在close系统调用时,当一个文件的最后一个owner在执行该操作时,会执行unlink,从而陷入阻塞.

而调用fsync时,会把文件数据强制刷新到磁盘中,这个速度比较慢,而调用io时,底层会调用该操作,使得io操作阻塞在此处.

为了解决上述两个问题,bio的机制是,在后台启动的两个线程,一个线程为关闭文件功能即close系统调用,另一个是将文件的更新同步到磁盘上的操作即fsync系统调用.

具体实现位于文件bio.c中.

//任务格式
struct bio_job {
    //任务创建时间
    time_t time; /* Time at which the job was created. */
    /* Job specific arguments pointers. If we need to pass more than three
     * arguments we can just pass a pointer to a structure or alike. */
     //参数
    void *arg1, *arg2, *arg3;
};

//bio线程初始化
void bioInit(void) {
    pthread_attr_t attr;
    pthread_t thread;
    size_t stacksize;
    int j;

    /* Initialization of state vars and objects */
    //两个线程,初始化相关变量
    for (j = 0; j < REDIS_BIO_NUM_OPS; j++) {
        pthread_mutex_init(&bio_mutex[j],NULL);
        pthread_cond_init(&bio_condvar[j],NULL);
        bio_jobs[j] = listCreate();
        bio_pending[j] = 0;
    }
    //设置栈空间
    /* Set the stack size as by default it may be small in some system */
    pthread_attr_init(&attr);
    pthread_attr_getstacksize(&attr,&stacksize);
    if (!stacksize) stacksize = 1; /* The world is full of Solaris Fixes */
    while (stacksize < REDIS_THREAD_STACK_SIZE) stacksize *= 2;
    pthread_attr_setstacksize(&attr, stacksize);

    /* Ready to spawn our threads. We use the single argument the thread
     * function accepts in order to pass the job ID the thread is
     * responsible of. */
    //启动线程
    for (j = 0; j < REDIS_BIO_NUM_OPS; j++) {
        void *arg = (void*)(unsigned long) j;
        if (pthread_create(&thread,&attr,bioProcessBackgroundJobs,arg) != 0) {
            redisLog(REDIS_WARNING,"Fatal: Can't initialize Background Jobs.");
            exit(1);
        }
        bio_threads[j] = thread;
    }
}
//增加任务
void bioCreateBackgroundJob(int type, void *arg1, void *arg2, void *arg3) {
    struct bio_job *job = zmalloc(sizeof(*job));

    job->time = time(NULL);
    job->arg1 = arg1;
    job->arg2 = arg2;
    job->arg3 = arg3;
    pthread_mutex_lock(&bio_mutex[type]);
    listAddNodeTail(bio_jobs[type],job);
    bio_pending[type]++;
    pthread_cond_signal(&bio_condvar[type]);
    pthread_mutex_unlock(&bio_mutex[type]);
}
//后台线程主函数
void *bioProcessBackgroundJobs(void *arg) {
    struct bio_job *job;
    unsigned long type = (unsigned long) arg;
    sigset_t sigset;

    /* Make the thread killable at any time, so that bioKillThreads()
     * can work reliably. */
    pthread_setcancelstate(PTHREAD_CANCEL_ENABLE, NULL);
    pthread_setcanceltype(PTHREAD_CANCEL_ASYNCHRONOUS, NULL);

    pthread_mutex_lock(&bio_mutex[type]);
    /* Block SIGALRM so we are sure that only the main thread will
     * receive the watchdog signal. */
    sigemptyset(&sigset);
    sigaddset(&sigset, SIGALRM);
    if (pthread_sigmask(SIG_BLOCK, &sigset, NULL))
        redisLog(REDIS_WARNING,
            "Warning: can't mask SIGALRM in bio.c thread: %s", strerror(errno));

    while(1) {
        listNode *ln;

        /* The loop always starts with the lock hold. */
        if (listLength(bio_jobs[type]) == 0) {
            pthread_cond_wait(&bio_condvar[type],&bio_mutex[type]);
            continue;
        }
        /* Pop the job from the queue. */
        //取出任务
        ln = listFirst(bio_jobs[type]);
        job = ln->value;
        /* It is now possible to unlock the background system as we know have
         * a stand alone job structure to process.*/
        pthread_mutex_unlock(&bio_mutex[type]);

        /* Process the job accordingly to its type. */
        if (type == REDIS_BIO_CLOSE_FILE) {
            //如果是文件类型,关闭文件
            close((long)job->arg1);
        } else if (type == REDIS_BIO_AOF_FSYNC) {
            //将文件内容同步到磁盘上
            aof_fsync((long)job->arg1);
        } else {
            redisPanic("Wrong job type in bioProcessBackgroundJobs().");
        }
        zfree(job);

        /* Lock again before reiterating the loop, if there are no longer
         * jobs to process we'll block again in pthread_cond_wait(). */
        pthread_mutex_lock(&bio_mutex[type]);
        listDelNode(bio_jobs[type],ln);
        bio_pending[type]--;
    }
}
//返回type类型的任务个数
unsigned long long bioPendingJobsOfType(int type) {
    unsigned long long val;
    pthread_mutex_lock(&bio_mutex[type]);
    val = bio_pending[type];
    pthread_mutex_unlock(&bio_mutex[type]);
    return val;
}
//杀掉bio后台线程
void bioKillThreads(void) {
    int err, j;

    for (j = 0; j < REDIS_BIO_NUM_OPS; j++) {
        if (pthread_cancel(bio_threads[j]) == 0) {
            if ((err = pthread_join(bio_threads[j],NULL)) != 0) {
                redisLog(REDIS_WARNING,
                    "Bio thread for job type #%d can be joined: %s",
                        j, strerror(err));
            } else {
                redisLog(REDIS_WARNING,
                    "Bio thread for job type #%d terminated",j);
            }
        }
    }
}