[LU-10592] sanity test_300h: create files failed

• Status: Open
• Project: Lustre
• Type: Bug
• Priority: Minor
• Reporter: Olaf Faaland
• Assignee: Lai Siyao
• Resolution: Unresolved

Environment

centos7
master
4 MDTs
DNE

• Severity: 3

Description

== sanity test 300h: check default striped directory for striped directory
checking striped_dir 4 1
warning: '-c' deprecated, use '-T' instead
open(/mnt/lustre/d300h.sanity/striped_dir/f-0) error: Permission denied
total: 0 open/close in 0.01 seconds: 0.00 ops/second

Appeared during sanity test run by autotest:
https://testing.hpdd.intel.com/test_sessions/b2b996ad-c684-4d8c-bd32-311b15d64bb5

Patch being tested fixed an autoconf bug re: GSS, unrelated to the code involved here.
Code tested was master (29d84d6) + one patch (4d35ca9).

Issue Links

• is related to: LU-10753 sanity test 300c fails with 'create 5...

Comments

[Olaf Faaland]

Based on

checking striped_dir 4 1

in the test output, the directory is striped across all 4 MDTs, starting index is 1.

The ldlm lock lock request reply came back ELDLM_LOCK_ABORTED

00000080:00200000:0.0:1517372397.928921:0:18125:0:(namei.c:612:ll_lookup_it()) VFS Op:name=f-0, dir=[0x200002344:0xaa6:0x0](ffff880035edb210), intent=open|creat
00000002:00010000:0.0:1517372397.928925:0:18125:0:(mdc_locks.c:1157:mdc_intent_lock()) (name: f-0,[0x2c0000bd6:0x19:0x0]) in obj [0x2c0000bd4:0x4:0x0], intent: open|creat flags 0100103
00010000:00010000:0.0:1517372397.928936:0:18125:0:(ldlm_lock.c:746:ldlm_lock_addref_internal_nolock()) ### ldlm_lock_addref(CW) ns: ?? lock: ffff880064906fc0/0xabd0817407e0a8ed lrc: 3/0,1 mode: --/CW res: ?? rrc=?? type: ??? flags: 0x10000000000000 nid: local remote: 0x0 expref: -99 pid: 18125 timeout: 0 lvb_type: 0
00010000:00010000:0.0:1517372397.928938:0:18125:0:(ldlm_request.c:942:ldlm_cli_enqueue()) ### client-side enqueue START, flags 0x1000 ns: lustre-MDT0003-mdc-ffff8800649f3000 lock: ffff880064906fc0/0xabd0817407e0a8ed lrc: 3/0,1 mode: --/CW res: [0x2c0000bd4:0x4:0x0].0x0 bits 0x1/0x0 rrc: 2 type: IBT flags: 0x0 nid: local remote: 0x0 expref: -99 pid: 18125 timeout: 0 lvb_type: 0
00010000:00010000:0.0:1517372397.928942:0:18125:0:(ldlm_request.c:1014:ldlm_cli_enqueue()) ### sending request ns: lustre-MDT0003-mdc-ffff8800649f3000 lock: ffff880064906fc0/0xabd0817407e0a8ed lrc: 3/0,1 mode: --/CW res: [0x2c0000bd4:0x4:0x0].0x0 bits 0x1/0x0 rrc: 2 type: IBT flags: 0x0 nid: local remote: 0x0 expref: -99 pid: 18125 timeout: 0 lvb_type: 0
00000100:00100000:0.0:1517372397.928948:0:18125:0:(client.c:1602:ptlrpc_send_new_req()) Sending RPC pname:cluuid:pid:xid:nid:opc createmany:7a726210-355e-8b2f-cdf8-bad9267d68d7:18125:1591077819788496:10.9.6.222@tcp:101
00000100:00100000:0.0:1517372397.928973:0:18125:0:(client.c:2321:ptlrpc_set_wait()) set ffff8800414c0b00 going to sleep for 6 seconds
00000100:00100000:0.0:1517372397.938198:0:18125:0:(client.c:2027:ptlrpc_check_set()) Completed RPC pname:cluuid:pid:xid:nid:opc createmany:7a726210-355e-8b2f-cdf8-bad9267d68d7:18125:1591077819788496:10.9.6.222@tcp:101
00010000:00010000:0.0:1517372397.938201:0:18125:0:(ldlm_request.c:587:ldlm_cli_enqueue_fini()) ### client-side enqueue END (ABORTED) ns: lustre-MDT0003-mdc-ffff8800649f3000 lock: ffff880064906fc0/0xabd0817407e0a8ed lrc: 4/0,1 mode: --/CW res: [0x2c0000bd4:0x4:0x0].0x0 bits 0x1/0x0 rrc: 2 type: IBT flags: 0x0 nid: local remote: 0x0 expref: -99 pid: 18125 timeout: 0 lvb_type: 0
