000000000000000d     0   656      2 0x00000000
          2012-11-14 17:23:42  ffff882f89179e10 0000000000000046 0000000000000000 ffffffff81052026
          2012-11-14 17:23:42  ffff882f89179da0 ffff882fcdd12ae0 ffff882f89179da0 ffffffff8104da6d
          2012-11-14 17:23:42  ffff882f89177af8 ffff882f89179fd8 000000000000f4e8 ffff882f89177af8
          2012-11-14 17:23:42 Call Trace:
          2012-11-14 17:23:42  [<ffffffff81052026>] ? enqueue_task+0x66/0x80
          2012-11-14 17:23:42  [<ffffffff8104da6d>] ? check_preempt_curr+0x6d/0x90
          2012-11-14 17:23:42  [<ffffffffa087b330>] ? check_for_clients+0x0/0x90 [ptlrpc]
          2012-11-14 17:23:42  [<ffffffffa087cd25>] target_recovery_overseer+0x95/0x250 [ptlrpc]
          2012-11-14 17:23:42  [<ffffffffa087b130>] ? exp_connect_healthy+0x0/0x20 [ptlrpc]
          2012-11-14 17:23:42  [<ffffffff81091090>] ? autoremove_wake_function+0x0/0x40
          2012-11-14 17:23:42  [<ffffffffa0883f8e>] target_recovery_thread+0x58e/0x19d0 [ptlrpc]
          2012-11-14 17:23:42  [<ffffffff8106ed2f>] ? do_exit+0x5af/0x870
          2012-11-14 17:23:42  [<ffffffffa0883a00>] ? target_recovery_thread+0x0/0x19d0 [ptlrpc]
          2012-11-14 17:23:42  [<ffffffff8100c14a>] child_rip+0xa/0x20
          2012-11-14 17:23:42  [<ffffffffa0883a00>] ? target_recovery_thread+0x0/0x19d0 [ptlrpc]
          2012-11-14 17:23:42  [<ffffffffa0883a00>] ? target_recovery_thread+0x0/0x19d0 [ptlrpc]
          2012-11-14 17:23:42  [<ffffffff8100c140>] ? child_rip+0x0/0x20
          2012-11-14 17:24:01 Lustre: Found index 130 for ls1-OST0082, updating log
          2012-11-14 17:24:01 Lustre: Found index 81 for ls1-OST0051, updating log
          2012-11-14 17:24:01 Lustre: Skipped 3 previous similar messages
          2012-11-14 17:24:02 Lustre: Found index 33 for ls1-OST0021, updating log
          2012-11-14 17:24:02 Lustre: Skipped 4 previous similar messages
          2012-11-14 17:24:05 Lustre: Found index 354 for ls1-OST0162, updating log
          2012-11-14 17:24:05 Lustre: Skipped 17 previous similar messages
          2012-11-14 17:24:09 Lustre: Found index 357 for ls1-OST0165, updating log
          2012-11-14 17:24:09 Lustre: Skipped 50 previous similar messages
          2012-11-14 17:24:17 Lustre: Found index 150 for ls1-OST0096, updating log
          2012-11-14 17:24:17 Lustre: Skipped 126 previous similar messages
          2012-11-14 17:24:19 LustreError: 11-0: ls1-MDT0000-osp-MDT0000: Communicating with 0@lo, operation mds_connect failed with -11
          2012-11-14 17:24:33 Lustre: Found index 280 for ls1-OST0118, updating log
          2012-11-14 17:24:33 Lustre: Skipped 31 previous similar messages
          2012-11-14 17:24:51 grove-mds1 login: LustreError: 11-0: ls1-MDT0000-osp-MDT0000: Communicating with 0@lo, operation mds_connect failed with -11
