用strace处理程序异常挂死情况

1. 环境：

ubuntu 系统 + strace + vim

2.编写挂死程序：(参考博客）

#include <stdio.h>
#include <sys/types.h>
#include <unistd.h>
#include <string.h>

int main(int argc, char** argv)
{
        getpid();
        if(argc < 2)
        {
                printf("pick one (user|system)\n");
                return 1;
        }
        if(!strcmp(argv[1], "user"))
                while(1);
        else if(!strcmp(argv[1], "system"))
                sleep(500);    

        return 0;
}

3.利用strace查看日志：

root@:~/watson# strace ./a.out user -o user_trace.log
execve("./a.out", ["./a.out", "user", "-o", "user_trace.log"], [/* 20 vars */]) = 0
brk(0)                                  = 0x9b49000
access("/etc/ld.so.nohwcap", F_OK)      = -1 ENOENT (No such file or directory)
mmap2(NULL, 8192, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0) = 0xb7773000
access("/etc/ld.so.preload", R_OK)      = -1 ENOENT (No such file or directory)
open("/etc/ld.so.cache", O_RDONLY|O_CLOEXEC) = 3
fstat64(3, {st_mode=S_IFREG|0644, st_size=91359, ...}) = 0
mmap2(NULL, 91359, PROT_READ, MAP_PRIVATE, 3, 0) = 0xb775c000
close(3)                                = 0
access("/etc/ld.so.nohwcap", F_OK)      = -1 ENOENT (No such file or directory)
open("/lib/i386-linux-gnu/libc.so.6", O_RDONLY|O_CLOEXEC) = 3
read(3, "\177ELF\1\1\1\0\0\0\0\0\0\0\0\0\3\0\3\0\1\0\0\0000\226\1\0004\0\0\0"..., 512) = 512
fstat64(3, {st_mode=S_IFREG|0755, st_size=1730024, ...}) = 0
mmap2(NULL, 1743580, PROT_READ|PROT_EXEC, MAP_PRIVATE|MAP_DENYWRITE, 3, 0) = 0xb75b2000
mprotect(0xb7755000, 4096, PROT_NONE)   = 0
mmap2(0xb7756000, 12288, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 0x1a3) = 0xb7756000
mmap2(0xb7759000, 10972, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_ANONYMOUS, -1, 0) = 0xb7759000
close(3)                                = 0
mmap2(NULL, 4096, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0) = 0xb75b1000
set_thread_area({entry_number:-1 -> 6, base_addr:0xb75b1900, limit:1048575, seg_32bit:1, contents:0, read_exec_only:0, limit_in_pages:1, seg_not_present:0, useable:1}) = 0
mprotect(0xb7756000, 8192, PROT_READ)   = 0
mprotect(0x8049000, 4096, PROT_READ)    = 0
mprotect(0xb7796000, 4096, PROT_READ)   = 0
munmap(0xb775c000, 91359)               = 0
getpid()                                = 28915

root@：~/watson# strace ./a.out system -o kernel_trace.log
execve("./a.out", ["./a.out", "system", "-o", "kernel_trace.log"], [/* 20 vars */]) = 0
brk(0)                                  = 0x8ee6000
access("/etc/ld.so.nohwcap", F_OK)      = -1 ENOENT (No such file or directory)
mmap2(NULL, 8192, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0) = 0xb7769000
access("/etc/ld.so.preload", R_OK)      = -1 ENOENT (No such file or directory)
open("/etc/ld.so.cache", O_RDONLY|O_CLOEXEC) = 3
fstat64(3, {st_mode=S_IFREG|0644, st_size=91359, ...}) = 0
mmap2(NULL, 91359, PROT_READ, MAP_PRIVATE, 3, 0) = 0xb7752000
close(3)                                = 0
access("/etc/ld.so.nohwcap", F_OK)      = -1 ENOENT (No such file or directory)
open("/lib/i386-linux-gnu/libc.so.6", O_RDONLY|O_CLOEXEC) = 3
read(3, "\177ELF\1\1\1\0\0\0\0\0\0\0\0\0\3\0\3\0\1\0\0\0000\226\1\0004\0\0\0"..., 512) = 512
fstat64(3, {st_mode=S_IFREG|0755, st_size=1730024, ...}) = 0
mmap2(NULL, 1743580, PROT_READ|PROT_EXEC, MAP_PRIVATE|MAP_DENYWRITE, 3, 0) = 0xb75a8000
mprotect(0xb774b000, 4096, PROT_NONE)   = 0
mmap2(0xb774c000, 12288, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 0x1a3) = 0xb774c000
mmap2(0xb774f000, 10972, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_ANONYMOUS, -1, 0) = 0xb774f000
close(3)                                = 0
mmap2(NULL, 4096, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0) = 0xb75a7000
set_thread_area({entry_number:-1 -> 6, base_addr:0xb75a7900, limit:1048575, seg_32bit:1, contents:0, read_exec_only:0, limit_in_pages:1, seg_not_present:0, useable:1}) = 0
mprotect(0xb774c000, 8192, PROT_READ)   = 0
mprotect(0x8049000, 4096, PROT_READ)    = 0
mprotect(0xb778c000, 4096, PROT_READ)   = 0
munmap(0xb7752000, 91359)               = 0
getpid()                                = 28917
rt_sigprocmask(SIG_BLOCK, [CHLD], [], 8) = 0
rt_sigaction(SIGCHLD, NULL, {SIG_DFL, [], 0}, 8) = 0
rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0
nanosleep({500, 0}, 

tip：

1. 对于user层面测试，出现

getpid()                                = 28934
^C--- SIGINT (Interrupt) @ 0 (0) ---

SIGINT的捕捉，中断出现。

对于 getpid() = 28915，则是getid()函数执行的过程，后续无log输出。

陷入while(1)操作。

2. 对于system层面测试，出现

nanosleep({500, 0}, ^C <unfinished ...>

unfinished出现。

nanosleep 是未完整，当修改程序sleep(1)

nanosleep({1, 0}, 0xbfac2df8)           = 0
exit_group(0)                           = ?

最终退出exit_group

是因为在调用sleep时卡死，没法正常运行，是挂死在系统调用。（具体看接口手册）

4. 结论（前提没有exit_group)
1. strace log显示最终的log完整，则卡死在程序逻辑上。

2. strace log显示最终的log不完整，则卡死在系统调用上。

（结论或许有反驳，当调用一个get_id的接口是，该接口自己实现的。）

int get_id()
{
　　return 1;
}

输出的log不完整，也就挂死在get_id，该也是调用，并非系统调用。