我编写了一个代码来创建一些线程,每当其中一个线程完成时,就会创建一个新线程来替换它。由于我无法使用 pthreads 创建大量线程 (>450),因此我使用了 clone 系统调用。(请注意,我知道拥有如此大量线程的含义,但这个程序只是为了给系统施加压力)。
由于 clone() 需要将子线程的堆栈空间指定为参数,因此我为每个线程分配所需的堆栈空间块并在线程完成时释放它。当一个线程完成时,我向父级发送一个信号以通知它。
代码如下:
#include <sched.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <signal.h>
#include <unistd.h>
#include <errno.h>
#define NUM_THREADS 5
unsigned long long total_count=0;
int num_threads = NUM_THREADS;
static int thread_pids[NUM_THREADS];
static void *thread_stacks[NUM_THREADS];
int ppid;
int worker() {
int i;
union sigval s={0};
for(i=0;i!=99999999;i++);
if(sigqueue(ppid, SIGUSR1, s)!=0)
fprintf(stderr, "ERROR sigqueue");
fprintf(stderr, "Child [%d] done\n", getpid());
return 0;
}
void sigint_handler(int signal) {
char fname[35]="";
FILE *fp;
int ch;
if(signal == SIGINT) {
fprintf(stderr, "Caught SIGINT\n");
sprintf(fname, "/proc/%d/status", getpid());
fp = fopen(fname,"r");
while((ch=fgetc(fp))!=EOF)
fprintf(stderr, "%c", (char)ch);
fclose(fp);
fprintf(stderr, "No. of threads created so far = %llu\n", total_count);
exit(0);
} else
fprintf(stderr, "Unhandled signal (%d) received\n", signal);
}
int main(int argc, char *argv[]) {
int rc, i; long t;
void *chld_stack, *chld_stack2;
siginfo_t siginfo;
sigset_t sigset, oldsigset;
if(argc>1) {
num_threads = atoi(argv[1]);
if(num_threads<1) {
fprintf(stderr, "Number of threads must be >0\n");
return -1;
}
}
signal(SIGINT, sigint_handler);
/* Block SIGUSR1 */
sigemptyset(&sigset);
sigaddset(&sigset, SIGUSR1);
if(sigprocmask(SIG_BLOCK, &sigset, &oldsigset)==-1)
fprintf(stderr, "ERROR: cannot block SIGUSR1 \"%s\"\n", strerror(errno));
printf("Number of threads = %d\n", num_threads);
ppid = getpid();
for(t=0,i=0;t<num_threads;t++,i++) {
chld_stack = (void *) malloc(148*512);
chld_stack2 = ((char *)chld_stack + 148*512 - 1);
if(chld_stack == NULL) {
fprintf(stderr, "ERROR[%ld]: malloc for stack-space failed\n", t);
break;
}
rc = clone(worker, chld_stack2, CLONE_VM|CLONE_FS|CLONE_FILES, NULL);
if(rc == -1) {
fprintf(stderr, "ERROR[%ld]: return code from pthread_create() is %d\n", t, errno);
break;
}
thread_pids[i]=rc;
thread_stacks[i]=chld_stack;
fprintf(stderr, " [index:%d] = [pid:%d] ; [stack:0x%p]\n", i, thread_pids[i], thread_stacks[i]);
total_count++;
}
sigemptyset(&sigset);
sigaddset(&sigset, SIGUSR1);
while(1) {
fprintf(stderr, "Waiting for signal from childs\n");
if(sigwaitinfo(&sigset, &siginfo) == -1)
fprintf(stderr, "- ERROR returned by sigwaitinfo : \"%s\"\n", strerror(errno));
fprintf(stderr, "Got some signal from pid:%d\n", siginfo.si_pid);
/* A child finished, free the stack area allocated for it */
for(i=0;i<NUM_THREADS;i++) {
fprintf(stderr, " [index:%d] = [pid:%d] ; [stack:%p]\n", i, thread_pids[i], thread_stacks[i]);
if(thread_pids[i]==siginfo.si_pid) {
free(thread_stacks[i]);
thread_stacks[i]=NULL;
break;
}
}
fprintf(stderr, "Search for child ended with i=%d\n",i);
if(i==NUM_THREADS)
continue;
/* Create a new thread in its place */
chld_stack = (void *) malloc(148*512);
chld_stack2 = ((char *)chld_stack + 148*512 - 1);
if(chld_stack == NULL) {
fprintf(stderr, "ERROR[%ld]: malloc for stack-space failed\n", t);
break;
}
rc = clone(worker, chld_stack2, CLONE_VM|CLONE_FS|CLONE_FILES, NULL);
if(rc == -1) {
fprintf(stderr, "ERROR[%ld]: return code from clone() is %d\n", t, errno);
break;
}
thread_pids[i]=rc;
thread_stacks[i]=chld_stack;
total_count++;
}
fprintf(stderr, "Broke out of infinite loop. [total_count=%llu] [i=%d]\n",total_count, i);
return 0;
}
我使用了几个数组来跟踪子进程的 pid 和堆栈区基地址(用于释放它)。
当我运行这个程序时,它会在一段时间后终止。使用 gdb 运行告诉我其中一个线程出现 SIGSEGV(分段错误)。但它没有给我任何位置,输出类似于以下内容:
Program received signal SIGSEGV, Segmentation fault.
[Switching to LWP 15864]
0x00000000 in ?? ()
我尝试使用以下命令行在 valgrind 下运行它:
valgrind --tool=memcheck --leak-check=yes --show-reachable=yes -v --num-callers=20 --track-fds=yes ./a.out
但它在 valgrind 下继续运行,没有任何问题。
我对如何调试这个程序感到困惑。我觉得这可能是一些堆栈溢出或其他问题,但增加堆栈大小(高达 74KB)并没有解决问题。
我唯一的疑问是分段错误的原因和位置或如何调试此程序。