          2012-11-14 17:25:14 LustreError: Skipped 1 previous similar message
          2012-11-14 17:25:18 Lustre: ls1-MDT0000: Recovery over after 5:00, of 3 clients 2 recovered and 1 was evicted.
          2012-11-14 17:26:29 LustreError: 11-0: ls1-MDT0000-osp-MDT0000: Communicating with 0@lo, operation mds_connect failed with -11
          2012-11-14 17:26:29 LustreError: Skipped 2 previous similar messages
          2012-11-14 17:28:59 LustreError: 11-0: ls1-MDT0000-osp-MDT0000: Communicating with 0@lo, operation mds_connect failed with -11
          2012-11-14 17:28:59 LustreError: Skipped 5 previous similar messages
          2012-11-14 17:29:03 Lustre: ls1-OST0031-osc-MDT0000: Connection restored to ls1-OST0031 (at 172.20.1.49@o2ib500)
          2012-11-14 17:29:03 LustreError: 32077:0:(osp_sync.c:584:osp_sync_process_record()) processed all old entries: 0xcef:1
          2012-11-14 17:29:03 Lustre: ls1-OST0032-osc-MDT0000: Connection restored to ls1-OST0032 (at 172.20.1.50@o2ib500)
          2012-11-14 17:29:03 LustreError: 32080:0:(osp_sync.c:584:osp_sync_process_record()) processed all old entries: 0xcf0:1
          2012-11-14 17:29:06 Lustre: ls1-OST0092-osc-MDT0000: Connection restored to ls1-OST0092 (at 172.20.1.146@o2ib500)
          2012-11-14 17:29:06 LustreError: 32368:0:(osp_sync.c:584:osp_sync_process_record()) processed all old entries: 0xd50:1
          2012-11-14 17:29:06 LustreError: 32368:0:(osp_sync.c:584:osp_sync_process_record()) Skipped 6 previous similar messages
          2012-11-14 17:29:06 Lustre: Skipped 6 previous similar messages
          2012-11-14 17:29:24 Lustre: ls1-OST002e-osc-MDT0000: Connection restored to ls1-OST002e (at 172.20.1.46@o2ib500)
          2012-11-14 17:29:24 LustreError: 32068:0:(osp_sync.c:584:osp_sync_process_record()) processed all old entries: 0xcec:1
          2012-11-14 17:29:24 LustreError: 32068:0:(osp_sync.c:584:osp_sync_process_record()) Skipped 7 previous similar messages
          2012-11-14 17:29:24 Lustre: Skipped 7 previous similar messages
          2012-11-14 17:29:53 Lustre: ls1-OST00b4-osc-MDT0000: Connection restored to ls1-OST00b4 (at 172.20.1.180@o2ib500)
          2012-11-14 17:29:53 LustreError: 32470:0:(osp_sync.c:584:osp_sync_process_record()) processed all old entries: 0xd72:1
          2012-11-14 17:29:53 LustreError: 32470:0:(osp_sync.c:584:osp_sync_process_record()) Skipped 212 previous similar messages
          2012-11-14 17:29:53 Lustre: Skipped 213 previous similar messages
          2012-11-14 17:30:18 Lustre: ls1-OST010e-osc-MDT0000: Connection restored to ls1-OST010e (at 172.20.2.70@o2ib500)
          2012-11-14 17:30:18 LustreError: 32740:0:(osp_sync.c:584:osp_sync_process_record()) processed all old entries: 0xdcc:1
          2012-11-14 17:30:18 LustreError: 32740:0:(osp_sync.c:584:osp_sync_process_record()) Skipped 70 previous similar messages
          
