Code hangs randomly after 1hr/1day/30 days
I am using Altera Cyclone V FPGA with ARM 7 core, I am running a application with 7 thread with mutexes.
The application randomly hangs after 1hr or 1 Day or 1 Month, no defined time.
I ran strace when the application is running smoothly and it gives:
---------------------------------------------------------------------------------------------------------
-------------------- RUNNING / HEALTHY STATE
---------------------------------------------------------------------------------------------------------
root@socfpga:~# strace -p 297 -f
Process 297 attached with 7 threads
[pid 311] recvfrom(6, <unfinished ...>
[pid 297] nanosleep({0, 10000000}, <unfinished ...>
[pid 340] nanosleep({0, 500000000}, <unfinished ...>
......
[pid 339] <... nanosleep resumed> NULL) = 0
[pid 339] nanosleep({0, 500000000}, <unfinished ...>
[pid 297] <... nanosleep resumed> NULL) = 0
[pid 297] nanosleep({0, 10000000}, NULL) = 0
[pid 297] nanosleep({0, 10000000}, NULL) = ? ERESTART_RESTARTBLOCK (Interrupted by signal)
[pid 297] --- SIGRT_2 {si_signo=SIGRT_2, si_code=SI_TIMER, si_pid=0, si_uid=0, si_value=209660} ---
[pid 297] rt_sigreturn() = -1 EINTR (Interrupted system call)
[pid 297] nanosleep({0, 10000000}, NULL) = 0
[pid 297] nanosleep({0, 10000000}, <unfinished ...>
[pid 340] <... nanosleep resumed> NULL) = 0
[pid 340] nanosleep({0, 500000000}, <unfinished ...>
[pid 297] <... nanosleep resumed> NULL) = 0
[pid 297] nanosleep({0, 10000000}, NULL) = 0
[pid 297] nanosleep({0, 10000000}, <unfinished ...>
[pid 339] <... nanosleep resumed> NULL) = 0
[pid 339] nanosleep({0, 500000000}, <unfinished ...>
[pid 297] <... nanosleep resumed> NULL) = 0
[pid 297] nanosleep({0, 10000000}, NULL) = 0
[pid 297] nanosleep({0, 10000000}, NULL) = ? ERESTART_RESTARTBLOCK (Interrupted by signal)
[pid 297] --- SIGRT_2 {si_signo=SIGRT_2, si_code=SI_TIMER, si_pid=0, si_uid=0, si_value=209660} ---
[pid 297] rt_sigreturn() = -1 EINTR (Interrupted system call)
[pid 297] nanosleep({0, 10000000}, NULL) = 0
[pid 297] nanosleep({0, 10000000}, <unfinished ...>
[pid 340] <... nanosleep resumed> NULL) = 0
[pid 340] nanosleep({0, 500000000}, <unfinished ...>
[pid 297] <... nanosleep resumed> NULL) = 0
[pid 297] nanosleep({0, 10000000}, NULL) = 0
[pid 297] nanosleep({0, 10000000}, <unfinished ...>
[pid 339] <... nanosleep resumed> NULL) = 0
[pid 339] nanosleep({0, 500000000}, <unfinished ...>
[pid 297] <... nanosleep resumed> NULL) = 0
[pid 297] nanosleep({0, 10000000}, NULL) = 0
[pid 297] nanosleep({0, 10000000}, NULL) = ? ERESTART_RESTARTBLOCK (Interrupted by signal)
[pid 297] --- SIGRT_2 {si_signo=SIGRT_2, si_code=SI_TIMER, si_pid=0, si_uid=0, si_value=209660} ---
[pid 297] rt_sigreturn() = -1 EINTR (Interrupted system call)
[pid 297] nanosleep({0, 10000000}, NULL) = 0
[pid 297] nanosleep({0, 10000000}, <unfinished ...>
[pid 340] <... nanosleep resumed> NULL) = 0
[pid 340] nanosleep({0, 500000000}, <unfinished ...>
[pid 297] <... nanosleep resumed> NULL) = 0
.......
