[linux-next:master] [perf target] 5ddf4c3a17: perf-sanity-tests.perf_record_tests.fail

[linux-next:master] [perf target] 5ddf4c3a17: perf-sanity-tests.perf_record_tests.fail

[kernel test robot]

Hello,

kernel test robot noticed "perf-sanity-tests.perf_record_tests.fail" on:

commit: 5ddf4c3a17dc499fcbaf35692bc894340062dee8 ("perf target: Separate parse_uid into its own function")
https://git.kernel.org/cgit/linux/kernel/git/next/linux-next.git master

[test failed on linux-next/master f817b6dd2b62d921a6cdc0a3ac599cd1851f343c]

in testcase: perf-sanity-tests
version: 
with following parameters:

	perf_compiler: clang
	group: group-02


config: x86_64-rhel-9.4-bpf
compiler: gcc-12
test machine: 8 threads 1 sockets Intel(R) Core(TM) i7-7700 CPU @ 3.60GHz (Kaby Lake) with 32G memory

(please refer to attached dmesg/kmsg for entire log/backtrace)


If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <oliver.sang@intel.com>
| Closes: https://lore.kernel.org/oe-lkp/202506251422.589f230a-lkp@intel.com


2025-06-22 14:23:54 sudo /usr/src/linux-perf-x86_64-rhel-9.4-bpf-5ddf4c3a17dc499fcbaf35692bc894340062dee8/tools/perf/perf test 126 -v
126: perf record tests                                               : Running (1 active)
--- start ---
test child forked, pid 8698
 13bca6c-13bcaa5 g test_loop
perf does have symbol 'test_loop'
Basic --per-thread mode test
Per-thread record [Skipped event not supported]
Register capture test
Register capture test [Failed missing output]
Basic --system-wide mode test
System-wide record [Skipped not supported]
Basic target workload test
Workload record [Failed record]
Branch counter test
branch counter feature not supported on all core PMUs (/sys/bus/event_source/devices/cpu) [Skipped]
Cgroup sampling test
Cgroup sampling [Skipped not supported]
Basic leader sampling test
Leader sampling [Failed record]
Topdown leader sampling test
Topdown leader sampling [Skipped event parsing failed]
precise_max attribute test
precise_max attribute [Skipped no cycles:P event]
precise_max attribute [Skipped no instructions:P event]
precise_max attribute [Skipped no hardware events]
---- end(-1) ----
126: perf record tests                                               : FAILED!


The kernel config and materials to reproduce are available at:
https://download.01.org/0day-ci/archive/20250625/202506251422.589f230a-lkp@intel.com



-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki

Re: [linux-next:master] [perf target] 5ddf4c3a17: perf-sanity-tests.perf_record_tests.fail

[Ian Rogers]

On Wed, Jun 25, 2025 at 12:10 AM kernel test robot
<oliver.sang@intel.com> wrote:
>
>
>
> Hello,
>
> kernel test robot noticed "perf-sanity-tests.perf_record_tests.fail" on:
>
> commit: 5ddf4c3a17dc499fcbaf35692bc894340062dee8 ("perf target: Separate parse_uid into its own function")
> https://git.kernel.org/cgit/linux/kernel/git/next/linux-next.git master
>
> [test failed on linux-next/master f817b6dd2b62d921a6cdc0a3ac599cd1851f343c]
>
> in testcase: perf-sanity-tests
> version:
> with following parameters:
>
>         perf_compiler: clang
>         group: group-02
>
>
> config: x86_64-rhel-9.4-bpf
> compiler: gcc-12
> test machine: 8 threads 1 sockets Intel(R) Core(TM) i7-7700 CPU @ 3.60GHz (Kaby Lake) with 32G memory
>
> (please refer to attached dmesg/kmsg for entire log/backtrace)
>
>
> If you fix the issue in a separate patch/commit (i.e. not just a new version of
> the same patch/commit), kindly add following tags
> | Reported-by: kernel test robot <oliver.sang@intel.com>
> | Closes: https://lore.kernel.org/oe-lkp/202506251422.589f230a-lkp@intel.com
>
>
> 2025-06-22 14:23:54 sudo /usr/src/linux-perf-x86_64-rhel-9.4-bpf-5ddf4c3a17dc499fcbaf35692bc894340062dee8/tools/perf/perf test 126 -v
> 126: perf record tests                                               : Running (1 active)
> --- start ---
> test child forked, pid 8698
>  13bca6c-13bcaa5 g test_loop
> perf does have symbol 'test_loop'
> Basic --per-thread mode test
> Per-thread record [Skipped event not supported]
> Register capture test
> Register capture test [Failed missing output]

Register capturing is different functionality to UID filtering.

> Basic --system-wide mode test
> System-wide record [Skipped not supported]
> Basic target workload test
> Workload record [Failed record]

Something seems off, possibly something to do with permissions here.

