我有一个要尽可能提高韧性的大型程序,其中包含大量线程。
我需要捕获SIGBUS
SIGSEGV
信号,并在必要时重新初始化问题线程,或禁用线程以继续使用降低的功能。
我的第一个想法是执行setjump
,然后设置信号处理程序,可以记录问题,然后进行longjump
返回到线程中的恢复点。问题在于,信号处理程序需要确定信号来自哪个线程,以使用适当的跳转缓冲区,否则跳回错误的线程将毫无意义。
有没有人有任何想法如何在信号处理程序中确定有问题的线程?
我有一个要尽可能提高韧性的大型程序,其中包含大量线程。
我需要捕获SIGBUS
SIGSEGV
信号,并在必要时重新初始化问题线程,或禁用线程以继续使用降低的功能。
我的第一个想法是执行setjump
,然后设置信号处理程序,可以记录问题,然后进行longjump
返回到线程中的恢复点。问题在于,信号处理程序需要确定信号来自哪个线程,以使用适当的跳转缓冲区,否则跳回错误的线程将毫无意义。
有没有人有任何想法如何在信号处理程序中确定有问题的线程?
#include <assert.h>
#include <errno.h>
#include <pthread.h>
#include <signal.h>
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include <sys/syscall.h>
#define MAX_DAFT_THREADS (1024) // arbitrary
#define CHECK_OSCALL(call, onfail) { \
if ((call) == -1) { \
char buf[512]; \
strerror_r(errno, buf, sizeof(buf)); \
fprintf(stderr, "%s@%d failed: %s\n", __FILE__, __LINE__, buf); \
onfail; \
} \
}
/*********************** daft thread accounting *****************/
typedef void* (*threadproc_t)(void* arg);
struct daft_thread_t {
threadproc_t start_routine;
void* start_routine_arg;
pthread_t pthread;
pid_t tid;
};
struct daft_thread_accounting_info_t {
int monitor_pipe[2];
pthread_mutex_t info_lock;
size_t daft_thread_count;
struct daft_thread_t daft_threads[MAX_DAFT_THREADS];
};
static struct daft_thread_accounting_info_t g_thread_accounting;
void daft_thread_accounting_info_init(struct daft_thread_accounting_info_t* inf)
{
memset(inf, 0, sizeof(*inf));
pthread_mutex_init(&inf->info_lock, NULL);
CHECK_OSCALL(pipe(inf->monitor_pipe), abort());
}
struct daft_thread_wrapper_data_t {
struct daft_thread_t* thread_info;
};
static void* daft_thread_wrapper(void* arg)
{
struct daft_thread_t* wrapper = arg;
wrapper->tid = gettid();
return (*wrapper->start_routine)(wrapper->start_routine_arg);
}
static void start_daft_thread(threadproc_t proc, void* arg)
{
struct daft_thread_t* info;
pthread_mutex_lock(&g_thread_accounting.info_lock);
assert (g_thread_accounting.daft_thread_count < MAX_DAFT_THREADS);
info = &g_thread_accounting.daft_threads[g_thread_accounting.daft_thread_count++];
pthread_mutex_unlock(&g_thread_accounting.info_lock);
info->start_routine = proc;
info->start_routine_arg = arg;
CHECK_OSCALL(pthread_create(&info->pthread, NULL, daft_thread_wrapper, info), abort());
}
static struct daft_thread_t* find_thread_by_tid(pid_t thread_id)
{
int k;
struct daft_thread_t* info = NULL;
pthread_mutex_lock(&g_thread_accounting.info_lock);
for (k = 0; k < g_thread_accounting.daft_thread_count; ++k) {
if (g_thread_accounting.daft_threads[k].tid == thread_id) {
info = &g_thread_accounting.daft_threads[k];
break;
}
}
pthread_mutex_unlock(&g_thread_accounting.info_lock);
return info;
}
static void restart_daft_thread(struct daft_thread_t* info)
{
void* unused;
CHECK_OSCALL(pthread_cancel(info->pthread), abort());
CHECK_OSCALL(pthread_join(info->pthread, &unused), abort());
info->tid = 0;
CHECK_OSCALL(pthread_create(&info->pthread, NULL, daft_thread_wrapper, info), abort());
}
/************* signal handling stuff **************/
struct sigdeath_notify_info {
int signum;
pid_t tid;
};
static void sigdeath_handler(int signum, siginfo_t* info, void* ctx)
{
int z;
struct sigdeath_notify_info inf = {
.signum = signum,
.tid = gettid()
};
z = write(g_thread_accounting.monitor_pipe[1], &inf, sizeof(inf));
assert (z == sizeof(inf)); // or else SIGABRT. Are we handling that too? Hope not.
pause(); // returning doesn't do us any good.
