今天和以前的同事聊了下Redis的執行緒與程序。晚上仔細地翻了下程式碼。把內容整理一下發表出來。

事實上，redis是支援多程序與多執行緒的（從2.x？之後），而不是網上千篇一律的redis單執行緒單程序。

多程序分析：

int rdbSaveBackground(char *filename) {
    pid_t childpid;
    long long start;

    if (server.rdb_child_pid != -1) return REDIS_ERR;

    server.dirty_before_bgsave = server.dirty;
    server.lastbgsave_try = time
 
(NULL);

    start = ustime();
    if ((childpid = fork()) == 0) {
        int retval;

        /* Child */
        if (server.ipfd > 0) close(server.ipfd);
        if (server.sofd > 0) close(server.sofd);
        retval = rdbSave(filename);
        if (retval == REDIS_OK) {
            size_t private_dirty = zmalloc_get_private_dirty();

            if
 
 (private_dirty) {
                redisLog(REDIS_NOTICE,
                    "RDB: %zu MB of memory used by copy-on-write",
                    private_dirty/(1024*1024));
            }
        }
        exitFromChild((retval == REDIS_OK) ? 0 : 1);
    } else {
        /* Parent */
        server.stat_fork_time = ustime()-start;
        if
 
 (childpid == -1) {
            server.lastbgsave_status = REDIS_ERR;
            redisLog(REDIS_WARNING,"Can't save in background: fork: %s",
                strerror(errno));
            return REDIS_ERR;
        }
        redisLog(REDIS_NOTICE,"Background saving started by pid %d",childpid);
        server.rdb_save_time_start = time(NULL);
        server.rdb_child_pid = childpid;
        updateDictResizePolicy();
        return REDIS_OK;
    }
    return REDIS_OK; /* unreached */
}

redis對cache落盤時有save和bgsave兩種方式。bgsave將會fork()出一個後臺程序。關鍵在於這一行程式碼：if ((childpid = fork()) == 0)

而redis的多執行緒是怎麼實現的呢？

在bio.h裡有幾行關鍵的程式碼。

/* Background job opcodes */
#define REDIS_BIO_CLOSE_FILE    0 /* Deferred close(2) syscall. */
#define REDIS_BIO_AOF_FSYNC     1 /* Deferred AOF fsync. */
#define REDIS_BIO_NUM_OPS       2

這裡，redis定義了background IO job數量為2。可以大膽地猜測，background job的數量會隨著這個server軟體的複雜度而增加，甚至，會把bio提升成為background job層面。

那麼，這兩個執行緒是如何生成的呢？

/* Initialize the background system, spawning the thread. */
void bioInit(void) {
    pthread_attr_t attr;
    pthread_t thread;
    size_t stacksize;
    int j;

    /* Initialization of state vars and objects */
    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;
    }

    /* 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. */
    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);
        }
    }
}

這裡的

/* 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. */
    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);
        }
    }

建立了REDIS_BIO_NUM_OPS個執行緒。

這兩個執行緒的入口函式都是bioProcessBackgroundJobs，那reds怎麼知道到底是要對應REDIS_BIO_CLOSE_FILE型別還是對應REDIS_BIO_AOF_FSYNC呢？

我們看一下程式碼。

void *bioProcessBackgroundJobs(void *arg) {
    struct bio_job *job;
    unsigned long type = (unsigned long) arg;
    sigset_t sigset;

    pthread_detach(pthread_self());
    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. */
        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) {
            close((long)job->arg1);
        } else if (type == REDIS_BIO_AOF_FSYNC) {
            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]--;
    }
}

關鍵就在以下程式碼。

/* Process the job accordingly to its type. */
        if (type == REDIS_BIO_CLOSE_FILE) {
            close((long)job->arg1);
        } else if (type == REDIS_BIO_AOF_FSYNC) {
            aof_fsync((long)job->arg1);
        } else {
            redisPanic("Wrong job type in bioProcessBackgroundJobs().");
        }

明白了嗎？:)