[LU-2542] interop 2.3.0<->2.1.3: sanity FAIL: test_118[fg] Must return error due to dropped pages

• Status: Resolved
• Project: Lustre
• Affects Version/s: Lustre 2.3.0
• Type: Bug
• Priority: Minor
• Reporter: Jay Lan (Inactive)
• Assignee: Nathaniel Clark
• Resolution: Not a Bug
• Labels: sles11

Environment

server: 2.1.3-1nasS, centos 6.3 2.6.32_279.2.1
client: 2.3.0-1nasC, sles11sp2 3.0.42_0.7.3

• Severity: 3

Description

Sanity test 118f and 118g failed:

== sanity test 118f: Simulate unrecoverable OSC side error =========================================== 16:50:28 (1356655828)
2+0 records in
2+0 records out
131072 bytes (131 kB) copied, 0.00567025 s, 23.1 MB/s
fail_loc=0x8000040a
sanity test_118f: @@@@@@ FAIL: Must return error due to dropped pages, rc=0
Trace dump:
= /usr/lib64/lustre/tests/test-framework.sh:3643:error_noexit()
= /usr/lib64/lustre/tests/test-framework.sh:3665:error()
= /usr/lib64/lustre/tests/sanity.sh:6168:test_118f()
= /usr/lib64/lustre/tests/test-framework.sh:3907:run_one()
= /usr/lib64/lustre/tests/test-framework.sh:3937:run_one_logged()
= /usr/lib64/lustre/tests/test-framework.sh:3765:run_test()
= /usr/lib64/lustre/tests/sanity.sh:6191:main()
Dumping lctl log to /var/acc-sm/test_logs/sanity.test_118f.*.1356655829.log
FAIL 118f (2s)

== sanity test 118g: Don't stay in wait if we got local -ENOMEM ===================================== 16:50:30 (1356655830)
2+0 records in
2+0 records out
131072 bytes (131 kB) copied, 0.00573784 s, 22.8 MB/s
fail_loc=0x406
fail_loc=0
sanity test_118g: @@@@@@ FAIL: Must return error due to dropped pages, rc=0
Trace dump:
= /usr/lib64/lustre/tests/test-framework.sh:3643:error_noexit()
= /usr/lib64/lustre/tests/test-framework.sh:3665:error()
= /usr/lib64/lustre/tests/sanity.sh:6205:test_118g()
= /usr/lib64/lustre/tests/test-framework.sh:3907:run_one()
= /usr/lib64/lustre/tests/test-framework.sh:3937:run_one_logged()
= /usr/lib64/lustre/tests/test-framework.sh:3765:run_test()
= /usr/lib64/lustre/tests/sanity.sh:6226:main()
Dumping lctl log to /var/acc-sm/test_logs/sanity.test_118g.*.1356655831.log
FAIL 118g (2s)

Comments

[Peter Jones]

Nathaniel

Could you please look into this one?

Thanks

Peter

[Nathaniel Clark]

Both tests seem to have a disconnect between the return value of multiop and what dmesg said happened. dmesg shows the correct errors happening on the lustre level "Write request failed with". This may be some issue with changes in the vfs layer of the kernel for sles11sp2.

[John Fuchs-Chesney (Inactive)]

Jay – any further action required on this?
If not, may I mark it as resolved?
Thanks,
~ jfc.

[Jay Lan (Inactive)]

Please close it. We have focused on 2.4.x and no problem in these
test environments.

[John Fuchs-Chesney (Inactive)]

Closed per direction of customer.