}
static void register_signal_handlers()
{
struct sigaction sa = {};
sa.sa_sigaction = sigdeath_handler;
sa.sa_flags = SA_SIGINFO;
CHECK_OSCALL(sigaction(SIGSEGV, &sa, NULL), abort());
CHECK_OSCALL(sigaction(SIGBUS, &sa, NULL), abort());
}
pid_t gettid() { return (pid_t) syscall(SYS_gettid); }
/** This is the code that segfaults randomly. Kwality with a 'k'. */
static void* someone_please_fix_me(void* arg)
{
char* i_think_this_address_looks_nice = (char*) 42;
sleep(1 + rand() % 200);
i_think_this_address_looks_nice[0] = 'q'; // ugh
return NULL;
}
// main() will serve as the monitor thread here
int main()
{
int k;
struct sigdeath_notify_info death;
daft_thread_accounting_info_init(&g_thread_accounting);
register_signal_handlers();
for (k = 0; k < 200; ++k) {
start_daft_thread(someone_please_fix_me, (void*) k);
}
while (read(g_thread_accounting.monitor_pipe[0], &death, sizeof(death)) == sizeof(death)) {
struct daft_thread_t* info = find_thread_by_tid(death.tid);
if (info == NULL) {
fprintf(stderr, "*** thread_id %u not found\n", death.tid);
continue;
}
fprintf(stderr, "Thread %u (%d) died of %d, restarting.\n",
death.tid, (int) info->start_routine_arg, death.signum);
restart_daft_thread(info);
}
fprintf(stderr, "Shouldn't get here.\n");
return 0;
}
在我的Linux系统上,使用syscall(SYS_gettid)
可以正常工作:gcc pt.c -lpthread -Wall -Wextra
//pt.c
#define _GNU_SOURCE
#include <stdio.h>
#include <pthread.h>
#include <unistd.h>
#include <sys/syscall.h>
#include <setjmp.h>
#include <signal.h>
#include <string.h>
#include <ucontext.h>
#include <stdlib.h>
static sigjmp_buf jmpbuf[65536];
static void handler(int sig, siginfo_t *siginfo, void *context)
{
//ucontext_t *ucontext = context;
pid_t tid = syscall(SYS_gettid);
printf("Thread %d in handler, signal %d\n", tid, sig);
siglongjmp(jmpbuf[tid], 1);
}
static void *threadfunc(void *data)
{
int index, segvindex = *(int *)data;
pid_t tid = syscall(SYS_gettid);
for(index = 0; index < 500; index++) {
if (sigsetjmp(jmpbuf[tid], 1) == 1) {
printf("Recovery of thread %d\n", tid);
continue;
}
printf("Thread %d, index %d\n", tid, index);
if (index % 5 == segvindex) {
printf("%zu\n", strlen((char *)2)); // SIGSEGV
}
pthread_yield();
}
return NULL;
}
int main(void)
{
pthread_t thread1, thread2, thread3;
int segvindex1 = rand() % 5;
int segvindex2 = rand() % 5;
int segvindex3 = rand() % 5;
struct sigaction sact;
memset(&sact, 0, sizeof sact);
sact.sa_sigaction = handler;
sact.sa_flags = SA_SIGINFO;
if (sigaction(SIGSEGV, &sact, NULL) < 0) {
perror("sigaction");
return 1;
}
pthread_create(&thread1, NULL, &threadfunc, (void *) &segvindex1);
pthread_create(&thread2, NULL, &threadfunc, (void *) &segvindex2);
pthread_create(&thread3, NULL, &threadfunc, (void *) &segvindex3);
pthread_join(thread1, NULL);
pthread_join(thread2, NULL);
pthread_join(thread3, NULL);
return 0;
}
pthread_self
。它是异步信号安全的。SIGSEGV
的线程应该通过异步信号安全的方式启动一个新线程,而不应该执行siglongjmp
,因为这可能会导致调用非异步信号安全的函数。syscall(SYS_gettid)
是异步信号安全的。它满足所有异步信号安全规则。由于它是Linux特有的,因此不在异步信号安全函数的POSIX列表上。几乎相同的getpid()
在列表上。 - 4566976
sigsetjump()/siglongjmp()
而不是setjmp()/longjmp()
,这样就不需要重置信号处理程序。 - Andrew Henle