[pid 297] nanosleep({0, 10000000}, NULL) = ? ERESTART_RESTARTBLOCK (Interrupted by signal)
[pid 297] --- SIGRT_2 {si_signo=SIGRT_2, si_code=SI_TIMER, si_pid=0, si_uid=0, si_value=209660} ---
[pid 297] gettimeofday({1495402377, 473913}, NULL) = 0
[pid 297] write(3, "20170521 21:32:57.473 INFO d"..., 100) = 100
[pid 297] rt_sigreturn() = -1 EINTR (Interrupted system call)
[pid 297] gettimeofday({1495402377, 474831}, NULL) = 0
[pid 297] write(3, "20170521 21:32:57.474 ERROR d"..., 110) = 110
[pid 297] nanosleep({0, 10000000}, NULL) = 0
[pid 297] nanosleep({0, 10000000}, <unfinished ...>
[pid 340] <... nanosleep resumed> NULL) = 0
[pid 340] nanosleep({0, 500000000}, <unfinished ...>
[pid 297] <... nanosleep resumed> NULL) = 0
[pid 297] nanosleep({0, 10000000}, NULL) = 0
[pid 297] nanosleep({0, 10000000}, ^CProcess 297 detached
<detached ...>
Process 309 detached
Process 310 detached
Process 311 detached
Process 312 detached
Process 339 detached
Process 340 detached
randomly the application hangs and the strace output is as follows:
---------------------------------------------------------------------------------------------------------
-------------------- HANG STATE
---------------------------------------------------------------------------------------------------------
root@socfpga:~# strace -p 297
Process 297 attached
futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL^CProcess 297 detached
<detached ...>
root@socfpga:~# strace -p 297 -f
Process 297 attached with 7 threads
[pid 312] futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL <unfinished ...>
[pid 340] futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL <unfinished ...>
[pid 339] futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL <unfinished ...>
[pid 311] futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL <unfinished ...>
[pid 310] futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL <unfinished ...>
[pid 309] futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL <unfinished ...>
[pid 297] futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL <unfinished ...>
[pid 312] <... futex resumed> ) = ? ERESTARTSYS (To be restarted if SA_RESTART is set)
[pid 312] --- SIGRT_2 {si_signo=SIGRT_2, si_code=SI_TIMER, si_pid=0, si_uid=0, si_value=209660} ---
[pid 312] rt_sigreturn() = -1 EINTR (Interrupted system call)
[pid 312] futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL) = ? ERESTARTSYS (To be restarted if SA_RESTART is set)
[pid 312] --- SIGRT_2 {si_signo=SIGRT_2, si_code=SI_TIMER, si_pid=0, si_uid=0, si_value=209660} ---
[pid 312] rt_sigreturn() = -1 EINTR (Interrupted system call)
[pid 312] futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL) = ? ERESTARTSYS (To be restarted if SA_RESTART is set)
[pid 312] --- SIGRT_2 {si_signo=SIGRT_2, si_code=SI_TIMER, si_pid=0, si_uid=0, si_value=209660} ---
[pid 312] rt_sigreturn() = -1 EINTR (Interrupted system call)
[pid 312] futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL) = ? ERESTARTSYS (To be restarted if SA_RESTART is set)
[pid 312] --- SIGRT_2 {si_signo=SIGRT_2, si_code=SI_TIMER, si_pid=0, si_uid=0, si_value=209660} ---
[pid 312] rt_sigreturn() = -1 EINTR (Interrupted system call)
[pid 312] futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL) = ? ERESTARTSYS (To be restarted if SA_RESTART is set)
[pid 312] --- SIGRT_2 {si_signo=SIGRT_2, si_code=SI_TIMER, si_pid=0, si_uid=0, si_value=209660} ---
