[LU-8704] RPC sent inside mdd_create transaction. Created: 13/Oct/16  Updated: 01/May/23

Status: Open
Project: Lustre
Component/s: None
Affects Version/s: Lustre 2.9.0
Fix Version/s: None

Type: Bug Priority: Major
Reporter: Di Wang Assignee: Alex Zhuravlev
Resolution: Unresolved Votes: 0
Labels: None

Issue Links:
Related
is related to LU-8250 MDT recovery stalled on secondary node Resolved
Severity: 3
Rank (Obsolete): 9223372036854775807

 Description   

We should avoid sending RPC inside the transaction.

13:55:02:[  379.880842] Lustre: DEBUG MARKER: == sanity test 2: mkdir; touch; rmdir; check file ==================================================== 13:54:59 (1476305699)
13:55:02:[  380.160834] LustreError: 6841:0:(client.c:2881:ptlrpc_queue_wait()) ASSERTION( get_current()->journal_info == ((void *)0) ) failed: 
13:55:02:[  380.170698] LustreError: 6841:0:(client.c:2881:ptlrpc_queue_wait()) LBUG
13:55:02:[  380.174895] Pid: 6841, comm: mdt00_001
13:55:02:[  380.176601] 
13:55:02:[  380.176601] Call Trace:
13:55:02:[  380.179634]  [<ffffffffa06ba7d3>] libcfs_debug_dumpstack+0x53/0x80 [libcfs]
13:55:02:[  380.184449]  [<ffffffffa06bad75>] lbug_with_loc+0x45/0xc0 [libcfs]
13:55:02:[  380.186288]  [<ffffffffa0a1310c>] ptlrpc_queue_wait+0x20c/0x270 [ptlrpc]
13:55:02:[  380.188200]  [<ffffffffa06934e4>] fld_client_rpc+0x104/0x530 [fld]
13:55:02:[  380.190107]  [<ffffffffa069827f>] fld_server_lookup+0x15f/0x320 [fld]
13:55:02:[  380.191885]  [<ffffffffa0e4fdf7>] lod_fld_lookup+0x327/0x510 [lod]
13:55:02:[  380.193825]  [<ffffffffa0e577dc>] lod_generate_and_set_lovea+0x40c/0x810 [lod]
13:55:02:[  380.195666]  [<ffffffffa0e6be0e>] lod_striping_create+0x19e/0x1e0 [lod]
13:55:02:[  380.197640]  [<ffffffffa0e6c032>] lod_object_create+0x1e2/0x200 [lod]
13:55:02:[  380.199501]  [<ffffffffa0ed04d5>] mdd_object_create_internal+0xb5/0x280 [mdd]
13:55:02:[  380.201606]  [<ffffffffa0ebce75>] mdd_object_create+0x75/0xb80 [mdd]
13:55:02:[  380.203426]  [<ffffffffa0ec7605>] ? mdd_declare_create+0x535/0xdf0 [mdd]
13:55:02:[  380.205406]  [<ffffffffa0ec8b2e>] mdd_create+0xc6e/0x1270 [mdd]
13:55:02:[  380.207108]  [<ffffffffa0da9fcb>] mdt_reint_open+0x223b/0x31a0 [mdt]
13:55:02:[  380.208957]  [<ffffffffa0d9f480>] mdt_reint_rec+0x80/0x210 [mdt]
13:55:02:[  380.210619]  [<ffffffffa0d81da2>] mdt_reint_internal+0x5b2/0x9b0 [mdt]
13:55:02:[  380.212432]  [<ffffffffa0d82302>] mdt_intent_reint+0x162/0x430 [mdt]
13:55:02:[  380.214072]  [<ffffffffa0d8cb7c>] mdt_intent_policy+0x5bc/0xbb0 [mdt]
13:55:02:[  380.215883]  [<ffffffffa09d01e7>] ldlm_lock_enqueue+0x387/0x970 [ptlrpc]
13:55:02:[  380.217555]  [<ffffffffa09f9303>] ldlm_handle_enqueue0+0x9c3/0x1680 [ptlrpc]
13:55:02:[  380.219414]  [<ffffffffa0a20f50>] ? lustre_swab_ldlm_request+0x0/0x30 [ptlrpc]
13:55:02:[  380.221180]  [<ffffffffa0a79c12>] tgt_enqueue+0x62/0x210 [ptlrpc]
13:55:02:[  380.222948]  [<ffffffffa0a7e075>] tgt_request_handle+0x915/0x1320 [ptlrpc]
13:55:02:[  380.224791]  [<ffffffffa0a29feb>] ptlrpc_server_handle_request+0x21b/0xa90 [ptlrpc]
13:55:02:[  380.226730]  [<ffffffffa0a27ba8>] ? ptlrpc_wait_event+0x98/0x340 [ptlrpc]
13:55:02:[  380.228547]  [<ffffffff810b8952>] ? default_wake_function+0x12/0x20
13:55:02:[  380.230351]  [<ffffffff810af0b8>] ? __wake_up_common+0x58/0x90
13:55:02:[  380.231951]  [<ffffffffa0a2e0a0>] ptlrpc_main+0xaa0/0x1de0 [ptlrpc]
13:55:02:[  380.233724]  [<ffffffffa0a2d600>] ? ptlrpc_main+0x0/0x1de0 [ptlrpc]
13:55:02:[  380.235241]  [<ffffffff810a5b8f>] kthread+0xcf/0xe0
13:55:02:[  380.236822]  [<ffffffff810a5ac0>] ? kthread+0x0/0xe0
13:55:02:[  380.238250]  [<ffffffff81646b98>] ret_from_fork+0x58/0x90
13:55:02:[  380.239859]  [<ffffffff810a5ac0>] ? kthread+0x0/0xe0


 Comments   
Comment by Gerrit Updater [ 16/Oct/16 ]

wangdi (di.wang@intel.com) uploaded a new patch: http://review.whamcloud.com/23188
Subject: LU-8704 lod: cache FLD entries in declare striping create
Project: fs/lustre-release
Branch: master
Current Patch Set: 1
Commit: be6fde5933d86f2ece4f433142fe8190929fa833

Comment by Joseph Gmitter (Inactive) [ 18/Oct/16 ]

A second patch is at http://review.whamcloud.com/#/c/23111/

Comment by Gerrit Updater [ 21/Aug/21 ]

"Alex Zhuravlev <bzzz@whamcloud.com>" uploaded a new patch: https://review.whamcloud.com/44720
Subject: LU-8704 osp: update local fldb cache
Project: fs/lustre-release
Branch: master
Current Patch Set: 1
Commit: 41d474cf1c6262610a6e4bc54248573231829c68

Comment by Gerrit Updater [ 01/May/23 ]

"Oleg Drokin <green@whamcloud.com>" merged in patch https://review.whamcloud.com/c/fs/lustre-release/+/44720/
Subject: LU-8704 osp: update local fldb cache
Project: fs/lustre-release
Branch: master
Current Patch Set:
Commit: 7278b74abf2eb2233262973cea07b90c8c98537f

Generated at Sat Feb 10 02:19:50 UTC 2024 using Jira 9.4.14#940014-sha1:734e6822bbf0d45eff9af51f82432957f73aa32c.