flaky test: TestUsernsCheckpoint

[lifubang]

I saw this happend many times in centos7.

=== RUN   TestUsernsCheckpoint
time="2024-05-07T10:08:51Z" level=warning msg="--- Quoting \"/tmp/TestUsernsCheckpoint611938415/003/criu-parent/dump.log\""
time="2024-05-07T10:08:51Z" level=warning msg="116:(09.514467) freezer.state=FREEZING"
time="2024-05-07T10:08:51Z" level=warning msg="117:(09.614644) freezer.state=FREEZING"
time="2024-05-07T10:08:51Z" level=warning msg="118:(09.714816) freezer.state=FREEZING"
time="2024-05-07T10:08:51Z" level=warning msg="119:(09.814957) freezer.state=FREEZING"
time="2024-05-07T10:08:51Z" level=warning msg="120:(09.915110) freezer.state=FREEZING"
time="2024-05-07T10:08:51Z" level=warning msg="121:(10.000432) Error (criu/cr-dump.c:1467): Timeout reached. Try to interrupt: 0"
time="2024-05-07T10:08:51Z" level=warning msg="122:(10.000563) freezer.state=FREEZING"
time="2024-05-07T10:08:51Z" level=warning msg="123:(10.000694) Error (compel/src/lib/infect.c:234): Unseizable non-zombie 9017 found, state D, err -1/10"
time="2024-05-07T10:08:51Z" level=warning msg="124:(10.000773) Unfreezing tasks into 1"
time="2024-05-07T10:08:51Z" level=warning msg="125:(10.000778) \tUnseizing 9017 into 1"
time="2024-05-07T10:08:51Z" level=warning msg="126:(10.000783) Error (compel/src/lib/infect.c:355): Unable to detach from 9017: No such process"
time="2024-05-07T10:08:51Z" level=warning msg="127:(10.000800) Writing image inventory (version 1)"
time="2024-05-07T10:08:51Z" level=warning msg="128:(10.000976) Error (criu/cr-dump.c:1581): Pre-dumping FAILED."
time="2024-05-07T10:08:51Z" level=warning msg=---
    checkpoint_test.go:115: === /tmp/TestUsernsCheckpoint611938415/003/criu-parent/dump.log ===
    checkpoint_test.go:115: (00.000052) Version: 3.16 (gitid 0)
    checkpoint_test.go:115: (00.000067) Running on cirrus-task-5639495050067968 Linux 3.10.0-1160.114.2.el7.x86_64 #1 SMP Wed Mar 20 15:54:52 UTC 2024 x86_64
    checkpoint_test.go:115: (00.000070) Would overwrite RPC settings with values from /etc/criu/runc.conf
    checkpoint_test.go:115: (00.000094) Loaded kdat cache from /run/criu/criu.kdat
    checkpoint_test.go:115: (00.000142) rlimit: RLIMIT_NOFILE unlimited for self
    checkpoint_test.go:115: (00.000148) Enforcing memory tracking for pre-dump.
    checkpoint_test.go:115: (00.000156) Enforcing tasks run after pre-dump.
    checkpoint_test.go:115: (00.000170) irmap: Searching irmap cache in work dir
    checkpoint_test.go:115: (00.000180) No irmap-cache image
    checkpoint_test.go:115: (00.000181) irmap: Searching irmap cache in parent
    checkpoint_test.go:115: (00.000185) No parent images directory provided
    checkpoint_test.go:115: (00.000187) irmap: No irmap cache
    checkpoint_test.go:115: (00.000205) cpu: x86_family 25 x86_vendor_id AuthenticAMD x86_model_id AMD EPYC 7B13
    checkpoint_test.go:115: (00.000210) cpu: fpu: xfeatures_mask 0x5 xsave_size 832 xsave_size_max 2440 xsaves_size 832
    checkpoint_test.go:115: (00.000213) cpu: fpu: x87 floating point registers     xstate_offsets      0 / 0      xstate_sizes    160 / 160   
    checkpoint_test.go:115: (00.000215) cpu: fpu: AVX registers                    xstate_offsets    576 / 576    xstate_sizes    256 / 256   
    checkpoint_test.go:115: (00.000217) cpu: fpu:1 fxsr:1 xsave:1 xsaveopt:1 xsavec:1 xgetbv1:1 xsaves:0
    checkpoint_test.go:115: (00.000338) Detected cgroup V1 freezer
    checkpoint_test.go:115: (00.000340) freezing processes: 100000 attempts with 100 ms steps
    checkpoint_test.go:115: (00.000351) freezer.state=THAWED