[pid 312] rt_sigreturn() = -1 EINTR (Interrupted system call)
[pid 312] futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL) = ? ERESTARTSYS (To be restarted if SA_RESTART is set)
[pid 312] --- SIGRT_2 {si_signo=SIGRT_2, si_code=SI_TIMER, si_pid=0, si_uid=0, si_value=209660} ---
[pid 312] rt_sigreturn() = -1 EINTR (Interrupted system call)
[pid 312] futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL) = ? ERESTARTSYS (To be restarted if SA_RESTART is set)
[pid 312] --- SIGRT_2 {si_signo=SIGRT_2, si_code=SI_TIMER, si_pid=0, si_uid=0, si_value=209660} ---
[pid 312] rt_sigreturn() = -1 EINTR (Interrupted system call)
[pid 312] futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL) = ? ERESTARTSYS (To be restarted if SA_RESTART is set)
[pid 312] --- SIGRT_2 {si_signo=SIGRT_2, si_code=SI_TIMER, si_pid=0, si_uid=0, si_value=209660} ---
[pid 312] rt_sigreturn() = -1 EINTR (Interrupted system call)
[pid 312] futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL^CProcess 297 detached
Process 309 detached
Process 310 detached
Process 311 detached
Process 312 detached
<detached ...>
Process 339 detached
Process 340 detached
root@socfpga:~# strace -p 310
Process 310 attached
futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL^CProcess 310 detached
<detached ...>
root@socfpga:~# strace -p 311
Process 311 attached
futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL^CProcess 311 detached
<detached ...>
root@socfpga:~# strace -p 312
Process 312 attached
futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL) = ? ERESTARTSYS (To be restarted if SA_RESTART is set)
--- SIGRT_2 {si_signo=SIGRT_2, si_code=SI_TIMER, si_pid=0, si_uid=0, si_value=209660} ---
rt_sigreturn() = -1 EINTR (Interrupted system call)
futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL) = ? ERESTARTSYS (To be restarted if SA_RESTART is set)
--- SIGRT_2 {si_signo=SIGRT_2, si_code=SI_TIMER, si_pid=0, si_uid=0, si_value=209660} ---
rt_sigreturn() = -1 EINTR (Interrupted system call)
futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL) = ? ERESTARTSYS (To be restarted if SA_RESTART is set)
--- SIGRT_2 {si_signo=SIGRT_2, si_code=SI_TIMER, si_pid=0, si_uid=0, si_value=209660} ---
rt_sigreturn() = -1 EINTR (Interrupted system call)
futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL) = ? ERESTARTSYS (To be restarted if SA_RESTART is set)
--- SIGRT_2 {si_signo=SIGRT_2, si_code=SI_TIMER, si_pid=0, si_uid=0, si_value=209660} ---
rt_sigreturn() = -1 EINTR (Interrupted system call)
futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL) = ? ERESTARTSYS (To be restarted if SA_RESTART is set)
--- SIGRT_2 {si_signo=SIGRT_2, si_code=SI_TIMER, si_pid=0, si_uid=0, si_value=209660} ---
rt_sigreturn() = -1 EINTR (Interrupted system call)
futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL) = ? ERESTARTSYS (To be restarted if SA_RESTART is set)
--- SIGRT_2 {si_signo=SIGRT_2, si_code=SI_TIMER, si_pid=0, si_uid=0, si_value=209660} ---
rt_sigreturn() = -1 EINTR (Interrupted system call)
futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL) = ? ERESTARTSYS (To be restarted if SA_RESTART is set)
--- SIGRT_2 {si_signo=SIGRT_2, si_code=SI_TIMER, si_pid=0, si_uid=0, si_value=209660} ---
rt_sigreturn() = -1 EINTR (Interrupted system call)
futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL) = ? ERESTARTSYS (To be restarted if SA_RESTART is set)
