diff --git a/auto/modules b/auto/modules index 9bc2e04..33f7972 100644 --- a/auto/modules +++ b/auto/modules @@ -325,6 +325,11 @@ if [ $HTTP_STUB_STATUS = YES ]; then HTTP_SRCS="$HTTP_SRCS src/http/modules/ngx_http_stub_status_module.c" fi +if [ $HTTP_STATUS_HEAP = YES ]; then + HTTP_MODULES="$HTTP_MODULES $HTTP_STATUS_HEAP_MODULE" + HTTP_SRCS="$HTTP_SRCS $HTTP_STATUS_HEAP_SRCS" +fi + #if [ -r $NGX_OBJS/auto ]; then # . $NGX_OBJS/auto #fi diff --git a/auto/options b/auto/options index aca314b..111f6c7 100644 --- a/auto/options +++ b/auto/options @@ -89,6 +89,7 @@ HTTP_UPSTREAM_IP_HASH=YES # STUB HTTP_STUB_STATUS=NO +HTTP_STATUS_HEAP=NO MAIL=NO MAIL_SSL=NO @@ -218,6 +219,7 @@ do # STUB --with-http_stub_status_module) HTTP_STUB_STATUS=YES ;; + --with-http_status_heap_module) HTTP_STATUS_HEAP=YES ;; --with-mail) MAIL=YES ;; --with-mail_ssl_module) MAIL_SSL=YES ;; @@ -317,6 +319,7 @@ cat << END --with-http_random_index_module enable ngx_http_random_index_module --with-http_secure_link_module enable ngx_http_secure_link_module --with-http_stub_status_module enable ngx_http_stub_status_module + --with-http_status_heap_module enable ngx_http_status_heap_module --without-http_charset_module disable ngx_http_charset_module --without-http_gzip_module disable ngx_http_gzip_module diff --git a/auto/os/features b/auto/os/features index ae0590e..75188e9 100644 --- a/auto/os/features +++ b/auto/os/features @@ -252,3 +252,24 @@ if [ $ngx_found != yes ]; then NGX_LIBDL="-ldl" fi fi + + +ngx_feature="sysinfo()" +ngx_feature_name="NGX_HAVE_SYSINFO" +ngx_feature_run=no +ngx_feature_incs="#include " +ngx_feature_path= +ngx_feature_libs= +ngx_feature_test="struct sysinfo s; + sysinfo(&s);" +. auto/feature + +ngx_feature="getloadavg()" +ngx_feature_name="NGX_HAVE_GETLOADAVG" +ngx_feature_run=no +ngx_feature_incs="#include " +ngx_feature_path= +ngx_feature_libs= +ngx_feature_test="double loadavg[1]; + getloadavg(loadavg, 1);" +. auto/feature diff --git a/auto/sources b/auto/sources index e4649b0..a48c343 100644 --- a/auto/sources +++ b/auto/sources @@ -23,8 +23,11 @@ CORE_DEPS="src/core/nginx.h \ src/core/ngx_crc.h \ src/core/ngx_crc32.h \ src/core/ngx_md5.h \ + src/core/ngx_lookup3.h \ src/core/ngx_sha1.h \ src/core/ngx_rbtree.h \ + src/core/ngx_rbtreehash.h \ + src/core/ngx_flathash.h \ src/core/ngx_radix_tree.h \ src/core/ngx_slab.h \ src/core/ngx_times.h \ @@ -50,7 +53,10 @@ CORE_SRCS="src/core/nginx.c \ src/core/ngx_inet.c \ src/core/ngx_file.c \ src/core/ngx_crc32.c \ + src/core/ngx_lookup3.c \ src/core/ngx_rbtree.c \ + src/core/ngx_rbtreehash.c \ + src/core/ngx_flathash.c \ src/core/ngx_radix_tree.c \ src/core/ngx_slab.c \ src/core/ngx_times.c \ @@ -373,6 +379,10 @@ HTTP_STATUS_MODULE=ngx_http_status_module HTTP_STATUS_SRCS=src/http/modules/ngx_http_status_module.c +HTTP_STATUS_HEAP_MODULE=ngx_http_status_heap_module +HTTP_STATUS_HEAP_SRCS=src/http/modules/ngx_http_status_heap_module.c + + HTTP_GEO_MODULE=ngx_http_geo_module HTTP_GEO_SRCS=src/http/modules/ngx_http_geo_module.c diff --git a/src/core/ngx_core.h b/src/core/ngx_core.h index d5f18b8..809bd71 100644 --- a/src/core/ngx_core.h +++ b/src/core/ngx_core.h @@ -75,6 +75,9 @@ typedef void (*ngx_connection_handler_pt)(ngx_connection_t *c); #include #include #include +#include +#include +#include #define LF (u_char) 10 diff --git a/src/core/ngx_flathash.c b/src/core/ngx_flathash.c new file mode 100644 index 0000000..206036e --- /dev/null +++ b/src/core/ngx_flathash.c @@ -0,0 +1,83 @@ + +/* + * Copyright (C) Kirill A. Korinskiy + */ + +#include +#include + + +typedef struct { + u_char data[1]; +} ngx_flathash_node_t; + + +#define ngx_flathash_hashsize(n) ((uint32_t)1 << (n)) +#define ngx_flathash_hashmask(n) (ngx_flathash_hashsize(n) - 1) +#define ngx_flathash_hashfunc(a, b) ngx_lookup3_hashlittle(a, b, 0x715517) + + +/* + * Really simple index + */ +static inline ngx_flathash_node_t * +ngx_flathash_index(ngx_flathash_t *hashtable, uint32_t hash) { + return (ngx_flathash_node_t *)(hashtable->data + + ((offsetof(ngx_flathash_node_t, data) + + hashtable->value_len) + * hash)); +}; + + +void * +ngx_flathash_get(ngx_flathash_t *hashtable, ngx_str_t *key) +{ + uint32_t hash; + ngx_flathash_node_t *rn; + + hash = ngx_flathash_hashfunc(key->data, key->len) + & ngx_flathash_hashmask(hashtable->bits); + + rn = ngx_flathash_index(hashtable, hash); + + return rn->data; +} + + +size_t +ngx_flathash_need_memory(size_t length, size_t size) +{ + uint32_t bits; + size_t i; + + for (bits = 0, i = size; i; i >>= 1, bits++); + + bits += 2; + + return offsetof(ngx_flathash_t, data) + + ((offsetof(ngx_flathash_node_t, data) + + length) + * 1<value_len = length; + + hashtable->bits = 0; + + for (i = size; i; i >>= 1, hashtable->bits++); + + hashtable->bits += 2; + + hashtable->length = 1 << hashtable->bits; + + + ngx_memzero(hashtable->data, hashtable->length); + + return NGX_OK; +} diff --git a/src/core/ngx_flathash.h b/src/core/ngx_flathash.h new file mode 100644 index 0000000..990018e --- /dev/null +++ b/src/core/ngx_flathash.h @@ -0,0 +1,26 @@ + +/* + * Copyright (C) Kirill A. Korinskiy + */ + +#ifndef _NGX_FLATHASH_H_INCLUDED_ +#define _NGX_FLATHASH_H_INCLUDED_ + +#include +#include + +typedef struct { + size_t value_len; + size_t length; + u_char bits; + u_char data[1]; +} ngx_flathash_t; + +void *ngx_flathash_get(ngx_flathash_t *hashtable, ngx_str_t *key); + +size_t ngx_flathash_need_memory(size_t length, size_t size); + +ngx_int_t ngx_flathash_init(ngx_flathash_t *hashtable, size_t length, size_t size); + + +#endif /* _NGX_FLATHASH_H_INCLUDED_ */ diff --git a/src/core/ngx_lookup3.c b/src/core/ngx_lookup3.c new file mode 100644 index 0000000..190b64b --- /dev/null +++ b/src/core/ngx_lookup3.c @@ -0,0 +1,761 @@ +/* + * ngx_lookup3.c, by Kirill A. Korinskiy + */ + +#include +#include + +/* +------------------------------------------------------------------------------- +lookup3.c, by Bob Jenkins, May 2006, Public Domain. + +These are functions for producing 32-bit hashes for hash table lookup. +hashword(), hashlittle(), hashlittle2(), hashbig(), mix(), and final() +are externally useful functions. Routines to test the hash are included +if SELF_TEST is defined. You can use this free for any purpose. It's in +the public domain. It has no warranty. + +You probably want to use hashlittle(). hashlittle() and hashbig() +hash byte arrays. hashlittle() is is faster than hashbig() on +little-endian machines. Intel and AMD are little-endian machines. +On second thought, you probably want hashlittle2(), which is identical to +hashlittle() except it returns two 32-bit hashes for the price of one. +You could implement hashbig2() if you wanted but I haven't bothered here. + +If you want to find a hash of, say, exactly 7 integers, do + a = i1; b = i2; c = i3; + mix(a,b,c); + a += i4; b += i5; c += i6; + mix(a,b,c); + a += i7; + final(a,b,c); +then use c as the hash value. If you have a variable length array of +4-byte integers to hash, use hashword(). If you have a byte array (like +a character string), use hashlittle(). If you have several byte arrays, or +a mix of things, see the comments above hashlittle(). + +Why is this so big? I read 12 bytes at a time into 3 4-byte integers, +then mix those integers. This is fast (you can do a lot more thorough +mixing with 12*3 instructions on 3 integers than you can with 3 instructions +on 1 byte), but shoehorning those bytes into integers efficiently is messy. +------------------------------------------------------------------------------- +*/ + +/* + * My best guess at if you are big-endian or little-endian. This may + * need adjustment. + */ +#if (defined(__BYTE_ORDER) && defined(__LITTLE_ENDIAN) && \ + __BYTE_ORDER == __LITTLE_ENDIAN) || \ + (defined(i386) || defined(__i386__) || defined(__i486__) || \ + defined(__i586__) || defined(__i686__) || defined(vax) || defined(MIPSEL)) +# define HASH_LITTLE_ENDIAN 1 +# define HASH_BIG_ENDIAN 0 +#elif (defined(__BYTE_ORDER) && defined(__BIG_ENDIAN) && \ + __BYTE_ORDER == __BIG_ENDIAN) || \ + (defined(sparc) || defined(POWERPC) || defined(mc68000) || defined(sel)) +# define HASH_LITTLE_ENDIAN 0 +# define HASH_BIG_ENDIAN 1 +#else +# define HASH_LITTLE_ENDIAN 0 +# define HASH_BIG_ENDIAN 0 +#endif + +#define hashsize(n) ((uint32_t)1<<(n)) +#define hashmask(n) (hashsize(n)-1) +#define rot(x,k) (((x)<<(k)) | ((x)>>(32-(k)))) + +/* +------------------------------------------------------------------------------- +mix -- mix 3 32-bit values reversibly. + +This is reversible, so any information in (a,b,c) before mix() is +still in (a,b,c) after mix(). + +If four pairs of (a,b,c) inputs are run through mix(), or through +mix() in reverse, there are at least 32 bits of the output that +are sometimes the same for one pair and different for another pair. +This was tested for: +* pairs that differed by one bit, by two bits, in any combination + of top bits of (a,b,c), or in any combination of bottom bits of + (a,b,c). +* "differ" is defined as +, -, ^, or ~^. For + and -, I transformed + the output delta to a Gray code (a^(a>>1)) so a string of 1's (as + is commonly produced by subtraction) look like a single 1-bit + difference. +* the base values were pseudorandom, all zero but one bit set, or + all zero plus a counter that starts at zero. + +Some k values for my "a-=c; a^=rot(c,k); c+=b;" arrangement that +satisfy this are + 4 6 8 16 19 4 + 9 15 3 18 27 15 + 14 9 3 7 17 3 +Well, "9 15 3 18 27 15" didn't quite get 32 bits diffing +for "differ" defined as + with a one-bit base and a two-bit delta. I +used http://burtleburtle.net/bob/hash/avalanche.html to choose +the operations, constants, and arrangements of the variables. + +This does not achieve avalanche. There are input bits of (a,b,c) +that fail to affect some output bits of (a,b,c), especially of a. The +most thoroughly mixed value is c, but it doesn't really even achieve +avalanche in c. + +This allows some parallelism. Read-after-writes are good at doubling +the number of bits affected, so the goal of mixing pulls in the opposite +direction as the goal of parallelism. I did what I could. Rotates +seem to cost as much as shifts on every machine I could lay my hands +on, and rotates are much kinder to the top and bottom bits, so I used +rotates. +------------------------------------------------------------------------------- +*/ +#define mix(a,b,c) \ +{ \ + a -= c; a ^= rot(c, 4); c += b; \ + b -= a; b ^= rot(a, 6); a += c; \ + c -= b; c ^= rot(b, 8); b += a; \ + a -= c; a ^= rot(c,16); c += b; \ + b -= a; b ^= rot(a,19); a += c; \ + c -= b; c ^= rot(b, 4); b += a; \ +} + +/* +------------------------------------------------------------------------------- +final -- final mixing of 3 32-bit values (a,b,c) into c + +Pairs of (a,b,c) values differing in only a few bits will usually +produce values of c that look totally different. This was tested for +* pairs that differed by one bit, by two bits, in any combination + of top bits of (a,b,c), or in any combination of bottom bits of + (a,b,c). +* "differ" is defined as +, -, ^, or ~^. For + and -, I transformed + the output delta to a Gray code (a^(a>>1)) so a string of 1's (as + is commonly produced by subtraction) look like a single 1-bit + difference. +* the base values were pseudorandom, all zero but one bit set, or + all zero plus a counter that starts at zero. + +These constants passed: + 14 11 25 16 4 14 24 + 12 14 25 16 4 14 24 +and these came close: + 4 8 15 26 3 22 24 + 10 8 15 26 3 22 24 + 11 8 15 26 3 22 24 +------------------------------------------------------------------------------- +*/ +#define final(a,b,c) \ +{ \ + c ^= b; c -= rot(b,14); \ + a ^= c; a -= rot(c,11); \ + b ^= a; b -= rot(a,25); \ + c ^= b; c -= rot(b,16); \ + a ^= c; a -= rot(c,4); \ + b ^= a; b -= rot(a,14); \ + c ^= b; c -= rot(b,24); \ +} + +/* +-------------------------------------------------------------------- + This works on all machines. To be useful, it requires + -- that the key be an array of uint32_t's, and + -- that the length be the number of uint32_t's in the key + + The function hashword() is identical to hashlittle() on little-endian + machines, and identical to hashbig() on big-endian machines, + except that the length has to be measured in uint32_ts rather than in + bytes. hashlittle() is more complicated than hashword() only because + hashlittle() has to dance around fitting the key bytes into registers. +-------------------------------------------------------------------- +*/ +uint32_t ngx_lookup3_hashword(const uint32_t *k, /* the key, an array of uint32_t values */ + size_t length, /* the length of the key, in uint32_ts */ + uint32_t initval) /* the previous hash, or an arbitrary value */ +{ + uint32_t a,b,c; + + /* Set up the internal state */ + a = b = c = 0xdeadbeef + (((uint32_t)length)<<2) + initval; + + /*------------------------------------------------- handle most of the key */ + while (length > 3) + { + a += k[0]; + b += k[1]; + c += k[2]; + mix(a,b,c); + length -= 3; + k += 3; + } + + /*------------------------------------------- handle the last 3 uint32_t's */ + switch(length) /* all the case statements fall through */ + { + case 3 : c+=k[2]; + case 2 : b+=k[1]; + case 1 : a+=k[0]; + final(a,b,c); + case 0: /* case 0: nothing left to add */ + break; + } + /*------------------------------------------------------ report the result */ + return c; +} + + +/* +-------------------------------------------------------------------- +hashword2() -- same as hashword(), but take two seeds and return two +32-bit values. pc and pb must both be nonnull, and *pc and *pb must +both be initialized with seeds. If you pass in (*pb)==0, the output +(*pc) will be the same as the return value from hashword(). +-------------------------------------------------------------------- +*/ +void ngx_lookup3_hashword2 (const uint32_t *k, /* the key, an array of uint32_t values */ + size_t length, /* the length of the key, in uint32_ts */ + uint32_t *pc, /* IN: seed OUT: primary hash value */ + uint32_t *pb) /* IN: more seed OUT: secondary hash value */ +{ + uint32_t a,b,c; + + /* Set up the internal state */ + a = b = c = 0xdeadbeef + ((uint32_t)(length<<2)) + *pc; + c += *pb; + + /*------------------------------------------------- handle most of the key */ + while (length > 3) + { + a += k[0]; + b += k[1]; + c += k[2]; + mix(a,b,c); + length -= 3; + k += 3; + } + + /*------------------------------------------- handle the last 3 uint32_t's */ + switch(length) /* all the case statements fall through */ + { + case 3 : c+=k[2]; + case 2 : b+=k[1]; + case 1 : a+=k[0]; + final(a,b,c); + case 0: /* case 0: nothing left to add */ + break; + } + /*------------------------------------------------------ report the result */ + *pc=c; *pb=b; +} + + +/* +------------------------------------------------------------------------------- +hashlittle() -- hash a variable-length key into a 32-bit value + k : the key (the unaligned variable-length array of bytes) + length : the length of the key, counting by bytes + initval : can be any 4-byte value +Returns a 32-bit value. Every bit of the key affects every bit of +the return value. Two keys differing by one or two bits will have +totally different hash values. + +The best hash table sizes are powers of 2. There is no need to do +mod a prime (mod is sooo slow!). If you need less than 32 bits, +use a bitmask. For example, if you need only 10 bits, do + h = (h & hashmask(10)); +In which case, the hash table should have hashsize(10) elements. + +If you are hashing n strings (uint8_t **)k, do it like this: + for (i=0, h=0; i 12) + { + a += k[0]; + b += k[1]; + c += k[2]; + mix(a,b,c); + length -= 12; + k += 3; + } + + /*----------------------------- handle the last (probably partial) block */ + /* + * "k[2]&0xffffff" actually reads beyond the end of the string, but + * then masks off the part it's not allowed to read. Because the + * string is aligned, the masked-off tail is in the same word as the + * rest of the string. Every machine with memory protection I've seen + * does it on word boundaries, so is OK with this. But VALGRIND will + * still catch it and complain. The masking trick does make the hash + * noticably faster for short strings (like English words). + */ +#ifndef VALGRIND + + switch(length) + { + case 12: c+=k[2]; b+=k[1]; a+=k[0]; break; + case 11: c+=k[2]&0xffffff; b+=k[1]; a+=k[0]; break; + case 10: c+=k[2]&0xffff; b+=k[1]; a+=k[0]; break; + case 9 : c+=k[2]&0xff; b+=k[1]; a+=k[0]; break; + case 8 : b+=k[1]; a+=k[0]; break; + case 7 : b+=k[1]&0xffffff; a+=k[0]; break; + case 6 : b+=k[1]&0xffff; a+=k[0]; break; + case 5 : b+=k[1]&0xff; a+=k[0]; break; + case 4 : a+=k[0]; break; + case 3 : a+=k[0]&0xffffff; break; + case 2 : a+=k[0]&0xffff; break; + case 1 : a+=k[0]&0xff; break; + case 0 : return c; /* zero length strings require no mixing */ + } + +#else /* make valgrind happy */ + const uint8_t *k8; + + k8 = (const uint8_t *)k; + switch(length) + { + case 12: c+=k[2]; b+=k[1]; a+=k[0]; break; + case 11: c+=((uint32_t)k8[10])<<16; /* fall through */ + case 10: c+=((uint32_t)k8[9])<<8; /* fall through */ + case 9 : c+=k8[8]; /* fall through */ + case 8 : b+=k[1]; a+=k[0]; break; + case 7 : b+=((uint32_t)k8[6])<<16; /* fall through */ + case 6 : b+=((uint32_t)k8[5])<<8; /* fall through */ + case 5 : b+=k8[4]; /* fall through */ + case 4 : a+=k[0]; break; + case 3 : a+=((uint32_t)k8[2])<<16; /* fall through */ + case 2 : a+=((uint32_t)k8[1])<<8; /* fall through */ + case 1 : a+=k8[0]; break; + case 0 : return c; + } + +#endif /* !valgrind */ + + } else if (HASH_LITTLE_ENDIAN && ((u.i & 0x1) == 0)) { + const uint16_t *k = (const uint16_t *)key; /* read 16-bit chunks */ + const uint8_t *k8; + + /*--------------- all but last block: aligned reads and different mixing */ + while (length > 12) + { + a += k[0] + (((uint32_t)k[1])<<16); + b += k[2] + (((uint32_t)k[3])<<16); + c += k[4] + (((uint32_t)k[5])<<16); + mix(a,b,c); + length -= 12; + k += 6; + } + + /*----------------------------- handle the last (probably partial) block */ + k8 = (const uint8_t *)k; + switch(length) + { + case 12: c+=k[4]+(((uint32_t)k[5])<<16); + b+=k[2]+(((uint32_t)k[3])<<16); + a+=k[0]+(((uint32_t)k[1])<<16); + break; + case 11: c+=((uint32_t)k8[10])<<16; /* fall through */ + case 10: c+=k[4]; + b+=k[2]+(((uint32_t)k[3])<<16); + a+=k[0]+(((uint32_t)k[1])<<16); + break; + case 9 : c+=k8[8]; /* fall through */ + case 8 : b+=k[2]+(((uint32_t)k[3])<<16); + a+=k[0]+(((uint32_t)k[1])<<16); + break; + case 7 : b+=((uint32_t)k8[6])<<16; /* fall through */ + case 6 : b+=k[2]; + a+=k[0]+(((uint32_t)k[1])<<16); + break; + case 5 : b+=k8[4]; /* fall through */ + case 4 : a+=k[0]+(((uint32_t)k[1])<<16); + break; + case 3 : a+=((uint32_t)k8[2])<<16; /* fall through */ + case 2 : a+=k[0]; + break; + case 1 : a+=k8[0]; + break; + case 0 : return c; /* zero length requires no mixing */ + } + + } else { /* need to read the key one byte at a time */ + const uint8_t *k = (const uint8_t *)key; + + /*--------------- all but the last block: affect some 32 bits of (a,b,c) */ + while (length > 12) + { + a += k[0]; + a += ((uint32_t)k[1])<<8; + a += ((uint32_t)k[2])<<16; + a += ((uint32_t)k[3])<<24; + b += k[4]; + b += ((uint32_t)k[5])<<8; + b += ((uint32_t)k[6])<<16; + b += ((uint32_t)k[7])<<24; + c += k[8]; + c += ((uint32_t)k[9])<<8; + c += ((uint32_t)k[10])<<16; + c += ((uint32_t)k[11])<<24; + mix(a,b,c); + length -= 12; + k += 12; + } + + /*-------------------------------- last block: affect all 32 bits of (c) */ + switch(length) /* all the case statements fall through */ + { + case 12: c+=((uint32_t)k[11])<<24; + case 11: c+=((uint32_t)k[10])<<16; + case 10: c+=((uint32_t)k[9])<<8; + case 9 : c+=k[8]; + case 8 : b+=((uint32_t)k[7])<<24; + case 7 : b+=((uint32_t)k[6])<<16; + case 6 : b+=((uint32_t)k[5])<<8; + case 5 : b+=k[4]; + case 4 : a+=((uint32_t)k[3])<<24; + case 3 : a+=((uint32_t)k[2])<<16; + case 2 : a+=((uint32_t)k[1])<<8; + case 1 : a+=k[0]; + break; + case 0 : return c; + } + } + + final(a,b,c); + return c; +} + + +/* + * hashlittle2: return 2 32-bit hash values + * + * This is identical to hashlittle(), except it returns two 32-bit hash + * values instead of just one. This is good enough for hash table + * lookup with 2^^64 buckets, or if you want a second hash if you're not + * happy with the first, or if you want a probably-unique 64-bit ID for + * the key. *pc is better mixed than *pb, so use *pc first. If you want + * a 64-bit value do something like "*pc + (((uint64_t)*pb)<<32)". + */ +void ngx_lookup3_hashlittle2(const void *key, /* the key to hash */ + size_t length, /* length of the key */ + uint32_t *pc, /* IN: primary initval, OUT: primary hash */ + uint32_t *pb) /* IN: secondary initval, OUT: secondary hash */ +{ + uint32_t a,b,c; /* internal state */ + union { const void *ptr; size_t i; } u; /* needed for Mac Powerbook G4 */ + + /* Set up the internal state */ + a = b = c = 0xdeadbeef + ((uint32_t)length) + *pc; + c += *pb; + + u.ptr = key; + if (HASH_LITTLE_ENDIAN && ((u.i & 0x3) == 0)) { + const uint32_t *k = (const uint32_t *)key; /* read 32-bit chunks */ + + /*------ all but last block: aligned reads and affect 32 bits of (a,b,c) */ + while (length > 12) + { + a += k[0]; + b += k[1]; + c += k[2]; + mix(a,b,c); + length -= 12; + k += 3; + } + + /*----------------------------- handle the last (probably partial) block */ + /* + * "k[2]&0xffffff" actually reads beyond the end of the string, but + * then masks off the part it's not allowed to read. Because the + * string is aligned, the masked-off tail is in the same word as the + * rest of the string. Every machine with memory protection I've seen + * does it on word boundaries, so is OK with this. But VALGRIND will + * still catch it and complain. The masking trick does make the hash + * noticably faster for short strings (like English words). + */ +#ifndef VALGRIND + + switch(length) + { + case 12: c+=k[2]; b+=k[1]; a+=k[0]; break; + case 11: c+=k[2]&0xffffff; b+=k[1]; a+=k[0]; break; + case 10: c+=k[2]&0xffff; b+=k[1]; a+=k[0]; break; + case 9 : c+=k[2]&0xff; b+=k[1]; a+=k[0]; break; + case 8 : b+=k[1]; a+=k[0]; break; + case 7 : b+=k[1]&0xffffff; a+=k[0]; break; + case 6 : b+=k[1]&0xffff; a+=k[0]; break; + case 5 : b+=k[1]&0xff; a+=k[0]; break; + case 4 : a+=k[0]; break; + case 3 : a+=k[0]&0xffffff; break; + case 2 : a+=k[0]&0xffff; break; + case 1 : a+=k[0]&0xff; break; + case 0 : *pc=c; *pb=b; return; /* zero length strings require no mixing */ + } + +#else /* make valgrind happy */ + switch(length) + { + case 12: c+=k[2]; b+=k[1]; a+=k[0]; break; + case 11: c+=((uint32_t)k8[10])<<16; /* fall through */ + case 10: c+=((uint32_t)k8[9])<<8; /* fall through */ + case 9 : c+=k8[8]; /* fall through */ + case 8 : b+=k[1]; a+=k[0]; break; + case 7 : b+=((uint32_t)k8[6])<<16; /* fall through */ + case 6 : b+=((uint32_t)k8[5])<<8; /* fall through */ + case 5 : b+=k8[4]; /* fall through */ + case 4 : a+=k[0]; break; + case 3 : a+=((uint32_t)k8[2])<<16; /* fall through */ + case 2 : a+=((uint32_t)k8[1])<<8; /* fall through */ + case 1 : a+=k8[0]; break; + case 0 : *pc=c; *pb=b; return; /* zero length strings require no mixing */ + } + +#endif /* !valgrind */ + + } else if (HASH_LITTLE_ENDIAN && ((u.i & 0x1) == 0)) { + const uint16_t *k = (const uint16_t *)key; /* read 16-bit chunks */ + const uint8_t *k8; + + /*--------------- all but last block: aligned reads and different mixing */ + while (length > 12) + { + a += k[0] + (((uint32_t)k[1])<<16); + b += k[2] + (((uint32_t)k[3])<<16); + c += k[4] + (((uint32_t)k[5])<<16); + mix(a,b,c); + length -= 12; + k += 6; + } + + /*----------------------------- handle the last (probably partial) block */ + k8 = (const uint8_t *)k; + switch(length) + { + case 12: c+=k[4]+(((uint32_t)k[5])<<16); + b+=k[2]+(((uint32_t)k[3])<<16); + a+=k[0]+(((uint32_t)k[1])<<16); + break; + case 11: c+=((uint32_t)k8[10])<<16; /* fall through */ + case 10: c+=k[4]; + b+=k[2]+(((uint32_t)k[3])<<16); + a+=k[0]+(((uint32_t)k[1])<<16); + break; + case 9 : c+=k8[8]; /* fall through */ + case 8 : b+=k[2]+(((uint32_t)k[3])<<16); + a+=k[0]+(((uint32_t)k[1])<<16); + break; + case 7 : b+=((uint32_t)k8[6])<<16; /* fall through */ + case 6 : b+=k[2]; + a+=k[0]+(((uint32_t)k[1])<<16); + break; + case 5 : b+=k8[4]; /* fall through */ + case 4 : a+=k[0]+(((uint32_t)k[1])<<16); + break; + case 3 : a+=((uint32_t)k8[2])<<16; /* fall through */ + case 2 : a+=k[0]; + break; + case 1 : a+=k8[0]; + break; + case 0 : *pc=c; *pb=b; return; /* zero length strings require no mixing */ + } + + } else { /* need to read the key one byte at a time */ + const uint8_t *k = (const uint8_t *)key; + + /*--------------- all but the last block: affect some 32 bits of (a,b,c) */ + while (length > 12) + { + a += k[0]; + a += ((uint32_t)k[1])<<8; + a += ((uint32_t)k[2])<<16; + a += ((uint32_t)k[3])<<24; + b += k[4]; + b += ((uint32_t)k[5])<<8; + b += ((uint32_t)k[6])<<16; + b += ((uint32_t)k[7])<<24; + c += k[8]; + c += ((uint32_t)k[9])<<8; + c += ((uint32_t)k[10])<<16; + c += ((uint32_t)k[11])<<24; + mix(a,b,c); + length -= 12; + k += 12; + } + + /*-------------------------------- last block: affect all 32 bits of (c) */ + switch(length) /* all the case statements fall through */ + { + case 12: c+=((uint32_t)k[11])<<24; + case 11: c+=((uint32_t)k[10])<<16; + case 10: c+=((uint32_t)k[9])<<8; + case 9 : c+=k[8]; + case 8 : b+=((uint32_t)k[7])<<24; + case 7 : b+=((uint32_t)k[6])<<16; + case 6 : b+=((uint32_t)k[5])<<8; + case 5 : b+=k[4]; + case 4 : a+=((uint32_t)k[3])<<24; + case 3 : a+=((uint32_t)k[2])<<16; + case 2 : a+=((uint32_t)k[1])<<8; + case 1 : a+=k[0]; + break; + case 0 : *pc=c; *pb=b; return; /* zero length strings require no mixing */ + } + } + + final(a,b,c); + *pc=c; *pb=b; +} + + + +/* + * hashbig(): + * This is the same as hashword() on big-endian machines. It is different + * from hashlittle() on all machines. hashbig() takes advantage of + * big-endian byte ordering. + */ +uint32_t ngx_lookup3_hashbig(const void *key, size_t length, uint32_t initval) +{ + uint32_t a,b,c; + union { const void *ptr; size_t i; } u; /* to cast key to (size_t) happily */ + + /* Set up the internal state */ + a = b = c = 0xdeadbeef + ((uint32_t)length) + initval; + + u.ptr = key; + if (HASH_BIG_ENDIAN && ((u.i & 0x3) == 0)) { + const uint32_t *k = (const uint32_t *)key; /* read 32-bit chunks */ + + /*------ all but last block: aligned reads and affect 32 bits of (a,b,c) */ + while (length > 12) + { + a += k[0]; + b += k[1]; + c += k[2]; + mix(a,b,c); + length -= 12; + k += 3; + } + + /*----------------------------- handle the last (probably partial) block */ + /* + * "k[2]<<8" actually reads beyond the end of the string, but + * then shifts out the part it's not allowed to read. Because the + * string is aligned, the illegal read is in the same word as the + * rest of the string. Every machine with memory protection I've seen + * does it on word boundaries, so is OK with this. But VALGRIND will + * still catch it and complain. The masking trick does make the hash + * noticably faster for short strings (like English words). + */ +#ifndef VALGRIND + + switch(length) + { + case 12: c+=k[2]; b+=k[1]; a+=k[0]; break; + case 11: c+=k[2]&0xffffff00; b+=k[1]; a+=k[0]; break; + case 10: c+=k[2]&0xffff0000; b+=k[1]; a+=k[0]; break; + case 9 : c+=k[2]&0xff000000; b+=k[1]; a+=k[0]; break; + case 8 : b+=k[1]; a+=k[0]; break; + case 7 : b+=k[1]&0xffffff00; a+=k[0]; break; + case 6 : b+=k[1]&0xffff0000; a+=k[0]; break; + case 5 : b+=k[1]&0xff000000; a+=k[0]; break; + case 4 : a+=k[0]; break; + case 3 : a+=k[0]&0xffffff00; break; + case 2 : a+=k[0]&0xffff0000; break; + case 1 : a+=k[0]&0xff000000; break; + case 0 : return c; /* zero length strings require no mixing */ + } + +#else /* make valgrind happy */ + + k8 = (const uint8_t *)k; + switch(length) /* all the case statements fall through */ + { + case 12: c+=k[2]; b+=k[1]; a+=k[0]; break; + case 11: c+=((uint32_t)k8[10])<<8; /* fall through */ + case 10: c+=((uint32_t)k8[9])<<16; /* fall through */ + case 9 : c+=((uint32_t)k8[8])<<24; /* fall through */ + case 8 : b+=k[1]; a+=k[0]; break; + case 7 : b+=((uint32_t)k8[6])<<8; /* fall through */ + case 6 : b+=((uint32_t)k8[5])<<16; /* fall through */ + case 5 : b+=((uint32_t)k8[4])<<24; /* fall through */ + case 4 : a+=k[0]; break; + case 3 : a+=((uint32_t)k8[2])<<8; /* fall through */ + case 2 : a+=((uint32_t)k8[1])<<16; /* fall through */ + case 1 : a+=((uint32_t)k8[0])<<24; break; + case 0 : return c; + } + +#endif /* !VALGRIND */ + + } else { /* need to read the key one byte at a time */ + const uint8_t *k = (const uint8_t *)key; + + /*--------------- all but the last block: affect some 32 bits of (a,b,c) */ + while (length > 12) + { + a += ((uint32_t)k[0])<<24; + a += ((uint32_t)k[1])<<16; + a += ((uint32_t)k[2])<<8; + a += ((uint32_t)k[3]); + b += ((uint32_t)k[4])<<24; + b += ((uint32_t)k[5])<<16; + b += ((uint32_t)k[6])<<8; + b += ((uint32_t)k[7]); + c += ((uint32_t)k[8])<<24; + c += ((uint32_t)k[9])<<16; + c += ((uint32_t)k[10])<<8; + c += ((uint32_t)k[11]); + mix(a,b,c); + length -= 12; + k += 12; + } + + /*-------------------------------- last block: affect all 32 bits of (c) */ + switch(length) /* all the case statements fall through */ + { + case 12: c+=k[11]; + case 11: c+=((uint32_t)k[10])<<8; + case 10: c+=((uint32_t)k[9])<<16; + case 9 : c+=((uint32_t)k[8])<<24; + case 8 : b+=k[7]; + case 7 : b+=((uint32_t)k[6])<<8; + case 6 : b+=((uint32_t)k[5])<<16; + case 5 : b+=((uint32_t)k[4])<<24; + case 4 : a+=k[3]; + case 3 : a+=((uint32_t)k[2])<<8; + case 2 : a+=((uint32_t)k[1])<<16; + case 1 : a+=((uint32_t)k[0])<<24; + break; + case 0 : return c; + } + } + + final(a,b,c); + return c; +} + +/* Local Variables: */ +/* mode: c */ +/* c-basic-offset: 4 */ +/* c-file-offsets: ((arglist-cont-nonempty . 4)) */ +/* End: */ diff --git a/src/core/ngx_lookup3.h b/src/core/ngx_lookup3.h new file mode 100644 index 0000000..3aa1579 --- /dev/null +++ b/src/core/ngx_lookup3.h @@ -0,0 +1,95 @@ +/* + * ngx_lookup3.h by Kirill A. Korinskiy + */ + +#ifndef _NGX_LOOKUP3_H_INCLUDED_ +#define _NGX_LOOKUP3_H_INCLUDED_ + +#include +#include + +/* +-------------------------------------------------------------------- + This works on all machines. To be useful, it requires + -- that the key be an array of uint32_t's, and + -- that the length be the number of uint32_t's in the key + + The function hashword() is identical to hashlittle() on little-endian + machines, and identical to hashbig() on big-endian machines, + except that the length has to be measured in uint32_ts rather than in + bytes. hashlittle() is more complicated than hashword() only because + hashlittle() has to dance around fitting the key bytes into registers. +-------------------------------------------------------------------- +*/ +uint32_t ngx_lookup3_hashword(const uint32_t *k, /* the key, an array of uint32_t values */ + size_t length, /* the length of the key, in uint32_ts */ + uint32_t initval); /* the previous hash, or an arbitrary value */ + +void ngx_lookup3_hashword2 (const uint32_t *k, /* the key, an array of uint32_t values */ + size_t length, /* the length of the key, in uint32_ts */ + uint32_t *pc, /* IN: seed OUT: primary hash value */ + uint32_t *pb); /* IN: more seed OUT: secondary hash value */ + + +/* +------------------------------------------------------------------------------- +hashlittle() -- hash a variable-length key into a 32-bit value + k : the key (the unaligned variable-length array of bytes) + length : the length of the key, counting by bytes + initval : can be any 4-byte value +Returns a 32-bit value. Every bit of the key affects every bit of +the return value. Two keys differing by one or two bits will have +totally different hash values. + +The best hash table sizes are powers of 2. There is no need to do +mod a prime (mod is sooo slow!). If you need less than 32 bits, +use a bitmask. For example, if you need only 10 bits, do + h = (h & hashmask(10)); +In which case, the hash table should have hashsize(10) elements. + +If you are hashing n strings (uint8_t **)k, do it like this: + for (i=0, h=0; i +#include + +typedef struct { + u_char color; + uint32_t crc32; + + ngx_rbtreehash_list_node_t list_item; + + size_t len; + u_char data[1]; +} ngx_rbtreehash_node_t; + +typedef struct { + ngx_str_t key; + ngx_str_t data; +} ngx_rbtreehash_key_t; + +typedef struct { + ngx_pool_t *pool; /* this pool need only for tempory using and must destroy afer create tree */ + ngx_array_t keys; /* keys for hash */ + ngx_rbtreehash_t *hash; +} ngx_rbtreehash_ctx_t; + +static ngx_command_t ngx_rbtreehash_commands[] = { + ngx_null_command +}; + +static ngx_core_module_t ngx_rbtreehash_module_ctx = { + ngx_string("rbtreehash"), + NULL, + NULL +}; + +ngx_module_t ngx_rbtreehash_module = { + NGX_MODULE_V1, + &ngx_rbtreehash_module_ctx, /* module context */ + ngx_rbtreehash_commands, /* module directives */ + NGX_CORE_MODULE, /* module type */ + NULL, /* init master */ + NULL, /* init module */ + NULL, /* init process */ + NULL, /* init thread */ + NULL, /* exit thread */ + NULL, /* exit process */ + NULL, /* exit master */ + NGX_MODULE_V1_PADDING +}; + +static void* +ngx_rbtreehash_alloc(ngx_rbtreehash_pool_t *pool, size_t size) +{ + if (pool->pool) { + /* use pool to allocated memory */ + return ngx_palloc(pool->pool, size); + } + + if (pool->shm_zone) { + /* or shm */ + return ngx_slab_alloc((ngx_slab_pool_t *) pool->shm_zone->shm.addr, + size); + } + + /* or system system memory */ + if (!pool->log) { + /* if not set log for pool use cycle log */ + return ngx_alloc(size, ngx_cycle->log); + } + + return ngx_alloc(size, pool->log); +} + +static void +ngx_rbtreehash_free(ngx_rbtreehash_pool_t *pool, void *p) +{ + if (pool->pool) { + /* can't have free in pool-based alloc */ + return; + } + + if (pool->shm_zone) { + ngx_slab_free((ngx_slab_pool_t *) pool->shm_zone->shm.addr, p); + return; + } + + ngx_free(p); +} + + +static void +ngx_rbtreehash_list_insert(ngx_rbtreehash_t *hash, ngx_rbtreehash_node_t *node) +{ + node->list_item.len = node->len; + node->list_item.data = node->data; + node->list_item.next = NULL; + node->list_item.prev = NULL; + + if (hash->data->list.head) { + hash->data->list.tail->next = &node->list_item; + node->list_item.prev = hash->data->list.tail; + hash->data->list.tail = &node->list_item; + } else { + hash->data->list.head = &node->list_item; + hash->data->list.tail = &node->list_item; + } +} + + +static void +ngx_rbtreehash_list_delete(ngx_rbtreehash_t *hash, ngx_rbtreehash_node_t *node) +{ + /* not safe, sure */ + + if (&node->list_item == hash->data->list.head) { + hash->data->list.head = hash->data->list.head->next; + hash->data->list.head->prev = NULL; + } else if (&node->list_item == hash->data->list.tail) { + hash->data->list.tail = hash->data->list.tail->prev; + } else { + node->list_item.prev->next = node->list_item.next; + node->list_item.next->prev = node->list_item.prev; + } +} + + +static void +ngx_rbtreehash_rbtree_insert_value(ngx_rbtree_node_t *temp, + ngx_rbtree_node_t *node, ngx_rbtree_node_t *sentinel) +{ + ngx_rbtree_node_t **p; + ngx_rbtreehash_node_t *rn, *rnt; + + for ( ;; ) { + + if (node->key < temp->key) { + + p = &temp->left; + + } else if (node->key > temp->key) { + + p = &temp->right; + + } else { /* node->key == temp->key */ + + rn = (ngx_rbtreehash_node_t *) &node->color; + rnt = (ngx_rbtreehash_node_t *) &temp->color; + + p = rn->crc32 < rnt->crc32 + ? &temp->left : &temp->right; + } + + if (*p == sentinel) { + break; + } + + temp = *p; + } + + *p = node; + node->parent = temp; + node->left = sentinel; + node->right = sentinel; + ngx_rbt_red(node); +} + +ngx_rbtree_node_t* ngx_rbtreehash_insert(ngx_rbtreehash_t *hash, ngx_str_t *key, + void *value, size_t len) +{ + uint32_t n; + ngx_rbtree_node_t *node; + ngx_rbtreehash_node_t *rn; + + n = offsetof(ngx_rbtree_node_t, color) + + offsetof(ngx_rbtreehash_node_t, data) + + len; + + node = ngx_rbtreehash_alloc(&hash->pool, n); + if (node == NULL) { + return NULL; + } + hash->data->nodes++; + + rn = (ngx_rbtreehash_node_t*) &node->color; + + node->key = ngx_lookup3_hashlittle(key->data, key->len, 0); + rn->crc32 = ngx_crc32_short(key->data, key->len); + rn->len = len; + ngx_memcpy(rn->data, value, len); + + ngx_rbtree_insert(hash->data->tree, node); + ngx_rbtreehash_list_insert(hash, rn); + + return node; +} + +ngx_int_t ngx_rbtreehash_delete(ngx_rbtreehash_t *hash, ngx_str_t *key) +{ + ngx_uint_t hash32; + ngx_uint_t crc32; + ngx_rbtree_node_t *node; + ngx_rbtreehash_node_t *rn; + + hash32 = ngx_lookup3_hashlittle(key->data, key->len, 0); + crc32 = ngx_crc32_short(key->data, key->len); + node = hash->data->tree->root; + + while (node != hash->data->tree->sentinel) { + if (hash32 < node->key) { + node = node->left; + continue; + } + + if (hash32 > node->key) { + node = node->right; + continue; + } + + do { + rn = (ngx_rbtreehash_node_t*) &node->color; + + if (crc32 == rn->crc32) { + break; + } + + if (crc32 == rn->crc32) { + break; + } + + node = crc32 < rn->crc32 ? node->left : node->right; + } while (node != hash->data->tree->sentinel && hash32 == node->key); + + break; + } + + if (node == hash->data->tree->sentinel) { + return NGX_OK; + } + + ngx_rbtree_delete(hash->data->tree, node); + + ngx_rbtreehash_list_delete(hash, rn); + + ngx_rbtreehash_free(&hash->pool, node); + + hash->data->nodes--; + + return NGX_OK; +} + +ngx_int_t ngx_rbtreehash_init(ngx_rbtreehash_t *hash) +{ + ngx_rbtree_node_t *sentinel; + + hash->data = ngx_rbtreehash_alloc(&hash->pool, sizeof(ngx_rbtreehash_hash_t)); + ngx_memzero(hash->data, sizeof(ngx_rbtreehash_hash_t)); + + hash->data->tree = ngx_rbtreehash_alloc(&hash->pool, sizeof(ngx_rbtree_t)); + if (hash->data->tree == NULL) { + return NGX_ERROR; + } + + sentinel = ngx_rbtreehash_alloc(&hash->pool, sizeof(ngx_rbtree_node_t)); + if (sentinel == NULL) { + return NGX_ERROR; + } + + ngx_rbtree_init(hash->data->tree, sentinel, + ngx_rbtreehash_rbtree_insert_value); + + hash->data->list.head = NULL; + hash->data->list.tail = NULL; + + return NGX_OK; +} + +ngx_int_t ngx_rbtreehash_destroy(ngx_rbtreehash_t *hash) +{ + ngx_rbtree_node_t *node; + + for (;;) { + if (hash->data->tree->root == hash->data->tree->sentinel) { + break; + } + + node = ngx_rbtree_min(hash->data->tree->root, + hash->data->tree->sentinel); + + ngx_rbtree_delete(hash->data->tree, node); + + ngx_rbtreehash_free(&hash->pool, node); + + } + + return NGX_OK; +} + +static ngx_int_t +ngx_rbtreehash_init_tree(ngx_shm_zone_t *shm_zone, void *data) +{ + uint32_t i; + ngx_rbtreehash_t *hash; + ngx_rbtreehash_ctx_t *octx = data; + ngx_rbtreehash_ctx_t *ctx; + ngx_rbtreehash_key_t *keys; + + ctx = shm_zone->data; + + if (octx && + ngx_strncmp(ctx->hash->pool.shm_key.data, + octx->hash->pool.shm_key.data, + ctx->hash->pool.shm_key.len) != 0) { + ngx_log_error(NGX_LOG_EMERG, shm_zone->shm.log, 0, + "rbhash use path \"%s\" with previously it used " + "the \"%s\"", ctx->hash->pool.shm_key.data, + octx->hash->pool.shm_key.data); + return NGX_ERROR; + } + + if (ngx_rbtreehash_init(ctx->hash) != NGX_OK) { + return NGX_ERROR; + } + + keys = ctx->keys.elts; + + for (i = 0; i < ctx->keys.nelts; i++) { + if (keys[i].key.len == 0) { + continue; + } + + if (ngx_rbtreehash_insert(ctx->hash, &keys[i].key, + keys[i].data.data, + keys[i].data.len) == NULL) { + return NGX_ERROR; + } + + } + + if (ctx->pool) { + ngx_destroy_pool(ctx->pool); + ctx->pool = NULL; + } + + /* setup hash->data to all linked conf */ + for (hash = ctx->hash; hash->next; hash = hash->next) { + hash->next->data = hash->data; + } + + for (; hash->prev; hash = hash->prev) { + hash->prev->data = hash->data; + } + + return NGX_OK; +} + +void* ngx_rbtreehash_find(ngx_rbtreehash_t *hash, ngx_str_t *key, size_t *len) +{ + ngx_uint_t hash32; + ngx_uint_t crc32; + ngx_rbtree_node_t *node; + ngx_rbtree_node_t *sentinel; + ngx_rbtreehash_node_t *rn; + + if (!hash->data) { + return NULL; + } + + if (hash->data->nodes == 0) { + return NULL; + } + + if (key->len == 0) { + return NULL; + } + + hash32 = ngx_lookup3_hashlittle(key->data, key->len, 0); + crc32 = ngx_crc32_short(key->data, key->len); + + node = hash->data->tree->root; + sentinel = hash->data->tree->sentinel; + + while (node != sentinel) { + if (hash32 < node->key) { + node = node->left; + continue; + } + + if (hash32 > node->key) { + node = node->right; + continue; + } + + do { + rn = (ngx_rbtreehash_node_t*) &node->color; + + if (crc32 == rn->crc32) { + *len = rn->len; + return rn->data; + } + + if (crc32 == rn->crc32) { + break; + } + + node = crc32 < rn->crc32 ? node->left : node->right; + + } while (node != sentinel && hash32 == node->key); + break; + } + + return NULL; +} + +char * +ngx_rbtreehash_crete_shared_by_size(ngx_conf_t *cf, ngx_command_t *cmd, void *conf) +{ + ngx_str_t *value; + char *p = conf; + size_t size; + ngx_rbtreehash_ctx_t *ctx; + + ctx = ngx_pcalloc(cf->pool, sizeof(ngx_rbtreehash_ctx_t)); + if (ctx == NULL) { + return NGX_CONF_ERROR; + } + + ctx->hash = (ngx_rbtreehash_t*) (p + cmd->offset); + + if (cf->args->nelts != 3) { + return "need two args"; + } + + value = cf->args->elts; + + if (ctx->hash->pool.shm_zone) { + return "is duplicate"; + } + + size = ngx_parse_offset(&value[2]); + + ctx->hash->pool.shm_key.len = value[1].len + NGX_INT_T_LEN; + ctx->hash->pool.shm_key.data = ngx_palloc(cf->pool, ctx->hash->pool.shm_key.len); + if (ctx->hash->pool.shm_key.data == NULL) { + return NGX_CONF_ERROR; + } + + ngx_sprintf(ctx->hash->pool.shm_key.data, "%V%d", &value[1], size); + + if (size < (size_t) (8 * ngx_pagesize)) { + size = (size_t) (8 * ngx_pagesize); + } else { + size = 8 * ngx_pagesize * (size / (8 * ngx_pagesize) + 1); + } + + ctx->hash->pool.shm_zone = ngx_shared_memory_add(cf, &ctx->hash->pool.shm_key, + size, + &ngx_rbtreehash_module); + + if (ctx->hash->pool.shm_zone == NULL) { + return NGX_CONF_ERROR; + } + + ctx->hash->pool.shm_zone->init = ngx_rbtreehash_init_tree; + ctx->hash->pool.shm_zone->data = ctx; + ctx->hash->pool.pool = NULL; + ctx->hash->pool.log = cf->log; + + return NGX_CONF_OK; +} + +char * +ngx_rbtreehash_from_path(ngx_conf_t *cf, ngx_command_t *cmd, void *conf) +{ + ngx_str_t *value; + char *p = conf; + ngx_str_t data; + ngx_str_t path; + ngx_int_t fd; + ngx_file_info_t fi; + ngx_rbtreehash_key_t *key; + size_t need_shmem = 0; + ngx_rbtreehash_ctx_t *ctx; + u_char *ptr; + u_char *ptr_last; + u_char *ptr_end; + size_t len; + + ctx = ngx_pcalloc(cf->pool, sizeof(ngx_rbtreehash_ctx_t)); + if (ctx == NULL) { + return NGX_CONF_ERROR; + } + + ctx->hash = (ngx_rbtreehash_t*) (p + cmd->offset); + + if (cf->args->nelts != 2) { + return "need two args"; + } + + value = cf->args->elts; + + if (ctx->hash->pool.shm_zone) { + return "is duplicate"; + } + + ctx->pool = ngx_create_pool(4096, cf->log); + if (ctx->pool == NULL) { + return NGX_CONF_ERROR; + } + + if (ngx_conf_full_name(cf->cycle, &value[1], 0) == NGX_ERROR) { + return NGX_CONF_ERROR; + } + + path = value[1]; /* shm_key is a path to file with data */ + + fd = ngx_open_file(path.data, NGX_FILE_RDONLY, NGX_FILE_OPEN, 0); + if (fd == NGX_INVALID_FILE) { + if (ngx_errno == NGX_ENOENT) { + return NGX_CONF_OK; + } + + ngx_log_error(NGX_LOG_CRIT, cf->log, ngx_errno, + ngx_open_file_n " \"%s\" failed", path.data); + return NGX_CONF_ERROR; + } + + if (ngx_fd_info(fd, &fi) == NGX_FILE_ERROR) { + ngx_log_error(NGX_LOG_CRIT, cf->log, ngx_errno, + ngx_fd_info_n " \"%s\" failed", path.data); + + return NGX_CONF_ERROR; + } + + data.len = ngx_file_size(&fi); + data.data = mmap(NULL, data.len, PROT_READ, MAP_PRIVATE, fd, 0); + if (data.data == MAP_FAILED) { + return NGX_CONF_ERROR; + } + + for (ptr = data.data, ptr_end = data.data + data.len, len = 0; + ptr <= ptr_end; ptr++) { + if (*ptr == '\n' || ptr == ptr_end) { + len++; + } + } + + if (ngx_array_init(&ctx->keys, ctx->pool, len, + sizeof(ngx_rbtreehash_key_t)) != NGX_OK) { + return NGX_CONF_ERROR; + } + + key = ngx_array_push(&ctx->keys); + ngx_memzero(key, ctx->keys.size); + for (ptr_last = ptr = data.data, ptr_end = data.data + data.len + ; ptr < ptr_end; ptr++) { + switch (*ptr) { + case ' ': + { + if (*ptr == *ptr_last) { + ptr++; + ptr_last = ptr; + } + break; + } + case ':': + { + if (key->key.data != NULL) { + continue; + } + key->key.len = ptr - ptr_last; + key->key.data = ngx_palloc(ctx->pool, key->key.len); + if (key->key.data == NULL) { + goto error; + } + + memcpy(key->key.data, ptr_last, key->key.len); + + ptr++; + ptr_last = ptr; + break; + } + case '\n': + { + if (key->key.data == NULL) { + key->key.len = ptr - ptr_last; + key->key.data = ngx_palloc(ctx->pool, key->key.len); + if (key->key.data == NULL) { + goto error; + } + + memcpy(key->key.data, ptr_last, key->key.len); + + key->data = key->key; + } else { + key->data.len = ptr - ptr_last; + key->data.data = ngx_palloc(ctx->pool, key->data.len); + if (key->data.data == NULL) { + goto error; + } + + memcpy(key->data.data, ptr_last, key->data.len); + } + + need_shmem += ngx_align(offsetof(ngx_rbtree_node_t, color) + + offsetof(ngx_rbtreehash_node_t, data) + + key->data.len, + ngx_pagesize); + + ptr++; + ptr_last = ptr; + key = ngx_array_push(&ctx->keys); + ngx_memzero(key, ctx->keys.size); + break; + } + } + } + + ctx->hash->pool.shm_key.len = path.len + NGX_INT_T_LEN; + ctx->hash->pool.shm_key.data = ngx_palloc(cf->pool, ctx->hash->pool.shm_key.len); + if (ctx->hash->pool.shm_key.data == NULL) { + goto error; + } + + /* shm_key is path to file and value hash function on the contents of file оп*/ + ngx_sprintf(ctx->hash->pool.shm_key.data, "%s %d", &path, + ngx_lookup3_hashlittle(data.data, data.len, 0)); + + + munmap(data.data, data.len); + + need_shmem += ngx_align(sizeof(ngx_rbtree_t), ngx_pagesize) + + ngx_align(sizeof(ngx_rbtree_node_t), ngx_pagesize) /* sentinel */ + + ngx_align(sizeof(ngx_rbtreehash_hash_t), ngx_pagesize); /* hash_data */ + + if (need_shmem < (size_t) (8 * ngx_pagesize)) { + need_shmem = (size_t) (8 * ngx_pagesize); + } else { + need_shmem = 8 * ngx_pagesize * (need_shmem / (8 * ngx_pagesize) + 1); + } + + ctx->hash->pool.shm_zone = ngx_shared_memory_add(cf, &ctx->hash->pool.shm_key, + need_shmem, + &ngx_rbtreehash_module); + + if (ctx->hash->pool.shm_zone == NULL) { + goto error_wo_data; + } + + ctx->hash->pool.shm_zone->init = ngx_rbtreehash_init_tree; + ctx->hash->pool.shm_zone->data = ctx; + ctx->hash->pool.pool = NULL; + + return NGX_CONF_OK; + + error: + munmap(data.data, data.len); + error_wo_data: + ngx_destroy_pool(ctx->pool); + return NGX_CONF_ERROR; +} + +ngx_int_t ngx_rbtreehash_merge_value(ngx_rbtreehash_t *conf, ngx_rbtreehash_t *prev) +{ + ngx_rbtreehash_t *hash; + + if (prev->pool.shm_zone || prev->pool.pool) { + conf->pool = prev->pool; + } + + for (hash = prev; hash->next; hash = hash->next); + hash->next = conf; + conf->prev = hash; + + return NGX_OK; +} + +/* Local Variables: */ +/* mode: c */ +/* c-basic-offset: 4 */ +/* c-file-offsets: ((arglist-cont-nonempty . 4)) */ +/* End: */ diff --git a/src/core/ngx_rbtreehash.h b/src/core/ngx_rbtreehash.h new file mode 100644 index 0000000..657bab2 --- /dev/null +++ b/src/core/ngx_rbtreehash.h @@ -0,0 +1,77 @@ + +/* + * Copyright (C) Kirill A. Korinskiy + */ + +#ifndef __NGX_RBTREEHASH +#define __NGX_RBTREEHASH + +#include +#include + +typedef struct ngx_rbtreehash_list_node_s ngx_rbtreehash_list_node_t; + +struct ngx_rbtreehash_list_node_s { + size_t len; + void *data; + + ngx_rbtreehash_list_node_t *next; + ngx_rbtreehash_list_node_t *prev; +}; + +typedef struct { + ngx_rbtreehash_list_node_t *head; + ngx_rbtreehash_list_node_t *tail; +} ngx_rbtreehash_list_t; + + +typedef struct { + /* in hash using shm_zone */ + ngx_shm_zone_t *shm_zone; + ngx_str_t shm_key; + + /* ... or pool */ + ngx_pool_t *pool; + + ngx_log_t *log; +} ngx_rbtreehash_pool_t; + +typedef struct { + ngx_rbtree_t *tree; + size_t nodes; + + ngx_rbtreehash_list_t list; +} ngx_rbtreehash_hash_t; + +typedef struct ngx_rbtreehash_s ngx_rbtreehash_t; + +struct ngx_rbtreehash_s { + ngx_rbtreehash_pool_t pool; + ngx_rbtreehash_hash_t *data; + + /* hack to pointer to next/prev config */ + ngx_rbtreehash_t *next; + ngx_rbtreehash_t *prev; +}; + +ngx_int_t ngx_rbtreehash_init(ngx_rbtreehash_t *hash); +ngx_int_t ngx_rbtreehash_destroy(ngx_rbtreehash_t *hash); +ngx_rbtree_node_t* ngx_rbtreehash_insert(ngx_rbtreehash_t *hash, ngx_str_t *key, + void *value, size_t len); +ngx_int_t ngx_rbtreehash_delete(ngx_rbtreehash_t *hash, ngx_str_t *key); +void *ngx_rbtreehash_find(ngx_rbtreehash_t *hash, ngx_str_t *key, size_t *len); + +char *ngx_rbtreehash_crete_shared_by_size(ngx_conf_t *cf, ngx_command_t *cmd, void *conf); +char *ngx_rbtreehash_from_path(ngx_conf_t *cf, ngx_command_t *cmd, void *conf); + +ngx_int_t ngx_rbtreehash_merge_value(ngx_rbtreehash_t *conf, ngx_rbtreehash_t *prev); + +extern ngx_module_t ngx_rbtreehash_module; + +#endif //__NGX_RBTREEHASH + +/* Local Variables: */ +/* mode: c */ +/* c-basic-offset: 4 */ +/* c-file-offsets: ((arglist-cont-nonempty . 4)) */ +/* End: */ diff --git a/src/http/modules/ngx_http_status_heap_module.c b/src/http/modules/ngx_http_status_heap_module.c new file mode 100644 index 0000000..7562e0d --- /dev/null +++ b/src/http/modules/ngx_http_status_heap_module.c @@ -0,0 +1,357 @@ + +/* + * Copyright (C) Kirill A. Korinskiy + */ + + +#include +#include +#include + + +typedef struct { + ngx_rbtreehash_t heap; +} ngx_http_status_heap_srv_conf_t; + +typedef struct { + ngx_uint_t counter; + + size_t len; + u_char data[1]; +} ngx_http_status_heap_node_t; + + +static ngx_int_t ngx_http_status_heap_init(ngx_conf_t *cf); + +static void *ngx_http_status_heap_create_srv_conf(ngx_conf_t *cf); +static char *ngx_http_status_heap_merge_srv_conf(ngx_conf_t *cf, + void *parent, void *child); + +static char *ngx_http_status_heap_show(ngx_conf_t *cf, + ngx_command_t *cmd, void *conf); +static char *ngx_http_status_heap_show_all(ngx_conf_t *cf, + ngx_command_t *cmd, void *conf); + +static ngx_int_t ngx_http_status_heap_add_handler(ngx_http_request_t *r); +static ngx_int_t ngx_http_status_heap_show_handler(ngx_http_request_t *r); +static ngx_int_t ngx_http_status_heap_show_all_handler(ngx_http_request_t *r); + + +static ngx_command_t ngx_http_status_heap_commands[] = { + + { ngx_string("status_heap_show"), + NGX_HTTP_SRV_CONF|NGX_HTTP_LOC_CONF|NGX_CONF_NOARGS, + ngx_http_status_heap_show, + NGX_HTTP_LOC_CONF_OFFSET, + 0, + NULL }, + + + { ngx_string("status_heap_show_all"), + NGX_HTTP_SRV_CONF|NGX_HTTP_LOC_CONF|NGX_CONF_NOARGS, + ngx_http_status_heap_show_all, + NGX_HTTP_LOC_CONF_OFFSET, + 0, + NULL }, + + { ngx_string("status_heap"), + NGX_HTTP_SRV_CONF|NGX_CONF_TAKE2, + ngx_rbtreehash_crete_shared_by_size, + NGX_HTTP_SRV_CONF_OFFSET, + offsetof(ngx_http_status_heap_srv_conf_t, heap), + NULL }, + + ngx_null_command +}; + + +static ngx_http_module_t ngx_http_status_heap_module_ctx = { + NULL, /* preconfiguration */ + ngx_http_status_heap_init, /* postconfiguration */ + + NULL, /* create main configuration */ + NULL, /* init main configuration */ + + ngx_http_status_heap_create_srv_conf, /* create server configuration */ + ngx_http_status_heap_merge_srv_conf, /* merge server configuration */ + + NULL, /* create location configration */ + NULL /* merge location configration */ +}; + + +ngx_module_t ngx_http_status_heap_module = { + NGX_MODULE_V1, + &ngx_http_status_heap_module_ctx, /* module context */ + ngx_http_status_heap_commands, /* module directives */ + NGX_HTTP_MODULE, /* module type */ + NULL, /* init master */ + NULL, /* init module */ + NULL, /* init process */ + NULL, /* init thread */ + NULL, /* exit thread */ + NULL, /* exit process */ + NULL, /* exit master */ + NGX_MODULE_V1_PADDING +}; + + +static ngx_int_t +ngx_http_status_heap_add_handler(ngx_http_request_t *r) +{ + size_t len = 0; + + ngx_http_status_heap_node_t *node; + ngx_http_status_heap_srv_conf_t *conf; + + conf = ngx_http_get_module_srv_conf(r, ngx_http_status_heap_module); + + if (conf->heap.data == NULL) { + return NGX_DECLINED; + } + + node = ngx_rbtreehash_find(&conf->heap, &r->uri, &len); + if (len && len < offsetof(ngx_http_status_heap_node_t, data)) { + return NGX_HTTP_INTERNAL_SERVER_ERROR; + } + + if (node) { + node->counter++; + return NGX_DECLINED; + } + + len = offsetof(ngx_http_status_heap_node_t, data) + r->uri.len; + + node = ngx_pcalloc(r->pool, len); + if (node == NULL) { + return NGX_HTTP_INTERNAL_SERVER_ERROR; + } + + node->counter = 1; + + node->len = r->uri.len; + + ngx_memcpy(node->data, r->uri.data, r->uri.len); + + ngx_rbtreehash_insert(&conf->heap, &r->uri, node, len); + + return NGX_DECLINED; +} + + +static ngx_int_t +ngx_http_status_heap_show_handler(ngx_http_request_t *r) +{ + size_t len = 0; + ngx_buf_t *b; + ngx_int_t rc; + ngx_chain_t out; + + ngx_http_status_heap_node_t *node; + ngx_http_status_heap_srv_conf_t *conf; + + if (r->method != NGX_HTTP_GET && r->method != NGX_HTTP_HEAD) { + return NGX_HTTP_NOT_ALLOWED; + } + + rc = ngx_http_discard_request_body(r); + + if (rc != NGX_OK) { + return rc; + } + + r->headers_out.content_type.len = sizeof("text/plain") - 1; + r->headers_out.content_type.data = (u_char *) "text/plain"; + + conf = ngx_http_get_module_srv_conf(r, ngx_http_status_heap_module); + + if (conf->heap.data == NULL) { + return NGX_HTTP_NOT_FOUND; + } + + node = ngx_rbtreehash_find(&conf->heap, &r->uri_remainder, &len); + if (len && len < offsetof(ngx_http_status_heap_node_t, data)) { + return NGX_HTTP_INTERNAL_SERVER_ERROR; + } + + if (node == NULL) { + return NGX_HTTP_NOT_FOUND; + } + + b = ngx_create_temp_buf(r->pool, NGX_INT_T_LEN); + if (b == NULL) { + return NGX_HTTP_INTERNAL_SERVER_ERROR; + } + + out.buf = b; + out.next = NULL; + + b->last = ngx_sprintf(b->last, "%d", node->counter); + + r->headers_out.status = NGX_HTTP_OK; + r->headers_out.content_length_n = b->last - b->pos; + + b->last_buf = 1; + + rc = ngx_http_send_header(r); + + if (rc == NGX_ERROR || rc > NGX_OK || r->header_only) { + return rc; + } + + return ngx_http_output_filter(r, &out); +} + + +static ngx_int_t +ngx_http_status_heap_show_all_handler(ngx_http_request_t *r) +{ + size_t len = 0; + ngx_buf_t *b; + ngx_int_t rc; + ngx_str_t uri; + ngx_chain_t *out, *out_head = NULL, *out_prev = NULL; + + ngx_rbtreehash_list_node_t *item; + ngx_http_status_heap_node_t *node; + ngx_http_status_heap_srv_conf_t *conf; + + if (r->method != NGX_HTTP_GET && r->method != NGX_HTTP_HEAD) { + return NGX_HTTP_NOT_ALLOWED; + } + + rc = ngx_http_discard_request_body(r); + + if (rc != NGX_OK) { + return rc; + } + + r->headers_out.content_type.len = sizeof("text/plain") - 1; + r->headers_out.content_type.data = (u_char *) "text/plain"; + + conf = ngx_http_get_module_srv_conf(r, ngx_http_status_heap_module); + + if (conf->heap.data == NULL) { + return NGX_HTTP_NOT_FOUND; + } + + item = conf->heap.data->list.head; + + while (item) { + out = ngx_palloc(r->pool, sizeof(ngx_chain_t)); + if (out == NULL) { + return NGX_HTTP_INTERNAL_SERVER_ERROR; + } + + if (out_head == NULL) { + out_head = out; + } + + if (out_prev != NULL) { + out_prev->next = out; + } + + out->next = NULL; + + node = (ngx_http_status_heap_node_t *) item->data; + + uri.len = node->len; + uri.data = node->data; + + b = ngx_create_temp_buf(r->pool, uri.len + sizeof("\t\n") - 1 + NGX_INT_T_LEN); + if (b == NULL) { + return NGX_HTTP_INTERNAL_SERVER_ERROR; + } + + out->buf = b; + + b->last = ngx_sprintf(b->last, "%V\t%d\n", &uri, node->counter); + + len += b->last - b->pos; + + out_prev = out; + + item = item->next; + } + + + r->headers_out.status = NGX_HTTP_OK; + r->headers_out.content_length_n = len; + + b->last_buf = 1; + + rc = ngx_http_send_header(r); + + if (rc == NGX_ERROR || rc > NGX_OK || r->header_only) { + return rc; + } + + return ngx_http_output_filter(r, out_head); +} + + +static ngx_int_t ngx_http_status_heap_init(ngx_conf_t *cf) +{ + ngx_http_handler_pt *h; + ngx_http_core_main_conf_t *cmcf; + + cmcf = ngx_http_conf_get_module_main_conf(cf, ngx_http_core_module); + + h = ngx_array_push(&cmcf->phases[NGX_HTTP_POST_READ_PHASE].handlers); + if (h == NULL) { + return NGX_ERROR; + } + + *h = ngx_http_status_heap_add_handler; + + return NGX_OK; +} + + +static void *ngx_http_status_heap_create_srv_conf(ngx_conf_t *cf) +{ + ngx_http_status_heap_srv_conf_t *conf; + + conf = ngx_pcalloc(cf->pool, sizeof(ngx_http_status_heap_srv_conf_t)); + if (conf == NULL) { + return NGX_CONF_ERROR; + } + + return conf; +} + + +static char *ngx_http_status_heap_merge_srv_conf(ngx_conf_t *cf, + void *parent, void *child) +{ + ngx_http_status_heap_srv_conf_t *prev = parent; + ngx_http_status_heap_srv_conf_t *conf = child; + + ngx_rbtreehash_merge_value(&conf->heap, &prev->heap); + + return NGX_CONF_OK; +} + + +static char * +ngx_http_status_heap_show(ngx_conf_t *cf, ngx_command_t *cmd, void *conf) +{ + ngx_http_core_loc_conf_t *clcf; + + clcf = ngx_http_conf_get_module_loc_conf(cf, ngx_http_core_module); + clcf->handler = ngx_http_status_heap_show_handler; + + return NGX_CONF_OK; +} + + +static char * +ngx_http_status_heap_show_all(ngx_conf_t *cf, ngx_command_t *cmd, void *conf) +{ + ngx_http_core_loc_conf_t *clcf; + + clcf = ngx_http_conf_get_module_loc_conf(cf, ngx_http_core_module); + clcf->handler = ngx_http_status_heap_show_all_handler; + + return NGX_CONF_OK; +} diff --git a/src/http/ngx_http_core_module.c b/src/http/ngx_http_core_module.c index 966cbc2..c52eeea 100644 --- a/src/http/ngx_http_core_module.c +++ b/src/http/ngx_http_core_module.c @@ -845,6 +845,14 @@ ngx_http_core_find_config_phase(ngx_http_request_t *r, clcf = ngx_http_get_module_loc_conf(r, ngx_http_core_module); + if (!clcf->regex_locations) { + r->uri_remainder.len = r->uri.len - clcf->name.len; + r->uri_remainder.data = r->uri.data + clcf->name.len; + } else { + r->uri_remainder.len = 0; + r->uri_remainder.data = NULL; + } + if (!r->internal && clcf->internal) { ngx_http_finalize_request(r, NGX_HTTP_NOT_FOUND); return NGX_OK; diff --git a/src/http/ngx_http_request.h b/src/http/ngx_http_request.h index 97ffbbf..517994d 100644 --- a/src/http/ngx_http_request.h +++ b/src/http/ngx_http_request.h @@ -373,6 +373,7 @@ struct ngx_http_request_s { ngx_str_t request_line; ngx_str_t uri; + ngx_str_t uri_remainder; ngx_str_t args; ngx_str_t exten; ngx_str_t unparsed_uri; diff --git a/src/http/ngx_http_variables.c b/src/http/ngx_http_variables.c index d41b996..bd64108 100644 --- a/src/http/ngx_http_variables.c +++ b/src/http/ngx_http_variables.c @@ -7,6 +7,7 @@ #include #include #include +#include #include @@ -27,6 +28,14 @@ static ngx_int_t ngx_http_variable_unknown_header_out(ngx_http_request_t *r, ngx_http_variable_value_t *v, uintptr_t data); static ngx_int_t ngx_http_variable_cookie(ngx_http_request_t *r, ngx_http_variable_value_t *v, uintptr_t data); +static ngx_int_t ngx_http_variable_urlencode(ngx_http_request_t *r, + ngx_http_variable_value_t *v, uintptr_t data); +static ngx_int_t ngx_http_variable_urldecode(ngx_http_request_t *r, + ngx_http_variable_value_t *v, uintptr_t data); +static ngx_int_t ngx_http_variable_crc32(ngx_http_request_t *r, + ngx_http_variable_value_t *v, uintptr_t data); +static ngx_int_t ngx_http_variable_md5(ngx_http_request_t *r, + ngx_http_variable_value_t *v, uintptr_t data); static ngx_int_t ngx_http_variable_argument(ngx_http_request_t *r, ngx_http_variable_value_t *v, uintptr_t data); @@ -88,6 +97,16 @@ static ngx_int_t ngx_http_variable_hostname(ngx_http_request_t *r, ngx_http_variable_value_t *v, uintptr_t data); static ngx_int_t ngx_http_variable_pid(ngx_http_request_t *r, ngx_http_variable_value_t *v, uintptr_t data); +static ngx_int_t ngx_http_variable_timestamp(ngx_http_request_t *r, + ngx_http_variable_value_t *v, uintptr_t data); +static ngx_int_t ngx_http_variable_mstimestamp(ngx_http_request_t *r, + ngx_http_variable_value_t *v, uintptr_t data); +static ngx_int_t ngx_http_variable_loadavg_1m(ngx_http_request_t *r, + ngx_http_variable_value_t *v, uintptr_t data); +static ngx_int_t ngx_http_variable_loadavg_5m(ngx_http_request_t *r, + ngx_http_variable_value_t *v, uintptr_t data); +static ngx_int_t ngx_http_variable_loadavg_15m(ngx_http_request_t *r, + ngx_http_variable_value_t *v, uintptr_t data); /* * TODO: @@ -160,6 +179,10 @@ static ngx_http_variable_t ngx_http_core_variables[] = { offsetof(ngx_http_request_t, uri), NGX_HTTP_VAR_NOCACHEABLE, 0 }, + { ngx_string("uri_remainder"), NULL, ngx_http_variable_request, + offsetof(ngx_http_request_t, uri_remainder), + NGX_HTTP_VAR_NOCACHEABLE, 0 }, + { ngx_string("document_uri"), NULL, ngx_http_variable_request, offsetof(ngx_http_request_t, uri), NGX_HTTP_VAR_NOCACHEABLE, 0 }, @@ -250,6 +273,21 @@ static ngx_http_variable_t ngx_http_core_variables[] = { { ngx_string("pid"), NULL, ngx_http_variable_pid, 0, 0, 0 }, + { ngx_string("timestamp"), NULL, ngx_http_variable_timestamp, + 0, 0, 0 }, + + { ngx_string("mstimestamp"), NULL, ngx_http_variable_mstimestamp, + 0, 0, 0 }, + + { ngx_string("loadavg_1m"), NULL, ngx_http_variable_loadavg_1m, + 0, 0, 0 }, + + { ngx_string("loadavg_5m"), NULL, ngx_http_variable_loadavg_5m, + 0, 0, 0 }, + + { ngx_string("loadavg_15m"), NULL, ngx_http_variable_loadavg_15m, + 0, 0, 0 }, + { ngx_null_string, NULL, NULL, 0, 0, 0 } }; @@ -511,6 +549,42 @@ ngx_http_get_variable(ngx_http_request_t *r, ngx_str_t *name, ngx_uint_t key, return NULL; } + if (ngx_strncmp(name->data, "urlencode_", 10) == 0) { + + if (ngx_http_variable_urlencode(r, vv, (uintptr_t) name) == NGX_OK) { + return vv; + } + + return NULL; + } + + if (ngx_strncmp(name->data, "urldecode_", 10) == 0) { + + if (ngx_http_variable_urldecode(r, vv, (uintptr_t) name) == NGX_OK) { + return vv; + } + + return NULL; + } + + if (ngx_strncmp(name->data, "crc32_", 6) == 0) { + + if (ngx_http_variable_crc32(r, vv, (uintptr_t) name) == NGX_OK) { + return vv; + } + + return NULL; + } + + if (ngx_strncmp(name->data, "md5_", 4) == 0) { + + if (ngx_http_variable_md5(r, vv, (uintptr_t) name) == NGX_OK) { + return vv; + } + + return NULL; + } + if (ngx_strncmp(name->data, "arg_", 4) == 0) { if (ngx_http_variable_argument(r, vv, (uintptr_t) name) == NGX_OK) { @@ -779,6 +853,200 @@ ngx_http_variable_cookie(ngx_http_request_t *r, ngx_http_variable_value_t *v, static ngx_int_t +ngx_http_variable_urlencode(ngx_http_request_t *r, ngx_http_variable_value_t *v, + uintptr_t data) +{ + ngx_str_t *name = (ngx_str_t *) data; + + ngx_str_t sub_name; + + ngx_uint_t key; + + ngx_http_variable_value_t *vv; + + sub_name.len = name->len - (sizeof("urlencode_") - 1); + sub_name.data = name->data + sizeof("urlencode_") - 1; + + key = ngx_hash_strlow(sub_name.data, sub_name.data, sub_name.len); + + vv = ngx_http_get_variable(r, &sub_name, key, 0); + + if (vv == NULL || !vv->valid) { + return NGX_ERROR; + } + + if (vv->not_found) { + v->not_found = 1; + return NGX_OK; + } + + v->len = vv->len + + 2 * ngx_escape_uri(NULL, vv->data, vv->len, NGX_ESCAPE_ARGS); + + v->data = ngx_palloc(r->pool, v->len); + if (v->data == NULL) { + v->not_found = 1; + return NGX_OK; + } + + (void) ngx_escape_uri(v->data, vv->data, vv->len, NGX_ESCAPE_ARGS); + + v->valid = 1; + v->not_found = 0; + v->no_cacheable = vv->no_cacheable; + + return NGX_OK; +} + + +static ngx_int_t +ngx_http_variable_urldecode(ngx_http_request_t *r, ngx_http_variable_value_t *v, + uintptr_t data) +{ + ngx_str_t *name = (ngx_str_t *) data; + + u_char *dst, *src; + ngx_str_t sub_name; + ngx_uint_t key; + + ngx_http_variable_value_t *vv; + + sub_name.len = name->len - (sizeof("urldecode_") - 1); + sub_name.data = name->data + sizeof("urldecode_") - 1; + + key = ngx_hash_strlow(sub_name.data, sub_name.data, sub_name.len); + + vv = ngx_http_get_variable(r, &sub_name, key, 0); + + if (vv == NULL || !vv->valid) { + return NGX_ERROR; + } + + if (vv->not_found) { + v->not_found = 1; + return NGX_OK; + } + + v->len = vv->len; + + v->data = ngx_palloc(r->pool, v->len); + if (v->data == NULL) { + v->not_found = 1; + return NGX_OK; + } + + dst = v->data; + src = vv->data; + + ngx_unescape_uri(&dst, &src, vv->len, NGX_ESCAPE_ARGS); + + v->len = dst - v->data; + + v->valid = 1; + v->not_found = 0; + v->no_cacheable = vv->no_cacheable; + + return NGX_OK; +} + + +static ngx_int_t +ngx_http_variable_crc32(ngx_http_request_t *r, ngx_http_variable_value_t *v, + uintptr_t data) +{ + ngx_str_t *name = (ngx_str_t *) data; + + ngx_str_t sub_name; + ngx_uint_t key; + + ngx_http_variable_value_t *vv; + + sub_name.len = name->len - (sizeof("crc32_") - 1); + sub_name.data = name->data + sizeof("crc32_") - 1; + + key = ngx_hash_strlow(sub_name.data, sub_name.data, sub_name.len); + + vv = ngx_http_get_variable(r, &sub_name, key, 0); + + if (vv == NULL || !vv->valid) { + return NGX_ERROR; + } + + if (vv->not_found) { + v->not_found = 1; + return NGX_OK; + } + + v->len = sizeof("3C32515A") - 1; + + v->data = ngx_palloc(r->pool, v->len); + if (v->data == NULL) { + v->not_found = 1; + return NGX_OK; + } + + ngx_sprintf(v->data, "%08XD", ngx_crc32_long(vv->data, vv->len)); + + v->valid = 1; + v->not_found = 0; + v->no_cacheable = vv->no_cacheable; + + return NGX_OK; +} + + +static ngx_int_t +ngx_http_variable_md5(ngx_http_request_t *r, ngx_http_variable_value_t *v, + uintptr_t data) +{ + ngx_str_t *name = (ngx_str_t *) data; + + ngx_str_t sub_name; + ngx_uint_t key; + ngx_md5_t md5; + uint32_t hash[4]; + + ngx_http_variable_value_t *vv; + + sub_name.len = name->len - (sizeof("md5_") - 1); + sub_name.data = name->data + sizeof("md5_") - 1; + + key = ngx_hash_strlow(sub_name.data, sub_name.data, sub_name.len); + + vv = ngx_http_get_variable(r, &sub_name, key, 0); + + if (vv == NULL || !vv->valid) { + return NGX_ERROR; + } + + if (vv->not_found) { + v->not_found = 1; + return NGX_OK; + } + + v->len = sizeof("7002945D4B8D9E472866092689DB3EAD") - 1; + + v->data = ngx_palloc(r->pool, v->len); + if (v->data == NULL) { + v->not_found = 1; + return NGX_OK; + } + + ngx_md5_init(&md5); + ngx_md5_update(&md5, vv->data, vv->len); + ngx_md5_final((u_char*)hash, &md5); + + ngx_sprintf(v->data, "%08XD%08XD%08XD%08XD", hash[0], hash[1], hash[2], hash[3]); + + v->valid = 1; + v->not_found = 0; + v->no_cacheable = vv->no_cacheable; + + return NGX_OK; +} + + +static ngx_int_t ngx_http_variable_argument(ngx_http_request_t *r, ngx_http_variable_value_t *v, uintptr_t data) { @@ -1590,7 +1858,7 @@ ngx_http_variable_pid(ngx_http_request_t *r, { u_char *p; - p = ngx_pnalloc(r->pool, NGX_INT64_LEN); + p = ngx_pnalloc(r->pool, NGX_INT_T_LEN); if (p == NULL) { return NGX_ERROR; } @@ -1604,6 +1872,128 @@ ngx_http_variable_pid(ngx_http_request_t *r, return NGX_OK; } +static ngx_int_t +ngx_http_variable_timestamp(ngx_http_request_t *r, + ngx_http_variable_value_t *v, uintptr_t data) +{ + u_char *p; + + p = ngx_pnalloc(r->pool, NGX_INT64_LEN); + if (p == NULL) { + return NGX_ERROR; + } + + v->len = ngx_sprintf(p, "%T", ngx_time()) - p; + v->valid = 1; + v->no_cacheable = 0; + v->not_found = 0; + v->data = p; + + return NGX_OK; +} + + +static ngx_int_t +ngx_http_variable_mstimestamp(ngx_http_request_t *r, + ngx_http_variable_value_t *v, uintptr_t data) +{ + u_char *p; + + p = ngx_pnalloc(r->pool, NGX_INT64_LEN + sizeof("123") - 1); + if (p == NULL) { + return NGX_ERROR; + } + + v->len = ngx_sprintf(p, "%T%03M", ngx_time(), (ngx_timeofday())->msec) - p; + v->valid = 1; + v->no_cacheable = 0; + v->not_found = 0; + v->data = p; + + return NGX_OK; +} + + +static ngx_int_t +ngx_http_variable_loadavg_1m(ngx_http_request_t *r, + ngx_http_variable_value_t *v, uintptr_t data) +{ + u_char *p; + ngx_int_t la; + + p = ngx_pnalloc(r->pool, NGX_INT64_LEN); + if (p == NULL) { + return NGX_ERROR; + } + + la = ngx_get_loadavg(0); + if (la == NGX_ERROR) { + return NGX_ERROR; + } + + v->len = ngx_sprintf(p, "%i", la) - p; + v->valid = 1; + v->no_cacheable = 1; + v->not_found = 0; + v->data = p; + + return NGX_OK; +} + + +static ngx_int_t +ngx_http_variable_loadavg_5m(ngx_http_request_t *r, + ngx_http_variable_value_t *v, uintptr_t data) +{ + u_char *p; + ngx_int_t la; + + p = ngx_pnalloc(r->pool, NGX_INT_T_LEN); + if (p == NULL) { + return NGX_ERROR; + } + + la = ngx_get_loadavg(1); + if (la == NGX_ERROR) { + return NGX_ERROR; + } + + v->len = ngx_sprintf(p, "%i", la) - p; + v->valid = 1; + v->no_cacheable = 1; + v->not_found = 0; + v->data = p; + + return NGX_OK; +} + + +static ngx_int_t +ngx_http_variable_loadavg_15m(ngx_http_request_t *r, + ngx_http_variable_value_t *v, uintptr_t data) +{ + u_char *p; + ngx_int_t la; + + p = ngx_pnalloc(r->pool, NGX_INT_T_LEN); + if (p == NULL) { + return NGX_ERROR; + } + + la = ngx_get_loadavg(2); + if (la == NGX_ERROR) { + return NGX_ERROR; + } + + v->len = ngx_sprintf(p, "%i", la) - p; + v->valid = 1; + v->no_cacheable = 1; + v->not_found = 0; + v->data = p; + + return NGX_OK; +} + ngx_int_t ngx_http_variables_add_core_vars(ngx_conf_t *cf) @@ -1717,6 +2107,34 @@ ngx_http_variables_init_vars(ngx_conf_t *cf) continue; } + if (ngx_strncmp(v[i].name.data, "urlencode_", 10) == 0) { + v[i].get_handler = ngx_http_variable_urlencode; + v[i].data = (uintptr_t) &v[i].name; + + continue; + } + + if (ngx_strncmp(v[i].name.data, "urldecode_", 10) == 0) { + v[i].get_handler = ngx_http_variable_urldecode; + v[i].data = (uintptr_t) &v[i].name; + + continue; + } + + if (ngx_strncmp(v[i].name.data, "crc32_", 6) == 0) { + v[i].get_handler = ngx_http_variable_crc32; + v[i].data = (uintptr_t) &v[i].name; + + continue; + } + + if (ngx_strncmp(v[i].name.data, "md5_", 4) == 0) { + v[i].get_handler = ngx_http_variable_md5; + v[i].data = (uintptr_t) &v[i].name; + + continue; + } + if (ngx_strncmp(v[i].name.data, "arg_", 4) == 0) { v[i].get_handler = ngx_http_variable_argument; v[i].data = (uintptr_t) &v[i].name; diff --git a/src/os/unix/ngx_user.c b/src/os/unix/ngx_user.c index 4bad1c3..0e4f949 100644 --- a/src/os/unix/ngx_user.c +++ b/src/os/unix/ngx_user.c @@ -7,6 +7,9 @@ #include #include +#if (NGX_HAVE_SYSINFO) +#include +#endif /* * Solaris has thread-safe crypt() @@ -106,3 +109,32 @@ ngx_crypt(ngx_pool_t *pool, u_char *key, u_char *salt, u_char **encrypted) #endif #endif /* NGX_CRYPT */ + + +ngx_int_t ngx_get_loadavg(ngx_uint_t n) +{ +#if (NGX_HAVE_SYSINFO) + struct sysinfo s; + + if (sysinfo(&s)) { + goto error; + } + + return s.loads[n]/65536; + +#endif /* NGX_HAVE_SYSINFO */ + +#if (NGX_HAVE_GETLOADAVG) + double loadavg[1]; + + if (getloadavg(loadavg, 1) == -1) { + goto error; + } + + return (int)loadavg[n]; + +#endif /* NGX_HAVE_SYSINFO */ + +error: + return NGX_ERROR; +} diff --git a/src/os/unix/ngx_user.h b/src/os/unix/ngx_user.h index a24a66b..a4f151a 100644 --- a/src/os/unix/ngx_user.h +++ b/src/os/unix/ngx_user.h @@ -19,6 +19,7 @@ typedef gid_t ngx_gid_t; ngx_int_t ngx_crypt(ngx_pool_t *pool, u_char *key, u_char *salt, u_char **encrypted); +ngx_int_t ngx_get_loadavg(ngx_uint_t n); #endif /* _NGX_USER_H_INCLUDED_ */