PFL known issues tracking ticket (LU-9349)

[LU-9380] sanity test_27y: lod_comp_ost_in_use() ASSERTION(inuse->op_count < inuse->op_size) failed Created: 21/Apr/17  Updated: 02/May/17  Resolved: 02/May/17

Status: Resolved
Project: Lustre
Component/s: None
Affects Version/s: Lustre 2.10.0
Fix Version/s: None

Type: Technical task Priority: Critical
Reporter: Maloo Assignee: Zhenyu Xu
Resolution: Duplicate Votes: 0
Labels: None

Issue Links:
Duplicate
duplicates LU-9359 sanity test_27p: /mnt/lustre/d27p.san... Resolved
Related
is related to LU-8998 Progressive File Layout (PFL) Resolved
Rank (Obsolete): 9223372036854775807

 Description   

This issue was created by maloo for Andreas Dilger <andreas.dilger@intel.com>

This issue relates to the following test suite run: https://testing.hpdd.intel.com/test_sets/c2b63c9e-263d-11e7-b742-5254006e85c2
while testing https://review.whamcloud.com/26706

The sub-test test_27y failed with the following error in the MDS log:
https://testing.hpdd.intel.com/test_logs/c3d92a5a-263d-11e7-b742-5254006e85c2/show_text

[ 1624.276745] LustreError: ASSERTION(inuse->op_count < inuse->op_size) failed: 
[ 1624.278892] LustreError: 5262:0:(lod_qos.c:857:lod_comp_ost_in_use()) LBUG
[ 1624.280618] Pid: 5262, comm: mdt00_000
[ 1624.282082] 
[ 1624.282082] Call Trace:
[ 1624.284606]  libcfs_debug_dumpstack+0x53/0x80 [libcfs]
[ 1624.286283]  lbug_with_loc+0x41/0xb0 [libcfs]
[ 1624.287932]  lod_env_info.part.10+0x0/0x36 [lod]
[ 1624.289596]  lod_alloc_rr.constprop.18+0xf1e/0xff0 [lod]
[ 1624.291344]  lod_qos_prep_create+0x12a9/0x17d0 [lod]
[ 1624.294781]  lod_prepare_create+0x2ab/0x380 [lod]
[ 1624.296429]  lod_declare_striped_object+0x1ee/0x970 [lod]
[ 1624.298281]  lod_declare_xattr_set+0x221/0xa30 [lod]
[ 1624.299993]  mdd_create_data+0x487/0x720 [mdd]
[ 1624.301726]  mdt_mfd_open+0xbc3/0xe70 [mdt]
[ 1624.303386]  mdt_finish_open+0x49b/0x690 [mdt]
[ 1624.305112]  mdt_reint_open+0x179c/0x31a0 [mdt]
[ 1624.313705]  mdt_reint_rec+0x80/0x210 [mdt]
[ 1624.315362]  mdt_reint_internal+0x5b2/0x980 [mdt]
[ 1624.316977]  mdt_intent_reint+0x162/0x430 [mdt]
[ 1624.318633]  mdt_intent_policy+0x43e/0xc30 [mdt]
[ 1624.320309]  ldlm_lock_enqueue+0x387/0x970 [ptlrpc]
[ 1624.321921]  ldlm_handle_enqueue0+0x9c3/0x1680 [ptlrpc]
[ 1624.325217]  tgt_enqueue+0x62/0x210 [ptlrpc]
[ 1624.326758]  tgt_request_handle+0x915/0x1320 [ptlrpc]
[ 1624.328334]  ptlrpc_server_handle_request+0x21b/0xa90 [ptlrpc]
[ 1624.334546]  ptlrpc_main+0xaa0/0x1de0 [ptlrpc]

Info required for matching: sanity 27y



 Comments   
Comment by Zhenyu Xu [ 24/Apr/17 ]

https://review.whamcloud.com/#/c/26706/4 contains the fix.

This patch fixes the misunderstanding of ost_pool::op->size, it indicates the buffer size allocated instead of the array count. Another issue fixed is that in lod_alloc_qos(), only fill in the ost inused array when the lod_qos_declare_object_on() succeeds.

Comment by Peter Jones [ 02/May/17 ]

IIUC this is fixed by the landing of LU-9359

Generated at Sat Feb 10 02:25:41 UTC 2024 using Jira 9.4.14#940014-sha1:734e6822bbf0d45eff9af51f82432957f73aa32c.