    checkpoint_test.go:115: (00.000358) freezer.state=FREEZING
    checkpoint_test.go:115: (00.100446) freezer.state=FREEZING
    checkpoint_test.go:115: (00.201766) freezer.state=FREEZING
    checkpoint_test.go:115: (00.301871) freezer.state=FREEZING
    checkpoint_test.go:115: (00.401990) freezer.state=FREEZING
    checkpoint_test.go:115: (00.502110) freezer.state=FREEZING
    checkpoint_test.go:115: (00.602214) freezer.state=FREEZING
    checkpoint_test.go:115: (00.702313) freezer.state=FREEZING
    checkpoint_test.go:115: (00.802425) freezer.state=FREEZING
    checkpoint_test.go:115: (00.902531) freezer.state=FREEZING
    checkpoint_test.go:115: (01.002635) freezer.state=FREEZING
    checkpoint_test.go:115: (01.102755) freezer.state=FREEZING
    checkpoint_test.go:115: (01.202870) freezer.state=FREEZING
    checkpoint_test.go:115: (01.303058) freezer.state=FREEZING
    checkpoint_test.go:115: (01.403208) freezer.state=FREEZING
    checkpoint_test.go:115: (01.503308) freezer.state=FREEZING
    checkpoint_test.go:115: (01.603429) freezer.state=FREEZING
    checkpoint_test.go:115: (01.703589) freezer.state=FREEZING
    checkpoint_test.go:115: (01.803726) freezer.state=FREEZING
    checkpoint_test.go:115: (01.903872) freezer.state=FREEZING
    checkpoint_test.go:115: (02.004022) freezer.state=FREEZING
    checkpoint_test.go:115: (02.104139) freezer.state=FREEZING
    checkpoint_test.go:115: (02.204270) freezer.state=FREEZING
    checkpoint_test.go:115: (02.304422) freezer.state=FREEZING
    checkpoint_test.go:115: (02.404578) freezer.state=FREEZING
    checkpoint_test.go:115: (02.504717) freezer.state=FREEZING
    checkpoint_test.go:115: (02.604860) freezer.state=FREEZING
    checkpoint_test.go:115: (02.704987) freezer.state=FREEZING
    checkpoint_test.go:115: (02.805144) freezer.state=FREEZING
    checkpoint_test.go:115: (02.905275) freezer.state=FREEZING
    checkpoint_test.go:115: (03.005410) freezer.state=FREEZING
    checkpoint_test.go:115: (03.105546) freezer.state=FREEZING
    checkpoint_test.go:115: (03.205676) freezer.state=FREEZING
    checkpoint_test.go:115: (03.305821) freezer.state=FREEZING
    checkpoint_test.go:115: (03.405941) freezer.state=FREEZING
    checkpoint_test.go:115: (03.506057) freezer.state=FREEZING
    checkpoint_test.go:115: (03.606181) freezer.state=FREEZING
    checkpoint_test.go:115: (03.706322) freezer.state=FREEZING
    checkpoint_test.go:115: (03.806446) freezer.state=FREEZING
    checkpoint_test.go:115: (03.906569) freezer.state=FREEZING
    checkpoint_test.go:115: (04.006738) freezer.state=FREEZING
    checkpoint_test.go:115: (04.106903) freezer.state=FREEZING
    checkpoint_test.go:115: (04.207032) freezer.state=FREEZING
    checkpoint_test.go:115: (04.307154) freezer.state=FREEZING
    checkpoint_test.go:115: (04.407273) freezer.state=FREEZING
    checkpoint_test.go:115: (04.507399) freezer.state=FREEZING
    checkpoint_test.go:115: (04.607502) freezer.state=FREEZING
    checkpoint_test.go:115: (04.707592) freezer.state=FREEZING
    checkpoint_test.go:115: (04.807698) freezer.state=FREEZING
    checkpoint_test.go:115: (04.907829) freezer.state=FREEZING
    checkpoint_test.go:115: (05.007957) freezer.state=FREEZING
    checkpoint_test.go:115: (05.108092) freezer.state=FREEZING
    checkpoint_test.go:115: (05.208199) freezer.state=FREEZING
    checkpoint_test.go:115: (05.308309) freezer.state=FREEZING
    checkpoint_test.go:115: (05.408418) freezer.state=FREEZING
    checkpoint_test.go:115: (05.508566) freezer.state=FREEZING
    checkpoint_test.go:115: (05.608724) freezer.state=FREEZING
