[sparc64] fio bus error

On 08/20/2016 09:19 AM, Anatoly Pugachev wrote:
> Hello!
>
> I'm getting bus error on sparc64 debian sid linux with git compiled fio:
>
> mator@nvg5120:~/fio.git$ git describe
> fio-2.13-77-gd1f6fca
>
> mator@nvg5120:~/fio.git$ cat /tmp/test.fio
> [global]
> bs=8k
> iodepth=16
> iodepth_batch=8
> randrepeat=1
> size=1m
> directory=/home/mator/fio.dir
> numjobs=5
> [job1]
> ioengine=sync
> bs=1k
> direct=1
> rw=randread
> filename=file1:file2
>
>
> mator@nvg5120:~/fio.git$ gdb -q
> (gdb) file ./fio
> Reading symbols from ./fio...done.
> (gdb) set args /tmp/test.fio
> (gdb) run
> Starting program: /home/mator/fio.git/fio /tmp/test.fio
> [Thread debugging using libthread_db enabled]
> Using host libthread_db library "/lib/sparc64-linux-gnu/libthread_db.so.1".
> job1: (g=0): rw=randread, bs=1K-1K/1K-1K/1K-1K, ioengine=sync, iodepth=16
> ...
> fio-2.13-77-gd1f6f
> [New Thread 0xffff80011025b910 (LWP 15753)]
> Starting 5 processes
>
> Thread 2 "fio" received signal SIGBUS, Bus error.
> [Switching to Thread 0xffff80011025b910 (LWP 15753)]
> calc_log_samples () at stat.c:2461
> 2461                            tmp = add_bw_samples(td, &now);
> (gdb) bt
> #0  calc_log_samples () at stat.c:2461
> #1  0x000000000018e944 in helper_thread_main (data=0xffff800100ac5670)
> at helper_thread.c:121
> #2  0xffff80010063ba04 in start_thread (arg=0xffff80011025b910) at
> pthread_create.c:335
> #3  0xffff800100944f58 in __thread_start () at
> ../sysdeps/unix/sysv/linux/sparc/sparc64/clone.S:93
> Backtrace stopped: previous frame identical to this frame (corrupt stack?)
> (gdb)

Does this help?

On Mon, Aug 22, 2016 at 8:32 PM, Jens Axboe <axboe@kernel.dk> wrote:
> On 08/20/2016 09:19 AM, Anatoly Pugachev wrote:
>> Thread 2 "fio" received signal SIGBUS, Bus error.
>> [Switching to Thread 0xffff80011025b910 (LWP 15753)]
>> calc_log_samples () at stat.c:2461
>> 2461                            tmp = add_bw_samples(td, &now);
>> (gdb) bt
>> #0  calc_log_samples () at stat.c:2461
>> #1  0x000000000018e944 in helper_thread_main (data=0xffff800100ac5670)
>> at helper_thread.c:121
>> #2  0xffff80010063ba04 in start_thread (arg=0xffff80011025b910) at
>> pthread_create.c:335
>> #3  0xffff800100944f58 in __thread_start () at
>> ../sysdeps/unix/sysv/linux/sparc/sparc64/clone.S:93
>> Backtrace stopped: previous frame identical to this frame (corrupt stack?)
>> (gdb)
>
>
> Does this help?
>
> diff --git a/stat.c b/stat.c
> index 552d88dde067..74c2686c660c 100644
> --- a/stat.c
> +++ b/stat.c
> @@ -2457,12 +2457,12 @@ int calc_log_samples(void)
>                         next = min(td->o.iops_avg_time, td->o.bw_avg_time);
>                         continue;
>                 }
> -               if (!per_unit_log(td->bw_log)) {
> +               if (td->bw_log && !per_unit_log(td->bw_log)) {
>                         tmp = add_bw_samples(td, &now);
>                         if (tmp < next)
>                                 next = tmp;
>                 }
> -               if (!per_unit_log(td->iops_log)) {
> +               if (td->iops_log && !per_unit_log(td->iops_log)) {
>                         tmp = add_iops_samples(td, &now);
>                         if (tmp < next)
>                                 next = tmp;
>


Jens,

yes, this patch fixed sigbus. Thanks.
--
To unsubscribe from this list: send the line "unsubscribe sparclinux" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

On 08/22/2016 01:17 PM, Anatoly Pugachev wrote:
> On Mon, Aug 22, 2016 at 8:32 PM, Jens Axboe <axboe@kernel.dk> wrote:
>> On 08/20/2016 09:19 AM, Anatoly Pugachev wrote:
>>> Thread 2 "fio" received signal SIGBUS, Bus error.
>>> [Switching to Thread 0xffff80011025b910 (LWP 15753)]
>>> calc_log_samples () at stat.c:2461
>>> 2461                            tmp = add_bw_samples(td, &now);
>>> (gdb) bt
>>> #0  calc_log_samples () at stat.c:2461
>>> #1  0x000000000018e944 in helper_thread_main (data=0xffff800100ac5670)
>>> at helper_thread.c:121
>>> #2  0xffff80010063ba04 in start_thread (arg=0xffff80011025b910) at
>>> pthread_create.c:335
>>> #3  0xffff800100944f58 in __thread_start () at
>>> ../sysdeps/unix/sysv/linux/sparc/sparc64/clone.S:93
>>> Backtrace stopped: previous frame identical to this frame (corrupt stack?)
>>> (gdb)
>>
>>
>> Does this help?
>>
>> diff --git a/stat.c b/stat.c
>> index 552d88dde067..74c2686c660c 100644
>> --- a/stat.c
>> +++ b/stat.c
>> @@ -2457,12 +2457,12 @@ int calc_log_samples(void)
>>                         next = min(td->o.iops_avg_time, td->o.bw_avg_time);
>>                         continue;
>>                 }
>> -               if (!per_unit_log(td->bw_log)) {
>> +               if (td->bw_log && !per_unit_log(td->bw_log)) {
>>                         tmp = add_bw_samples(td, &now);
>>                         if (tmp < next)
>>                                 next = tmp;
>>                 }
>> -               if (!per_unit_log(td->iops_log)) {
>> +               if (td->iops_log && !per_unit_log(td->iops_log)) {
>>                         tmp = add_iops_samples(td, &now);
>>                         if (tmp < next)
>>                                 next = tmp;
>>
>
>
> Jens,
>
> yes, this patch fixed sigbus. Thanks.

Great, thanks for reporting. I have committed the fix.