--- SIGRT_2 {si_signo=SIGRT_2, si_code=SI_TIMER, si_pid=0, si_uid=0, si_value=209660} ---
rt_sigreturn() = -1 EINTR (Interrupted system call)
futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL) = ? ERESTARTSYS (To be restarted if SA_RESTART is set)
--- SIGRT_2 {si_signo=SIGRT_2, si_code=SI_TIMER, si_pid=0, si_uid=0, si_value=209660} ---
rt_sigreturn() = -1 EINTR (Interrupted system call)
futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL) = ? ERESTARTSYS (To be restarted if SA_RESTART is set)
--- SIGRT_2 {si_signo=SIGRT_2, si_code=SI_TIMER, si_pid=0, si_uid=0, si_value=209660} ---
rt_sigreturn() = -1 EINTR (Interrupted system call)
futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL) = ? ERESTARTSYS (To be restarted if SA_RESTART is set)
--- SIGRT_2 {si_signo=SIGRT_2, si_code=SI_TIMER, si_pid=0, si_uid=0, si_value=209660} ---
rt_sigreturn() = -1 EINTR (Interrupted system call)
futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL) = ? ERESTARTSYS (To be restarted if SA_RESTART is set)
--- SIGRT_2 {si_signo=SIGRT_2, si_code=SI_TIMER, si_pid=0, si_uid=0, si_value=209660} ---
rt_sigreturn() = -1 EINTR (Interrupted system call)
futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL) = ? ERESTARTSYS (To be restarted if SA_RESTART is set)
--- SIGRT_2 {si_signo=SIGRT_2, si_code=SI_TIMER, si_pid=0, si_uid=0, si_value=209660} ---
rt_sigreturn() = -1 EINTR (Interrupted system call)
futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL) = ? ERESTARTSYS (To be restarted if SA_RESTART is set)
--- SIGRT_2 {si_signo=SIGRT_2, si_code=SI_TIMER, si_pid=0, si_uid=0, si_value=209660} ---
rt_sigreturn() = -1 EINTR (Interrupted system call)
futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL) = ? ERESTARTSYS (To be restarted if SA_RESTART is set)
--- SIGRT_2 {si_signo=SIGRT_2, si_code=SI_TIMER, si_pid=0, si_uid=0, si_value=209660} ---
rt_sigreturn() = -1 EINTR (Interrupted system call)
futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL) = ? ERESTARTSYS (To be restarted if SA_RESTART is set)
--- SIGRT_2 {si_signo=SIGRT_2, si_code=SI_TIMER, si_pid=0, si_uid=0, si_value=209660} ---
rt_sigreturn() = -1 EINTR (Interrupted system call)
futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL) = ? ERESTARTSYS (To be restarted if SA_RESTART is set)
--- SIGRT_2 {si_signo=SIGRT_2, si_code=SI_TIMER, si_pid=0, si_uid=0, si_value=209660} ---
rt_sigreturn() = -1 EINTR (Interrupted system call)
futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL) = ? ERESTARTSYS (To be restarted if SA_RESTART is set)
--- SIGRT_2 {si_signo=SIGRT_2, si_code=SI_TIMER, si_pid=0, si_uid=0, si_value=209660} ---
rt_sigreturn() = -1 EINTR (Interrupted system call)
futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL) = ? ERESTARTSYS (To be restarted if SA_RESTART is set)
--- SIGRT_2 {si_signo=SIGRT_2, si_code=SI_TIMER, si_pid=0, si_uid=0, si_value=209660} ---
rt_sigreturn() = -1 EINTR (Interrupted system call)
futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL) = ? ERESTARTSYS (To be restarted if SA_RESTART is set)
--- SIGRT_2 {si_signo=SIGRT_2, si_code=SI_TIMER, si_pid=0, si_uid=0, si_value=209660} ---
rt_sigreturn() = -1 EINTR (Interrupted system call)
futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL) = ? ERESTARTSYS (To be restarted if SA_RESTART is set)
--- SIGRT_2 {si_signo=SIGRT_2, si_code=SI_TIMER, si_pid=0, si_uid=0, si_value=209660} ---