          morrone Christopher Morrone (Inactive) added a comment - Console messages after boot on our test filesystem yesterday: 2012-11-14 17:20:03 Mounting grove-mds1/mgs on /mnt/lustre/local/ls1-MGS0000 2012-11-14 17:20:03 Lustre: Lustre: Build Version: 2.3.54-6chaos-6chaos--PRISTINE-2.6.32-220.23.1.2chaos.ch5.x86_64 2012-11-14 17:20:05 Mounting grove-mds1/mdt0 on /mnt/lustre/local/ls1-MDT0000 2012-11-14 17:20:05 Lustre: Found index 0 for ls1-MDT0000, updating log 2012-11-14 17:20:05 LustreError: 31856:0:(mgc_request.c:248:do_config_log_add()) failed processing sptlrpc log: -2 2012-11-14 17:20:05 LustreError: 31859:0:(sec_config.c:1024:sptlrpc_target_local_copy_conf()) missing llog context 2012-11-14 17:20:09 Lustre: ls1-MDT0000: Temporarily refusing client connection from 0@lo 2012-11-14 17:20:09 LustreError: 11-0: ls1-MDT0000-osp-MDT0000: Communicating with 0@lo, operation mds_connect failed with -11 2012-11-14 17:20:09 LustreError: 31856:0:(mdd_lfsck.c:323:mdd_lfsck_setup()) ls1-MDD0000: Lustre LFSCK unsupported on this device. 2012-11-14 17:20:09 Lustre: 31856:0:(fld_index.c:319:fld_index_init()) srv-ls1-MDT0000: File "fld" doesn't support range lookup, using stub. DNE and FIDs on OST will not work with this backend 2012-11-14 17:20:10 grove-mds1 login: Lustre: ls1-MDT0000: Will be in recovery for at least 5:00, or until 3 clients reconnect. 2012-11-14 17:20:34 LustreError: 11-0: ls1-MDT0000-osp-MDT0000: Communicating with 0@lo, operation mds_connect failed with -11 2012-11-14 17:20:59 LustreError: 11-0: ls1-MDT0000-osp-MDT0000: Communicating with 0@lo, operation mds_connect failed with -11 2012-11-14 17:21:49 LustreError: 11-0: ls1-MDT0000-osp-MDT0000: Communicating with 0@lo, operation mds_connect failed with -11 2012-11-14 17:22:14 LustreError: 11-0: ls1-MDT0000-osp-MDT0000: Communicating with 0@lo, operation mds_connect failed with -11 2012-11-14 17:22:58 grove-mds1 login: LustreError: 11-0: ls1-MDT0000-osp-MDT0000: Communicating with 0@lo, operation mds_connect failed with -11 2012-11-14 17:23:29 LustreError: 11-0: ls1-MDT0000-osp-MDT0000: Communicating with 0@lo, operation mds_connect failed with -11 2012-11-14 17:23:42 INFO: task tgt_recov:656 blocked for more than 120 seconds. 2012-11-14 17:23:42 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. 2012-11-14 17:23:42 tgt_recov D 000000000000000d 0 656 2 0x00000000 2012-11-14 17:23:42 ffff882f89179e10 0000000000000046 0000000000000000 ffffffff81052026 2012-11-14 17:23:42 ffff882f89179da0 ffff882fcdd12ae0 ffff882f89179da0 ffffffff8104da6d 2012-11-14 17:23:42 ffff882f89177af8 ffff882f89179fd8 000000000000f4e8 ffff882f89177af8 2012-11-14 17:23:42 Call Trace: 2012-11-14 17:23:42 [<ffffffff81052026>] ? enqueue_task+0x66/0x80 2012-11-14 17:23:42 [<ffffffff8104da6d>] ? check_preempt_curr+0x6d/0x90 2012-11-14 17:23:42 [<ffffffffa087b330>] ? check_for_clients+0x0/0x90 [ptlrpc] 2012-11-14 17:23:42 [<ffffffffa087cd25>] target_recovery_overseer+0x95/0x250 [ptlrpc] 2012-11-14 17:23:42 [<ffffffffa087b130>] ? exp_connect_healthy+0x0/0x20 [ptlrpc] 2012-11-14 17:23:42 [<ffffffff81091090>] ? autoremove_wake_function+0x0/0x40 2012-11-14 17:23:42 [<ffffffffa0883f8e>] target_recovery_thread+0x58e/0x19d0 [ptlrpc] 2012-11-14 17:23:42 [<ffffffff8106ed2f>] ? do_exit+0x5af/0x870 2012-11-14 17:23:42 [<ffffffffa0883a00>] ? target_recovery_thread+0x0/0x19d0 [ptlrpc] 2012-11-14 17:23:42 [<ffffffff8100c14a>] child_rip+0xa/0x20 2012-11-14 17:23:42 [<ffffffffa0883a00>] ? target_recovery_thread+0x0/0x19d0 [ptlrpc] 2012-11-14 17:23:42 [<ffffffffa0883a00>] ? target_recovery_thread+0x0/0x19d0 [ptlrpc] 2012-11-14 17:23:42 [<ffffffff8100c140>] ? child_rip+0x0/0x20 2012-11-14 17:24:01 Lustre: Found index 130 for ls1-OST0082, updating log 2012-11-14 17:24:01 Lustre: Found index 81 for ls1-OST0051, updating log 2012-11-14 17:24:01 Lustre: Skipped 3 previous similar messages 2012-11-14 17:24:02 Lustre: Found index 33 for ls1-OST0021, updating log 2012-11-14 17:24:02 Lustre: Skipped 4 previous similar messages 2012-11-14 17:24:05 Lustre: Found index 354 for ls1-OST0162, updating log 2012-11-14 17:24:05 Lustre: Skipped 17 previous similar messages 2012-11-14 17:24:09 Lustre: Found index 357 for ls1-OST0165, updating log 2012-11-14 17:24:09 Lustre: Skipped 50 previous similar messages 2012-11-14 17:24:17 Lustre: Found index 150 