00010000:00010000:0.0:1517372397.938205:0:18125:0:(ldlm_request.c:533:failed_lock_cleanup()) ### setting FL_LOCAL_ONLY | LDLM_FL_FAILED | LDLM_FL_ATOMIC_CB | LDLM_FL_CBPENDING ns: lustre-MDT0003-mdc-ffff8800649f3000 lock: ffff880064906fc0/0xabd0817407e0a8ed lrc: 4/0,1 mode: --/CW res: [0x2c0000bd4:0x4:0x0].0x0 bits 0x1/0x0 rrc: 2 type: IBT flags: 0x206400000000 nid: local remote: 0x0 expref: -99 pid: 18125 timeout: 0 lvb_type: 0
00010000:00010000:0.0:1517372397.938208:0:18125:0:(ldlm_lock.c:800:ldlm_lock_decref_internal_nolock()) ### ldlm_lock_decref(CW) ns: ?? lock: ffff880064906fc0/0xabd0817407e0a8ed lrc: 4/0,1 mode: --/CW res: ?? rrc=?? type: ??? flags: 0x10206400000000 nid: local remote: 0x0 expref: -99 pid: 18125 timeout: 0 lvb_type: 0
00010000:00010000:0.0:1517372397.938210:0:18125:0:(ldlm_lock.c:856:ldlm_lock_decref_internal()) ### final decref done on cbpending lock ns: ?? lock: ffff880064906fc0/0xabd0817407e0a8ed lrc: 3/0,0 mode: --/CW res: ?? rrc=?? type: ??? flags: 0x10206400000000 nid: local remote: 0x0 expref: -99 pid: 18125 timeout: 0 lvb_type: 0
00010000:00010000:0.0:1517372397.938211:0:18125:0:(ldlm_lockd.c:1597:ldlm_handle_bl_callback()) ### client blocking AST callback handler ns: lustre-MDT0003-mdc-ffff8800649f3000 lock: ffff880064906fc0/0xabd0817407e0a8ed lrc: 4/0,0 mode: --/CW res: [0x2c0000bd4:0x4:0x0].0x0 bits 0x1/0x0 rrc: 2 type: IBT flags: 0x206400000000 nid: local remote: 0x0 expref: -99 pid: 18125 timeout: 0 lvb_type: 0
00010000:00010000:0.0:1517372397.938213:0:18125:0:(ldlm_lockd.c:1610:ldlm_handle_bl_callback()) Lock ffff880064906fc0 already unused, calling callback (ffffffffc0c503c0)
00010000:00010000:0.0:1517372397.938215:0:18125:0:(ldlm_request.c:1054:ldlm_cli_cancel_local()) ### client-side cancel ns: lustre-MDT0003-mdc-ffff8800649f3000 lock: ffff880064906fc0/0xabd0817407e0a8ed lrc: 5/0,0 mode: --/CW res: [0x2c0000bd4:0x4:0x0].0x0 bits 0x1/0x0 rrc: 2 type: IBT flags: 0x20e400000000 nid: local remote: 0x0 expref: -99 pid: 18125 timeout: 0 lvb_type: 0
00010000:00010000:0.0:1517372397.938217:0:18125:0:(ldlm_request.c:1067:ldlm_cli_cancel_local()) not sending request (at caller's instruction)
00010000:00010000:0.0:1517372397.938218:0:18125:0:(ldlm_lockd.c:1619:ldlm_handle_bl_callback()) ### client blocking callback handler END ns: lustre-MDT0003-mdc-ffff8800649f3000 lock: ffff880064906fc0/0xabd0817407e0a8ed lrc: 3/0,0 mode: --/CW res: [0x2c0000bd4:0x4:0x0].0x0 bits 0x1/0x0 rrc: 2 type: IBT flags: 0x4a0f400000000 nid: local remote: 0x0 expref: -99 pid: 18125 timeout: 0 lvb_type: 0
00010000:00010000:0.0:1517372397.938221:0:18125:0:(ldlm_lock.c:199:ldlm_lock_put()) ### final lock_put on destroyed lock, freeing it. ns: lustre-MDT0003-mdc-ffff8800649f3000 lock: ffff880064906fc0/0xabd0817407e0a8ed lrc: 0/0,0 mode: --/CW res: [0x2c0000bd4:0x4:0x0].0x0 bits 0x1/0x0 rrc: 2 type: IBT flags: 0x4a0f400000000 nid: local remote: 0x0 expref: -99 pid: 18125 timeout: 0 lvb_type: 0
00000002:00100000:0.0:1517372397.938226:0:18125:0:(mdc_locks.c:605:mdc_finish_enqueue()) @@@ op: 3 disposition: 17, status: -13  req@ffff88007b626d00 x1591077819788496/t0(0) o101->lustre-MDT0003-mdc-ffff8800649f3000@10.9.6.222@tcp:12/10 lens 880/544 e 0 to 0 dl 1517372404 ref 1 fl Complete:R/0/0 rc 301/301
00000080:00200000:0.0:1517372397.938237:0:18125:0:(namei.c:1017:ll_create_it()) VFS Op:name=f-0, dir=[0x200002344:0xaa6:0x0](ffff880035edb210), intent=open|creat
00000400:00000080:1.0:1517372398.185172:0:18237:0:(module.c:121:libcfs_ioctl()) libcfs ioctl cmd 3221775648
00000001:02000400:1.0:1517372398.185177:0:18237:0:(debug.c:500:libcfs_debug_mark_buffer()) DEBUG MARKER: /usr/sbin/lctl mark  sanity test_300h: @@@@@@ FAIL: create files failed 

[Peter Jones]

Lai

What do you advise here?

Peter