X-Git-Url: https://git.saurik.com/redis.git/blobdiff_plain/bafa88c8b700b1648b561e86dce6ceca4c139d46..b4b5144694a4134544221a5587b81a98aec608be:/src/dscache.c diff --git a/src/dscache.c b/src/dscache.c index fb862c05..31498358 100644 --- a/src/dscache.c +++ b/src/dscache.c @@ -73,6 +73,16 @@ * impossible since anyway the io_keys stuff will work as lock? * * - Serialize special encoded things in a raw form. + * + * - When putting IO read operations on top of the queue, do this only if + * the already-on-top operation is not a save or if it is a save that + * is scheduled for later execution. If there is a save that is ready to + * fire, let's insert the load operation just before the first save that + * is scheduled for later exection for instance. + * + * - Support MULTI/EXEC transactions via a journal file, that is played on + * startup to check if there is cleanup to do. This way we can implement + * transactions with our simple file based KV store. */ /* Virtual Memory is composed mainly of two subsystems: @@ -97,6 +107,8 @@ */ void spawnIOThread(void); +int cacheScheduleIOPushJobs(int flags); +int processActiveIOJobs(int max); /* =================== Virtual Memory - Blocking Side ====================== */ @@ -120,6 +132,7 @@ void dsInit(void) { server.io_ready_clients = listCreate(); pthread_mutex_init(&server.io_mutex,NULL); pthread_cond_init(&server.io_condvar,NULL); + pthread_mutex_init(&server.bgsavethread_mutex,NULL); server.io_active_threads = 0; if (pipe(pipefds) == -1) { redisLog(REDIS_WARNING,"Unable to intialized DS: pipe(2): %s. Exiting." @@ -172,8 +185,7 @@ int cacheFreeOneEntry(void) { * are swappable objects */ int maxtries = 100; - if (dictSize(db->dict) == 0) continue; - for (i = 0; i < 5; i++) { + for (i = 0; i < 5 && dictSize(db->dict); i++) { dictEntry *de; double swappability; robj keyobj; @@ -200,10 +212,17 @@ int cacheFreeOneEntry(void) { } } if (best == NULL) { - /* FIXME: If there are objects that are in the write queue - * so we can't delete them we should block here, at the cost of - * slowness as the object cache memory limit is considered - * n hard limit. */ + /* Not able to free a single object? we should check if our + * IO queues have stuff in queue, and try to consume the queue + * otherwise we'll use an infinite amount of memory if changes to + * the dataset are faster than I/O */ + if (listLength(server.cache_io_queue) > 0) { + redisLog(REDIS_DEBUG,"--- Busy waiting IO to reclaim memory"); + cacheScheduleIOPushJobs(REDIS_IO_ASAP); + processActiveIOJobs(1); + return REDIS_OK; + } + /* Nothing to free at all... */ return REDIS_ERR; } key = dictGetEntryKey(best); @@ -221,13 +240,6 @@ int cacheFreeOneEntry(void) { return REDIS_OK; } -/* Return true if it's safe to swap out objects in a given moment. - * Basically we don't want to swap objects out while there is a BGSAVE - * or a BGAEOREWRITE running in backgroud. */ -int dsCanTouchDiskStore(void) { - return (server.bgsavechildpid == -1 && server.bgrewritechildpid == -1); -} - /* ==================== Disk store negative caching ======================== * * When disk store is enabled, we need negative caching, that is, to remember @@ -304,7 +316,14 @@ void freeIOJob(iojob *j) { /* Every time a thread finished a Job, it writes a byte into the write side * of an unix pipe in order to "awake" the main thread, and this function - * is called. */ + * is called. + * + * If privdata == NULL the function will try to put more jobs in the queue + * of IO jobs to process as more room is made. privdata is equal to NULL + * when the function is called from the event loop, so we want to push + * more IO jobs in the queue. Instead when the function is called by + * other functions that want to create a write-barrier to avoid race + * conditions we don't push new jobs in the queue. */ void vmThreadedIOCompletedJob(aeEventLoop *el, int fd, void *privdata, int mask) { @@ -312,7 +331,6 @@ void vmThreadedIOCompletedJob(aeEventLoop *el, int fd, void *privdata, int retval, processed = 0, toprocess = -1; REDIS_NOTUSED(el); REDIS_NOTUSED(mask); - REDIS_NOTUSED(privdata); /* For every byte we read in the read side of the pipe, there is one * I/O job completed to process. */ @@ -365,12 +383,12 @@ void vmThreadedIOCompletedJob(aeEventLoop *el, int fd, void *privdata, } cacheScheduleIODelFlag(j->db,j->key,REDIS_IO_LOADINPROG); handleClientsBlockedOnSwappedKey(j->db,j->key); - freeIOJob(j); } else if (j->type == REDIS_IOJOB_SAVE) { cacheScheduleIODelFlag(j->db,j->key,REDIS_IO_SAVEINPROG); - freeIOJob(j); } + freeIOJob(j); processed++; + if (privdata == NULL) cacheScheduleIOPushJobs(0); if (processed == toprocess) return; } if (retval < 0 && errno != EAGAIN) { @@ -392,6 +410,7 @@ void *IOThreadEntryPoint(void *arg) { iojob *j; listNode *ln; REDIS_NOTUSED(arg); + long long start; pthread_detach(pthread_self()); lockThreadedIO(); @@ -399,10 +418,13 @@ void *IOThreadEntryPoint(void *arg) { /* Get a new job to process */ if (listLength(server.io_newjobs) == 0) { /* Wait for more work to do */ + redisLog(REDIS_DEBUG,"[T] wait for signal"); pthread_cond_wait(&server.io_condvar,&server.io_mutex); + redisLog(REDIS_DEBUG,"[T] signal received"); continue; } - redisLog(REDIS_DEBUG,"%ld IO jobs to process", + start = ustime(); + redisLog(REDIS_DEBUG,"[T] %ld IO jobs to process", listLength(server.io_newjobs)); ln = listFirst(server.io_newjobs); j = ln->value; @@ -412,7 +434,7 @@ void *IOThreadEntryPoint(void *arg) { ln = listLast(server.io_processing); /* We use ln later to remove it */ unlockThreadedIO(); - redisLog(REDIS_DEBUG,"Thread %ld: new job type %s: %p about key '%s'", + redisLog(REDIS_DEBUG,"[T] %ld: new job type %s: %p about key '%s'", (long) pthread_self(), (j->type == REDIS_IOJOB_LOAD) ? "load" : "save", (void*)j, (char*)j->key->ptr); @@ -425,22 +447,25 @@ void *IOThreadEntryPoint(void *arg) { if (j->val) j->expire = expire; } else if (j->type == REDIS_IOJOB_SAVE) { if (j->val) { - dsSet(j->db,j->key,j->val); + dsSet(j->db,j->key,j->val,j->expire); } else { dsDel(j->db,j->key); } } /* Done: insert the job into the processed queue */ - redisLog(REDIS_DEBUG,"Thread %ld completed the job: %p (key %s)", + redisLog(REDIS_DEBUG,"[T] %ld completed the job: %p (key %s)", (long) pthread_self(), (void*)j, (char*)j->key->ptr); + redisLog(REDIS_DEBUG,"[T] lock IO"); lockThreadedIO(); + redisLog(REDIS_DEBUG,"[T] IO locked"); listDelNode(server.io_processing,ln); listAddNodeTail(server.io_processed,j); /* Signal the main thread there is new stuff to process */ redisAssert(write(server.io_ready_pipe_write,"x",1) == 1); + redisLog(REDIS_DEBUG,"TIME (%c): %lld\n", j->type == REDIS_IOJOB_LOAD ? 'L' : 'S', ustime()-start); } /* never reached, but that's the full pattern... */ unlockThreadedIO(); @@ -466,62 +491,95 @@ void spawnIOThread(void) { server.io_active_threads++; } -/* Wait that all the pending IO Jobs are processed */ -void waitEmptyIOJobsQueue(void) { - while(1) { +/* Wait that up to 'max' pending IO Jobs are processed by the I/O thread. + * From our point of view an IO job processed means that the count of + * server.io_processed must increase by one. + * + * If max is -1, all the pending IO jobs will be processed. + * + * Returns the number of IO jobs processed. + * + * NOTE: while this may appear like a busy loop, we are actually blocked + * by IO since we continuously acquire/release the IO lock. */ +int processActiveIOJobs(int max) { + int processed = 0; + + while(max == -1 || max > 0) { int io_processed_len; + redisLog(REDIS_DEBUG,"[P] lock IO"); lockThreadedIO(); + redisLog(REDIS_DEBUG,"Waiting IO jobs processing: new:%d proessing:%d processed:%d",listLength(server.io_newjobs),listLength(server.io_processing),listLength(server.io_processed)); + if (listLength(server.io_newjobs) == 0 && listLength(server.io_processing) == 0) { + /* There is nothing more to process */ + redisLog(REDIS_DEBUG,"[P] Nothing to process, unlock IO, return"); unlockThreadedIO(); - return; + break; } + +#if 1 /* If there are new jobs we need to signal the thread to - * process the next one. */ - redisLog(REDIS_DEBUG,"waitEmptyIOJobsQueue: new %d, processing %d", + * process the next one. FIXME: drop this if useless. */ + redisLog(REDIS_DEBUG,"[P] waitEmptyIOJobsQueue: new %d, processing %d, processed %d", listLength(server.io_newjobs), - listLength(server.io_processing)); + listLength(server.io_processing), + listLength(server.io_processed)); - /* FIXME: signal or not? if (listLength(server.io_newjobs)) { + redisLog(REDIS_DEBUG,"[P] There are new jobs, signal"); pthread_cond_signal(&server.io_condvar); } - */ - /* While waiting for empty jobs queue condition we post-process some - * finshed job, as I/O threads may be hanging trying to write against - * the io_ready_pipe_write FD but there are so much pending jobs that - * it's blocking. */ +#endif + + /* Check if we can process some finished job */ io_processed_len = listLength(server.io_processed); + redisLog(REDIS_DEBUG,"[P] Unblock IO"); unlockThreadedIO(); + redisLog(REDIS_DEBUG,"[P] Wait"); + usleep(10000); if (io_processed_len) { vmThreadedIOCompletedJob(NULL,server.io_ready_pipe_read, (void*)0xdeadbeef,0); - /* FIXME: probably wiser to drop this sleeps. Anyway - * the contention on the IO thread will avoid we to loop - * too fast here. */ - usleep(1000); /* 1 millisecond */ - } else { - /* FIXME: same as fixme above. */ - usleep(10000); /* 10 milliseconds */ + processed++; + if (max != -1) max--; } } + return processed; } -/* Process all the IO Jobs already completed by threads but still waiting - * processing from the main thread. */ -void processAllPendingIOJobs(void) { - while(1) { +void waitEmptyIOJobsQueue(void) { + processActiveIOJobs(-1); +} + +/* Process up to 'max' IO Jobs already completed by threads but still waiting + * processing from the main thread. + * + * If max == -1 all the pending jobs are processed. + * + * The number of processed jobs is returned. */ +int processPendingIOJobs(int max) { + int processed = 0; + + while(max == -1 || max > 0) { int io_processed_len; lockThreadedIO(); io_processed_len = listLength(server.io_processed); unlockThreadedIO(); - if (io_processed_len == 0) return; + if (io_processed_len == 0) break; vmThreadedIOCompletedJob(NULL,server.io_ready_pipe_read, (void*)0xdeadbeef,0); + if (max != -1) max--; + processed++; } + return processed; +} + +void processAllPendingIOJobs(void) { + processPendingIOJobs(-1); } /* This function must be called while with threaded IO locked */ @@ -529,11 +587,23 @@ void queueIOJob(iojob *j) { redisLog(REDIS_DEBUG,"Queued IO Job %p type %d about key '%s'\n", (void*)j, j->type, (char*)j->key->ptr); listAddNodeTail(server.io_newjobs,j); - if (server.io_active_threads < server.vm_max_threads) - spawnIOThread(); } -void dsCreateIOJob(int type, redisDb *db, robj *key, robj *val) { +/* Consume all the IO scheduled operations, and all the thread IO jobs + * so that eventually the state of diskstore is a point-in-time snapshot. + * + * This is useful when we need to BGSAVE with diskstore enabled. */ +void cacheForcePointInTime(void) { + redisLog(REDIS_NOTICE,"Diskstore: synching on disk to reach point-in-time state."); + while (listLength(server.cache_io_queue) != 0) { + cacheScheduleIOPushJobs(REDIS_IO_ASAP); + processActiveIOJobs(1); + } + waitEmptyIOJobsQueue(); + processAllPendingIOJobs(); +} + +void cacheCreateIOJob(int type, redisDb *db, robj *key, robj *val, time_t expire) { iojob *j; j = zmalloc(sizeof(*j)); @@ -543,6 +613,7 @@ void dsCreateIOJob(int type, redisDb *db, robj *key, robj *val) { incrRefCount(key); j->val = val; if (val) incrRefCount(val); + j->expire = expire; lockThreadedIO(); queueIOJob(j); @@ -587,8 +658,6 @@ void dsCreateIOJob(int type, redisDb *db, robj *key, robj *val) { #define REDIS_IO_LOADINPROG 4 #define REDIS_IO_SAVEINPROG 8 -void cacheScheduleIOPushJobs(int onlyloads); - void cacheScheduleIOAddFlag(redisDb *db, robj *key, long flag) { struct dictEntry *de = dictFind(db->io_queued,key); @@ -649,7 +718,7 @@ void cacheScheduleIO(redisDb *db, robj *key, int type) { * in queue for the same key. */ if (type == REDIS_IO_LOAD && !(flags & REDIS_IO_SAVE)) { listAddNodeHead(server.cache_io_queue, op); - cacheScheduleIOPushJobs(1); + cacheScheduleIOPushJobs(REDIS_IO_ONLYLOADS); } else { /* FIXME: probably when this happens we want to at least move * the write job about this queue on top, and set the creation time @@ -659,16 +728,25 @@ void cacheScheduleIO(redisDb *db, robj *key, int type) { } /* Push scheduled IO operations into IO Jobs that the IO thread can process. - * If 'onlyloads' is true only IO_LOAD jobs are processed: this is useful - * since it's save to push LOAD IO jobs from any place of the code, while + * + * If flags include REDIS_IO_ONLYLOADS only load jobs are processed:this is + * useful since it's safe to push LOAD IO jobs from any place of the code, while * SAVE io jobs should never be pushed while we are processing a command * (not protected by lookupKey() that will block on keys in IO_SAVEINPROG - * state. */ -#define MAX_IO_JOBS_QUEUE 100 -void cacheScheduleIOPushJobs(int onlyloads) { + * state. + * + * The REDIS_IO_ASAP flag tells the function to don't wait for the IO job + * scheduled completion time, but just do the operation ASAP. This is useful + * when we need to reclaim memory from the IO queue. + */ +#define MAX_IO_JOBS_QUEUE 10 +int cacheScheduleIOPushJobs(int flags) { time_t now = time(NULL); listNode *ln; - int jobs, topush = 0; + int jobs, topush = 0, pushed = 0; + + /* Don't push new jobs if there is a threaded BGSAVE in progress. */ + if (server.bgsavethread != (pthread_t) -1) return 0; /* Sync stuff on disk, but only if we have less * than MAX_IO_JOBS_QUEUE IO jobs. */ @@ -683,66 +761,70 @@ void cacheScheduleIOPushJobs(int onlyloads) { while((ln = listFirst(server.cache_io_queue)) != NULL) { ioop *op = ln->value; + struct dictEntry *de; + robj *val; if (!topush) break; topush--; - if (op->type == REDIS_IO_LOAD || - (!onlyloads && (now - op->ctime) >= server.cache_flush_delay)) + if (op->type != REDIS_IO_LOAD && flags & REDIS_IO_ONLYLOADS) break; + + /* Don't execute SAVE before the scheduled time for completion */ + if (op->type == REDIS_IO_SAVE && !(flags & REDIS_IO_ASAP) && + (now - op->ctime) < server.cache_flush_delay) break; + + /* Don't add a SAVE job in the IO thread queue if there is already + * a save in progress for the same key. */ + if (op->type == REDIS_IO_SAVE && + cacheScheduleIOGetFlags(op->db,op->key) & REDIS_IO_SAVEINPROG) { - struct dictEntry *de; - robj *val; - - /* Don't add a SAVE job in queue if there is already - * a save in progress for the same key. */ - if (op->type == REDIS_IO_SAVE && - cacheScheduleIOGetFlags(op->db,op->key) & REDIS_IO_SAVEINPROG) - { - /* Move the operation at the end of the list of there - * are other operations. Otherwise break, nothing to do - * here. */ - if (listLength(server.cache_io_queue) > 1) { - listDelNode(server.cache_io_queue,ln); - listAddNodeTail(server.cache_io_queue,op); - continue; - } else { - break; - } + /* Move the operation at the end of the list if there + * are other operations, so we can try to process the next one. + * Otherwise break, nothing to do here. */ + if (listLength(server.cache_io_queue) > 1) { + listDelNode(server.cache_io_queue,ln); + listAddNodeTail(server.cache_io_queue,op); + continue; + } else { + break; } + } - redisLog(REDIS_DEBUG,"Creating IO %s Job for key %s", - op->type == REDIS_IO_LOAD ? "load" : "save", op->key->ptr); + redisLog(REDIS_DEBUG,"Creating IO %s Job for key %s", + op->type == REDIS_IO_LOAD ? "load" : "save", op->key->ptr); - if (op->type == REDIS_IO_LOAD) { - dsCreateIOJob(REDIS_IOJOB_LOAD,op->db,op->key,NULL); + if (op->type == REDIS_IO_LOAD) { + cacheCreateIOJob(REDIS_IOJOB_LOAD,op->db,op->key,NULL,0); + } else { + time_t expire = -1; + + /* Lookup the key, in order to put the current value in the IO + * Job. Otherwise if the key does not exists we schedule a disk + * store delete operation, setting the value to NULL. */ + de = dictFind(op->db->dict,op->key->ptr); + if (de) { + val = dictGetEntryVal(de); + expire = getExpire(op->db,op->key); } else { - /* Lookup the key, in order to put the current value in the IO - * Job. Otherwise if the key does not exists we schedule a disk - * store delete operation, setting the value to NULL. */ - de = dictFind(op->db->dict,op->key->ptr); - if (de) { - val = dictGetEntryVal(de); - } else { - /* Setting the value to NULL tells the IO thread to delete - * the key on disk. */ - val = NULL; - } - dsCreateIOJob(REDIS_IOJOB_SAVE,op->db,op->key,val); + /* Setting the value to NULL tells the IO thread to delete + * the key on disk. */ + val = NULL; } - /* Mark the operation as in progress. */ - cacheScheduleIODelFlag(op->db,op->key,op->type); - cacheScheduleIOAddFlag(op->db,op->key, - (op->type == REDIS_IO_LOAD) ? REDIS_IO_LOADINPROG : - REDIS_IO_SAVEINPROG); - /* Finally remove the operation from the queue. - * But we'll have trace of it in the hash table. */ - listDelNode(server.cache_io_queue,ln); - decrRefCount(op->key); - zfree(op); - } else { - break; /* too early */ + cacheCreateIOJob(REDIS_IOJOB_SAVE,op->db,op->key,val,expire); } + /* Mark the operation as in progress. */ + cacheScheduleIODelFlag(op->db,op->key,op->type); + cacheScheduleIOAddFlag(op->db,op->key, + (op->type == REDIS_IO_LOAD) ? REDIS_IO_LOADINPROG : + REDIS_IO_SAVEINPROG); + /* Finally remove the operation from the queue. + * But we'll have trace of it in the hash table. */ + listDelNode(server.cache_io_queue,ln); + decrRefCount(op->key); + zfree(op); + pushed++; } + return pushed; } void cacheCron(void) { @@ -808,62 +890,17 @@ int waitForSwappedKey(redisClient *c, robj *key) { listAddNodeTail(l,c); /* Are we already loading the key from disk? If not create a job */ - if (de == NULL) - cacheScheduleIO(c->db,key,REDIS_IO_LOAD); - return 1; -} - -/* Preload keys for any command with first, last and step values for - * the command keys prototype, as defined in the command table. */ -void waitForMultipleSwappedKeys(redisClient *c, struct redisCommand *cmd, int argc, robj **argv) { - int j, last; - if (cmd->vm_firstkey == 0) return; - last = cmd->vm_lastkey; - if (last < 0) last = argc+last; - for (j = cmd->vm_firstkey; j <= last; j += cmd->vm_keystep) { - redisAssert(j < argc); - waitForSwappedKey(c,argv[j]); - } -} - -/* Preload keys needed for the ZUNIONSTORE and ZINTERSTORE commands. - * Note that the number of keys to preload is user-defined, so we need to - * apply a sanity check against argc. */ -void zunionInterBlockClientOnSwappedKeys(redisClient *c, struct redisCommand *cmd, int argc, robj **argv) { - int i, num; - REDIS_NOTUSED(cmd); - - num = atoi(argv[2]->ptr); - if (num > (argc-3)) return; - for (i = 0; i < num; i++) { - waitForSwappedKey(c,argv[3+i]); - } -} - -/* Preload keys needed to execute the entire MULTI/EXEC block. - * - * This function is called by blockClientOnSwappedKeys when EXEC is issued, - * and will block the client when any command requires a swapped out value. */ -void execBlockClientOnSwappedKeys(redisClient *c, struct redisCommand *cmd, int argc, robj **argv) { - int i, margc; - struct redisCommand *mcmd; - robj **margv; - REDIS_NOTUSED(cmd); - REDIS_NOTUSED(argc); - REDIS_NOTUSED(argv); - - if (!(c->flags & REDIS_MULTI)) return; - for (i = 0; i < c->mstate.count; i++) { - mcmd = c->mstate.commands[i].cmd; - margc = c->mstate.commands[i].argc; - margv = c->mstate.commands[i].argv; - - if (mcmd->vm_preload_proc != NULL) { - mcmd->vm_preload_proc(c,mcmd,margc,margv); - } else { - waitForMultipleSwappedKeys(c,mcmd,margc,margv); - } + if (de == NULL) { + int flags = cacheScheduleIOGetFlags(c->db,key); + + /* It is possible that even if there are no clients waiting for + * a load operation, still we have a load operation in progress. + * For instance think to a client performing a GET and then + * closing the connection */ + if ((flags & (REDIS_IO_LOAD|REDIS_IO_LOADINPROG)) == 0) + cacheScheduleIO(c->db,key,REDIS_IO_LOAD); } + return 1; } /* Is this client attempting to run a command against swapped keys? @@ -877,10 +914,39 @@ void execBlockClientOnSwappedKeys(redisClient *c, struct redisCommand *cmd, int * Return 1 if the client is marked as blocked, 0 if the client can * continue as the keys it is going to access appear to be in memory. */ int blockClientOnSwappedKeys(redisClient *c, struct redisCommand *cmd) { - if (cmd->vm_preload_proc != NULL) { - cmd->vm_preload_proc(c,cmd,c->argc,c->argv); + int *keyindex, numkeys, j, i; + + /* EXEC is a special case, we need to preload all the commands + * queued into the transaction */ + if (cmd->proc == execCommand) { + struct redisCommand *mcmd; + robj **margv; + int margc; + + if (!(c->flags & REDIS_MULTI)) return 0; + for (i = 0; i < c->mstate.count; i++) { + mcmd = c->mstate.commands[i].cmd; + margc = c->mstate.commands[i].argc; + margv = c->mstate.commands[i].argv; + + keyindex = getKeysFromCommand(mcmd,margv,margc,&numkeys, + REDIS_GETKEYS_PRELOAD); + for (j = 0; j < numkeys; j++) { + redisLog(REDIS_WARNING,"Preloading %s", + (char*)margv[keyindex[j]]->ptr); + waitForSwappedKey(c,margv[keyindex[j]]); + } + getKeysFreeResult(keyindex); + } } else { - waitForMultipleSwappedKeys(c,cmd,c->argc,c->argv); + keyindex = getKeysFromCommand(cmd,c->argv,c->argc,&numkeys, + REDIS_GETKEYS_PRELOAD); + for (j = 0; j < numkeys; j++) { + redisLog(REDIS_WARNING,"Preloading %s", + (char*)c->argv[keyindex[j]]->ptr); + waitForSwappedKey(c,c->argv[keyindex[j]]); + } + getKeysFreeResult(keyindex); } /* If the client was blocked for at least one key, mark it as blocked. */