提交 cfbbcd24 编写于 作者: S Sage Weil

ceph: use strong hash function for mapping objects to pgs

We were using the (weak) dcache hash function, but it was leaving lower
bits consecutive for consecutive (inode) objects.  We really want to make
the object to pg mapping random and uniform, so use a proper hash function
here.

This is Robert Jenkin's public domain hash function (with some minor
cleanup):
	http://burtleburtle.net/bob/hash/evahash.html

This is a protocol revision.
Signed-off-by: NSage Weil <sage@newdream.net>
上级 c6cf7263
......@@ -73,32 +73,79 @@ int ceph_caps_for_mode(int mode)
return 0;
}
/* Name hashing routines. Initial hash value */
/* Hash courtesy of the R5 hash in reiserfs modulo sign bits */
#define ceph_init_name_hash() 0
/* partial hash update function. Assume roughly 4 bits per character */
static unsigned long ceph_partial_name_hash(unsigned long c,
unsigned long prevhash)
{
return (prevhash + (c << 4) + (c >> 4)) * 11;
}
/*
* Finally: cut down the number of bits to a int value (and try to avoid
* losing bits)
* Robert Jenkin's hash function.
* http://burtleburtle.net/bob/hash/evahash.html
* This is in the public domain.
*/
static unsigned long ceph_end_name_hash(unsigned long hash)
{
return hash & 0xffffffff;
}
#define mix(a, b, c) \
do { \
a = a - b; a = a - c; a = a ^ (c >> 13); \
b = b - c; b = b - a; b = b ^ (a << 8); \
c = c - a; c = c - b; c = c ^ (b >> 13); \
a = a - b; a = a - c; a = a ^ (c >> 12); \
b = b - c; b = b - a; b = b ^ (a << 16); \
c = c - a; c = c - b; c = c ^ (b >> 5); \
a = a - b; a = a - c; a = a ^ (c >> 3); \
b = b - c; b = b - a; b = b ^ (a << 10); \
c = c - a; c = c - b; c = c ^ (b >> 15); \
} while (0)
/* Compute the hash for a name string. */
unsigned int ceph_full_name_hash(const char *name, unsigned int len)
unsigned int ceph_full_name_hash(const char *str, unsigned int length)
{
unsigned long hash = ceph_init_name_hash();
while (len--)
hash = ceph_partial_name_hash(*name++, hash);
return ceph_end_name_hash(hash);
const unsigned char *k = (const unsigned char *)str;
__u32 a, b, c; /* the internal state */
__u32 len; /* how many key bytes still need mixing */
/* Set up the internal state */
len = length;
a = 0x9e3779b9; /* the golden ratio; an arbitrary value */
b = a;
c = 0; /* variable initialization of internal state */
/* handle most of the key */
while (len >= 12) {
a = a + (k[0] + ((__u32)k[1] << 8) + ((__u32)k[2] << 16) +
((__u32)k[3] << 24));
b = b + (k[4] + ((__u32)k[5] << 8) + ((__u32)k[6] << 16) +
((__u32)k[7] << 24));
c = c + (k[8] + ((__u32)k[9] << 8) + ((__u32)k[10] << 16) +
((__u32)k[11] << 24));
mix(a, b, c);
k = k + 12;
len = len - 12;
}
/* handle the last 11 bytes */
c = c + length;
switch (len) { /* all the case statements fall through */
case 11:
c = c + ((__u32)k[10] << 24);
case 10:
c = c + ((__u32)k[9] << 16);
case 9:
c = c + ((__u32)k[8] << 8);
/* the first byte of c is reserved for the length */
case 8:
b = b + ((__u32)k[7] << 24);
case 7:
b = b + ((__u32)k[6] << 16);
case 6:
b = b + ((__u32)k[5] << 8);
case 5:
b = b + k[4];
case 4:
a = a + ((__u32)k[3] << 24);
case 3:
a = a + ((__u32)k[2] << 16);
case 2:
a = a + ((__u32)k[1] << 8);
case 1:
a = a + k[0];
/* case 0: nothing left to add */
}
mix(a, b, c);
return c;
}
......@@ -38,7 +38,7 @@
#define CEPH_OSD_PROTOCOL 7 /* cluster internal */
#define CEPH_MDS_PROTOCOL 9 /* cluster internal */
#define CEPH_MON_PROTOCOL 5 /* cluster internal */
#define CEPH_OSDC_PROTOCOL 21 /* server/client */
#define CEPH_OSDC_PROTOCOL 22 /* server/client */
#define CEPH_MDSC_PROTOCOL 29 /* server/client */
#define CEPH_MONC_PROTOCOL 15 /* server/client */
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册