rt_sigreturn() = -1 EINTR (Interrupted system call)
futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL) = ? ERESTARTSYS (To be restarted if SA_RESTART is set)
--- SIGRT_2 {si_signo=SIGRT_2, si_code=SI_TIMER, si_pid=0, si_uid=0, si_value=209660} ---
rt_sigreturn() = -1 EINTR (Interrupted system call)
futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL) = ? ERESTARTSYS (To be restarted if SA_RESTART is set)
--- SIGRT_2 {si_signo=SIGRT_2, si_code=SI_TIMER, si_pid=0, si_uid=0, si_value=209660} ---
rt_sigreturn() = -1 EINTR (Interrupted system call)
futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL) = ? ERESTARTSYS (To be restarted if SA_RESTART is set)
--- SIGRT_2 {si_signo=SIGRT_2, si_code=SI_TIMER, si_pid=0, si_uid=0, si_value=209660} ---
rt_sigreturn() = -1 EINTR (Interrupted system call)
futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL) = ? ERESTARTSYS (To be restarted if SA_RESTART is set)
--- SIGRT_2 {si_signo=SIGRT_2, si_code=SI_TIMER, si_pid=0, si_uid=0, si_value=209660} ---
rt_sigreturn() = -1 EINTR (Interrupted system call)
futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL) = ? ERESTARTSYS (To be restarted if SA_RESTART is set)
--- SIGRT_2 {si_signo=SIGRT_2, si_code=SI_TIMER, si_pid=0, si_uid=0, si_value=209660} ---
rt_sigreturn() = -1 EINTR (Interrupted system call)
futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL) = ? ERESTARTSYS (To be restarted if SA_RESTART is set)
--- SIGRT_2 {si_signo=SIGRT_2, si_code=SI_TIMER, si_pid=0, si_uid=0, si_value=209660} ---
rt_sigreturn() = -1 EINTR (Interrupted system call)
futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL) = ? ERESTARTSYS (To be restarted if SA_RESTART is set)
--- SIGRT_2 {si_signo=SIGRT_2, si_code=SI_TIMER, si_pid=0, si_uid=0, si_value=209660} ---
rt_sigreturn() = -1 EINTR (Interrupted system call)
futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL) = ? ERESTARTSYS (To be restarted if SA_RESTART is set)
--- SIGRT_2 {si_signo=SIGRT_2, si_code=SI_TIMER, si_pid=0, si_uid=0, si_value=209660} ---
rt_sigreturn() = -1 EINTR (Interrupted system call)
futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL) = ? ERESTARTSYS (To be restarted if SA_RESTART is set)
--- SIGRT_2 {si_signo=SIGRT_2, si_code=SI_TIMER, si_pid=0, si_uid=0, si_value=209660} ---
rt_sigreturn() = -1 EINTR (Interrupted system call)
futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL) = ? ERESTARTSYS (To be restarted if SA_RESTART is set)
--- SIGRT_2 {si_signo=SIGRT_2, si_code=SI_TIMER, si_pid=0, si_uid=0, si_value=209660} ---
rt_sigreturn() = -1 EINTR (Interrupted system call)
futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL) = ? ERESTARTSYS (To be restarted if SA_RESTART is set)
--- SIGRT_2 {si_signo=SIGRT_2, si_code=SI_TIMER, si_pid=0, si_uid=0, si_value=209660} ---
rt_sigreturn() = -1 EINTR (Interrupted system call)
futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL) = ? ERESTARTSYS (To be restarted if SA_RESTART is set)
--- SIGRT_2 {si_signo=SIGRT_2, si_code=SI_TIMER, si_pid=0, si_uid=0, si_value=209660} ---
rt_sigreturn() = -1 EINTR (Interrupted system call)
futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL
) = ? ERESTARTSYS (To be restarted if SA_RESTART is set)
--- SIGRT_2 {si_signo=SIGRT_2, si_code=SI_TIMER, si_pid=0, si_uid=0, si_value=209660} ---
rt_sigreturn() = -1 EINTR (Interrupted system call)
futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL
) = ? ERESTARTSYS (To be restarted if SA_RESTART is set)
--- SIGRT_2 {si_signo=SIGRT_2, si_code=SI_TIMER, si_pid=0, si_uid=0, si_value=209660} ---
rt_sigreturn() = -1 EINTR (Interrupted system call)
futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL) = ? ERESTARTSYS (To be restarted if SA_RESTART is set)
--- SIGRT_2 {si_signo=SIGRT_2, si_code=SI_TIMER, si_pid=0, si_uid=0, si_value=209660} ---
rt_sigreturn() = -1 EINTR (Interrupted system call)
futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL^CProcess 312 detached
<detached ...>
root@socfpga:~# strace -p 339
Process 339 attached
futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL
^CProcess 339 detached
<detached ...>
Quit anyway? (y or n) y
Detaching from program: /home/user/user/process_cc, process 297
root@socfpga:~# gdb -p 309
GNU gdb (Linaro GDB) 7.8-2014.09
Copyright (C) 2014 Free Software Foundation, Inc.
License GPLv3+: GNU GPL version 3 or later <http://gnu.org/licenses/gpl.html>
This is free software: you are free to change and redistribute it.
There is NO WARRANTY, to the extent permitted by law. Type "show copying"
and "show warranty" for details.
This GDB was configured as "arm-angstrom-linux-gnueabi".
Type "show configuration" for configuration details.
For bug reporting instructions, please see:
<http://bugs.linaro.org>.
Find the GDB manual and other documentation resources online at:
<http://www.gnu.org/software/gdb/documentation/>.
For help, type "help".
Type "apropos word" to search for commands related to "word".
Attaching to process 309
warning: process 309 is a cloned process
Reading symbols from /home/user/user/process_cc...done.
Reading symbols from /usr/lib/liblog4c.so.3...done.
Loaded symbols for /usr/lib/liblog4c.so.3
Reading symbols from /lib/libpthread.so.0...(no debugging symbols found)...done.
warning: Unable to find libthread_db matching inferior's thread library, thread debugging will not be available.
Loaded symbols for /lib/libpthread.so.0
Reading symbols from /lib/libm.so.6...(no debugging symbols found)...done.
Loaded symbols for /lib/libm.so.6
Reading symbols from /lib/librt.so.1...(no debugging symbols found)...done.
Loaded symbols for /lib/librt.so.1
Reading symbols from /lib/libc.so.6...(no debugging symbols found)...done.
Loaded symbols for /lib/libc.so.6
Reading symbols from /lib/ld-linux-armhf.so.3...(no debugging symbols found)...done.
Loaded symbols for /lib/ld-linux-armhf.so.3
warning: Unable to find libthread_db matching inferior's thread library, thread debugging will not be available.
0x76f3ed50 in ?? () from /lib/libpthread.so.0
(gdb) bt
#0 0x76f3ed50 in ?? () from /lib/libpthread.so.0
#1 0x00000000 in ?? ()
Backtrace stopped: previous frame identical to this frame (corrupt stack?)
(gdb) quit
A debugging session is active.
Inferior 1 [process 309] will be detached.
Quit anyway? (y or n) y
Detaching from program: /home/user/user/process_cc, process 309
root@socfpga:~# gdb -p 310
GNU gdb (Linaro GDB) 7.8-2014.09
Copyright (C) 2014 Free Software Foundation, Inc.
License GPLv3+: GNU GPL version 3 or later <http://gnu.org/licenses/gpl.html>
This is free software: you are free to change and redistribute it.
There is NO WARRANTY, to the extent permitted by law. Type "show copying"
and "show warranty" for details.
This GDB was configured as "arm-angstrom-linux-gnueabi".
Type "show configuration" for configuration details.
For bug reporting instructions, please see:
<http://bugs.linaro.org>.
Find the GDB manual and other documentation resources online at:
<http://www.gnu.org/software/gdb/documentation/>.
For help, type "help".
Type "apropos word" to search for commands related to "word".
Attaching to process 310
warning: process 310 is a cloned process
Reading symbols from /home/user/user/process_cc...done.
Reading symbols from /usr/lib/liblog4c.so.3...done.
Loaded symbols for /usr/lib/liblog4c.so.3
Reading symbols from /lib/libpthread.so.0...(no debugging symbols found)...done.
warning: Unable to find libthread_db matching inferior's thread library, thread debugging will not be available.
Loaded symbols for /lib/libpthread.so.0
Reading symbols from /lib/libm.so.6...(no debugging symbols found)...done.
Loaded symbols for /lib/libm.so.6
Reading symbols from /lib/librt.so.1...(no debugging symbols found)...done.
Loaded symbols for /lib/librt.so.1
Reading symbols from /lib/libc.so.6...(no debugging symbols found)...done.
Loaded symbols for /lib/libc.so.6
Reading symbols from /lib/ld-linux-armhf.so.3...(no debugging symbols found)...done.
Loaded symbols for /lib/ld-linux-armhf.so.3
warning: Unable to find libthread_db matching inferior's thread library, thread debugging will not be available.
0x76f3ed50 in ?? () from /lib/libpthread.so.0
(gdb) bt
#0 0x76f3ed50 in ?? () from /lib/libpthread.so.0
#1 0x00000000 in ?? ()
Backtrace stopped: previous frame identical to this frame (corrupt stack?)
(gdb)
#0 0x76f3ed50 in ?? () from /lib/libpthread.so.0
#1 0x00000000 in ?? ()
Backtrace stopped: previous frame identical to this frame (corrupt stack?)
(gdb) quit
A debugging session is active.
Inferior 1 [process 310] will be detached.
Quit anyway? (y or n) y
Detaching from program: /home/user/user/process_cc, process 310
Memory layout.
Start Addr End Addr Size Offset objfile
0x10000 0x23000 0x13000 0x0 /home/user/user/process_cc
0x33000 0x34000 0x1000 0x13000 /home/user/user/process_cc
0x34000 0x208000 0x1d4000 0x0
0x1eba000 0x1edb000 0x21000 0x0 [heap]
0x73800000 0x73801000 0x1000 0x0
0x73801000 0x74000000 0x7ff000 0x0 [stack:340]
0x74000000 0x74001000 0x1000 0x0
0x74001000 0x74800000 0x7ff000 0x0 [stack:339]
0x74800000 0x74821000 0x21000 0x0
0x74821000 0x74900000 0xdf000 0x0
0x74900000 0x74921000 0x21000 0x0
0x74921000 0x74a00000 0xdf000 0x0
0x74a00000 0x74a21000 0x21000 0x0
0x74a21000 0x74b00000 0xdf000 0x0
0x74b64000 0x74b65000 0x1000 0x0
0x74b65000 0x75364000 0x7ff000 0x0 [stack:312]
0x75364000 0x75365000 0x1000 0x0
0x75365000 0x75b64000 0x7ff000 0x0 [stack:311]
0x75b64000 0x75b65000 0x1000 0x0
0x75b65000 0x76364000 0x7ff000 0x0 [stack:310]
0x76364000 0x76365000 0x1000 0x0
0x76365000 0x76b64000 0x7ff000 0x0 [stack:309]
0x76b64000 0x76d64000 0x200000 0xff200000 /dev/mem
0x76d64000 0x76e89000 0x125000 0x0 /lib/libc-2.20.so
0x76e89000 0x76e99000 0x10000 0x125000 /lib/libc-2.20.so
0x76e99000 0x76e9b000 0x2000 0x125000 /lib/libc-2.20.so
0x76e9b000 0x76e9c000 0x1000 0x127000 /lib/libc-2.20.so
0x76e9c000 0x76e9f000 0x3000 0x0
