Linux coredump解决流程

一、打开core文件限制

a.sudo vi /etc/profile

b.文件末尾添加ulimit -c unlimited

source /etc/profile

把文件重新加载到内存

c.root@ubuntu:~/code# ulimit -c

unlimited

说明core文件限制已经去处。

二、让core文件生成在进程当前目录

echo "core-%e-%p-%t" > /proc/sys/kernel/core_pattern

三、写一个同一块内存释放两次引起coredump的例子定位并解决

a.编写err.cpp代码如下，同一块内存释放了两次。

root@ubuntu:~/code# cat err.cpp

#include<cstdlib>
using namespace std;
void repeatFree(char *p)
{
if(NULL != p)
{
free(p);
}
}
int main()
{
char* pstr =(char*) malloc();
free(pstr);
repeatFree(pstr);
}

b.g++ -o err err.cpp

编译生成err可执行文件。

c.  ./err

root@ubuntu:~/code# ./err 

*** Error in `./err': double free or corruption (top): 0x0000000001911010 ***

======= Backtrace: =========

/lib/x86_64-linux-gnu/libc.so.(+0x77725)[0x7fbe4039f725]

/lib/x86_64-linux-gnu/libc.so.(+0x7ff4a)[0x7fbe403a7f4a]

/lib/x86_64-linux-gnu/libc.so.(cfree+0x4c)[0x7fbe403ababc]

./err[0x400585]

./err[0x4005b6]

/lib/x86_64-linux-gnu/libc.so.(__libc_start_main+0xf0)[0x7fbe40348830]

./err[0x400499]

======= Memory map: ========

- r-xp  :  /root/code/err

- r--p  :  /root/code/err

- rw-p  :  /root/code/err

- rw-p  :    [heap]

7fbe3c000000-7fbe3c021000 rw-p  :  

7fbe3c021000-7fbe40000000 ---p  :  

7fbe40112000-7fbe40128000 r-xp  :   /lib/x86_64-linux-gnu/libgcc_s.so.

7fbe40128000-7fbe40327000 ---p  :   /lib/x86_64-linux-gnu/libgcc_s.so.

7fbe40327000-7fbe40328000 rw-p  :   /lib/x86_64-linux-gnu/libgcc_s.so.

7fbe40328000-7fbe404e8000 r-xp  :   /lib/x86_64-linux-gnu/libc-2.23.so

7fbe404e8000-7fbe406e7000 ---p 001c0000 :   /lib/x86_64-linux-gnu/libc-2.23.so

7fbe406e7000-7fbe406eb000 r--p 001bf000 :   /lib/x86_64-linux-gnu/libc-2.23.so

7fbe406eb000-7fbe406ed000 rw-p 001c3000 :   /lib/x86_64-linux-gnu/libc-2.23.so

7fbe406ed000-7fbe406f1000 rw-p  :  

7fbe406f1000-7fbe40717000 r-xp  :   /lib/x86_64-linux-gnu/ld-2.23.so

7fbe408fb000-7fbe408fe000 rw-p  :  

7fbe40913000-7fbe40916000 rw-p  :  

7fbe40916000-7fbe40917000 r--p  :   /lib/x86_64-linux-gnu/ld-2.23.so

7fbe40917000-7fbe40918000 rw-p  :   /lib/x86_64-linux-gnu/ld-2.23.so

7fbe40918000-7fbe40919000 rw-p  :  

7ffe51f1b000-7ffe51f3c000 rw-p  :        [stack]

7ffe51ff4000-7ffe51ff6000 r--p  :        [vvar]

7ffe51ff6000-7ffe51ff8000 r-xp  :        [vdso]

ffffffffff600000-ffffffffff601000 r-xp  :  [vsyscall]

Aborted (core dumped)

产生了core文件

root@ubuntu:~/code# ll

total 168

drwxr-xr-x  2 root root   4096 Mar  9 18:20 ./

drwx------ 10 root root   4096 Mar  9 18:18 ../

-rw-------  1 root root 544768 Mar  9 18:20 core-err-9665-1489112441

-rwxr-xr-x  1 root root   8696 Mar  9 18:20 err*

-rw-r--r--  1 root root    185 Mar  9 18:18 err.cpp

d.gdb ./err core-err-9665-1489112441

执行gdb 执行程序 core文件，然后在gdb里面where

root@ubuntu:~/code# gdb ./err core-err--

GNU gdb (Ubuntu 7.11-0ubuntu1) 7.11

Copyright (C)  Free Software Foundation, Inc.

License GPLv3+: GNU GPL version  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 "x86_64-linux-gnu".

Type "show configuration" for configuration details.

For bug reporting instructions, please see:

<http://www.gnu.org/software/gdb/bugs/>.

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"...

Reading symbols from ./err...(no debugging symbols found)...done.

[New LWP ]

Core was generated by `./err'.

Program terminated with signal SIGABRT, Aborted.

#  0x00007fbe4035d418 in __GI_raise (sig=sig@entry=) at ../sysdeps/unix/sysv/linux/raise.c:

../sysdeps/unix/sysv/linux/raise.c: No such file or directory.

(gdb) where

#  0x00007fbe4035d418 in __GI_raise (sig=sig@entry=) at ../sysdeps/unix/sysv/linux/raise.c:

#  0x00007fbe4035f01a in __GI_abort () at abort.c:

#  0x00007fbe4039f72a in __libc_message (do_abort=do_abort@entry=, fmt=fmt@entry=0x7fbe404b86b0 "*** Error in `%s': %s: 0x%s ***\n") at ../sysdeps/posix/libc_fatal.c:

#  0x00007fbe403a7f4a in malloc_printerr (ar_ptr=<optimized out>, ptr=<optimized out>, str=0x7fbe404b87a0 "double free or corruption (top)", action=) at malloc.c:

#  _int_free (av=<optimized out>, p=<optimized out>, have_lock=) at malloc.c:

#  0x00007fbe403ababc in __GI___libc_free (mem=<optimized out>) at malloc.c:

#  0x0000000000400585 in repeatFree(char*) ()

#  0x00000000004005b6 in main () 

通过调堆栈就能发现死在repeatFree(char*)函数里面，重复释放了同一块内存。