for ls1-OST0096, updating log 2012-11-14 17:24:17 Lustre: Skipped 126 previous similar messages 2012-11-14 17:24:19 LustreError: 11-0: ls1-MDT0000-osp-MDT0000: Communicating with 0@lo, operation mds_connect failed with -11 2012-11-14 17:24:33 Lustre: Found index 280 for ls1-OST0118, updating log 2012-11-14 17:24:33 Lustre: Skipped 31 previous similar messages 2012-11-14 17:24:51 grove-mds1 login: LustreError: 11-0: ls1-MDT0000-osp-MDT0000: Communicating with 0@lo, operation mds_connect failed with -11 2012-11-14 17:25:14 LustreError: Skipped 1 previous similar message 2012-11-14 17:25:18 Lustre: ls1-MDT0000: Recovery over after 5:00, of 3 clients 2 recovered and 1 was evicted. 2012-11-14 17:26:29 LustreError: 11-0: ls1-MDT0000-osp-MDT0000: Communicating with 0@lo, operation mds_connect failed with -11 2012-11-14 17:26:29 LustreError: Skipped 2 previous similar messages 2012-11-14 17:28:59 LustreError: 11-0: ls1-MDT0000-osp-MDT0000: Communicating with 0@lo, operation mds_connect failed with -11 2012-11-14 17:28:59 LustreError: Skipped 5 previous similar messages 2012-11-14 17:29:03 Lustre: ls1-OST0031-osc-MDT0000: Connection restored to ls1-OST0031 (at 172.20.1.49@o2ib500) 2012-11-14 17:29:03 LustreError: 32077:0:(osp_sync.c:584:osp_sync_process_record()) processed all old entries: 0xcef:1 2012-11-14 17:29:03 Lustre: ls1-OST0032-osc-MDT0000: Connection restored to ls1-OST0032 (at 172.20.1.50@o2ib500) 2012-11-14 17:29:03 LustreError: 32080:0:(osp_sync.c:584:osp_sync_process_record()) processed all old entries: 0xcf0:1 2012-11-14 17:29:06 Lustre: ls1-OST0092-osc-MDT0000: Connection restored to ls1-OST0092 (at 172.20.1.146@o2ib500) 2012-11-14 17:29:06 LustreError: 32368:0:(osp_sync.c:584:osp_sync_process_record()) processed all old entries: 0xd50:1 2012-11-14 17:29:06 LustreError: 32368:0:(osp_sync.c:584:osp_sync_process_record()) Skipped 6 previous similar messages 2012-11-14 17:29:06 Lustre: Skipped 6 previous similar messages 2012-11-14 17:29:24 Lustre: ls1-OST002e-osc-MDT0000: Connection restored to ls1-OST002e (at 172.20.1.46@o2ib500) 2012-11-14 17:29:24 LustreError: 32068:0:(osp_sync.c:584:osp_sync_process_record()) processed all old entries: 0xcec:1 2012-11-14 17:29:24 LustreError: 32068:0:(osp_sync.c:584:osp_sync_process_record()) Skipped 7 previous similar messages 2012-11-14 17:29:24 Lustre: Skipped 7 previous similar messages 2012-11-14 17:29:53 Lustre: ls1-OST00b4-osc-MDT0000: Connection restored to ls1-OST00b4 (at 172.20.1.180@o2ib500) 2012-11-14 17:29:53 LustreError: 32470:0:(osp_sync.c:584:osp_sync_process_record()) processed all old entries: 0xd72:1 2012-11-14 17:29:53 LustreError: 32470:0:(osp_sync.c:584:osp_sync_process_record()) Skipped 212 previous similar messages 2012-11-14 17:29:53 Lustre: Skipped 213 previous similar messages 2012-11-14 17:30:18 Lustre: ls1-OST010e-osc-MDT0000: Connection restored to ls1-OST010e (at 172.20.2.70@o2ib500) 2012-11-14 17:30:18 LustreError: 32740:0:(osp_sync.c:584:osp_sync_process_record()) processed all old entries: 0xdcc:1 2012-11-14 17:30:18 LustreError: 32740:0:(osp_sync.c:584:osp_sync_process_record()) Skipped 70 previous similar messages

          hm, can you describe the case with more details please? I think we fixed the major source of these messages. basically a regular mount should not cause this.
          I'm not saying the message should stay as is, but I'd like to make sure this is not a side effect of some misbehavior.

          bzzz Alex Zhuravlev added a comment - hm, can you describe the case with more details please? I think we fixed the major source of these messages. basically a regular mount should not cause this. I'm not saying the message should stay as is, but I'd like to make sure this is not a side effect of some misbehavior.
          pjones Peter Jones added a comment -

          Alex

          Can you please triage and assign this one?

          Thanks

          Peter

          pjones Peter Jones added a comment - Alex Can you please triage and assign this one? Thanks Peter

          People

            bzzz Alex Zhuravlev
            prakash Prakash Surya (Inactive)
            Votes:
            0 Vote for this issue
            Watchers:
            5 Start watching this issue

            Dates

              Created:
              Updated:
              Resolved: