/* Factory method to return a set that *can* hold "value". When the object has * an integer-encodable value, an intset will be returned. Otherwise a regular * hash table. */ robj* setTypeCreate(robj* value) { if (isObjectRepresentableAsLongLong(value, NULL) == REDIS_OK) { return createIntsetObject(); } return createSetObject(); }
/* convert a hash dictionary encoding to a dictionary array encoding */ robj *cowSetCopy(robj *val) { robj *newval; if (val->encoding == REDIS_ENCODING_INTSET) { size_t bytes; redisLog(REDIS_NOTICE, "cowSetCopy REDIS_ENCODING_INTSET"); newval = createIntsetObject(); /* do raw memory copy */ bytes = intsetBlobLen(val->ptr); newval->ptr = zrealloc(newval->ptr, bytes); memcpy(newval->ptr, val->ptr, bytes); return newval; } else if (val->encoding == REDIS_ENCODING_HT) { dict *olddict = (dict *)val->ptr; cowDictArray *dar; redisLog(REDIS_NOTICE, "cowSetCopy REDIS_ENCODING_HT"); dar = cowConvertDictToArray(olddict); newval = createObject(REDIS_SET, dar); newval->encoding = REDIS_ENCODING_HTARRAY; return newval; } else { /* error. unexpected encoding */ return NULL; } return NULL; }
void sunionDiffGenericCommand(redisClient *c, robj **setkeys, int setnum, robj *dstkey, int op) { robj **sets = zmalloc(sizeof(robj*)*setnum); setTypeIterator *si; robj *ele, *dstset = NULL; int j, cardinality = 0; for (j = 0; j < setnum; j++) { robj *setobj = dstkey ? lookupKeyWrite(c->db,setkeys[j]) : lookupKeyRead(c->db,setkeys[j]); if (!setobj) { sets[j] = NULL; continue; } if (checkType(c,setobj,REDIS_SET)) { zfree(sets); return; } sets[j] = setobj; } /* We need a temp set object to store our union. If the dstkey * is not NULL (that is, we are inside an SUNIONSTORE operation) then * this set object will be the resulting object to set into the target key*/ dstset = createIntsetObject(); /* Iterate all the elements of all the sets, add every element a single * time to the result set */ for (j = 0; j < setnum; j++) { if (op == REDIS_OP_DIFF && j == 0 && !sets[j]) break; /* result set is empty */ if (!sets[j]) continue; /* non existing keys are like empty sets */ si = setTypeInitIterator(sets[j]); while((ele = setTypeNextObject(si)) != NULL) { if (op == REDIS_OP_UNION || j == 0) { if (setTypeAdd(dstset,ele)) { cardinality++; } } else if (op == REDIS_OP_DIFF) { if (setTypeRemove(dstset,ele)) { cardinality--; } } decrRefCount(ele); } setTypeReleaseIterator(si); /* Exit when result set is empty. */ if (op == REDIS_OP_DIFF && cardinality == 0) break; } /* Output the content of the resulting set, if not in STORE mode */ if (!dstkey) { addReplyMultiBulkLen(c,cardinality); si = setTypeInitIterator(dstset); while((ele = setTypeNextObject(si)) != NULL) { addReplyBulk(c,ele); decrRefCount(ele); } setTypeReleaseIterator(si); decrRefCount(dstset); } else { /* If we have a target key where to store the resulting set * create this key with the result set inside */ dbDelete(c->db,dstkey); if (setTypeSize(dstset) > 0) { dbAdd(c->db,dstkey,dstset); addReplyLongLong(c,setTypeSize(dstset)); } else { decrRefCount(dstset); addReply(c,shared.czero); } touchWatchedKey(c->db,dstkey); server.dirty++; } zfree(sets); }
void sinterGenericCommand(redisClient *c, robj **setkeys, unsigned long setnum, robj *dstkey) { robj **sets = zmalloc(sizeof(robj*)*setnum); setTypeIterator *si; robj *eleobj, *dstset = NULL; int64_t intobj; void *replylen = NULL; unsigned long j, cardinality = 0; int encoding; for (j = 0; j < setnum; j++) { robj *setobj = dstkey ? lookupKeyWrite(c->db,setkeys[j]) : lookupKeyRead(c->db,setkeys[j]); if (!setobj) { zfree(sets); if (dstkey) { if (dbDelete(c->db,dstkey)) { touchWatchedKey(c->db,dstkey); server.dirty++; } addReply(c,shared.czero); } else { addReply(c,shared.emptymultibulk); } return; } if (checkType(c,setobj,REDIS_SET)) { zfree(sets); return; } sets[j] = setobj; } /* Sort sets from the smallest to largest, this will improve our * algorithm's performace */ qsort(sets,setnum,sizeof(robj*),qsortCompareSetsByCardinality); /* The first thing we should output is the total number of elements... * since this is a multi-bulk write, but at this stage we don't know * the intersection set size, so we use a trick, append an empty object * to the output list and save the pointer to later modify it with the * right length */ if (!dstkey) { replylen = addDeferredMultiBulkLength(c); } else { /* If we have a target key where to store the resulting set * create this key with an empty set inside */ dstset = createIntsetObject(); } /* Iterate all the elements of the first (smallest) set, and test * the element against all the other sets, if at least one set does * not include the element it is discarded */ si = setTypeInitIterator(sets[0]); while((encoding = setTypeNext(si,&eleobj,&intobj)) != -1) { for (j = 1; j < setnum; j++) { if (encoding == REDIS_ENCODING_INTSET) { /* intset with intset is simple... and fast */ if (sets[j]->encoding == REDIS_ENCODING_INTSET && !intsetFind((intset*)sets[j]->ptr,intobj)) { break; /* in order to compare an integer with an object we * have to use the generic function, creating an object * for this */ } else if (sets[j]->encoding == REDIS_ENCODING_HT) { eleobj = createStringObjectFromLongLong(intobj); if (!setTypeIsMember(sets[j],eleobj)) { decrRefCount(eleobj); break; } decrRefCount(eleobj); } } else if (encoding == REDIS_ENCODING_HT) { /* Optimization... if the source object is integer * encoded AND the target set is an intset, we can get * a much faster path. */ if (eleobj->encoding == REDIS_ENCODING_INT && sets[j]->encoding == REDIS_ENCODING_INTSET && !intsetFind((intset*)sets[j]->ptr,(long)eleobj->ptr)) { break; /* else... object to object check is easy as we use the * type agnostic API here. */ } else if (!setTypeIsMember(sets[j],eleobj)) { break; } } } /* Only take action when all sets contain the member */ if (j == setnum) { if (!dstkey) { if (encoding == REDIS_ENCODING_HT) addReplyBulk(c,eleobj); else addReplyBulkLongLong(c,intobj); cardinality++; } else { if (encoding == REDIS_ENCODING_INTSET) { eleobj = createStringObjectFromLongLong(intobj); setTypeAdd(dstset,eleobj); decrRefCount(eleobj); } else { setTypeAdd(dstset,eleobj); } } } } setTypeReleaseIterator(si); if (dstkey) { /* Store the resulting set into the target, if the intersection * is not an empty set. */ dbDelete(c->db,dstkey); if (setTypeSize(dstset) > 0) { dbAdd(c->db,dstkey,dstset); addReplyLongLong(c,setTypeSize(dstset)); } else { decrRefCount(dstset); addReply(c,shared.czero); } touchWatchedKey(c->db,dstkey); server.dirty++; } else { setDeferredMultiBulkLength(c,replylen,cardinality); } zfree(sets); }
void msaddCommand(redisClient *c) { int setnum, valnum; int i, j; robj **sets; setnum = atoi(c->argv[1]->ptr); valnum = atoi(c->argv[2]->ptr); if (setnum < 1) { addReplyError(c, "at least 1 input key is needed for MSADD"); return; } if (valnum < 1) { addReplyError(c, "at least 1 input value is needed for MSADD"); return; } /* test if the expected number of keys would overflow */ if (3+setnum+valnum > c->argc) { addReply(c,shared.syntaxerr); return; } int useintset = 0; for (j = 0; j < valnum; j++) { robj *value = c->argv[3 + setnum + j]; if (isObjectRepresentableAsLongLong(value,NULL) != REDIS_OK) { useintset = 1; break; } } sets = zmalloc(sizeof(robj*)*setnum); int notset = 0; for (i = 0; i < setnum; i++) { robj *key = c->argv[3 + i]; robj *set = lookupKeyWrite(c->db, key); if (set == NULL) { if (useintset == 1) set = createIntsetObject(); else set = createSetObject(); dbAdd(c->db,key,set); } else { if (set->type != REDIS_SET) { notset = 1; break; } } sets[i] = set; } if (notset == 1) { addReply(c,shared.wrongtypeerr); } else { long long inserted = 0; for (i = 0; i < setnum; i++) { for (j = 0; j < valnum; j++) { robj *key = c->argv[3 + i]; robj *value = c->argv[3 + setnum + j]; robj *set = sets[i]; if (setTypeAdd(set,value)) { touchWatchedKey(c->db,key); server.dirty++; inserted++; } } } addReplyLongLong(c,inserted); } zfree(sets); }
void sunionDiffGenericCommand(redisClient *c, robj **setkeys, int setnum, robj *dstkey, int op) { robj **sets = zmalloc(sizeof(robj*)*setnum); setTypeIterator *si; robj *ele, *dstset = NULL; int j, cardinality = 0; int diff_algo = 1; for (j = 0; j < setnum; j++) { robj *setobj = dstkey ? lookupKeyWrite(c->db,setkeys[j]) : lookupKeyRead(c->db,setkeys[j]); if (!setobj) { sets[j] = NULL; continue; } if (checkType(c,setobj,REDIS_SET)) { zfree(sets); return; } sets[j] = setobj; } /* Select what DIFF algorithm to use. * * Algorithm 1 is O(N*M) where N is the size of the element first set * and M the total number of sets. * * Algorithm 2 is O(N) where N is the total number of elements in all * the sets. * * We compute what is the best bet with the current input here. */ if (op == REDIS_OP_DIFF && sets[0]) { long long algo_one_work = 0, algo_two_work = 0; for (j = 0; j < setnum; j++) { if (sets[j] == NULL) continue; algo_one_work += setTypeSize(sets[0]); algo_two_work += setTypeSize(sets[j]); } /* Algorithm 1 has better constant times and performs less operations * if there are elements in common. Give it some advantage. */ algo_one_work /= 2; diff_algo = (algo_one_work <= algo_two_work) ? 1 : 2; if (diff_algo == 1 && setnum > 1) { /* With algorithm 1 it is better to order the sets to subtract * by decreasing size, so that we are more likely to find * duplicated elements ASAP. */ qsort(sets+1,setnum-1,sizeof(robj*), qsortCompareSetsByRevCardinality); } } /* We need a temp set object to store our union. If the dstkey * is not NULL (that is, we are inside an SUNIONSTORE operation) then * this set object will be the resulting object to set into the target key*/ dstset = createIntsetObject(); if (op == REDIS_OP_UNION) { /* Union is trivial, just add every element of every set to the * temporary set. */ for (j = 0; j < setnum; j++) { if (!sets[j]) continue; /* non existing keys are like empty sets */ si = setTypeInitIterator(sets[j]); while((ele = setTypeNextObject(si)) != NULL) { if (setTypeAdd(dstset,ele)) cardinality++; decrRefCount(ele); } setTypeReleaseIterator(si); } } else if (op == REDIS_OP_DIFF && sets[0] && diff_algo == 1) { /* DIFF Algorithm 1: * * We perform the diff by iterating all the elements of the first set, * and only adding it to the target set if the element does not exist * into all the other sets. * * This way we perform at max N*M operations, where N is the size of * the first set, and M the number of sets. */ si = setTypeInitIterator(sets[0]); while((ele = setTypeNextObject(si)) != NULL) { for (j = 1; j < setnum; j++) { if (!sets[j]) continue; /* no key is an empty set. */ if (sets[j] == sets[0]) break; /* same set! */ if (setTypeIsMember(sets[j],ele)) break; } if (j == setnum) { /* There is no other set with this element. Add it. */ setTypeAdd(dstset,ele); cardinality++; } decrRefCount(ele); } setTypeReleaseIterator(si); } else if (op == REDIS_OP_DIFF && sets[0] && diff_algo == 2) { /* DIFF Algorithm 2: * * Add all the elements of the first set to the auxiliary set. * Then remove all the elements of all the next sets from it. * * This is O(N) where N is the sum of all the elements in every * set. */ for (j = 0; j < setnum; j++) { if (!sets[j]) continue; /* non existing keys are like empty sets */ si = setTypeInitIterator(sets[j]); while((ele = setTypeNextObject(si)) != NULL) { if (j == 0) { if (setTypeAdd(dstset,ele)) cardinality++; } else { if (setTypeRemove(dstset,ele)) cardinality--; } decrRefCount(ele); } setTypeReleaseIterator(si); /* Exit if result set is empty as any additional removal * of elements will have no effect. */ if (cardinality == 0) break; } } /* Output the content of the resulting set, if not in STORE mode */ if (!dstkey) { addReplyMultiBulkLen(c,cardinality); si = setTypeInitIterator(dstset); while((ele = setTypeNextObject(si)) != NULL) { addReplyBulk(c,ele); decrRefCount(ele); } setTypeReleaseIterator(si); decrRefCount(dstset); } else { /* If we have a target key where to store the resulting set * create this key with the result set inside */ int deleted = dbDelete(c->db,dstkey); if (setTypeSize(dstset) > 0) { dbAdd(c->db,dstkey,dstset); addReplyLongLong(c,setTypeSize(dstset)); notifyKeyspaceEvent(REDIS_NOTIFY_SET, op == REDIS_OP_UNION ? "sunionstore" : "sdiffstore", dstkey,c->db->id); } else { decrRefCount(dstset); addReply(c,shared.czero); if (deleted) notifyKeyspaceEvent(REDIS_NOTIFY_GENERIC,"del", dstkey,c->db->id); } signalModifiedKey(c->db,dstkey); server.dirty++; } zfree(sets); }
void sinterGenericCommand(redisClient *c, robj **setkeys, unsigned long setnum, robj *dstkey) { robj **sets = zmalloc(sizeof(robj*)*setnum); setTypeIterator *si;//迭代器 robj *eleobj, *dstset = NULL; int64_t intobj; void *replylen = NULL; unsigned long j, cardinality = 0; int encoding; for (j = 0; j < setnum; j++) {//得到所有的集合 robj *setobj = dstkey ? lookupKeyWrite(c->db,setkeys[j]) : lookupKeyRead(c->db,setkeys[j]); if (!setobj) {//任何一个集合不存在,那么总的交集就为空 zfree(sets); if (dstkey) { if (dbDelete(c->db,dstkey)) { signalModifiedKey(c->db,dstkey); server.dirty++; } addReply(c,shared.czero); } else { addReply(c,shared.emptymultibulk); } return; } if (checkType(c,setobj,REDIS_SET)) { zfree(sets); return; } sets[j] = setobj; } /* Sort sets from the smallest to largest, this will improve our * algorithm's performance */ //按照集合元素个数从小到大排序 qsort(sets,setnum,sizeof(robj*),qsortCompareSetsByCardinality); /* The first thing we should output is the total number of elements... * since this is a multi-bulk write, but at this stage we don't know * the intersection set size, so we use a trick, append an empty object * to the output list and save the pointer to later modify it with the * right length */ if (!dstkey) { replylen = addDeferredMultiBulkLength(c); } else { /* If we have a target key where to store the resulting set * create this key with an empty set inside */ dstset = createIntsetObject(); } /* Iterate all the elements of the first (smallest) set, and test * the element against all the other sets, if at least one set does * not include the element it is discarded */ /** 求多个集合交集的算法思想: 首先按照集合元素个数对集合进行qsort,然后遍历排序后的第一个集合中的元素,查看该元素在 其他集合中是否存在,如果在其他集合中都存在,那么该元素为一个结果 */ si = setTypeInitIterator(sets[0]); while((encoding = setTypeNext(si,&eleobj,&intobj)) != -1) { for (j = 1; j < setnum; j++) { if (sets[j] == sets[0]) continue;//这段代码没意义啊 if (encoding == REDIS_ENCODING_INTSET) {//intset /* intset with intset is simple... and fast */ //集合sets[j]编码为intset if (sets[j]->encoding == REDIS_ENCODING_INTSET && !intsetFind((intset*)sets[j]->ptr,intobj))//在集合sets[j]中没有找到集合sets[0]的intobj { break; /* in order to compare an integer with an object we * have to use the generic function, creating an object * for this */ } else if (sets[j]->encoding == REDIS_ENCODING_HT) {//集合sets[j]编码为HT,sets[0]为INTSET eleobj = createStringObjectFromLongLong(intobj);//将sets[0]中的intobj转换为sds if (!setTypeIsMember(sets[j],eleobj)) {//如果eleobj不在集合sets[j]中 decrRefCount(eleobj); break; } decrRefCount(eleobj); } } else if (encoding == REDIS_ENCODING_HT) {//HT /* Optimization... if the source object is integer * encoded AND the target set is an intset, we can get * a much faster path. */ if (eleobj->encoding == REDIS_ENCODING_INT && sets[j]->encoding == REDIS_ENCODING_INTSET && !intsetFind((intset*)sets[j]->ptr,(long)eleobj->ptr)) { break; /* else... object to object check is easy as we use the * type agnostic API here. */ } else if (!setTypeIsMember(sets[j],eleobj)) { break; } } } /* Only take action when all sets contain the member */ if (j == setnum) { if (!dstkey) { if (encoding == REDIS_ENCODING_HT) addReplyBulk(c,eleobj); else addReplyBulkLongLong(c,intobj); cardinality++; } else {//添加到临时目标集合 if (encoding == REDIS_ENCODING_INTSET) { eleobj = createStringObjectFromLongLong(intobj); setTypeAdd(dstset,eleobj); decrRefCount(eleobj); } else { setTypeAdd(dstset,eleobj); } } } } setTypeReleaseIterator(si); if (dstkey) { /* Store the resulting set into the target, if the intersection * is not an empty set. */ int deleted = dbDelete(c->db,dstkey);//覆盖原来的目标集合 if (setTypeSize(dstset) > 0) { dbAdd(c->db,dstkey,dstset); addReplyLongLong(c,setTypeSize(dstset)); notifyKeyspaceEvent(REDIS_NOTIFY_SET,"sinterstore", dstkey,c->db->id); } else {//空集 decrRefCount(dstset); addReply(c,shared.czero); if (deleted) notifyKeyspaceEvent(REDIS_NOTIFY_GENERIC,"del", dstkey,c->db->id); } signalModifiedKey(c->db,dstkey); server.dirty++; } else { setDeferredMultiBulkLength(c,replylen,cardinality); } zfree(sets); }