> Branch counter test
> branch counter feature not supported on all core PMUs (/sys/bus/event_source/devices/cpu) [Skipped]
> Cgroup sampling test
> Cgroup sampling [Skipped not supported]
> Basic leader sampling test
> Leader sampling [Failed record]

And here.

I suspect this was a test machine issue although later patches do add
UID filtering tests to this test. I don't see anything actionable
here.

Thanks,
Ian

> Topdown leader sampling test
> Topdown leader sampling [Skipped event parsing failed]
> precise_max attribute test
> precise_max attribute [Skipped no cycles:P event]
> precise_max attribute [Skipped no instructions:P event]
> precise_max attribute [Skipped no hardware events]
> ---- end(-1) ----
> 126: perf record tests                                               : FAILED!
>
>
> The kernel config and materials to reproduce are available at:
> https://download.01.org/0day-ci/archive/20250625/202506251422.589f230a-lkp@intel.com
>
>
>
> --
> 0-DAY CI Kernel Test Service
> https://github.com/intel/lkp-tests/wiki
>

Re: [linux-next:master] [perf target] 5ddf4c3a17: perf-sanity-tests.perf_record_tests.fail

[Namhyung Kim]

Hello,

On Wed, Jun 25, 2025 at 07:59:16AM -0700, Ian Rogers wrote:
> On Wed, Jun 25, 2025 at 12:10 AM kernel test robot
> <oliver.sang@intel.com> wrote:
> >
> >
> >
> > Hello,
> >
> > kernel test robot noticed "perf-sanity-tests.perf_record_tests.fail" on:
> >
> > commit: 5ddf4c3a17dc499fcbaf35692bc894340062dee8 ("perf target: Separate parse_uid into its own function")
> > https://git.kernel.org/cgit/linux/kernel/git/next/linux-next.git master
> >
> > [test failed on linux-next/master f817b6dd2b62d921a6cdc0a3ac599cd1851f343c]
> >
> > in testcase: perf-sanity-tests
> > version:
> > with following parameters:
> >
> >         perf_compiler: clang
> >         group: group-02
> >
> >
> > config: x86_64-rhel-9.4-bpf
> > compiler: gcc-12
> > test machine: 8 threads 1 sockets Intel(R) Core(TM) i7-7700 CPU @ 3.60GHz (Kaby Lake) with 32G memory
> >
> > (please refer to attached dmesg/kmsg for entire log/backtrace)
> >
> >
> > If you fix the issue in a separate patch/commit (i.e. not just a new version of
> > the same patch/commit), kindly add following tags
> > | Reported-by: kernel test robot <oliver.sang@intel.com>
> > | Closes: https://lore.kernel.org/oe-lkp/202506251422.589f230a-lkp@intel.com
> >
> >
> > 2025-06-22 14:23:54 sudo /usr/src/linux-perf-x86_64-rhel-9.4-bpf-5ddf4c3a17dc499fcbaf35692bc894340062dee8/tools/perf/perf test 126 -v
> > 126: perf record tests                                               : Running (1 active)
> > --- start ---
> > test child forked, pid 8698
> >  13bca6c-13bcaa5 g test_loop
> > perf does have symbol 'test_loop'
> > Basic --per-thread mode test
> > Per-thread record [Skipped event not supported]
> > Register capture test
> > Register capture test [Failed missing output]
> 
> Register capturing is different functionality to UID filtering.

Right.

> 
> > Basic --system-wide mode test
> > System-wide record [Skipped not supported]
> > Basic target workload test
> > Workload record [Failed record]
> 
> Something seems off, possibly something to do with permissions here.

Yeah, not sure what happended here.

> 
> > Branch counter test
> > branch counter feature not supported on all core PMUs (/sys/bus/event_source/devices/cpu) [Skipped]
> > Cgroup sampling test
> > Cgroup sampling [Skipped not supported]
> > Basic leader sampling test
> > Leader sampling [Failed record]
> 
> And here.
> 
> I suspect this was a test machine issue although later patches do add
> UID filtering tests to this test. I don't see anything actionable
> here.

I agree that none of these failures related to UID filtering.
But it seems leader sampling test is using 'cycles' events without
checking its availability.  So it'll fail on VMs that don't expose HW
PMUs.

Thanks,
Namhyung

> 
> > Topdown leader sampling test
> > Topdown leader sampling [Skipped event parsing failed]
> > precise_max attribute test
> > precise_max attribute [Skipped no cycles:P event]
> > precise_max attribute [Skipped no instructions:P event]
> > precise_max attribute [Skipped no hardware events]
> > ---- end(-1) ----
> > 126: perf record tests                                               : FAILED!
> >
> >
> > The kernel config and materials to reproduce are available at:
> > https://download.01.org/0day-ci/archive/20250625/202506251422.589f230a-lkp@intel.com
> >
> >
> >
> > --
> > 0-DAY CI Kernel Test Service
> > https://github.com/intel/lkp-tests/wiki
> >