Skip site navigation (1)Skip section navigation (2)
Date:      Wed, 19 Aug 2020 17:40:59 +0000
From:      bugzilla-noreply@freebsd.org
To:        bugs@FreeBSD.org
Subject:   [Bug 248757] panic: waiting too long for pmc to be free
Message-ID:  <bug-248757-227@https.bugs.freebsd.org/bugzilla/>

next in thread | raw e-mail | index | archive | help
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=3D248757

            Bug ID: 248757
           Summary: panic: waiting too long for pmc to be free
           Product: Base System
           Version: CURRENT
          Hardware: amd64
                OS: Any
            Status: New
          Severity: Affects Only Me
          Priority: ---
         Component: kern
          Assignee: bugs@FreeBSD.org
          Reporter: luporl@FreeBSD.org

When executing the commands below, sometimes the system panics:

stress -c 1 -t 10 &
pmcstat -t stress -p mem_load_retired.l2_miss sleep 3

panic: [pmc,2749] (ri17, rc1) waiting too long for pmc to be free=20=20=20=
=20=20=20=20=20=20=20=20=20=20=20
cpuid =3D 2
time =3D 1597858367
KDB: stack backtrace:
db_trace_self_wrapper() at db_trace_self_wrapper+0x2b/frame 0xfffffe005fc9a=
760=20
vpanic() at vpanic+0x182/frame 0xfffffe005fc9a7b0=20=20=20=20=20=20=20=20=
=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20
panic() at panic+0x43/frame 0xfffffe005fc9a810=20=20=20=20=20=20=20=20=20=
=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20
pmc_wait_for_pmc_idle() at pmc_wait_for_pmc_idle+0xa2/frame 0xfffffe005fc9a=
840=20
pmc_release_pmc_descriptor() at pmc_release_pmc_descriptor+0x204/frame
0xfffffe0
pmc_syscall_handler() at pmc_syscall_handler+0x4be/frame 0xfffffe005fc9a9d0=
=20=20=20=20
amd64_syscall() at amd64_syscall+0x140/frame 0xfffffe005fc9aaf0=20=20=20=20=
=20=20=20=20=20=20=20=20=20=20=20=20
fast_syscall_common() at fast_syscall_common+0xf8/frame 0xfffffe005fc9aaf0=
=20=20=20=20=20
--- syscall (0, FreeBSD ELF64, nosys), rip =3D 0x800a8a96a, rsp =3D
0x7fffffffe368,-
KDB: enter: panic
[ thread pid 1852 tid 100126 ]
Stopped at      kdb_enter+0x37: movq    $0,0x10bc706(%rip)=20=20=20=20=20=
=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20=20
db>

I'm running -CURRENT on an amd64 VM (qemu with kvm).
I've performed several different tests with pmcstat and stress and got no
panics.

--=20
You are receiving this mail because:
You are the assignee for the bug.=



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?bug-248757-227>