void sinterGenericCommand(client *c, robj **setkeys, unsigned long setnum, robj *dstkey) { robj **sets = zmalloc(sizeof(robj*)*setnum); setTypeIterator *si; robj *dstset = NULL; sds elesds; int64_t intobj; void *replylen = NULL; unsigned long j, cardinality = 0; int encoding; for (j = 0; j < setnum; j++) { robj *setobj = dstkey ? lookupKeyWrite(c->db,setkeys[j]) : lookupKeyRead(c->db,setkeys[j]); if (!setobj) { zfree(sets); if (dstkey) { if (dbDelete(c->db,dstkey)) { signalModifiedKey(c->db,dstkey); server.dirty++; } addReply(c,shared.czero); } else { addReply(c,shared.emptymultibulk); } return; } if (checkType(c,setobj,OBJ_SET)) { zfree(sets); return; } sets[j] = setobj; } /* Sort sets from the smallest to largest, this will improve our * algorithm's performance */ qsort(sets,setnum,sizeof(robj*),qsortCompareSetsByCardinality); /* The first thing we should output is the total number of elements... * since this is a multi-bulk write, but at this stage we don't know * the intersection set size, so we use a trick, append an empty object * to the output list and save the pointer to later modify it with the * right length */ if (!dstkey) { replylen = addDeferredMultiBulkLength(c); } else { /* If we have a target key where to store the resulting set * create this key with an empty set inside */ dstset = createIntsetObject(); } /* Iterate all the elements of the first (smallest) set, and test * the element against all the other sets, if at least one set does * not include the element it is discarded */ si = setTypeInitIterator(sets[0]); while((encoding = setTypeNext(si,&elesds,&intobj)) != -1) { for (j = 1; j < setnum; j++) { if (sets[j] == sets[0]) continue; if (encoding == OBJ_ENCODING_INTSET) { /* intset with intset is simple... and fast */ if (sets[j]->encoding == OBJ_ENCODING_INTSET && !intsetFind((intset*)sets[j]->ptr,intobj)) { break; /* in order to compare an integer with an object we * have to use the generic function, creating an object * for this */ } else if (sets[j]->encoding == OBJ_ENCODING_HT) { elesds = sdsfromlonglong(intobj); if (!setTypeIsMember(sets[j],elesds)) { sdsfree(elesds); break; } sdsfree(elesds); } } else if (encoding == OBJ_ENCODING_HT) { if (!setTypeIsMember(sets[j],elesds)) { break; } } } /* Only take action when all sets contain the member */ if (j == setnum) { if (!dstkey) { if (encoding == OBJ_ENCODING_HT) addReplyBulkCBuffer(c,elesds,sdslen(elesds)); else addReplyBulkLongLong(c,intobj); cardinality++; } else { if (encoding == OBJ_ENCODING_INTSET) { elesds = sdsfromlonglong(intobj); setTypeAdd(dstset,elesds); sdsfree(elesds); } else { setTypeAdd(dstset,elesds); } } } } setTypeReleaseIterator(si); if (dstkey) { /* Store the resulting set into the target, if the intersection * is not an empty set. */ int deleted = dbDelete(c->db,dstkey); if (setTypeSize(dstset) > 0) { dbAdd(c->db,dstkey,dstset); addReplyLongLong(c,setTypeSize(dstset)); notifyKeyspaceEvent(NOTIFY_SET,"sinterstore", dstkey,c->db->id); } else { decrRefCount(dstset); addReply(c,shared.czero); if (deleted) notifyKeyspaceEvent(NOTIFY_GENERIC,"del", dstkey,c->db->id); } signalModifiedKey(c->db,dstkey); server.dirty++; } else { setDeferredMultiBulkLength(c,replylen,cardinality); } zfree(sets); }
/* Factory method to return a set that *can* hold "value". When the object has * an integer-encodable value, an intset will be returned. Otherwise a regular * hash table. */ robj *setTypeCreate(sds value) { if (isSdsRepresentableAsLongLong(value,NULL) == C_OK) return createIntsetObject(); return createSetObject(); }