    checkpoint_test.go:115: (05.708885) freezer.state=FREEZING
    checkpoint_test.go:115: (05.809035) freezer.state=FREEZING
    checkpoint_test.go:115: (05.909159) freezer.state=FREEZING
    checkpoint_test.go:115: (06.009283) freezer.state=FREEZING
    checkpoint_test.go:115: (06.109410) freezer.state=FREEZING
    checkpoint_test.go:115: (06.209537) freezer.state=FREEZING
    checkpoint_test.go:115: (06.309662) freezer.state=FREEZING
    checkpoint_test.go:115: (06.409787) freezer.state=FREEZING
    checkpoint_test.go:115: (06.509905) freezer.state=FREEZING
    checkpoint_test.go:115: (06.610031) freezer.state=FREEZING
    checkpoint_test.go:115: (06.710165) freezer.state=FREEZING
    checkpoint_test.go:115: (06.810288) freezer.state=FREEZING
    checkpoint_test.go:115: (06.910416) freezer.state=FREEZING
    checkpoint_test.go:115: (07.010552) freezer.state=FREEZING
    checkpoint_test.go:115: (07.110678) freezer.state=FREEZING
    checkpoint_test.go:115: (07.210806) freezer.state=FREEZING
    checkpoint_test.go:115: (07.310933) freezer.state=FREEZING
    checkpoint_test.go:115: (07.411069) freezer.state=FREEZING
    checkpoint_test.go:115: (07.511252) freezer.state=FREEZING
    checkpoint_test.go:115: (07.611415) freezer.state=FREEZING
    checkpoint_test.go:115: (07.711588) freezer.state=FREEZING
    checkpoint_test.go:115: (07.811742) freezer.state=FREEZING
    checkpoint_test.go:115: (07.911897) freezer.state=FREEZING
    checkpoint_test.go:115: (08.012029) freezer.state=FREEZING
    checkpoint_test.go:115: (08.112217) freezer.state=FREEZING
    checkpoint_test.go:115: (08.212392) freezer.state=FREEZING
    checkpoint_test.go:115: (08.312553) freezer.state=FREEZING
    checkpoint_test.go:115: (08.412734) freezer.state=FREEZING
    checkpoint_test.go:115: (08.512909) freezer.state=FREEZING
    checkpoint_test.go:115: (08.613067) freezer.state=FREEZING
    checkpoint_test.go:115: (08.713220) freezer.state=FREEZING
    checkpoint_test.go:115: (08.813373) freezer.state=FREEZING
    checkpoint_test.go:115: (08.913548) freezer.state=FREEZING
    checkpoint_test.go:115: (09.013704) freezer.state=FREEZING
    checkpoint_test.go:115: (09.113850) freezer.state=FREEZING
    checkpoint_test.go:115: (09.213999) freezer.state=FREEZING
    checkpoint_test.go:115: (09.314151) freezer.state=FREEZING
    checkpoint_test.go:115: (09.414305) freezer.state=FREEZING
    checkpoint_test.go:115: (09.514467) freezer.state=FREEZING
    checkpoint_test.go:115: (09.614644) freezer.state=FREEZING
    checkpoint_test.go:115: (09.714816) freezer.state=FREEZING
    checkpoint_test.go:115: (09.814957) freezer.state=FREEZING
    checkpoint_test.go:115: (09.915110) freezer.state=FREEZING
    checkpoint_test.go:115: (10.000432) Error (criu/cr-dump.c:1467): Timeout reached. Try to interrupt: 0
    checkpoint_test.go:115: (10.000563) freezer.state=FREEZING
    checkpoint_test.go:115: (10.000694) Error (compel/src/lib/infect.c:234): Unseizable non-zombie 9017 found, state D, err -1/10
    checkpoint_test.go:115: (10.000773) Unfreezing tasks into 1
    checkpoint_test.go:115: (10.000778) 	Unseizing 9017 into 1
    checkpoint_test.go:115: (10.000783) Error (compel/src/lib/infect.c:355): Unable to detach from 9017: No such process
    checkpoint_test.go:115: (10.000800) Writing image inventory (version 1)
    checkpoint_test.go:115: (10.000976) Error (criu/cr-dump.c:1581): Pre-dumping FAILED.
    checkpoint_test.go:115: === END ===
    checkpoint_test.go:119: criu failed: type PRE_DUMP errno 0
--- FAIL: TestUsernsCheckpoint (10.31s)