Community
cancel
Showing results for 
Search instead for 
Did you mean: 
psing51
Beginner
184 Views

Assertion 'Cannot write magic record to trace' failed.

Hi,
I am trying vtune 2020u0 on rhel 7.6 in intel 8280.
For testing the setup i used APS, and it ran fine and generated the results without any issue.

Then i tried out the hpc-performance analysis on using amplxe-cl command as - 

time mpirun -np $SLURM_NPROCS -ppn $SLURM_NTASKS_PER_NODE amplxe-cl -collect hpc-performance -data-limit 0 -result-dir result_hpcperf -- ${INSTALL_ROOT}/wrf.exe

 the run has finished , but is seems that the data gathering command has experienced some issue - 

WRF: SUCCESS COMPLETE wrf
vcs/collectunits1/tmu/src/tmu.c:437 write_trace: Assertion 'Cannot write magic record to trace' failed.

Abort trap signal
Image              PC                Routine            Line        Source
wrf.exe            00000000030C8DDB  for__signal_handl     Unknown  Unknown
libpthread-2.17.s  00002AAAACFB25D0  Unknown               Unknown  Unknown
libc-2.17.so       00002AAAAD8E7207  gsignal               Unknown  Unknown
libc-2.17.so       00002AAAAD8E88F8  abort                 Unknown  Unknown
libittnotify_coll  00002AAAAACE2D88  Unknown               Unknown  Unknown
libittnotify_coll  00002AAAAACE33AB  Unknown               Unknown  Unknown
libittnotify_coll  00002AAAAACE34F7  Unknown               Unknown  Unknown
libittnotify_coll  00002AAAAACE4C9B  Unknown               Unknown  Unknown
libittnotify_coll  00002AAAAACD7B81  Unknown               Unknown  Unknown
libittnotify_coll  00002AAAAACD79A3  Unknown               Unknown  Unknown
libittnotify_coll  00002AAAAACD77F6  Unknown               Unknown  Unknown
ld-2.17.so         00002AAAAAABAFCA  Unknown               Unknown  Unknown
libc-2.17.so       00002AAAAD8EAB69  Unknown               Unknown  Unknown
libc-2.17.so       00002AAAAD8EABB7  Unknown               Unknown  Unknown
libc-2.17.so       00002AAAAD8D33DC  __libc_start_main     Unknown  Unknown
wrf.exe            0000000000415169  Unknown               Unknown  Unknown

 

around 11 hours have elapsed and i still see amplxe-cl process running (top command)
 

   PID USER      PR  NI    VIRT    RES    SHR S  %CPU %MEM     TIME+ COMMAND
 42453 root      20   0  626072  53584  32180 S   6.2  0.0   0:29.60 amplxe-cl
111683 root      20   0  164668   2616   1556 R   6.2  0.0   0:00.01 top
     1 root      20   0   56060   8328   2620 S   0.0  0.0   1:04.08 systemd
     2 root      20   0       0      0      0 S   0.0  0.0   0:00.12 kthreadd
     3 root      20   0       0      0      0 S   0.0  0.0   0:00.06 ksoftirqd/0

 

and i can see a 17mb directory was also created (result_hpcperf.node1).
I am not sure if i will face issues with other collection/analysis types
Though i tried out the amplxe self checker script, and log seems to indicate that the setup is fine.

Please let me know if i can provide more information from my end to fix this issue. 

0 Kudos
3 Replies
Vladimir_R_Intel
Employee
184 Views

Hi,

please try the same analysis type on some simple application like ls. If it works then please try your mpirun command without libittnotify_collector.so (you can just rename this library located in <vtune_install>/lib64/runtime).

ChithraJ_Intel
Moderator
184 Views

Hi Puneet,

Could you please confirm whether the above solution worked for you.

ChithraJ_Intel
Moderator
184 Views

Hi Puneet,

We are closing this case by assuming that your issue got resolved. Please feel free to raise a new thread if you have further issues.

Reply