On 04/12/2018 03:05 PM, Arnaldo Carvalho de Melo wrote:
> Em Thu, Apr 12, 2018 at 01:47:23PM +0200, Thomas Richter escreveu:
>> Using perf on 4.16.0 kernel on s390 shows warning
>> failed: can't open node sysfs data
>> each time I run command perf record ... for example:
>>
>> [root@s35lp76 perf]# ./perf record -e rB0000 -- sleep 1
>> [ perf record: Woken up 1 times to write data ]
>> failed: can't open node sysfs data
>> [ perf record: Captured and wrote 0.001 MB perf.data (4 samples) ]
>> [root@s35lp76 perf]#
>>
>> BTW: I find this error message not very informative.
>
> What an understatement :-)
>
>> It turns out commit e2091cedd51bf ("perf tools: Add MEM_TOPOLOGY
>> feature to perf data file") tries to open directory named
>> /sys/devices/system/node/ which does not exist on s390.
>>
>> This is the call stack:
>> __cmd_record
>> +---> perf_session__write_header
>> +---> perf_header__adds_write
>> +---> do_write_feat
>> +---> write_mem_topology
>> +---> build_mem_topology
>> prints warning
>> The issue starts in do_write_feat() which unconditionally
>> loops over all features and now includes HEADER_MEM_TOPOLOGY and calls
>> write_mem_topology().
>> Function record__init_features() at the beginning of __cmd_record()
>> sets all features and then turns off some.
>>
>> Fix this by removed the warning, if the directory is not present
>> memory node information is not available and won't be displayed.
>
> Can't we instead improve the error message and turn this into a
> pr_debug2? Isn't it a reasonable scenario that the user expects this
> topology information to be present and then ends up without it?
>
> Perhaps something like:
>
> pr_debug2("%s: could't read %s, does this arch have topology
> information?\n", __func__, path);
>
> - Arnaldo
>
Fine with me, I will provide a version 2....
--
Thomas Richter, Dept 3303, IBM LTC Boeblingen Germany
--
Vorsitzende des Aufsichtsrats: Martina Koederitz
Geschäftsführung: Dirk Wittkopp
Sitz der Gesellschaft: Böblingen / Registergericht: Amtsgericht Stuttgart, HRB
243294
