Redis是单线程还是双线程？适用场景及经验总结 road

尊重劳动成功，转载请附上本文链接及作者：jianfeng_soft@163.com   （road）

         最近（周五）在与朋友聊天时，聊到他们做游戏服务端用到一个排行榜的功能，自然接下来我们就聊到了redis，但由于线程问题，网上普遍看到都是单线程，不管是单线程或但即便是双线程，hashes..hgetall...也会出现cpu瓶颈，对于解决此瓶颈，目前能想到的就是在前面先打一层MC(Midnight Commander)来减少请求量

     个人总结，在试用redis前，首先需要准确定位你是使用redis 的 cache呢还是使用她的存储？

     cache实用于前面提到的排行榜，统计短数据量的场景，因为用redis的list存排行榜数据，如果内存不够可以T出。

     另外我大致以个人经验简述一下redis的场景和注意事项，希望能给未有过实用经验的小伙伴带来一些帮助，redis 只适合应用于大量写入复杂的数据结构，或者简单的数据结构但要持久化的场景，并且最关键是数据容量必须要小于内存，

     因此必须要在使用前做硬件内存容量规划，比如未来的增长预算，当前存入一个hashes kv需要占用多少空间，依此来做预算。

     即便做了持久化，内存碎片也很严重，意思就是即便数据被移到磁盘（rdb或aof），所有数据始终都会仍然存在于占用内存 （因此你需要考虑是否需要做持久化？做持久化是选择rdb还是aof？）

           rdb： 好处是只会短期内影响读写速度，但是可能丢数据 ；

           aof： 每一次写都导致有性能下级，并且恢复时间要长，比mc的延迟更高，特别是做了持久化，即便不做持久化也比mc更延迟。

    综合评测redis优缺点
         优点：内存操作特别快，高级的数据结构可用， 
         缺点：磁盘操作慢，偶尔延迟，耗内存 

最后附带以下是段落是摘自网络对redis线程（单双之谜）进行贴码透析：

多进程分析：

 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对cache落盘时有save和bgsave两种方式。bgsave将会fork()出一个后台进程。关键在于这一行代码：if ((childpid = fork()) == 0)

而redis的多线程是怎么实现的呢？

在bio.h里有几行关键的代码。

 /* 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

这里，redis定义了background IO job数量为2。可以大胆地猜测，background job的数量会随着这个server软件的复杂度而增加，甚至，会把bio提升成为background job层面。

那么，这两个线程是如何生成的呢？

 /* 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);
         }
     }
 }

这里的

 /* 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);
         }
     }

创建了REDIS_BIO_NUM_OPS个线程。

这两个线程的入口函数都是bioProcessBackgroundJobs，那reds怎么知道到底是要对应REDIS_BIO_CLOSE_FILE类型还是对应REDIS_BIO_AOF_FSYNC呢？

我们看一下代码。

 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]--;
     }
 }

关键就在以下代码。

 /* 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().");
        }