0x76e9f000 0x76ea5000 0x6000 0x0 /lib/librt-2.20.so
0x76ea5000 0x76eb4000 0xf000 0x6000 /lib/librt-2.20.so
---Type <return> to continue, or q <return> to quit---
0x76eb4000 0x76eb5000 0x1000 0x5000 /lib/librt-2.20.so
0x76eb5000 0x76eb6000 0x1000 0x6000 /lib/librt-2.20.so
0x76eb6000 0x76f1f000 0x69000 0x0 /lib/libm-2.20.so
0x76f1f000 0x76f2e000 0xf000 0x69000 /lib/libm-2.20.so
0x76f2e000 0x76f2f000 0x1000 0x68000 /lib/libm-2.20.so
0x76f2f000 0x76f30000 0x1000 0x69000 /lib/libm-2.20.so
0x76f30000 0x76f44000 0x14000 0x0 /lib/libpthread-2.20.so
0x76f44000 0x76f54000 0x10000 0x14000 /lib/libpthread-2.20.so
0x76f54000 0x76f55000 0x1000 0x14000 /lib/libpthread-2.20.so
0x76f55000 0x76f56000 0x1000 0x15000 /lib/libpthread-2.20.so
0x76f56000 0x76f58000 0x2000 0x0
0x76f58000 0x76f6e000 0x16000 0x0 /usr/lib/liblog4c.so.3
0x76f6e000 0x76f75000 0x7000 0x16000 /usr/lib/liblog4c.so.3
0x76f75000 0x76f77000 0x2000 0x15000 /usr/lib/liblog4c.so.3
0x76f77000 0x76f96000 0x1f000 0x0 /lib/ld-2.20.so
0x76f99000 0x76f9b000 0x2000 0x0
0x76fa4000 0x76fa5000 0x1000 0x0
0x76fa5000 0x76fa6000 0x1000 0x0 [sigpage]
0x76fa6000 0x76fa7000 0x1000 0x1f000 /lib/ld-2.20.so
0x76fa7000 0x76fa8000 0x1000 0x20000 /lib/ld-2.20.so
0x7e9f4000 0x7ea1a000 0x26000 0x0 [stack]
0xffff0000 0xffff1000 0x1000 0x0 [vectors]
Please point out the reason for such behavior so that the issue can be resolved.
asked on Stack Overflow May 7, 2020 by 
faiz321
faiz3211 Answer
Based on the strace output, it looks like all 7 threads are waiting for the same mutex:
[pid 312] futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL <unfinished ...>
[pid 340] futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL <unfinished ...>
[pid 339] futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL <unfinished ...>
[pid 311] futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL <unfinished ...>
[pid 310] futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL <unfinished ...>
[pid 309] futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL <unfinished ...>
[pid 297] futex(0x1eba830, FUTEX_WAIT_PRIVATE, 2, NULL <unfinished ...>
Attaching to the process (not a specific thread) with gdb and executing thread apply all bt would be a good start to identify which thread holds the mutex those threads are waiting for. If it is not obvious from the output, switch to one of the threads that are waiting (t <gdb-thread-id>), select the frame before the pthread_mutex_lock call (s <frame-id>; assuming pthread mutexes are used) and determine the owner by executing print <pthread_mutex_t-ptr>->__data.__owner. If gdb cannot resolve __data.__owner, you need to identify the owner via print *((int*)(<pthread_mutex_t-ptr>)+2). Search for the ID in the info threads output or in the initial command output to identify the owning thread and its stack trace (t <gdb-thread-id> and bt).
Be sure to create a core dump for later analysis by executing generate in gdb (can be reopened later with gdb <executable> <core-dump>).
answered on Stack Overflow May 12, 2020 by 
horstr
horstrUser contributions licensed under CC BY-SA 3.0