fluencelabs/redis
1
0
Fork 0
mirror of https://github.com/fluencelabs/redis synced 2025-04-03 16:21:03 +00:00
Code Issues Projects Releases Wiki Activity

HyperLogLog algorithm fixed in two ways.

Browse Source 
There was an error in the computation of 2^register, and the sequence of
zeroes computed after the hashing did not included the "1".
This commit is contained in:
antirez 2014-03-28 18:24:05 +01:00
parent ded86076b3
commit f90a4af3d7
1 changed files with 8 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
src/hyperloglog.c
View File

@ -236,13 +236,18 @@ int hllAdd(uint8_t *registers, unsigned char *ele, size_t elesize) {
/* Count the number of zeroes starting from bit REDIS_HLL_REGISTERS /* Count the number of zeroes starting from bit REDIS_HLL_REGISTERS
* (that is a power of two corresponding to the first bit we don't use * (that is a power of two corresponding to the first bit we don't use
* as index). The max run can be 64-P bits. * as index). The max run can be 64-P+1 bits.
*
* Note that the final "1" ending the sequence of zeroes must be
* included in the count, so if we find "001" the count is 3, and
* the smallest count possible is no zeroes at all, just a 1 bit
* at the first position, that is a count of 1.
* *
* This may sound like inefficient, but actually in the average case * This may sound like inefficient, but actually in the average case
* there are high probabilities to find a 1 after a few iterations. */ * there are high probabilities to find a 1 after a few iterations. */
hash = MurmurHash64A(ele,elesize,0); hash = MurmurHash64A(ele,elesize,0);
bit = REDIS_HLL_REGISTERS; bit = REDIS_HLL_REGISTERS;
count = 0; count = 1;
while((hash & bit) == 0) { while((hash & bit) == 0) {
count++; count++;
/* Test the next bit. Note that if we run out of bits in the 64 /* Test the next bit. Note that if we run out of bits in the 64
@ -281,7 +286,7 @@ uint64_t hllCount(uint8_t *registers) {
ez++; ez++;
E += 1; /* 2^(-reg[j]) is 1 when m is 0. */ E += 1; /* 2^(-reg[j]) is 1 when m is 0. */
} else { } else {
E += 1.0/(2ULL << reg); /* 2^(-reg[j]) is the same as 1/2^reg[j]. */ E += 1.0/(1ULL << reg); /* 2^(-reg[j]) is the same as 1/2^reg[j]. */
} }
} }
/* Muliply the inverse of E for alpha_m * m^2 to have the raw estimate. */ /* Muliply the inverse of E for alpha_m * m^2 to have the raw estimate. */